Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: deepcogito/cogito-v1-preview-qwen-14B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepcogito/cogito-v1-preview-qwen-14B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eda8db8d4f92d34ea930e7b6135e12eb2b5b20743c9efc2b899a11c0f0052e65
+size 137714904

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31c97e2c57eca8d1c1f38156661f8f7cb78ad51dd85660d4d6203904e301cac3
+size 275817586

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad9b95af34faa8b8f788848a73bc7bc5d19aa2d95731d9fc93513a92b113e95
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97db20ceac943e882d0ecf5e8eeed018c91160df8660f48a0ca5335a26f3cc08
+size 1064

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if not enable_thinking is defined %}\n    {%- set enable_thinking = false %}\n{%- endif %}\n{%- if tools %}\n    {{- \"<|im_start|>system\n\" }}\n    {%- if messages[0]['role'] == 'system' %}\n        {%- if enable_thinking %}\n            {{- \"Enable deep thinking subroutine.\n\n\" + messages[0]['content'] + \"\n\n\" }}\n        {%- else %}\n            {{- messages[0]['content'] + \"\n\n\" }}\n        {%- endif %}\n    {%- elif enable_thinking %}\n        {{- \"Enable deep thinking subroutine.\n\n\" }}\n    {%- endif %}\n    {{- \"# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- '\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n' }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {%- if enable_thinking %}\n            {{- \"<|im_start|>system\n\" + \"Enable deep thinking subroutine.\n\n\" + messages[0]['content'] + \"<|im_end|>\n\" }}\n        {%- else %}\n            {{- \"<|im_start|>system\n\" + messages[0]['content'] + \"<|im_end|>\n\" }}\n        {%- endif %}\n    {%- elif enable_thinking %}\n        {{- \"<|im_start|>system\n\" + \"Enable deep thinking subroutine.\" + \"<|im_end|>\n\" }}\n    {%- endif %}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- elif message.content is iterable and message.content is not string %}\n            {%- for content_item in message.content %}\n                {%- if content_item.type == 'text' %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>' + '\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\n' }}\n            {%- if message.content is string %}\n                {{- message.content }}\n            {%- elif message.content is iterable and message.content is not string %}\n                {%- for content_item in message.content %}\n                    {%- if content_item.type == 'text' %}\n                        {{- content_item.text }}\n                    {%- endif %}\n                {%- endfor %}\n            {%- endif %}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\n<tool_call>\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\n<tool_response>\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- elif message.content is iterable and message.content is not string %}\n            {%- for content_item in message.content %}\n                {%- if content_item.type == 'text' %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\n' }}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,831 @@
+{
+  "best_global_step": 900,
+  "best_metric": 0.22129979729652405,
+  "best_model_checkpoint": "./outputs/lora-out/checkpoint-500",
+  "epoch": 1.6700083542188806,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001670843776106934,
