Sudanl commited on
Commit
ee7038a
·
verified ·
1 Parent(s): 7a35d7c

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Magpie-Align/Llama-3-8B-Magpie-Pro-SFT-v0.1",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 500000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.40.2",
26
+ "use_cache": false,
27
+ "vocab_size": 128256
28
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": 128001,
5
+ "max_length": 4096,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.40.2"
9
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2108e0fc41e17279a678d733971a05afe8afbab171378df83bed36e36691580d
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a580f75958f92fda75814ab71514f8167f0f675d097b9fb4401182d36656953a
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af9dc049ff91556852e959ac97f190081b25ca95a82917f510afd8cdd75485f1
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec3b4a3f08c5510af42de15459d6cd40dfe3cf62f950fae3ec2907531ec8bce0
3
+ size 1168138808
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
trainer_state.json ADDED
@@ -0,0 +1,1655 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9782608695652173,
5
+ "eval_steps": 115,
6
+ "global_step": 230,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008695652173913044,
13
+ "grad_norm": 27.9770450592041,
14
+ "learning_rate": 2.0000000000000002e-07,
15
+ "loss": 2.2478,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.008695652173913044,
20
+ "eval_loss": 2.349900007247925,
21
+ "eval_runtime": 27.4212,
22
+ "eval_samples_per_second": 1.823,
23
+ "eval_steps_per_second": 0.474,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.017391304347826087,
28
+ "grad_norm": 28.724267959594727,
29
+ "learning_rate": 4.0000000000000003e-07,
30
+ "loss": 2.1994,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.02608695652173913,
35
+ "grad_norm": 28.540616989135742,
36
+ "learning_rate": 6.000000000000001e-07,
37
+ "loss": 2.2229,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.034782608695652174,
42
+ "grad_norm": 28.697280883789062,
43
+ "learning_rate": 8.000000000000001e-07,
44
+ "loss": 2.2037,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.043478260869565216,
49
+ "grad_norm": 28.92486000061035,
50
+ "learning_rate": 1.0000000000000002e-06,
51
+ "loss": 2.1981,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.05217391304347826,
56
+ "grad_norm": 29.778339385986328,
57
+ "learning_rate": 1.2000000000000002e-06,
58
+ "loss": 2.1414,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.06086956521739131,
63
+ "grad_norm": 29.21839141845703,
64
+ "learning_rate": 1.4000000000000001e-06,
65
+ "loss": 2.1423,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.06956521739130435,
70
+ "grad_norm": 18.694778442382812,
71
+ "learning_rate": 1.6000000000000001e-06,
72
+ "loss": 1.9974,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.0782608695652174,
77
+ "grad_norm": 17.274688720703125,
78
+ "learning_rate": 1.8000000000000001e-06,
79
+ "loss": 1.9562,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.08695652173913043,
84
+ "grad_norm": 15.813633918762207,
85
+ "learning_rate": 2.0000000000000003e-06,
86
+ "loss": 1.9486,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.09565217391304348,
91
+ "grad_norm": 6.602424144744873,
92
+ "learning_rate": 2.2e-06,
93
+ "loss": 1.7994,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.10434782608695652,
98
+ "grad_norm": 6.037355422973633,
99
+ "learning_rate": 2.4000000000000003e-06,
100
+ "loss": 1.766,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.11304347826086956,
105
+ "grad_norm": 4.949301242828369,
106
+ "learning_rate": 2.6e-06,
107
+ "loss": 1.7459,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.12173913043478261,
112
+ "grad_norm": 2.621478796005249,
113
+ "learning_rate": 2.8000000000000003e-06,
114
+ "loss": 1.6899,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.13043478260869565,
119
+ "grad_norm": 3.7320492267608643,
120
+ "learning_rate": 3e-06,
121
+ "loss": 1.7185,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.1391304347826087,
126
+ "grad_norm": 3.5459675788879395,
127
+ "learning_rate": 3.2000000000000003e-06,
128
+ "loss": 1.6988,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.14782608695652175,
133
+ "grad_norm": 3.048675060272217,
134
+ "learning_rate": 3.4000000000000005e-06,
135
+ "loss": 1.6822,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.1565217391304348,
140
+ "grad_norm": 2.540501832962036,
141
+ "learning_rate": 3.6000000000000003e-06,
142
+ "loss": 1.6814,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.16521739130434782,
147
+ "grad_norm": 2.129035234451294,
148
+ "learning_rate": 3.8000000000000005e-06,
149
+ "loss": 1.659,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.17391304347826086,
154
+ "grad_norm": 1.9875308275222778,
155
+ "learning_rate": 4.000000000000001e-06,
156
+ "loss": 1.6249,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.1826086956521739,
161
+ "grad_norm": 1.7227815389633179,
162
+ "learning_rate": 4.2000000000000004e-06,
163
+ "loss": 1.6261,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.19130434782608696,
168
+ "grad_norm": 1.6309900283813477,
169
+ "learning_rate": 4.4e-06,
170
+ "loss": 1.6043,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.2,
175
+ "grad_norm": 1.4524799585342407,
176
