DecoderImmortal commited on
Commit
7fafb47
·
verified ·
1 Parent(s): 3335811

Upload folder using huggingface_hub

Browse files
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.9989717223650385,
3
+ "total_flos": 9.034546879177687e+18,
4
+ "train_loss": 1.1365475546675945,
5
+ "train_runtime": 15552.1986,
6
+ "train_samples_per_second": 32.015,
7
+ "train_steps_per_second": 0.062
8
+ }
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128001,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 8192,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 500000.0,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.40.2",
25
+ "use_cache": false,
26
+ "vocab_size": 128256
27
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": 128001,
5
+ "transformers_version": "4.40.2"
6
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e83bde3b0ca1a1b7cb0a148f5c61147df7dccb93123148b646beb75f56528fbb
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bee540f0bdc633e90eab2a8c0156b092afe010c93cf6bbbfc8fe8ac54250a2f
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dac300286fe3d0147236c54e82be8b77666b394992d53023202b2746b9771cd
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e56825f7f2e2d65447f3c01b44738f8580af4e797376c4c1226a176795642276
3
+ size 1168138808
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|eot_id|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
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": "<|reserved_special_token_4|>",
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": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
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 system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|begin_of_text|>' + '<|start_header_id|>system<|end_header_id|>\\n\\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\\n\\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.9989717223650385,
3
+ "total_flos": 9.034546879177687e+18,
4
+ "train_loss": 1.1365475546675945,
5
+ "train_runtime": 15552.1986,
6
+ "train_samples_per_second": 32.015,
7
+ "train_steps_per_second": 0.062
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 972, "loss": 1.5713, "learning_rate": 1.9994839090452616e-05, "epoch": 0.02056555269922879, "percentage": 1.03, "elapsed_time": "0:02:42", "remaining_time": "4:20:24"}
2
+ {"current_steps": 20, "total_steps": 972, "loss": 1.3565, "learning_rate": 1.9979236966675828e-05, "epoch": 0.04113110539845758, "percentage": 2.06, "elapsed_time": "0:05:29", "remaining_time": "4:21:46"}
3
+ {"current_steps": 30, "total_steps": 972, "loss": 1.3132, "learning_rate": 1.9953209739827946e-05, "epoch": 0.061696658097686374, "percentage": 3.09, "elapsed_time": "0:08:07", "remaining_time": "4:15:18"}
4
+ {"current_steps": 40, "total_steps": 972, "loss": 1.2708, "learning_rate": 1.9916784600016132e-05, "epoch": 0.08226221079691516, "percentage": 4.12, "elapsed_time": "0:10:50", "remaining_time": "4:12:37"}
5
+ {"current_steps": 50, "total_steps": 972, "loss": 1.2658, "learning_rate": 1.9869999599832804e-05, "epoch": 0.10282776349614396, "percentage": 5.14, "elapsed_time": "0:13:17", "remaining_time": "4:05:14"}
6
+ {"current_steps": 60, "total_steps": 972, "loss": 1.2531, "learning_rate": 1.981290361460287e-05, "epoch": 0.12339331619537275, "percentage": 6.17, "elapsed_time": "0:15:47", "remaining_time": "3:59:58"}
7
+ {"current_steps": 70, "total_steps": 972, "loss": 1.2339, "learning_rate": 1.974555629132469e-05, "epoch": 0.14395886889460155, "percentage": 7.2, "elapsed_time": "0:18:24", "remaining_time": "3:57:09"}
8
+ {"current_steps": 80, "total_steps": 972, "loss": 1.2372, "learning_rate": 1.9668027986358082e-05, "epoch": 0.16452442159383032, "percentage": 8.23, "elapsed_time": "0:20:57", "remaining_time": "3:53:43"}
9
+ {"current_steps": 90, "total_steps": 972, "loss": 1.2298, "learning_rate": 1.9580399691924484e-05, "epoch": 0.18508997429305912, "percentage": 9.26, "elapsed_time": "0:23:34", "remaining_time": "3:51:04"}
10
+ {"current_steps": 100, "total_steps": 972, "loss": 1.2312, "learning_rate": 1.9482762951496056e-05, "epoch": 0.20565552699228792, "percentage": 10.29, "elapsed_time": "0:26:21", "remaining_time": "3:49:47"}
11
+ {"current_steps": 110, "total_steps": 972, "loss": 1.2316, "learning_rate": 1.9375219764162096e-05, "epoch": 0.2262210796915167, "percentage": 11.32, "elapsed_time": "0:29:03", "remaining_time": "3:47:40"}
12
+ {"current_steps": 120, "total_steps": 972, "loss": 1.2337, "learning_rate": 1.92578824780727e-05, "epoch": 0.2467866323907455, "percentage": 12.35, "elapsed_time": "0:31:43", "remaining_time": "3:45:16"}
13
+ {"current_steps": 130, "total_steps": 972, "loss": 1.2136, "learning_rate": 1.913087367307095e-05, "epoch": 0.26735218508997427, "percentage": 13.37, "elapsed_time": "0:34:31", "remaining_time": "3:43:36"}
14
+ {"current_steps": 140, "total_steps": 972, "loss": 1.2072, "learning_rate": 1.8994326032636318e-05, "epoch": 0.2879177377892031, "percentage": 14.4, "elapsed_time": "0:36:56", "remaining_time": "3:39:30"}
15