+      "eval_loss": 1.3396345376968384,
+      "eval_runtime": 153.6384,
+      "eval_samples_per_second": 0.82,
+      "eval_steps_per_second": 0.41,
+      "step": 1
+    },
+    {
+      "epoch": 0.01670843776106934,
+      "grad_norm": 0.30638471245765686,
+      "learning_rate": 1.005586592178771e-06,
+      "loss": 0.2994,
+      "step": 10
+    },
+    {
+      "epoch": 0.03341687552213868,
+      "grad_norm": 0.3499000072479248,
+      "learning_rate": 2.1229050279329612e-06,
+      "loss": 0.3112,
+      "step": 20
+    },
+    {
+      "epoch": 0.05012531328320802,
+      "grad_norm": 0.469807505607605,
+      "learning_rate": 3.240223463687151e-06,
+      "loss": 0.2718,
+      "step": 30
+    },
+    {
+      "epoch": 0.06683375104427736,
+      "grad_norm": 0.37554535269737244,
+      "learning_rate": 4.357541899441341e-06,
+      "loss": 0.2881,
+      "step": 40
+    },
+    {
+      "epoch": 0.0835421888053467,
+      "grad_norm": 0.3698641061782837,
+      "learning_rate": 5.474860335195531e-06,
+      "loss": 0.2249,
+      "step": 50
+    },
+    {
+      "epoch": 0.10025062656641603,
+      "grad_norm": 0.31917405128479004,
+      "learning_rate": 6.592178770949721e-06,
+      "loss": 0.2273,
+      "step": 60
+    },
+    {
+      "epoch": 0.11695906432748537,
+      "grad_norm": 0.2854767143726349,
+      "learning_rate": 7.709497206703911e-06,
+      "loss": 0.1996,
+      "step": 70
+    },
+    {
+      "epoch": 0.1336675020885547,
+      "grad_norm": 0.23341946303844452,
+      "learning_rate": 8.826815642458101e-06,
+      "loss": 0.1783,
+      "step": 80
+    },
+    {
+      "epoch": 0.15037593984962405,
+      "grad_norm": 2.197625160217285,
+      "learning_rate": 9.944134078212291e-06,
+      "loss": 0.1554,
+      "step": 90
+    },
+    {
+      "epoch": 0.1670843776106934,
+      "grad_norm": 0.29353854060173035,
+      "learning_rate": 1.1061452513966481e-05,
+      "loss": 0.1418,
+      "step": 100
+    },
+    {
+      "epoch": 0.1670843776106934,
+      "eval_loss": 1.165885329246521,
+      "eval_runtime": 163.1026,
+      "eval_samples_per_second": 0.773,
+      "eval_steps_per_second": 0.386,
+      "step": 100
+    },
+    {
+      "epoch": 0.18379281537176273,
+      "grad_norm": 0.2958841621875763,
+      "learning_rate": 1.2178770949720671e-05,
+      "loss": 0.0965,
+      "step": 110
+    },
+    {
+      "epoch": 0.20050125313283207,
+      "grad_norm": 0.2041017860174179,
+      "learning_rate": 1.3296089385474861e-05,
+      "loss": 0.1274,
+      "step": 120
+    },
+    {
+      "epoch": 0.2172096908939014,
+      "grad_norm": 0.48421984910964966,
+      "learning_rate": 1.4413407821229052e-05,
+      "loss": 0.1045,
+      "step": 130
+    },
+    {
+      "epoch": 0.23391812865497075,
+      "grad_norm": 0.17917853593826294,
+      "learning_rate": 1.553072625698324e-05,
+      "loss": 0.0781,
+      "step": 140
+    },
+    {
+      "epoch": 0.2506265664160401,
+      "grad_norm": 0.17654608190059662,
+      "learning_rate": 1.664804469273743e-05,
+      "loss": 0.098,
+      "step": 150
+    },
+    {
+      "epoch": 0.2673350041771094,
+      "grad_norm": 0.27942919731140137,
+      "learning_rate": 1.776536312849162e-05,
+      "loss": 0.0828,
+      "step": 160
+    },
+    {
+      "epoch": 0.28404344193817876,
+      "grad_norm": 0.27304232120513916,
+      "learning_rate": 1.888268156424581e-05,
+      "loss": 0.0736,
