Delta-Vector commited on
Commit
efb7a8c
·
verified ·
1 Parent(s): cea2cb2

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128019,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 3072,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 9216,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 8.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.45.0.dev0",
34
+ "use_cache": false,
35
+ "vocab_size": 128256
36
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "transformers_version": "4.45.0.dev0"
7
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8acd5cd8c1131a9db8dcd3064c5476a547a0120767779bed5507b241371cb89
3
+ size 4978354640
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98df118622d1b9ebfe84684a1ac7669bc03b8ebbb2029b6ffabbb742881deb87
3
+ size 4047172128
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 9025492992
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.norm.weight": "model-00002-of-00002.safetensors"
297
+ }
298
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
3
+ size 14244
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|im_start|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|im_end|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|im_end|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|finetune_right_pad_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
trainer_state.json ADDED
@@ -0,0 +1,1423 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9990344383649823,
5
+ "eval_steps": 49,
6
+ "global_step": 194,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.005149662053427744,
13
+ "grad_norm": 9.3125,
14
+ "learning_rate": 5.555555555555555e-07,
15
+ "loss": 1.6733,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.005149662053427744,
20
+ "eval_loss": 1.6590306758880615,
21
+ "eval_runtime": 1698.6705,
22
+ "eval_samples_per_second": 0.555,
23
+ "eval_steps_per_second": 0.555,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.010299324106855488,
28
+ "grad_norm": 9.5625,
29
+ "learning_rate": 1.111111111111111e-06,
30
+ "loss": 1.6598,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.01544898616028323,
35
+ "grad_norm": 13.9375,
36
+ "learning_rate": 1.6666666666666667e-06,
37
+ "loss": 1.6732,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.020598648213710977,
42
+ "grad_norm": 14.125,
43
+ "learning_rate": 2.222222222222222e-06,
44
+ "loss": 1.6195,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.025748310267138717,
49
+ "grad_norm": 17.125,
50
+ "learning_rate": 2.7777777777777783e-06,
51
+ "loss": 1.6886,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.03089797232056646,
56
+ "grad_norm": 14.9375,
57
+ "learning_rate": 3.3333333333333333e-06,
58
+ "loss": 1.6817,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.036047634373994206,
63
+ "grad_norm": 13.125,
64
+ "learning_rate": 3.88888888888889e-06,
65
+ "loss": 1.6891,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.04119729642742195,
70
+ "grad_norm": 9.875,
71
+ "learning_rate": 4.444444444444444e-06,
72
+ "loss": 1.6443,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.046346958480849694,
77
+ "grad_norm": 9.25,
78
+ "learning_rate": 5e-06,
79
+ "loss": 1.6221,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.051496620534277435,
84
+ "grad_norm": 7.875,
85
+ "learning_rate": 5.555555555555557e-06,
86
+ "loss": 1.6435,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.05664628258770518,
91
+ "grad_norm": 10.0625,
92
+ "learning_rate": 6.111111111111112e-06,
93
+ "loss": 1.6459,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.06179594464113292,
98
+ "grad_norm": 7.0,
99
+ "learning_rate": 6.666666666666667e-06,
100
+ "loss": 1.6,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.06694560669456066,
105
+ "grad_norm": 6.78125,
106
+ "learning_rate": 7.222222222222223e-06,
107
+ "loss": 1.6128,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.07209526874798841,
112
+ "grad_norm": 4.1875,
113
+ "learning_rate": 7.77777777777778e-06,
114
+ "loss": 1.5681,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.07724493080141616,
119
+ "grad_norm": 2.875,
120
+ "learning_rate": 8.333333333333334e-06,
121
+ "loss": 1.5742,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.0823945928548439,
126
+ "grad_norm": 2.734375,
127
+ "learning_rate": 8.888888888888888e-06,
128
+ "loss": 1.5442,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.08754425490827164,
133
+ "grad_norm": 2.234375,
134
+ "learning_rate": 9.444444444444445e-06,
135