+ {"current_steps": 150, "total_steps": 972, "loss": 1.2017, "learning_rate": 1.8848382205272924e-05, "epoch": 0.30848329048843187, "percentage": 15.43, "elapsed_time": "0:39:49", "remaining_time": "3:38:14"}
16
+ {"current_steps": 160, "total_steps": 972, "loss": 1.208, "learning_rate": 1.869319465548762e-05, "epoch": 0.32904884318766064, "percentage": 16.46, "elapsed_time": "0:42:24", "remaining_time": "3:35:11"}
17
+ {"current_steps": 170, "total_steps": 972, "loss": 1.2012, "learning_rate": 1.852892550451345e-05, "epoch": 0.3496143958868895, "percentage": 17.49, "elapsed_time": "0:45:32", "remaining_time": "3:34:51"}
18
+ {"current_steps": 180, "total_steps": 972, "loss": 1.2035, "learning_rate": 1.835574636094494e-05, "epoch": 0.37017994858611825, "percentage": 18.52, "elapsed_time": "0:48:12", "remaining_time": "3:32:07"}
19
+ {"current_steps": 190, "total_steps": 972, "loss": 1.2147, "learning_rate": 1.8173838141462145e-05, "epoch": 0.390745501285347, "percentage": 19.55, "elapsed_time": "0:50:37", "remaining_time": "3:28:21"}
20
+ {"current_steps": 200, "total_steps": 972, "loss": 1.2126, "learning_rate": 1.798339088183071e-05, "epoch": 0.41131105398457585, "percentage": 20.58, "elapsed_time": "0:53:23", "remaining_time": "3:26:04"}
21
+ {"current_steps": 210, "total_steps": 972, "loss": 1.2089, "learning_rate": 1.7784603538375453e-05, "epoch": 0.4318766066838046, "percentage": 21.6, "elapsed_time": "0:55:48", "remaining_time": "3:22:31"}
22
+ {"current_steps": 220, "total_steps": 972, "loss": 1.1879, "learning_rate": 1.7577683780134756e-05, "epoch": 0.4524421593830334, "percentage": 22.63, "elapsed_time": "0:58:16", "remaining_time": "3:19:12"}
23
+ {"current_steps": 230, "total_steps": 972, "loss": 1.2097, "learning_rate": 1.7362847771913035e-05, "epoch": 0.4730077120822622, "percentage": 23.66, "elapsed_time": "1:00:41", "remaining_time": "3:15:46"}
24
+ {"current_steps": 240, "total_steps": 972, "loss": 1.187, "learning_rate": 1.714031994845782e-05, "epoch": 0.493573264781491, "percentage": 24.69, "elapsed_time": "1:03:04", "remaining_time": "3:12:23"}
25
+ {"current_steps": 250, "total_steps": 972, "loss": 1.1835, "learning_rate": 1.6910332779997378e-05, "epoch": 0.5141388174807198, "percentage": 25.72, "elapsed_time": "1:05:48", "remaining_time": "3:10:01"}
26
+ {"current_steps": 260, "total_steps": 972, "loss": 1.1906, "learning_rate": 1.6673126529383905e-05, "epoch": 0.5347043701799485, "percentage": 26.75, "elapsed_time": "1:08:39", "remaining_time": "3:08:00"}
27
+ {"current_steps": 270, "total_steps": 972, "loss": 1.1736, "learning_rate": 1.642894900109584e-05, "epoch": 0.5552699228791774, "percentage": 27.78, "elapsed_time": "1:11:28", "remaining_time": "3:05:50"}
28
+ {"current_steps": 280, "total_steps": 972, "loss": 1.19, "learning_rate": 1.6178055282361642e-05, "epoch": 0.5758354755784062, "percentage": 28.81, "elapsed_time": "1:14:15", "remaining_time": "3:03:30"}
29
+ {"current_steps": 290, "total_steps": 972, "loss": 1.1851, "learning_rate": 1.5920707476675446e-05, "epoch": 0.596401028277635, "percentage": 29.84, "elapsed_time": "1:16:52", "remaining_time": "3:00:48"}
30
+ {"current_steps": 300, "total_steps": 972, "loss": 1.1824, "learning_rate": 1.565717442998292e-05, "epoch": 0.6169665809768637, "percentage": 30.86, "elapsed_time": "1:19:14", "remaining_time": "2:57:29"}
31
+ {"current_steps": 310, "total_steps": 972, "loss": 1.1543, "learning_rate": 1.5387731449823474e-05, "epoch": 0.6375321336760925, "percentage": 31.89, "elapsed_time": "1:21:44", "remaining_time": "2:54:33"}
32
+ {"current_steps": 320, "total_steps": 972, "loss": 1.1683, "learning_rate": 1.5112660017722122e-05, "epoch": 0.6580976863753213, "percentage": 32.92, "elapsed_time": "1:24:33", "remaining_time": "2:52:17"}
33
+ {"current_steps": 330, "total_steps": 972, "loss": 1.1643, "learning_rate": 1.4832247495131566e-05, "epoch": 0.6786632390745502, "percentage": 33.95, "elapsed_time": "1:27:35", "remaining_time": "2:50:24"}
34
+ {"current_steps": 340, "total_steps": 972, "loss": 1.1679, "learning_rate": 1.45467868232316e-05, "epoch": 0.699228791773779, "percentage": 34.98, "elapsed_time": "1:30:20", "remaining_time": "2:47:55"}
35
+ {"current_steps": 350, "total_steps": 972, "loss": 1.1605, "learning_rate": 1.4256576216899494e-05, "epoch": 0.7197943444730077, "percentage": 36.01, "elapsed_time": "1:32:54", "remaining_time": "2:45:06"}
36
+ {"current_steps": 360, "total_steps": 972, "loss": 1.1681, "learning_rate": 1.3961918853171073e-05, "epoch": 0.7403598971722365, "percentage": 37.04, "elapsed_time": "1:35:49", "remaining_time": "2:42:54"}
37
+ {"current_steps": 370, "total_steps": 972, "loss": 1.1545, "learning_rate": 1.3663122554517917e-05, "epoch": 0.7609254498714653, "percentage": 38.07, "elapsed_time": "1:38:26", "remaining_time": "2:40:10"}
38
+ {"current_steps": 380, "total_steps": 972, "loss": 1.167, "learning_rate": 1.3360499467271552e-05, "epoch": 0.781491002570694, "percentage": 39.09, "elapsed_time": "1:41:08", "remaining_time": "2:37:34"}
39