+      "step": 170
+    },
+    {
+      "epoch": 0.3007518796992481,
+      "grad_norm": 0.14034102857112885,
+      "learning_rate": 2e-05,
+      "loss": 0.0569,
+      "step": 180
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.5805022716522217,
+      "learning_rate": 1.9998108044133286e-05,
+      "loss": 0.0618,
+      "step": 190
+    },
+    {
+      "epoch": 0.3341687552213868,
+      "grad_norm": 0.25085538625717163,
+      "learning_rate": 1.9992432892432534e-05,
+      "loss": 0.0398,
+      "step": 200
+    },
+    {
+      "epoch": 0.3341687552213868,
+      "eval_loss": 0.5738930702209473,
+      "eval_runtime": 140.0905,
+      "eval_samples_per_second": 0.899,
+      "eval_steps_per_second": 0.45,
+      "step": 200
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 0.34200987219810486,
+      "learning_rate": 1.998297669232506e-05,
+      "loss": 0.0519,
+      "step": 210
+    },
+    {
+      "epoch": 0.36758563074352546,
+      "grad_norm": 0.38726481795310974,
+      "learning_rate": 1.996974302195352e-05,
+      "loss": 0.0421,
+      "step": 220
+    },
+    {
+      "epoch": 0.3842940685045948,
+      "grad_norm": 0.28290650248527527,
+      "learning_rate": 1.995273688882197e-05,
+      "loss": 0.0553,
+      "step": 230
+    },
+    {
+      "epoch": 0.40100250626566414,
+      "grad_norm": 0.27175962924957275,
+      "learning_rate": 1.993196472790108e-05,
+      "loss": 0.0459,
+      "step": 240
+    },
+    {
+      "epoch": 0.4177109440267335,
+      "grad_norm": 0.727622926235199,
+      "learning_rate": 1.9907434399193196e-05,
+      "loss": 0.0528,
+      "step": 250
+    },
+    {
+      "epoch": 0.4344193817878028,
+      "grad_norm": 0.23912201821804047,
+      "learning_rate": 1.9879155184758175e-05,
+      "loss": 0.0346,
+      "step": 260
+    },
+    {
+      "epoch": 0.45112781954887216,
+      "grad_norm": 0.26580628752708435,
+      "learning_rate": 1.9847137785201158e-05,
+      "loss": 0.0376,
+      "step": 270
+    },
+    {
+      "epoch": 0.4678362573099415,
+      "grad_norm": 0.2178439199924469,
+      "learning_rate": 1.9811394315623523e-05,
+      "loss": 0.0371,
+      "step": 280
+    },
+    {
+      "epoch": 0.48454469507101083,
+      "grad_norm": 0.2314031422138214,
+      "learning_rate": 1.9771938301038664e-05,
+      "loss": 0.0333,
+      "step": 290
+    },
+    {
+      "epoch": 0.5012531328320802,
+      "grad_norm": 0.2636023759841919,
+      "learning_rate": 1.9728784671254237e-05,
+      "loss": 0.0441,
+      "step": 300
+    },
+    {
+      "epoch": 0.5012531328320802,
+      "eval_loss": 0.336988240480423,
+      "eval_runtime": 135.4262,
+      "eval_samples_per_second": 0.93,
+      "eval_steps_per_second": 0.465,
+      "step": 300
+    },
+    {
+      "epoch": 0.5179615705931495,
+      "grad_norm": 0.18716369569301605,
+      "learning_rate": 1.9681949755222846e-05,
+      "loss": 0.0306,
+      "step": 310
+    },
+    {
+      "epoch": 0.5346700083542189,
+      "grad_norm": 0.2816139757633209,
+      "learning_rate": 1.9631451274863326e-05,
+      "loss": 0.0352,
+      "step": 320
+    },
+    {
+      "epoch": 0.5513784461152882,
+      "grad_norm": 0.2788981795310974,
+      "learning_rate": 1.957730833835491e-05,
+      "loss": 0.0415,
+      "step": 330
+    },
+    {
+      "epoch": 0.5680868838763575,
+      "grad_norm": 0.31909164786338806,
+      "learning_rate": 1.951954143290687e-05,
