azzzacs commited on
Commit
2e3409d
·
verified ·
1 Parent(s): 0339fe4

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128001,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 131072,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 128004,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 8.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.51.3",
34
+ "unsloth_version": "2025.5.6",
35
+ "use_cache": true,
36
+ "vocab_size": 128256
37
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "max_length": 131072,
7
+ "pad_token_id": 128004,
8
+ "temperature": 0.6,
9
+ "top_p": 0.95,
10
+ "transformers_version": "4.51.3"
11
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea0915eff4251aa0f46e787991f28e38b30041a283dc5bfd8d9bdec1fbfb52e8
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae2086d43d7c54095e11ac654765fbde64bfa5553974158de2d648586d44835
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e6c5541dfac65ddd01ec38cb19e56a20404824b7adda61b7f2fcdfc8e27651
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:d70bff4a277e4bbf876870369dbf498031f41c46f45ba224a4f9e266610be1b2
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
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2768285b45b2a0c05f6f50bbb8c0287fca6f62a8cde6d1b1f02151ac72ee8dc
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9461b4de4699af4ad996ce9cb1a82c1240e596bed02d68b4c4d541394b6348c2
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end▁of▁sentence|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
3
+ size 17209530
tokenizer_config.json ADDED
@@ -0,0 +1,2068 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "128000": {
7
+ "content": "<|begin▁of▁sentence|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "128001": {
15
+ "content": "<|end▁of▁sentence|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "128002": {
23
+ "content": "<|reserved_special_token_0|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "128003": {
31
+ "content": "<|reserved_special_token_1|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "128004": {
39
+ "content": "<|finetune_right_pad_id|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "128005": {
47
+ "content": "<|reserved_special_token_2|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "128006": {
55
+ "content": "<|start_header_id|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "128007": {
63
+ "content": "<|end_header_id|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "128008": {
71
+ "content": "<|eom_id|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "128009": {
79
+ "content": "<|eot_id|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "128010": {
87
+ "content": "<|python_tag|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "128011": {
95
+ "content": "<|User|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "128012": {
103
+ "content": "<|Assistant|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "128013": {
111
+ "content": "<think>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "128014": {
119
+ "content": "</think>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "128015": {
127
+ "content": "<|▁pad▁|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "128016": {
135
+ "content": "<|reserved_special_token_8|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "128017": {
143
+ "content": "<|reserved_special_token_9|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "128018": {
151
+ "content": "<|reserved_special_token_10|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "128019": {
159
+ "content": "<|reserved_special_token_11|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "128020": {
167
+ "content": "<|reserved_special_token_12|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "128021": {
175
+ "content": "<|reserved_special_token_13|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "128022": {
183
+ "content": "<|reserved_special_token_14|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "128023": {
191
+ "content": "<|reserved_special_token_15|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "128024": {
199
+ "content": "<|reserved_special_token_16|>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "128025": {
207
+ "content": "<|reserved_special_token_17|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "128026": {
215
+ "content": "<|reserved_special_token_18|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "128027": {
223
+ "content": "<|reserved_special_token_19|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "128028": {
231
+ "content": "<|reserved_special_token_20|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "128029": {
239
+ "content": "<|reserved_special_token_21|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "128030": {
247
+ "content": "<|reserved_special_token_22|>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "128031": {
255
+ "content": "<|reserved_special_token_23|>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "128032": {
263
+ "content": "<|reserved_special_token_24|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "128033": {
271
+ "content": "<|reserved_special_token_25|>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": true
277
+ },
278
+ "128034": {
279
+ "content": "<|reserved_special_token_26|>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": true
285
+ },
286
+ "128035": {
287
+ "content": "<|reserved_special_token_27|>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": true
293
+ },
294
+ "128036": {
295
+ "content": "<|reserved_special_token_28|>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": true
301
+ },
302
+ "128037": {
303
+ "content": "<|reserved_special_token_29|>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": true
309
+ },
310
+ "128038": {
311
+ "content": "<|reserved_special_token_30|>",
312
+ "lstrip": false,
313
+ "normalized": false,
314
+ "rstrip": false,
315
+ "single_word": false,
316
+ "special": true
317
+ },
318
+ "128039": {
319
+ "content": "<|reserved_special_token_31|>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false,
324
+ "special": true
325
+ },
326
+ "128040": {
327
+ "content": "<|reserved_special_token_32|>",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": false,
331
+ "single_word": false,
332
+ "special": true
333
+ },
334
+ "128041": {
335
+ "content": "<|reserved_special_token_33|>",
336
+ "lstrip": false,
337
+ "normalized": false,
338
+ "rstrip": false,
339
+ "single_word": false,
340
+ "special": true
341
+ },
342
+ "128042": {
343
+ "content": "<|reserved_special_token_34|>",
344
+ "lstrip": false,
345
+ "normalized": false,
346
+ "rstrip": false,
347
+ "single_word": false,
348
+ "special": true
349
+ },
350
+ "128043": {
351
+ "content": "<|reserved_special_token_35|>",
352
+ "lstrip": false,
353
+ "normalized": false,
354
+ "rstrip": false,
355
+ "single_word": false,
356
+ "special": true
357
+ },
358
+ "128044": {
359
+ "content": "<|reserved_special_token_36|>",
360
+ "lstrip": false,
361
+ "normalized": false,
362
+ "rstrip": false,
363
+ "single_word": false,
364
+ "special": true
365
+ },
366
+ "128045": {
367
+ "content": "<|reserved_special_token_37|>",
368
+ "lstrip": false,
369
+ "normalized": false,
370
+ "rstrip": false,
371
+ "single_word": false,
372
+ "special": true
373
+ },
374
+ "128046": {
375
+ "content": "<|reserved_special_token_38|>",
376
+ "lstrip": false,
377
+ "normalized": false,
378
+ "rstrip": false,
379
+ "single_word": false,
380
+ "special": true
381
+ },
382
+ "128047": {
383
+ "content": "<|reserved_special_token_39|>",
384
+ "lstrip": false,
385
+ "normalized": false,
386
+ "rstrip": false,
387
+ "single_word": false,
388
+ "special": true
389
+ },
390
+ "128048": {
391
+ "content": "<|reserved_special_token_40|>",
392
+ "lstrip": false,
393
+ "normalized": false,
394
+ "rstrip": false,
395
+ "single_word": false,
396
+ "special": true
397
+ },
398
+ "128049": {
399
+ "content": "<|reserved_special_token_41|>",
400
+ "lstrip": false,
401
+ "normalized": false,
402
+ "rstrip": false,
403
+ "single_word": false,
404
+ "special": true
405
+ },
406
+ "128050": {
407
+ "content": "<|reserved_special_token_42|>",
408
+ "lstrip": false,
409
+ "normalized": false,
410
+ "rstrip": false,
411
+ "single_word": false,
412
+ "special": true
413
+ },
414
+ "128051": {
415
+ "content": "<|reserved_special_token_43|>",
416
+ "lstrip": false,
417
+ "normalized": false,
418
+ "rstrip": false,
419
+ "single_word": false,
420
+ "special": true
421
+ },
422
+ "128052": {
423
+ "content": "<|reserved_special_token_44|>",
424
+ "lstrip": false,
425
+ "normalized": false,
426
+ "rstrip": false,
427
+ "single_word": false,
428
+ "special": true
429
+ },
430
+ "128053": {
431
+ "content": "<|reserved_special_token_45|>",
432
+ "lstrip": false,
433
+ "normalized": false,
434
+ "rstrip": false,
435
+ "single_word": false,
436
+ "special": true
437
+ },
438
+ "128054": {
439
+ "content": "<|reserved_special_token_46|>",
440
+ "lstrip": false,
441
+ "normalized": false,
442
+ "rstrip": false,
443
+ "single_word": false,
444
+ "special": true
445
+ },
446
+ "128055": {
447
+ "content": "<|reserved_special_token_47|>",
448
+ "lstrip": false,
449
+ "normalized": false,
450
+ "rstrip": false,
451
+ "single_word": false,
452
+ "special": true
453
+ },
454
+ "128056": {
455
+ "content": "<|reserved_special_token_48|>",
456
+ "lstrip": false,
457
+ "normalized": false,
458
+ "rstrip": false,
459
+ "single_word": false,
460
+ "special": true
461
+ },
462
+ "128057": {
463
+ "content": "<|reserved_special_token_49|>",
464
+ "lstrip": false,
465
+ "normalized": false,
466
+ "rstrip": false,
467
+ "single_word": false,
468
+ "special": true
469
+ },
470
+ "128058": {
471
+ "content": "<|reserved_special_token_50|>",
472
+ "lstrip": false,
473
+ "normalized": false,
474
+ "rstrip": false,
475
+ "single_word": false,
476
+ "special": true
477
+ },
478
+ "128059": {
479
+ "content": "<|reserved_special_token_51|>",
480
+ "lstrip": false,
481
+ "normalized": false,
482
+ "rstrip": false,
483
+ "single_word": false,
484
+ "special": true
485
+ },
486
+ "128060": {
487
+ "content": "<|reserved_special_token_52|>",
488
+ "lstrip": false,
489
+ "normalized": false,
490
+ "rstrip": false,
491
+ "single_word": false,
492
+ "special": true
493
+ },
494
+ "128061": {
495
+ "content": "<|reserved_special_token_53|>",
496
+ "lstrip": false,
497
+ "normalized": false,
498
+ "rstrip": false,
499
+ "single_word": false,
500
+ "special": true
501
+ },
502
+ "128062": {
503
+ "content": "<|reserved_special_token_54|>",
504
+ "lstrip": false,
505
+ "normalized": false,
506
+ "rstrip": false,
507
+ "single_word": false,
508
+ "special": true
509
+ },
510
+ "128063": {
511
+ "content": "<|reserved_special_token_55|>",
512
+ "lstrip": false,
513
+ "normalized": false,
514
+ "rstrip": false,
515
+ "single_word": false,
516
+ "special": true
517
+ },
518
+ "128064": {
519
+ "content": "<|reserved_special_token_56|>",
520
+ "lstrip": false,
521
+ "normalized": false,
522
+ "rstrip": false,
523
+ "single_word": false,
524
+ "special": true
525
+ },
526
+ "128065": {
527
+ "content": "<|reserved_special_token_57|>",
528
+ "lstrip": false,
529
+ "normalized": false,
530
+ "rstrip": false,
531
+ "single_word": false,
532
+ "special": true
533
+ },
534
+ "128066": {
535
+ "content": "<|reserved_special_token_58|>",
536
+ "lstrip": false,
537
+ "normalized": false,
538
+ "rstrip": false,
539
+ "single_word": false,
540
+ "special": true
541
+ },
542
+ "128067": {
543
+ "content": "<|reserved_special_token_59|>",
544
+ "lstrip": false,
545
+ "normalized": false,
546
+ "rstrip": false,
547
+ "single_word": false,
548
+ "special": true
549
+ },
550