+ "loss": 1.5707,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.09269391696169939,
140
+ "grad_norm": 1.8125,
141
+ "learning_rate": 1e-05,
142
+ "loss": 1.5419,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.09784357901512714,
147
+ "grad_norm": 1.890625,
148
+ "learning_rate": 1.0555555555555557e-05,
149
+ "loss": 1.5595,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.10299324106855487,
154
+ "grad_norm": 1.578125,
155
+ "learning_rate": 1.1111111111111113e-05,
156
+ "loss": 1.5199,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.10814290312198262,
161
+ "grad_norm": 1.4296875,
162
+ "learning_rate": 1.1666666666666668e-05,
163
+ "loss": 1.5539,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.11329256517541036,
168
+ "grad_norm": 1.3125,
169
+ "learning_rate": 1.2222222222222224e-05,
170
+ "loss": 1.5596,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.11844222722883811,
175
+ "grad_norm": 1.03125,
176
+ "learning_rate": 1.2777777777777777e-05,
177
+ "loss": 1.5245,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.12359188928226585,
182
+ "grad_norm": 0.99609375,
183
+ "learning_rate": 1.3333333333333333e-05,
184
+ "loss": 1.5023,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.1287415513356936,
189
+ "grad_norm": 1.0546875,
190
+ "learning_rate": 1.388888888888889e-05,
191
+ "loss": 1.5238,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.13389121338912133,
196
+ "grad_norm": 0.9765625,
197
+ "learning_rate": 1.4444444444444446e-05,
198
+ "loss": 1.5156,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.1390408754425491,
203
+ "grad_norm": 0.9921875,
204
+ "learning_rate": 1.5000000000000002e-05,
205
+ "loss": 1.4935,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.14419053749597682,
210
+ "grad_norm": 0.890625,
211
+ "learning_rate": 1.555555555555556e-05,
212
+ "loss": 1.4596,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.14934019954940458,
217
+ "grad_norm": 0.9375,
218
+ "learning_rate": 1.6111111111111115e-05,
219
+ "loss": 1.4786,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.15448986160283232,
224
+ "grad_norm": 0.9140625,
225
+ "learning_rate": 1.6666666666666667e-05,
226
+ "loss": 1.5071,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.15963952365626005,
231
+ "grad_norm": 0.91015625,
232
+ "learning_rate": 1.7222222222222224e-05,
233
+ "loss": 1.483,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.1647891857096878,
238
+ "grad_norm": 0.83984375,
239
+ "learning_rate": 1.7777777777777777e-05,
240
+ "loss": 1.4428,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.16993884776311555,
245
+ "grad_norm": 0.91015625,
246
+ "learning_rate": 1.8333333333333333e-05,
247
+ "loss": 1.4917,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.17508850981654328,
252
+ "grad_norm": 1.03125,
253
+ "learning_rate": 1.888888888888889e-05,
254
+ "loss": 1.4407,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.18023817186997104,
259
+ "grad_norm": 1.09375,
260
+ "learning_rate": 1.9444444444444445e-05,
261
+ "loss": 1.4626,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.18538783392339878,
266
+ "grad_norm": 0.8671875,
267
+ "learning_rate": 2e-05,
268
+ "loss": 1.4678,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.1905374959768265,
273
+ "grad_norm": 0.9296875,
274
+ "learning_rate": 1.9999601726381415e-05,
275
+ "loss": 1.446,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.19568715803025427,
280
+ "grad_norm": 1.046875,
281
+ "learning_rate": 1.9998406937250035e-05,
282
+ "loss": 1.4688,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.200836820083682,
287
+ "grad_norm": 0.9140625,
288
+ "learning_rate": 1.9996415727776456e-05,
289
+ "loss": 1.4704,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.20598648213710974,
294
+ "grad_norm": 0.984375,
295
+ "learning_rate": 1.999362825656992e-05,
296
+ "loss": 1.4307,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.2111361441905375,
301
+ "grad_norm": 1.015625,
302
+ "learning_rate": 1.9990044745665672e-05,
303
+ "loss": 1.4086,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.21628580624396523,
308
+ "grad_norm": 0.8828125,
309
+ "learning_rate": 1.998566548050729e-05,
310
+ "loss": 1.4272,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.221435468297393,
315
+ "grad_norm": 0.890625,
316
+ "learning_rate": 1.9980490809923928e-05,
317
+ "loss": 1.4274,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.22658513035082073,
322
+ "grad_norm": 0.828125,
323
+ "learning_rate": 1.9974521146102535e-05,
324