+      "loss": 0.0299,
+      "step": 340
+    },
+    {
+      "epoch": 0.5847953216374269,
+      "grad_norm": 0.13859644532203674,
+      "learning_rate": 1.9458172417006347e-05,
+      "loss": 0.0269,
+      "step": 350
+    },
+    {
+      "epoch": 0.6015037593984962,
+      "grad_norm": 0.1854671686887741,
+      "learning_rate": 1.939322451214727e-05,
+      "loss": 0.0552,
+      "step": 360
+    },
+    {
+      "epoch": 0.6182121971595655,
+      "grad_norm": 0.310477614402771,
+      "learning_rate": 1.932472229404356e-05,
+      "loss": 0.0422,
+      "step": 370
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.21453866362571716,
+      "learning_rate": 1.9252691683329907e-05,
+      "loss": 0.0342,
+      "step": 380
+    },
+    {
+      "epoch": 0.6516290726817042,
+      "grad_norm": 0.28465718030929565,
+      "learning_rate": 1.9177159935753612e-05,
+      "loss": 0.0354,
+      "step": 390
+    },
+    {
+      "epoch": 0.6683375104427736,
+      "grad_norm": 0.11518735438585281,
+      "learning_rate": 1.9098155631861272e-05,
+      "loss": 0.0356,
+      "step": 400
+    },
+    {
+      "epoch": 0.6683375104427736,
+      "eval_loss": 0.3165595233440399,
+      "eval_runtime": 148.5689,
+      "eval_samples_per_second": 0.848,
+      "eval_steps_per_second": 0.424,
+      "step": 400
+    },
+    {
+      "epoch": 0.6850459482038429,
+      "grad_norm": 0.11679059267044067,
+      "learning_rate": 1.901570866618413e-05,
+      "loss": 0.0385,
+      "step": 410
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 0.5093502998352051,
+      "learning_rate": 1.8929850235926265e-05,
+      "loss": 0.0399,
+      "step": 420
+    },
+    {
+      "epoch": 0.7184628237259816,
+      "grad_norm": 0.3631969392299652,
+      "learning_rate": 1.884061282915985e-05,
+      "loss": 0.0286,
+      "step": 430
+    },
+    {
+      "epoch": 0.7351712614870509,
+      "grad_norm": 0.38055914640426636,
+      "learning_rate": 1.8748030212531936e-05,
+      "loss": 0.0255,
+      "step": 440
+    },
+    {
+      "epoch": 0.7518796992481203,
+      "grad_norm": 0.16323517262935638,
+      "learning_rate": 1.8652137418487454e-05,
+      "loss": 0.0376,
+      "step": 450
+    },
+    {
+      "epoch": 0.7685881370091896,
+      "grad_norm": 0.16024459898471832,
+      "learning_rate": 1.8552970732013267e-05,
+      "loss": 0.0344,
+      "step": 460
+    },
+    {
+      "epoch": 0.7852965747702589,
+      "grad_norm": 0.35534510016441345,
+      "learning_rate": 1.8450567676908222e-05,
+      "loss": 0.0225,
+      "step": 470
+    },
+    {
+      "epoch": 0.8020050125313283,
+      "grad_norm": 0.4883843660354614,
+      "learning_rate": 1.834496700158449e-05,
+      "loss": 0.0246,
+      "step": 480
+    },
+    {
+      "epoch": 0.8187134502923976,
+      "grad_norm": 0.2900645136833191,
+      "learning_rate": 1.823620866440552e-05,
+      "loss": 0.0239,
+      "step": 490
+    },
+    {
+      "epoch": 0.835421888053467,
+      "grad_norm": 0.19605468213558197,
+      "learning_rate": 1.8124333818566124e-05,
+      "loss": 0.0245,
+      "step": 500
+    },
+    {
+      "epoch": 0.835421888053467,
+      "eval_loss": 0.2774077355861664,
+      "eval_runtime": 148.0785,
+      "eval_samples_per_second": 0.851,
+      "eval_steps_per_second": 0.425,
+      "step": 500
+    },
+    {
+      "epoch": 0.8521303258145363,