+ "learning_rate": 4.600000000000001e-06,
177
+ "loss": 1.6014,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.20869565217391303,
182
+ "grad_norm": 1.5349876880645752,
183
+ "learning_rate": 4.800000000000001e-06,
184
+ "loss": 1.6097,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.21739130434782608,
189
+ "grad_norm": 1.4749583005905151,
190
+ "learning_rate": 5e-06,
191
+ "loss": 1.6108,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.22608695652173913,
196
+ "grad_norm": 1.3951363563537598,
197
+ "learning_rate": 5.2e-06,
198
+ "loss": 1.6179,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.23478260869565218,
203
+ "grad_norm": 1.4121828079223633,
204
+ "learning_rate": 5.400000000000001e-06,
205
+ "loss": 1.5842,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.24347826086956523,
210
+ "grad_norm": 1.259391188621521,
211
+ "learning_rate": 5.600000000000001e-06,
212
+ "loss": 1.563,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.25217391304347825,
217
+ "grad_norm": 1.2551765441894531,
218
+ "learning_rate": 5.8e-06,
219
+ "loss": 1.5829,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.2608695652173913,
224
+ "grad_norm": 1.2322245836257935,
225
+ "learning_rate": 6e-06,
226
+ "loss": 1.5877,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.26956521739130435,
231
+ "grad_norm": 1.136198878288269,
232
+ "learning_rate": 6.200000000000001e-06,
233
+ "loss": 1.5464,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.2782608695652174,
238
+ "grad_norm": 1.2440415620803833,
239
+ "learning_rate": 6.4000000000000006e-06,
240
+ "loss": 1.537,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.28695652173913044,
245
+ "grad_norm": 1.1897674798965454,
246
+ "learning_rate": 6.600000000000001e-06,
247
+ "loss": 1.5757,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.2956521739130435,
252
+ "grad_norm": 1.173654556274414,
253
+ "learning_rate": 6.800000000000001e-06,
254
+ "loss": 1.5542,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.30434782608695654,
259
+ "grad_norm": 1.1894692182540894,
260
+ "learning_rate": 7e-06,
261
+ "loss": 1.5822,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.3130434782608696,
266
+ "grad_norm": 1.1219773292541504,
267
+ "learning_rate": 7.2000000000000005e-06,
268
+ "loss": 1.5596,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.3217391304347826,
273
+ "grad_norm": 1.2288638353347778,
274
+ "learning_rate": 7.4e-06,
275
+ "loss": 1.5512,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.33043478260869563,
280
+ "grad_norm": 1.1236315965652466,
281
+ "learning_rate": 7.600000000000001e-06,
282
+ "loss": 1.5378,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.3391304347826087,
287
+ "grad_norm": 1.086173415184021,
288
+ "learning_rate": 7.800000000000002e-06,
289
+ "loss": 1.5475,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.34782608695652173,
294
+ "grad_norm": 1.13786780834198,
295
+ "learning_rate": 8.000000000000001e-06,
296
+ "loss": 1.5345,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.3565217391304348,
301
+ "grad_norm": 1.078940510749817,
302
+ "learning_rate": 8.2e-06,
303
+ "loss": 1.5736,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.3652173913043478,
308
+ "grad_norm": 1.06036376953125,
309
+ "learning_rate": 8.400000000000001e-06,
310
+ "loss": 1.5402,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.3739130434782609,
315
+ "grad_norm": 1.0889636278152466,
316
+ "learning_rate": 8.6e-06,
317
+ "loss": 1.5594,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.3826086956521739,
322
+ "grad_norm": 1.089091181755066,
323
+ "learning_rate": 8.8e-06,
324
+ "loss": 1.5298,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.391304347826087,
329
+ "grad_norm": 1.1010075807571411,
330
+ "learning_rate": 9e-06,
331
+ "loss": 1.54,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.4,
336
+ "grad_norm": 1.0824369192123413,
337
+ "learning_rate": 9.200000000000002e-06,
338
+ "loss": 1.5344,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.40869565217391307,
343
+ "grad_norm": 1.130077838897705,
344
+ "learning_rate": 9.4e-06,
345
+ "loss": 1.5425,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.41739130434782606,
350
+ "grad_norm": 1.0903602838516235,
351
+ "learning_rate": 9.600000000000001e-06,
352
+ "loss": 1.5515,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.4260869565217391,
357
+ "grad_norm": 1.1305510997772217,
358
+ "learning_rate": 9.800000000000001e-06,
359
+ "loss": 1.5288,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.43478260869565216,
364
+ "grad_norm": 1.1045012474060059,
365
+ "learning_rate": 1e-05,
366
+ "loss": 1.5156,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.4434782608695652,
371
+ "grad_norm": 1.132230281829834,
372
+ "learning_rate": 1.02e-05,
373
+ "loss": 1.5193,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.45217391304347826,
378
+ "grad_norm": 1.1561248302459717,
379
+ "learning_rate": 1.04e-05,
380
+ "loss": 1.5198,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.4608695652173913,
385
+ "grad_norm": 1.1394556760787964,
386
+ "learning_rate": 1.0600000000000002e-05,
387
+ "loss": 1.5609,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.46956521739130436,
392
+ "grad_norm": 1.2164558172225952,
393
+ "learning_rate": 1.0800000000000002e-05,
394