+ "128068": {
551
+ "content": "<|reserved_special_token_60|>",
552
+ "lstrip": false,
553
+ "normalized": false,
554
+ "rstrip": false,
555
+ "single_word": false,
556
+ "special": true
557
+ },
558
+ "128069": {
559
+ "content": "<|reserved_special_token_61|>",
560
+ "lstrip": false,
561
+ "normalized": false,
562
+ "rstrip": false,
563
+ "single_word": false,
564
+ "special": true
565
+ },
566
+ "128070": {
567
+ "content": "<|reserved_special_token_62|>",
568
+ "lstrip": false,
569
+ "normalized": false,
570
+ "rstrip": false,
571
+ "single_word": false,
572
+ "special": true
573
+ },
574
+ "128071": {
575
+ "content": "<|reserved_special_token_63|>",
576
+ "lstrip": false,
577
+ "normalized": false,
578
+ "rstrip": false,
579
+ "single_word": false,
580
+ "special": true
581
+ },
582
+ "128072": {
583
+ "content": "<|reserved_special_token_64|>",
584
+ "lstrip": false,
585
+ "normalized": false,
586
+ "rstrip": false,
587
+ "single_word": false,
588
+ "special": true
589
+ },
590
+ "128073": {
591
+ "content": "<|reserved_special_token_65|>",
592
+ "lstrip": false,
593
+ "normalized": false,
594
+ "rstrip": false,
595
+ "single_word": false,
596
+ "special": true
597
+ },
598
+ "128074": {
599
+ "content": "<|reserved_special_token_66|>",
600
+ "lstrip": false,
601
+ "normalized": false,
602
+ "rstrip": false,
603
+ "single_word": false,
604
+ "special": true
605
+ },
606
+ "128075": {
607
+ "content": "<|reserved_special_token_67|>",
608
+ "lstrip": false,
609
+ "normalized": false,
610
+ "rstrip": false,
611
+ "single_word": false,
612
+ "special": true
613
+ },
614
+ "128076": {
615
+ "content": "<|reserved_special_token_68|>",
616
+ "lstrip": false,
617
+ "normalized": false,
618
+ "rstrip": false,
619
+ "single_word": false,
620
+ "special": true
621
+ },
622
+ "128077": {
623
+ "content": "<|reserved_special_token_69|>",
624
+ "lstrip": false,
625
+ "normalized": false,
626
+ "rstrip": false,
627
+ "single_word": false,
628
+ "special": true
629
+ },
630
+ "128078": {
631
+ "content": "<|reserved_special_token_70|>",
632
+ "lstrip": false,
633
+ "normalized": false,
634
+ "rstrip": false,
635
+ "single_word": false,
636
+ "special": true
637
+ },
638
+ "128079": {
639
+ "content": "<|reserved_special_token_71|>",
640
+ "lstrip": false,
641
+ "normalized": false,
642
+ "rstrip": false,
643
+ "single_word": false,
644
+ "special": true
645
+ },
646
+ "128080": {
647
+ "content": "<|reserved_special_token_72|>",
648
+ "lstrip": false,
649
+ "normalized": false,
650
+ "rstrip": false,
651
+ "single_word": false,
652
+ "special": true
653
+ },
654
+ "128081": {
655
+ "content": "<|reserved_special_token_73|>",
656
+ "lstrip": false,
657
+ "normalized": false,
658
+ "rstrip": false,
659
+ "single_word": false,
660
+ "special": true
661
+ },
662
+ "128082": {
663
+ "content": "<|reserved_special_token_74|>",
664
+ "lstrip": false,
665
+ "normalized": false,
666
+ "rstrip": false,
667
+ "single_word": false,
668
+ "special": true
669
+ },
670
+ "128083": {
671
+ "content": "<|reserved_special_token_75|>",
672
+ "lstrip": false,
673
+ "normalized": false,
674
+ "rstrip": false,
675
+ "single_word": false,
676
+ "special": true
677
+ },
678
+ "128084": {
679
+ "content": "<|reserved_special_token_76|>",
680
+ "lstrip": false,
681
+ "normalized": false,
682
+ "rstrip": false,
683
+ "single_word": false,
684
+ "special": true
685
+ },
686
+ "128085": {
687
+ "content": "<|reserved_special_token_77|>",
688
+ "lstrip": false,
689
+ "normalized": false,
690
+ "rstrip": false,
691
+ "single_word": false,
692
+ "special": true
693
+ },
694
+ "128086": {
695
+ "content": "<|reserved_special_token_78|>",
696
+ "lstrip": false,
697
+ "normalized": false,
698
+ "rstrip": false,
699
+ "single_word": false,
700
+ "special": true
701
+ },
702
+ "128087": {
703
+ "content": "<|reserved_special_token_79|>",
704
+ "lstrip": false,
705
+ "normalized": false,
706
+ "rstrip": false,
707
+ "single_word": false,
708
+ "special": true
709
+ },
710
+ "128088": {
711
+ "content": "<|reserved_special_token_80|>",
712
+ "lstrip": false,
713
+ "normalized": false,
714
+ "rstrip": false,
715
+ "single_word": false,
716
+ "special": true
717
+ },
718
+ "128089": {
719
+ "content": "<|reserved_special_token_81|>",
720
+ "lstrip": false,
721
+ "normalized": false,
722
+ "rstrip": false,
723
+ "single_word": false,
724
+ "special": true
725
+ },
726
+ "128090": {
727
+ "content": "<|reserved_special_token_82|>",
728
+ "lstrip": false,
729
+ "normalized": false,
730
+ "rstrip": false,
731
+ "single_word": false,
732
+ "special": true
733
+ },
734
+ "128091": {
735
+ "content": "<|reserved_special_token_83|>",
736
+ "lstrip": false,
737
+ "normalized": false,
738
+ "rstrip": false,
739
+ "single_word": false,
740
+ "special": true
741
+ },
742
+ "128092": {
743
+ "content": "<|reserved_special_token_84|>",
744
+ "lstrip": false,
745
+ "normalized": false,
746
+ "rstrip": false,
747
+ "single_word": false,
748
+ "special": true
749
+ },
750
+ "128093": {
751
+ "content": "<|reserved_special_token_85|>",
752
+ "lstrip": false,
753
+ "normalized": false,
754
+ "rstrip": false,
755
+ "single_word": false,
756
+ "special": true
757
+ },
758
+ "128094": {
759
+ "content": "<|reserved_special_token_86|>",
760
+ "lstrip": false,
761
+ "normalized": false,
762
+ "rstrip": false,
763
+ "single_word": false,
764
+ "special": true
765
+ },
766
+ "128095": {
767
+ "content": "<|reserved_special_token_87|>",
768
+ "lstrip": false,
769
+ "normalized": false,
770
+ "rstrip": false,
771
+ "single_word": false,
772
+ "special": true
773
+ },
774
+ "128096": {
775
+ "content": "<|reserved_special_token_88|>",
776
+ "lstrip": false,
777
+ "normalized": false,
778
+ "rstrip": false,
779
+ "single_word": false,
780
+ "special": true
781
+ },
782
+ "128097": {
783
+ "content": "<|reserved_special_token_89|>",
784
+ "lstrip": false,
785
+ "normalized": false,
786
+ "rstrip": false,
787
+ "single_word": false,
788
+ "special": true
789
+ },
790
+ "128098": {
791
+ "content": "<|reserved_special_token_90|>",
792
+ "lstrip": false,
793
+ "normalized": false,
794
+ "rstrip": false,
795
+ "single_word": false,
796
+ "special": true
797
+ },
798
+ "128099": {
799
+ "content": "<|reserved_special_token_91|>",
800
+ "lstrip": false,
801
+ "normalized": false,
802
+ "rstrip": false,
803
+ "single_word": false,
804
+ "special": true
805
+ },
806
+ "128100": {
807
+ "content": "<|reserved_special_token_92|>",
808
+ "lstrip": false,
809
+ "normalized": false,
810
+ "rstrip": false,
811
+ "single_word": false,
812
+ "special": true
813
+ },
814
+ "128101": {
815
+ "content": "<|reserved_special_token_93|>",
816
+ "lstrip": false,
817
+ "normalized": false,
818
+ "rstrip": false,
819
+ "single_word": false,
820
+ "special": true
821
+ },
822
+ "128102": {
823
+ "content": "<|reserved_special_token_94|>",
824
+ "lstrip": false,
825
+ "normalized": false,
826
+ "rstrip": false,
827
+ "single_word": false,
828
+ "special": true
829
+ },
830
+ "128103": {
831
+ "content": "<|reserved_special_token_95|>",
832
+ "lstrip": false,
833
+ "normalized": false,
834
+ "rstrip": false,
835
+ "single_word": false,
836
+ "special": true
837
+ },
838
+ "128104": {
839
+ "content": "<|reserved_special_token_96|>",
840
+ "lstrip": false,
841
+ "normalized": false,
842
+ "rstrip": false,
843
+ "single_word": false,
844
+ "special": true
845
+ },
846
+ "128105": {
847
+ "content": "<|reserved_special_token_97|>",
848
+ "lstrip": false,
849
+ "normalized": false,
850
+ "rstrip": false,
851
+ "single_word": false,
852
+ "special": true
853
+ },
854
+ "128106": {
855
+ "content": "<|reserved_special_token_98|>",
856
+ "lstrip": false,
857
+ "normalized": false,
858
+ "rstrip": false,
859
+ "single_word": false,
860
+ "special": true
861
+ },
862
+ "128107": {
863
+ "content": "<|reserved_special_token_99|>",
864
+ "lstrip": false,
865
+ "normalized": false,
866
+ "rstrip": false,
867
+ "single_word": false,
868
+ "special": true
869
+ },
870
+ "128108": {
871
+ "content": "<|reserved_special_token_100|>",
872
+ "lstrip": false,
873
+ "normalized": false,
874
+ "rstrip": false,
875
+ "single_word": false,
876
+ "special": true
877
+ },
878
+ "128109": {
879
+ "content": "<|reserved_special_token_101|>",
880
+ "lstrip": false,
881
+ "normalized": false,
882
+ "rstrip": false,
883
+ "single_word": false,
884
+ "special": true
885
+ },
886
+ "128110": {
887
+ "content": "<|reserved_special_token_102|>",
888
+ "lstrip": false,
889
+ "normalized": false,
890
+ "rstrip": false,
891
+ "single_word": false,
892
+ "special": true
893
+ },
894
+ "128111": {
895
+ "content": "<|reserved_special_token_103|>",
896
+ "lstrip": false,
897
+ "normalized": false,
898
+ "rstrip": false,
899
+ "single_word": false,
900
+ "special": true
901
+ },
902
+ "128112": {
903
+ "content": "<|reserved_special_token_104|>",
904
+ "lstrip": false,
905
+ "normalized": false,
906
+ "rstrip": false,
907
+ "single_word": false,
908
+ "special": true
909
+ },
910
+ "128113": {
911
+ "content": "<|reserved_special_token_105|>",
912
+ "lstrip": false,
913
+ "normalized": false,
914
+ "rstrip": false,
915
+ "single_word": false,
916
+ "special": true
917
+ },
918
+ "128114": {
919
+ "content": "<|reserved_special_token_106|>",
920
+ "lstrip": false,
921
+ "normalized": false,
922
+ "rstrip": false,
923
+ "single_word": false,
924
+ "special": true
925
+ },
926
+ "128115": {
927
+ "content": "<|reserved_special_token_107|>",
928
+ "lstrip": false,
929
+ "normalized": false,
930
+ "rstrip": false,
931
+ "single_word": false,
932
+ "special": true
933
+ },
934
+ "128116": {
935
+ "content": "<|reserved_special_token_108|>",
936
+ "lstrip": false,
937
+ "normalized": false,
938
+ "rstrip": false,
939
+ "single_word": false,
940
+ "special": true
941
+ },
942
+ "128117": {
943
+ "content": "<|reserved_special_token_109|>",
944
+ "lstrip": false,
945
+ "normalized": false,
946
+ "rstrip": false,
947
+ "single_word": false,
948
+ "special": true
949
+ },
950
+ "128118": {
951
+ "content": "<|reserved_special_token_110|>",
952
+ "lstrip": false,
953
+ "normalized": false,
954
+ "rstrip": false,
955
+ "single_word": false,
956
+ "special": true
957
+ },
958
+ "128119": {
959
+ "content": "<|reserved_special_token_111|>",
960
+ "lstrip": false,
961
+ "normalized": false,
962
+ "rstrip": false,
963
+ "single_word": false,
964
+ "special": true
965
+ },
966
+ "128120": {
967
+ "content": "<|reserved_special_token_112|>",
968
+ "lstrip": false,
969
+ "normalized": false,
970
+ "rstrip": false,
971
+ "single_word": false,
972
+ "special": true
973
+ },
974
+ "128121": {
975
+ "content": "<|reserved_special_token_113|>",
976
+ "lstrip": false,
977
+ "normalized": false,
978
+ "rstrip": false,
979
+ "single_word": false,
980
+ "special": true
981
+ },
982
+ "128122": {
983
+ "content": "<|reserved_special_token_114|>",
984
+ "lstrip": false,
985
+ "normalized": false,
986
+ "rstrip": false,
987
+ "single_word": false,
988
+ "special": true
989
+ },
990
+ "128123": {
991
+ "content": "<|reserved_special_token_115|>",
992
+ "lstrip": false,
993
+ "normalized": false,
994
+ "rstrip": false,
995
+ "single_word": false,
996
+ "special": true
997
+ },
998
+ "128124": {
999
+ "content": "<|reserved_special_token_116|>",
1000
+ "lstrip": false,
1001
+ "normalized": false,
1002
+ "rstrip": false,
1003
+ "single_word": false,
1004
+ "special": true
1005
+ },
1006
+ "128125": {
1007
+ "content": "<|reserved_special_token_117|>",
1008
+ "lstrip": false,
1009
+ "normalized": false,
1010
+ "rstrip": false,
1011
+ "single_word": false,
1012
+ "special": true
1013
+ },
1014
+ "128126": {
1015
+ "content": "<|reserved_special_token_118|>",
1016
+ "lstrip": false,