+      "grad_norm": 0.30637845396995544,
+      "learning_rate": 1.8009384796520487e-05,
+      "loss": 0.0511,
+      "step": 510
+    },
+    {
+      "epoch": 0.8688387635756056,
+      "grad_norm": 0.16957111656665802,
+      "learning_rate": 1.789140509396394e-05,
+      "loss": 0.0262,
+      "step": 520
+    },
+    {
+      "epoch": 0.885547201336675,
+      "grad_norm": 0.14532604813575745,
+      "learning_rate": 1.7770439353374555e-05,
+      "loss": 0.0338,
+      "step": 530
+    },
+    {
+      "epoch": 0.9022556390977443,
+      "grad_norm": 0.19348469376564026,
+      "learning_rate": 1.7646533347120852e-05,
+      "loss": 0.0238,
+      "step": 540
+    },
+    {
+      "epoch": 0.9189640768588136,
+      "grad_norm": 0.579799234867096,
+      "learning_rate": 1.7519733960141927e-05,
+      "loss": 0.0424,
+      "step": 550
+    },
+    {
+      "epoch": 0.935672514619883,
+      "grad_norm": 0.18844471871852875,
+      "learning_rate": 1.7390089172206594e-05,
+      "loss": 0.0385,
+      "step": 560
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.15091806650161743,
+      "learning_rate": 1.7257648039758273e-05,
+      "loss": 0.0413,
+      "step": 570
+    },
+    {
+      "epoch": 0.9690893901420217,
+      "grad_norm": 0.21383507549762726,
+      "learning_rate": 1.712246067735248e-05,
+      "loss": 0.0222,
+      "step": 580
+    },
+    {
+      "epoch": 0.985797827903091,
+      "grad_norm": 0.21775048971176147,
+      "learning_rate": 1.6984578238693888e-05,
+      "loss": 0.0319,
+      "step": 590
+    },
+    {
+      "epoch": 1.001670843776107,
+      "grad_norm": 0.25965356826782227,
+      "learning_rate": 1.684405289728025e-05,
+      "loss": 0.0269,
+      "step": 600
+    },
+    {
+      "epoch": 1.001670843776107,
+      "eval_loss": 0.2528988718986511,
+      "eval_runtime": 145.2519,
+      "eval_samples_per_second": 0.867,
+      "eval_steps_per_second": 0.434,
+      "step": 600
+    },
+    {
+      "epoch": 1.0183792815371762,
+      "grad_norm": 0.4102862477302551,
+      "learning_rate": 1.6700937826660384e-05,
+      "loss": 0.0362,
+      "step": 610
+    },
+    {
+      "epoch": 1.0350877192982457,
+      "grad_norm": 0.2472643405199051,
+      "learning_rate": 1.6555287180313787e-05,
+      "loss": 0.0179,
+      "step": 620
+    },
+    {
+      "epoch": 1.0517961570593148,
+      "grad_norm": 0.3665148913860321,
+      "learning_rate": 1.6407156071159432e-05,
+      "loss": 0.0321,
+      "step": 630
+    },
+    {
+      "epoch": 1.0685045948203844,
+      "grad_norm": 0.1608251929283142,
+      "learning_rate": 1.6256600550701513e-05,
+      "loss": 0.0246,
+      "step": 640
+    },
+    {
+      "epoch": 1.0852130325814535,
+      "grad_norm": 0.16940800845623016,
+      "learning_rate": 1.6103677587820076e-05,
+      "loss": 0.0198,
+      "step": 650
+    },
+    {
+      "epoch": 1.101921470342523,
+      "grad_norm": 0.3891701400279999,
+      "learning_rate": 1.594844504721447e-05,
+      "loss": 0.0273,
+      "step": 660
+    },
+    {
+      "epoch": 1.1186299081035922,
+      "grad_norm": 0.28342196345329285,
+      "learning_rate": 1.5790961667507884e-05,
+      "loss": 0.0226,
+      "step": 670
+    },
+    {
+      "epoch": 1.1353383458646618,
+      "grad_norm": 0.2786351144313812,
+      "learning_rate": 1.5631287039021143e-05,
+      "loss": 0.0181,
+      "step": 680
+    },
+    {
+      "epoch": 1.1520467836257309,