+ "loss": 1.5497,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.4782608695652174,
399
+ "grad_norm": 1.1864646673202515,
400
+ "learning_rate": 1.1000000000000001e-05,
401
+ "loss": 1.5278,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.48695652173913045,
406
+ "grad_norm": 1.2279999256134033,
407
+ "learning_rate": 1.1200000000000001e-05,
408
+ "loss": 1.5035,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.4956521739130435,
413
+ "grad_norm": 1.1659705638885498,
414
+ "learning_rate": 1.14e-05,
415
+ "loss": 1.5278,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.5043478260869565,
420
+ "grad_norm": 1.1985366344451904,
421
+ "learning_rate": 1.16e-05,
422
+ "loss": 1.5238,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.5130434782608696,
427
+ "grad_norm": 1.1645257472991943,
428
+ "learning_rate": 1.18e-05,
429
+ "loss": 1.5181,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.5217391304347826,
434
+ "grad_norm": 1.2394540309906006,
435
+ "learning_rate": 1.2e-05,
436
+ "loss": 1.5253,
437
+ "step": 60
438
+ },
439
+ {
440
+ "epoch": 0.5304347826086957,
441
+ "grad_norm": 1.1257425546646118,
442
+ "learning_rate": 1.22e-05,
443
+ "loss": 1.5086,
444
+ "step": 61
445
+ },
446
+ {
447
+ "epoch": 0.5391304347826087,
448
+ "grad_norm": 1.205934762954712,
449
+ "learning_rate": 1.2400000000000002e-05,
450
+ "loss": 1.5302,
451
+ "step": 62
452
+ },
453
+ {
454
+ "epoch": 0.5478260869565217,
455
+ "grad_norm": 1.2120305299758911,
456
+ "learning_rate": 1.2600000000000001e-05,
457
+ "loss": 1.5126,
458
+ "step": 63
459
+ },
460
+ {
461
+ "epoch": 0.5565217391304348,
462
+ "grad_norm": 1.0931782722473145,
463
+ "learning_rate": 1.2800000000000001e-05,
464
+ "loss": 1.4921,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 0.5652173913043478,
469
+ "grad_norm": 1.0688101053237915,
470
+ "learning_rate": 1.3000000000000001e-05,
471
+ "loss": 1.5567,
472
+ "step": 65
473
+ },
474
+ {
475
+ "epoch": 0.5739130434782609,
476
+ "grad_norm": 1.1482597589492798,
477
+ "learning_rate": 1.3200000000000002e-05,
478
+ "loss": 1.521,
479
+ "step": 66
480
+ },
481
+ {
482
+ "epoch": 0.5826086956521739,
483
+ "grad_norm": 1.11100435256958,
484
+ "learning_rate": 1.3400000000000002e-05,
485
+ "loss": 1.4961,
486
+ "step": 67
487
+ },
488
+ {
489
+ "epoch": 0.591304347826087,
490
+ "grad_norm": 1.1361342668533325,
491
+ "learning_rate": 1.3600000000000002e-05,
492
+ "loss": 1.5143,
493
+ "step": 68
494
+ },
495
+ {
496
+ "epoch": 0.6,
497
+ "grad_norm": 1.0989760160446167,
498
+ "learning_rate": 1.38e-05,
499
+ "loss": 1.5044,
500
+ "step": 69
501
+ },
502
+ {
503
+ "epoch": 0.6086956521739131,
504
+ "grad_norm": 1.1394468545913696,
505
+ "learning_rate": 1.4e-05,
506
+ "loss": 1.5028,
507
+ "step": 70
508
+ },
509
+ {
510
+ "epoch": 0.6173913043478261,
511
+ "grad_norm": 1.1451812982559204,
512
+ "learning_rate": 1.4200000000000001e-05,
513
+ "loss": 1.531,
514
+ "step": 71
515
+ },
516
+ {
517
+ "epoch": 0.6260869565217392,
518
+ "grad_norm": 1.118803858757019,
519
+ "learning_rate": 1.4400000000000001e-05,
520
+ "loss": 1.5319,
521
+ "step": 72
522
+ },
523
+ {
524
+ "epoch": 0.6347826086956522,
525
+ "grad_norm": 1.1544065475463867,
526
+ "learning_rate": 1.46e-05,
527
+ "loss": 1.524,
528
+ "step": 73
529
+ },
530
+ {
531
+ "epoch": 0.6434782608695652,
532
+ "grad_norm": 1.1219969987869263,
533
+ "learning_rate": 1.48e-05,
534
+ "loss": 1.4892,
535
+ "step": 74
536
+ },
537
+ {
538
+ "epoch": 0.6521739130434783,
539
+ "grad_norm": 1.1506638526916504,
540
+ "learning_rate": 1.5000000000000002e-05,
541
+ "loss": 1.5218,
542
+ "step": 75
543
+ },
544
+ {
545
+ "epoch": 0.6608695652173913,
546
+ "grad_norm": 1.1717455387115479,
547
+ "learning_rate": 1.5200000000000002e-05,
548
+ "loss": 1.5207,
549
+ "step": 76
550
+ },
551
+ {
552
+ "epoch": 0.6695652173913044,
553
+ "grad_norm": 1.110942006111145,
554
+ "learning_rate": 1.54e-05,
555
+ "loss": 1.5658,
556
+ "step": 77
557
+ },
558
+ {
559
+ "epoch": 0.6782608695652174,
560
+ "grad_norm": 1.2768936157226562,
561
+ "learning_rate": 1.5600000000000003e-05,
562
+ "loss": 1.501,
563
+ "step": 78
564
+ },
565
+ {
566
+ "epoch": 0.6869565217391305,
567
+ "grad_norm": 1.26193368434906,
568
+ "learning_rate": 1.58e-05,
569
+ "loss": 1.5385,
570
+ "step": 79
571
+ },
572
+ {
573
+ "epoch": 0.6956521739130435,
574
+ "grad_norm": 1.2869552373886108,
575
+ "learning_rate": 1.6000000000000003e-05,
576
+ "loss": 1.523,
577
+ "step": 80
578
+ },
579
+ {
580
+ "epoch": 0.7043478260869566,
581
+ "grad_norm": 1.2835365533828735,
582
+ "learning_rate": 1.62e-05,
583
+ "loss": 1.5154,
584
+ "step": 81
585
+ },
586
+ {
587
+ "epoch": 0.7130434782608696,
588
+ "grad_norm": 1.2280563116073608,
589
+ "learning_rate": 1.64e-05,
590
+ "loss": 1.5089,
591
+ "step": 82
592
+ },
593
+ {
594
+ "epoch": 0.7217391304347827,
595
+ "grad_norm": 1.2316559553146362,
596
+ "learning_rate": 1.66e-05,
597
+ "loss": 1.5296,
598
+ "step": 83
599
+ },
600
+ {
601
+ "epoch": 0.7304347826086957,
602
+ "grad_norm": 1.2359421253204346,
603
+ "learning_rate": 1.6800000000000002e-05,
604
+ "loss": 1.5187,
605
+ "step": 84
606
+ },
607
+ {
608
+ "epoch": 0.7391304347826086,
609
+ "grad_norm": 1.1773601770401,
610
+ "learning_rate": 1.7e-05,
611
+ "loss": 1.5102,
612
+ "step": 85
613
+ },
614
+ {
615
+ "epoch": 0.7478260869565218,
616
+ "grad_norm": 1.2701928615570068,
617