1017
+ "normalized": false,
1018
+ "rstrip": false,
1019
+ "single_word": false,
1020
+ "special": true
1021
+ },
1022
+ "128127": {
1023
+ "content": "<|reserved_special_token_119|>",
1024
+ "lstrip": false,
1025
+ "normalized": false,
1026
+ "rstrip": false,
1027
+ "single_word": false,
1028
+ "special": true
1029
+ },
1030
+ "128128": {
1031
+ "content": "<|reserved_special_token_120|>",
1032
+ "lstrip": false,
1033
+ "normalized": false,
1034
+ "rstrip": false,
1035
+ "single_word": false,
1036
+ "special": true
1037
+ },
1038
+ "128129": {
1039
+ "content": "<|reserved_special_token_121|>",
1040
+ "lstrip": false,
1041
+ "normalized": false,
1042
+ "rstrip": false,
1043
+ "single_word": false,
1044
+ "special": true
1045
+ },
1046
+ "128130": {
1047
+ "content": "<|reserved_special_token_122|>",
1048
+ "lstrip": false,
1049
+ "normalized": false,
1050
+ "rstrip": false,
1051
+ "single_word": false,
1052
+ "special": true
1053
+ },
1054
+ "128131": {
1055
+ "content": "<|reserved_special_token_123|>",
1056
+ "lstrip": false,
1057
+ "normalized": false,
1058
+ "rstrip": false,
1059
+ "single_word": false,
1060
+ "special": true
1061
+ },
1062
+ "128132": {
1063
+ "content": "<|reserved_special_token_124|>",
1064
+ "lstrip": false,
1065
+ "normalized": false,
1066
+ "rstrip": false,
1067
+ "single_word": false,
1068
+ "special": true
1069
+ },
1070
+ "128133": {
1071
+ "content": "<|reserved_special_token_125|>",
1072
+ "lstrip": false,
1073
+ "normalized": false,
1074
+ "rstrip": false,
1075
+ "single_word": false,
1076
+ "special": true
1077
+ },
1078
+ "128134": {
1079
+ "content": "<|reserved_special_token_126|>",
1080
+ "lstrip": false,
1081
+ "normalized": false,
1082
+ "rstrip": false,
1083
+ "single_word": false,
1084
+ "special": true
1085
+ },
1086
+ "128135": {
1087
+ "content": "<|reserved_special_token_127|>",
1088
+ "lstrip": false,
1089
+ "normalized": false,
1090
+ "rstrip": false,
1091
+ "single_word": false,
1092
+ "special": true
1093
+ },
1094
+ "128136": {
1095
+ "content": "<|reserved_special_token_128|>",
1096
+ "lstrip": false,
1097
+ "normalized": false,
1098
+ "rstrip": false,
1099
+ "single_word": false,
1100
+ "special": true
1101
+ },
1102
+ "128137": {
1103
+ "content": "<|reserved_special_token_129|>",
1104
+ "lstrip": false,
1105
+ "normalized": false,
1106
+ "rstrip": false,
1107
+ "single_word": false,
1108
+ "special": true
1109
+ },
1110
+ "128138": {
1111
+ "content": "<|reserved_special_token_130|>",
1112
+ "lstrip": false,
1113
+ "normalized": false,
1114
+ "rstrip": false,
1115
+ "single_word": false,
1116
+ "special": true
1117
+ },
1118
+ "128139": {
1119
+ "content": "<|reserved_special_token_131|>",
1120
+ "lstrip": false,
1121
+ "normalized": false,
1122
+ "rstrip": false,
1123
+ "single_word": false,
1124
+ "special": true
1125
+ },
1126
+ "128140": {
1127
+ "content": "<|reserved_special_token_132|>",
1128
+ "lstrip": false,
1129
+ "normalized": false,
1130
+ "rstrip": false,
1131
+ "single_word": false,
1132
+ "special": true
1133
+ },
1134
+ "128141": {
1135
+ "content": "<|reserved_special_token_133|>",
1136
+ "lstrip": false,
1137
+ "normalized": false,
1138
+ "rstrip": false,
1139
+ "single_word": false,
1140
+ "special": true
1141
+ },
1142
+ "128142": {
1143
+ "content": "<|reserved_special_token_134|>",
1144
+ "lstrip": false,
1145
+ "normalized": false,
1146
+ "rstrip": false,
1147
+ "single_word": false,
1148
+ "special": true
1149
+ },
1150
+ "128143": {
1151
+ "content": "<|reserved_special_token_135|>",
1152
+ "lstrip": false,
1153
+ "normalized": false,
1154
+ "rstrip": false,
1155
+ "single_word": false,
1156
+ "special": true
1157
+ },
1158
+ "128144": {
1159
+ "content": "<|reserved_special_token_136|>",
1160
+ "lstrip": false,
1161
+ "normalized": false,
1162
+ "rstrip": false,
1163
+ "single_word": false,
1164
+ "special": true
1165
+ },
1166
+ "128145": {
1167
+ "content": "<|reserved_special_token_137|>",
1168
+ "lstrip": false,
1169
+ "normalized": false,
1170
+ "rstrip": false,
1171
+ "single_word": false,
1172
+ "special": true
1173
+ },
1174
+ "128146": {
1175
+ "content": "<|reserved_special_token_138|>",
1176
+ "lstrip": false,
1177
+ "normalized": false,
1178
+ "rstrip": false,
1179
+ "single_word": false,
1180
+ "special": true
1181
+ },
1182
+ "128147": {
1183
+ "content": "<|reserved_special_token_139|>",
1184
+ "lstrip": false,
1185
+ "normalized": false,
1186
+ "rstrip": false,
1187
+ "single_word": false,
1188
+ "special": true
1189
+ },
1190
+ "128148": {
1191
+ "content": "<|reserved_special_token_140|>",
1192
+ "lstrip": false,
1193
+ "normalized": false,
1194
+ "rstrip": false,
1195
+ "single_word": false,
1196
+ "special": true
1197
+ },
1198
+ "128149": {
1199
+ "content": "<|reserved_special_token_141|>",
1200
+ "lstrip": false,
1201
+ "normalized": false,
1202
+ "rstrip": false,
1203
+ "single_word": false,
1204
+ "special": true
1205
+ },
1206
+ "128150": {
1207
+ "content": "<|reserved_special_token_142|>",
1208
+ "lstrip": false,
1209
+ "normalized": false,
1210
+ "rstrip": false,
1211
+ "single_word": false,
1212
+ "special": true
1213
+ },
1214
+ "128151": {
1215
+ "content": "<|reserved_special_token_143|>",
1216
+ "lstrip": false,
1217
+ "normalized": false,
1218
+ "rstrip": false,
1219
+ "single_word": false,
1220
+ "special": true
1221
+ },
1222
+ "128152": {
1223
+ "content": "<|reserved_special_token_144|>",
1224
+ "lstrip": false,
1225
+ "normalized": false,
1226
+ "rstrip": false,
1227
+ "single_word": false,
1228
+ "special": true
1229
+ },
1230
+ "128153": {
1231
+ "content": "<|reserved_special_token_145|>",
1232
+ "lstrip": false,
1233
+ "normalized": false,
1234
+ "rstrip": false,
1235
+ "single_word": false,
1236
+ "special": true
1237
+ },
1238
+ "128154": {
1239
+ "content": "<|reserved_special_token_146|>",
1240
+ "lstrip": false,
1241
+ "normalized": false,
1242
+ "rstrip": false,
1243
+ "single_word": false,
1244
+ "special": true
1245
+ },
1246
+ "128155": {
1247
+ "content": "<|reserved_special_token_147|>",
1248
+ "lstrip": false,
1249
+ "normalized": false,
1250
+ "rstrip": false,
1251
+ "single_word": false,
1252
+ "special": true
1253
+ },
1254
+ "128156": {
1255
+ "content": "<|reserved_special_token_148|>",
1256
+ "lstrip": false,
1257
+ "normalized": false,
1258
+ "rstrip": false,
1259
+ "single_word": false,
1260
+ "special": true
1261
+ },
1262
+ "128157": {
1263
+ "content": "<|reserved_special_token_149|>",
1264
+ "lstrip": false,
1265
+ "normalized": false,
1266
+ "rstrip": false,
1267
+ "single_word": false,
1268
+ "special": true
1269
+ },
1270
+ "128158": {
1271
+ "content": "<|reserved_special_token_150|>",
1272
+ "lstrip": false,
1273
+ "normalized": false,
1274
+ "rstrip": false,
1275
+ "single_word": false,
1276
+ "special": true
1277
+ },
1278
+ "128159": {
1279
+ "content": "<|reserved_special_token_151|>",
1280
+ "lstrip": false,
1281
+ "normalized": false,
1282
+ "rstrip": false,
1283
+ "single_word": false,
1284
+ "special": true
1285
+ },
1286
+ "128160": {
1287
+ "content": "<|reserved_special_token_152|>",
1288
+ "lstrip": false,
1289
+ "normalized": false,
1290
+ "rstrip": false,
1291
+ "single_word": false,
1292
+ "special": true
1293
+ },
1294
+ "128161": {
1295
+ "content": "<|reserved_special_token_153|>",
1296
+ "lstrip": false,
1297
+ "normalized": false,
1298
+ "rstrip": false,
1299
+ "single_word": false,
1300
+ "special": true
1301
+ },
1302
+ "128162": {
1303
+ "content": "<|reserved_special_token_154|>",
1304
+ "lstrip": false,
1305
+ "normalized": false,
1306
+ "rstrip": false,
1307
+ "single_word": false,
1308
+ "special": true
1309
+ },
1310
+ "128163": {
1311
+ "content": "<|reserved_special_token_155|>",
1312
+ "lstrip": false,
1313
+ "normalized": false,
1314
+ "rstrip": false,
1315
+ "single_word": false,
1316
+ "special": true
1317
+ },
1318
+ "128164": {
1319
+ "content": "<|reserved_special_token_156|>",
1320
+ "lstrip": false,
1321
+ "normalized": false,
1322
+ "rstrip": false,
1323
+ "single_word": false,
1324
+ "special": true
1325
+ },
1326
+ "128165": {
1327
+ "content": "<|reserved_special_token_157|>",
1328
+ "lstrip": false,
1329
+ "normalized": false,
1330
+ "rstrip": false,
1331
+ "single_word": false,
1332
+ "special": true
1333
+ },
1334
+ "128166": {
1335
+ "content": "<|reserved_special_token_158|>",
1336
+ "lstrip": false,
1337
+ "normalized": false,
1338
+ "rstrip": false,
1339
+ "single_word": false,
1340
+ "special": true
1341
+ },
1342
+ "128167": {
1343
+ "content": "<|reserved_special_token_159|>",
1344
+ "lstrip": false,
1345
+ "normalized": false,
1346
+ "rstrip": false,
1347
+ "single_word": false,
1348
+ "special": true
1349
+ },
1350
+ "128168": {
1351
+ "content": "<|reserved_special_token_160|>",
1352
+ "lstrip": false,
1353
+ "normalized": false,
1354
+ "rstrip": false,
1355
+ "single_word": false,
1356
+ "special": true
1357
+ },
1358
+ "128169": {
1359
+ "content": "<|reserved_special_token_161|>",
1360
+ "lstrip": false,
1361
+ "normalized": false,
1362
+ "rstrip": false,
1363
+ "single_word": false,
1364
+ "special": true
1365
+ },
1366
+ "128170": {
1367
+ "content": "<|reserved_special_token_162|>",
1368
+ "lstrip": false,
1369
+ "normalized": false,
1370
+ "rstrip": false,
1371
+ "single_word": false,
1372
+ "special": true
1373
+ },
1374
+ "128171": {
1375
+ "content": "<|reserved_special_token_163|>",
1376
+ "lstrip": false,
1377
+ "normalized": false,
1378
+ "rstrip": false,
1379
+ "single_word": false,
1380
+ "special": true
1381
+ },
1382
+ "128172": {
1383
+ "content": "<|reserved_special_token_164|>",
1384
+ "lstrip": false,
1385
+ "normalized": false,
1386
+ "rstrip": false,
1387
+ "single_word": false,
1388
+ "special": true
1389
+ },
1390
+ "128173": {
1391
+ "content": "<|reserved_special_token_165|>",
1392
+ "lstrip": false,
1393
+ "normalized": false,
1394
+ "rstrip": false,
1395
+ "single_word": false,
1396
+ "special": true
1397
+ },
1398
+ "128174": {
1399
+ "content": "<|reserved_special_token_166|>",
1400
+ "lstrip": false,
1401
+ "normalized": false,
1402
+ "rstrip": false,
1403
+ "single_word": false,
1404
+ "special": true
1405
+ },
1406
+ "128175": {
1407
+ "content": "<|reserved_special_token_167|>",
1408
+ "lstrip": false,
1409
+ "normalized": false,
1410
+ "rstrip": false,
1411
+ "single_word": false,
1412
+ "special": true
1413
+ },
1414
+ "128176": {
1415
+ "content": "<|reserved_special_token_168|>",
1416
+ "lstrip": false,
1417
+ "normalized": false,
1418
+ "rstrip": false,
1419
+ "single_word": false,
1420
+ "special": true
1421
+ },
1422
+ "128177": {
1423
+ "content": "<|reserved_special_token_169|>",
1424
+ "lstrip": false,
1425
+ "normalized": false,
1426
+ "rstrip": false,
1427
+ "single_word": false,
1428
+ "special": true
1429
+ },
1430
+ "128178": {
1431
+ "content": "<|reserved_special_token_170|>",
1432
+ "lstrip": false,
1433
+ "normalized": false,
1434
+ "rstrip": false,
1435
+ "single_word": false,
1436
+ "special": true
1437
+ },
1438
+ "128179": {
1439
+ "content": "<|reserved_special_token_171|>",
1440
+ "lstrip": false,
1441
+ "normalized": false,
1442
+ "rstrip": false,
1443
+ "single_word": false,
1444
+ "special": true
1445
+ },
1446
+ "128180": {
1447
+ "content": "<|reserved_special_token_172|>",
1448
+ "lstrip": false,
1449
+ "normalized": false,
1450
+ "rstrip": false,
1451
+ "single_word": false,
1452
+ "special": true
1453
+ },
1454
+ "128181": {
1455
+ "content": "<|reserved_special_token_173|>",
1456
+ "lstrip": false,
1457
+ "normalized": false,
1458
+ "rstrip": false,
1459
+ "single_word": false,
1460
+ "special": true
1461
+ },
1462
+ "128182": {
1463
+ "content": "<|reserved_special_token_174|>",
1464
+ "lstrip": false,
1465