+      "grad_norm": 0.31003037095069885,
+      "learning_rate": 1.5469481581224274e-05,
+      "loss": 0.0241,
+      "step": 690
+    },
+    {
+      "epoch": 1.1687552213868004,
+      "grad_norm": 0.24711792171001434,
+      "learning_rate": 1.53056065198743e-05,
+      "loss": 0.0318,
+      "step": 700
+    },
+    {
+      "epoch": 1.1687552213868004,
+      "eval_loss": 0.2420859932899475,
+      "eval_runtime": 149.4544,
+      "eval_samples_per_second": 0.843,
+      "eval_steps_per_second": 0.422,
+      "step": 700
+    },
+    {
+      "epoch": 1.1854636591478696,
+      "grad_norm": 0.2184493988752365,
+      "learning_rate": 1.5139723863847977e-05,
+      "loss": 0.0224,
+      "step": 710
+    },
+    {
+      "epoch": 1.2021720969089391,
+      "grad_norm": 0.2765026092529297,
+      "learning_rate": 1.4971896381678152e-05,
+      "loss": 0.028,
+      "step": 720
+    },
+    {
+      "epoch": 1.2188805346700082,
+      "grad_norm": 0.3602149188518524,
+      "learning_rate": 1.480218757780272e-05,
+      "loss": 0.0313,
+      "step": 730
+    },
+    {
+      "epoch": 1.2355889724310778,
+      "grad_norm": 0.23113080859184265,
+      "learning_rate": 1.4630661668535106e-05,
+      "loss": 0.0255,
+      "step": 740
+    },
+    {
+      "epoch": 1.252297410192147,
+      "grad_norm": 0.34203672409057617,
+      "learning_rate": 1.4457383557765385e-05,
+      "loss": 0.0184,
+      "step": 750
+    },
+    {
+      "epoch": 1.2690058479532165,
+      "grad_norm": 0.25321242213249207,
+      "learning_rate": 1.4282418812401197e-05,
+      "loss": 0.0263,
+      "step": 760
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.14375656843185425,
+      "learning_rate": 1.4105833637557835e-05,
+      "loss": 0.0223,
+      "step": 770
+    },
+    {
+      "epoch": 1.3024227234753551,
+      "grad_norm": 0.2957589626312256,
+      "learning_rate": 1.3927694851506805e-05,
+      "loss": 0.0229,
+      "step": 780
+    },
+    {
+      "epoch": 1.3191311612364243,
+      "grad_norm": 0.1572154015302658,
+      "learning_rate": 1.3748069860392381e-05,
+      "loss": 0.019,
+      "step": 790
+    },
+    {
+      "epoch": 1.3358395989974938,
+      "grad_norm": 0.17799264192581177,
+      "learning_rate": 1.356702663272571e-05,
+      "loss": 0.0261,
+      "step": 800
+    },
+    {
+      "epoch": 1.3358395989974938,
+      "eval_loss": 0.2350257933139801,
+      "eval_runtime": 153.9563,
+      "eval_samples_per_second": 0.818,
+      "eval_steps_per_second": 0.409,
+      "step": 800
+    },
+    {
+      "epoch": 1.352548036758563,
+      "grad_norm": 0.4011281132698059,
+      "learning_rate": 1.3384633673666132e-05,
+      "loss": 0.0126,
+      "step": 810
+    },
+    {
+      "epoch": 1.3692564745196325,
+      "grad_norm": 0.2754865884780884,
+      "learning_rate": 1.3200959999099441e-05,
+      "loss": 0.0265,
+      "step": 820
+    },
+    {
+      "epoch": 1.3859649122807016,
+      "grad_norm": 0.2379375398159027,
+      "learning_rate": 1.3016075109522865e-05,
+      "loss": 0.0305,
+      "step": 830
+    },
+    {
+      "epoch": 1.4026733500417712,
+      "grad_norm": 0.2875842750072479,
+      "learning_rate": 1.2830048963746703e-05,
+      "loss": 0.0248,
+      "step": 840
+    },
+    {
+      "epoch": 1.4193817878028403,
+      "grad_norm": 0.3549558222293854,
+      "learning_rate": 1.2642951952422533e-05,