+ "learning_rate": 1.72e-05,
618
+ "loss": 1.5049,
619
+ "step": 86
620
+ },
621
+ {
622
+ "epoch": 0.7565217391304347,
623
+ "grad_norm": 1.2413982152938843,
624
+ "learning_rate": 1.7400000000000003e-05,
625
+ "loss": 1.4875,
626
+ "step": 87
627
+ },
628
+ {
629
+ "epoch": 0.7652173913043478,
630
+ "grad_norm": 1.1729072332382202,
631
+ "learning_rate": 1.76e-05,
632
+ "loss": 1.508,
633
+ "step": 88
634
+ },
635
+ {
636
+ "epoch": 0.7739130434782608,
637
+ "grad_norm": 1.2796519994735718,
638
+ "learning_rate": 1.7800000000000002e-05,
639
+ "loss": 1.4953,
640
+ "step": 89
641
+ },
642
+ {
643
+ "epoch": 0.782608695652174,
644
+ "grad_norm": 1.1654998064041138,
645
+ "learning_rate": 1.8e-05,
646
+ "loss": 1.5115,
647
+ "step": 90
648
+ },
649
+ {
650
+ "epoch": 0.7913043478260869,
651
+ "grad_norm": 1.2365690469741821,
652
+ "learning_rate": 1.8200000000000002e-05,
653
+ "loss": 1.4861,
654
+ "step": 91
655
+ },
656
+ {
657
+ "epoch": 0.8,
658
+ "grad_norm": 1.2018343210220337,
659
+ "learning_rate": 1.8400000000000003e-05,
660
+ "loss": 1.5328,
661
+ "step": 92
662
+ },
663
+ {
664
+ "epoch": 0.808695652173913,
665
+ "grad_norm": 1.1778483390808105,
666
+ "learning_rate": 1.86e-05,
667
+ "loss": 1.4973,
668
+ "step": 93
669
+ },
670
+ {
671
+ "epoch": 0.8173913043478261,
672
+ "grad_norm": 1.2713650465011597,
673
+ "learning_rate": 1.88e-05,
674
+ "loss": 1.5172,
675
+ "step": 94
676
+ },
677
+ {
678
+ "epoch": 0.8260869565217391,
679
+ "grad_norm": 1.3153022527694702,
680
+ "learning_rate": 1.9e-05,
681
+ "loss": 1.502,
682
+ "step": 95
683
+ },
684
+ {
685
+ "epoch": 0.8347826086956521,
686
+ "grad_norm": 1.1676228046417236,
687
+ "learning_rate": 1.9200000000000003e-05,
688
+ "loss": 1.5095,
689
+ "step": 96
690
+ },
691
+ {
692
+ "epoch": 0.8434782608695652,
693
+ "grad_norm": 1.3076750040054321,
694
+ "learning_rate": 1.94e-05,
695
+ "loss": 1.5199,
696
+ "step": 97
697
+ },
698
+ {
699
+ "epoch": 0.8521739130434782,
700
+ "grad_norm": 1.1498546600341797,
701
+ "learning_rate": 1.9600000000000002e-05,
702
+ "loss": 1.514,
703
+ "step": 98
704
+ },
705
+ {
706
+ "epoch": 0.8608695652173913,
707
+ "grad_norm": 1.2685290575027466,
708
+ "learning_rate": 1.98e-05,
709
+ "loss": 1.503,
710
+ "step": 99
711
+ },
712
+ {
713
+ "epoch": 0.8695652173913043,
714
+ "grad_norm": 1.2121868133544922,
715
+ "learning_rate": 2e-05,
716
+ "loss": 1.5182,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.8782608695652174,
721
+ "grad_norm": 1.269320011138916,
722
+ "learning_rate": 1.9997080140801932e-05,
723
+ "loss": 1.4833,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.8869565217391304,
728
+ "grad_norm": 1.21848726272583,
729
+ "learning_rate": 1.998832226832327e-05,
730
+ "loss": 1.517,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.8956521739130435,
735
+ "grad_norm": 1.2216753959655762,
736
+ "learning_rate": 1.9973731496914914e-05,
737
+ "loss": 1.4846,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.9043478260869565,
742
+ "grad_norm": 1.162424087524414,
743
+ "learning_rate": 1.995331634717649e-05,
744
+ "loss": 1.5128,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.9130434782608695,
749
+ "grad_norm": 1.173030972480774,
750
+ "learning_rate": 1.992708874098054e-05,
751
+ "loss": 1.5261,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.9217391304347826,
756
+ "grad_norm": 1.0961143970489502,
757
+ "learning_rate": 1.9895063994510512e-05,
758
+ "loss": 1.4848,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.9304347826086956,
763
+ "grad_norm": 1.2185754776000977,
764
+ "learning_rate": 1.985726080931651e-05,
765
+ "loss": 1.4958,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.9391304347826087,
770
+ "grad_norm": 1.1143345832824707,
771
+ "learning_rate": 1.9813701261394136e-05,
772
+ "loss": 1.5084,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 0.9478260869565217,
777
+ "grad_norm": 1.2007545232772827,
778
+ "learning_rate": 1.9764410788292724e-05,
779
+ "loss": 1.5032,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 0.9565217391304348,
784
+ "grad_norm": 1.1655194759368896,
785
+ "learning_rate": 1.9709418174260523e-05,
786
+ "loss": 1.5104,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 0.9652173913043478,
791
+ "grad_norm": 1.2042982578277588,
792
+ "learning_rate": 1.9648755533435517e-05,
793
+ "loss": 1.5274,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 0.9739130434782609,
798
+ "grad_norm": 1.135833740234375,
799
+ "learning_rate": 1.9582458291091664e-05,
800
+ "loss": 1.5159,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 0.9826086956521739,
805
+ "grad_norm": 1.1194689273834229,
806
+ "learning_rate": 1.9510565162951538e-05,
807
+ "loss": 1.4841,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 0.991304347826087,
812
+ "grad_norm": 1.1721700429916382,
813
+ "learning_rate": 1.9433118132577432e-05,
814
+ "loss": 1.4958,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 1.0,
819
+ "grad_norm": 1.1297590732574463,
820
+ "learning_rate": 1.9350162426854152e-05,
821
+ "loss": 1.4974,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 1.0,
826
+ "eval_loss": 1.658707618713379,
827
+ "eval_runtime": 27.8072,
828
+ "eval_samples_per_second": 1.798,
829
+ "eval_steps_per_second": 0.468,
830
+ "step": 115
831
+ },
832
+ {
833
+ "epoch": 1.008695652173913,
834
+ "grad_norm": 1.189160943031311,
