nicoboss commited on
Commit
a2682ec
·
verified ·
1 Parent(s): 8328621

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +5 -0
  2. README.md +147 -0
  3. adapter_config.json +39 -0
  4. adapter_model.safetensors +3 -0
  5. checkpoint-145/README.md +202 -0
  6. checkpoint-145/adapter_config.json +39 -0
  7. checkpoint-145/adapter_model.safetensors +3 -0
  8. checkpoint-145/optimizer.bin +3 -0
  9. checkpoint-145/pytorch_model_fsdp.bin +3 -0
  10. checkpoint-145/rng_state_0.pth +3 -0
  11. checkpoint-145/rng_state_1.pth +3 -0
  12. checkpoint-145/scheduler.pt +3 -0
  13. checkpoint-145/special_tokens_map.json +23 -0
  14. checkpoint-145/tokenizer.json +3 -0
  15. checkpoint-145/tokenizer_config.json +2064 -0
  16. checkpoint-145/trainer_state.json +1201 -0
  17. checkpoint-145/training_args.bin +3 -0
  18. checkpoint-174/README.md +202 -0
  19. checkpoint-174/adapter_config.json +39 -0
  20. checkpoint-174/adapter_model.safetensors +3 -0
  21. checkpoint-174/optimizer.bin +3 -0
  22. checkpoint-174/pytorch_model_fsdp.bin +3 -0
  23. checkpoint-174/rng_state_0.pth +3 -0
  24. checkpoint-174/rng_state_1.pth +3 -0
  25. checkpoint-174/scheduler.pt +3 -0
  26. checkpoint-174/special_tokens_map.json +23 -0
  27. checkpoint-174/tokenizer.json +3 -0
  28. checkpoint-174/tokenizer_config.json +2064 -0
  29. checkpoint-174/trainer_state.json +1428 -0
  30. checkpoint-174/training_args.bin +3 -0
  31. checkpoint-203/README.md +202 -0
  32. checkpoint-203/adapter_config.json +39 -0
  33. checkpoint-203/adapter_model.safetensors +3 -0
  34. checkpoint-203/optimizer.bin +3 -0
  35. checkpoint-203/pytorch_model_fsdp.bin +3 -0
  36. checkpoint-203/rng_state_0.pth +3 -0
  37. checkpoint-203/rng_state_1.pth +3 -0
  38. checkpoint-203/scheduler.pt +3 -0
  39. checkpoint-203/special_tokens_map.json +23 -0
  40. checkpoint-203/tokenizer.json +3 -0
  41. checkpoint-203/tokenizer_config.json +2064 -0
  42. checkpoint-203/trainer_state.json +1663 -0
  43. checkpoint-203/training_args.bin +3 -0
  44. checkpoint-232/README.md +202 -0
  45. checkpoint-232/adapter_config.json +39 -0
  46. checkpoint-232/adapter_model.safetensors +3 -0
  47. checkpoint-232/optimizer.bin +3 -0
  48. checkpoint-232/pytorch_model_fsdp.bin +3 -0
  49. checkpoint-232/rng_state_0.pth +3 -0
  50. checkpoint-232/rng_state_1.pth +3 -0
.gitattributes CHANGED
@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-145/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-174/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-203/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-232/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: Meta-Llama-3.1-8B-Instruct-abliterated-ICONN-1-BasicChat
8
+ results: []
9
+ license: llama3.1
10
+ datasets:
11
+ - Enderchef/ICONN-1-BasicChat-Data-SuperLite
12
+ ---
13
+
14
+ [Meta-Llama-3.1-8B-Instruct-abliterated](https://huggingface.co/mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated) finetuned using the [ICONN-1-BasicChat-Data-SuperLite](https://huggingface.co/datasets/Enderchef/ICONN-1-BasicChat-Data-SuperLite) dataset as requested by [@Enderchef](https://huggingface.co/Enderchef) under https://huggingface.co/mradermacher/model_requests/discussions/918
15
+
16
+ axolotl version: `0.9.0`
17
+ ```yaml
18
+ base_model: /dpool/Meta-Llama-3.1-8B-Instruct-abliterated
19
+ model_type: LlamaForCausalLM
20
+ tokenizer_type: AutoTokenizer
21
+
22
+ load_in_8bit: false
23
+ load_in_4bit: false
24
+
25
+ datasets:
26
+ - path: /apool/axolotl/0001.parquet
27
+ chat_template: llama3
28
+ type:
29
+ system_prompt: ""
30
+ field_system: system
31
+ field_instruction: input
32
+ field_output: output
33
+ dataset_prepared_path:
34
+ val_set_size: 0.05
35
+ output_dir: ./outputs/lora-out
36
+
37
+ adapter: lora
38
+ lora_model_dir:
39
+
40
+ sequence_len: 4096
41
+ sample_packing: false
42
+ pad_to_sequence_len: true
43
+
44
+ lora_r: 16
45
+ lora_alpha: 32
46
+ lora_dropout: 0.05
47
+ lora_target_linear: true
48
+
49
+ gradient_accumulation_steps: 4
50
+ micro_batch_size: 2
51
+ num_epochs: 8
52
+ optimizer: adamw_torch_fused
53
+ lr_scheduler: cosine
54
+ learning_rate: 0.00001
55
+
56
+ bf16: auto
57
+ tf32: false
58
+
59
+ gradient_checkpointing: true
60
+ gradient_checkpointing_kwargs:
61
+ use_reentrant: true
62
+ resume_from_checkpoint:
63
+ logging_steps: 1
64
+ flash_attention: true
65
+
66
+ warmup_steps: 10
67
+ evals_per_epoch: 4
68
+ saves_per_epoch: 1
69
+ weight_decay: 0.0
70
+ fsdp:
71
+ - full_shard
72
+ - auto_wrap
73
+ fsdp_config:
74
+ fsdp_limit_all_gathers: true
75
+ fsdp_sync_module_states: true
76
+ fsdp_offload_params: true
77
+ fsdp_use_orig_params: false
78
+ fsdp_cpu_ram_efficient_loading: true
79
+ fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
80
+ fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer
81
+ fsdp_state_dict_type: FULL_STATE_DICT
82
+ fsdp_sharding_strategy: FULL_SHARD
83
+ special_tokens:
84
+ pad_token: <|end_of_text|>
85
+
86
+ ```
87
+
88
+ ### Training hyperparameters
89
+
90
+ The following hyperparameters were used during training:
91
+ - learning_rate: 1e-05
92
+ - train_batch_size: 2
93
+ - eval_batch_size: 2
94
+ - seed: 42
95
+ - distributed_type: multi-GPU
96
+ - num_devices: 2
97
+ - gradient_accumulation_steps: 4
98
+ - total_train_batch_size: 16
99
+ - total_eval_batch_size: 4
100
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
101
+ - lr_scheduler_type: cosine
102
+ - lr_scheduler_warmup_steps: 10
103
+ - num_epochs: 8.0
104
+
105
+ ### Training results
106
+
107
+ | Training Loss | Epoch | Step | Validation Loss |
108
+ |:-------------:|:------:|:----:|:---------------:|
109
+ | 3.5587 | 0.0336 | 1 | 3.4337 |
110
+ | 3.6702 | 0.2689 | 8 | 3.4260 |
111
+ | 3.5802 | 0.5378 | 16 | 3.3161 |
112
+ | 3.2421 | 0.8067 | 24 | 3.0272 |
113
+ | 2.322 | 1.0672 | 32 | 2.4812 |
114
+ | 1.9774 | 1.3361 | 40 | 1.8708 |
115
+ | 1.5103 | 1.6050 | 48 | 1.3871 |
116
+ | 1.1904 | 1.8739 | 56 | 1.0542 |
117
+ | 1.0394 | 2.1345 | 64 | 0.8591 |
118
+ | 0.5501 | 2.4034 | 72 | 0.6723 |
119
+ | 0.2454 | 2.6723 | 80 | 0.5369 |
120
+ | 0.4499 | 2.9412 | 88 | 0.4286 |
121
+ | 0.2194 | 3.2017 | 96 | 0.3691 |
122
+ | 0.1172 | 3.4706 | 104 | 0.2802 |
123
+ | 0.0739 | 3.7395 | 112 | 0.1948 |
124
+ | 0.1524 | 4.0 | 120 | 0.1457 |
125
+ | 0.0444 | 4.2689 | 128 | 0.1125 |
126
+ | 0.1385 | 4.5378 | 136 | 0.0759 |
127
+ | 0.0591 | 4.8067 | 144 | 0.0560 |
128
+ | 0.0252 | 5.0672 | 152 | 0.0460 |
129
+ | 0.0066 | 5.3361 | 160 | 0.0370 |
130
+ | 0.023 | 5.6050 | 168 | 0.0252 |
131
+ | 0.0033 | 5.8739 | 176 | 0.0202 |
132
+ | 0.0029 | 6.1345 | 184 | 0.0168 |
133
+ | 0.0024 | 6.4034 | 192 | 0.0154 |
134
+ | 0.0103 | 6.6723 | 200 | 0.0146 |
135
+ | 0.0108 | 6.9412 | 208 | 0.0139 |
136
+ | 0.0049 | 7.2017 | 216 | 0.0138 |
137
+ | 0.0025 | 7.4706 | 224 | 0.0139 |
138
+ | 0.0036 | 7.7395 | 232 | 0.0136 |
139
+
140
+
141
+ ### Framework versions
142
+
143
+ - PEFT 0.15.2
144
+ - Transformers 4.51.3
145
+ - Pytorch 2.7.0+cu128
146
+ - Datasets 3.5.0
147
+ - Tokenizers 0.21.1
adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/dpool/Meta-Llama-3.1-8B-Instruct-abliterated",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": null,
10
+ "inference_mode": false,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 16,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "q_proj",
28
+ "v_proj",
29
+ "down_proj",
30
+ "gate_proj",
31
+ "up_proj",
32
+ "o_proj",
33
+ "k_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3088de2095a094689856cbb540058569e7b1847fcc298cd95e277fd301f50912
3
+ size 167832240
checkpoint-145/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /dpool/Meta-Llama-3.1-8B-Instruct-abliterated
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
checkpoint-145/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/dpool/Meta-Llama-3.1-8B-Instruct-abliterated",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": null,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 16,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "k_proj",
29
+ "q_proj",
30
+ "down_proj",
31
+ "o_proj",
32
+ "v_proj",
33
+ "up_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-145/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d997716beab7f4cd774dd60234be78b42e93e10224ab35c75e419e53d90aafc
3
+ size 167832240
checkpoint-145/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:222506a21270ad96439305cbf428c9a4533a199f09d43818fec2eab19353fc97
3
+ size 335945763
checkpoint-145/pytorch_model_fsdp.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d5fb0a4ed606bf80b0d52cd2103e17d7d066f35452c1c0adab0789133a777d1
3
+ size 167939969
checkpoint-145/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f3995d4f55db7fca766ea6e010b25d3a8855fec8cac136c140cc37364a72f4f
3
+ size 14917
checkpoint-145/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b117ae4a199d55cb4264907d202fb94cb68a741f67337ae6b03edf1b71a3af
3
+ size 14917
checkpoint-145/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac5e302559d4df236dfd3a99a9c84e96c200fc02bfa44b894c6fb456acefcebb
3
+ size 1465
checkpoint-145/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-145/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-145/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizer"
2064
+ }
checkpoint-145/trainer_state.json ADDED
@@ -0,0 +1,1201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.840336134453781,
6
+ "eval_steps": 8,
7
+ "global_step": 145,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.03361344537815126,
14
+ "grad_norm": 2.6346614360809326,
15
+ "learning_rate": 0.0,
16
+ "loss": 3.5587,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.03361344537815126,
21
+ "eval_loss": 3.4337246417999268,
22
+ "eval_runtime": 12.0401,
23
+ "eval_samples_per_second": 2.076,
24
+ "eval_steps_per_second": 0.581,
25
+ "step": 1
26
+ },
27
+ {
28
+ "epoch": 0.06722689075630252,
29
+ "grad_norm": 3.2896828651428223,
30
+ "learning_rate": 1.0000000000000002e-06,
31
+ "loss": 3.6974,
32
+ "step": 2
33
+ },
34
+ {
35
+ "epoch": 0.10084033613445378,
36
+ "grad_norm": 2.942761182785034,
37
+ "learning_rate": 2.0000000000000003e-06,
38
+ "loss": 3.7682,
39
+ "step": 3
40
+ },
41
+ {
42
+ "epoch": 0.13445378151260504,
43
+ "grad_norm": 3.322763442993164,
44
+ "learning_rate": 3e-06,
45
+ "loss": 4.1233,
46
+ "step": 4
47
+ },
48
+ {
49
+ "epoch": 0.16806722689075632,
50
+ "grad_norm": 2.542609214782715,
51
+ "learning_rate": 4.000000000000001e-06,
52
+ "loss": 3.7296,
53
+ "step": 5
54
+ },
55
+ {
56
+ "epoch": 0.20168067226890757,
57
+ "grad_norm": 2.8525142669677734,
58
+ "learning_rate": 5e-06,
59
+ "loss": 3.8537,
60
+ "step": 6
61
+ },
62
+ {
63
+ "epoch": 0.23529411764705882,
64
+ "grad_norm": 2.3698537349700928,
65
+ "learning_rate": 6e-06,
66
+ "loss": 3.648,
67
+ "step": 7
68
+ },
69
+ {
70
+ "epoch": 0.2689075630252101,
71
+ "grad_norm": 2.540416955947876,
72
+ "learning_rate": 7e-06,
73
+ "loss": 3.6702,
74
+ "step": 8
75
+ },
76
+ {
77
+ "epoch": 0.2689075630252101,
78
+ "eval_loss": 3.4260427951812744,
79
+ "eval_runtime": 12.0264,
80
+ "eval_samples_per_second": 2.079,
81
+ "eval_steps_per_second": 0.582,
82
+ "step": 8
83
+ },
84
+ {
85
+ "epoch": 0.3025210084033613,
86
+ "grad_norm": 2.424398422241211,
87
+ "learning_rate": 8.000000000000001e-06,
88
+ "loss": 3.3544,
89
+ "step": 9
90
+ },
91
+ {
92
+ "epoch": 0.33613445378151263,
93
+ "grad_norm": 3.290915012359619,
94
+ "learning_rate": 9e-06,
95
+ "loss": 3.9672,
96
+ "step": 10
97
+ },
98
+ {
99
+ "epoch": 0.3697478991596639,
100
+ "grad_norm": 2.8242039680480957,
101
+ "learning_rate": 1e-05,
102
+ "loss": 3.591,
103
+ "step": 11
104
+ },
105
+ {
106
+ "epoch": 0.40336134453781514,
107
+ "grad_norm": 2.9474833011627197,
108
+ "learning_rate": 9.999499358833745e-06,
109
+ "loss": 3.6958,
110
+ "step": 12
111
+ },
112
+ {
113
+ "epoch": 0.4369747899159664,
114
+ "grad_norm": 3.4582228660583496,
115
+ "learning_rate": 9.99799753559161e-06,
116
+ "loss": 3.99,
117
+ "step": 13
118
+ },
119
+ {
120
+ "epoch": 0.47058823529411764,
121
+ "grad_norm": 3.1884031295776367,
122
+ "learning_rate": 9.99549483102341e-06,
123
+ "loss": 3.8204,
124
+ "step": 14
125
+ },
126
+ {
127
+ "epoch": 0.5042016806722689,
128
+ "grad_norm": 2.423398017883301,
129
+ "learning_rate": 9.991991746311916e-06,
130
+ "loss": 3.0469,
131
+ "step": 15
132
+ },
133
+ {
134
+ "epoch": 0.5378151260504201,
135
+ "grad_norm": 3.3329102993011475,
136
+ "learning_rate": 9.9874889829725e-06,
137
+ "loss": 3.5802,
138
+ "step": 16
139
+ },
140
+ {
141
+ "epoch": 0.5378151260504201,
142
+ "eval_loss": 3.316091299057007,
143
+ "eval_runtime": 12.0143,
144
+ "eval_samples_per_second": 2.081,
145
+ "eval_steps_per_second": 0.583,
146
+ "step": 16
147
+ },
148
+ {
149
+ "epoch": 0.5714285714285714,
150
+ "grad_norm": 2.8659586906433105,
151
+ "learning_rate": 9.981987442712634e-06,
152
+ "loss": 3.0165,
153
+ "step": 17
154
+ },
155
+ {
156
+ "epoch": 0.6050420168067226,
157
+ "grad_norm": 3.4627182483673096,
158
+ "learning_rate": 9.97548822725133e-06,
159
+ "loss": 3.9333,
160
+ "step": 18
161
+ },
162
+ {
163
+ "epoch": 0.6386554621848739,
164
+ "grad_norm": 3.3491547107696533,
165
+ "learning_rate": 9.967992638098517e-06,
166
+ "loss": 3.5018,
167
+ "step": 19
168
+ },
169
+ {
170
+ "epoch": 0.6722689075630253,
171
+ "grad_norm": 2.7486977577209473,
172
+ "learning_rate": 9.959502176294384e-06,
173
+ "loss": 2.9875,
174
+ "step": 20
175
+ },
176
+ {
177
+ "epoch": 0.7058823529411765,
178
+ "grad_norm": 2.9063732624053955,
179
+ "learning_rate": 9.950018542108818e-06,
180
+ "loss": 3.0974,
181
+ "step": 21
182
+ },
183
+ {
184
+ "epoch": 0.7394957983193278,
185
+ "grad_norm": 3.2880260944366455,
186
+ "learning_rate": 9.939543634700891e-06,
187
+ "loss": 3.141,
188
+ "step": 22
189
+ },
190
+ {
191
+ "epoch": 0.773109243697479,
192
+ "grad_norm": 3.086613416671753,
193
+ "learning_rate": 9.928079551738542e-06,
194
+ "loss": 3.0282,
195
+ "step": 23
196
+ },
197
+ {
198
+ "epoch": 0.8067226890756303,
199
+ "grad_norm": 3.7129077911376953,
200
+ "learning_rate": 9.915628588978522e-06,
201
+ "loss": 3.2421,
202
+ "step": 24
203
+ },
204
+ {
205
+ "epoch": 0.8067226890756303,
206
+ "eval_loss": 3.0272111892700195,
207
+ "eval_runtime": 12.0429,
208
+ "eval_samples_per_second": 2.076,
209
+ "eval_steps_per_second": 0.581,
210
+ "step": 24
211
+ },
212
+ {
213
+ "epoch": 0.8403361344537815,
214
+ "grad_norm": 4.430984973907471,
215
+ "learning_rate": 9.902193239806634e-06,
216
+ "loss": 3.2481,
217
+ "step": 25
218
+ },
219
+ {
220
+ "epoch": 0.8739495798319328,
221
+ "grad_norm": 3.6558125019073486,
222
+ "learning_rate": 9.887776194738433e-06,
223
+ "loss": 2.8553,
224
+ "step": 26
225
+ },
226
+ {
227
+ "epoch": 0.907563025210084,
228
+ "grad_norm": 4.079296112060547,
229
+ "learning_rate": 9.872380340880416e-06,
230
+ "loss": 3.0176,
231
+ "step": 27
232
+ },
233
+ {
234
+ "epoch": 0.9411764705882353,
235
+ "grad_norm": 4.859598159790039,
236
+ "learning_rate": 9.856008761351882e-06,
237
+ "loss": 2.7999,
238
+ "step": 28
239
+ },
240
+ {
241
+ "epoch": 0.9747899159663865,
242
+ "grad_norm": 4.5133957862854,
243
+ "learning_rate": 9.838664734667496e-06,
244
+ "loss": 2.933,
245
+ "step": 29
246
+ },
247
+ {
248
+ "epoch": 1.0,
249
+ "grad_norm": 4.612884044647217,
250
+ "learning_rate": 9.820351734080754e-06,
251
+ "loss": 2.5651,
252
+ "step": 30
253
+ },
254
+ {
255
+ "epoch": 1.0336134453781514,