+      "loss": 0.0238,
+      "step": 850
+    },
+    {
+      "epoch": 1.4360902255639099,
+      "grad_norm": 0.14091502130031586,
+      "learning_rate": 1.2454854871407993e-05,
+      "loss": 0.0175,
+      "step": 860
+    },
+    {
+      "epoch": 1.452798663324979,
+      "grad_norm": 0.2457050085067749,
+      "learning_rate": 1.2265828894978273e-05,
+      "loss": 0.0273,
+      "step": 870
+    },
+    {
+      "epoch": 1.4695071010860485,
+      "grad_norm": 0.09693857282400131,
+      "learning_rate": 1.2075945548894388e-05,
+      "loss": 0.0261,
+      "step": 880
+    },
+    {
+      "epoch": 1.4862155388471177,
+      "grad_norm": 0.47048380970954895,
+      "learning_rate": 1.188527668333846e-05,
+      "loss": 0.0261,
+      "step": 890
+    },
+    {
+      "epoch": 1.5029239766081872,
+      "grad_norm": 0.2266128808259964,
+      "learning_rate": 1.1693894445726245e-05,
+      "loss": 0.0137,
+      "step": 900
+    },
+    {
+      "epoch": 1.5029239766081872,
+      "eval_loss": 0.22129979729652405,
+      "eval_runtime": 149.564,
+      "eval_samples_per_second": 0.842,
+      "eval_steps_per_second": 0.421,
+      "step": 900
+    },
+    {
+      "epoch": 1.5196324143692563,
+      "grad_norm": 0.06724128127098083,
+      "learning_rate": 1.1501871253407196e-05,
+      "loss": 0.0263,
+      "step": 910
+    },
+    {
+      "epoch": 1.536340852130326,
+      "grad_norm": 0.23750649392604828,
+      "learning_rate": 1.1309279766262355e-05,
+      "loss": 0.0241,
+      "step": 920
+    },
+    {
+      "epoch": 1.553049289891395,
+      "grad_norm": 0.10435036569833755,
+      "learning_rate": 1.1116192859210527e-05,
+      "loss": 0.0208,
+      "step": 930
+    },
+    {
+      "epoch": 1.5697577276524646,
+      "grad_norm": 0.10308808833360672,
+      "learning_rate": 1.092268359463302e-05,
+      "loss": 0.027,
+      "step": 940
+    },
+    {
+      "epoch": 1.5864661654135337,
+      "grad_norm": 0.28695517778396606,
+      "learning_rate": 1.072882519472752e-05,
+      "loss": 0.0184,
+      "step": 950
+    },
+    {
+      "epoch": 1.6031746031746033,
+      "grad_norm": 0.1586754024028778,
+      "learning_rate": 1.053469101380142e-05,
+      "loss": 0.0194,
+      "step": 960
+    },
+    {
+      "epoch": 1.6198830409356724,
+      "grad_norm": 0.16197402775287628,
+      "learning_rate": 1.0340354510515235e-05,
+      "loss": 0.0276,
+      "step": 970
+    },
+    {
+      "epoch": 1.636591478696742,
+      "grad_norm": 0.40588006377220154,
+      "learning_rate": 1.0145889220086465e-05,
+      "loss": 0.0191,
+      "step": 980
+    },
+    {
+      "epoch": 1.653299916457811,
+      "grad_norm": 0.13650530576705933,
+      "learning_rate": 9.951368726464526e-06,
+      "loss": 0.0185,
+      "step": 990
+    },
+    {
+      "epoch": 1.6700083542188806,
+      "grad_norm": 0.21690163016319275,
+      "learning_rate": 9.756866634487243e-06,
+      "loss": 0.0194,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6700083542188806,
+      "eval_loss": 0.23432661592960358,
+      "eval_runtime": 147.9907,
+      "eval_samples_per_second": 0.851,
+      "eval_steps_per_second": 0.426,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1794,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3779092362934354e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afe453b7095218139e71d1162a82f070679af7eabc0c7438b0afd0e0657026d8
+size 6584