835
+ "learning_rate": 1.9261746489577767e-05,
836
+ "loss": 1.4661,
837
+ "step": 116
838
+ },
839
+ {
840
+ "epoch": 1.017391304347826,
841
+ "grad_norm": 1.2425116300582886,
842
+ "learning_rate": 1.9167921953165827e-05,
843
+ "loss": 1.5087,
844
+ "step": 117
845
+ },
846
+ {
847
+ "epoch": 1.0043478260869565,
848
+ "grad_norm": 1.1860764026641846,
849
+ "learning_rate": 1.9068743608505454e-05,
850
+ "loss": 1.4146,
851
+ "step": 118
852
+ },
853
+ {
854
+ "epoch": 1.0130434782608695,
855
+ "grad_norm": 1.4199373722076416,
856
+ "learning_rate": 1.896426937295704e-05,
857
+ "loss": 1.3588,
858
+ "step": 119
859
+ },
860
+ {
861
+ "epoch": 1.0217391304347827,
862
+ "grad_norm": 1.3657387495040894,
863
+ "learning_rate": 1.8854560256532098e-05,
864
+ "loss": 1.3389,
865
+ "step": 120
866
+ },
867
+ {
868
+ "epoch": 1.0304347826086957,
869
+ "grad_norm": 1.4500665664672852,
870
+ "learning_rate": 1.873968032626518e-05,
871
+ "loss": 1.3416,
872
+ "step": 121
873
+ },
874
+ {
875
+ "epoch": 1.0391304347826087,
876
+ "grad_norm": 1.4582746028900146,
877
+ "learning_rate": 1.8619696668800494e-05,
878
+ "loss": 1.3226,
879
+ "step": 122
880
+ },
881
+ {
882
+ "epoch": 1.0478260869565217,
883
+ "grad_norm": 1.5258561372756958,
884
+ "learning_rate": 1.8494679351215212e-05,
885
+ "loss": 1.3183,
886
+ "step": 123
887
+ },
888
+ {
889
+ "epoch": 1.0565217391304347,
890
+ "grad_norm": 1.42508864402771,
891
+ "learning_rate": 1.8364701380102267e-05,
892
+ "loss": 1.3535,
893
+ "step": 124
894
+ },
895
+ {
896
+ "epoch": 1.065217391304348,
897
+ "grad_norm": 1.4576255083084106,
898
+ "learning_rate": 1.8229838658936566e-05,
899
+ "loss": 1.2911,
900
+ "step": 125
901
+ },
902
+ {
903
+ "epoch": 1.0739130434782609,
904
+ "grad_norm": 1.3179984092712402,
905
+ "learning_rate": 1.8090169943749477e-05,
906
+ "loss": 1.3239,
907
+ "step": 126
908
+ },
909
+ {
910
+ "epoch": 1.0826086956521739,
911
+ "grad_norm": 1.3821628093719482,
912
+ "learning_rate": 1.7945776797137544e-05,
913
+ "loss": 1.3119,
914
+ "step": 127
915
+ },
916
+ {
917
+ "epoch": 1.0913043478260869,
918
+ "grad_norm": 1.3231525421142578,
919
+ "learning_rate": 1.7796743540632226e-05,
920
+ "loss": 1.304,
921
+ "step": 128
922
+ },
923
+ {
924
+ "epoch": 1.1,
925
+ "grad_norm": 1.3649060726165771,
926
+ "learning_rate": 1.7643157205458483e-05,
927
+ "loss": 1.3113,
928
+ "step": 129
929
+ },
930
+ {
931
+ "epoch": 1.108695652173913,
932
+ "grad_norm": 1.2634330987930298,
933
+ "learning_rate": 1.7485107481711014e-05,
934
+ "loss": 1.3116,
935
+ "step": 130
936
+ },
937
+ {
938
+ "epoch": 1.117391304347826,
939
+ "grad_norm": 1.2672367095947266,
940
+ "learning_rate": 1.7322686665977738e-05,
941
+ "loss": 1.338,
942
+ "step": 131
943
+ },
944
+ {
945
+ "epoch": 1.126086956521739,
946
+ "grad_norm": 1.2646681070327759,
947
+ "learning_rate": 1.715598960744121e-05,
948
+ "loss": 1.3083,
949
+ "step": 132
950
+ },
951
+ {
952
+ "epoch": 1.134782608695652,
953
+ "grad_norm": 1.2951526641845703,
954
+ "learning_rate": 1.6985113652489374e-05,
955
+ "loss": 1.3318,
956
+ "step": 133
957
+ },
958
+ {
959
+ "epoch": 1.1434782608695653,
960
+ "grad_norm": 1.2833969593048096,
961
+ "learning_rate": 1.6810158587867973e-05,
962
+ "loss": 1.3544,
963
+ "step": 134
964
+ },
965
+ {
966
+ "epoch": 1.1521739130434783,
967
+ "grad_norm": 1.2921353578567505,
968
+ "learning_rate": 1.6631226582407954e-05,
969
+ "loss": 1.2928,
970
+ "step": 135
971
+ },
972
+ {
973
+ "epoch": 1.1608695652173913,
974
+ "grad_norm": 1.2432658672332764,
975
+ "learning_rate": 1.6448422127361707e-05,
976
+ "loss": 1.3029,
977
+ "step": 136
978
+ },
979
+ {
980
+ "epoch": 1.1695652173913043,
981
+ "grad_norm": 1.2263303995132446,
982
+ "learning_rate": 1.626185197538314e-05,
983
+ "loss": 1.318,
984
+ "step": 137
985
+ },
986
+ {
987
+ "epoch": 1.1782608695652175,
988
+ "grad_norm": 1.3209857940673828,
989
+ "learning_rate": 1.6071625078187113e-05,
990
+ "loss": 1.3315,
991
+ "step": 138
992
+ },
993
+ {
994
+ "epoch": 1.1869565217391305,
995
+ "grad_norm": 1.279836654663086,
996
+ "learning_rate": 1.5877852522924733e-05,
997
+ "loss": 1.3287,
998
+ "step": 139
999
+ },
1000
+ {
1001
+ "epoch": 1.1956521739130435,
1002
+ "grad_norm": 1.2511873245239258,
1003
+ "learning_rate": 1.568064746731156e-05,
1004
+ "loss": 1.2982,
1005
+ "step": 140
1006
+ },
1007
+ {
1008
+ "epoch": 1.2043478260869565,
1009
+ "grad_norm": 1.3275624513626099,
1010
+ "learning_rate": 1.5480125073546705e-05,
1011
+ "loss": 1.2863,
1012
+ "step": 141
1013
+ },
1014
+ {
1015
+ "epoch": 1.2130434782608694,
1016
+ "grad_norm": 1.2315387725830078,
1017
+ "learning_rate": 1.527640244106133e-05,
1018
+ "loss": 1.3091,
1019
+ "step": 142
1020
+ },
1021
+ {
1022
+ "epoch": 1.2217391304347827,
1023
+ "grad_norm": 1.2301815748214722,
1024
+ "learning_rate": 1.5069598538135905e-05,
1025
+ "loss": 1.3336,
1026
+ "step": 143
1027
+ },
1028
+ {
1029
+ "epoch": 1.2304347826086957,
1030
+ "grad_norm": 1.2598013877868652,
1031
+ "learning_rate": 1.485983413242606e-05,
1032
+ "loss": 1.3238,
1033
+ "step": 144
1034
+ },
1035
+ {
1036
+ "epoch": 1.2391304347826086,
1037
+ "grad_norm": 1.223031759262085,
1038
+ "learning_rate": 1.4647231720437687e-05,
1039
+ "loss": 1.2943,
1040
+ "step": 145
1041
+ },
1042
+ {
1043
+ "epoch": 1.2478260869565219,
1044
+ "grad_norm": 1.2285338640213013,
1045