256
+ "grad_norm": 4.931149959564209,
257
+ "learning_rate": 9.801073426888447e-06,
258
+ "loss": 2.5854,
259
+ "step": 31
260
+ },
261
+ {
262
+ "epoch": 1.0672268907563025,
263
+ "grad_norm": 5.286943435668945,
264
+ "learning_rate": 9.780833673696255e-06,
265
+ "loss": 2.322,
266
+ "step": 32
267
+ },
268
+ {
269
+ "epoch": 1.0672268907563025,
270
+ "eval_loss": 2.48122239112854,
271
+ "eval_runtime": 12.0206,
272
+ "eval_samples_per_second": 2.08,
273
+ "eval_steps_per_second": 0.582,
274
+ "step": 32
275
+ },
276
+ {
277
+ "epoch": 1.1008403361344539,
278
+ "grad_norm": 4.670954704284668,
279
+ "learning_rate": 9.759636527645633e-06,
280
+ "loss": 2.4513,
281
+ "step": 33
282
+ },
283
+ {
284
+ "epoch": 1.134453781512605,
285
+ "grad_norm": 4.8246169090271,
286
+ "learning_rate": 9.737486233602149e-06,
287
+ "loss": 2.1937,
288
+ "step": 34
289
+ },
290
+ {
291
+ "epoch": 1.1680672268907564,
292
+ "grad_norm": 4.8713836669921875,
293
+ "learning_rate": 9.714387227305422e-06,
294
+ "loss": 2.3228,
295
+ "step": 35
296
+ },
297
+ {
298
+ "epoch": 1.2016806722689075,
299
+ "grad_norm": 5.048571586608887,
300
+ "learning_rate": 9.69034413448083e-06,
301
+ "loss": 1.9506,
302
+ "step": 36
303
+ },
304
+ {
305
+ "epoch": 1.2352941176470589,
306
+ "grad_norm": 5.047688007354736,
307
+ "learning_rate": 9.665361769913187e-06,
308
+ "loss": 2.2959,
309
+ "step": 37
310
+ },
311
+ {
312
+ "epoch": 1.26890756302521,
313
+ "grad_norm": 5.056053161621094,
314
+ "learning_rate": 9.639445136482549e-06,
315
+ "loss": 2.0905,
316
+ "step": 38
317
+ },
318
+ {
319
+ "epoch": 1.3025210084033614,
320
+ "grad_norm": 3.506237506866455,
321
+ "learning_rate": 9.612599424162344e-06,
322
+ "loss": 1.9687,
323
+ "step": 39
324
+ },
325
+ {
326
+ "epoch": 1.3361344537815127,
327
+ "grad_norm": 4.794375896453857,
328
+ "learning_rate": 9.584830008980068e-06,
329
+ "loss": 1.9774,
330
+ "step": 40
331
+ },
332
+ {
333
+ "epoch": 1.3361344537815127,
334
+ "eval_loss": 1.870819091796875,
335
+ "eval_runtime": 12.0354,
336
+ "eval_samples_per_second": 2.077,
337
+ "eval_steps_per_second": 0.582,
338
+ "step": 40
339
+ },
340
+ {
341
+ "epoch": 1.3697478991596639,
342
+ "grad_norm": 5.138720512390137,
343
+ "learning_rate": 9.55614245194068e-06,
344
+ "loss": 1.6505,
345
+ "step": 41
346
+ },
347
+ {
348
+ "epoch": 1.403361344537815,
349
+ "grad_norm": 3.800957679748535,
350
+ "learning_rate": 9.526542497912984e-06,
351
+ "loss": 1.8317,
352
+ "step": 42
353
+ },
354
+ {
355
+ "epoch": 1.4369747899159664,
356
+ "grad_norm": 4.458896636962891,
357
+ "learning_rate": 9.496036074479184e-06,
358
+ "loss": 1.6714,
359
+ "step": 43
360
+ },
361
+ {
362
+ "epoch": 1.4705882352941178,
363
+ "grad_norm": 3.317945718765259,
364
+ "learning_rate": 9.464629290747844e-06,
365
+ "loss": 1.825,
366
+ "step": 44
367
+ },
368
+ {
369
+ "epoch": 1.504201680672269,
370
+ "grad_norm": 3.235334634780884,
371
+ "learning_rate": 9.432328436130493e-06,
372
+ "loss": 1.5301,
373
+ "step": 45
374
+ },
375
+ {
376
+ "epoch": 1.53781512605042,
377
+ "grad_norm": 3.7489278316497803,
378
+ "learning_rate": 9.399139979082148e-06,
379
+ "loss": 1.5717,
380
+ "step": 46
381
+ },
382
+ {
383
+ "epoch": 1.5714285714285714,
384
+ "grad_norm": 2.814138889312744,
385
+ "learning_rate": 9.365070565805941e-06,
386
+ "loss": 1.6659,
387
+ "step": 47
388
+ },
389
+ {
390
+ "epoch": 1.6050420168067228,
391
+ "grad_norm": 3.219665765762329,
392
+ "learning_rate": 9.330127018922195e-06,
393
+ "loss": 1.5103,
394
+ "step": 48
395
+ },
396
+ {
397
+ "epoch": 1.6050420168067228,
398
+ "eval_loss": 1.3871335983276367,
399
+ "eval_runtime": 12.0361,
400
+ "eval_samples_per_second": 2.077,
401
+ "eval_steps_per_second": 0.582,
402
+ "step": 48
403
+ },
404
+ {
405
+ "epoch": 1.638655462184874,
406
+ "grad_norm": 3.621195077896118,
407
+ "learning_rate": 9.294316336102132e-06,
408
+ "loss": 1.4593,
409
+ "step": 49
410
+ },
411
+ {
412
+ "epoch": 1.6722689075630253,
413
+ "grad_norm": 3.5364909172058105,
414
+ "learning_rate": 9.257645688666557e-06,
415
+ "loss": 1.4013,
416
+ "step": 50
417
+ },
418
+ {
419
+ "epoch": 1.7058823529411766,
420
+ "grad_norm": 2.968980073928833,
421
+ "learning_rate": 9.220122420149753e-06,
422
+ "loss": 1.4879,
423
+ "step": 51
424
+ },
425
+ {
426
+ "epoch": 1.7394957983193278,
427
+ "grad_norm": 2.562370777130127,
428
+ "learning_rate": 9.181754044828882e-06,
429
+ "loss": 1.3619,
430
+ "step": 52
431
+ },
432
+ {
433
+ "epoch": 1.773109243697479,
434
+ "grad_norm": 2.976408004760742,
435
+ "learning_rate": 9.142548246219212e-06,
436
+ "loss": 1.2078,
437
+ "step": 53
438
+ },
439
+ {
440
+ "epoch": 1.8067226890756303,
441
+ "grad_norm": 3.2309634685516357,
442
+ "learning_rate": 9.102512875535439e-06,
443
+ "loss": 1.0231,
444
+ "step": 54
445
+ },
446
+ {
447
+ "epoch": 1.8403361344537816,
448
+ "grad_norm": 2.9703569412231445,
449
+ "learning_rate": 9.06165595011943e-06,
450
+ "loss": 1.5202,
451
+ "step": 55
452
+ },
453
+ {
454
+ "epoch": 1.8739495798319328,
455
+ "grad_norm": 3.620556354522705,
456
+ "learning_rate": 9.019985651834703e-06,
457
+ "loss": 1.1904,
458
+ "step": 56
459
+ },
460
+ {
461
+ "epoch": 1.8739495798319328,
462
+ "eval_loss": 1.0541609525680542,
463
+ "eval_runtime": 12.0294,
464
+ "eval_samples_per_second": 2.078,
465
+ "eval_steps_per_second": 0.582,
466
+ "step": 56
467
+ },
468
+ {
469
+ "epoch": 1.907563025210084,
470
+ "grad_norm": 2.8404018878936768,
471
+ "learning_rate": 8.97751032542795e-06,
472
+ "loss": 1.1275,
473
+ "step": 57
474
+ },
475
+ {
476
+ "epoch": 1.9411764705882353,
477
+ "grad_norm": 2.9330008029937744,
478
+ "learning_rate": 8.93423847685795e-06,
479
+ "loss": 1.2625,
480
+ "step": 58
481
+ },
482
+ {
483
+ "epoch": 1.9747899159663866,
484
+ "grad_norm": 3.747128963470459,
485
+ "learning_rate": 8.890178771592198e-06,
486
+ "loss": 1.0427,
487
+ "step": 59
488
+ },
489
+ {
490
+ "epoch": 2.0,
491
+ "grad_norm": 4.598628520965576,
492
+ "learning_rate": 8.845340032871584e-06,
493
+ "loss": 0.5982,
494
+ "step": 60
495
+ },
496
+ {
497
+ "epoch": 2.033613445378151,
498
+ "grad_norm": 2.659691333770752,
499
+ "learning_rate": 8.799731239943488e-06,
500
+ "loss": 1.0643,
501
+ "step": 61
502
+ },
503
+ {
504
+ "epoch": 2.0672268907563027,
505
+ "grad_norm": 3.448178768157959,
506
+ "learning_rate": 8.753361526263622e-06,
507
+ "loss": 0.8037,
508
+ "step": 62
509
+ },
510
+ {
511
+ "epoch": 2.100840336134454,
512
+ "grad_norm": 4.392441272735596,
513
+ "learning_rate": 8.706240177667003e-06,
514
+ "loss": 0.5474,
515
+ "step": 63
516
+ },
517
+ {
518
+ "epoch": 2.134453781512605,
519
+ "grad_norm": 3.435783624649048,
520
+ "learning_rate": 8.658376630508391e-06,
521
+ "loss": 1.0394,
522
+ "step": 64
523
+ },
524
+ {
525
+ "epoch": 2.134453781512605,
526
+ "eval_loss": 0.8591052889823914,
527
+ "eval_runtime": 12.0335,
528
+ "eval_samples_per_second": 2.078,
529
+ "eval_steps_per_second": 0.582,
530
+ "step": 64
531
+ },
532
+ {
533
+ "epoch": 2.168067226890756,
534
+ "grad_norm": 3.652780294418335,
535
+ "learning_rate": 8.609780469772623e-06,
536
+ "loss": 0.8207,
537
+ "step": 65
538
+ },
539
+ {
540
+ "epoch": 2.2016806722689077,
541
+ "grad_norm": 4.205479145050049,
542
+ "learning_rate": 8.56046142715513e-06,
543
+ "loss": 0.7293,
544
+ "step": 66
545
+ },
546
+ {
547
+ "epoch": 2.235294117647059,
548
+ "grad_norm": 4.328608512878418,
549
+ "learning_rate": 8.510429379113114e-06,
550
+ "loss": 1.1445,
551
+ "step": 67
552
+ },
553
+ {
554
+ "epoch": 2.26890756302521,
555
+ "grad_norm": 2.992579936981201,
556
+ "learning_rate": 8.459694344887732e-06,
557
+ "loss": 0.461,
558
+ "step": 68
559
+ },
560
+ {
561
+ "epoch": 2.302521008403361,
562
+ "grad_norm": 3.3023149967193604,
563
+ "learning_rate": 8.408266484497664e-06,
564
+ "loss": 0.9115,
565
+ "step": 69
566
+ },
567
+ {
568
+ "epoch": 2.3361344537815127,
569
+ "grad_norm": 3.0709333419799805,
570
+ "learning_rate": 8.356156096704516e-06,
571
+ "loss": 0.3745,
572
+ "step": 70
573
+ },
574
+ {
575
+ "epoch": 2.369747899159664,
576
+ "grad_norm": 3.3897287845611572,
577
+ "learning_rate": 8.303373616950408e-06,
578
+ "loss": 0.4913,
579
+ "step": 71
580
+ },
581
+ {
582
+ "epoch": 2.403361344537815,
583
+ "grad_norm": 3.306938886642456,
584
+ "learning_rate": 8.249929615268234e-06,
585
+ "loss": 0.5501,
586
+ "step": 72
587
+ },
588
+ {
589
+ "epoch": 2.403361344537815,
590
+ "eval_loss": 0.6722928881645203,
591
+ "eval_runtime": 12.0411,
592
+ "eval_samples_per_second": 2.076,
593
+ "eval_steps_per_second": 0.581,
594
+ "step": 72
595
+ },
596
+ {
597
+ "epoch": 2.4369747899159666,
598
+ "grad_norm": 3.504460334777832,
599
+ "learning_rate": 8.195834794164925e-06,
600
+ "loss": 1.0348,
601
+ "step": 73
602
+ },
603
+ {
604
+ "epoch": 2.4705882352941178,
605
+ "grad_norm": 3.0955419540405273,
606
+ "learning_rate": 8.141099986478212e-06,
607
+ "loss": 0.9719,
608
+ "step": 74
609
+ },
610
+ {
611
+ "epoch": 2.504201680672269,
612
+ "grad_norm": 3.5875039100646973,
613
+ "learning_rate": 8.085736153207277e-06,
614
+ "loss": 0.6814,
615
+ "step": 75
616
+ },
617
+ {
618
+ "epoch": 2.53781512605042,
619
+ "grad_norm": 3.203245162963867,
620
+ "learning_rate": 8.029754381317741e-06,
621
+ "loss": 0.9234,
622
+ "step": 76
623
+ },
624
+ {
625
+ "epoch": 2.571428571428571,
626
+ "grad_norm": 2.9670157432556152,
627
+ "learning_rate": 7.973165881521435e-06,
628
+ "loss": 0.6265,
629
+ "step": 77
630
+ },
631
+ {
632
+ "epoch": 2.6050420168067228,
633
+ "grad_norm": 3.2151577472686768,
634
+ "learning_rate": 7.915981986031367e-06,
635
+ "loss": 0.313,
636
+ "step": 78
637
+ },
638
+ {
639
+ "epoch": 2.638655462184874,
640
+ "grad_norm": 2.7305543422698975,
641
+ "learning_rate": 7.858214146292394e-06,
642
+ "loss": 0.4951,
643
+ "step": 79
644
+ },
645
+ {
646
+ "epoch": 2.6722689075630255,
647
+ "grad_norm": 3.675318717956543,
648
+ "learning_rate": 7.799873930687979e-06,
649
+ "loss": 0.2454,
650
+ "step": 80
651
+ },
652
+ {
653
+ "epoch": 2.6722689075630255,
654
+ "eval_loss": 0.536856472492218,
655
+ "eval_runtime": 12.0568,
656
+ "eval_samples_per_second": 2.074,
657
+ "eval_steps_per_second": 0.581,
658
+ "step": 80
659
+ },
660
+ {
661
+ "epoch": 2.7058823529411766,
662
+ "grad_norm": 1.8047897815704346,
663
+ "learning_rate": 7.74097302222355e-06,
664
+ "loss": 0.4276,
665
+ "step": 81
666
+ },
667
+ {
668
+ "epoch": 2.7394957983193278,
669
+ "grad_norm": 2.843857765197754,
670
+ "learning_rate": 7.681523216186912e-06,
671
+ "loss": 0.1704,
672
+ "step": 82
673
+ },
674
+ {
675
+ "epoch": 2.773109243697479,
676
+ "grad_norm": 2.3356502056121826,
677
+ "learning_rate": 7.621536417786159e-06,
678
+ "loss": 0.2967,
679
+ "step": 83
680
+ },
681
+ {
682
+ "epoch": 2.80672268907563,
683
+ "grad_norm": 2.3808438777923584,
684
+ "learning_rate": 7.5610246397655715e-06,
685
+ "loss": 0.2374,
686
+ "step": 84
687
+ },
688
+ {
689
+ "epoch": 2.8403361344537816,
690
+ "grad_norm": 2.5754661560058594,
691
+ "learning_rate": 7.500000000000001e-06,
692
+ "loss": 0.6951,
693
+ "step": 85
694
+ },
695
+ {
696
+ "epoch": 2.8739495798319328,
697
+ "grad_norm": 3.8589160442352295,
698
+ "learning_rate": 7.438474719068174e-06,
699
+ "loss": 0.3943,
700
+ "step": 86
701
+ },
702
+ {
703
+ "epoch": 2.907563025210084,
704
+ "grad_norm": 2.7497880458831787,
705
+ "learning_rate": 7.37646111780545e-06,
706
+ "loss": 0.3995,
707
+ "step": 87
708
+ },
709
+ {
710
+ "epoch": 2.9411764705882355,
711
+ "grad_norm": 3.4608285427093506,
712
+ "learning_rate": 7.313971614836496e-06,
713
+ "loss": 0.4499,
714
+ "step": 88
715
+ },
716
+ {
717
+ "epoch": 2.9411764705882355,
718
+ "eval_loss": 0.42864924669265747,
719
+ "eval_runtime": 12.0207,
720
+ "eval_samples_per_second": 2.08,
721
+ "eval_steps_per_second": 0.582,
722
+ "step": 88
723
+ },
724
+ {
725
+ "epoch": 2.9747899159663866,
726
+ "grad_norm": 3.7563107013702393,
727
+ "learning_rate": 7.251018724088367e-06,
728
+ "loss": 0.3587,
729
+ "step": 89
730
+ },
731
+ {
732
+ "epoch": 3.0,
733
+ "grad_norm": 2.986473798751831,
734
+ "learning_rate": 7.187615052284522e-06,
735
+ "loss": 0.2523,
736
+ "step": 90
737
+ },
738
+ {
739
+ "epoch": 3.033613445378151,
740
+ "grad_norm": 2.074615240097046,
741
+ "learning_rate": 7.12377329642024e-06,
742
+ "loss": 0.3245,
743
+ "step": 91
744
+ },
745
+ {
746
+ "epoch": 3.0672268907563027,
747
+ "grad_norm": 1.6591023206710815,
748
+ "learning_rate": 7.059506241219964e-06,
749
+ "loss": 0.404,
750
+ "step": 92
751
+ },
752
+ {
753
+ "epoch": 3.100840336134454,
754
+ "grad_norm": 2.0738601684570312,
755
+ "learning_rate": 6.994826756577082e-06,
756
+ "loss": 0.4466,
757
+ "step": 93
758
+ },
759
+ {
760
+ "epoch": 3.134453781512605,
761
+ "grad_norm": 1.8895370960235596,
762
+ "learning_rate": 6.9297477949766445e-06,
763
+ "loss": 0.1547,
764
+ "step": 94
765
+ },
766
+ {
767
+ "epoch": 3.168067226890756,
768
+ "grad_norm": 2.5287699699401855,
769
+ "learning_rate": 6.864282388901544e-06,
770
+ "loss": 0.5676,
771
+ "step": 95
772
+ },
773
+ {
774
+ "epoch": 3.2016806722689077,
775
+ "grad_norm": 2.2020397186279297,
776
+ "learning_rate": 6.79844364822268e-06,
777
+ "loss": 0.2194,
778
+ "step": 96
779
+ },
780
+ {
781
+ "epoch": 3.2016806722689077,
782
+ "eval_loss": 0.36906442046165466,
783
+ "eval_runtime": 12.0127,
784
+ "eval_samples_per_second": 2.081,
785
+ "eval_steps_per_second": 0.583,
786
+ "step": 96
787
+ },
788
+ {
789
+ "epoch": 3.235294117647059,
790
+ "grad_norm": 2.3070523738861084,
791
+ "learning_rate": 6.732244757573619e-06,
792
+ "loss": 0.2882,
793
+ "step": 97
794
+ },
795
+ {
796
+ "epoch": 3.26890756302521,
797
+ "grad_norm": 1.7963759899139404,
798
+ "learning_rate": 6.665698973710289e-06,
799
+ "loss": 0.1729,
800
+ "step": 98
801
+ },
802
+ {
803
+ "epoch": 3.302521008403361,
804
+ "grad_norm": 2.02447772026062,
805
+ "learning_rate": 6.598819622856227e-06,
806
+ "loss": 0.2463,
807
+ "step": 99
808
+ },
809
+ {
810
+ "epoch": 3.3361344537815127,
811
+ "grad_norm": 1.7601453065872192,
812
+ "learning_rate": 6.531620098033919e-06,
813
+ "loss": 0.2725,
814
+ "step": 100
815
+ },
816
+ {
817
+ "epoch": 3.369747899159664,
818
+ "grad_norm": 2.4182164669036865,
819
+ "learning_rate": 6.464113856382752e-06,
820
+ "loss": 0.2115,
821
+ "step": 101
822
+ },
823
+ {
824
+ "epoch": 3.403361344537815,
825
+ "grad_norm": 2.505795955657959,
826
+ "learning_rate": 6.396314416464151e-06,
827
+ "loss": 0.4502,
828
+ "step": 102
829
+ },
830
+ {
831
+ "epoch": 3.4369747899159666,
832
+ "grad_norm": 1.630191683769226,
833
+ "learning_rate": 6.328235355554382e-06,
834
+ "loss": 0.103,
835
+ "step": 103
836
+ },
837
+ {
838
+ "epoch": 3.4705882352941178,
839
+ "grad_norm": 1.4123270511627197,
840
+ "learning_rate": 6.259890306925627e-06,
841
+ "loss": 0.1172,
842
+ "step": 104
843
+ },
844
+ {
845
+ "epoch": 3.4705882352941178,
846
+ "eval_loss": 0.2801525294780731,
847
+ "eval_runtime": 12.0227,
848
+ "eval_samples_per_second": 2.079,
849
+ "eval_steps_per_second": 0.582,
850
+ "step": 104
851
+ },
852
+ {
853
+ "epoch": 3.504201680672269,
854
+ "grad_norm": 1.7171785831451416,
855
+ "learning_rate": 6.191292957115825e-06,
856
+ "loss": 0.2991,
857
+ "step": 105
858
+ },
859
+ {
860
+ "epoch": 3.53781512605042,
861
+ "grad_norm": 1.4823782444000244,
862
+ "learning_rate": 6.122457043187863e-06,
863
+ "loss": 0.216,
864
+ "step": 106
865
+ },
866
+ {
867