+ "loss": 1.3833,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.23173479240424846,
329
+ "grad_norm": 0.9453125,
330
+ "learning_rate": 1.9967756964555044e-05,
331
+ "loss": 1.4207,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.23688445445767622,
336
+ "grad_norm": 0.8515625,
337
+ "learning_rate": 1.9960198804080462e-05,
338
+ "loss": 1.4168,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.24203411651110396,
343
+ "grad_norm": 0.85546875,
344
+ "learning_rate": 1.995184726672197e-05,
345
+ "loss": 1.3842,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.2471837785645317,
350
+ "grad_norm": 0.89453125,
351
+ "learning_rate": 1.9942703017718977e-05,
352
+ "loss": 1.4107,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.2523334406179594,
357
+ "grad_norm": 0.8671875,
358
+ "learning_rate": 1.99327667854541e-05,
359
+ "loss": 1.4425,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.2523334406179594,
364
+ "eval_loss": 1.304018259048462,
365
+ "eval_runtime": 1700.3742,
366
+ "eval_samples_per_second": 0.554,
367
+ "eval_steps_per_second": 0.554,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.2574831026713872,
372
+ "grad_norm": 0.8359375,
373
+ "learning_rate": 1.9922039361395186e-05,
374
+ "loss": 1.3989,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.26263276472481495,
379
+ "grad_norm": 0.86328125,
380
+ "learning_rate": 1.991052160003223e-05,
381
+ "loss": 1.373,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.26778242677824265,
386
+ "grad_norm": 0.83203125,
387
+ "learning_rate": 1.989821441880933e-05,
388
+ "loss": 1.392,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.2729320888316704,
393
+ "grad_norm": 0.82421875,
394
+ "learning_rate": 1.9885118798051607e-05,
395
+ "loss": 1.403,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.2780817508850982,
400
+ "grad_norm": 0.80859375,
401
+ "learning_rate": 1.9871235780887114e-05,
402
+ "loss": 1.4111,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.2832314129385259,
407
+ "grad_norm": 0.77734375,
408
+ "learning_rate": 1.9856566473163747e-05,
409
+ "loss": 1.3713,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 0.28838107499195365,
414
+ "grad_norm": 0.81640625,
415
+ "learning_rate": 1.984111204336116e-05,
416
+ "loss": 1.3748,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 0.2935307370453814,
421
+ "grad_norm": 0.83984375,
422
+ "learning_rate": 1.9824873722497694e-05,
423
+ "loss": 1.3923,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 0.29868039909880917,
428
+ "grad_norm": 0.80078125,
429
+ "learning_rate": 1.9807852804032306e-05,
430
+ "loss": 1.36,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 0.3038300611522369,
435
+ "grad_norm": 0.83203125,
436
+ "learning_rate": 1.9790050643761552e-05,
437
+ "loss": 1.3809,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 0.30897972320566464,
442
+ "grad_norm": 0.7578125,
443
+ "learning_rate": 1.9771468659711595e-05,
444
+ "loss": 1.4097,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 0.3141293852590924,
449
+ "grad_norm": 0.828125,
450
+ "learning_rate": 1.975210833202524e-05,
451
+ "loss": 1.4105,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 0.3192790473125201,
456
+ "grad_norm": 0.74609375,
457
+ "learning_rate": 1.9731971202844036e-05,
458
+ "loss": 1.3961,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 0.32442870936594786,
463
+ "grad_norm": 0.83984375,
464
+ "learning_rate": 1.9711058876185446e-05,
465
+ "loss": 1.4012,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 0.3295783714193756,
470
+ "grad_norm": 0.76953125,
471
+ "learning_rate": 1.9689373017815076e-05,
472
+ "loss": 1.3832,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 0.33472803347280333,
477
+ "grad_norm": 0.91796875,
478
+ "learning_rate": 1.9666915355113976e-05,
479
+ "loss": 1.3909,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 0.3398776955262311,
484
+ "grad_norm": 0.73828125,
485
+ "learning_rate": 1.964368767694107e-05,
486
+ "loss": 1.382,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 0.34502735757965886,
491
+ "grad_norm": 0.84375,
492
+ "learning_rate": 1.9619691833490645e-05,
493
+ "loss": 1.3805,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 0.35017701963308656,
498
+ "grad_norm": 0.7578125,
499
+ "learning_rate": 1.9594929736144978e-05,
500
+ "loss": 1.3804,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 0.3553266816865143,
505
+ "grad_norm": 0.76953125,
506
+ "learning_rate": 1.956940335732209e-05,
507
+ "loss": 1.3655,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 0.3604763437399421,