+ {"current_steps": 390, "total_steps": 972, "loss": 1.1706, "learning_rate": 1.3054365735530666e-05, "epoch": 0.8020565552699229, "percentage": 40.12, "elapsed_time": "1:43:38", "remaining_time": "2:34:40"}
40
+ {"current_steps": 400, "total_steps": 972, "loss": 1.1512, "learning_rate": 1.2745041170891827e-05, "epoch": 0.8226221079691517, "percentage": 41.15, "elapsed_time": "1:46:32", "remaining_time": "2:32:21"}
41
+ {"current_steps": 410, "total_steps": 972, "loss": 1.161, "learning_rate": 1.243284891834894e-05, "epoch": 0.8431876606683805, "percentage": 42.18, "elapsed_time": "1:49:05", "remaining_time": "2:29:32"}
42
+ {"current_steps": 420, "total_steps": 972, "loss": 1.1499, "learning_rate": 1.211811511871033e-05, "epoch": 0.8637532133676092, "percentage": 43.21, "elapsed_time": "1:51:47", "remaining_time": "2:26:55"}
43
+ {"current_steps": 430, "total_steps": 972, "loss": 1.1428, "learning_rate": 1.1801168567886159e-05, "epoch": 0.884318766066838, "percentage": 44.24, "elapsed_time": "1:54:27", "remaining_time": "2:24:16"}
44
+ {"current_steps": 440, "total_steps": 972, "loss": 1.1548, "learning_rate": 1.1482340373402128e-05, "epoch": 0.9048843187660668, "percentage": 45.27, "elapsed_time": "1:56:58", "remaining_time": "2:21:25"}
45
+ {"current_steps": 450, "total_steps": 972, "loss": 1.1375, "learning_rate": 1.1161963608498254e-05, "epoch": 0.9254498714652957, "percentage": 46.3, "elapsed_time": "2:00:09", "remaining_time": "2:19:23"}
46
+ {"current_steps": 460, "total_steps": 972, "loss": 1.1441, "learning_rate": 1.0840372964174148e-05, "epoch": 0.9460154241645244, "percentage": 47.33, "elapsed_time": "2:02:42", "remaining_time": "2:16:34"}
47
+ {"current_steps": 470, "total_steps": 972, "loss": 1.1374, "learning_rate": 1.051790439954422e-05, "epoch": 0.9665809768637532, "percentage": 48.35, "elapsed_time": "2:05:32", "remaining_time": "2:14:05"}
48
+ {"current_steps": 480, "total_steps": 972, "loss": 1.135, "learning_rate": 1.0194894790868113e-05, "epoch": 0.987146529562982, "percentage": 49.38, "elapsed_time": "2:08:33", "remaining_time": "2:11:46"}
49
+ {"current_steps": 490, "total_steps": 972, "loss": 1.1268, "learning_rate": 9.871681579623028e-06, "epoch": 1.0077120822622108, "percentage": 50.41, "elapsed_time": "2:11:22", "remaining_time": "2:09:13"}
50
+ {"current_steps": 500, "total_steps": 972, "loss": 1.0911, "learning_rate": 9.548602419985584e-06, "epoch": 1.0282776349614395, "percentage": 51.44, "elapsed_time": "2:14:15", "remaining_time": "2:06:44"}
51
+ {"current_steps": 510, "total_steps": 972, "loss": 1.0816, "learning_rate": 9.225994826091431e-06, "epoch": 1.0488431876606683, "percentage": 52.47, "elapsed_time": "2:17:01", "remaining_time": "2:04:08"}
52
+ {"current_steps": 520, "total_steps": 972, "loss": 1.0833, "learning_rate": 8.904195819441222e-06, "epoch": 1.069408740359897, "percentage": 53.5, "elapsed_time": "2:19:30", "remaining_time": "2:01:15"}
53
+ {"current_steps": 530, "total_steps": 972, "loss": 1.081, "learning_rate": 8.583541576821191e-06, "epoch": 1.089974293059126, "percentage": 54.53, "elapsed_time": "2:22:16", "remaining_time": "1:58:39"}
54
+ {"current_steps": 540, "total_steps": 972, "loss": 1.0793, "learning_rate": 8.264367079106194e-06, "epoch": 1.1105398457583548, "percentage": 55.56, "elapsed_time": "2:24:47", "remaining_time": "1:55:49"}
55
+ {"current_steps": 550, "total_steps": 972, "loss": 1.0979, "learning_rate": 7.947005761312097e-06, "epoch": 1.1311053984575836, "percentage": 56.58, "elapsed_time": "2:27:17", "remaining_time": "1:53:00"}
56
+ {"current_steps": 560, "total_steps": 972, "loss": 1.0868, "learning_rate": 7.6317891642631e-06, "epoch": 1.1516709511568124, "percentage": 57.61, "elapsed_time": "2:29:56", "remaining_time": "1:50:18"}
57
+ {"current_steps": 570, "total_steps": 972, "loss": 1.0613, "learning_rate": 7.319046588237864e-06, "epoch": 1.1722365038560412, "percentage": 58.64, "elapsed_time": "2:32:22", "remaining_time": "1:47:28"}
58
+ {"current_steps": 580, "total_steps": 972, "loss": 1.0801, "learning_rate": 7.009104748956304e-06, "epoch": 1.19280205655527, "percentage": 59.67, "elapsed_time": "2:34:53", "remaining_time": "1:44:41"}
59
+ {"current_steps": 590, "total_steps": 972, "loss": 1.0838, "learning_rate": 6.7022874362664155e-06, "epoch": 1.2133676092544987, "percentage": 60.7, "elapsed_time": "2:37:35", "remaining_time": "1:42:02"}
60
+ {"current_steps": 600, "total_steps": 972, "loss": 1.0692, "learning_rate": 6.398915175887698e-06, "epoch": 1.2339331619537275, "percentage": 61.73, "elapsed_time": "2:39:55", "remaining_time": "1:39:09"}
61
+ {"current_steps": 610, "total_steps": 972, "loss": 1.093, "learning_rate": 6.099304894564544e-06, "epoch": 1.2544987146529563, "percentage": 62.76, "elapsed_time": "2:42:44", "remaining_time": "1:36:34"}
62
+ {"current_steps": 620, "total_steps": 972, "loss": 1.0781, "learning_rate": 5.8037695889794e-06, "epoch": 1.275064267352185, "percentage": 63.79, "elapsed_time": "2:45:09", "remaining_time": "1:33:46"}
63
+ {"current_steps": 630, "total_steps": 972, "loss": 1.0833, "learning_rate": 5.512617998771598e-06, "epoch": 1.2956298200514138, "percentage": 64.81, "elapsed_time": "2:47:44", "remaining_time": "1:31:03"}