+ "normalized": false,
1466
+ "rstrip": false,
1467
+ "single_word": false,
1468
+ "special": true
1469
+ },
1470
+ "128183": {
1471
+ "content": "<|reserved_special_token_175|>",
1472
+ "lstrip": false,
1473
+ "normalized": false,
1474
+ "rstrip": false,
1475
+ "single_word": false,
1476
+ "special": true
1477
+ },
1478
+ "128184": {
1479
+ "content": "<|reserved_special_token_176|>",
1480
+ "lstrip": false,
1481
+ "normalized": false,
1482
+ "rstrip": false,
1483
+ "single_word": false,
1484
+ "special": true
1485
+ },
1486
+ "128185": {
1487
+ "content": "<|reserved_special_token_177|>",
1488
+ "lstrip": false,
1489
+ "normalized": false,
1490
+ "rstrip": false,
1491
+ "single_word": false,
1492
+ "special": true
1493
+ },
1494
+ "128186": {
1495
+ "content": "<|reserved_special_token_178|>",
1496
+ "lstrip": false,
1497
+ "normalized": false,
1498
+ "rstrip": false,
1499
+ "single_word": false,
1500
+ "special": true
1501
+ },
1502
+ "128187": {
1503
+ "content": "<|reserved_special_token_179|>",
1504
+ "lstrip": false,
1505
+ "normalized": false,
1506
+ "rstrip": false,
1507
+ "single_word": false,
1508
+ "special": true
1509
+ },
1510
+ "128188": {
1511
+ "content": "<|reserved_special_token_180|>",
1512
+ "lstrip": false,
1513
+ "normalized": false,
1514
+ "rstrip": false,
1515
+ "single_word": false,
1516
+ "special": true
1517
+ },
1518
+ "128189": {
1519
+ "content": "<|reserved_special_token_181|>",
1520
+ "lstrip": false,
1521
+ "normalized": false,
1522
+ "rstrip": false,
1523
+ "single_word": false,
1524
+ "special": true
1525
+ },
1526
+ "128190": {
1527
+ "content": "<|reserved_special_token_182|>",
1528
+ "lstrip": false,
1529
+ "normalized": false,
1530
+ "rstrip": false,
1531
+ "single_word": false,
1532
+ "special": true
1533
+ },
1534
+ "128191": {
1535
+ "content": "<|reserved_special_token_183|>",
1536
+ "lstrip": false,
1537
+ "normalized": false,
1538
+ "rstrip": false,
1539
+ "single_word": false,
1540
+ "special": true
1541
+ },
1542
+ "128192": {
1543
+ "content": "<|reserved_special_token_184|>",
1544
+ "lstrip": false,
1545
+ "normalized": false,
1546
+ "rstrip": false,
1547
+ "single_word": false,
1548
+ "special": true
1549
+ },
1550
+ "128193": {
1551
+ "content": "<|reserved_special_token_185|>",
1552
+ "lstrip": false,
1553
+ "normalized": false,
1554
+ "rstrip": false,
1555
+ "single_word": false,
1556
+ "special": true
1557
+ },
1558
+ "128194": {
1559
+ "content": "<|reserved_special_token_186|>",
1560
+ "lstrip": false,
1561
+ "normalized": false,
1562
+ "rstrip": false,
1563
+ "single_word": false,
1564
+ "special": true
1565
+ },
1566
+ "128195": {
1567
+ "content": "<|reserved_special_token_187|>",
1568
+ "lstrip": false,
1569
+ "normalized": false,
1570
+ "rstrip": false,
1571
+ "single_word": false,
1572
+ "special": true
1573
+ },
1574
+ "128196": {
1575
+ "content": "<|reserved_special_token_188|>",
1576
+ "lstrip": false,
1577
+ "normalized": false,
1578
+ "rstrip": false,
1579
+ "single_word": false,
1580
+ "special": true
1581
+ },
1582
+ "128197": {
1583
+ "content": "<|reserved_special_token_189|>",
1584
+ "lstrip": false,
1585
+ "normalized": false,
1586
+ "rstrip": false,
1587
+ "single_word": false,
1588
+ "special": true
1589
+ },
1590
+ "128198": {
1591
+ "content": "<|reserved_special_token_190|>",
1592
+ "lstrip": false,
1593
+ "normalized": false,
1594
+ "rstrip": false,
1595
+ "single_word": false,
1596
+ "special": true
1597
+ },
1598
+ "128199": {
1599
+ "content": "<|reserved_special_token_191|>",
1600
+ "lstrip": false,
1601
+ "normalized": false,
1602
+ "rstrip": false,
1603
+ "single_word": false,
1604
+ "special": true
1605
+ },
1606
+ "128200": {
1607
+ "content": "<|reserved_special_token_192|>",
1608
+ "lstrip": false,
1609
+ "normalized": false,
1610
+ "rstrip": false,
1611
+ "single_word": false,
1612
+ "special": true
1613
+ },
1614
+ "128201": {
1615
+ "content": "<|reserved_special_token_193|>",
1616
+ "lstrip": false,
1617
+ "normalized": false,
1618
+ "rstrip": false,
1619
+ "single_word": false,
1620
+ "special": true
1621
+ },
1622
+ "128202": {
1623
+ "content": "<|reserved_special_token_194|>",
1624
+ "lstrip": false,
1625
+ "normalized": false,
1626
+ "rstrip": false,
1627
+ "single_word": false,
1628
+ "special": true
1629
+ },
1630
+ "128203": {
1631
+ "content": "<|reserved_special_token_195|>",
1632
+ "lstrip": false,
1633
+ "normalized": false,
1634
+ "rstrip": false,
1635
+ "single_word": false,
1636
+ "special": true
1637
+ },
1638
+ "128204": {
1639
+ "content": "<|reserved_special_token_196|>",
1640
+ "lstrip": false,
1641
+ "normalized": false,
1642
+ "rstrip": false,
1643
+ "single_word": false,
1644
+ "special": true
1645
+ },
1646
+ "128205": {
1647
+ "content": "<|reserved_special_token_197|>",
1648
+ "lstrip": false,
1649
+ "normalized": false,
1650
+ "rstrip": false,
1651
+ "single_word": false,
1652
+ "special": true
1653
+ },
1654
+ "128206": {
1655
+ "content": "<|reserved_special_token_198|>",
1656
+ "lstrip": false,
1657
+ "normalized": false,
1658
+ "rstrip": false,
1659
+ "single_word": false,
1660
+ "special": true
1661
+ },
1662
+ "128207": {
1663
+ "content": "<|reserved_special_token_199|>",
1664
+ "lstrip": false,
1665
+ "normalized": false,
1666
+ "rstrip": false,
1667
+ "single_word": false,
1668
+ "special": true
1669
+ },
1670
+ "128208": {
1671
+ "content": "<|reserved_special_token_200|>",
1672
+ "lstrip": false,
1673
+ "normalized": false,
1674
+ "rstrip": false,
1675
+ "single_word": false,
1676
+ "special": true
1677
+ },
1678
+ "128209": {
1679
+ "content": "<|reserved_special_token_201|>",
1680
+ "lstrip": false,
1681
+ "normalized": false,
1682
+ "rstrip": false,
1683
+ "single_word": false,
1684
+ "special": true
1685
+ },
1686
+ "128210": {
1687
+ "content": "<|reserved_special_token_202|>",
1688
+ "lstrip": false,
1689
+ "normalized": false,
1690
+ "rstrip": false,
1691
+ "single_word": false,
1692
+ "special": true
1693
+ },
1694
+ "128211": {
1695
+ "content": "<|reserved_special_token_203|>",
1696
+ "lstrip": false,
1697
+ "normalized": false,
1698
+ "rstrip": false,
1699
+ "single_word": false,
1700
+ "special": true
1701
+ },
1702
+ "128212": {
1703
+ "content": "<|reserved_special_token_204|>",
1704
+ "lstrip": false,
1705
+ "normalized": false,
1706
+ "rstrip": false,
1707
+ "single_word": false,
1708
+ "special": true
1709
+ },
1710
+ "128213": {
1711
+ "content": "<|reserved_special_token_205|>",
1712
+ "lstrip": false,
1713
+ "normalized": false,
1714
+ "rstrip": false,
1715
+ "single_word": false,
1716
+ "special": true
1717
+ },
1718
+ "128214": {
1719
+ "content": "<|reserved_special_token_206|>",
1720
+ "lstrip": false,
1721
+ "normalized": false,
1722
+ "rstrip": false,
1723
+ "single_word": false,
1724
+ "special": true
1725
+ },
1726
+ "128215": {
1727
+ "content": "<|reserved_special_token_207|>",
1728
+ "lstrip": false,
1729
+ "normalized": false,
1730
+ "rstrip": false,
1731
+ "single_word": false,
1732
+ "special": true
1733
+ },
1734
+ "128216": {
1735
+ "content": "<|reserved_special_token_208|>",
1736
+ "lstrip": false,
1737
+ "normalized": false,
1738
+ "rstrip": false,
1739
+ "single_word": false,
1740
+ "special": true
1741
+ },
1742
+ "128217": {
1743
+ "content": "<|reserved_special_token_209|>",
1744
+ "lstrip": false,
1745
+ "normalized": false,
1746
+ "rstrip": false,
1747
+ "single_word": false,
1748
+ "special": true
1749
+ },
1750
+ "128218": {
1751
+ "content": "<|reserved_special_token_210|>",
1752
+ "lstrip": false,
1753
+ "normalized": false,
1754
+ "rstrip": false,
1755
+ "single_word": false,
1756
+ "special": true
1757
+ },
1758
+ "128219": {
1759
+ "content": "<|reserved_special_token_211|>",
1760
+ "lstrip": false,
1761
+ "normalized": false,
1762
+ "rstrip": false,
1763
+ "single_word": false,
1764
+ "special": true
1765
+ },
1766
+ "128220": {
1767
+ "content": "<|reserved_special_token_212|>",
1768
+ "lstrip": false,
1769
+ "normalized": false,
1770
+ "rstrip": false,
1771
+ "single_word": false,
1772
+ "special": true
1773
+ },
1774
+ "128221": {
1775
+ "content": "<|reserved_special_token_213|>",
1776
+ "lstrip": false,
1777
+ "normalized": false,
1778
+ "rstrip": false,
1779
+ "single_word": false,
1780
+ "special": true
1781
+ },
1782
+ "128222": {
1783
+ "content": "<|reserved_special_token_214|>",
1784
+ "lstrip": false,
1785
+ "normalized": false,
1786
+ "rstrip": false,
1787
+ "single_word": false,
1788
+ "special": true
1789
+ },
1790
+ "128223": {
1791
+ "content": "<|reserved_special_token_215|>",
1792
+ "lstrip": false,
1793
+ "normalized": false,
1794
+ "rstrip": false,
1795
+ "single_word": false,
1796
+ "special": true
1797
+ },
1798
+ "128224": {
1799
+ "content": "<|reserved_special_token_216|>",
1800
+ "lstrip": false,
1801
+ "normalized": false,
1802
+ "rstrip": false,
1803
+ "single_word": false,
1804
+ "special": true
1805
+ },
1806
+ "128225": {
1807
+ "content": "<|reserved_special_token_217|>",
1808
+ "lstrip": false,
1809
+ "normalized": false,
1810
+ "rstrip": false,
1811
+ "single_word": false,
1812
+ "special": true
1813
+ },
1814
+ "128226": {
1815
+ "content": "<|reserved_special_token_218|>",
1816
+ "lstrip": false,
1817
+ "normalized": false,
1818
+ "rstrip": false,
1819
+ "single_word": false,
1820
+ "special": true
1821
+ },
1822
+ "128227": {
1823
+ "content": "<|reserved_special_token_219|>",
1824
+ "lstrip": false,
1825
+ "normalized": false,
1826
+ "rstrip": false,
1827
+ "single_word": false,
1828
+ "special": true
1829
+ },
1830
+ "128228": {
1831
+ "content": "<|reserved_special_token_220|>",
1832
+ "lstrip": false,
1833
+ "normalized": false,
1834
+ "rstrip": false,
1835
+ "single_word": false,
1836
+ "special": true
1837
+ },
1838
+ "128229": {
1839
+ "content": "<|reserved_special_token_221|>",
1840
+ "lstrip": false,
1841
+ "normalized": false,
1842
+ "rstrip": false,
1843
+ "single_word": false,
1844
+ "special": true
1845
+ },
1846
+ "128230": {
1847
+ "content": "<|reserved_special_token_222|>",
1848
+ "lstrip": false,
1849
+ "normalized": false,
1850
+ "rstrip": false,
1851
+ "single_word": false,
1852
+ "special": true
1853
+ },
1854
+ "128231": {
1855
+ "content": "<|reserved_special_token_223|>",
1856
+ "lstrip": false,
1857
+ "normalized": false,
1858
+ "rstrip": false,
1859
+ "single_word": false,
1860
+ "special": true
1861
+ },
1862
+ "128232": {
1863
+ "content": "<|reserved_special_token_224|>",
1864
+ "lstrip": false,
1865
+ "normalized": false,
1866
+ "rstrip": false,
1867
+ "single_word": false,
1868
+ "special": true
1869
+ },
1870
+ "128233": {
1871
+ "content": "<|reserved_special_token_225|>",
1872
+ "lstrip": false,
1873
+ "normalized": false,
1874
+ "rstrip": false,
1875
+ "single_word": false,
1876
+ "special": true
1877
+ },
1878
+ "128234": {
1879
+ "content": "<|reserved_special_token_226|>",
1880
+ "lstrip": false,
1881
+ "normalized": false,
1882
+ "rstrip": false,
1883
+ "single_word": false,
1884
+ "special": true
1885
+ },
1886
+ "128235": {
1887
+ "content": "<|reserved_special_token_227|>",
1888
+ "lstrip": false,
1889
+ "normalized": false,
1890
+ "rstrip": false,
1891
+ "single_word": false,
1892
+ "special": true
1893
+ },
1894
+ "128236": {
1895
+ "content": "<|reserved_special_token_228|>",
1896
+ "lstrip": false,
1897
+ "normalized": false,
1898
+ "rstrip": false,
1899
+ "single_word": false,
1900
+ "special": true
1901
+ },
1902
+ "128237": {
1903
+ "content": "<|reserved_special_token_229|>",
1904
+ "lstrip": false,
1905
+ "normalized": false,
1906
+ "rstrip": false,
1907
+ "single_word": false,
1908
+ "special": true
1909
+ },
1910
+ "128238": {
1911
+ "content": "<|reserved_special_token_230|>",
1912
+ "lstrip": false,
1913
+ "normalized": false,