512
+ "grad_norm": 0.7265625,
513
+ "learning_rate": 1.954311473031864e-05,
514
+ "loss": 1.3518,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 0.3656260057933698,
519
+ "grad_norm": 0.8125,
520
+ "learning_rate": 1.9516065949147945e-05,
521
+ "loss": 1.3908,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 0.37077566784679755,
526
+ "grad_norm": 0.73828125,
527
+ "learning_rate": 1.9488259168373198e-05,
528
+ "loss": 1.359,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 0.3759253299002253,
533
+ "grad_norm": 0.7890625,
534
+ "learning_rate": 1.9459696602935838e-05,
535
+ "loss": 1.3655,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 0.381074991953653,
540
+ "grad_norm": 0.76953125,
541
+ "learning_rate": 1.9430380527979124e-05,
542
+ "loss": 1.3783,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 0.3862246540070808,
547
+ "grad_norm": 0.77734375,
548
+ "learning_rate": 1.94003132786669e-05,
549
+ "loss": 1.3515,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 0.39137431606050854,
554
+ "grad_norm": 0.7109375,
555
+ "learning_rate": 1.936949724999762e-05,
556
+ "loss": 1.3505,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 0.39652397811393625,
561
+ "grad_norm": 0.76953125,
562
+ "learning_rate": 1.9337934896613516e-05,
563
+ "loss": 1.3355,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 0.401673640167364,
568
+ "grad_norm": 0.796875,
569
+ "learning_rate": 1.930562873260514e-05,
570
+ "loss": 1.3004,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 0.40682330222079177,
575
+ "grad_norm": 0.765625,
576
+ "learning_rate": 1.927258133131105e-05,
577
+ "loss": 1.3993,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 0.4119729642742195,
582
+ "grad_norm": 0.80078125,
583
+ "learning_rate": 1.9238795325112867e-05,
584
+ "loss": 1.362,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 0.41712262632764724,
589
+ "grad_norm": 0.77734375,
590
+ "learning_rate": 1.9204273405225588e-05,
591
+ "loss": 1.402,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 0.422272288381075,
596
+ "grad_norm": 0.734375,
597
+ "learning_rate": 1.9169018321483198e-05,
598
+ "loss": 1.344,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 0.42742195043450276,
603
+ "grad_norm": 0.74609375,
604
+ "learning_rate": 1.9133032882119656e-05,
605
+ "loss": 1.3598,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 0.43257161248793047,
610
+ "grad_norm": 0.77734375,
611
+ "learning_rate": 1.9096319953545186e-05,
612
+ "loss": 1.3534,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 0.43772127454135823,
617
+ "grad_norm": 0.75390625,
618
+ "learning_rate": 1.9058882460117972e-05,
619
+ "loss": 1.3772,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 0.442870936594786,
624
+ "grad_norm": 0.7421875,
625
+ "learning_rate": 1.9020723383911214e-05,
626
+ "loss": 1.377,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 0.4480205986482137,
631
+ "grad_norm": 0.765625,
632
+ "learning_rate": 1.8981845764475585e-05,
633
+ "loss": 1.3455,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 0.45317026070164146,
638
+ "grad_norm": 0.75,
639
+ "learning_rate": 1.8942252698597113e-05,
640
+ "loss": 1.3543,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 0.4583199227550692,
645
+ "grad_norm": 0.76953125,
646
+ "learning_rate": 1.890194734005053e-05,
647
+ "loss": 1.348,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 0.4634695848084969,
652
+ "grad_norm": 0.77734375,
653
+ "learning_rate": 1.8860932899348028e-05,
654
+ "loss": 1.3453,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 0.4686192468619247,
659
+ "grad_norm": 0.74609375,
660
+ "learning_rate": 1.881921264348355e-05,
661
+ "loss": 1.3391,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 0.47376890891535245,
666
+ "grad_norm": 0.73828125,
667
+ "learning_rate": 1.8776789895672557e-05,
668
+ "loss": 1.3562,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 0.47891857096878016,
673
+ "grad_norm": 0.7734375,
674
+ "learning_rate": 1.8733668035087302e-05,
675
+ "loss": 1.3366,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 0.4840682330222079,
680
+ "grad_norm": 0.72265625,
681
+ "learning_rate": 1.8689850496587674e-05,
682
+ "loss": 1.3733,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 0.4892178950756357,
687
+ "grad_norm": 0.79296875,
688
+ "learning_rate": 1.8645340770447595e-05,
689
+ "loss": 1.3383,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 0.4943675571290634,
694
+ "grad_norm": 0.77734375,