64
+ {"current_steps": 640, "total_steps": 972, "loss": 1.0715, "learning_rate": 5.226154284003411e-06, "epoch": 1.3161953727506428, "percentage": 65.84, "elapsed_time": "2:50:09", "remaining_time": "1:28:15"}
65
+ {"current_steps": 650, "total_steps": 972, "loss": 1.0829, "learning_rate": 4.944677707410315e-06, "epoch": 1.3367609254498714, "percentage": 66.87, "elapsed_time": "2:52:51", "remaining_time": "1:25:37"}
66
+ {"current_steps": 660, "total_steps": 972, "loss": 1.0865, "learning_rate": 4.668482321767371e-06, "epoch": 1.3573264781491003, "percentage": 67.9, "elapsed_time": "2:55:20", "remaining_time": "1:22:53"}
67
+ {"current_steps": 670, "total_steps": 972, "loss": 1.0533, "learning_rate": 4.397856662698368e-06, "epoch": 1.3778920308483291, "percentage": 68.93, "elapsed_time": "2:58:05", "remaining_time": "1:20:16"}
68
+ {"current_steps": 680, "total_steps": 972, "loss": 1.0745, "learning_rate": 4.133083447248599e-06, "epoch": 1.398457583547558, "percentage": 69.96, "elapsed_time": "3:00:34", "remaining_time": "1:17:32"}
69
+ {"current_steps": 690, "total_steps": 972, "loss": 1.0899, "learning_rate": 3.874439278536187e-06, "epoch": 1.4190231362467867, "percentage": 70.99, "elapsed_time": "3:03:17", "remaining_time": "1:14:54"}
70
+ {"current_steps": 700, "total_steps": 972, "loss": 1.0784, "learning_rate": 3.6221943567905283e-06, "epoch": 1.4395886889460154, "percentage": 72.02, "elapsed_time": "3:05:56", "remaining_time": "1:12:15"}
71
+ {"current_steps": 710, "total_steps": 972, "loss": 1.0819, "learning_rate": 3.3766121970796716e-06, "epoch": 1.4601542416452442, "percentage": 73.05, "elapsed_time": "3:08:13", "remaining_time": "1:09:27"}
72
+ {"current_steps": 720, "total_steps": 972, "loss": 1.069, "learning_rate": 3.1379493540215677e-06, "epoch": 1.480719794344473, "percentage": 74.07, "elapsed_time": "3:11:01", "remaining_time": "1:06:51"}
73
+ {"current_steps": 730, "total_steps": 972, "loss": 1.0785, "learning_rate": 2.906455153766744e-06, "epoch": 1.5012853470437018, "percentage": 75.1, "elapsed_time": "3:13:47", "remaining_time": "1:04:14"}
74
+ {"current_steps": 740, "total_steps": 972, "loss": 1.057, "learning_rate": 2.6823714335324237e-06, "epoch": 1.5218508997429305, "percentage": 76.13, "elapsed_time": "3:16:46", "remaining_time": "1:01:41"}
75
+ {"current_steps": 750, "total_steps": 972, "loss": 1.0553, "learning_rate": 2.46593228896017e-06, "epoch": 1.5424164524421595, "percentage": 77.16, "elapsed_time": "3:19:31", "remaining_time": "0:59:03"}
76
+ {"current_steps": 760, "total_steps": 972, "loss": 1.0542, "learning_rate": 2.257363829560986e-06, "epoch": 1.562982005141388, "percentage": 78.19, "elapsed_time": "3:22:02", "remaining_time": "0:56:21"}
77
+ {"current_steps": 770, "total_steps": 972, "loss": 1.0799, "learning_rate": 2.0568839425033906e-06, "epoch": 1.583547557840617, "percentage": 79.22, "elapsed_time": "3:24:48", "remaining_time": "0:53:43"}
78
+ {"current_steps": 780, "total_steps": 972, "loss": 1.0571, "learning_rate": 1.864702064991173e-06, "epoch": 1.6041131105398456, "percentage": 80.25, "elapsed_time": "3:27:27", "remaining_time": "0:51:03"}
79
+ {"current_steps": 790, "total_steps": 972, "loss": 1.0472, "learning_rate": 1.6810189654686715e-06, "epoch": 1.6246786632390746, "percentage": 81.28, "elapsed_time": "3:30:17", "remaining_time": "0:48:26"}
80
+ {"current_steps": 800, "total_steps": 972, "loss": 1.0703, "learning_rate": 1.5060265338821123e-06, "epoch": 1.6452442159383034, "percentage": 82.3, "elapsed_time": "3:33:04", "remaining_time": "0:45:48"}
81
+ {"current_steps": 810, "total_steps": 972, "loss": 1.055, "learning_rate": 1.3399075812161488e-06, "epoch": 1.6658097686375322, "percentage": 83.33, "elapsed_time": "3:35:49", "remaining_time": "0:43:09"}
82
+ {"current_steps": 820, "total_steps": 972, "loss": 1.0622, "learning_rate": 1.1828356485149927e-06, "epoch": 1.686375321336761, "percentage": 84.36, "elapsed_time": "3:38:41", "remaining_time": "0:40:32"}
83
+ {"current_steps": 830, "total_steps": 972, "loss": 1.0526, "learning_rate": 1.0349748255876536e-06, "epoch": 1.7069408740359897, "percentage": 85.39, "elapsed_time": "3:42:02", "remaining_time": "0:37:59"}
84
+ {"current_steps": 840, "total_steps": 972, "loss": 1.051, "learning_rate": 8.964795795867176e-07, "epoch": 1.7275064267352185, "percentage": 86.42, "elapsed_time": "3:44:42", "remaining_time": "0:35:18"}
85
+ {"current_steps": 850, "total_steps": 972, "loss": 1.0574, "learning_rate": 7.67494593639686e-07, "epoch": 1.7480719794344473, "percentage": 87.45, "elapsed_time": "3:47:31", "remaining_time": "0:32:39"}
86
+ {"current_steps": 860, "total_steps": 972, "loss": 1.0589, "learning_rate": 6.481546157014996e-07, "epoch": 1.7686375321336762, "percentage": 88.48, "elapsed_time": "3:50:11", "remaining_time": "0:29:58"}
87
+ {"current_steps": 870, "total_steps": 972, "loss": 1.0578, "learning_rate": 5.385843177861261e-07, "epoch": 1.7892030848329048, "percentage": 89.51, "elapsed_time": "3:52:41", "remaining_time": "0:27:16"}
88