+ "epoch": 3.571428571428571,
868
+ "grad_norm": 2.7622790336608887,
869
+ "learning_rate": 6.053396349978632e-06,
870
+ "loss": 0.1453,
871
+ "step": 107
872
+ },
873
+ {
874
+ "epoch": 3.6050420168067228,
875
+ "grad_norm": 2.2422022819519043,
876
+ "learning_rate": 5.984124707338528e-06,
877
+ "loss": 0.0875,
878
+ "step": 108
879
+ },
880
+ {
881
+ "epoch": 3.638655462184874,
882
+ "grad_norm": 1.8057119846343994,
883
+ "learning_rate": 5.914655987361934e-06,
884
+ "loss": 0.2743,
885
+ "step": 109
886
+ },
887
+ {
888
+ "epoch": 3.6722689075630255,
889
+ "grad_norm": 1.2743725776672363,
890
+ "learning_rate": 5.8450041016092465e-06,
891
+ "loss": 0.2001,
892
+ "step": 110
893
+ },
894
+ {
895
+ "epoch": 3.7058823529411766,
896
+ "grad_norm": 2.135080575942993,
897
+ "learning_rate": 5.77518299832099e-06,
898
+ "loss": 0.2931,
899
+ "step": 111
900
+ },
901
+ {
902
+ "epoch": 3.7394957983193278,
903
+ "grad_norm": 2.7830662727355957,
904
+ "learning_rate": 5.705206659624597e-06,
905
+ "loss": 0.0739,
906
+ "step": 112
907
+ },
908
+ {
909
+ "epoch": 3.7394957983193278,
910
+ "eval_loss": 0.1947932094335556,
911
+ "eval_runtime": 12.0169,
912
+ "eval_samples_per_second": 2.08,
913
+ "eval_steps_per_second": 0.583,
914
+ "step": 112
915
+ },
916
+ {
917
+ "epoch": 3.773109243697479,
918
+ "grad_norm": 2.2503886222839355,
919
+ "learning_rate": 5.635089098734394e-06,
920
+ "loss": 0.1452,
921
+ "step": 113
922
+ },
923
+ {
924
+ "epoch": 3.80672268907563,
925
+ "grad_norm": 1.5595289468765259,
926
+ "learning_rate": 5.564844357145365e-06,
927
+ "loss": 0.0696,
928
+ "step": 114
929
+ },
930
+ {
931
+ "epoch": 3.8403361344537816,
932
+ "grad_norm": 1.9559892416000366,
933
+ "learning_rate": 5.49448650182125e-06,
934
+ "loss": 0.1231,
935
+ "step": 115
936
+ },
937
+ {
938
+ "epoch": 3.8739495798319328,
939
+ "grad_norm": 1.3151509761810303,
940
+ "learning_rate": 5.4240296223775465e-06,
941
+ "loss": 0.0796,
942
+ "step": 116
943
+ },
944
+ {
945
+ "epoch": 3.907563025210084,
946
+ "grad_norm": 2.6869540214538574,
947
+ "learning_rate": 5.353487828259973e-06,
948
+ "loss": 0.1171,
949
+ "step": 117
950
+ },
951
+ {
952
+ "epoch": 3.9411764705882355,
953
+ "grad_norm": 3.4072158336639404,
954
+ "learning_rate": 5.282875245918963e-06,
955
+ "loss": 0.2115,
956
+ "step": 118
957
+ },
958
+ {
959
+ "epoch": 3.9747899159663866,
960
+ "grad_norm": 2.99674916267395,
961
+ "learning_rate": 5.212206015980742e-06,
962
+ "loss": 0.1756,
963
+ "step": 119
964
+ },
965
+ {
966
+ "epoch": 4.0,
967
+ "grad_norm": 1.7564973831176758,
968
+ "learning_rate": 5.141494290415592e-06,
969
+ "loss": 0.1524,
970
+ "step": 120
971
+ },
972
+ {
973
+ "epoch": 4.0,
974
+ "eval_loss": 0.14572814106941223,
975
+ "eval_runtime": 12.0344,
976
+ "eval_samples_per_second": 2.077,
977
+ "eval_steps_per_second": 0.582,
978
+ "step": 120
979
+ },
980
+ {
981
+ "epoch": 4.033613445378151,
982
+ "grad_norm": 1.6185134649276733,
983
+ "learning_rate": 5.070754229703811e-06,
984
+ "loss": 0.2036,
985
+ "step": 121
986
+ },
987
+ {
988
+ "epoch": 4.067226890756302,
989
+ "grad_norm": 1.89780855178833,
990
+ "learning_rate": 5e-06,
991
+ "loss": 0.1084,
992
+ "step": 122
993
+ },
994
+ {
995
+ "epoch": 4.100840336134453,
996
+ "grad_norm": 1.0683470964431763,
997
+ "learning_rate": 4.929245770296191e-06,
998
+ "loss": 0.024,
999
+ "step": 123
1000
+ },
1001
+ {
1002
+ "epoch": 4.1344537815126055,
1003
+ "grad_norm": 1.3199543952941895,
1004
+ "learning_rate": 4.85850570958441e-06,
1005
+ "loss": 0.0721,
1006
+ "step": 124
1007
+ },
1008
+ {
1009
+ "epoch": 4.168067226890757,
1010
+ "grad_norm": 1.3227624893188477,
1011
+ "learning_rate": 4.78779398401926e-06,
1012
+ "loss": 0.1053,
1013
+ "step": 125
1014
+ },
1015
+ {
1016
+ "epoch": 4.201680672268908,
1017
+ "grad_norm": 0.9929068684577942,
1018
+ "learning_rate": 4.717124754081038e-06,
1019
+ "loss": 0.0404,
1020
+ "step": 126
1021
+ },
1022
+ {
1023
+ "epoch": 4.235294117647059,
1024
+ "grad_norm": 2.746427536010742,
1025
+ "learning_rate": 4.646512171740028e-06,
1026
+ "loss": 0.1037,
1027
+ "step": 127
1028
+ },
1029
+ {
1030
+ "epoch": 4.26890756302521,
1031
+ "grad_norm": 1.6636719703674316,
1032
+ "learning_rate": 4.575970377622456e-06,
1033
+ "loss": 0.0444,
1034
+ "step": 128
1035
+ },
1036
+ {
1037
+ "epoch": 4.26890756302521,
1038
+ "eval_loss": 0.1125473603606224,
1039
+ "eval_runtime": 12.0488,
1040
+ "eval_samples_per_second": 2.075,
1041
+ "eval_steps_per_second": 0.581,
1042
+ "step": 128
1043
+ },
1044
+ {
1045
+ "epoch": 4.302521008403361,
1046
+ "grad_norm": 1.1535725593566895,
1047
+ "learning_rate": 4.505513498178752e-06,
1048
+ "loss": 0.0378,
1049
+ "step": 129
1050
+ },
1051
+ {
1052
+ "epoch": 4.336134453781512,
1053
+ "grad_norm": 1.7697710990905762,
1054
+ "learning_rate": 4.435155642854637e-06,
1055
+ "loss": 0.0869,
1056
+ "step": 130
1057
+ },
1058
+ {
1059
+ "epoch": 4.369747899159664,
1060
+ "grad_norm": 0.9928828477859497,
1061
+ "learning_rate": 4.364910901265607e-06,
1062
+ "loss": 0.0737,
1063
+ "step": 131
1064
+ },
1065
+ {
1066
+ "epoch": 4.4033613445378155,
1067
+ "grad_norm": 1.6332063674926758,
1068
+ "learning_rate": 4.294793340375405e-06,
1069
+ "loss": 0.1098,
1070
+ "step": 132
1071
+ },
1072
+ {
1073
+ "epoch": 4.436974789915967,
1074
+ "grad_norm": 2.2281079292297363,
1075
+ "learning_rate": 4.224817001679011e-06,
1076
+ "loss": 0.0657,
1077
+ "step": 133
1078
+ },
1079
+ {
1080
+ "epoch": 4.470588235294118,
1081
+ "grad_norm": 3.8611080646514893,
1082
+ "learning_rate": 4.154995898390756e-06,
1083
+ "loss": 0.1013,
1084
+ "step": 134
1085
+ },
1086
+ {
1087
+ "epoch": 4.504201680672269,
1088
+ "grad_norm": 0.7134477496147156,
1089
+ "learning_rate": 4.085344012638067e-06,
1090
+ "loss": 0.0105,
1091
+ "step": 135
1092
+ },
1093
+ {
1094
+ "epoch": 4.53781512605042,
1095
+ "grad_norm": 3.5929417610168457,
1096
+ "learning_rate": 4.015875292661474e-06,
1097
+ "loss": 0.1385,
1098
+ "step": 136
1099
+ },
1100
+ {
1101
+ "epoch": 4.53781512605042,
1102
+ "eval_loss": 0.0758795514702797,
1103
+ "eval_runtime": 12.0325,
1104
+ "eval_samples_per_second": 2.078,
1105
+ "eval_steps_per_second": 0.582,
1106
+ "step": 136
1107
+ },
1108
+ {
1109
+ "epoch": 4.571428571428571,
1110
+ "grad_norm": 1.6059097051620483,
1111
+ "learning_rate": 3.94660365002137e-06,
1112
+ "loss": 0.0688,
1113
+ "step": 137
1114
+ },
1115
+ {
1116
+ "epoch": 4.605042016806722,
1117
+ "grad_norm": 1.931578278541565,
1118
+ "learning_rate": 3.877542956812137e-06,
1119
+ "loss": 0.061,
1120
+ "step": 138
1121
+ },
1122
+ {
1123
+ "epoch": 4.6386554621848735,
1124
+ "grad_norm": 4.694330215454102,
1125
+ "learning_rate": 3.808707042884176e-06,
1126
+ "loss": 0.0645,
1127
+ "step": 139
1128
+ },
1129
+ {
1130
+ "epoch": 4.6722689075630255,
1131
+ "grad_norm": 1.5269956588745117,
1132
+ "learning_rate": 3.7401096930743753e-06,
1133
+ "loss": 0.0695,
1134
+ "step": 140
1135
+ },
1136
+ {
1137
+ "epoch": 4.705882352941177,
1138
+ "grad_norm": 1.7759701013565063,
1139
+ "learning_rate": 3.6717646444456196e-06,
1140
+ "loss": 0.0327,
1141
+ "step": 141
1142
+ },
1143
+ {
1144
+ "epoch": 4.739495798319328,
1145
+ "grad_norm": 1.899479627609253,
1146
+ "learning_rate": 3.60368558353585e-06,
1147
+ "loss": 0.0428,
1148
+ "step": 142
1149
+ },
1150
+ {
1151
+ "epoch": 4.773109243697479,
1152
+ "grad_norm": 1.7261422872543335,
1153
+ "learning_rate": 3.5358861436172487e-06,
1154
+ "loss": 0.0628,
1155
+ "step": 143
1156
+ },
1157
+ {
1158
+ "epoch": 4.80672268907563,
1159
+ "grad_norm": 3.8707656860351562,
1160
+ "learning_rate": 3.4683799019660834e-06,
1161
+ "loss": 0.0591,
1162
+ "step": 144
1163
+ },
1164
+ {
1165
+ "epoch": 4.80672268907563,
1166
+ "eval_loss": 0.05604570358991623,
1167
+ "eval_runtime": 12.0383,
1168
+ "eval_samples_per_second": 2.077,
1169
+ "eval_steps_per_second": 0.581,
1170
+ "step": 144
1171
+ },
1172
+ {
1173
+ "epoch": 4.840336134453781,
1174
+ "grad_norm": 0.8072419762611389,
1175
+ "learning_rate": 3.401180377143774e-06,
1176
+ "loss": 0.0301,
1177
+ "step": 145
1178
+ }
1179
+ ],
1180
+ "logging_steps": 1,
1181
+ "max_steps": 232,
1182
+ "num_input_tokens_seen": 0,
1183
+ "num_train_epochs": 8,
1184
+ "save_steps": 29,
1185
+ "stateful_callbacks": {
1186
+ "TrainerControl": {
1187
+ "args": {
1188
+ "should_epoch_stop": false,
1189
+ "should_evaluate": false,
1190
+ "should_log": false,
1191
+ "should_save": true,
1192
+ "should_training_stop": false
1193
+ },
1194
+ "attributes": {}
1195
+ }
1196
+ },
1197
+ "total_flos": 1.9879032791236608e+17,
1198
+ "train_batch_size": 2,
1199
+ "trial_name": null,
1200
+ "trial_params": null
1201
+ }
checkpoint-145/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85f8f9b09204e1090ec2369a8805ad857a677dac1a4ca5d19752c2e11cd99114
3
+ size 7505
checkpoint-174/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /dpool/Meta-Llama-3.1-8B-Instruct-abliterated
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
checkpoint-174/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/dpool/Meta-Llama-3.1-8B-Instruct-abliterated",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": null,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 16,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "k_proj",
29
+ "q_proj",
30
+ "down_proj",
31
+ "o_proj",
32
+ "v_proj",
33
+ "up_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-174/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28946910885cff0e267f00196d7bb5fca581d1ac7ff6b5068d048115451be4b3
3
+ size 167832240
checkpoint-174/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb28a6472e73533fa4281268f479a4125d45a145f85a7672527c98bd8018815
3
+ size 335945763
checkpoint-174/pytorch_model_fsdp.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaa2fecd11b46bf65dcedf327f862a304824965a56064bcd365b85f7f0d7c7de
3
+ size 167939969
checkpoint-174/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5d03633ddaefc33c68b6ff80e801228f61bca02cc659b01bbe33bd59e6ce3eb
3
+ size 14917
checkpoint-174/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d809e04092ed28648d209095c1865c4c02c4ab7efc199ee4df781a157516d5b
3
+ size 14917
checkpoint-174/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:823d85f163319c9fbcd7895a2a56f1ffac018612047c6bba65b8553f619dd28a
3
+ size 1465
checkpoint-174/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-174/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-174/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizer"
2064
+ }
checkpoint-174/trainer_state.json ADDED
@@ -0,0 +1,1428 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 5.80672268907563,
6
+ "eval_steps": 8,
7
+ "global_step": 174,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.03361344537815126,
14
+ "grad_norm": 2.6346614360809326,
15
+ "learning_rate": 0.0,
16
+ "loss": 3.5587,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.03361344537815126,
21
+ "eval_loss": 3.4337246417999268,
22
+ "eval_runtime": 12.0401,
23
+ "eval_samples_per_second": 2.076,
24
+ "eval_steps_per_second": 0.581,
25
+ "step": 1
26
+ },
27
+ {
28
+ "epoch": 0.06722689075630252,
29
+ "grad_norm": 3.2896828651428223,
30
+ "learning_rate": 1.0000000000000002e-06,
31
+ "loss": 3.6974,
32
+ "step": 2
33
+ },
34
+ {
35
+ "epoch": 0.10084033613445378,
36
+ "grad_norm": 2.942761182785034,
37
+ "learning_rate": 2.0000000000000003e-06,
38
+ "loss": 3.7682,
39
+ "step": 3
40
+ },
41
+ {
42
+ "epoch": 0.13445378151260504,
43
+ "grad_norm": 3.322763442993164,
44
+ "learning_rate": 3e-06,
45
+ "loss": 4.1233,
46
+ "step": 4
47
+ },
48
+ {
49
+ "epoch": 0.16806722689075632,
50
+ "grad_norm": 2.542609214782715,
51
+ "learning_rate": 4.000000000000001e-06,
52
+ "loss": 3.7296,
53
+ "step": 5
54
+ },
55
+ {
56
+ "epoch": 0.20168067226890757,
57
+ "grad_norm": 2.8525142669677734,
58
+ "learning_rate": 5e-06,
59
+ "loss": 3.8537,
60
+ "step": 6
61
+ },
62
+ {
63
+ "epoch": 0.23529411764705882,
64
+ "grad_norm": 2.3698537349700928,
65
+ "learning_rate": 6e-06,
66
+ "loss": 3.648,
67
+ "step": 7
68
+ },
69
+ {
70
+ "epoch": 0.2689075630252101,
71
+ "grad_norm": 2.540416955947876,
72
+ "learning_rate": 7e-06,
73
+ "loss": 3.6702,
74
+ "step": 8
75
+ },
76
+ {
77
+ "epoch": 0.2689075630252101,
78
+ "eval_loss": 3.4260427951812744,
79
+ "eval_runtime": 12.0264,
80
+ "eval_samples_per_second": 2.079,
81
+ "eval_steps_per_second": 0.582,
82
+ "step": 8
83
+ },
84
+ {
85
+ "epoch": 0.3025210084033613,
86
+ "grad_norm": 2.424398422241211,
87
+ "learning_rate": 8.000000000000001e-06,
88
+ "loss": 3.3544,
89
+ "step": 9
90
+ },
91
+ {
92
+ "epoch": 0.33613445378151263,
93
+ "grad_norm": 3.290915012359619,
94
+ "learning_rate": 9e-06,
95
+ "loss": 3.9672,
96
+ "step": 10
97
+ },
98
+ {
99
+ "epoch": 0.3697478991596639,
100
+ "grad_norm": 2.8242039680480957,
101
+ "learning_rate": 1e-05,
102
+ "loss": 3.591,
103
+ "step": 11
104
+ },
105
+ {
106
+ "epoch": 0.40336134453781514,
107
+ "grad_norm": 2.9474833011627197,
108
+ "learning_rate": 9.999499358833745e-06,
109
+ "loss": 3.6958,
110
+ "step": 12
111
+ },
112
+ {
113
+ "epoch": 0.4369747899159664,
114
+ "grad_norm": 3.4582228660583496,
115
+ "learning_rate": 9.99799753559161e-06,
116
+ "loss": 3.99,
117
+ "step": 13
118
+ },
119
+ {
120
+ "epoch": 0.47058823529411764,
121
+ "grad_norm": 3.1884031295776367,
122
+ "learning_rate": 9.99549483102341e-06,
123
+ "loss": 3.8204,
124
+ "step": 14
125
+ },
126
+ {
127
+ "epoch": 0.5042016806722689,
128
+ "grad_norm": 2.423398017883301,
129
+ "learning_rate": 9.991991746311916e-06,
130
+ "loss": 3.0469,
131
+ "step": 15
132
+ },
133
+ {
134
+ "epoch": 0.5378151260504201,
135
+ "grad_norm": 3.3329102993011475,
136
+ "learning_rate": 9.9874889829725e-06,
137
+ "loss": 3.5802,
138
+ "step": 16
139
+ },
140
+ {
141
+ "epoch": 0.5378151260504201,
142
+ "eval_loss": 3.316091299057007,
143
+ "eval_runtime": 12.0143,
144
+ "eval_samples_per_second": 2.081,
145
+ "eval_steps_per_second": 0.583,
146
+ "step": 16
147
+ },
148
+ {
149
+ "epoch": 0.5714285714285714,
150
+ "grad_norm": 2.8659586906433105,
151
+ "learning_rate": 9.981987442712634e-06,
152
+ "loss": 3.0165,
153
+ "step": 17
154
+ },
155
+ {
156
+ "epoch": 0.6050420168067226,
157
+ "grad_norm": 3.4627182483673096,
158
+ "learning_rate": 9.97548822725133e-06,
159
+ "loss": 3.9333,
160
+ "step": 18
161
+ },
162
+ {
163
+ "epoch": 0.6386554621848739,
164
+ "grad_norm": 3.3491547107696533,
165
+ "learning_rate": 9.967992638098517e-06,
166
+ "loss": 3.5018,
167
+ "step": 19
168
+ },
169
+ {
170
+ "epoch": 0.6722689075630253,
171
+ "grad_norm": 2.7486977577209473,
172
+ "learning_rate": 9.959502176294384e-06,
173
+ "loss": 2.9875,
174
+ "step": 20
175
+ },
176
+ {
177
+ "epoch": 0.7058823529411765,
178
+ "grad_norm": 2.9063732624053955,
179
+ "learning_rate": 9.950018542108818e-06,
180
+ "loss": 3.0974,
181
+ "step": 21
182
+ },
183
+ {
184
+ "epoch": 0.7394957983193278,
185
+ "grad_norm": 3.2880260944366455,
186
+ "learning_rate": 9.939543634700891e-06,
187
+ "loss": 3.141,
188
+ "step": 22
189
+ },
190
+ {
191
+ "epoch": 0.773109243697479,
192
+ "grad_norm": 3.086613416671753,
193
+ "learning_rate": 9.928079551738542e-06,
194
+ "loss": 3.0282,
195
+ "step": 23
196
+ },
197
+ {
198
+ "epoch": 0.8067226890756303,
199
+ "grad_norm": 3.7129077911376953,
200
+ "learning_rate": 9.915628588978522e-06,
201
+ "loss": 3.2421,
202
+ "step": 24
203
+ },
204
+ {
205
+ "epoch": 0.8067226890756303,
206