695
+ "learning_rate": 1.8600142402077006e-05,
696
+ "loss": 1.3333,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 0.49951721918249115,
701
+ "grad_norm": 0.875,
702
+ "learning_rate": 1.8554258991739454e-05,
703
+ "loss": 1.3422,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 0.5046668812359189,
708
+ "grad_norm": 0.80078125,
709
+ "learning_rate": 1.850769419426531e-05,
710
+ "loss": 1.3564,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 0.5046668812359189,
715
+ "eval_loss": 1.2450780868530273,
716
+ "eval_runtime": 1700.3802,
717
+ "eval_samples_per_second": 0.554,
718
+ "eval_steps_per_second": 0.554,
719
+ "step": 98
720
+ },
721
+ {
722
+ "epoch": 0.5098165432893467,
723
+ "grad_norm": 0.875,
724
+ "learning_rate": 1.8460451718760653e-05,
725
+ "loss": 1.3322,
726
+ "step": 99
727
+ },
728
+ {
729
+ "epoch": 0.5149662053427744,
730
+ "grad_norm": 0.75390625,
731
+ "learning_rate": 1.8412535328311813e-05,
732
+ "loss": 1.3379,
733
+ "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.5201158673962021,
737
+ "grad_norm": 0.88671875,
738
+ "learning_rate": 1.8363948839685638e-05,
739
+ "loss": 1.3512,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.5252655294496299,
744
+ "grad_norm": 0.7734375,
745
+ "learning_rate": 1.8314696123025456e-05,
746
+ "loss": 1.3655,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.5304151915030576,
751
+ "grad_norm": 0.84765625,
752
+ "learning_rate": 1.8264781101542797e-05,
753
+ "loss": 1.3363,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.5355648535564853,
758
+ "grad_norm": 0.83203125,
759
+ "learning_rate": 1.8214207751204917e-05,
760
+ "loss": 1.3398,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.5407145156099131,
765
+ "grad_norm": 0.85546875,
766
+ "learning_rate": 1.816298010041806e-05,
767
+ "loss": 1.3327,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.5458641776633408,
772
+ "grad_norm": 0.82421875,
773
+ "learning_rate": 1.8111102229706593e-05,
774
+ "loss": 1.343,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.5510138397167685,
779
+ "grad_norm": 0.78515625,
780
+ "learning_rate": 1.805857827138798e-05,
781
+ "loss": 1.3181,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.5561635017701964,
786
+ "grad_norm": 0.78515625,
787
+ "learning_rate": 1.8005412409243604e-05,
788
+ "loss": 1.3375,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.5613131638236241,
793
+ "grad_norm": 0.74609375,
794
+ "learning_rate": 1.7951608878185533e-05,
795
+ "loss": 1.2939,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.5664628258770518,
800
+ "grad_norm": 0.91796875,
801
+ "learning_rate": 1.789717196391916e-05,
802
+ "loss": 1.3739,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.5716124879304796,
807
+ "grad_norm": 0.74609375,
808
+ "learning_rate": 1.7842106002601854e-05,
809
+ "loss": 1.3492,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.5767621499839073,
814
+ "grad_norm": 0.828125,
815
+ "learning_rate": 1.778641538049755e-05,
816
+ "loss": 1.3026,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.581911812037335,
821
+ "grad_norm": 0.84765625,
822
+ "learning_rate": 1.773010453362737e-05,
823
+ "loss": 1.2874,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.5870614740907628,
828
+ "grad_norm": 0.82421875,
829
+ "learning_rate": 1.7673177947416258e-05,
830
+ "loss": 1.328,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.5922111361441905,
835
+ "grad_norm": 0.84375,
836
+ "learning_rate": 1.7615640156335713e-05,
837
+ "loss": 1.3258,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.5973607981976183,
842
+ "grad_norm": 0.78515625,
843
+ "learning_rate": 1.7557495743542586e-05,
844
+ "loss": 1.3586,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.602510460251046,
849
+ "grad_norm": 0.7890625,
850
+ "learning_rate": 1.749874934051401e-05,
851
+ "loss": 1.2967,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.6076601223044737,
856
+ "grad_norm": 0.75390625,
857
+ "learning_rate": 1.7439405626678496e-05,
858
+ "loss": 1.3443,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.6128097843579016,
863
+ "grad_norm": 0.875,
864
+ "learning_rate": 1.7379469329043166e-05,
865
+ "loss": 1.3578,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.6179594464113293,
870
+ "grad_norm": 0.82421875,
871
+ "learning_rate": 1.7318945221817255e-05,
872
+ "loss": 1.353,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.623109108464757,
877
+ "grad_norm": 0.79296875,
878
+ "learning_rate": 1.7257838126031797e-05,
879