+ {"current_steps": 880, "total_steps": 972, "loss": 1.0663, "learning_rate": 4.388981657242819e-07, "epoch": 1.8097686375321338, "percentage": 90.53, "elapsed_time": "3:55:40", "remaining_time": "0:24:38"}
89
+ {"current_steps": 890, "total_steps": 972, "loss": 1.0671, "learning_rate": 3.4920029958333656e-07, "epoch": 1.8303341902313623, "percentage": 91.56, "elapsed_time": "3:58:04", "remaining_time": "0:21:56"}
90
+ {"current_steps": 900, "total_steps": 972, "loss": 1.0573, "learning_rate": 2.695844248743318e-07, "epoch": 1.8508997429305913, "percentage": 92.59, "elapsed_time": "4:00:51", "remaining_time": "0:19:16"}
91
+ {"current_steps": 910, "total_steps": 972, "loss": 1.063, "learning_rate": 2.0013371465976816e-07, "epoch": 1.87146529562982, "percentage": 93.62, "elapsed_time": "4:03:36", "remaining_time": "0:16:35"}
92
+ {"current_steps": 920, "total_steps": 972, "loss": 1.0703, "learning_rate": 1.409207226644227e-07, "epoch": 1.8920308483290489, "percentage": 94.65, "elapsed_time": "4:05:56", "remaining_time": "0:13:54"}
93
+ {"current_steps": 930, "total_steps": 972, "loss": 1.0615, "learning_rate": 9.200730747996211e-08, "epoch": 1.9125964010282777, "percentage": 95.68, "elapsed_time": "4:08:18", "remaining_time": "0:11:12"}
94
+ {"current_steps": 940, "total_steps": 972, "loss": 1.0591, "learning_rate": 5.344456794255881e-08, "epoch": 1.9331619537275064, "percentage": 96.71, "elapsed_time": "4:10:51", "remaining_time": "0:08:32"}
95
+ {"current_steps": 950, "total_steps": 972, "loss": 1.0591, "learning_rate": 2.5272789750980797e-08, "epoch": 1.9537275064267352, "percentage": 97.74, "elapsed_time": "4:13:33", "remaining_time": "0:05:52"}
96
+ {"current_steps": 960, "total_steps": 972, "loss": 1.0602, "learning_rate": 7.521403380956748e-09, "epoch": 1.974293059125964, "percentage": 98.77, "elapsed_time": "4:16:06", "remaining_time": "0:03:12"}
97
+ {"current_steps": 970, "total_steps": 972, "loss": 1.0495, "learning_rate": 2.089533397653387e-10, "epoch": 1.9948586118251928, "percentage": 99.79, "elapsed_time": "4:18:35", "remaining_time": "0:00:31"}
98
+ {"current_steps": 972, "total_steps": 972, "epoch": 1.9989717223650385, "percentage": 100.0, "elapsed_time": "4:19:12", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,709 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9989717223650385,
5
+ "eval_steps": 500,
6
+ "global_step": 972,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02056555269922879,
13
+ "grad_norm": 9.233743238441296,
14
+ "learning_rate": 1.9994839090452616e-05,
15
+ "loss": 1.5713,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.04113110539845758,
20
+ "grad_norm": 13.69020758087521,
21
+ "learning_rate": 1.9979236966675828e-05,
22
+ "loss": 1.3565,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.061696658097686374,
27
+ "grad_norm": 9.2629201307749,
28
+ "learning_rate": 1.9953209739827946e-05,
29
+ "loss": 1.3132,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.08226221079691516,
34
+ "grad_norm": 5.836967088114798,
35
+ "learning_rate": 1.9916784600016132e-05,
36
+ "loss": 1.2708,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.10282776349614396,
41
+ "grad_norm": 9.00423601885076,
42
+ "learning_rate": 1.9869999599832804e-05,
43
+ "loss": 1.2658,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.12339331619537275,
48
+ "grad_norm": 13.166982152661006,
49
+ "learning_rate": 1.981290361460287e-05,
50
+ "loss": 1.2531,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.14395886889460155,
55
+ "grad_norm": 10.728661259090346,
56
+ "learning_rate": 1.974555629132469e-05,
57
+ "loss": 1.2339,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.16452442159383032,
62
+ "grad_norm": 9.294779587967374,
63
+ "learning_rate": 1.9668027986358082e-05,
64
+ "loss": 1.2372,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.18508997429305912,
69
+ "grad_norm": 6.388693353299931,
70
+ "learning_rate": 1.9580399691924484e-05,
71
+ "loss": 1.2298,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.20565552699228792,
76
+ "grad_norm": 5.685294719278735,
77
+ "learning_rate": 1.9482762951496056e-05,
78
+ "loss": 1.2312,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.2262210796915167,
83
+ "grad_norm": 6.685866232367591,
84
+ "learning_rate": 1.9375219764162096e-05,
85
+ "loss": 1.2316,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2467866323907455,
90
+ "grad_norm": 7.688018717119547,
91
+ "learning_rate": 1.92578824780727e-05,
92
+ "loss": 1.2337,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.26735218508997427,
97
+ "grad_norm": 3.884064710067138,
98
+ "learning_rate": 1.913087367307095e-05,
99
+ "loss": 1.2136,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.2879177377892031,
104
+ "grad_norm": 9.444686410104936,
105
+ "learning_rate": 1.8994326032636318e-05,
106
+ "loss": 1.2072,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.30848329048843187,
111
+ "grad_norm": 4.864822081558493,
112
+ "learning_rate": 1.8848382205272924e-05,
113
+ "loss": 1.2017,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.32904884318766064,