+ "eval_loss": 3.0272111892700195,
207
+ "eval_runtime": 12.0429,
208
+ "eval_samples_per_second": 2.076,
209
+ "eval_steps_per_second": 0.581,
210
+ "step": 24
211
+ },
212
+ {
213
+ "epoch": 0.8403361344537815,
214
+ "grad_norm": 4.430984973907471,
215
+ "learning_rate": 9.902193239806634e-06,
216
+ "loss": 3.2481,
217
+ "step": 25
218
+ },
219
+ {
220
+ "epoch": 0.8739495798319328,
221
+ "grad_norm": 3.6558125019073486,
222
+ "learning_rate": 9.887776194738433e-06,
223
+ "loss": 2.8553,
224
+ "step": 26
225
+ },
226
+ {
227
+ "epoch": 0.907563025210084,
228
+ "grad_norm": 4.079296112060547,
229
+ "learning_rate": 9.872380340880416e-06,
230
+ "loss": 3.0176,
231
+ "step": 27
232
+ },
233
+ {
234
+ "epoch": 0.9411764705882353,
235
+ "grad_norm": 4.859598159790039,
236
+ "learning_rate": 9.856008761351882e-06,
237
+ "loss": 2.7999,
238
+ "step": 28
239
+ },
240
+ {
241
+ "epoch": 0.9747899159663865,
242
+ "grad_norm": 4.5133957862854,
243
+ "learning_rate": 9.838664734667496e-06,
244
+ "loss": 2.933,
245
+ "step": 29
246
+ },
247
+ {
248
+ "epoch": 1.0,
249
+ "grad_norm": 4.612884044647217,
250
+ "learning_rate": 9.820351734080754e-06,
251
+ "loss": 2.5651,
252
+ "step": 30
253
+ },
254
+ {
255
+ "epoch": 1.0336134453781514,
256
+ "grad_norm": 4.931149959564209,
257
+ "learning_rate": 9.801073426888447e-06,
258
+ "loss": 2.5854,
259
+ "step": 31
260
+ },
261
+ {
262
+ "epoch": 1.0672268907563025,
263
+ "grad_norm": 5.286943435668945,
264
+ "learning_rate": 9.780833673696255e-06,
265
+ "loss": 2.322,
266
+ "step": 32
267
+ },
268
+ {
269
+ "epoch": 1.0672268907563025,
270
+ "eval_loss": 2.48122239112854,
271
+ "eval_runtime": 12.0206,
272
+ "eval_samples_per_second": 2.08,
273
+ "eval_steps_per_second": 0.582,
274
+ "step": 32
275
+ },
276
+ {
277
+ "epoch": 1.1008403361344539,
278
+ "grad_norm": 4.670954704284668,
279
+ "learning_rate": 9.759636527645633e-06,
280
+ "loss": 2.4513,
281
+ "step": 33
282
+ },
283
+ {
284
+ "epoch": 1.134453781512605,
285
+ "grad_norm": 4.8246169090271,
286
+ "learning_rate": 9.737486233602149e-06,
287
+ "loss": 2.1937,
288
+ "step": 34
289
+ },
290
+ {
291
+ "epoch": 1.1680672268907564,
292
+ "grad_norm": 4.8713836669921875,
293
+ "learning_rate": 9.714387227305422e-06,
294
+ "loss": 2.3228,
295
+ "step": 35
296
+ },
297
+ {
298
+ "epoch": 1.2016806722689075,
299
+ "grad_norm": 5.048571586608887,
300
+ "learning_rate": 9.69034413448083e-06,
301
+ "loss": 1.9506,
302
+ "step": 36
303
+ },
304
+ {
305
+ "epoch": 1.2352941176470589,
306
+ "grad_norm": 5.047688007354736,
307
+ "learning_rate": 9.665361769913187e-06,
308
+ "loss": 2.2959,
309
+ "step": 37
310
+ },
311
+ {
312
+ "epoch": 1.26890756302521,
313
+ "grad_norm": 5.056053161621094,
314
+ "learning_rate": 9.639445136482549e-06,
315
+ "loss": 2.0905,
316
+ "step": 38
317
+ },
318
+ {
319
+ "epoch": 1.3025210084033614,
320
+ "grad_norm": 3.506237506866455,
321
+ "learning_rate": 9.612599424162344e-06,
322
+ "loss": 1.9687,
323
+ "step": 39
324
+ },
325
+ {
326
+ "epoch": 1.3361344537815127,
327
+ "grad_norm": 4.794375896453857,
328
+ "learning_rate": 9.584830008980068e-06,
329
+ "loss": 1.9774,
330
+ "step": 40
331
+ },
332
+ {
333
+ "epoch": 1.3361344537815127,
334
+ "eval_loss": 1.870819091796875,
335
+ "eval_runtime": 12.0354,
336
+ "eval_samples_per_second": 2.077,
337
+ "eval_steps_per_second": 0.582,
338
+ "step": 40
339
+ },
340
+ {
341
+ "epoch": 1.3697478991596639,
342
+ "grad_norm": 5.138720512390137,
343
+ "learning_rate": 9.55614245194068e-06,
344
+ "loss": 1.6505,
345
+ "step": 41
346
+ },
347
+ {
348
+ "epoch": 1.403361344537815,
349
+ "grad_norm": 3.800957679748535,
350
+ "learning_rate": 9.526542497912984e-06,
351
+ "loss": 1.8317,
352
+ "step": 42
353
+ },
354
+ {
355
+ "epoch": 1.4369747899159664,
356
+ "grad_norm": 4.458896636962891,
357
+ "learning_rate": 9.496036074479184e-06,
358
+ "loss": 1.6714,
359
+ "step": 43
360
+ },
361
+ {
362
+ "epoch": 1.4705882352941178,
363
+ "grad_norm": 3.317945718765259,
364
+ "learning_rate": 9.464629290747844e-06,
365
+ "loss": 1.825,
366
+ "step": 44
367
+ },
368
+ {
369
+ "epoch": 1.504201680672269,
370
+ "grad_norm": 3.235334634780884,
371
+ "learning_rate": 9.432328436130493e-06,
372
+ "loss": 1.5301,
373
+ "step": 45
374
+ },
375
+ {
376
+ "epoch": 1.53781512605042,
377
+ "grad_norm": 3.7489278316497803,
378
+ "learning_rate": 9.399139979082148e-06,
379
+ "loss": 1.5717,
380
+ "step": 46
381
+ },
382
+ {
383
+ "epoch": 1.5714285714285714,
384
+ "grad_norm": 2.814138889312744,
385
+ "learning_rate": 9.365070565805941e-06,
386
+ "loss": 1.6659,
387
+ "step": 47
388
+ },
389
+ {
390
+ "epoch": 1.6050420168067228,
391
+ "grad_norm": 3.219665765762329,
392
+ "learning_rate": 9.330127018922195e-06,
393
+ "loss": 1.5103,
394
+ "step": 48
395
+ },
396
+ {
397
+ "epoch": 1.6050420168067228,
398
+ "eval_loss": 1.3871335983276367,
399
+ "eval_runtime": 12.0361,
400
+ "eval_samples_per_second": 2.077,
401
+ "eval_steps_per_second": 0.582,
402
+ "step": 48
403
+ },
404
+ {
405
+ "epoch": 1.638655462184874,
406
+ "grad_norm": 3.621195077896118,
407
+ "learning_rate": 9.294316336102132e-06,
408
+ "loss": 1.4593,
409
+ "step": 49
410
+ },
411
+ {
412
+ "epoch": 1.6722689075630253,
413
+ "grad_norm": 3.5364909172058105,
414
+ "learning_rate": 9.257645688666557e-06,
415
+ "loss": 1.4013,
416
+ "step": 50
417
+ },
418
+ {
419
+ "epoch": 1.7058823529411766,
420
+ "grad_norm": 2.968980073928833,
421
+ "learning_rate": 9.220122420149753e-06,
422
+ "loss": 1.4879,
423
+ "step": 51
424
+ },
425
+ {
426
+ "epoch": 1.7394957983193278,
427
+ "grad_norm": 2.562370777130127,
428
+ "learning_rate": 9.181754044828882e-06,
429
+ "loss": 1.3619,
430
+ "step": 52
431
+ },
432
+ {
433
+ "epoch": 1.773109243697479,
434
+ "grad_norm": 2.976408004760742,
435
+ "learning_rate": 9.142548246219212e-06,
436
+ "loss": 1.2078,
437
+ "step": 53
438
+ },
439
+ {
440
+ "epoch": 1.8067226890756303,
441
+ "grad_norm": 3.2309634685516357,
442
+ "learning_rate": 9.102512875535439e-06,
443
+ "loss": 1.0231,
444
+ "step": 54
445
+ },
446
+ {
447
+ "epoch": 1.8403361344537816,
448
+ "grad_norm": 2.9703569412231445,
449
+ "learning_rate": 9.06165595011943e-06,
450
+ "loss": 1.5202,
451
+ "step": 55
452
+ },
453
+ {
454
+ "epoch": 1.8739495798319328,
455
+ "grad_norm": 3.620556354522705,
456
+ "learning_rate": 9.019985651834703e-06,
457
+ "loss": 1.1904,
458
+ "step": 56
459
+ },
460
+ {
461
+ "epoch": 1.8739495798319328,
462
+ "eval_loss": 1.0541609525680542,
463
+ "eval_runtime": 12.0294,
464
+ "eval_samples_per_second": 2.078,
465
+ "eval_steps_per_second": 0.582,
466
+ "step": 56
467
+ },
468
+ {
469
+ "epoch": 1.907563025210084,
470
+ "grad_norm": 2.8404018878936768,
471
+ "learning_rate": 8.97751032542795e-06,
472
+ "loss": 1.1275,
473
+ "step": 57
474
+ },
475
+ {
476
+ "epoch": 1.9411764705882353,
477
+ "grad_norm": 2.9330008029937744,
478
+ "learning_rate": 8.93423847685795e-06,
479
+ "loss": 1.2625,
480
+ "step": 58
481
+ },
482
+ {
483
+ "epoch": 1.9747899159663866,
484
+ "grad_norm": 3.747128963470459,
485
+ "learning_rate": 8.890178771592198e-06,
486
+ "loss": 1.0427,
487
+ "step": 59
488
+ },
489
+ {
490
+ "epoch": 2.0,
491
+ "grad_norm": 4.598628520965576,
492
+ "learning_rate": 8.845340032871584e-06,
493
+ "loss": 0.5982,
494
+ "step": 60
495
+ },
496
+ {
497
+ "epoch": 2.033613445378151,
498
+ "grad_norm": 2.659691333770752,
499
+ "learning_rate": 8.799731239943488e-06,
500
+ "loss": 1.0643,
501
+ "step": 61
502
+ },
503
+ {
504
+ "epoch": 2.0672268907563027,
505
+ "grad_norm": 3.448178768157959,
506
+ "learning_rate": 8.753361526263622e-06,
507
+ "loss": 0.8037,
508
+ "step": 62
509
+ },
510
+ {
511
+ "epoch": 2.100840336134454,
512
+ "grad_norm": 4.392441272735596,
513
+ "learning_rate": 8.706240177667003e-06,
514
+ "loss": 0.5474,
515
+ "step": 63
516
+ },
517
+ {
518
+ "epoch": 2.134453781512605,
519
+ "grad_norm": 3.435783624649048,
520
+ "learning_rate": 8.658376630508391e-06,
521
+ "loss": 1.0394,
522
+ "step": 64
523
+ },
524
+ {
525
+ "epoch": 2.134453781512605,
526
+ "eval_loss": 0.8591052889823914,
527
+ "eval_runtime": 12.0335,
528
+ "eval_samples_per_second": 2.078,
529
+ "eval_steps_per_second": 0.582,
530
+ "step": 64
531
+ },
532
+ {
533
+ "epoch": 2.168067226890756,
534
+ "grad_norm": 3.652780294418335,
535
+ "learning_rate": 8.609780469772623e-06,
536
+ "loss": 0.8207,
537
+ "step": 65
538
+ },
539
+ {
540
+ "epoch": 2.2016806722689077,
541
+ "grad_norm": 4.205479145050049,
542
+ "learning_rate": 8.56046142715513e-06,
543
+ "loss": 0.7293,
544
+ "step": 66
545
+ },
546
+ {
547
+ "epoch": 2.235294117647059,
548
+ "grad_norm": 4.328608512878418,
549
+ "learning_rate": 8.510429379113114e-06,
550
+ "loss": 1.1445,
551
+ "step": 67
552
+ },
553
+ {
554
+ "epoch": 2.26890756302521,
555
+ "grad_norm": 2.992579936981201,
556
+ "learning_rate": 8.459694344887732e-06,
557
+ "loss": 0.461,
558
+ "step": 68
559
+ },
560
+ {
561
+ "epoch": 2.302521008403361,
562
+ "grad_norm": 3.3023149967193604,
563
+ "learning_rate": 8.408266484497664e-06,
564
+ "loss": 0.9115,
565
+ "step": 69
566
+ },
567
+ {
568
+ "epoch": 2.3361344537815127,
569
+ "grad_norm": 3.0709333419799805,
570
+ "learning_rate": 8.356156096704516e-06,
571
+ "loss": 0.3745,
572
+ "step": 70
573
+ },
574
+ {
575
+ "epoch": 2.369747899159664,
576
+ "grad_norm": 3.3897287845611572,
577
+ "learning_rate": 8.303373616950408e-06,
578
+ "loss": 0.4913,
579
+ "step": 71
580
+ },
581
+ {
582
+ "epoch": 2.403361344537815,
583
+ "grad_norm": 3.306938886642456,
584
+ "learning_rate": 8.249929615268234e-06,
585
+ "loss": 0.5501,
586
+ "step": 72
587
+ },
588
+ {
589
+ "epoch": 2.403361344537815,
590
+ "eval_loss": 0.6722928881645203,
591
+ "eval_runtime": 12.0411,
592
+ "eval_samples_per_second": 2.076,
593
+ "eval_steps_per_second": 0.581,
594
+ "step": 72
595
+ },
596
+ {
597
+ "epoch": 2.4369747899159666,
598
+ "grad_norm": 3.504460334777832,
599
+ "learning_rate": 8.195834794164925e-06,
600
+ "loss": 1.0348,
601
+ "step": 73
602
+ },
603
+ {
604
+ "epoch": 2.4705882352941178,
605
+ "grad_norm": 3.0955419540405273,
606
+ "learning_rate": 8.141099986478212e-06,
607
+ "loss": 0.9719,
608
+ "step": 74
609
+ },
610
+ {
611
+ "epoch": 2.504201680672269,
612
+ "grad_norm": 3.5875039100646973,
613
+ "learning_rate": 8.085736153207277e-06,
614
+ "loss": 0.6814,
615
+ "step": 75
616
+ },
617
+ {
618
+ "epoch": 2.53781512605042,
619
+ "grad_norm": 3.203245162963867,
620
+ "learning_rate": 8.029754381317741e-06,
621
+ "loss": 0.9234,
622
+ "step": 76
623
+ },
624
+ {
625
+ "epoch": 2.571428571428571,
626
+ "grad_norm": 2.9670157432556152,
627
+ "learning_rate": 7.973165881521435e-06,
628
+ "loss": 0.6265,
629
+ "step": 77
630
+ },
631
+ {
632
+ "epoch": 2.6050420168067228,
633
+ "grad_norm": 3.2151577472686768,
634
+ "learning_rate": 7.915981986031367e-06,
635
+ "loss": 0.313,
636
+ "step": 78
637
+ },
638
+ {
639
+ "epoch": 2.638655462184874,
640
+ "grad_norm": 2.7305543422698975,
641
+ "learning_rate": 7.858214146292394e-06,
642
+ "loss": 0.4951,
643
+ "step": 79
644
+ },
645
+ {
646
+ "epoch": 2.6722689075630255,
647
+ "grad_norm": 3.675318717956543,
648
+ "learning_rate": 7.799873930687979e-06,
649
+ "loss": 0.2454,
650
+ "step": 80
651
+ },
652
+ {
653
+ "epoch": 2.6722689075630255,
654
+ "eval_loss": 0.536856472492218,
655
+ "eval_runtime": 12.0568,
656
+ "eval_samples_per_second": 2.074,
657
+ "eval_steps_per_second": 0.581,
658
+ "step": 80
659
+ },
660
+ {
661
+ "epoch": 2.7058823529411766,
662
+ "grad_norm": 1.8047897815704346,
663
+ "learning_rate": 7.74097302222355e-06,
664
+ "loss": 0.4276,
665
+ "step": 81
666
+ },
667
+ {
668
+ "epoch": 2.7394957983193278,
669
+ "grad_norm": 2.843857765197754,
670
+ "learning_rate": 7.681523216186912e-06,
671
+ "loss": 0.1704,
672
+ "step": 82
673
+ },
674
+ {
675
+ "epoch": 2.773109243697479,
676
+ "grad_norm": 2.3356502056121826,
677
+ "learning_rate": 7.621536417786159e-06,
678
+ "loss": 0.2967,
679
+ "step": 83
680
+ },
681
+ {
682
+ "epoch": 2.80672268907563,
683
+ "grad_norm": 2.3808438777923584,
684
+ "learning_rate": 7.5610246397655715e-06,
685
+ "loss": 0.2374,
686
+ "step": 84
687
+ },
688
+ {
689
+ "epoch": 2.8403361344537816,
690
+ "grad_norm": 2.5754661560058594,
691
+ "learning_rate": 7.500000000000001e-06,
692
+ "loss": 0.6951,
693
+ "step": 85
694
+ },
695
+ {
696
+ "epoch": 2.8739495798319328,
697
+ "grad_norm": 3.8589160442352295,
698
+ "learning_rate": 7.438474719068174e-06,
699
+ "loss": 0.3943,
700
+ "step": 86
701
+ },
702
+ {
703
+ "epoch": 2.907563025210084,
704
+ "grad_norm": 2.7497880458831787,
705
+ "learning_rate": 7.37646111780545e-06,
706
+ "loss": 0.3995,
707
+ "step": 87
708
+ },
709
+ {
710
+ "epoch": 2.9411764705882355,
711
+ "grad_norm": 3.4608285427093506,
712
+ "learning_rate": 7.313971614836496e-06,
713
+ "loss": 0.4499,
714
+ "step": 88
715
+ },
716
+ {
717
+ "epoch": 2.9411764705882355,
718
+ "eval_loss": 0.42864924669265747,
719
+ "eval_runtime": 12.0207,
720
+ "eval_samples_per_second": 2.08,
721
+ "eval_steps_per_second": 0.582,
722
+ "step": 88
723
+ },
724
+ {
725
+ "epoch": 2.9747899159663866,
726
+ "grad_norm": 3.7563107013702393,
727
+ "learning_rate": 7.251018724088367e-06,
728
+ "loss": 0.3587,
729
+ "step": 89
730
+ },
731
+ {
732
+ "epoch": 3.0,
733
+ "grad_norm": 2.986473798751831,
734
+ "learning_rate": 7.187615052284522e-06,
735
+ "loss": 0.2523,
736
+ "step": 90
737
+ },
738
+ {
739
+ "epoch": 3.033613445378151,
740
+ "grad_norm": 2.074615240097046,
741
+ "learning_rate": 7.12377329642024e-06,
742
+ "loss": 0.3245,
743
+ "step": 91
744
+ },
745
+ {
746
+ "epoch": 3.0672268907563027,
747
+ "grad_norm": 1.6591023206710815,
748
+ "learning_rate": 7.059506241219964e-06,
749
+ "loss": 0.404,
750
+ "step": 92
751
+ },
752
+ {
753
+ "epoch": 3.100840336134454,
754
+ "grad_norm": 2.0738601684570312,
755
+ "learning_rate": 6.994826756577082e-06,
756
+ "loss": 0.4466,
757
+ "step": 93
758
+ },
759
+ {
760
+ "epoch": 3.134453781512605,
761
+ "grad_norm": 1.8895370960235596,
762
+ "learning_rate": 6.9297477949766445e-06,
763
+ "loss": 0.1547,
764
+ "step": 94
765
+ },
766
+ {
767
+ "epoch": 3.168067226890756,
768
+ "grad_norm": 2.5287699699401855,
769
+ "learning_rate": 6.864282388901544e-06,
770
+ "loss": 0.5676,
771
+ "step": 95
772
+ },
773
+ {
774
+ "epoch": 3.2016806722689077,
775
+ "grad_norm": 2.2020397186279297,
776
+ "learning_rate": 6.79844364822268e-06,
777
+ "loss": 0.2194,
778
+ "step": 96
779
+ },
780
+ {
781
+ "epoch": 3.2016806722689077,
782
+ "eval_loss": 0.36906442046165466,
783
+ "eval_runtime": 12.0127,
784
+ "eval_samples_per_second": 2.081,
785
+ "eval_steps_per_second": 0.583,
786
+ "step": 96
787
+ },
788
+ {
789
+ "epoch": 3.235294117647059,
790
+ "grad_norm": 2.3070523738861084,
791
+ "learning_rate": 6.732244757573619e-06,
792
+ "loss": 0.2882,
793
+ "step": 97
794
+ },
795
+ {
796
+ "epoch": 3.26890756302521,
797
+ "grad_norm": 1.7963759899139404,
798
+ "learning_rate": 6.665698973710289e-06,
799
+ "loss": 0.1729,
800
+ "step": 98
801
+ },
802
+ {
803
+ "epoch": 3.302521008403361,
804
+ "grad_norm": 2.02447772026062,
805
+ "learning_rate": 6.598819622856227e-06,
806
+ "loss": 0.2463,
807
+ "step": 99
808
+ },
809
+ {
810
+ "epoch": 3.3361344537815127,
811
+ "grad_norm": 1.7601453065872192,
812
+ "learning_rate": 6.531620098033919e-06,
813
+ "loss": 0.2725,
814
+ "step": 100
815
+ },
816
+ {
817
+ "epoch": 3.369747899159664,
818
+ "grad_norm": 2.4182164669036865,