+ "loss": 1.3388,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.6282587705181848,
884
+ "grad_norm": 0.8125,
885
+ "learning_rate": 1.719615290915563e-05,
886
+ "loss": 1.3432,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.6334084325716125,
891
+ "grad_norm": 0.7890625,
892
+ "learning_rate": 1.7133894484707657e-05,
893
+ "loss": 1.3497,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.6385580946250402,
898
+ "grad_norm": 0.82421875,
899
+ "learning_rate": 1.7071067811865477e-05,
900
+ "loss": 1.3239,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.643707756678468,
905
+ "grad_norm": 0.765625,
906
+ "learning_rate": 1.7007677895070358e-05,
907
+ "loss": 1.3457,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.6488574187318957,
912
+ "grad_norm": 0.765625,
913
+ "learning_rate": 1.694372978362861e-05,
914
+ "loss": 1.3505,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.6540070807853234,
919
+ "grad_norm": 0.890625,
920
+ "learning_rate": 1.6879228571309377e-05,
921
+ "loss": 1.3564,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.6591567428387513,
926
+ "grad_norm": 0.71484375,
927
+ "learning_rate": 1.6814179395938915e-05,
928
+ "loss": 1.315,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.664306404892179,
933
+ "grad_norm": 0.9140625,
934
+ "learning_rate": 1.6748587438991303e-05,
935
+ "loss": 1.3245,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.6694560669456067,
940
+ "grad_norm": 0.8125,
941
+ "learning_rate": 1.6682457925175762e-05,
942
+ "loss": 1.3176,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.6746057289990345,
947
+ "grad_norm": 0.72265625,
948
+ "learning_rate": 1.6615796122020443e-05,
949
+ "loss": 1.335,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.6797553910524622,
954
+ "grad_norm": 0.84375,
955
+ "learning_rate": 1.6548607339452853e-05,
956
+ "loss": 1.3302,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.6849050531058899,
961
+ "grad_norm": 0.80859375,
962
+ "learning_rate": 1.6480896929376905e-05,
963
+ "loss": 1.3532,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.6900547151593177,
968
+ "grad_norm": 0.93359375,
969
+ "learning_rate": 1.641267028524661e-05,
970
+ "loss": 1.2829,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.6952043772127454,
975
+ "grad_norm": 0.79296875,
976
+ "learning_rate": 1.6343932841636455e-05,
977
+ "loss": 1.2986,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.7003540392661731,
982
+ "grad_norm": 0.765625,
983
+ "learning_rate": 1.627469007380852e-05,
984
+ "loss": 1.3589,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.7055037013196009,
989
+ "grad_norm": 0.79296875,
990
+ "learning_rate": 1.6204947497276346e-05,
991
+ "loss": 1.3704,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.7106533633730286,
996
+ "grad_norm": 0.765625,
997
+ "learning_rate": 1.6134710667365598e-05,
998
+ "loss": 1.3371,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.7158030254264564,
1003
+ "grad_norm": 0.87109375,
1004
+ "learning_rate": 1.6063985178771555e-05,
1005
+ "loss": 1.3284,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.7209526874798842,
1010
+ "grad_norm": 0.75,
1011
+ "learning_rate": 1.599277666511347e-05,
1012
+ "loss": 1.3307,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.7261023495333119,
1017
+ "grad_norm": 0.75,
1018
+ "learning_rate": 1.592109079848583e-05,
1019
+ "loss": 1.3265,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.7312520115867396,
1024
+ "grad_norm": 0.7421875,
1025
+ "learning_rate": 1.584893328900653e-05,
1026
+ "loss": 1.3313,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.7364016736401674,
1031
+ "grad_norm": 0.7421875,
1032
+ "learning_rate": 1.577630988436206e-05,
1033
+ "loss": 1.345,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.7415513356935951,
1038
+ "grad_norm": 0.71484375,
1039
+ "learning_rate": 1.5703226369349642e-05,
1040
+ "loss": 1.2963,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.7467009977470228,
1045
+ "grad_norm": 0.77734375,
1046
+ "learning_rate": 1.562968856541648e-05,
1047
+ "loss": 1.3287,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.7518506598004506,
1052
+ "grad_norm": 0.77734375,
1053
+ "learning_rate": 1.5555702330196024e-05,
1054
+ "loss": 1.3291,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.7570003218538783,
1059
+ "grad_norm": 0.75390625,
1060
+ "learning_rate": 1.5481273557041402e-05,
1061
+ "loss": 1.333,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.7570003218538783,
1066
+ "eval_loss": 1.2201098203659058,