1914
+ "rstrip": false,
1915
+ "single_word": false,
1916
+ "special": true
1917
+ },
1918
+ "128239": {
1919
+ "content": "<|reserved_special_token_231|>",
1920
+ "lstrip": false,
1921
+ "normalized": false,
1922
+ "rstrip": false,
1923
+ "single_word": false,
1924
+ "special": true
1925
+ },
1926
+ "128240": {
1927
+ "content": "<|reserved_special_token_232|>",
1928
+ "lstrip": false,
1929
+ "normalized": false,
1930
+ "rstrip": false,
1931
+ "single_word": false,
1932
+ "special": true
1933
+ },
1934
+ "128241": {
1935
+ "content": "<|reserved_special_token_233|>",
1936
+ "lstrip": false,
1937
+ "normalized": false,
1938
+ "rstrip": false,
1939
+ "single_word": false,
1940
+ "special": true
1941
+ },
1942
+ "128242": {
1943
+ "content": "<|reserved_special_token_234|>",
1944
+ "lstrip": false,
1945
+ "normalized": false,
1946
+ "rstrip": false,
1947
+ "single_word": false,
1948
+ "special": true
1949
+ },
1950
+ "128243": {
1951
+ "content": "<|reserved_special_token_235|>",
1952
+ "lstrip": false,
1953
+ "normalized": false,
1954
+ "rstrip": false,
1955
+ "single_word": false,
1956
+ "special": true
1957
+ },
1958
+ "128244": {
1959
+ "content": "<|reserved_special_token_236|>",
1960
+ "lstrip": false,
1961
+ "normalized": false,
1962
+ "rstrip": false,
1963
+ "single_word": false,
1964
+ "special": true
1965
+ },
1966
+ "128245": {
1967
+ "content": "<|reserved_special_token_237|>",
1968
+ "lstrip": false,
1969
+ "normalized": false,
1970
+ "rstrip": false,
1971
+ "single_word": false,
1972
+ "special": true
1973
+ },
1974
+ "128246": {
1975
+ "content": "<|reserved_special_token_238|>",
1976
+ "lstrip": false,
1977
+ "normalized": false,
1978
+ "rstrip": false,
1979
+ "single_word": false,
1980
+ "special": true
1981
+ },
1982
+ "128247": {
1983
+ "content": "<|reserved_special_token_239|>",
1984
+ "lstrip": false,
1985
+ "normalized": false,
1986
+ "rstrip": false,
1987
+ "single_word": false,
1988
+ "special": true
1989
+ },
1990
+ "128248": {
1991
+ "content": "<|reserved_special_token_240|>",
1992
+ "lstrip": false,
1993
+ "normalized": false,
1994
+ "rstrip": false,
1995
+ "single_word": false,
1996
+ "special": true
1997
+ },
1998
+ "128249": {
1999
+ "content": "<|reserved_special_token_241|>",
2000
+ "lstrip": false,
2001
+ "normalized": false,
2002
+ "rstrip": false,
2003
+ "single_word": false,
2004
+ "special": true
2005
+ },
2006
+ "128250": {
2007
+ "content": "<|reserved_special_token_242|>",
2008
+ "lstrip": false,
2009
+ "normalized": false,
2010
+ "rstrip": false,
2011
+ "single_word": false,
2012
+ "special": true
2013
+ },
2014
+ "128251": {
2015
+ "content": "<|reserved_special_token_243|>",
2016
+ "lstrip": false,
2017
+ "normalized": false,
2018
+ "rstrip": false,
2019
+ "single_word": false,
2020
+ "special": true
2021
+ },
2022
+ "128252": {
2023
+ "content": "<|reserved_special_token_244|>",
2024
+ "lstrip": false,
2025
+ "normalized": false,
2026
+ "rstrip": false,
2027
+ "single_word": false,
2028
+ "special": true
2029
+ },
2030
+ "128253": {
2031
+ "content": "<|reserved_special_token_245|>",
2032
+ "lstrip": false,
2033
+ "normalized": false,
2034
+ "rstrip": false,
2035
+ "single_word": false,
2036
+ "special": true
2037
+ },
2038
+ "128254": {
2039
+ "content": "<|reserved_special_token_246|>",
2040
+ "lstrip": false,
2041
+ "normalized": false,
2042
+ "rstrip": false,
2043
+ "single_word": false,
2044
+ "special": true
2045
+ },
2046
+ "128255": {
2047
+ "content": "<|reserved_special_token_247|>",
2048
+ "lstrip": false,
2049
+ "normalized": false,
2050
+ "rstrip": false,
2051
+ "single_word": false,
2052
+ "special": true
2053
+ }
2054
+ },
2055
+ "bos_token": "<|begin▁of▁sentence|>",
2056
+ "chat_template": "{{bos_token}}{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|User|>' + message['content'] }}{% elif message['role'] == 'assistant' and message['content'] is not none %}{{ '<|Assistant|>' + message['content'] + '<|end▁of▁sentence|>' }}{% endif %}{% endfor %}",
2057
+ "clean_up_tokenization_spaces": false,
2058
+ "eos_token": "<|end▁of▁sentence|>",
2059
+ "extra_special_tokens": {},
2060
+ "legacy": true,
2061
+ "model_max_length": 16384,
2062
+ "pad_token": "<|finetune_right_pad_id|>",
2063
+ "padding_side": "right",
2064
+ "sp_model_kwargs": {},
2065
+ "tokenizer_class": "LlamaTokenizerFast",
2066
+ "unk_token": null,
2067
+ "use_default_system_prompt": false
2068
+ }
trainer_state.json ADDED
@@ -0,0 +1,3233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 8.0,
6
+ "eval_steps": 500,
7
+ "global_step": 4576,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.017497812773403325,
14
+ "grad_norm": 15.0,
15
+ "learning_rate": 1.0465116279069768e-06,
16
+ "loss": 1.1604,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.03499562554680665,
21
+ "grad_norm": 9.6875,
22
+ "learning_rate": 2.2093023255813954e-06,
23
+ "loss": 1.1391,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.05249343832020997,
28
+ "grad_norm": 4.09375,
29
+ "learning_rate": 3.372093023255814e-06,
30
+ "loss": 1.0272,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.0699912510936133,
35
+ "grad_norm": 2.3125,
36
+ "learning_rate": 4.5348837209302326e-06,
37
+ "loss": 0.8968,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.08748906386701662,
42
+ "grad_norm": 1.515625,
43
+ "learning_rate": 5.697674418604652e-06,
44
+ "loss": 0.8108,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.10498687664041995,
49
+ "grad_norm": 1.421875,
50
+ "learning_rate": 6.86046511627907e-06,
51
+ "loss": 0.8071,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.12248468941382328,
56
+ "grad_norm": 1.1953125,
57
+ "learning_rate": 8.023255813953488e-06,
58
+ "loss": 0.759,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.1399825021872266,
63
+ "grad_norm": 1.25,
64
+ "learning_rate": 9.186046511627908e-06,
65
+ "loss": 0.767,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.15748031496062992,
70
+ "grad_norm": 1.3046875,
71
+ "learning_rate": 1.0348837209302327e-05,
72
+ "loss": 0.7569,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.17497812773403323,
77
+ "grad_norm": 1.1171875,
78
+ "learning_rate": 1.1511627906976746e-05,
79
+ "loss": 0.7603,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.19247594050743658,
84
+ "grad_norm": 1.046875,
85
+ "learning_rate": 1.2674418604651164e-05,
86
+ "loss": 0.7424,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.2099737532808399,
91
+ "grad_norm": 1.3125,
92
+ "learning_rate": 1.3837209302325583e-05,
93
+ "loss": 0.7358,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.2274715660542432,
98
+ "grad_norm": 1.1015625,
99
+ "learning_rate": 1.5000000000000002e-05,
100
+ "loss": 0.7119,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.24496937882764655,
105
+ "grad_norm": 1.140625,
106
+ "learning_rate": 1.616279069767442e-05,
107
+ "loss": 0.7219,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.26246719160104987,
112
+ "grad_norm": 1.0859375,
113
+ "learning_rate": 1.7325581395348837e-05,
114
+ "loss": 0.7073,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.2799650043744532,
119
+ "grad_norm": 1.078125,
120
+ "learning_rate": 1.8488372093023256e-05,
121
+ "loss": 0.7135,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.2974628171478565,
126
+ "grad_norm": 1.046875,
127
+ "learning_rate": 1.9651162790697676e-05,
128
+ "loss": 0.72,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.31496062992125984,
133
+ "grad_norm": 0.96484375,
134
+ "learning_rate": 1.9999929041918377e-05,
135
+ "loss": 0.7111,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.3324584426946632,
140
+ "grad_norm": 1.0859375,
141
+ "learning_rate": 1.999958149482438e-05,
142
+ "loss": 0.7308,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.34995625546806647,
147
+ "grad_norm": 1.09375,
148
+ "learning_rate": 1.9998944336771236e-05,
149
+ "loss": 0.711,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.3674540682414698,
154
+ "grad_norm": 1.03125,
155
+ "learning_rate": 1.9998017588263007e-05,
156
+ "loss": 0.7096,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.38495188101487315,
161
+ "grad_norm": 1.15625,
162
+ "learning_rate": 1.9996801279122917e-05,
163
+ "loss": 0.7193,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.40244969378827644,
168
+ "grad_norm": 0.97265625,
169
+ "learning_rate": 1.9995295448492383e-05,
170
+ "loss": 0.7187,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.4199475065616798,
175
+ "grad_norm": 1.0546875,
176
+ "learning_rate": 1.9993500144829784e-05,
177
+ "loss": 0.7197,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.4374453193350831,
182
+ "grad_norm": 1.046875,
183
+ "learning_rate": 1.9991415425908868e-05,
184
+ "loss": 0.7117,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.4549431321084864,
189
+ "grad_norm": 1.1328125,
190
+ "learning_rate": 1.9989041358816926e-05,
191
+ "loss": 0.6958,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.47244094488188976,
196
+ "grad_norm": 1.0625,
197
+ "learning_rate": 1.9986378019952595e-05,
198
+ "loss": 0.7127,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.4899387576552931,
203
+ "grad_norm": 1.1640625,
204
+ "learning_rate": 1.998342549502343e-05,
205
+ "loss": 0.7068,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.5074365704286964,
210
+ "grad_norm": 1.0546875,
211
+ "learning_rate": 1.998018387904314e-05,
212
+ "loss": 0.6994,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.5249343832020997,
217
+ "grad_norm": 1.078125,
218
+ "learning_rate": 1.997665327632852e-05,
219
+ "loss": 0.713,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.5424321959755031,
224
+ "grad_norm": 1.2109375,
225
+ "learning_rate": 1.9972833800496107e-05,
226
+ "loss": 0.7119,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.5599300087489064,
231
+ "grad_norm": 1.0703125,
232
+ "learning_rate": 1.99687255744585e-05,
233
+ "loss": 0.6993,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.5774278215223098,
238
+ "grad_norm": 0.97265625,
239
+ "learning_rate": 1.9964328730420445e-05,
240
+ "loss": 0.706,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.594925634295713,
245
+ "grad_norm": 1.1484375,
246
+ "learning_rate": 1.995964340987454e-05,
247
+ "loss": 0.7167,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.6124234470691163,
252
+ "grad_norm": 1.109375,
253
+ "learning_rate": 1.9954669763596708e-05,
254
+ "loss": 0.7206,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.6299212598425197,
259
+ "grad_norm": 0.97265625,
260
+ "learning_rate": 1.9949407951641325e-05,
261
+ "loss": 0.6875,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.647419072615923,
266
+ "grad_norm": 1.0625,
267
+ "learning_rate": 1.99438581433361e-05,
268
+ "loss": 0.7256,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.6649168853893264,
273
+ "grad_norm": 1.1015625,
274
+ "learning_rate": 1.9938020517276583e-05,
275
+ "loss": 0.689,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.6824146981627297,
280
+ "grad_norm": 0.98828125,
281
+ "learning_rate": 1.9931895261320463e-05,
282
+ "loss": 0.7029,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.6999125109361329,
287
+ "grad_norm": 1.0078125,
288
+ "learning_rate": 1.9925482572581477e-05,
289
+ "loss": 0.7189,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.7174103237095363,
294
+ "grad_norm": 1.015625,
295
+ "learning_rate": 1.991878265742311e-05,
296
+ "loss": 0.7103,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.7349081364829396,
301
+ "grad_norm": 0.98046875,
302
+ "learning_rate": 1.9911795731451928e-05,
303
+ "loss": 0.7045,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.752405949256343,
308
+ "grad_norm": 1.1171875,
309