819
+ "learning_rate": 6.464113856382752e-06,
820
+ "loss": 0.2115,
821
+ "step": 101
822
+ },
823
+ {
824
+ "epoch": 3.403361344537815,
825
+ "grad_norm": 2.505795955657959,
826
+ "learning_rate": 6.396314416464151e-06,
827
+ "loss": 0.4502,
828
+ "step": 102
829
+ },
830
+ {
831
+ "epoch": 3.4369747899159666,
832
+ "grad_norm": 1.630191683769226,
833
+ "learning_rate": 6.328235355554382e-06,
834
+ "loss": 0.103,
835
+ "step": 103
836
+ },
837
+ {
838
+ "epoch": 3.4705882352941178,
839
+ "grad_norm": 1.4123270511627197,
840
+ "learning_rate": 6.259890306925627e-06,
841
+ "loss": 0.1172,
842
+ "step": 104
843
+ },
844
+ {
845
+ "epoch": 3.4705882352941178,
846
+ "eval_loss": 0.2801525294780731,
847
+ "eval_runtime": 12.0227,
848
+ "eval_samples_per_second": 2.079,
849
+ "eval_steps_per_second": 0.582,
850
+ "step": 104
851
+ },
852
+ {
853
+ "epoch": 3.504201680672269,
854
+ "grad_norm": 1.7171785831451416,
855
+ "learning_rate": 6.191292957115825e-06,
856
+ "loss": 0.2991,
857
+ "step": 105
858
+ },
859
+ {
860
+ "epoch": 3.53781512605042,
861
+ "grad_norm": 1.4823782444000244,
862
+ "learning_rate": 6.122457043187863e-06,
863
+ "loss": 0.216,
864
+ "step": 106
865
+ },
866
+ {
867
+ "epoch": 3.571428571428571,
868
+ "grad_norm": 2.7622790336608887,
869
+ "learning_rate": 6.053396349978632e-06,
870
+ "loss": 0.1453,
871
+ "step": 107
872
+ },
873
+ {
874
+ "epoch": 3.6050420168067228,
875
+ "grad_norm": 2.2422022819519043,
876
+ "learning_rate": 5.984124707338528e-06,
877
+ "loss": 0.0875,
878
+ "step": 108
879
+ },
880
+ {
881
+ "epoch": 3.638655462184874,
882
+ "grad_norm": 1.8057119846343994,
883
+ "learning_rate": 5.914655987361934e-06,
884
+ "loss": 0.2743,
885
+ "step": 109
886
+ },
887
+ {
888
+ "epoch": 3.6722689075630255,
889
+ "grad_norm": 1.2743725776672363,
890
+ "learning_rate": 5.8450041016092465e-06,
891
+ "loss": 0.2001,
892
+ "step": 110
893
+ },
894
+ {
895
+ "epoch": 3.7058823529411766,
896
+ "grad_norm": 2.135080575942993,
897
+ "learning_rate": 5.77518299832099e-06,
898
+ "loss": 0.2931,
899
+ "step": 111
900
+ },
901
+ {
902
+ "epoch": 3.7394957983193278,
903
+ "grad_norm": 2.7830662727355957,
904
+ "learning_rate": 5.705206659624597e-06,
905
+ "loss": 0.0739,
906
+ "step": 112
907
+ },
908
+ {
909
+ "epoch": 3.7394957983193278,
910
+ "eval_loss": 0.1947932094335556,
911
+ "eval_runtime": 12.0169,
912
+ "eval_samples_per_second": 2.08,
913
+ "eval_steps_per_second": 0.583,
914
+ "step": 112
915
+ },
916
+ {
917
+ "epoch": 3.773109243697479,
918
+ "grad_norm": 2.2503886222839355,
919
+ "learning_rate": 5.635089098734394e-06,
920
+ "loss": 0.1452,
921
+ "step": 113
922
+ },
923
+ {
924
+ "epoch": 3.80672268907563,
925
+ "grad_norm": 1.5595289468765259,
926
+ "learning_rate": 5.564844357145365e-06,
927
+ "loss": 0.0696,
928
+ "step": 114
929
+ },
930
+ {
931
+ "epoch": 3.8403361344537816,
932
+ "grad_norm": 1.9559892416000366,
933
+ "learning_rate": 5.49448650182125e-06,
934
+ "loss": 0.1231,
935
+ "step": 115
936
+ },
937
+ {
938
+ "epoch": 3.8739495798319328,
939
+ "grad_norm": 1.3151509761810303,
940
+ "learning_rate": 5.4240296223775465e-06,
941
+ "loss": 0.0796,
942
+ "step": 116
943
+ },
944
+ {
945
+ "epoch": 3.907563025210084,
946
+ "grad_norm": 2.6869540214538574,
947
+ "learning_rate": 5.353487828259973e-06,
948
+ "loss": 0.1171,
949
+ "step": 117
950
+ },
951
+ {
952
+ "epoch": 3.9411764705882355,
953
+ "grad_norm": 3.4072158336639404,
954
+ "learning_rate": 5.282875245918963e-06,
955
+ "loss": 0.2115,
956
+ "step": 118
957
+ },
958
+ {
959
+ "epoch": 3.9747899159663866,
960
+ "grad_norm": 2.99674916267395,
961
+ "learning_rate": 5.212206015980742e-06,
962
+ "loss": 0.1756,
963
+ "step": 119
964
+ },
965
+ {
966
+ "epoch": 4.0,
967
+ "grad_norm": 1.7564973831176758,
968
+ "learning_rate": 5.141494290415592e-06,
969
+ "loss": 0.1524,
970
+ "step": 120
971
+ },
972
+ {
973
+ "epoch": 4.0,
974
+ "eval_loss": 0.14572814106941223,
975
+ "eval_runtime": 12.0344,
976
+ "eval_samples_per_second": 2.077,
977
+ "eval_steps_per_second": 0.582,
978
+ "step": 120
979
+ },
980
+ {
981
+ "epoch": 4.033613445378151,
982
+ "grad_norm": 1.6185134649276733,
983
+ "learning_rate": 5.070754229703811e-06,
984
+ "loss": 0.2036,
985
+ "step": 121
986
+ },
987
+ {
988
+ "epoch": 4.067226890756302,
989
+ "grad_norm": 1.89780855178833,
990
+ "learning_rate": 5e-06,
991
+ "loss": 0.1084,
992
+ "step": 122
993
+ },
994
+ {
995
+ "epoch": 4.100840336134453,
996
+ "grad_norm": 1.0683470964431763,
997
+ "learning_rate": 4.929245770296191e-06,
998
+ "loss": 0.024,
999
+ "step": 123
1000
+ },
1001
+ {
1002
+ "epoch": 4.1344537815126055,
1003
+ "grad_norm": 1.3199543952941895,
1004
+ "learning_rate": 4.85850570958441e-06,
1005
+ "loss": 0.0721,
1006
+ "step": 124
1007
+ },
1008
+ {
1009
+ "epoch": 4.168067226890757,
1010
+ "grad_norm": 1.3227624893188477,
1011
+ "learning_rate": 4.78779398401926e-06,
1012
+ "loss": 0.1053,
1013
+ "step": 125
1014
+ },
1015
+ {
1016
+ "epoch": 4.201680672268908,
1017
+ "grad_norm": 0.9929068684577942,
1018
+ "learning_rate": 4.717124754081038e-06,
1019
+ "loss": 0.0404,
1020
+ "step": 126
1021
+ },
1022
+ {
1023
+ "epoch": 4.235294117647059,
1024
+ "grad_norm": 2.746427536010742,
1025
+ "learning_rate": 4.646512171740028e-06,
1026
+ "loss": 0.1037,
1027
+ "step": 127
1028
+ },
1029
+ {
1030
+ "epoch": 4.26890756302521,
1031
+ "grad_norm": 1.6636719703674316,
1032
+ "learning_rate": 4.575970377622456e-06,
1033
+ "loss": 0.0444,
1034
+ "step": 128
1035
+ },
1036
+ {
1037
+ "epoch": 4.26890756302521,
1038
+ "eval_loss": 0.1125473603606224,
1039
+ "eval_runtime": 12.0488,
1040
+ "eval_samples_per_second": 2.075,
1041
+ "eval_steps_per_second": 0.581,
1042
+ "step": 128
1043
+ },
1044
+ {
1045
+ "epoch": 4.302521008403361,
1046
+ "grad_norm": 1.1535725593566895,
1047
+ "learning_rate": 4.505513498178752e-06,
1048
+ "loss": 0.0378,
1049
+ "step": 129
1050
+ },
1051
+ {
1052
+ "epoch": 4.336134453781512,
1053
+ "grad_norm": 1.7697710990905762,
1054
+ "learning_rate": 4.435155642854637e-06,
1055
+ "loss": 0.0869,
1056
+ "step": 130
1057
+ },
1058
+ {
1059
+ "epoch": 4.369747899159664,
1060
+ "grad_norm": 0.9928828477859497,
1061
+ "learning_rate": 4.364910901265607e-06,
1062
+ "loss": 0.0737,
1063
+ "step": 131
1064
+ },
1065
+ {
1066
+ "epoch": 4.4033613445378155,
1067
+ "grad_norm": 1.6332063674926758,
1068
+ "learning_rate": 4.294793340375405e-06,
1069
+ "loss": 0.1098,
1070
+ "step": 132
1071
+ },
1072
+ {
1073
+ "epoch": 4.436974789915967,
1074
+ "grad_norm": 2.2281079292297363,
1075
+ "learning_rate": 4.224817001679011e-06,
1076
+ "loss": 0.0657,
1077
+ "step": 133
1078
+ },
1079
+ {
1080
+ "epoch": 4.470588235294118,
1081
+ "grad_norm": 3.8611080646514893,
1082
+ "learning_rate": 4.154995898390756e-06,
1083
+ "loss": 0.1013,
1084
+ "step": 134
1085
+ },
1086
+ {
1087
+ "epoch": 4.504201680672269,
1088
+ "grad_norm": 0.7134477496147156,
1089
+ "learning_rate": 4.085344012638067e-06,
1090
+ "loss": 0.0105,
1091
+ "step": 135
1092
+ },
1093
+ {
1094
+ "epoch": 4.53781512605042,
1095
+ "grad_norm": 3.5929417610168457,
1096
+ "learning_rate": 4.015875292661474e-06,
1097
+ "loss": 0.1385,
1098
+ "step": 136
1099
+ },
1100
+ {
1101
+ "epoch": 4.53781512605042,
1102
+ "eval_loss": 0.0758795514702797,
1103
+ "eval_runtime": 12.0325,
1104
+ "eval_samples_per_second": 2.078,
1105
+ "eval_steps_per_second": 0.582,
1106
+ "step": 136
1107
+ },
1108
+ {
1109
+ "epoch": 4.571428571428571,
1110
+ "grad_norm": 1.6059097051620483,
1111
+ "learning_rate": 3.94660365002137e-06,
1112
+ "loss": 0.0688,
1113
+ "step": 137
1114
+ },
1115
+ {
1116
+ "epoch": 4.605042016806722,
1117
+ "grad_norm": 1.931578278541565,
1118
+ "learning_rate": 3.877542956812137e-06,
1119
+ "loss": 0.061,
1120
+ "step": 138
1121
+ },
1122
+ {
1123
+ "epoch": 4.6386554621848735,
1124
+ "grad_norm": 4.694330215454102,
1125
+ "learning_rate": 3.808707042884176e-06,
1126
+ "loss": 0.0645,
1127
+ "step": 139
1128
+ },
1129
+ {
1130
+ "epoch": 4.6722689075630255,
1131
+ "grad_norm": 1.5269956588745117,
1132
+ "learning_rate": 3.7401096930743753e-06,
1133
+ "loss": 0.0695,
1134
+ "step": 140
1135
+ },
1136
+ {
1137
+ "epoch": 4.705882352941177,
1138
+ "grad_norm": 1.7759701013565063,
1139
+ "learning_rate": 3.6717646444456196e-06,
1140
+ "loss": 0.0327,
1141
+ "step": 141
1142
+ },
1143
+ {
1144
+ "epoch": 4.739495798319328,
1145
+ "grad_norm": 1.899479627609253,
1146
+ "learning_rate": 3.60368558353585e-06,
1147
+ "loss": 0.0428,
1148
+ "step": 142
1149
+ },
1150
+ {
1151
+ "epoch": 4.773109243697479,
1152
+ "grad_norm": 1.7261422872543335,
1153
+ "learning_rate": 3.5358861436172487e-06,
1154
+ "loss": 0.0628,
1155
+ "step": 143
1156
+ },
1157
+ {
1158
+ "epoch": 4.80672268907563,
1159
+ "grad_norm": 3.8707656860351562,
1160
+ "learning_rate": 3.4683799019660834e-06,
1161
+ "loss": 0.0591,
1162
+ "step": 144
1163
+ },
1164
+ {
1165
+ "epoch": 4.80672268907563,
1166
+ "eval_loss": 0.05604570358991623,
1167
+ "eval_runtime": 12.0383,
1168
+ "eval_samples_per_second": 2.077,
1169
+ "eval_steps_per_second": 0.581,
1170
+ "step": 144
1171
+ },
1172
+ {
1173
+ "epoch": 4.840336134453781,
1174
+ "grad_norm": 0.8072419762611389,
1175
+ "learning_rate": 3.401180377143774e-06,
1176
+ "loss": 0.0301,
1177
+ "step": 145
1178
+ },
1179
+ {
1180
+ "epoch": 4.873949579831933,
1181
+ "grad_norm": 0.8352177739143372,
1182
+ "learning_rate": 3.3343010262897125e-06,
1183
+ "loss": 0.0288,
1184
+ "step": 146
1185
+ },
1186
+ {
1187
+ "epoch": 4.907563025210084,
1188
+ "grad_norm": 2.471827745437622,
1189
+ "learning_rate": 3.2677552424263836e-06,
1190
+ "loss": 0.0198,
1191
+ "step": 147
1192
+ },
1193
+ {
1194
+ "epoch": 4.9411764705882355,
1195
+ "grad_norm": 1.5473682880401611,
1196
+ "learning_rate": 3.2015563517773214e-06,
1197
+ "loss": 0.0546,
1198
+ "step": 148
1199
+ },
1200
+ {
1201
+ "epoch": 4.974789915966387,
1202
+ "grad_norm": 1.4012079238891602,
1203
+ "learning_rate": 3.1357176110984578e-06,
1204
+ "loss": 0.033,
1205
+ "step": 149
1206
+ },
1207
+ {
1208
+ "epoch": 5.0,
1209
+ "grad_norm": 3.0382285118103027,
1210
+ "learning_rate": 3.070252205023356e-06,
1211
+ "loss": 0.0403,
1212
+ "step": 150
1213
+ },
1214
+ {
1215
+ "epoch": 5.033613445378151,
1216
+ "grad_norm": 0.7604548335075378,
1217
+ "learning_rate": 3.0051732434229185e-06,
1218
+ "loss": 0.014,
1219
+ "step": 151
1220
+ },
1221
+ {
1222
+ "epoch": 5.067226890756302,
1223
+ "grad_norm": 1.101543664932251,
1224
+ "learning_rate": 2.9404937587800374e-06,
1225
+ "loss": 0.0252,
1226
+ "step": 152
1227
+ },
1228
+ {
1229
+ "epoch": 5.067226890756302,
1230
+ "eval_loss": 0.04598259553313255,
1231
+ "eval_runtime": 12.0363,
1232
+ "eval_samples_per_second": 2.077,
1233
+ "eval_steps_per_second": 0.582,
1234
+ "step": 152
1235
+ },
1236
+ {
1237
+ "epoch": 5.100840336134453,
1238
+ "grad_norm": 1.4875141382217407,
1239
+ "learning_rate": 2.8762267035797607e-06,
1240
+ "loss": 0.0412,
1241
+ "step": 153
1242
+ },
1243
+ {
1244
+ "epoch": 5.1344537815126055,
1245
+ "grad_norm": 0.619445264339447,
1246
+ "learning_rate": 2.8123849477154808e-06,
1247
+ "loss": 0.0054,
1248
+ "step": 154
1249
+ },
1250
+ {
1251
+ "epoch": 5.168067226890757,
1252
+ "grad_norm": 1.1871784925460815,
1253
+ "learning_rate": 2.748981275911633e-06,
1254
+ "loss": 0.0413,
1255
+ "step": 155
1256
+ },
1257
+ {
1258
+ "epoch": 5.201680672268908,
1259
+ "grad_norm": 0.40735936164855957,
1260
+ "learning_rate": 2.6860283851635067e-06,
1261
+ "loss": 0.0074,
1262
+ "step": 156
1263
+ },
1264
+ {
1265
+ "epoch": 5.235294117647059,
1266
+ "grad_norm": 0.5911487340927124,
1267
+ "learning_rate": 2.6235388821945497e-06,
1268
+ "loss": 0.0081,
1269
+ "step": 157
1270
+ },
1271
+ {
1272
+ "epoch": 5.26890756302521,
1273
+ "grad_norm": 1.218485951423645,
1274
+ "learning_rate": 2.5615252809318287e-06,
1275
+ "loss": 0.0305,
1276
+ "step": 158
1277
+ },
1278
+ {
1279
+ "epoch": 5.302521008403361,
1280
+ "grad_norm": 1.8561826944351196,
1281
+ "learning_rate": 2.5000000000000015e-06,
1282
+ "loss": 0.0281,
1283
+ "step": 159
1284
+ },
1285
+ {
1286
+ "epoch": 5.336134453781512,
1287
+ "grad_norm": 0.45041966438293457,
1288
+ "learning_rate": 2.4389753602344298e-06,
1289
+ "loss": 0.0066,
1290
+ "step": 160
1291
+ },
1292
+ {
1293
+ "epoch": 5.336134453781512,
1294
+ "eval_loss": 0.03697740659117699,
1295
+ "eval_runtime": 12.0402,
1296
+ "eval_samples_per_second": 2.076,
1297
+ "eval_steps_per_second": 0.581,
1298
+ "step": 160
1299
+ },
1300
+ {
1301
+ "epoch": 5.369747899159664,
1302
+ "grad_norm": 1.5783069133758545,
1303
+ "learning_rate": 2.3784635822138424e-06,
1304
+ "loss": 0.026,
1305
+ "step": 161
1306
+ },
1307
+ {
1308
+ "epoch": 5.4033613445378155,
1309
+ "grad_norm": 1.163095474243164,
1310
+ "learning_rate": 2.318476783813088e-06,
1311
+ "loss": 0.0235,
1312
+ "step": 162
1313
+ },
1314
+ {
1315
+ "epoch": 5.436974789915967,
1316
+ "grad_norm": 0.9163492918014526,
1317
+ "learning_rate": 2.2590269777764516e-06,
1318
+ "loss": 0.0379,
1319
+ "step": 163
1320
+ },
1321
+ {
1322
+ "epoch": 5.470588235294118,
1323
+ "grad_norm": 0.6782473921775818,
1324
+ "learning_rate": 2.2001260693120236e-06,
1325
+ "loss": 0.0232,
1326
+ "step": 164
1327
+ },
1328
+ {
1329
+ "epoch": 5.504201680672269,
1330
+ "grad_norm": 0.7572933435440063,
1331
+ "learning_rate": 2.141785853707607e-06,
1332
+ "loss": 0.0201,
1333
+ "step": 165
1334
+ },
1335
+ {
1336
+ "epoch": 5.53781512605042,
1337
+ "grad_norm": 0.5534552335739136,
1338
+ "learning_rate": 2.0840180139686333e-06,
1339
+ "loss": 0.0159,
1340
+ "step": 166
1341
+ },
1342
+ {
1343
+ "epoch": 5.571428571428571,
1344
+ "grad_norm": 0.6240038275718689,
1345
+ "learning_rate": 2.0268341184785674e-06,
1346
+ "loss": 0.0127,
1347
+ "step": 167
1348
+ },
1349
+ {
1350
+ "epoch": 5.605042016806722,
1351
+ "grad_norm": 0.8554280400276184,
1352
+ "learning_rate": 1.9702456186822595e-06,
1353
+ "loss": 0.023,
1354
+ "step": 168
1355
+ },
1356
+ {
1357
+ "epoch": 5.605042016806722,
1358
+ "eval_loss": 0.025182316079735756,
1359
+ "eval_runtime": 12.0618,
1360
+ "eval_samples_per_second": 2.073,
1361
+ "eval_steps_per_second": 0.58,
1362
+ "step": 168
1363
+ },
1364
+ {
1365
+ "epoch": 5.6386554621848735,
1366
+ "grad_norm": 0.4920494556427002,
1367
+ "learning_rate": 1.9142638467927254e-06,
1368
+ "loss": 0.008,
1369
+ "step": 169
1370
+ },
1371
+ {
1372
+ "epoch": 5.6722689075630255,
1373
+ "grad_norm": 0.2633163332939148,
1374
+ "learning_rate": 1.8589000135217882e-06,
1375
+ "loss": 0.0051,
1376
+ "step": 170
1377
+ },
1378
+ {
1379
+ "epoch": 5.705882352941177,
1380
+ "grad_norm": 0.4242977797985077,
1381
+ "learning_rate": 1.8041652058350768e-06,
1382
+ "loss": 0.0116,
1383
+ "step": 171
1384
+ },
1385
+ {
1386
+ "epoch": 5.739495798319328,
1387
+ "grad_norm": 0.42241370677948,
1388
+ "learning_rate": 1.7500703847317663e-06,
1389
+ "loss": 0.0123,
1390
+ "step": 172
1391
+ },
1392
+ {
1393
+ "epoch": 5.773109243697479,
1394
+ "grad_norm": 0.2185809314250946,
1395
+ "learning_rate": 1.6966263830495939e-06,
1396
+ "loss": 0.0052,
1397
+ "step": 173
1398
+ },
1399
+ {
1400
+ "epoch": 5.80672268907563,
1401
+ "grad_norm": 0.2527461349964142,
1402
+ "learning_rate": 1.6438439032954857e-06,
1403
+ "loss": 0.0042,
1404
+ "step": 174
1405
+ }
1406
+ ],
1407
+ "logging_steps": 1,
1408
+ "max_steps": 232,
1409
+ "num_input_tokens_seen": 0,
1410
+ "num_train_epochs": 8,
1411