1067
+ "eval_runtime": 2166.0893,
1068
+ "eval_samples_per_second": 0.435,
1069
+ "eval_steps_per_second": 0.435,
1070
+ "step": 147
1071
+ },
1072
+ {
1073
+ "epoch": 0.762149983907306,
1074
+ "grad_norm": 0.734375,
1075
+ "learning_rate": 1.5406408174555978e-05,
1076
+ "loss": 1.3466,
1077
+ "step": 148
1078
+ },
1079
+ {
1080
+ "epoch": 0.7672996459607339,
1081
+ "grad_norm": 0.6953125,
1082
+ "learning_rate": 1.5331112146121104e-05,
1083
+ "loss": 1.3547,
1084
+ "step": 149
1085
+ },
1086
+ {
1087
+ "epoch": 0.7724493080141616,
1088
+ "grad_norm": 0.71484375,
1089
+ "learning_rate": 1.525539146942113e-05,
1090
+ "loss": 1.3049,
1091
+ "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 0.7775989700675893,
1095
+ "grad_norm": 0.71875,
1096
+ "learning_rate": 1.5179252175965632e-05,
1097
+ "loss": 1.2915,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 0.7827486321210171,
1102
+ "grad_norm": 0.6953125,
1103
+ "learning_rate": 1.5102700330609e-05,
1104
+ "loss": 1.329,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 0.7878982941744448,
1109
+ "grad_norm": 0.73046875,
1110
+ "learning_rate": 1.5025742031067316e-05,
1111
+ "loss": 1.2951,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 0.7930479562278725,
1116
+ "grad_norm": 0.7421875,
1117
+ "learning_rate": 1.4948383407432678e-05,
1118
+ "loss": 1.2913,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 0.7981976182813003,
1123
+ "grad_norm": 0.7265625,
1124
+ "learning_rate": 1.4870630621684873e-05,
1125
+ "loss": 1.2915,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 0.803347280334728,
1130
+ "grad_norm": 0.72265625,
1131
+ "learning_rate": 1.479248986720057e-05,
1132
+ "loss": 1.3233,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 0.8084969423881557,
1137
+ "grad_norm": 0.75390625,
1138
+ "learning_rate": 1.4713967368259981e-05,
1139
+ "loss": 1.2759,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 0.8136466044415835,
1144
+ "grad_norm": 0.7421875,
1145
+ "learning_rate": 1.4635069379551054e-05,
1146
+ "loss": 1.3446,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 0.8187962664950112,
1151
+ "grad_norm": 0.7109375,
1152
+ "learning_rate": 1.4555802185671297e-05,
1153
+ "loss": 1.3373,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 0.823945928548439,
1158
+ "grad_norm": 0.76171875,
1159
+ "learning_rate": 1.4476172100627127e-05,
1160
+ "loss": 1.3016,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 0.8290955906018668,
1165
+ "grad_norm": 0.73046875,
1166
+ "learning_rate": 1.4396185467330974e-05,
1167
+ "loss": 1.3983,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 0.8342452526552945,
1172
+ "grad_norm": 0.77734375,
1173
+ "learning_rate": 1.4315848657096006e-05,
1174
+ "loss": 1.3133,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 0.8393949147087223,
1179
+ "grad_norm": 0.7421875,
1180
+ "learning_rate": 1.4235168069128657e-05,
1181
+ "loss": 1.3356,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 0.84454457676215,
1186
+ "grad_norm": 0.96875,
1187
+ "learning_rate": 1.4154150130018867e-05,
1188
+ "loss": 1.319,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 0.8496942388155777,
1193
+ "grad_norm": 0.71875,
1194
+ "learning_rate": 1.407280129322819e-05,
1195
+ "loss": 1.3293,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 0.8548439008690055,
1200
+ "grad_norm": 0.71875,
1201
+ "learning_rate": 1.3991128038575741e-05,
1202
+ "loss": 1.3331,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 0.8599935629224332,
1207
+ "grad_norm": 0.74609375,
1208
+ "learning_rate": 1.3909136871722066e-05,
1209
+ "loss": 1.3043,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 0.8651432249758609,
1214
+ "grad_norm": 0.7265625,
1215
+ "learning_rate": 1.3826834323650899e-05,
1216
+ "loss": 1.3491,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 0.8702928870292888,
1221
+ "grad_norm": 0.72265625,
1222
+ "learning_rate": 1.374422695014897e-05,
1223
+ "loss": 1.3379,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 0.8754425490827165,
1228
+ "grad_norm": 0.71484375,
1229
+ "learning_rate": 1.3661321331283796e-05,
1230
+ "loss": 1.3071,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 0.8805922111361442,
1235
+ "grad_norm": 0.6796875,
1236
+ "learning_rate": 1.3578124070879534e-05,
1237
+ "loss": 1.3342,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 0.885741873189572,
1242
+ "grad_norm": 0.71484375,
1243
+ "learning_rate": 1.3494641795990986e-05,
1244
+ "loss": 1.3486,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 0.8908915352429997,