+ "learning_rate": 1.9904522019510647e-05,
310
+ "loss": 0.7112,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.7699037620297463,
315
+ "grad_norm": 1.03125,
316
+ "learning_rate": 1.989696175567089e-05,
317
+ "loss": 0.711,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.7874015748031497,
322
+ "grad_norm": 1.0546875,
323
+ "learning_rate": 1.988911518322566e-05,
324
+ "loss": 0.7174,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.8048993875765529,
329
+ "grad_norm": 1.078125,
330
+ "learning_rate": 1.9880982554681534e-05,
331
+ "loss": 0.7023,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.8223972003499562,
336
+ "grad_norm": 1.09375,
337
+ "learning_rate": 1.9872564131750488e-05,
338
+ "loss": 0.6956,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.8398950131233596,
343
+ "grad_norm": 1.0859375,
344
+ "learning_rate": 1.9863860185341514e-05,
345
+ "loss": 0.7003,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.8573928258967629,
350
+ "grad_norm": 1.03125,
351
+ "learning_rate": 1.985487099555189e-05,
352
+ "loss": 0.6849,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.8748906386701663,
357
+ "grad_norm": 0.9140625,
358
+ "learning_rate": 1.9845596851658168e-05,
359
+ "loss": 0.7017,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.8923884514435696,
364
+ "grad_norm": 0.9609375,
365
+ "learning_rate": 1.9836038052106853e-05,
366
+ "loss": 0.6809,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.9098862642169728,
371
+ "grad_norm": 0.96484375,
372
+ "learning_rate": 1.9826194904504824e-05,
373
+ "loss": 0.6961,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.9273840769903762,
378
+ "grad_norm": 0.97265625,
379
+ "learning_rate": 1.9816067725609403e-05,
380
+ "loss": 0.698,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.9448818897637795,
385
+ "grad_norm": 1.125,
386
+ "learning_rate": 1.9805656841318198e-05,
387
+ "loss": 0.7022,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.9623797025371829,
392
+ "grad_norm": 0.97265625,
393
+ "learning_rate": 1.9794962586658582e-05,
394
+ "loss": 0.6896,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.9798775153105862,
399
+ "grad_norm": 1.0390625,
400
+ "learning_rate": 1.978398530577693e-05,
401
+ "loss": 0.6915,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.9973753280839895,
406
+ "grad_norm": 0.99609375,
407
+ "learning_rate": 1.977272535192754e-05,
408
+ "loss": 0.6996,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 1.0139982502187226,
413
+ "grad_norm": 1.0390625,
414
+ "learning_rate": 1.9761183087461264e-05,
415
+ "loss": 0.6237,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 1.031496062992126,
420
+ "grad_norm": 1.1328125,
421
+ "learning_rate": 1.974935888381385e-05,
422
+ "loss": 0.5954,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 1.0489938757655293,
427
+ "grad_norm": 1.1484375,
428
+ "learning_rate": 1.9737253121493994e-05,
429
+ "loss": 0.6124,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 1.0664916885389326,
434
+ "grad_norm": 1.1640625,
435
+ "learning_rate": 1.9724866190071075e-05,
436
+ "loss": 0.6023,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 1.083989501312336,
441
+ "grad_norm": 1.1875,
442
+ "learning_rate": 1.971219848816264e-05,
443
+ "loss": 0.6128,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 1.1014873140857393,
448
+ "grad_norm": 1.2109375,
449
+ "learning_rate": 1.9699250423421568e-05,
450
+ "loss": 0.6167,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 1.1189851268591426,
455
+ "grad_norm": 1.203125,
456
+ "learning_rate": 1.9686022412522953e-05,
457
+ "loss": 0.6322,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 1.136482939632546,
462
+ "grad_norm": 0.94921875,
463
+ "learning_rate": 1.967251488115069e-05,
464
+ "loss": 0.6,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 1.1539807524059493,
469
+ "grad_norm": 1.0546875,
470
+ "learning_rate": 1.9658728263983783e-05,
471
+ "loss": 0.6204,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 1.1714785651793527,
476
+ "grad_norm": 1.140625,
477
+ "learning_rate": 1.964466300468235e-05,
478
+ "loss": 0.627,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 1.188976377952756,
483
+ "grad_norm": 1.0,
484
+ "learning_rate": 1.9630319555873364e-05,
485
+ "loss": 0.5988,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 1.2064741907261591,
490
+ "grad_norm": 1.1015625,
491
+ "learning_rate": 1.961569837913605e-05,
492
+ "loss": 0.6141,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 1.2239720034995625,
497
+ "grad_norm": 1.03125,
498
+ "learning_rate": 1.9600799944987077e-05,
499
+ "loss": 0.6171,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 1.2414698162729658,
504
+ "grad_norm": 1.1328125,
505
+ "learning_rate": 1.958562473286538e-05,
506
+ "loss": 0.613,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 1.2589676290463692,
511
+ "grad_norm": 1.109375,
512
+ "learning_rate": 1.957017323111675e-05,
513
+ "loss": 0.6169,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 1.2764654418197725,
518
+ "grad_norm": 1.1015625,
519
+ "learning_rate": 1.955444593697811e-05,
520
+ "loss": 0.6312,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 1.2939632545931758,
525
+ "grad_norm": 1.2109375,
526
+ "learning_rate": 1.9538443356561528e-05,
527
+ "loss": 0.6144,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 1.3114610673665792,
532
+ "grad_norm": 1.140625,
533
+ "learning_rate": 1.9522166004837908e-05,
534
+ "loss": 0.6096,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 1.3289588801399825,
539
+ "grad_norm": 1.1953125,
540
+ "learning_rate": 1.9505614405620436e-05,
541
+ "loss": 0.6225,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 1.3464566929133859,
546
+ "grad_norm": 1.1953125,
547
+ "learning_rate": 1.9488789091547716e-05,
548
+ "loss": 0.6156,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 1.3639545056867892,
553
+ "grad_norm": 1.078125,
554
+ "learning_rate": 1.9471690604066633e-05,
555
+ "loss": 0.644,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 1.3814523184601923,
560
+ "grad_norm": 1.140625,
561
+ "learning_rate": 1.945431949341492e-05,
562
+ "loss": 0.6221,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 1.3989501312335957,
567
+ "grad_norm": 1.046875,
568
+ "learning_rate": 1.9436676318603465e-05,
569
+ "loss": 0.6164,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 1.416447944006999,
574
+ "grad_norm": 1.0546875,
575
+ "learning_rate": 1.941876164739831e-05,
576
+ "loss": 0.6187,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 1.4339457567804024,
581
+ "grad_norm": 1.1953125,
582
+ "learning_rate": 1.940057605630239e-05,
583
+ "loss": 0.6041,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 1.4514435695538057,
588
+ "grad_norm": 1.0078125,
589
+ "learning_rate": 1.938212013053697e-05,
590
+ "loss": 0.6172,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 1.468941382327209,
595
+ "grad_norm": 1.125,
596
+ "learning_rate": 1.9363394464022814e-05,
597
+ "loss": 0.6107,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 1.4864391951006124,
602
+ "grad_norm": 1.1484375,
603
+ "learning_rate": 1.934439965936109e-05,
604
+ "loss": 0.6109,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 1.5039370078740157,
609
+ "grad_norm": 1.15625,
610
+ "learning_rate": 1.9325136327813945e-05,
611
+ "loss": 0.606,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 1.521434820647419,
616
+ "grad_norm": 1.1171875,
617
+ "learning_rate": 1.9305605089284873e-05,
618
+ "loss": 0.6264,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 1.5389326334208224,
623
+ "grad_norm": 1.140625,
624
+ "learning_rate": 1.9285806572298726e-05,
625
+ "loss": 0.6185,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 1.5564304461942258,
630
+ "grad_norm": 1.1953125,
631
+ "learning_rate": 1.926574141398153e-05,
632
+ "loss": 0.6243,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 1.5739282589676291,
637
+ "grad_norm": 1.0703125,
638
+ "learning_rate": 1.924541026003994e-05,
639
+ "loss": 0.6035,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 1.5914260717410325,
644
+ "grad_norm": 1.203125,
645
+ "learning_rate": 1.9224813764740496e-05,
646
+ "loss": 0.6297,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 1.6089238845144358,
651
+ "grad_norm": 1.078125,
652
+ "learning_rate": 1.9203952590888547e-05,
653
+ "loss": 0.6138,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 1.6264216972878391,
658
+ "grad_norm": 1.1640625,
659
+ "learning_rate": 1.918282740980693e-05,
660
+ "loss": 0.6211,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 1.6439195100612425,
665
+ "grad_norm": 1.140625,
666
+ "learning_rate": 1.9161438901314352e-05,
667
+ "loss": 0.6082,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 1.6614173228346458,
672
+ "grad_norm": 1.09375,
673
+ "learning_rate": 1.9139787753703554e-05,
674
+ "loss": 0.6023,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 1.678915135608049,
679
+ "grad_norm": 1.0859375,
680
+ "learning_rate": 1.91178746637191e-05,
681
+ "loss": 0.6152,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 1.6964129483814523,
686
+ "grad_norm": 1.296875,
687
+ "learning_rate": 1.9095700336535017e-05,
688
+ "loss": 0.6076,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 1.7139107611548556,
693
+ "grad_norm": 1.078125,
694
+ "learning_rate": 1.907326548573205e-05,
695
+ "loss": 0.6257,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 1.731408573928259,
700
+ "grad_norm": 1.21875,
701
+ "learning_rate": 1.905057083327474e-05,
702
+ "loss": 0.616,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 1.7489063867016623,
707
+ "grad_norm": 1.3203125,
708
+ "learning_rate": 1.9027617109488164e-05,
709
+ "loss": 0.6239,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 1.7664041994750657,
714
+ "grad_norm": 1.125,
715
+ "learning_rate": 1.9004405053034445e-05,
716
+ "loss": 0.5979,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 1.7839020122484688,
721
+ "grad_norm": 1.03125,
722
+ "learning_rate": 1.8980935410888973e-05,
723
+ "loss": 0.6177,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 1.8013998250218721,
728
+ "grad_norm": 1.0859375,
729
+ "learning_rate": 1.895720893831638e-05,
730
+ "loss": 0.5923,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 1.8188976377952755,
735
+ "grad_norm": 1.078125,
736
+ "learning_rate": 1.893322639884622e-05,
737
+ "loss": 0.6029,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 1.8363954505686788,
742
+ "grad_norm": 1.1328125,
743
+ "learning_rate": 1.8908988564248415e-05,
744
+ "loss": 0.6273,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 1.8538932633420822,
749
+ "grad_norm": 1.1953125,
750
+ "learning_rate": 1.8884496214508398e-05,
751
+ "loss": 0.6358,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 1.8713910761154855,
756
+ "grad_norm": 1.09375,
757
+ "learning_rate": 1.8859750137802037e-05,
758
+ "loss": 0.6321,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 1.8888888888888888,
763
+ "grad_norm": 1.1953125,
764
+ "learning_rate": 1.8834751130470247e-05,
765
+ "loss": 0.6118,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 1.9063867016622922,
770
+ "grad_norm": 1.140625,
771
+ "learning_rate": 1.8809499996993385e-05,
772
+ "loss": 0.6095,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 1.9238845144356955,
777
+ "grad_norm": 1.09375,
778
+ "learning_rate": 1.8783997549965344e-05,
779
+ "loss": 0.622,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 1.9413823272090989,
784
+ "grad_norm": 1.2421875,
785
+ "learning_rate": 1.875824461006741e-05,
786
+ "loss": 0.636,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 1.9588801399825022,
791
+ "grad_norm": 1.125,