+ "learning_rate": 1.4431915455992416e-05,
1046
+ "loss": 1.3045,
1047
+ "step": 146
1048
+ },
1049
+ {
1050
+ "epoch": 1.2565217391304349,
1051
+ "grad_norm": 1.176661729812622,
1052
+ "learning_rate": 1.4214011077725293e-05,
1053
+ "loss": 1.2958,
1054
+ "step": 147
1055
+ },
1056
+ {
1057
+ "epoch": 1.2652173913043478,
1058
+ "grad_norm": 1.2064881324768066,
1059
+ "learning_rate": 1.3993645835656955e-05,
1060
+ "loss": 1.2981,
1061
+ "step": 148
1062
+ },
1063
+ {
1064
+ "epoch": 1.2739130434782608,
1065
+ "grad_norm": 1.294325828552246,
1066
+ "learning_rate": 1.3770948416883205e-05,
1067
+ "loss": 1.3422,
1068
+ "step": 149
1069
+ },
1070
+ {
1071
+ "epoch": 1.2826086956521738,
1072
+ "grad_norm": 1.2420161962509155,
1073
+ "learning_rate": 1.3546048870425356e-05,
1074
+ "loss": 1.3275,
1075
+ "step": 150
1076
+ },
1077
+ {
1078
+ "epoch": 1.2913043478260868,
1079
+ "grad_norm": 1.2433290481567383,
1080
+ "learning_rate": 1.3319078531285286e-05,
1081
+ "loss": 1.2862,
1082
+ "step": 151
1083
+ },
1084
+ {
1085
+ "epoch": 1.3,
1086
+ "grad_norm": 1.1643811464309692,
1087
+ "learning_rate": 1.3090169943749475e-05,
1088
+ "loss": 1.2696,
1089
+ "step": 152
1090
+ },
1091
+ {
1092
+ "epoch": 1.308695652173913,
1093
+ "grad_norm": 1.2214665412902832,
1094
+ "learning_rate": 1.2859456783986892e-05,
1095
+ "loss": 1.2988,
1096
+ "step": 153
1097
+ },
1098
+ {
1099
+ "epoch": 1.317391304347826,
1100
+ "grad_norm": 1.2694072723388672,
1101
+ "learning_rate": 1.262707378198587e-05,
1102
+ "loss": 1.3163,
1103
+ "step": 154
1104
+ },
1105
+ {
1106
+ "epoch": 1.3260869565217392,
1107
+ "grad_norm": 1.229480504989624,
1108
+ "learning_rate": 1.2393156642875579e-05,
1109
+ "loss": 1.3025,
1110
+ "step": 155
1111
+ },
1112
+ {
1113
+ "epoch": 1.3347826086956522,
1114
+ "grad_norm": 1.2135909795761108,
1115
+ "learning_rate": 1.2157841967678064e-05,
1116
+ "loss": 1.3184,
1117
+ "step": 156
1118
+ },
1119
+ {
1120
+ "epoch": 1.3434782608695652,
1121
+ "grad_norm": 1.283299446105957,
1122
+ "learning_rate": 1.1921267173537085e-05,
1123
+ "loss": 1.3269,
1124
+ "step": 157
1125
+ },
1126
+ {
1127
+ "epoch": 1.3521739130434782,
1128
+ "grad_norm": 1.1701160669326782,
1129
+ "learning_rate": 1.1683570413470384e-05,
1130
+ "loss": 1.2864,
1131
+ "step": 158
1132
+ },
1133
+ {
1134
+ "epoch": 1.3608695652173912,
1135
+ "grad_norm": 1.1845210790634155,
1136
+ "learning_rate": 1.1444890495692214e-05,
1137
+ "loss": 1.3249,
1138
+ "step": 159
1139
+ },
1140
+ {
1141
+ "epoch": 1.3695652173913042,
1142
+ "grad_norm": 1.2007068395614624,
1143
+ "learning_rate": 1.1205366802553231e-05,
1144
+ "loss": 1.3045,
1145
+ "step": 160
1146
+ },
1147
+ {
1148
+ "epoch": 1.3782608695652174,
1149
+ "grad_norm": 1.2322540283203125,
1150
+ "learning_rate": 1.0965139209145153e-05,
1151
+ "loss": 1.3132,
1152
+ "step": 161
1153
+ },
1154
+ {
1155
+ "epoch": 1.3869565217391304,
1156
+ "grad_norm": 1.1864914894104004,
1157
+ "learning_rate": 1.0724348001617626e-05,
1158
+ "loss": 1.3101,
1159
+ "step": 162
1160
+ },
1161
+ {
1162
+ "epoch": 1.3956521739130434,
1163
+ "grad_norm": 1.1936239004135132,
1164
+ "learning_rate": 1.0483133795255072e-05,
1165
+ "loss": 1.2983,
1166
+ "step": 163
1167
+ },
1168
+ {
1169
+ "epoch": 1.4043478260869566,
1170
+ "grad_norm": 1.213137149810791,
1171
+ "learning_rate": 1.0241637452361323e-05,
1172
+ "loss": 1.336,
1173
+ "step": 164
1174
+ },
1175
+ {
1176
+ "epoch": 1.4130434782608696,
1177
+ "grad_norm": 1.1825729608535767,
1178
+ "learning_rate": 1e-05,
1179
+ "loss": 1.3098,
1180
+ "step": 165
1181
+ },
1182
+ {
1183
+ "epoch": 1.4217391304347826,
1184
+ "grad_norm": 1.1550593376159668,
1185
+ "learning_rate": 9.75836254763868e-06,
1186
+ "loss": 1.3096,
1187
+ "step": 166
1188
+ },
1189
+ {
1190
+ "epoch": 1.4304347826086956,
1191
+ "grad_norm": 1.1386010646820068,
1192
+ "learning_rate": 9.516866204744932e-06,
1193
+ "loss": 1.3167,
1194
+ "step": 167
1195
+ },
1196
+ {
1197
+ "epoch": 1.4391304347826086,
1198
+ "grad_norm": 1.2719810009002686,
1199
+ "learning_rate": 9.275651998382377e-06,
1200
+ "loss": 1.2959,
1201
+ "step": 168
1202
+ },
1203
+ {
1204
+ "epoch": 1.4478260869565218,
1205
+ "grad_norm": 1.2225759029388428,
1206
+ "learning_rate": 9.034860790854848e-06,
1207
+ "loss": 1.2942,
1208
+ "step": 169
1209
+ },
1210
+ {
1211
+ "epoch": 1.4565217391304348,
1212
+ "grad_norm": 1.1454390287399292,
1213
+ "learning_rate": 8.79463319744677e-06,
1214
+ "loss": 1.2971,
1215
+ "step": 170
1216
+ },
1217
+ {
1218
+ "epoch": 1.4652173913043478,
1219
+ "grad_norm": 1.2099990844726562,
1220
+ "learning_rate": 8.55510950430779e-06,
1221
+ "loss": 1.2989,
1222
+ "step": 171
1223
+ },
1224
+ {
1225
+ "epoch": 1.4739130434782608,
1226
+ "grad_norm": 1.2047284841537476,
1227
+ "learning_rate": 8.316429586529616e-06,
1228
+ "loss": 1.3048,
1229
+ "step": 172
1230
+ },
1231
+ {
1232
+ "epoch": 1.482608695652174,
1233
+ "grad_norm": 1.1526693105697632,
1234
+ "learning_rate": 8.078732826462917e-06,
1235
+ "loss": 1.2794,
1236
+ "step": 173
1237
+ },
1238
+ {
1239
+ "epoch": 1.491304347826087,
1240
+ "grad_norm": 1.188796877861023,
1241
+ "learning_rate": 7.84215803232194e-06,
1242
+ "loss": 1.305,
1243
+ "step": 174
1244
+ },
1245
+ {
1246
+ "epoch": 1.5,
1247
+ "grad_norm": 1.1713995933532715,
1248
+ "learning_rate": 7.606843357124426e-06,
1249
+ "loss": 1.3153,
1250