+ "save_steps": 29,
1412
+ "stateful_callbacks": {
1413
+ "TrainerControl": {
1414
+ "args": {
1415
+ "should_epoch_stop": false,
1416
+ "should_evaluate": false,
1417
+ "should_log": false,
1418
+ "should_save": true,
1419
+ "should_training_stop": false
1420
+ },
1421
+ "attributes": {}
1422
+ }
1423
+ },
1424
+ "total_flos": 2.3847936907542528e+17,
1425
+ "train_batch_size": 2,
1426
+ "trial_name": null,
1427
+ "trial_params": null
1428
+ }
checkpoint-174/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85f8f9b09204e1090ec2369a8805ad857a677dac1a4ca5d19752c2e11cd99114
3
+ size 7505
checkpoint-203/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /dpool/Meta-Llama-3.1-8B-Instruct-abliterated
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
checkpoint-203/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/dpool/Meta-Llama-3.1-8B-Instruct-abliterated",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": null,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 16,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "k_proj",
29
+ "q_proj",
30
+ "down_proj",
31
+ "o_proj",
32
+ "v_proj",
33
+ "up_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-203/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb727d0baa67ce624d31404aa7d08fe1b3d22bb0803dc227dbeacaabbccbc14
3
+ size 167832240
checkpoint-203/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bca54679ae7e3020560c58e2ab91174a8dd7193f742e34c0d749c4c10b0f52b
3
+ size 335945763
checkpoint-203/pytorch_model_fsdp.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f80aaff5df8aae32f9532e6510dddade30d9ab66bcf01bbdff6d8fd55d05f6c2
3
+ size 167939969
checkpoint-203/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:946b20ccae5cc7505d33498e01e5a06d60cc338801a396c1b81f36238f1be329
3
+ size 14917
checkpoint-203/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466c29719d4757f0e4597d2dd336041e8c37fe898267a6a8802f14780619ce27
3
+ size 14917
checkpoint-203/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:473ff78f69464127d7c06305629f8bf609b4e064be718572a8f613676519ef01
3
+ size 1465
checkpoint-203/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-203/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-203/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizer"
2064
+ }
checkpoint-203/trainer_state.json ADDED
@@ -0,0 +1,1663 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 6.773109243697479,
6
+ "eval_steps": 8,
7
+ "global_step": 203,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.03361344537815126,
14
+ "grad_norm": 2.6346614360809326,
15
+ "learning_rate": 0.0,
16
+ "loss": 3.5587,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.03361344537815126,
21
+ "eval_loss": 3.4337246417999268,
22
+ "eval_runtime": 12.0401,
23
+ "eval_samples_per_second": 2.076,
24
+ "eval_steps_per_second": 0.581,
25
+ "step": 1
26
+ },
27
+ {
28
+ "epoch": 0.06722689075630252,
29
+ "grad_norm": 3.2896828651428223,
30
+ "learning_rate": 1.0000000000000002e-06,
31
+ "loss": 3.6974,
32
+ "step": 2
33
+ },
34
+ {
35
+ "epoch": 0.10084033613445378,
36
+ "grad_norm": 2.942761182785034,
37
+ "learning_rate": 2.0000000000000003e-06,
38
+ "loss": 3.7682,
39
+ "step": 3
40
+ },
41
+ {
42
+ "epoch": 0.13445378151260504,
43
+ "grad_norm": 3.322763442993164,
44
+ "learning_rate": 3e-06,
45
+ "loss": 4.1233,
46
+ "step": 4
47
+ },
48
+ {
49
+ "epoch": 0.16806722689075632,
50
+ "grad_norm": 2.542609214782715,
51
+ "learning_rate": 4.000000000000001e-06,
52
+ "loss": 3.7296,
53
+ "step": 5
54
+ },
55
+ {
56
+ "epoch": 0.20168067226890757,
57
+ "grad_norm": 2.8525142669677734,
58
+ "learning_rate": 5e-06,
59
+ "loss": 3.8537,
60
+ "step": 6
61
+ },
62
+ {
63
+ "epoch": 0.23529411764705882,
64
+ "grad_norm": 2.3698537349700928,
65
+ "learning_rate": 6e-06,
66
+ "loss": 3.648,
67
+ "step": 7
68
+ },
69
+ {
70
+ "epoch": 0.2689075630252101,
71
+ "grad_norm": 2.540416955947876,
72
+ "learning_rate": 7e-06,
73
+ "loss": 3.6702,
74
+ "step": 8
75
+ },
76
+ {
77
+ "epoch": 0.2689075630252101,
78
+ "eval_loss": 3.4260427951812744,
79
+ "eval_runtime": 12.0264,
80
+ "eval_samples_per_second": 2.079,
81
+ "eval_steps_per_second": 0.582,
82
+ "step": 8
83
+ },
84
+ {
85
+ "epoch": 0.3025210084033613,
86
+ "grad_norm": 2.424398422241211,
87
+ "learning_rate": 8.000000000000001e-06,
88
+ "loss": 3.3544,
89
+ "step": 9
90
+ },
91
+ {
92
+ "epoch": 0.33613445378151263,
93
+ "grad_norm": 3.290915012359619,
94
+ "learning_rate": 9e-06,
95
+ "loss": 3.9672,
96
+ "step": 10
97
+ },
98
+ {
99
+ "epoch": 0.3697478991596639,
100
+ "grad_norm": 2.8242039680480957,
101
+ "learning_rate": 1e-05,
102
+ "loss": 3.591,
103
+ "step": 11
104
+ },
105
+ {
106
+ "epoch": 0.40336134453781514,
107
+ "grad_norm": 2.9474833011627197,
108
+ "learning_rate": 9.999499358833745e-06,
109
+ "loss": 3.6958,
110
+ "step": 12
111
+ },
112
+ {
113
+ "epoch": 0.4369747899159664,
114
+ "grad_norm": 3.4582228660583496,
115
+ "learning_rate": 9.99799753559161e-06,
116
+ "loss": 3.99,
117
+ "step": 13
118
+ },
119
+ {
120
+ "epoch": 0.47058823529411764,
121
+ "grad_norm": 3.1884031295776367,
122
+ "learning_rate": 9.99549483102341e-06,
123
+ "loss": 3.8204,
124
+ "step": 14
125
+ },
126
+ {
127
+ "epoch": 0.5042016806722689,
128
+ "grad_norm": 2.423398017883301,
129
+ "learning_rate": 9.991991746311916e-06,
130
+ "loss": 3.0469,
131
+ "step": 15
132
+ },
133
+ {
134
+ "epoch": 0.5378151260504201,
135
+ "grad_norm": 3.3329102993011475,
136
+ "learning_rate": 9.9874889829725e-06,
137
+ "loss": 3.5802,
138
+ "step": 16
139
+ },
140
+ {
141
+ "epoch": 0.5378151260504201,
142
+ "eval_loss": 3.316091299057007,
143
+ "eval_runtime": 12.0143,
144
+ "eval_samples_per_second": 2.081,
145
+ "eval_steps_per_second": 0.583,
146
+ "step": 16
147
+ },
148
+ {
149
+ "epoch": 0.5714285714285714,
150
+ "grad_norm": 2.8659586906433105,
151
+ "learning_rate": 9.981987442712634e-06,
152
+ "loss": 3.0165,
153
+ "step": 17
154
+ },
155
+ {
156
+ "epoch": 0.6050420168067226,
157
+ "grad_norm": 3.4627182483673096,
158
+ "learning_rate": 9.97548822725133e-06,
159
+ "loss": 3.9333,
160
+ "step": 18
161
+ },
162
+ {
163
+ "epoch": 0.6386554621848739,
164
+ "grad_norm": 3.3491547107696533,
165
+ "learning_rate": 9.967992638098517e-06,
166
+ "loss": 3.5018,
167
+ "step": 19
168
+ },
169
+ {
170
+ "epoch": 0.6722689075630253,
171
+ "grad_norm": 2.7486977577209473,
172
+ "learning_rate": 9.959502176294384e-06,
173
+ "loss": 2.9875,
174
+ "step": 20
175
+ },
176
+ {
177
+ "epoch": 0.7058823529411765,
178
+ "grad_norm": 2.9063732624053955,
179
+ "learning_rate": 9.950018542108818e-06,
180
+ "loss": 3.0974,
181
+ "step": 21
182
+ },
183
+ {
184
+ "epoch": 0.7394957983193278,
185
+ "grad_norm": 3.2880260944366455,
186
+ "learning_rate": 9.939543634700891e-06,
187
+ "loss": 3.141,
188
+ "step": 22
189
+ },
190
+ {
191
+ "epoch": 0.773109243697479,
192
+ "grad_norm": 3.086613416671753,
193
+ "learning_rate": 9.928079551738542e-06,
194
+ "loss": 3.0282,
195
+ "step": 23
196
+ },
197
+ {
198
+ "epoch": 0.8067226890756303,
199
+ "grad_norm": 3.7129077911376953,
200
+ "learning_rate": 9.915628588978522e-06,
201
+ "loss": 3.2421,
202
+ "step": 24
203
+ },
204
+ {
205
+ "epoch": 0.8067226890756303,
206
+ "eval_loss": 3.0272111892700195,
207
+ "eval_runtime": 12.0429,
208
+ "eval_samples_per_second": 2.076,
209
+ "eval_steps_per_second": 0.581,
210
+ "step": 24
211
+ },
212
+ {
213
+ "epoch": 0.8403361344537815,
214
+ "grad_norm": 4.430984973907471,
215
+ "learning_rate": 9.902193239806634e-06,
216
+ "loss": 3.2481,
217
+ "step": 25
218
+ },
219
+ {
220
+ "epoch": 0.8739495798319328,
221
+ "grad_norm": 3.6558125019073486,
222
+ "learning_rate": 9.887776194738433e-06,
223
+ "loss": 2.8553,
224
+ "step": 26
225
+ },
226
+ {
227
+ "epoch": 0.907563025210084,
228
+ "grad_norm": 4.079296112060547,
229
+ "learning_rate": 9.872380340880416e-06,
230
+ "loss": 3.0176,
231
+ "step": 27
232
+ },
233
+ {
234
+ "epoch": 0.9411764705882353,
235
+ "grad_norm": 4.859598159790039,
236
+ "learning_rate": 9.856008761351882e-06,
237
+ "loss": 2.7999,
238
+ "step": 28
239
+ },
240
+ {
241
+ "epoch": 0.9747899159663865,
242
+ "grad_norm": 4.5133957862854,
243
+ "learning_rate": 9.838664734667496e-06,
244
+ "loss": 2.933,
245
+ "step": 29
246
+ },
247
+ {
248
+ "epoch": 1.0,
249
+ "grad_norm": 4.612884044647217,
250
+ "learning_rate": 9.820351734080754e-06,
251
+ "loss": 2.5651,
252
+ "step": 30
253
+ },
254
+ {
255
+ "epoch": 1.0336134453781514,
256
+ "grad_norm": 4.931149959564209,
257
+ "learning_rate": 9.801073426888447e-06,
258
+ "loss": 2.5854,
259
+ "step": 31
260
+ },
261
+ {
262
+ "epoch": 1.0672268907563025,
263
+ "grad_norm": 5.286943435668945,
264
+ "learning_rate": 9.780833673696255e-06,
265
+ "loss": 2.322,
266
+ "step": 32
267
+ },
268
+ {
269
+ "epoch": 1.0672268907563025,
270
+ "eval_loss": 2.48122239112854,
271
+ "eval_runtime": 12.0206,
272
+ "eval_samples_per_second": 2.08,
273
+ "eval_steps_per_second": 0.582,
274
+ "step": 32
275
+ },
276
+ {
277
+ "epoch": 1.1008403361344539,
278
+ "grad_norm": 4.670954704284668,
279
+ "learning_rate": 9.759636527645633e-06,
280
+ "loss": 2.4513,
281
+ "step": 33
282
+ },
283
+ {
284
+ "epoch": 1.134453781512605,
285
+ "grad_norm": 4.8246169090271,
286
+ "learning_rate": 9.737486233602149e-06,
287
+ "loss": 2.1937,
288
+ "step": 34
289
+ },
290
+ {
291
+ "epoch": 1.1680672268907564,
292
+ "grad_norm": 4.8713836669921875,
293
+ "learning_rate": 9.714387227305422e-06,
294
+ "loss": 2.3228,
295
+ "step": 35
296
+ },
297
+ {
298
+ "epoch": 1.2016806722689075,
299
+ "grad_norm": 5.048571586608887,
300
+ "learning_rate": 9.69034413448083e-06,
301
+ "loss": 1.9506,
302
+ "step": 36
303
+ },
304
+ {
305
+ "epoch": 1.2352941176470589,
306
+ "grad_norm": 5.047688007354736,
307
+ "learning_rate": 9.665361769913187e-06,
308
+ "loss": 2.2959,
309
+ "step": 37
310
+ },
311
+ {
312
+ "epoch": 1.26890756302521,
313
+ "grad_norm": 5.056053161621094,
314
+ "learning_rate": 9.639445136482549e-06,
315
+ "loss": 2.0905,
316
+ "step": 38
317
+ },
318
+ {
319
+ "epoch": 1.3025210084033614,
320
+ "grad_norm": 3.506237506866455,
321
+ "learning_rate": 9.612599424162344e-06,
322
+ "loss": 1.9687,
323
+ "step": 39
324
+ },
325
+ {
326
+ "epoch": 1.3361344537815127,
327
+ "grad_norm": 4.794375896453857,
328
+ "learning_rate": 9.584830008980068e-06,
329
+ "loss": 1.9774,
330
+ "step": 40
331
+ },
332
+ {
333
+ "epoch": 1.3361344537815127,
334
+ "eval_loss": 1.870819091796875,
335
+ "eval_runtime": 12.0354,
336
+ "eval_samples_per_second": 2.077,
337
+ "eval_steps_per_second": 0.582,
338
+ "step": 40
339
+ },
340
+ {
341
+ "epoch": 1.3697478991596639,
342
+ "grad_norm": 5.138720512390137,
343
+ "learning_rate": 9.55614245194068e-06,
344
+ "loss": 1.6505,
345
+ "step": 41
346
+ },
347
+ {
348
+ "epoch": 1.403361344537815,
349
+ "grad_norm": 3.800957679748535,
350
+ "learning_rate": 9.526542497912984e-06,
351
+ "loss": 1.8317,
352
+ "step": 42
353
+ },
354
+ {
355
+ "epoch": 1.4369747899159664,
356
+ "grad_norm": 4.458896636962891,
357
+ "learning_rate": 9.496036074479184e-06,
358
+ "loss": 1.6714,
359
+ "step": 43
360
+ },
361
+ {
362
+ "epoch": 1.4705882352941178,
363
+ "grad_norm": 3.317945718765259,
364
+ "learning_rate": 9.464629290747844e-06,
365
+ "loss": 1.825,
366
+ "step": 44
367
+ },
368
+ {
369
+ "epoch": 1.504201680672269,
370
+ "grad_norm": 3.235334634780884,
371
+ "learning_rate": 9.432328436130493e-06,
372
+ "loss": 1.5301,
373
+ "step": 45
374
+ },
375
+ {
376
+ "epoch": 1.53781512605042,
377
+ "grad_norm": 3.7489278316497803,
378
+ "learning_rate": 9.399139979082148e-06,
379
+ "loss": 1.5717,
380
+ "step": 46
381
+ },
382
+ {
383
+ "epoch": 1.5714285714285714,
384
+ "grad_norm": 2.814138889312744,
385
+ "learning_rate": 9.365070565805941e-06,
386
+ "loss": 1.6659,
387
+ "step": 47
388
+ },
389
+ {
390
+ "epoch": 1.6050420168067228,
391
+ "grad_norm": 3.219665765762329,
392
+ "learning_rate": 9.330127018922195e-06,
393
+ "loss": 1.5103,
394
+ "step": 48
395
+ },
396
+ {
397
+ "epoch": 1.6050420168067228,
398
+ "eval_loss": 1.3871335983276367,
399
+ "eval_runtime": 12.0361,
400
+ "eval_samples_per_second": 2.077,
401
+ "eval_steps_per_second": 0.582,
402
+ "step": 48
403
+ },
404
+ {
405
+ "epoch": 1.638655462184874,
406
+ "grad_norm": 3.621195077896118,
407
+ "learning_rate": 9.294316336102132e-06,
408
+ "loss": 1.4593,
409
+ "step": 49
410
+ },
411
+ {
412
+ "epoch": 1.6722689075630253,
413
+ "grad_norm": 3.5364909172058105,
414
+ "learning_rate": 9.257645688666557e-06,
415
+ "loss": 1.4013,
416
+ "step": 50
417
+ },
418
+ {
419
+ "epoch": 1.7058823529411766,
420
+ "grad_norm": 2.968980073928833,
421
+ "learning_rate": 9.220122420149753e-06,
422
+ "loss": 1.4879,
423
+ "step": 51
424
+ },
425
+ {
426
+ "epoch": 1.7394957983193278,
427
+ "grad_norm": 2.562370777130127,
428
+ "learning_rate": 9.181754044828882e-06,
429
+ "loss": 1.3619,
430
+ "step": 52
431
+ },
432
+ {
433
+ "epoch": 1.773109243697479,
434
+ "grad_norm": 2.976408004760742,
435
+ "learning_rate": 9.142548246219212e-06,
436
+ "loss": 1.2078,
437
+ "step": 53
438
+ },
439
+ {
440
+ "epoch": 1.8067226890756303,
441
+ "grad_norm": 3.2309634685516357,
442
+ "learning_rate": 9.102512875535439e-06,
443
+ "loss": 1.0231,
444
+ "step": 54
445
+ },
446
+ {
447
+ "epoch": 1.8403361344537816,
448
+ "grad_norm": 2.9703569412231445,
449
+ "learning_rate": 9.06165595011943e-06,
450
+ "loss": 1.5202,
451
+ "step": 55
452
+ },
453
+ {
454
+ "epoch": 1.8739495798319328,
455
+ "grad_norm": 3.620556354522705,
456
+ "learning_rate": 9.019985651834703e-06,
457
+ "loss": 1.1904,
458
+ "step": 56
459
+ },
460
+ {
461
+ "epoch": 1.8739495798319328,
462
+ "eval_loss": 1.0541609525680542,
463
+ "eval_runtime": 12.0294,
464
+ "eval_samples_per_second": 2.078,
465
+ "eval_steps_per_second": 0.582,
466
+ "step": 56
467
+ },
468
+ {
469
+ "epoch": 1.907563025210084,
470
+ "grad_norm": 2.8404018878936768,
471
+ "learning_rate": 8.97751032542795e-06,
472
+ "loss": 1.1275,
473
+ "step": 57
474
+ },
475
+ {
476
+ "epoch": 1.9411764705882353,
477
+ "grad_norm": 2.9330008029937744,
478
+ "learning_rate": 8.93423847685795e-06,
479
+ "loss": 1.2625,
480
+ "step": 58
481
+ },
482
+ {
483
+ "epoch": 1.9747899159663866,
484
+ "grad_norm": 3.747128963470459,
485
+ "learning_rate": 8.890178771592198e-06,
486
+ "loss": 1.0427,
487
+ "step": 59
488
+ },
489
+ {
490
+ "epoch": 2.0,
491
+ "grad_norm": 4.598628520965576,
492
+ "learning_rate": 8.845340032871584e-06,
493
+ "loss": 0.5982,
494
+ "step": 60
495
+ },
496
+ {
497
+ "epoch": 2.033613445378151,
498
+ "grad_norm": 2.659691333770752,
499
+ "learning_rate": 8.799731239943488e-06,
500
+ "loss": 1.0643,
501
+ "step": 61
502
+ },
503
+ {
504
+ "epoch": 2.0672268907563027,
505
+ "grad_norm": 3.448178768157959,
506
+ "learning_rate": 8.753361526263622e-06,
507
+ "loss": 0.8037,
508
+ "step": 62
509
+ },
510
+ {
511
+ "epoch": 2.100840336134454,
512
+ "grad_norm": 4.392441272735596,
513
+ "learning_rate": 8.706240177667003e-06,
514
+ "loss": 0.5474,
515
+ "step": 63
516
+ },
517
+ {
518
+ "epoch": 2.134453781512605,
519
+ "grad_norm": 3.435783624649048,
520
+ "learning_rate": 8.658376630508391e-06,
521
+ "loss": 1.0394,
522
+ "step": 64
523
+ },
524
+ {
525
+ "epoch": 2.134453781512605,
526
+ "eval_loss": 0.8591052889823914,
527
+ "eval_runtime": 12.0335,
528
+ "eval_samples_per_second": 2.078,
529
+ "eval_steps_per_second": 0.582,
530
+ "step": 64
531