792
+ "learning_rate": 1.8732242006041864e-05,
793
+ "loss": 0.6089,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 1.9763779527559056,
798
+ "grad_norm": 1.1328125,
799
+ "learning_rate": 1.8705990574665288e-05,
800
+ "loss": 0.6169,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 1.993875765529309,
805
+ "grad_norm": 1.1640625,
806
+ "learning_rate": 1.8679491160721654e-05,
807
+ "loss": 0.6174,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 2.010498687664042,
812
+ "grad_norm": 1.640625,
813
+ "learning_rate": 1.8652744616975142e-05,
814
+ "loss": 0.566,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 2.027996500437445,
819
+ "grad_norm": 1.6328125,
820
+ "learning_rate": 1.8625751804142685e-05,
821
+ "loss": 0.5181,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 2.0454943132108485,
826
+ "grad_norm": 1.2890625,
827
+ "learning_rate": 1.8598513590866278e-05,
828
+ "loss": 0.5257,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 2.062992125984252,
833
+ "grad_norm": 1.2890625,
834
+ "learning_rate": 1.8571030853685016e-05,
835
+ "loss": 0.5193,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 2.080489938757655,
840
+ "grad_norm": 1.3125,
841
+ "learning_rate": 1.8543304477006906e-05,
842
+ "loss": 0.5252,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 2.0979877515310585,
847
+ "grad_norm": 1.390625,
848
+ "learning_rate": 1.851533535308038e-05,
849
+ "loss": 0.5194,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 2.115485564304462,
854
+ "grad_norm": 1.1875,
855
+ "learning_rate": 1.848712438196561e-05,
856
+ "loss": 0.5126,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 2.1329833770778652,
861
+ "grad_norm": 1.2890625,
862
+ "learning_rate": 1.8458672471505522e-05,
863
+ "loss": 0.5007,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 2.1504811898512686,
868
+ "grad_norm": 1.2421875,
869
+ "learning_rate": 1.8429980537296587e-05,
870
+ "loss": 0.5205,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 2.167979002624672,
875
+ "grad_norm": 1.25,
876
+ "learning_rate": 1.840104950265936e-05,
877
+ "loss": 0.5018,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 2.1854768153980753,
882
+ "grad_norm": 1.359375,
883
+ "learning_rate": 1.8371880298608768e-05,
884
+ "loss": 0.5216,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 2.2029746281714786,
889
+ "grad_norm": 1.4921875,
890
+ "learning_rate": 1.834247386382414e-05,
891
+ "loss": 0.5109,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 2.220472440944882,
896
+ "grad_norm": 1.359375,
897
+ "learning_rate": 1.8312831144619024e-05,
898
+ "loss": 0.512,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 2.2379702537182853,
903
+ "grad_norm": 1.390625,
904
+ "learning_rate": 1.828295309491069e-05,
905
+ "loss": 0.5139,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 2.2554680664916886,
910
+ "grad_norm": 1.3203125,
911
+ "learning_rate": 1.8252840676189484e-05,
912
+ "loss": 0.5277,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 2.272965879265092,
917
+ "grad_norm": 1.4375,
918
+ "learning_rate": 1.8222494857487845e-05,
919
+ "loss": 0.5175,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 2.2904636920384953,
924
+ "grad_norm": 1.4609375,
925
+ "learning_rate": 1.819191661534915e-05,
926
+ "loss": 0.5247,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 2.3079615048118987,
931
+ "grad_norm": 1.3046875,
932
+ "learning_rate": 1.8161106933796268e-05,
933
+ "loss": 0.5173,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 2.325459317585302,
938
+ "grad_norm": 2.0,
939
+ "learning_rate": 1.813006680429991e-05,
940
+ "loss": 0.5262,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 2.3429571303587053,
945
+ "grad_norm": 1.328125,
946
+ "learning_rate": 1.8098797225746703e-05,
947
+ "loss": 0.5167,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 2.3604549431321082,
952
+ "grad_norm": 1.2890625,
953
+ "learning_rate": 1.8067299204407075e-05,
954
+ "loss": 0.5254,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 2.377952755905512,
959
+ "grad_norm": 1.40625,
960
+ "learning_rate": 1.803557375390284e-05,
961
+ "loss": 0.5234,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 2.395450568678915,
966
+ "grad_norm": 1.4375,
967
+ "learning_rate": 1.8003621895174603e-05,
968
+ "loss": 0.5113,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 2.4129483814523183,
973
+ "grad_norm": 1.296875,
974
+ "learning_rate": 1.797144465644889e-05,
975
+ "loss": 0.5177,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 2.4304461942257216,
980
+ "grad_norm": 1.34375,
981
+ "learning_rate": 1.7939043073205076e-05,
982
+ "loss": 0.5289,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 2.447944006999125,
987
+ "grad_norm": 1.3671875,
988
+ "learning_rate": 1.7906418188142045e-05,
989
+ "loss": 0.524,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 2.4654418197725283,
994
+ "grad_norm": 1.34375,
995
+ "learning_rate": 1.7873571051144644e-05,
996
+ "loss": 0.5193,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 2.4829396325459316,
1001
+ "grad_norm": 1.421875,
1002
+ "learning_rate": 1.7840502719249898e-05,
1003
+ "loss": 0.5117,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 2.500437445319335,
1008
+ "grad_norm": 1.375,
1009
+ "learning_rate": 1.7807214256612995e-05,
1010
+ "loss": 0.5436,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 2.5179352580927383,
1015
+ "grad_norm": 1.3203125,
1016
+ "learning_rate": 1.777370673447303e-05,
1017
+ "loss": 0.5229,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 2.5354330708661417,
1022
+ "grad_norm": 1.375,
1023
+ "learning_rate": 1.7739981231118558e-05,
1024
+ "loss": 0.5243,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 2.552930883639545,
1029
+ "grad_norm": 1.3046875,
1030
+ "learning_rate": 1.770603883185286e-05,
1031
+ "loss": 0.5244,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 2.5704286964129484,
1036
+ "grad_norm": 1.375,
1037
+ "learning_rate": 1.7671880628959034e-05,
1038
+ "loss": 0.5284,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 2.5879265091863517,
1043
+ "grad_norm": 1.234375,
1044
+ "learning_rate": 1.763750772166486e-05,
1045
+ "loss": 0.5243,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 2.605424321959755,
1050
+ "grad_norm": 1.4375,
1051
+ "learning_rate": 1.7602921216107397e-05,
1052
+ "loss": 0.5299,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 2.6229221347331584,
1057
+ "grad_norm": 1.3046875,
1058
+ "learning_rate": 1.7568122225297407e-05,
1059
+ "loss": 0.5129,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 2.6404199475065617,
1064
+ "grad_norm": 1.40625,
1065
+ "learning_rate": 1.753311186908353e-05,
1066
+ "loss": 0.5222,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 2.657917760279965,
1071
+ "grad_norm": 1.3515625,
1072
+ "learning_rate": 1.7497891274116246e-05,
1073
+ "loss": 0.5314,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 2.6754155730533684,
1078
+ "grad_norm": 1.3203125,
1079
+ "learning_rate": 1.7462461573811632e-05,
1080
+ "loss": 0.5145,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 2.6929133858267718,
1085
+ "grad_norm": 1.3203125,
1086
+ "learning_rate": 1.742682390831487e-05,
1087
+ "loss": 0.5252,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 2.710411198600175,
1092
+ "grad_norm": 1.515625,
1093
+ "learning_rate": 1.739097942446356e-05,
1094
+ "loss": 0.5354,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 2.7279090113735784,
1099
+ "grad_norm": 1.328125,
1100
+ "learning_rate": 1.7354929275750832e-05,
1101
+ "loss": 0.5128,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 2.745406824146982,
1106
+ "grad_norm": 1.2890625,
1107
+ "learning_rate": 1.731867462228819e-05,
1108
+ "loss": 0.5337,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 2.7629046369203847,
1113
+ "grad_norm": 1.2890625,
1114
+ "learning_rate": 1.7282216630768223e-05,
1115
+ "loss": 0.51,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 2.7804024496937885,
1120
+ "grad_norm": 1.296875,
1121
+ "learning_rate": 1.7245556474427036e-05,
1122
+ "loss": 0.5161,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 2.7979002624671914,
1127
+ "grad_norm": 1.4765625,
1128
+ "learning_rate": 1.7208695333006483e-05,
1129
+ "loss": 0.5197,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 2.815398075240595,
1134
+ "grad_norm": 1.3046875,
1135
+ "learning_rate": 1.717163439271623e-05,
1136
+ "loss": 0.5267,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 2.832895888013998,
1141
+ "grad_norm": 1.3828125,
1142
+ "learning_rate": 1.7134374846195566e-05,
1143
+ "loss": 0.5144,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 2.850393700787402,
1148
+ "grad_norm": 1.3046875,
1149
+ "learning_rate": 1.7096917892475024e-05,
1150
+ "loss": 0.5255,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 2.8678915135608047,
1155
+ "grad_norm": 1.546875,
1156
+ "learning_rate": 1.7059264736937796e-05,
1157
+ "loss": 0.5197,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 2.885389326334208,
1162
+ "grad_norm": 1.3828125,
1163
+ "learning_rate": 1.702141659128095e-05,
1164
+ "loss": 0.5165,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 2.9028871391076114,
1169
+ "grad_norm": 1.296875,
1170
+ "learning_rate": 1.6983374673476428e-05,
1171
+ "loss": 0.5202,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 2.9203849518810148,
1176
+ "grad_norm": 1.328125,
1177
+ "learning_rate": 1.694514020773186e-05,
1178
+ "loss": 0.5227,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 2.937882764654418,
1183
+ "grad_norm": 1.328125,
1184
+ "learning_rate": 1.6906714424451154e-05,
1185
+ "loss": 0.5223,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 2.9553805774278215,
1190
+ "grad_norm": 1.3359375,
1191
+ "learning_rate": 1.6868098560194926e-05,
1192
+ "loss": 0.528,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 2.972878390201225,
1197
+ "grad_norm": 1.3046875,
1198
+ "learning_rate": 1.6829293857640675e-05,
1199
+ "loss": 0.518,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 2.990376202974628,
1204
+ "grad_norm": 1.3671875,
1205
+ "learning_rate": 1.679030156554282e-05,
1206
+ "loss": 0.5345,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 3.0069991251093615,
1211
+ "grad_norm": 1.6015625,
1212
+ "learning_rate": 1.6751122938692493e-05,
1213
+ "loss": 0.4821,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 3.024496937882765,
1218
+ "grad_norm": 1.6796875,
1219
+ "learning_rate": 1.6711759237877188e-05,
1220
+ "loss": 0.4391,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 3.041994750656168,
1225
+ "grad_norm": 1.890625,
1226
+ "learning_rate": 1.667221172984015e-05,
1227
+ "loss": 0.4258,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 3.059492563429571,
1232
+ "grad_norm": 1.6796875,
1233
+ "learning_rate": 1.663248168723964e-05,
1234
+ "loss": 0.4333,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 3.0769903762029744,
1239
+ "grad_norm": 1.7890625,
1240
+ "learning_rate": 1.6592570388607978e-05,
1241
+ "loss": 0.4318,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 3.094488188976378,
1246
+ "grad_norm": 1.703125,
1247
+ "learning_rate": 1.6552479118310378e-05,
1248
+ "loss": 0.4146,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 3.111986001749781,
1253
+ "grad_norm": 1.5078125,
1254
+ "learning_rate": 1.651220916650364e-05,
1255
+ "loss": 0.4209,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 3.1294838145231845,
1260
+ "grad_norm": 1.6171875,
1261
+ "learning_rate": 1.6471761829094623e-05,
1262
+ "loss": 0.4331,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 3.146981627296588,
1267
+ "grad_norm": 1.578125,
1268