118
+ "grad_norm": 5.9852253238798605,
119
+ "learning_rate": 1.869319465548762e-05,
120
+ "loss": 1.208,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.3496143958868895,
125
+ "grad_norm": 6.2970547396781225,
126
+ "learning_rate": 1.852892550451345e-05,
127
+ "loss": 1.2012,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.37017994858611825,
132
+ "grad_norm": 7.846752995277368,
133
+ "learning_rate": 1.835574636094494e-05,
134
+ "loss": 1.2035,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.390745501285347,
139
+ "grad_norm": 9.795450293111358,
140
+ "learning_rate": 1.8173838141462145e-05,
141
+ "loss": 1.2147,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.41131105398457585,
146
+ "grad_norm": 7.782933189444834,
147
+ "learning_rate": 1.798339088183071e-05,
148
+ "loss": 1.2126,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.4318766066838046,
153
+ "grad_norm": 5.494144367822917,
154
+ "learning_rate": 1.7784603538375453e-05,
155
+ "loss": 1.2089,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.4524421593830334,
160
+ "grad_norm": 6.609017931196138,
161
+ "learning_rate": 1.7577683780134756e-05,
162
+ "loss": 1.1879,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.4730077120822622,
167
+ "grad_norm": 8.906035242084766,
168
+ "learning_rate": 1.7362847771913035e-05,
169
+ "loss": 1.2097,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.493573264781491,
174
+ "grad_norm": 8.648775336727859,
175
+ "learning_rate": 1.714031994845782e-05,
176
+ "loss": 1.187,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5141388174807198,
181
+ "grad_norm": 5.843126331449411,
182
+ "learning_rate": 1.6910332779997378e-05,
183
+ "loss": 1.1835,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5347043701799485,
188
+ "grad_norm": 7.57208189767232,
189
+ "learning_rate": 1.6673126529383905e-05,
190
+ "loss": 1.1906,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.5552699228791774,
195
+ "grad_norm": 5.872037189234157,
196
+ "learning_rate": 1.642894900109584e-05,
197
+ "loss": 1.1736,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.5758354755784062,
202
+ "grad_norm": 5.59549822016061,
203
+ "learning_rate": 1.6178055282361642e-05,
204
+ "loss": 1.19,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.596401028277635,
209
+ "grad_norm": 7.1037529678120785,
210
+ "learning_rate": 1.5920707476675446e-05,
211
+ "loss": 1.1851,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6169665809768637,
216
+ "grad_norm": 4.7250598751432875,
217
+ "learning_rate": 1.565717442998292e-05,
218
+ "loss": 1.1824,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6375321336760925,
223
+ "grad_norm": 7.603461950437508,
224
+ "learning_rate": 1.5387731449823474e-05,
225
+ "loss": 1.1543,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.6580976863753213,
230
+ "grad_norm": 7.812378658902085,
231
+ "learning_rate": 1.5112660017722122e-05,
232
+ "loss": 1.1683,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.6786632390745502,
237
+ "grad_norm": 6.866611481508661,
238
+ "learning_rate": 1.4832247495131566e-05,
239
+ "loss": 1.1643,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.699228791773779,
244
+ "grad_norm": 8.447272563997627,
245
+ "learning_rate": 1.45467868232316e-05,
246
+ "loss": 1.1679,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7197943444730077,
251
+ "grad_norm": 8.29660722849121,
252
+ "learning_rate": 1.4256576216899494e-05,
253
+ "loss": 1.1605,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.7403598971722365,
258
+ "grad_norm": 6.408869669950844,
259
+ "learning_rate": 1.3961918853171073e-05,
260
+ "loss": 1.1681,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.7609254498714653,
265
+ "grad_norm": 7.257507857539118,
266
+ "learning_rate": 1.3663122554517917e-05,
267
+ "loss": 1.1545,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.781491002570694,
272
+ "grad_norm": 6.745599564457566,
273
+ "learning_rate": 1.3360499467271552e-05,
274
+ "loss": 1.167,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8020565552699229,
279
+ "grad_norm": 4.372254672475978,
280
+ "learning_rate": 1.3054365735530666e-05,
281
+ "loss": 1.1706,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.8226221079691517,
286
+ "grad_norm": 5.9583586806734585,
287
+ "learning_rate": 1.2745041170891827e-05,
288
+ "loss": 1.1512,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.8431876606683805,
293
+ "grad_norm": 8.218488729311929,
294
+ "learning_rate": 1.243284891834894e-05,
295
+ "loss": 1.161,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.8637532133676092,
300
+ "grad_norm": 9.05020466841952,
301
+ "learning_rate": 1.211811511871033e-05,
302
+ "loss": 1.1499,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.884318766066838,
307
+ "grad_norm": 7.133782169539759,
308
+ "learning_rate": 1.1801168567886159e-05,
309
+ "loss": 1.1428,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9048843187660668,
314
+ "grad_norm": 10.061681353175718,
315
+ "learning_rate": 1.1482340373402128e-05,
316