+ },
532
+ {
533
+ "epoch": 2.168067226890756,
534
+ "grad_norm": 3.652780294418335,
535
+ "learning_rate": 8.609780469772623e-06,
536
+ "loss": 0.8207,
537
+ "step": 65
538
+ },
539
+ {
540
+ "epoch": 2.2016806722689077,
541
+ "grad_norm": 4.205479145050049,
542
+ "learning_rate": 8.56046142715513e-06,
543
+ "loss": 0.7293,
544
+ "step": 66
545
+ },
546
+ {
547
+ "epoch": 2.235294117647059,
548
+ "grad_norm": 4.328608512878418,
549
+ "learning_rate": 8.510429379113114e-06,
550
+ "loss": 1.1445,
551
+ "step": 67
552
+ },
553
+ {
554
+ "epoch": 2.26890756302521,
555
+ "grad_norm": 2.992579936981201,
556
+ "learning_rate": 8.459694344887732e-06,
557
+ "loss": 0.461,
558
+ "step": 68
559
+ },
560
+ {
561
+ "epoch": 2.302521008403361,
562
+ "grad_norm": 3.3023149967193604,
563
+ "learning_rate": 8.408266484497664e-06,
564
+ "loss": 0.9115,
565
+ "step": 69
566
+ },
567
+ {
568
+ "epoch": 2.3361344537815127,
569
+ "grad_norm": 3.0709333419799805,
570
+ "learning_rate": 8.356156096704516e-06,
571
+ "loss": 0.3745,
572
+ "step": 70
573
+ },
574
+ {
575
+ "epoch": 2.369747899159664,
576
+ "grad_norm": 3.3897287845611572,
577
+ "learning_rate": 8.303373616950408e-06,
578
+ "loss": 0.4913,
579
+ "step": 71
580
+ },
581
+ {
582
+ "epoch": 2.403361344537815,
583
+ "grad_norm": 3.306938886642456,
584
+ "learning_rate": 8.249929615268234e-06,
585
+ "loss": 0.5501,
586
+ "step": 72
587
+ },
588
+ {
589
+ "epoch": 2.403361344537815,
590
+ "eval_loss": 0.6722928881645203,
591
+ "eval_runtime": 12.0411,
592
+ "eval_samples_per_second": 2.076,
593
+ "eval_steps_per_second": 0.581,
594
+ "step": 72
595
+ },
596
+ {
597
+ "epoch": 2.4369747899159666,
598
+ "grad_norm": 3.504460334777832,
599
+ "learning_rate": 8.195834794164925e-06,
600
+ "loss": 1.0348,
601
+ "step": 73
602
+ },
603
+ {
604
+ "epoch": 2.4705882352941178,
605
+ "grad_norm": 3.0955419540405273,
606
+ "learning_rate": 8.141099986478212e-06,
607
+ "loss": 0.9719,
608
+ "step": 74
609
+ },
610
+ {
611
+ "epoch": 2.504201680672269,
612
+ "grad_norm": 3.5875039100646973,
613
+ "learning_rate": 8.085736153207277e-06,
614
+ "loss": 0.6814,
615
+ "step": 75
616
+ },
617
+ {
618
+ "epoch": 2.53781512605042,
619
+ "grad_norm": 3.203245162963867,
620
+ "learning_rate": 8.029754381317741e-06,
621
+ "loss": 0.9234,
622
+ "step": 76
623
+ },
624
+ {
625
+ "epoch": 2.571428571428571,
626
+ "grad_norm": 2.9670157432556152,
627
+ "learning_rate": 7.973165881521435e-06,
628
+ "loss": 0.6265,
629
+ "step": 77
630
+ },
631
+ {
632
+ "epoch": 2.6050420168067228,
633
+ "grad_norm": 3.2151577472686768,
634
+ "learning_rate": 7.915981986031367e-06,
635
+ "loss": 0.313,
636
+ "step": 78
637
+ },
638
+ {
639
+ "epoch": 2.638655462184874,
640
+ "grad_norm": 2.7305543422698975,
641
+ "learning_rate": 7.858214146292394e-06,
642
+ "loss": 0.4951,
643
+ "step": 79
644
+ },
645
+ {
646
+ "epoch": 2.6722689075630255,
647
+ "grad_norm": 3.675318717956543,
648
+ "learning_rate": 7.799873930687979e-06,
649
+ "loss": 0.2454,
650
+ "step": 80
651
+ },
652
+ {
653
+ "epoch": 2.6722689075630255,
654
+ "eval_loss": 0.536856472492218,
655
+ "eval_runtime": 12.0568,
656
+ "eval_samples_per_second": 2.074,
657
+ "eval_steps_per_second": 0.581,
658
+ "step": 80
659
+ },
660
+ {
661
+ "epoch": 2.7058823529411766,
662
+ "grad_norm": 1.8047897815704346,
663
+ "learning_rate": 7.74097302222355e-06,
664
+ "loss": 0.4276,
665
+ "step": 81
666
+ },
667
+ {
668
+ "epoch": 2.7394957983193278,
669
+ "grad_norm": 2.843857765197754,
670
+ "learning_rate": 7.681523216186912e-06,
671
+ "loss": 0.1704,
672
+ "step": 82
673
+ },
674
+ {
675
+ "epoch": 2.773109243697479,
676
+ "grad_norm": 2.3356502056121826,
677
+ "learning_rate": 7.621536417786159e-06,
678
+ "loss": 0.2967,
679
+ "step": 83
680
+ },
681
+ {
682
+ "epoch": 2.80672268907563,
683
+ "grad_norm": 2.3808438777923584,
684
+ "learning_rate": 7.5610246397655715e-06,
685
+ "loss": 0.2374,
686
+ "step": 84
687
+ },
688
+ {
689
+ "epoch": 2.8403361344537816,
690
+ "grad_norm": 2.5754661560058594,
691
+ "learning_rate": 7.500000000000001e-06,
692
+ "loss": 0.6951,
693
+ "step": 85
694
+ },
695
+ {
696
+ "epoch": 2.8739495798319328,
697
+ "grad_norm": 3.8589160442352295,
698
+ "learning_rate": 7.438474719068174e-06,
699
+ "loss": 0.3943,
700
+ "step": 86
701
+ },
702
+ {
703
+ "epoch": 2.907563025210084,
704
+ "grad_norm": 2.7497880458831787,
705
+ "learning_rate": 7.37646111780545e-06,
706
+ "loss": 0.3995,
707
+ "step": 87
708
+ },
709
+ {
710
+ "epoch": 2.9411764705882355,
711
+ "grad_norm": 3.4608285427093506,
712
+ "learning_rate": 7.313971614836496e-06,
713
+ "loss": 0.4499,
714
+ "step": 88
715
+ },
716
+ {
717
+ "epoch": 2.9411764705882355,
718
+ "eval_loss": 0.42864924669265747,
719
+ "eval_runtime": 12.0207,
720
+ "eval_samples_per_second": 2.08,
721
+ "eval_steps_per_second": 0.582,
722
+ "step": 88
723
+ },
724
+ {
725
+ "epoch": 2.9747899159663866,
726
+ "grad_norm": 3.7563107013702393,
727
+ "learning_rate": 7.251018724088367e-06,
728
+ "loss": 0.3587,
729
+ "step": 89
730
+ },
731
+ {
732
+ "epoch": 3.0,
733
+ "grad_norm": 2.986473798751831,
734
+ "learning_rate": 7.187615052284522e-06,
735
+ "loss": 0.2523,
736
+ "step": 90
737
+ },
738
+ {
739
+ "epoch": 3.033613445378151,
740
+ "grad_norm": 2.074615240097046,
741
+ "learning_rate": 7.12377329642024e-06,
742
+ "loss": 0.3245,
743
+ "step": 91
744
+ },
745
+ {
746
+ "epoch": 3.0672268907563027,
747
+ "grad_norm": 1.6591023206710815,
748
+ "learning_rate": 7.059506241219964e-06,
749
+ "loss": 0.404,
750
+ "step": 92
751
+ },
752
+ {
753
+ "epoch": 3.100840336134454,
754
+ "grad_norm": 2.0738601684570312,
755
+ "learning_rate": 6.994826756577082e-06,
756
+ "loss": 0.4466,
757
+ "step": 93
758
+ },
759
+ {
760
+ "epoch": 3.134453781512605,
761
+ "grad_norm": 1.8895370960235596,
762
+ "learning_rate": 6.9297477949766445e-06,
763
+ "loss": 0.1547,
764
+ "step": 94
765
+ },
766
+ {
767
+ "epoch": 3.168067226890756,
768
+ "grad_norm": 2.5287699699401855,
769
+ "learning_rate": 6.864282388901544e-06,
770
+ "loss": 0.5676,
771
+ "step": 95
772
+ },
773
+ {
774
+ "epoch": 3.2016806722689077,
775
+ "grad_norm": 2.2020397186279297,
776
+ "learning_rate": 6.79844364822268e-06,
777
+ "loss": 0.2194,
778
+ "step": 96
779
+ },
780
+ {
781
+ "epoch": 3.2016806722689077,
782
+ "eval_loss": 0.36906442046165466,
783
+ "eval_runtime": 12.0127,
784
+ "eval_samples_per_second": 2.081,
785
+ "eval_steps_per_second": 0.583,
786
+ "step": 96
787
+ },
788
+ {
789
+ "epoch": 3.235294117647059,
790
+ "grad_norm": 2.3070523738861084,
791
+ "learning_rate": 6.732244757573619e-06,
792
+ "loss": 0.2882,
793
+ "step": 97
794
+ },
795
+ {
796
+ "epoch": 3.26890756302521,
797
+ "grad_norm": 1.7963759899139404,
798
+ "learning_rate": 6.665698973710289e-06,
799
+ "loss": 0.1729,
800
+ "step": 98
801
+ },
802
+ {
803
+ "epoch": 3.302521008403361,
804
+ "grad_norm": 2.02447772026062,
805
+ "learning_rate": 6.598819622856227e-06,
806
+ "loss": 0.2463,
807
+ "step": 99
808
+ },
809
+ {
810
+ "epoch": 3.3361344537815127,
811
+ "grad_norm": 1.7601453065872192,
812
+ "learning_rate": 6.531620098033919e-06,
813
+ "loss": 0.2725,
814
+ "step": 100
815
+ },
816
+ {
817
+ "epoch": 3.369747899159664,
818
+ "grad_norm": 2.4182164669036865,
819
+ "learning_rate": 6.464113856382752e-06,
820
+ "loss": 0.2115,
821
+ "step": 101
822
+ },
823
+ {
824
+ "epoch": 3.403361344537815,
825
+ "grad_norm": 2.505795955657959,
826
+ "learning_rate": 6.396314416464151e-06,
827
+ "loss": 0.4502,
828
+ "step": 102
829
+ },
830
+ {
831
+ "epoch": 3.4369747899159666,
832
+ "grad_norm": 1.630191683769226,
833
+ "learning_rate": 6.328235355554382e-06,
834
+ "loss": 0.103,
835
+ "step": 103
836
+ },
837
+ {
838
+ "epoch": 3.4705882352941178,
839
+ "grad_norm": 1.4123270511627197,
840
+ "learning_rate": 6.259890306925627e-06,
841
+ "loss": 0.1172,
842
+ "step": 104
843
+ },
844
+ {
845
+ "epoch": 3.4705882352941178,
846
+ "eval_loss": 0.2801525294780731,
847
+ "eval_runtime": 12.0227,
848
+ "eval_samples_per_second": 2.079,
849
+ "eval_steps_per_second": 0.582,
850
+ "step": 104
851
+ },
852
+ {
853
+ "epoch": 3.504201680672269,
854
+ "grad_norm": 1.7171785831451416,
855
+ "learning_rate": 6.191292957115825e-06,
856
+ "loss": 0.2991,
857
+ "step": 105
858
+ },
859
+ {
860
+ "epoch": 3.53781512605042,
861
+ "grad_norm": 1.4823782444000244,
862
+ "learning_rate": 6.122457043187863e-06,
863
+ "loss": 0.216,
864
+ "step": 106
865
+ },
866
+ {
867
+ "epoch": 3.571428571428571,
868
+ "grad_norm": 2.7622790336608887,
869
+ "learning_rate": 6.053396349978632e-06,
870
+ "loss": 0.1453,
871
+ "step": 107
872
+ },
873
+ {
874
+ "epoch": 3.6050420168067228,
875
+ "grad_norm": 2.2422022819519043,
876
+ "learning_rate": 5.984124707338528e-06,
877
+ "loss": 0.0875,
878
+ "step": 108
879
+ },
880
+ {
881
+ "epoch": 3.638655462184874,
882
+ "grad_norm": 1.8057119846343994,
883
+ "learning_rate": 5.914655987361934e-06,
884
+ "loss": 0.2743,
885
+ "step": 109
886
+ },
887
+ {
888
+ "epoch": 3.6722689075630255,
889
+ "grad_norm": 1.2743725776672363,
890
+ "learning_rate": 5.8450041016092465e-06,
891
+ "loss": 0.2001,
892
+ "step": 110
893
+ },
894
+ {
895
+ "epoch": 3.7058823529411766,
896
+ "grad_norm": 2.135080575942993,
897
+ "learning_rate": 5.77518299832099e-06,
898
+ "loss": 0.2931,
899
+ "step": 111
900
+ },
901
+ {
902
+ "epoch": 3.7394957983193278,
903
+ "grad_norm": 2.7830662727355957,
904
+ "learning_rate": 5.705206659624597e-06,
905
+ "loss": 0.0739,
906
+ "step": 112
907
+ },
908
+ {
909
+ "epoch": 3.7394957983193278,
910
+ "eval_loss": 0.1947932094335556,
911
+ "eval_runtime": 12.0169,
912
+ "eval_samples_per_second": 2.08,
913
+ "eval_steps_per_second": 0.583,
914
+ "step": 112
915
+ },
916
+ {
917
+ "epoch": 3.773109243697479,
918
+ "grad_norm": 2.2503886222839355,
919
+ "learning_rate": 5.635089098734394e-06,
920
+ "loss": 0.1452,
921
+ "step": 113
922
+ },
923
+ {
924
+ "epoch": 3.80672268907563,
925
+ "grad_norm": 1.5595289468765259,
926
+ "learning_rate": 5.564844357145365e-06,
927
+ "loss": 0.0696,
928
+ "step": 114
929
+ },
930
+ {
931
+ "epoch": 3.8403361344537816,
932
+ "grad_norm": 1.9559892416000366,
933
+ "learning_rate": 5.49448650182125e-06,
934
+ "loss": 0.1231,
935
+ "step": 115
936
+ },
937
+ {
938
+ "epoch": 3.8739495798319328,
939
+ "grad_norm": 1.3151509761810303,
940
+ "learning_rate": 5.4240296223775465e-06,
941
+ "loss": 0.0796,
942
+ "step": 116
943
+ },
944
+ {
945
+ "epoch": 3.907563025210084,
946
+ "grad_norm": 2.6869540214538574,
947
+ "learning_rate": 5.353487828259973e-06,
948
+ "loss": 0.1171,
949
+ "step": 117
950
+ },
951
+ {
952
+ "epoch": 3.9411764705882355,
953
+ "grad_norm": 3.4072158336639404,
954
+ "learning_rate": 5.282875245918963e-06,
955
+ "loss": 0.2115,
956
+ "step": 118
957
+ },
958
+ {
959
+ "epoch": 3.9747899159663866,
960
+ "grad_norm": 2.99674916267395,
961
+ "learning_rate": 5.212206015980742e-06,
962
+ "loss": 0.1756,
963
+ "step": 119
964
+ },
965
+ {
966
+ "epoch": 4.0,
967
+ "grad_norm": 1.7564973831176758,
968
+ "learning_rate": 5.141494290415592e-06,
969
+ "loss": 0.1524,
970
+ "step": 120
971
+ },
972
+ {
973
+ "epoch": 4.0,
974
+ "eval_loss": 0.14572814106941223,
975
+ "eval_runtime": 12.0344,
976
+ "eval_samples_per_second": 2.077,
977
+ "eval_steps_per_second": 0.582,
978
+ "step": 120
979
+ },
980
+ {
981
+ "epoch": 4.033613445378151,
982
+ "grad_norm": 1.6185134649276733,
983
+ "learning_rate": 5.070754229703811e-06,
984
+ "loss": 0.2036,
985
+ "step": 121
986
+ },
987
+ {
988
+ "epoch": 4.067226890756302,
989
+ "grad_norm": 1.89780855178833,
990
+ "learning_rate": 5e-06,
991
+ "loss": 0.1084,
992
+ "step": 122
993
+ },
994
+ {
995
+ "epoch": 4.100840336134453,
996
+ "grad_norm": 1.0683470964431763,
997
+ "learning_rate": 4.929245770296191e-06,
998
+ "loss": 0.024,
999
+ "step": 123
1000
+ },
1001
+ {
1002
+ "epoch": 4.1344537815126055,
1003
+ "grad_norm": 1.3199543952941895,
1004
+ "learning_rate": 4.85850570958441e-06,
1005
+ "loss": 0.0721,
1006
+ "step": 124
1007
+ },
1008
+ {
1009
+ "epoch": 4.168067226890757,
1010
+ "grad_norm": 1.3227624893188477,
1011
+ "learning_rate": 4.78779398401926e-06,
1012
+ "loss": 0.1053,
1013
+ "step": 125
1014
+ },
1015
+ {
1016
+ "epoch": 4.201680672268908,
1017
+ "grad_norm": 0.9929068684577942,
1018
+ "learning_rate": 4.717124754081038e-06,
1019
+ "loss": 0.0404,
1020
+ "step": 126
1021
+ },
1022
+ {
1023
+ "epoch": 4.235294117647059,
1024
+ "grad_norm": 2.746427536010742,
1025
+ "learning_rate": 4.646512171740028e-06,
1026
+ "loss": 0.1037,
1027
+ "step": 127
1028
+ },
1029
+ {
1030
+ "epoch": 4.26890756302521,
1031
+ "grad_norm": 1.6636719703674316,
1032
+ "learning_rate": 4.575970377622456e-06,
1033
+ "loss": 0.0444,
1034
+ "step": 128
1035
+ },
1036
+ {
1037
+ "epoch": 4.26890756302521,
1038
+ "eval_loss": 0.1125473603606224,
1039
+ "eval_runtime": 12.0488,
1040
+ "eval_samples_per_second": 2.075,
1041
+ "eval_steps_per_second": 0.581,
1042
+ "step": 128
1043
+ },
1044
+ {
1045
+ "epoch": 4.302521008403361,
1046
+ "grad_norm": 1.1535725593566895,
1047
+ "learning_rate": 4.505513498178752e-06,
1048
+ "loss": 0.0378,
1049
+ "step": 129
1050
+ },
1051
+ {
1052
+ "epoch": 4.336134453781512,
1053
+ "grad_norm": 1.7697710990905762,
1054
+ "learning_rate": 4.435155642854637e-06,
1055
+ "loss": 0.0869,
1056
+ "step": 130
1057
+ },
1058
+ {
1059
+ "epoch": 4.369747899159664,
1060
+ "grad_norm": 0.9928828477859497,
1061
+ "learning_rate": 4.364910901265607e-06,
1062
+ "loss": 0.0737,
1063
+ "step": 131
1064
+ },
1065
+ {
1066
+ "epoch": 4.4033613445378155,
1067
+ "grad_norm": 1.6332063674926758,
1068
+ "learning_rate": 4.294793340375405e-06,
1069
+ "loss": 0.1098,
1070
+ "step": 132
1071
+ },
1072
+ {
1073
+ "epoch": 4.436974789915967,
1074
+ "grad_norm": 2.2281079292297363,
1075
+ "learning_rate": 4.224817001679011e-06,
1076
+ "loss": 0.0657,
1077
+ "step": 133
1078
+ },
1079
+ {
1080
+ "epoch": 4.470588235294118,
1081
+ "grad_norm": 3.8611080646514893,
1082
+ "learning_rate": 4.154995898390756e-06,
1083
+ "loss": 0.1013,
1084
+ "step": 134
1085
+ },
1086
+ {
1087
+ "epoch": 4.504201680672269,
1088
+ "grad_norm": 0.7134477496147156,
1089
+ "learning_rate": 4.085344012638067e-06,
1090
+ "loss": 0.0105,
1091
+ "step": 135
1092
+ },
1093
+ {
1094
+ "epoch": 4.53781512605042,
1095
+ "grad_norm": 3.5929417610168457,
1096
+ "learning_rate": 4.015875292661474e-06,
1097
+ "loss": 0.1385,
1098
+ "step": 136
1099
+ },
1100
+ {
1101
+ "epoch": 4.53781512605042,
1102
+ "eval_loss": 0.0758795514702797,
1103
+ "eval_runtime": 12.0325,
1104
+ "eval_samples_per_second": 2.078,
1105
+ "eval_steps_per_second": 0.582,
1106
+ "step": 136
1107
+ },
1108
+ {
1109
+ "epoch": 4.571428571428571,
1110
+ "grad_norm": 1.6059097051620483,
1111
+ "learning_rate": 3.94660365002137e-06,
1112
+ "loss": 0.0688,
1113
+ "step": 137
1114
+ },
1115
+ {
1116
+ "epoch": 4.605042016806722,
1117
+ "grad_norm": 1.931578278541565,
1118
+ "learning_rate": 3.877542956812137e-06,
1119
+ "loss": 0.061,
1120
+ "step": 138
1121
+ },
1122
+ {
1123
+ "epoch": 4.6386554621848735,
1124
+ "grad_norm": 4.694330215454102,
1125
+ "learning_rate": 3.808707042884176e-06,
1126
+ "loss": 0.0645,
1127
+ "step": 139
1128
+ },
1129
+ {
1130
+ "epoch": 4.6722689075630255,
1131
+ "grad_norm": 1.5269956588745117,
1132
+ "learning_rate": 3.7401096930743753e-06,
1133
+ "loss": 0.0695,
1134
+ "step": 140
1135
+ },
1136
+ {
1137
+ "epoch": 4.705882352941177,