1249
+ "grad_norm": 0.73828125,
1250
+ "learning_rate": 1.3410881156375684e-05,
1251
+ "loss": 1.2531,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 0.8960411972964274,
1256
+ "grad_norm": 0.73046875,
1257
+ "learning_rate": 1.3326848823964243e-05,
1258
+ "loss": 1.3467,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 0.9011908593498552,
1263
+ "grad_norm": 0.68359375,
1264
+ "learning_rate": 1.3242551492328875e-05,
1265
+ "loss": 1.2883,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 0.9063405214032829,
1270
+ "grad_norm": 0.69921875,
1271
+ "learning_rate": 1.3157995876150252e-05,
1272
+ "loss": 1.3573,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 0.9114901834567106,
1277
+ "grad_norm": 0.703125,
1278
+ "learning_rate": 1.3073188710682612e-05,
1279
+ "loss": 1.3087,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 0.9166398455101384,
1284
+ "grad_norm": 0.7421875,
1285
+ "learning_rate": 1.2988136751217292e-05,
1286
+ "loss": 1.2934,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 0.9217895075635661,
1291
+ "grad_norm": 0.73828125,
1292
+ "learning_rate": 1.2902846772544625e-05,
1293
+ "loss": 1.3317,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 0.9269391696169939,
1298
+ "grad_norm": 0.796875,
1299
+ "learning_rate": 1.2817325568414299e-05,
1300
+ "loss": 1.2936,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 0.9320888316704217,
1305
+ "grad_norm": 0.703125,
1306
+ "learning_rate": 1.27315799509942e-05,
1307
+ "loss": 1.3156,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 0.9372384937238494,
1312
+ "grad_norm": 0.7109375,
1313
+ "learning_rate": 1.2645616750327792e-05,
1314
+ "loss": 1.3287,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 0.9423881557772771,
1319
+ "grad_norm": 0.73828125,
1320
+ "learning_rate": 1.2559442813790077e-05,
1321
+ "loss": 1.3513,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 0.9475378178307049,
1326
+ "grad_norm": 0.671875,
1327
+ "learning_rate": 1.2473065005542155e-05,
1328
+ "loss": 1.2912,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 0.9526874798841326,
1333
+ "grad_norm": 0.72265625,
1334
+ "learning_rate": 1.2386490205984488e-05,
1335
+ "loss": 1.3411,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 0.9578371419375603,
1340
+ "grad_norm": 0.77734375,
1341
+ "learning_rate": 1.2299725311208807e-05,
1342
+ "loss": 1.3789,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 0.9629868039909881,
1347
+ "grad_norm": 0.67578125,
1348
+ "learning_rate": 1.2212777232448837e-05,
1349
+ "loss": 1.307,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 0.9681364660444158,
1354
+ "grad_norm": 0.69921875,
1355
+ "learning_rate": 1.2125652895529766e-05,
1356
+ "loss": 1.303,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 0.9732861280978435,
1361
+ "grad_norm": 0.6796875,
1362
+ "learning_rate": 1.2038359240316589e-05,
1363
+ "loss": 1.2732,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 0.9784357901512714,
1368
+ "grad_norm": 0.68359375,
1369
+ "learning_rate": 1.1950903220161286e-05,
1370
+ "loss": 1.3369,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 0.9835854522046991,
1375
+ "grad_norm": 0.73046875,
1376
+ "learning_rate": 1.186329180134898e-05,
1377
+ "loss": 1.3079,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 0.9887351142581268,
1382
+ "grad_norm": 0.67578125,
1383
+ "learning_rate": 1.1775531962543036e-05,
1384
+ "loss": 1.3106,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 0.9938847763115546,
1389
+ "grad_norm": 0.67578125,
1390
+ "learning_rate": 1.1687630694229159e-05,
1391
+ "loss": 1.3163,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 0.9990344383649823,
1396
+ "grad_norm": 0.69921875,
1397
+ "learning_rate": 1.1599594998158602e-05,
1398
+ "loss": 1.3379,
1399
+ "step": 194
1400
+ }
1401
+ ],
1402
+ "logging_steps": 1,
1403
+ "max_steps": 388,
1404
+ "num_input_tokens_seen": 0,
1405
+ "num_train_epochs": 2,
1406
+ "save_steps": 194,
1407
+ "stateful_callbacks": {
1408
+ "TrainerControl": {
1409
+ "args": {
1410
+ "should_epoch_stop": false,
1411
+ "should_evaluate": false,
1412
+ "should_log": false,
1413
+ "should_save": true,
1414
+ "should_training_stop": false
1415
+ },
1416
+ "attributes": {}
1417
+ }
1418
+ },
1419
+ "total_flos": 2.513551014229967e+18,
1420
+ "train_batch_size": 1,
1421
+ "trial_name": null,
1422
+ "trial_params": null
1423
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d1662c19d7bf84ff745d0e2af8cb6e149213d533d01d7bc3702c01b9c21fe5c
3
+ size 6136