+ "loss": 1.1548,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.9254498714652957,
321
+ "grad_norm": 5.964595532826752,
322
+ "learning_rate": 1.1161963608498254e-05,
323
+ "loss": 1.1375,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.9460154241645244,
328
+ "grad_norm": 7.682863713931749,
329
+ "learning_rate": 1.0840372964174148e-05,
330
+ "loss": 1.1441,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.9665809768637532,
335
+ "grad_norm": 6.093064442303913,
336
+ "learning_rate": 1.051790439954422e-05,
337
+ "loss": 1.1374,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.987146529562982,
342
+ "grad_norm": 2.859419774137469,
343
+ "learning_rate": 1.0194894790868113e-05,
344
+ "loss": 1.135,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 1.0077120822622108,
349
+ "grad_norm": 5.504925974002832,
350
+ "learning_rate": 9.871681579623028e-06,
351
+ "loss": 1.1268,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 1.0282776349614395,
356
+ "grad_norm": 6.006410935514135,
357
+ "learning_rate": 9.548602419985584e-06,
358
+ "loss": 1.0911,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 1.0488431876606683,
363
+ "grad_norm": 3.2675854341672608,
364
+ "learning_rate": 9.225994826091431e-06,
365
+ "loss": 1.0816,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 1.069408740359897,
370
+ "grad_norm": 6.801925989140796,
371
+ "learning_rate": 8.904195819441222e-06,
372
+ "loss": 1.0833,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 1.089974293059126,
377
+ "grad_norm": 3.6643836420434663,
378
+ "learning_rate": 8.583541576821191e-06,
379
+ "loss": 1.081,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 1.1105398457583548,
384
+ "grad_norm": 6.747377788645208,
385
+ "learning_rate": 8.264367079106194e-06,
386
+ "loss": 1.0793,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 1.1311053984575836,
391
+ "grad_norm": 6.372537375904327,
392
+ "learning_rate": 7.947005761312097e-06,
393
+ "loss": 1.0979,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 1.1516709511568124,
398
+ "grad_norm": 6.925714108622525,
399
+ "learning_rate": 7.6317891642631e-06,
400
+ "loss": 1.0868,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 1.1722365038560412,
405
+ "grad_norm": 7.332135497496814,
406
+ "learning_rate": 7.319046588237864e-06,
407
+ "loss": 1.0613,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 1.19280205655527,
412
+ "grad_norm": 3.4981756709446454,
413
+ "learning_rate": 7.009104748956304e-06,
414
+ "loss": 1.0801,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 1.2133676092544987,
419
+ "grad_norm": 5.6660043695937,
420
+ "learning_rate": 6.7022874362664155e-06,
421
+ "loss": 1.0838,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 1.2339331619537275,
426
+ "grad_norm": 6.6393615146162634,
427
+ "learning_rate": 6.398915175887698e-06,
428
+ "loss": 1.0692,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 1.2544987146529563,
433
+ "grad_norm": 9.01722626725686,
434
+ "learning_rate": 6.099304894564544e-06,
435
+ "loss": 1.093,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 1.275064267352185,
440
+ "grad_norm": 7.465032128492785,
441
+ "learning_rate": 5.8037695889794e-06,
442
+ "loss": 1.0781,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 1.2956298200514138,
447
+ "grad_norm": 8.243642393853053,
448
+ "learning_rate": 5.512617998771598e-06,
449
+ "loss": 1.0833,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 1.3161953727506428,
454
+ "grad_norm": 3.1779811319825577,
455
+ "learning_rate": 5.226154284003411e-06,
456
+ "loss": 1.0715,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 1.3367609254498714,
461
+ "grad_norm": 4.120350391737107,
462
+ "learning_rate": 4.944677707410315e-06,
463
+ "loss": 1.0829,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 1.3573264781491003,
468
+ "grad_norm": 7.105813120974067,
469
+ "learning_rate": 4.668482321767371e-06,
470
+ "loss": 1.0865,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 1.3778920308483291,
475
+ "grad_norm": 8.035377582845337,
476
+ "learning_rate": 4.397856662698368e-06,
477
+ "loss": 1.0533,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 1.398457583547558,
482
+ "grad_norm": 8.049531770624485,
483
+ "learning_rate": 4.133083447248599e-06,
484
+ "loss": 1.0745,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 1.4190231362467867,
489
+ "grad_norm": 7.225962565044245,
490
+ "learning_rate": 3.874439278536187e-06,
491
+ "loss": 1.0899,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 1.4395886889460154,
496
+ "grad_norm": 7.270761540137814,
497
+ "learning_rate": 3.6221943567905283e-06,
498
+ "loss": 1.0784,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 1.4601542416452442,
503
+ "grad_norm": 8.705361491327107,
504
+ "learning_rate": 3.3766121970796716e-06,
505
+ "loss": 1.0819,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 1.480719794344473,
510
+ "grad_norm": 4.183940499981808,
511
+ "learning_rate": 3.1379493540215677e-06,
512
+ "loss": 1.069,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 1.5012853470437018,
517
+ "grad_norm": 6.398726679627311,