+ "step": 175
1251
+ },
1252
+ {
1253
+ "epoch": 1.508695652173913,
1254
+ "grad_norm": 1.2031924724578857,
1255
+ "learning_rate": 7.372926218014131e-06,
1256
+ "loss": 1.3235,
1257
+ "step": 176
1258
+ },
1259
+ {
1260
+ "epoch": 1.517391304347826,
1261
+ "grad_norm": 1.1624150276184082,
1262
+ "learning_rate": 7.140543216013109e-06,
1263
+ "loss": 1.2881,
1264
+ "step": 177
1265
+ },
1266
+ {
1267
+ "epoch": 1.526086956521739,
1268
+ "grad_norm": 1.1415232419967651,
1269
+ "learning_rate": 6.909830056250527e-06,
1270
+ "loss": 1.3027,
1271
+ "step": 178
1272
+ },
1273
+ {
1274
+ "epoch": 1.5347826086956522,
1275
+ "grad_norm": 1.2224611043930054,
1276
+ "learning_rate": 6.680921468714718e-06,
1277
+ "loss": 1.3007,
1278
+ "step": 179
1279
+ },
1280
+ {
1281
+ "epoch": 1.5434782608695652,
1282
+ "grad_norm": 1.1667900085449219,
1283
+ "learning_rate": 6.453951129574644e-06,
1284
+ "loss": 1.2827,
1285
+ "step": 180
1286
+ },
1287
+ {
1288
+ "epoch": 1.5521739130434784,
1289
+ "grad_norm": 1.1897790431976318,
1290
+ "learning_rate": 6.229051583116796e-06,
1291
+ "loss": 1.3233,
1292
+ "step": 181
1293
+ },
1294
+ {
1295
+ "epoch": 1.5608695652173914,
1296
+ "grad_norm": 1.1487510204315186,
1297
+ "learning_rate": 6.006354164343047e-06,
1298
+ "loss": 1.3236,
1299
+ "step": 182
1300
+ },
1301
+ {
1302
+ "epoch": 1.5695652173913044,
1303
+ "grad_norm": 1.1928635835647583,
1304
+ "learning_rate": 5.785988922274711e-06,
1305
+ "loss": 1.3001,
1306
+ "step": 183
1307
+ },
1308
+ {
1309
+ "epoch": 1.5782608695652174,
1310
+ "grad_norm": 1.1951863765716553,
1311
+ "learning_rate": 5.5680845440075885e-06,
1312
+ "loss": 1.2964,
1313
+ "step": 184
1314
+ },
1315
+ {
1316
+ "epoch": 1.5869565217391304,
1317
+ "grad_norm": 1.1351429224014282,
1318
+ "learning_rate": 5.352768279562315e-06,
1319
+ "loss": 1.3045,
1320
+ "step": 185
1321
+ },
1322
+ {
1323
+ "epoch": 1.5956521739130434,
1324
+ "grad_norm": 1.117018461227417,
1325
+ "learning_rate": 5.14016586757394e-06,
1326
+ "loss": 1.2889,
1327
+ "step": 186
1328
+ },
1329
+ {
1330
+ "epoch": 1.6043478260869564,
1331
+ "grad_norm": 1.1258199214935303,
1332
+ "learning_rate": 4.930401461864099e-06,
1333
+ "loss": 1.3015,
1334
+ "step": 187
1335
+ },
1336
+ {
1337
+ "epoch": 1.6130434782608696,
1338
+ "grad_norm": 1.1547445058822632,
1339
+ "learning_rate": 4.7235975589386715e-06,
1340
+ "loss": 1.2961,
1341
+ "step": 188
1342
+ },
1343
+ {
1344
+ "epoch": 1.6217391304347826,
1345
+ "grad_norm": 1.1343611478805542,
1346
+ "learning_rate": 4.519874926453303e-06,
1347
+ "loss": 1.2912,
1348
+ "step": 189
1349
+ },
1350
+ {
1351
+ "epoch": 1.6304347826086958,
1352
+ "grad_norm": 1.0676140785217285,
1353
+ "learning_rate": 4.319352532688444e-06,
1354
+ "loss": 1.2999,
1355
+ "step": 190
1356
+ },
1357
+ {
1358
+ "epoch": 1.6391304347826088,
1359
+ "grad_norm": 1.0918030738830566,
1360
+ "learning_rate": 4.12214747707527e-06,
1361
+ "loss": 1.2933,
1362
+ "step": 191
1363
+ },
1364
+ {
1365
+ "epoch": 1.6478260869565218,
1366
+ "grad_norm": 1.1060066223144531,
1367
+ "learning_rate": 3.9283749218128885e-06,
1368
+ "loss": 1.2918,
1369
+ "step": 192
1370
+ },
1371
+ {
1372
+ "epoch": 1.6565217391304348,
1373
+ "grad_norm": 1.095795750617981,
1374
+ "learning_rate": 3.738148024616863e-06,
1375
+ "loss": 1.299,
1376
+ "step": 193
1377
+ },
1378
+ {
1379
+ "epoch": 1.6652173913043478,
1380
+ "grad_norm": 1.0955934524536133,
1381
+ "learning_rate": 3.5515778726382967e-06,
1382
+ "loss": 1.2752,
1383
+ "step": 194
1384
+ },
1385
+ {
1386
+ "epoch": 1.6739130434782608,
1387
+ "grad_norm": 1.0838819742202759,
1388
+ "learning_rate": 3.3687734175920505e-06,
1389
+ "loss": 1.2836,
1390
+ "step": 195
1391
+ },
1392
+ {
1393
+ "epoch": 1.6826086956521737,
1394
+ "grad_norm": 1.0857439041137695,
1395
+ "learning_rate": 3.1898414121320277e-06,
1396
+ "loss": 1.2912,
1397
+ "step": 196
1398
+ },
1399
+ {
1400
+ "epoch": 1.691304347826087,
1401
+ "grad_norm": 1.1158169507980347,
1402
+ "learning_rate": 3.0148863475106315e-06,
1403
+ "loss": 1.3102,
1404
+ "step": 197
1405
+ },
1406
+ {
1407
+ "epoch": 1.7,
1408
+ "grad_norm": 1.0872242450714111,
1409
+ "learning_rate": 2.8440103925587904e-06,
1410
+ "loss": 1.3049,
1411
+ "step": 198
1412
+ },
1413
+ {
1414
+ "epoch": 1.7086956521739132,
1415
+ "grad_norm": 1.0633604526519775,
1416
+ "learning_rate": 2.6773133340222677e-06,
1417
+ "loss": 1.272,
1418
+ "step": 199
1419
+ },
1420
+ {
1421
+ "epoch": 1.7173913043478262,
1422
+ "grad_norm": 1.0870684385299683,
1423
+ "learning_rate": 2.514892518288988e-06,
1424
+ "loss": 1.3042,
1425
+ "step": 200
1426
+ },
1427
+ {
1428
+ "epoch": 1.7260869565217392,
1429
+ "grad_norm": 1.069403052330017,
1430
+ "learning_rate": 2.3568427945415163e-06,
1431
+ "loss": 1.2767,
1432
+ "step": 201
1433
+ },
1434
+ {
1435
+ "epoch": 1.7347826086956522,
1436
+ "grad_norm": 1.0961412191390991,
1437
+ "learning_rate": 2.2032564593677773e-06,
1438
+ "loss": 1.3146,
1439
+ "step": 202
1440
+ },
1441
+ {
1442
+ "epoch": 1.7434782608695651,
1443
+ "grad_norm": 1.0615010261535645,
1444
+ "learning_rate": 2.0542232028624585e-06,
1445
+ "loss": 1.3176,
1446
+ "step": 203
1447
+ },
1448
+ {
1449
+ "epoch": 1.7521739130434781,
1450
+ "grad_norm": 1.081389307975769,
1451
+ "learning_rate": 1.9098300562505266e-06,
1452
+ "loss": 1.2941,
1453
+ "step": 204
1454
+ },
1455
+ {
1456