1138
+ "grad_norm": 1.7759701013565063,
1139
+ "learning_rate": 3.6717646444456196e-06,
1140
+ "loss": 0.0327,
1141
+ "step": 141
1142
+ },
1143
+ {
1144
+ "epoch": 4.739495798319328,
1145
+ "grad_norm": 1.899479627609253,
1146
+ "learning_rate": 3.60368558353585e-06,
1147
+ "loss": 0.0428,
1148
+ "step": 142
1149
+ },
1150
+ {
1151
+ "epoch": 4.773109243697479,
1152
+ "grad_norm": 1.7261422872543335,
1153
+ "learning_rate": 3.5358861436172487e-06,
1154
+ "loss": 0.0628,
1155
+ "step": 143
1156
+ },
1157
+ {
1158
+ "epoch": 4.80672268907563,
1159
+ "grad_norm": 3.8707656860351562,
1160
+ "learning_rate": 3.4683799019660834e-06,
1161
+ "loss": 0.0591,
1162
+ "step": 144
1163
+ },
1164
+ {
1165
+ "epoch": 4.80672268907563,
1166
+ "eval_loss": 0.05604570358991623,
1167
+ "eval_runtime": 12.0383,
1168
+ "eval_samples_per_second": 2.077,
1169
+ "eval_steps_per_second": 0.581,
1170
+ "step": 144
1171
+ },
1172
+ {
1173
+ "epoch": 4.840336134453781,
1174
+ "grad_norm": 0.8072419762611389,
1175
+ "learning_rate": 3.401180377143774e-06,
1176
+ "loss": 0.0301,
1177
+ "step": 145
1178
+ },
1179
+ {
1180
+ "epoch": 4.873949579831933,
1181
+ "grad_norm": 0.8352177739143372,
1182
+ "learning_rate": 3.3343010262897125e-06,
1183
+ "loss": 0.0288,
1184
+ "step": 146
1185
+ },
1186
+ {
1187
+ "epoch": 4.907563025210084,
1188
+ "grad_norm": 2.471827745437622,
1189
+ "learning_rate": 3.2677552424263836e-06,
1190
+ "loss": 0.0198,
1191
+ "step": 147
1192
+ },
1193
+ {
1194
+ "epoch": 4.9411764705882355,
1195
+ "grad_norm": 1.5473682880401611,
1196
+ "learning_rate": 3.2015563517773214e-06,
1197
+ "loss": 0.0546,
1198
+ "step": 148
1199
+ },
1200
+ {
1201
+ "epoch": 4.974789915966387,
1202
+ "grad_norm": 1.4012079238891602,
1203
+ "learning_rate": 3.1357176110984578e-06,
1204
+ "loss": 0.033,
1205
+ "step": 149
1206
+ },
1207
+ {
1208
+ "epoch": 5.0,
1209
+ "grad_norm": 3.0382285118103027,
1210
+ "learning_rate": 3.070252205023356e-06,
1211
+ "loss": 0.0403,
1212
+ "step": 150
1213
+ },
1214
+ {
1215
+ "epoch": 5.033613445378151,
1216
+ "grad_norm": 0.7604548335075378,
1217
+ "learning_rate": 3.0051732434229185e-06,
1218
+ "loss": 0.014,
1219
+ "step": 151
1220
+ },
1221
+ {
1222
+ "epoch": 5.067226890756302,
1223
+ "grad_norm": 1.101543664932251,
1224
+ "learning_rate": 2.9404937587800374e-06,
1225
+ "loss": 0.0252,
1226
+ "step": 152
1227
+ },
1228
+ {
1229
+ "epoch": 5.067226890756302,
1230
+ "eval_loss": 0.04598259553313255,
1231
+ "eval_runtime": 12.0363,
1232
+ "eval_samples_per_second": 2.077,
1233
+ "eval_steps_per_second": 0.582,
1234
+ "step": 152
1235
+ },
1236
+ {
1237
+ "epoch": 5.100840336134453,
1238
+ "grad_norm": 1.4875141382217407,
1239
+ "learning_rate": 2.8762267035797607e-06,
1240
+ "loss": 0.0412,
1241
+ "step": 153
1242
+ },
1243
+ {
1244
+ "epoch": 5.1344537815126055,
1245
+ "grad_norm": 0.619445264339447,
1246
+ "learning_rate": 2.8123849477154808e-06,
1247
+ "loss": 0.0054,
1248
+ "step": 154
1249
+ },
1250
+ {
1251
+ "epoch": 5.168067226890757,
1252
+ "grad_norm": 1.1871784925460815,
1253
+ "learning_rate": 2.748981275911633e-06,
1254
+ "loss": 0.0413,
1255
+ "step": 155
1256
+ },
1257
+ {
1258
+ "epoch": 5.201680672268908,
1259
+ "grad_norm": 0.40735936164855957,
1260
+ "learning_rate": 2.6860283851635067e-06,
1261
+ "loss": 0.0074,
1262
+ "step": 156
1263
+ },
1264
+ {
1265
+ "epoch": 5.235294117647059,
1266
+ "grad_norm": 0.5911487340927124,
1267
+ "learning_rate": 2.6235388821945497e-06,
1268
+ "loss": 0.0081,
1269
+ "step": 157
1270
+ },
1271
+ {
1272
+ "epoch": 5.26890756302521,
1273
+ "grad_norm": 1.218485951423645,
1274
+ "learning_rate": 2.5615252809318287e-06,
1275
+ "loss": 0.0305,
1276
+ "step": 158
1277
+ },
1278
+ {
1279
+ "epoch": 5.302521008403361,
1280
+ "grad_norm": 1.8561826944351196,
1281
+ "learning_rate": 2.5000000000000015e-06,
1282
+ "loss": 0.0281,
1283
+ "step": 159
1284
+ },
1285
+ {
1286
+ "epoch": 5.336134453781512,
1287
+ "grad_norm": 0.45041966438293457,
1288
+ "learning_rate": 2.4389753602344298e-06,
1289
+ "loss": 0.0066,
1290
+ "step": 160
1291
+ },
1292
+ {
1293
+ "epoch": 5.336134453781512,
1294
+ "eval_loss": 0.03697740659117699,
1295
+ "eval_runtime": 12.0402,
1296
+ "eval_samples_per_second": 2.076,
1297
+ "eval_steps_per_second": 0.581,
1298
+ "step": 160
1299
+ },
1300
+ {
1301
+ "epoch": 5.369747899159664,
1302
+ "grad_norm": 1.5783069133758545,
1303
+ "learning_rate": 2.3784635822138424e-06,
1304
+ "loss": 0.026,
1305
+ "step": 161
1306
+ },
1307
+ {
1308
+ "epoch": 5.4033613445378155,
1309
+ "grad_norm": 1.163095474243164,
1310
+ "learning_rate": 2.318476783813088e-06,
1311
+ "loss": 0.0235,
1312
+ "step": 162
1313
+ },
1314
+ {
1315
+ "epoch": 5.436974789915967,
1316
+ "grad_norm": 0.9163492918014526,
1317
+ "learning_rate": 2.2590269777764516e-06,
1318
+ "loss": 0.0379,
1319
+ "step": 163
1320
+ },
1321
+ {
1322
+ "epoch": 5.470588235294118,
1323
+ "grad_norm": 0.6782473921775818,
1324
+ "learning_rate": 2.2001260693120236e-06,
1325
+ "loss": 0.0232,
1326
+ "step": 164
1327
+ },
1328
+ {
1329
+ "epoch": 5.504201680672269,
1330
+ "grad_norm": 0.7572933435440063,
1331
+ "learning_rate": 2.141785853707607e-06,
1332
+ "loss": 0.0201,
1333
+ "step": 165
1334
+ },
1335
+ {
1336
+ "epoch": 5.53781512605042,
1337
+ "grad_norm": 0.5534552335739136,
1338
+ "learning_rate": 2.0840180139686333e-06,
1339
+ "loss": 0.0159,
1340
+ "step": 166
1341
+ },
1342
+ {
1343
+ "epoch": 5.571428571428571,
1344
+ "grad_norm": 0.6240038275718689,
1345
+ "learning_rate": 2.0268341184785674e-06,
1346
+ "loss": 0.0127,
1347
+ "step": 167
1348
+ },
1349
+ {
1350
+ "epoch": 5.605042016806722,
1351
+ "grad_norm": 0.8554280400276184,
1352
+ "learning_rate": 1.9702456186822595e-06,
1353
+ "loss": 0.023,
1354
+ "step": 168
1355
+ },
1356
+ {
1357
+ "epoch": 5.605042016806722,
1358
+ "eval_loss": 0.025182316079735756,
1359
+ "eval_runtime": 12.0618,
1360
+ "eval_samples_per_second": 2.073,
1361
+ "eval_steps_per_second": 0.58,
1362
+ "step": 168
1363
+ },
1364
+ {
1365
+ "epoch": 5.6386554621848735,
1366
+ "grad_norm": 0.4920494556427002,
1367
+ "learning_rate": 1.9142638467927254e-06,
1368
+ "loss": 0.008,
1369
+ "step": 169
1370
+ },
1371
+ {
1372
+ "epoch": 5.6722689075630255,
1373
+ "grad_norm": 0.2633163332939148,
1374
+ "learning_rate": 1.8589000135217882e-06,
1375
+ "loss": 0.0051,
1376
+ "step": 170
1377
+ },
1378
+ {
1379
+ "epoch": 5.705882352941177,
1380
+ "grad_norm": 0.4242977797985077,
1381
+ "learning_rate": 1.8041652058350768e-06,
1382
+ "loss": 0.0116,
1383
+ "step": 171
1384
+ },
1385
+ {
1386
+ "epoch": 5.739495798319328,
1387
+ "grad_norm": 0.42241370677948,
1388
+ "learning_rate": 1.7500703847317663e-06,
1389
+ "loss": 0.0123,
1390
+ "step": 172
1391
+ },
1392
+ {
1393
+ "epoch": 5.773109243697479,
1394
+ "grad_norm": 0.2185809314250946,
1395
+ "learning_rate": 1.6966263830495939e-06,
1396
+ "loss": 0.0052,
1397
+ "step": 173
1398
+ },
1399
+ {
1400
+ "epoch": 5.80672268907563,
1401
+ "grad_norm": 0.2527461349964142,
1402
+ "learning_rate": 1.6438439032954857e-06,
1403
+ "loss": 0.0042,
1404
+ "step": 174
1405
+ },
1406
+ {
1407
+ "epoch": 5.840336134453781,
1408
+ "grad_norm": 1.115268349647522,
1409
+ "learning_rate": 1.5917335155023368e-06,
1410
+ "loss": 0.0388,
1411
+ "step": 175
1412
+ },
1413
+ {
1414
+ "epoch": 5.873949579831933,
1415
+ "grad_norm": 0.2189863622188568,
1416
+ "learning_rate": 1.5403056551122697e-06,
1417
+ "loss": 0.0033,
1418
+ "step": 176
1419
+ },
1420
+ {
1421
+ "epoch": 5.873949579831933,
1422
+ "eval_loss": 0.02022337168455124,
1423
+ "eval_runtime": 12.1511,
1424
+ "eval_samples_per_second": 2.057,
1425
+ "eval_steps_per_second": 0.576,
1426
+ "step": 176
1427
+ },
1428
+ {
1429
+ "epoch": 5.907563025210084,
1430
+ "grad_norm": 0.36403173208236694,
1431
+ "learning_rate": 1.4895706208868876e-06,
1432
+ "loss": 0.0046,
1433
+ "step": 177
1434
+ },
1435
+ {
1436
+ "epoch": 5.9411764705882355,
1437
+ "grad_norm": 0.43069425225257874,
1438
+ "learning_rate": 1.439538572844873e-06,
1439
+ "loss": 0.0117,
1440
+ "step": 178
1441
+ },
1442
+ {
1443
+ "epoch": 5.974789915966387,
1444
+ "grad_norm": 0.5442333817481995,
1445
+ "learning_rate": 1.390219530227378e-06,
1446
+ "loss": 0.0094,
1447
+ "step": 179
1448
+ },
1449
+ {
1450
+ "epoch": 6.0,
1451
+ "grad_norm": 0.33494141697883606,
1452
+ "learning_rate": 1.3416233694916086e-06,
1453
+ "loss": 0.0041,
1454
+ "step": 180
1455
+ },
1456
+ {
1457
+ "epoch": 6.033613445378151,
1458
+ "grad_norm": 0.4353264272212982,
1459
+ "learning_rate": 1.2937598223330006e-06,
1460
+ "loss": 0.0095,
1461
+ "step": 181
1462
+ },
1463
+ {
1464
+ "epoch": 6.067226890756302,
1465
+ "grad_norm": 0.8706492185592651,
1466
+ "learning_rate": 1.246638473736378e-06,
1467
+ "loss": 0.0306,
1468
+ "step": 182
1469
+ },
1470
+ {
1471
+ "epoch": 6.100840336134453,
1472
+ "grad_norm": 0.37063705921173096,
1473
+ "learning_rate": 1.2002687600565138e-06,
1474
+ "loss": 0.011,
1475
+ "step": 183
1476
+ },
1477
+ {
1478
+ "epoch": 6.1344537815126055,
1479
+ "grad_norm": 0.17374688386917114,
1480
+ "learning_rate": 1.1546599671284158e-06,
1481
+ "loss": 0.0029,
1482
+ "step": 184
1483
+ },
1484
+ {
1485
+ "epoch": 6.1344537815126055,
1486
+ "eval_loss": 0.016795845702290535,
1487
+ "eval_runtime": 12.0844,
1488
+ "eval_samples_per_second": 2.069,
1489
+ "eval_steps_per_second": 0.579,
1490
+ "step": 184
1491
+ },
1492
+ {
1493
+ "epoch": 6.168067226890757,
1494
+ "grad_norm": 0.6054437756538391,
1495
+ "learning_rate": 1.1098212284078037e-06,
1496
+ "loss": 0.0183,
1497
+ "step": 185
1498
+ },
1499
+ {
1500
+ "epoch": 6.201680672268908,
1501
+ "grad_norm": 0.39388203620910645,
1502
+ "learning_rate": 1.0657615231420492e-06,
1503
+ "loss": 0.0094,
1504
+ "step": 186
1505
+ },
1506
+ {
1507
+ "epoch": 6.235294117647059,
1508
+ "grad_norm": 0.27920323610305786,
1509
+ "learning_rate": 1.0224896745720513e-06,
1510
+ "loss": 0.0067,
1511
+ "step": 187
1512
+ },
1513
+ {
1514
+ "epoch": 6.26890756302521,
1515
+ "grad_norm": 0.4058905243873596,
1516
+ "learning_rate": 9.80014348165298e-07,
1517
+ "loss": 0.0067,
1518
+ "step": 188
1519
+ },
1520
+ {
1521
+ "epoch": 6.302521008403361,
1522
+ "grad_norm": 0.4656296968460083,
1523
+ "learning_rate": 9.383440498805712e-07,
1524
+ "loss": 0.0105,
1525
+ "step": 189
1526
+ },
1527
+ {
1528
+ "epoch": 6.336134453781512,
1529
+ "grad_norm": 0.3038158714771271,
1530
+ "learning_rate": 8.974871244645628e-07,
1531
+ "loss": 0.006,
1532
+ "step": 190
1533
+ },
1534
+ {
1535
+ "epoch": 6.369747899159664,
1536
+ "grad_norm": 0.3475418984889984,
1537
+ "learning_rate": 8.574517537807897e-07,
1538
+ "loss": 0.0096,
1539
+ "step": 191
1540
+ },
1541
+ {
1542
+ "epoch": 6.4033613445378155,
1543
+ "grad_norm": 0.17819644510746002,
1544
+ "learning_rate": 8.182459551711197e-07,
1545
+ "loss": 0.0024,
1546
+ "step": 192
1547
+ },
1548
+ {
1549
+ "epoch": 6.4033613445378155,
1550
+ "eval_loss": 0.01543365977704525,
1551
+ "eval_runtime": 12.0639,
1552
+ "eval_samples_per_second": 2.072,
1553
+ "eval_steps_per_second": 0.58,
1554
+ "step": 192
1555
+ },
1556
+ {
1557
+ "epoch": 6.436974789915967,
1558
+ "grad_norm": 0.7435154318809509,
1559
+ "learning_rate": 7.798775798502484e-07,
1560
+ "loss": 0.0136,
1561
+ "step": 193
1562
+ },
1563
+ {
1564
+ "epoch": 6.470588235294118,
1565
+ "grad_norm": 0.2663567364215851,
1566
+ "learning_rate": 7.423543113334436e-07,
1567
+ "loss": 0.0032,
1568
+ "step": 194
1569
+ },
1570
+ {
1571
+ "epoch": 6.504201680672269,
1572
+ "grad_norm": 0.29326626658439636,
1573
+ "learning_rate": 7.056836638978698e-07,
1574
+ "loss": 0.0075,
1575
+ "step": 195
1576
+ },
1577
+ {
1578
+ "epoch": 6.53781512605042,
1579
+ "grad_norm": 0.3095971643924713,
1580
+ "learning_rate": 6.698729810778065e-07,
1581
+ "loss": 0.01,
1582
+ "step": 196
1583
+ },
1584
+ {
1585
+ "epoch": 6.571428571428571,
1586
+ "grad_norm": 0.5871183276176453,
1587
+ "learning_rate": 6.349294341940593e-07,
1588
+ "loss": 0.0131,
1589
+ "step": 197
1590
+ },
1591
+ {
1592
+ "epoch": 6.605042016806722,
1593
+ "grad_norm": 0.6256702542304993,
1594
+ "learning_rate": 6.008600209178539e-07,
1595
+ "loss": 0.0165,
1596
+ "step": 198
1597
+ },
1598
+ {
1599
+ "epoch": 6.6386554621848735,
1600
+ "grad_norm": 0.10408986359834671,
1601
+ "learning_rate": 5.676715638695063e-07,
1602
+ "loss": 0.001,
1603
+ "step": 199
1604
+ },
1605
+ {
1606
+ "epoch": 6.6722689075630255,
1607
+ "grad_norm": 1.2808136940002441,
1608
+ "learning_rate": 5.353707092521581e-07,
1609
+ "loss": 0.0103,
1610
+ "step": 200
1611
+ },
1612
+ {
1613
+ "epoch": 6.6722689075630255,
1614
+ "eval_loss": 0.014628684148192406,
1615
+ "eval_runtime": 12.0564,
1616
+ "eval_samples_per_second": 2.074,
1617
+ "eval_steps_per_second": 0.581,
1618
+ "step": 200
1619
+ },
1620
+ {
1621
+ "epoch": 6.705882352941177,
1622
+ "grad_norm": 0.31355929374694824,
1623
+ "learning_rate": 5.039639255208156e-07,
1624
+ "loss": 0.0082,
1625
+ "step": 201
1626
+ },
1627
+ {
1628
+ "epoch": 6.739495798319328,
1629
+ "grad_norm": 0.3299062252044678,
1630
+ "learning_rate": 4.734575020870169e-07,
1631
+ "loss": 0.0088,
1632
+ "step": 202
1633
+ },
1634
+ {
1635
+ "epoch": 6.773109243697479,
1636
+ "grad_norm": 0.2100951075553894,
1637
+ "learning_rate": 4.43857548059321e-07,
1638
+ "loss": 0.0034,
1639
+ "step": 203
1640
+ }
1641
+ ],
1642
+ "logging_steps": 1,
1643
+ "max_steps": 232,
1644
+ "num_input_tokens_seen": 0,
1645
+ "num_train_epochs": 8,
1646
+ "save_steps": 29,
1647
+ "stateful_callbacks": {
1648
+ "TrainerControl": {
1649
+ "args": {
1650
+ "should_epoch_stop": false,
1651
+ "should_evaluate": false,
1652
+ "should_log": false,
1653
+ "should_save": true,
1654
+ "should_training_stop": false
1655
+ },
1656
+ "attributes": {}
1657
+ }
1658
+ },
1659
+ "total_flos": 2.7816841023848448e+17,
1660
+ "train_batch_size": 2,
1661
+ "trial_name": null,
1662
+ "trial_params": null
1663
+ }
checkpoint-203/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85f8f9b09204e1090ec2369a8805ad857a677dac1a4ca5d19752c2e11cd99114
3
+ size 7505
checkpoint-232/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /dpool/Meta-Llama-3.1-8B-Instruct-abliterated
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.2
checkpoint-232/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/dpool/Meta-Llama-3.1-8B-Instruct-abliterated",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": null,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 16,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "gate_proj",
28
+ "k_proj",
29
+ "q_proj",
30
+ "down_proj",
31
+ "o_proj",
32
+ "v_proj",
33
+ "up_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-232/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3088de2095a094689856cbb540058569e7b1847fcc298cd95e277fd301f50912
3
+ size 167832240
checkpoint-232/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9caf829c9c14a005eaa7872705409f970c087a1c8956a066982172d4859d718c
3
+ size 335945763
checkpoint-232/pytorch_model_fsdp.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:add2d1c8db478667ffb0e6cabc7f44dfe119ee0fb35c078fe63672ecedcc67da
3
+ size 167939969
checkpoint-232/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3dc28443c79745e45842e08f9d4ec7d1f0e34547a60e9a4742d818d8413d2fc
3
+ size 14917
checkpoint-232/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be2e5ee61c2a007b468486afda9c6a3ddceaa6a6d7f194f693ff66d9c0767168
3
+ size 14917