518
+ "learning_rate": 2.906455153766744e-06,
519
+ "loss": 1.0785,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 1.5218508997429305,
524
+ "grad_norm": 13.601116552168905,
525
+ "learning_rate": 2.6823714335324237e-06,
526
+ "loss": 1.057,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 1.5424164524421595,
531
+ "grad_norm": 5.5895207138975,
532
+ "learning_rate": 2.46593228896017e-06,
533
+ "loss": 1.0553,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 1.562982005141388,
538
+ "grad_norm": 6.267057233279022,
539
+ "learning_rate": 2.257363829560986e-06,
540
+ "loss": 1.0542,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 1.583547557840617,
545
+ "grad_norm": 4.378216644983502,
546
+ "learning_rate": 2.0568839425033906e-06,
547
+ "loss": 1.0799,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 1.6041131105398456,
552
+ "grad_norm": 7.255472699627192,
553
+ "learning_rate": 1.864702064991173e-06,
554
+ "loss": 1.0571,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 1.6246786632390746,
559
+ "grad_norm": 6.289474192540149,
560
+ "learning_rate": 1.6810189654686715e-06,
561
+ "loss": 1.0472,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 1.6452442159383034,
566
+ "grad_norm": 6.589217658649451,
567
+ "learning_rate": 1.5060265338821123e-06,
568
+ "loss": 1.0703,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 1.6658097686375322,
573
+ "grad_norm": 4.865701816340032,
574
+ "learning_rate": 1.3399075812161488e-06,
575
+ "loss": 1.055,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 1.686375321336761,
580
+ "grad_norm": 8.65763359081179,
581
+ "learning_rate": 1.1828356485149927e-06,
582
+ "loss": 1.0622,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 1.7069408740359897,
587
+ "grad_norm": 6.174972638755989,
588
+ "learning_rate": 1.0349748255876536e-06,
589
+ "loss": 1.0526,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 1.7275064267352185,
594
+ "grad_norm": 4.986705584850829,
595
+ "learning_rate": 8.964795795867176e-07,
596
+ "loss": 1.051,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 1.7480719794344473,
601
+ "grad_norm": 9.202122011281354,
602
+ "learning_rate": 7.67494593639686e-07,
603
+ "loss": 1.0574,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 1.7686375321336762,
608
+ "grad_norm": 8.058395431378568,
609
+ "learning_rate": 6.481546157014996e-07,
610
+ "loss": 1.0589,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 1.7892030848329048,
615
+ "grad_norm": 5.3354582297297135,
616
+ "learning_rate": 5.385843177861261e-07,
617
+ "loss": 1.0578,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 1.8097686375321338,
622
+ "grad_norm": 3.8239017444437415,
623
+ "learning_rate": 4.388981657242819e-07,
624
+ "loss": 1.0663,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 1.8303341902313623,
629
+ "grad_norm": 10.032769787716335,
630
+ "learning_rate": 3.4920029958333656e-07,
631
+ "loss": 1.0671,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 1.8508997429305913,
636
+ "grad_norm": 4.449303124886201,
637
+ "learning_rate": 2.695844248743318e-07,
638
+ "loss": 1.0573,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 1.87146529562982,
643
+ "grad_norm": 6.5875403409786735,
644
+ "learning_rate": 2.0013371465976816e-07,
645
+ "loss": 1.063,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 1.8920308483290489,
650
+ "grad_norm": 6.1087849946753545,
651
+ "learning_rate": 1.409207226644227e-07,
652
+ "loss": 1.0703,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 1.9125964010282777,
657
+ "grad_norm": 9.357948853303002,
658
+ "learning_rate": 9.200730747996211e-08,
659
+ "loss": 1.0615,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 1.9331619537275064,
664
+ "grad_norm": 6.746455746388351,
665
+ "learning_rate": 5.344456794255881e-08,
666
+ "loss": 1.0591,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 1.9537275064267352,
671
+ "grad_norm": 4.307020198331092,
672
+ "learning_rate": 2.5272789750980797e-08,
673
+ "loss": 1.0591,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 1.974293059125964,
678
+ "grad_norm": 2.368072060390636,
679
+ "learning_rate": 7.521403380956748e-09,
680
+ "loss": 1.0602,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 1.9948586118251928,
685
+ "grad_norm": 6.97337278897093,
686
+ "learning_rate": 2.089533397653387e-10,
687
+ "loss": 1.0495,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 1.9989717223650385,
692
+ "step": 972,
693
+ "total_flos": 9.034546879177687e+18,
694
+ "train_loss": 1.1365475546675945,
695
+ "train_runtime": 15552.1986,
696
+ "train_samples_per_second": 32.015,
697
+ "train_steps_per_second": 0.062
698
+ }
699
+ ],
700
+ "logging_steps": 10,
701
+ "max_steps": 972,
702
+ "num_input_tokens_seen": 0,
703
+ "num_train_epochs": 2,
704
+ "save_steps": 500,
705
+ "total_flos": 9.034546879177687e+18,
706
+ "train_batch_size": 8,
707
+ "trial_name": null,
708
+ "trial_params": null
709
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88259951b8c38f0d8395204b60d4008234b2092a5e8c6a346ddf1d6f5e27f01f
3
+ size 6520
training_loss.png ADDED