+ "epoch": 1.7608695652173914,
1457
+ "grad_norm": 1.055414080619812,
1458
+ "learning_rate": 1.7701613410634367e-06,
1459
+ "loss": 1.2926,
1460
+ "step": 205
1461
+ },
1462
+ {
1463
+ "epoch": 1.7695652173913043,
1464
+ "grad_norm": 1.0605552196502686,
1465
+ "learning_rate": 1.6352986198977327e-06,
1466
+ "loss": 1.2903,
1467
+ "step": 206
1468
+ },
1469
+ {
1470
+ "epoch": 1.7782608695652173,
1471
+ "grad_norm": 1.083540916442871,
1472
+ "learning_rate": 1.5053206487847916e-06,
1473
+ "loss": 1.302,
1474
+ "step": 207
1475
+ },
1476
+ {
1477
+ "epoch": 1.7869565217391306,
1478
+ "grad_norm": 1.0532197952270508,
1479
+ "learning_rate": 1.3803033311995072e-06,
1480
+ "loss": 1.3106,
1481
+ "step": 208
1482
+ },
1483
+ {
1484
+ "epoch": 1.7956521739130435,
1485
+ "grad_norm": 1.0551762580871582,
1486
+ "learning_rate": 1.2603196737348211e-06,
1487
+ "loss": 1.2788,
1488
+ "step": 209
1489
+ },
1490
+ {
1491
+ "epoch": 1.8043478260869565,
1492
+ "grad_norm": 1.0607982873916626,
1493
+ "learning_rate": 1.1454397434679022e-06,
1494
+ "loss": 1.2925,
1495
+ "step": 210
1496
+ },
1497
+ {
1498
+ "epoch": 1.8130434782608695,
1499
+ "grad_norm": 1.0949007272720337,
1500
+ "learning_rate": 1.0357306270429623e-06,
1501
+ "loss": 1.3353,
1502
+ "step": 211
1503
+ },
1504
+ {
1505
+ "epoch": 1.8217391304347825,
1506
+ "grad_norm": 1.0425626039505005,
1507
+ "learning_rate": 9.312563914945461e-07,
1508
+ "loss": 1.2878,
1509
+ "step": 212
1510
+ },
1511
+ {
1512
+ "epoch": 1.8304347826086955,
1513
+ "grad_norm": 1.0543763637542725,
1514
+ "learning_rate": 8.320780468341761e-07,
1515
+ "loss": 1.2827,
1516
+ "step": 213
1517
+ },
1518
+ {
1519
+ "epoch": 1.8391304347826087,
1520
+ "grad_norm": 1.0291991233825684,
1521
+ "learning_rate": 7.382535104222366e-07,
1522
+ "loss": 1.2935,
1523
+ "step": 214
1524
+ },
1525
+ {
1526
+ "epoch": 1.8478260869565217,
1527
+ "grad_norm": 1.0535385608673096,
1528
+ "learning_rate": 6.498375731458529e-07,
1529
+ "loss": 1.3051,
1530
+ "step": 215
1531
+ },
1532
+ {
1533
+ "epoch": 1.856521739130435,
1534
+ "grad_norm": 1.0559706687927246,
1535
+ "learning_rate": 5.668818674225684e-07,
1536
+ "loss": 1.278,
1537
+ "step": 216
1538
+ },
1539
+ {
1540
+ "epoch": 1.865217391304348,
1541
+ "grad_norm": 1.0581434965133667,
1542
+ "learning_rate": 4.894348370484648e-07,
1543
+ "loss": 1.3069,
1544
+ "step": 217
1545
+ },
1546
+ {
1547
+ "epoch": 1.873913043478261,
1548
+ "grad_norm": 1.039284586906433,
1549
+ "learning_rate": 4.1754170890833777e-07,
1550
+ "loss": 1.2723,
1551
+ "step": 218
1552
+ },
1553
+ {
1554
+ "epoch": 1.882608695652174,
1555
+ "grad_norm": 1.0665440559387207,
1556
+ "learning_rate": 3.5124446656448654e-07,
1557
+ "loss": 1.2797,
1558
+ "step": 219
1559
+ },
1560
+ {
1561
+ "epoch": 1.891304347826087,
1562
+ "grad_norm": 1.045371413230896,
1563
+ "learning_rate": 2.905818257394799e-07,
1564
+ "loss": 1.307,
1565
+ "step": 220
1566
+ },
1567
+ {
1568
+ "epoch": 1.9,
1569
+ "grad_norm": 1.035818338394165,
1570
+ "learning_rate": 2.355892117072789e-07,
1571
+ "loss": 1.3083,
1572
+ "step": 221
1573
+ },
1574
+ {
1575
+ "epoch": 1.908695652173913,
1576
+ "grad_norm": 1.044579029083252,
1577
+ "learning_rate": 1.8629873860586567e-07,
1578
+ "loss": 1.2914,
1579
+ "step": 222
1580
+ },
1581
+ {
1582
+ "epoch": 1.9173913043478261,
1583
+ "grad_norm": 1.0681899785995483,
1584
+ "learning_rate": 1.4273919068349184e-07,
1585
+ "loss": 1.3293,
1586
+ "step": 223
1587
+ },
1588
+ {
1589
+ "epoch": 1.9260869565217391,
1590
+ "grad_norm": 1.0404493808746338,
1591
+ "learning_rate": 1.0493600548948879e-07,
1592
+ "loss": 1.269,
1593
+ "step": 224
1594
+ },
1595
+ {
1596
+ "epoch": 1.9347826086956523,
1597
+ "grad_norm": 1.0317591428756714,
1598
+ "learning_rate": 7.291125901946027e-08,
1599
+ "loss": 1.2957,
1600
+ "step": 225
1601
+ },
1602
+ {
1603
+ "epoch": 1.9434782608695653,
1604
+ "grad_norm": 1.0500375032424927,
1605
+ "learning_rate": 4.6683652823513725e-08,
1606
+ "loss": 1.2982,
1607
+ "step": 226
1608
+ },
1609
+ {
1610
+ "epoch": 1.9521739130434783,
1611
+ "grad_norm": 1.0283217430114746,
1612
+ "learning_rate": 2.6268503085089547e-08,
1613
+ "loss": 1.2891,
1614
+ "step": 227
1615
+ },
1616
+ {
1617
+ "epoch": 1.9608695652173913,
1618
+ "grad_norm": 1.0270622968673706,
1619
+ "learning_rate": 1.1677731676733584e-08,
1620
+ "loss": 1.306,
1621
+ "step": 228
1622
+ },
1623
+ {
1624
+ "epoch": 1.9695652173913043,
1625
+ "grad_norm": 1.0450721979141235,
1626
+ "learning_rate": 2.9198591980705847e-09,
1627
+ "loss": 1.2695,
1628
+ "step": 229
1629
+ },
1630
+ {
1631
+ "epoch": 1.9782608695652173,
1632
+ "grad_norm": 1.0649240016937256,
1633
+ "learning_rate": 0.0,
1634
+ "loss": 1.325,
1635
+ "step": 230
1636
+ },
1637
+ {
1638
+ "epoch": 1.9782608695652173,
1639
+ "eval_loss": 1.6434073448181152,
1640
+ "eval_runtime": 27.6497,
1641
+ "eval_samples_per_second": 1.808,
1642
+ "eval_steps_per_second": 0.47,
1643
+ "step": 230
1644
+ }
1645
+ ],
1646
+ "logging_steps": 1,
1647
+ "max_steps": 230,
1648
+ "num_input_tokens_seen": 0,
1649
+ "num_train_epochs": 2,
1650
+ "save_steps": 39,
1651
+ "total_flos": 2.71497194303914e+18,
1652
+ "train_batch_size": 1,
1653
+ "trial_name": null,
1654
+ "trial_params": null
1655
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cfd92ccbe1f926c59425973144d4cd20461114edc7008f24647e5e628e889d4
3
+ size 7288