+ "learning_rate": 1.643113840769854e-05,
1269
+ "loss": 0.428,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 3.164479440069991,
1274
+ "grad_norm": 1.9609375,
1275
+ "learning_rate": 1.6390340209597074e-05,
1276
+ "loss": 0.4195,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 3.1819772528433945,
1281
+ "grad_norm": 1.7109375,
1282
+ "learning_rate": 1.6349368547696297e-05,
1283
+ "loss": 0.4232,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 3.199475065616798,
1288
+ "grad_norm": 1.6171875,
1289
+ "learning_rate": 1.6308224740484456e-05,
1290
+ "loss": 0.4258,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 3.216972878390201,
1295
+ "grad_norm": 1.640625,
1296
+ "learning_rate": 1.6266910111989498e-05,
1297
+ "loss": 0.424,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 3.2344706911636045,
1302
+ "grad_norm": 1.5703125,
1303
+ "learning_rate": 1.622542599173649e-05,
1304
+ "loss": 0.4326,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 3.251968503937008,
1309
+ "grad_norm": 1.4921875,
1310
+ "learning_rate": 1.6183773714704824e-05,
1311
+ "loss": 0.436,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 3.269466316710411,
1316
+ "grad_norm": 1.671875,
1317
+ "learning_rate": 1.6141954621285267e-05,
1318
+ "loss": 0.4423,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 3.2869641294838146,
1323
+ "grad_norm": 1.71875,
1324
+ "learning_rate": 1.6099970057236808e-05,
1325
+ "loss": 0.4348,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 3.304461942257218,
1330
+ "grad_norm": 1.8125,
1331
+ "learning_rate": 1.605782137364338e-05,
1332
+ "loss": 0.4306,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 3.3219597550306212,
1337
+ "grad_norm": 1.609375,
1338
+ "learning_rate": 1.6015509926870343e-05,
1339
+ "loss": 0.4321,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 3.3394575678040246,
1344
+ "grad_norm": 1.8203125,
1345
+ "learning_rate": 1.597303707852087e-05,
1346
+ "loss": 0.446,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 3.356955380577428,
1351
+ "grad_norm": 1.6484375,
1352
+ "learning_rate": 1.5930404195392114e-05,
1353
+ "loss": 0.4246,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 3.3744531933508313,
1358
+ "grad_norm": 1.7734375,
1359
+ "learning_rate": 1.588761264943122e-05,
1360
+ "loss": 0.4184,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 3.3919510061242346,
1365
+ "grad_norm": 1.8828125,
1366
+ "learning_rate": 1.5844663817691187e-05,
1367
+ "loss": 0.4267,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 3.409448818897638,
1372
+ "grad_norm": 2.0,
1373
+ "learning_rate": 1.5801559082286546e-05,
1374
+ "loss": 0.4358,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 3.4269466316710413,
1379
+ "grad_norm": 1.671875,
1380
+ "learning_rate": 1.5758299830348884e-05,
1381
+ "loss": 0.4438,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 3.4444444444444446,
1386
+ "grad_norm": 1.578125,
1387
+ "learning_rate": 1.5714887453982204e-05,
1388
+ "loss": 0.4413,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 3.4619422572178475,
1393
+ "grad_norm": 1.7109375,
1394
+ "learning_rate": 1.5671323350218135e-05,
1395
+ "loss": 0.4425,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 3.4794400699912513,
1400
+ "grad_norm": 1.640625,
1401
+ "learning_rate": 1.562760892097096e-05,
1402
+ "loss": 0.4326,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 3.4969378827646542,
1407
+ "grad_norm": 1.59375,
1408
+ "learning_rate": 1.5583745572992518e-05,
1409
+ "loss": 0.4335,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 3.514435695538058,
1414
+ "grad_norm": 1.734375,
1415
+ "learning_rate": 1.553973471782692e-05,
1416
+ "loss": 0.4405,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 3.531933508311461,
1421
+ "grad_norm": 1.7265625,
1422
+ "learning_rate": 1.5495577771765134e-05,
1423
+ "loss": 0.4259,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 3.5494313210848643,
1428
+ "grad_norm": 1.5546875,
1429
+ "learning_rate": 1.5451276155799405e-05,
1430
+ "loss": 0.4218,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 3.5669291338582676,
1435
+ "grad_norm": 1.65625,
1436
+ "learning_rate": 1.540683129557752e-05,
1437
+ "loss": 0.4248,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 3.584426946631671,
1442
+ "grad_norm": 1.71875,
1443
+ "learning_rate": 1.5362244621356946e-05,
1444
+ "loss": 0.4276,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 3.6019247594050743,
1449
+ "grad_norm": 1.6640625,
1450
+ "learning_rate": 1.531751756795879e-05,
1451
+ "loss": 0.4408,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 3.6194225721784776,
1456
+ "grad_norm": 1.59375,
1457
+ "learning_rate": 1.5272651574721632e-05,
1458
+ "loss": 0.4264,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 3.636920384951881,
1463
+ "grad_norm": 1.7109375,
1464
+ "learning_rate": 1.5227648085455202e-05,
1465
+ "loss": 0.4295,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 3.6544181977252843,
1470
+ "grad_norm": 1.7734375,
1471
+ "learning_rate": 1.5182508548393917e-05,
1472
+ "loss": 0.427,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 3.6719160104986877,
1477
+ "grad_norm": 1.6953125,
1478
+ "learning_rate": 1.5137234416150288e-05,
1479
+ "loss": 0.4398,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 3.689413823272091,
1484
+ "grad_norm": 1.546875,
1485
+ "learning_rate": 1.5091827145668156e-05,
1486
+ "loss": 0.4411,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 3.7069116360454943,
1491
+ "grad_norm": 1.734375,
1492
+ "learning_rate": 1.504628819817582e-05,
1493
+ "loss": 0.4181,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 3.7244094488188977,
1498
+ "grad_norm": 1.6484375,
1499
+ "learning_rate": 1.5000619039139011e-05,
1500
+ "loss": 0.4384,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 3.741907261592301,
1505
+ "grad_norm": 1.7109375,
1506
+ "learning_rate": 1.495482113821373e-05,
1507
+ "loss": 0.4293,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 3.7594050743657044,
1512
+ "grad_norm": 1.7734375,
1513
+ "learning_rate": 1.4908895969198951e-05,
1514
+ "loss": 0.4298,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 3.7769028871391077,
1519
+ "grad_norm": 1.625,
1520
+ "learning_rate": 1.4862845009989211e-05,
1521
+ "loss": 0.4403,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 3.794400699912511,
1526
+ "grad_norm": 1.6640625,
1527
+ "learning_rate": 1.4816669742527018e-05,
1528
+ "loss": 0.4373,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 3.8118985126859144,
1533
+ "grad_norm": 1.546875,
1534
+ "learning_rate": 1.4770371652755203e-05,
1535
+ "loss": 0.4268,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 3.8293963254593177,
1540
+ "grad_norm": 1.8203125,
1541
+ "learning_rate": 1.4723952230569057e-05,
1542
+ "loss": 0.4274,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 3.846894138232721,
1547
+ "grad_norm": 1.6953125,
1548
+ "learning_rate": 1.4677412969768427e-05,
1549
+ "loss": 0.4313,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 3.864391951006124,
1554
+ "grad_norm": 1.6484375,
1555
+ "learning_rate": 1.4630755368009611e-05,
1556
+ "loss": 0.4465,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 3.8818897637795278,
1561
+ "grad_norm": 1.546875,
1562
+ "learning_rate": 1.4583980926757184e-05,
1563
+ "loss": 0.4454,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 3.8993875765529307,
1568
+ "grad_norm": 1.921875,
1569
+ "learning_rate": 1.4537091151235673e-05,
1570
+ "loss": 0.4412,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 3.9168853893263345,
1575
+ "grad_norm": 1.796875,
1576
+ "learning_rate": 1.449008755038112e-05,
1577
+ "loss": 0.4289,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 3.9343832020997374,
1582
+ "grad_norm": 1.8515625,
1583
+ "learning_rate": 1.4442971636792518e-05,
1584
+ "loss": 0.4311,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 3.9518810148731407,
1589
+ "grad_norm": 1.6640625,
1590
+ "learning_rate": 1.4395744926683142e-05,
1591
+ "loss": 0.4263,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 3.969378827646544,
1596
+ "grad_norm": 1.875,
1597
+ "learning_rate": 1.4348408939831758e-05,
1598
+ "loss": 0.4435,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 3.9868766404199474,
1603
+ "grad_norm": 1.65625,
1604
+ "learning_rate": 1.4300965199533696e-05,
1605
+ "loss": 0.433,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 4.003499562554681,
1610
+ "grad_norm": 2.015625,
1611
+ "learning_rate": 1.4253415232551861e-05,
1612
+ "loss": 0.4271,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 4.020997375328084,
1617
+ "grad_norm": 2.28125,
1618
+ "learning_rate": 1.4205760569067577e-05,
1619
+ "loss": 0.3527,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 4.038495188101487,
1624
+ "grad_norm": 1.7265625,
1625
+ "learning_rate": 1.4158002742631359e-05,
1626
+ "loss": 0.3734,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 4.05599300087489,
1631
+ "grad_norm": 2.296875,
1632
+ "learning_rate": 1.4110143290113546e-05,
1633
+ "loss": 0.3634,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 4.073490813648294,
1638
+ "grad_norm": 1.9921875,
1639
+ "learning_rate": 1.4062183751654868e-05,
1640
+ "loss": 0.3462,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 4.090988626421697,
1645
+ "grad_norm": 1.96875,
1646
+ "learning_rate": 1.4014125670616856e-05,
1647
+ "loss": 0.3487,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 4.108486439195101,
1652
+ "grad_norm": 1.9921875,
1653
+ "learning_rate": 1.3965970593532201e-05,
1654
+ "loss": 0.3794,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 4.125984251968504,
1659
+ "grad_norm": 1.890625,
1660
+ "learning_rate": 1.3917720070054965e-05,
1661
+ "loss": 0.3634,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 4.1434820647419075,
1666
+ "grad_norm": 1.9609375,
1667
+ "learning_rate": 1.386937565291073e-05,
1668
+ "loss": 0.3601,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 4.16097987751531,
1673
+ "grad_norm": 1.9453125,
1674
+ "learning_rate": 1.382093889784662e-05,
1675
+ "loss": 0.3654,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 4.178477690288714,
1680
+ "grad_norm": 2.078125,
1681
+ "learning_rate": 1.3772411363581238e-05,
1682
+ "loss": 0.3492,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 4.195975503062117,
1687
+ "grad_norm": 1.96875,
1688
+ "learning_rate": 1.3723794611754502e-05,
1689
+ "loss": 0.3683,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 4.213473315835521,
1694
+ "grad_norm": 1.859375,
1695
+ "learning_rate": 1.3675090206877399e-05,
1696
+ "loss": 0.3634,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 4.230971128608924,
1701
+ "grad_norm": 2.1875,
1702
+ "learning_rate": 1.3626299716281639e-05,
1703
+ "loss": 0.3623,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 4.248468941382328,
1708
+ "grad_norm": 1.890625,
1709
+ "learning_rate": 1.3577424710069202e-05,
1710
+ "loss": 0.3596,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 4.2659667541557305,
1715
+ "grad_norm": 2.25,
1716
+ "learning_rate": 1.3528466761061839e-05,
1717
+ "loss": 0.3623,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 4.283464566929134,
1722
+ "grad_norm": 1.9453125,
1723
+ "learning_rate": 1.3479427444750415e-05,
1724
+ "loss": 0.3535,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 4.300962379702537,
1729
+ "grad_norm": 2.09375,
1730
+ "learning_rate": 1.343030833924426e-05,
1731
+ "loss": 0.3592,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 4.318460192475941,
1736
+ "grad_norm": 1.9765625,
1737
+ "learning_rate": 1.338111102522035e-05,
1738
+ "loss": 0.3644,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 4.335958005249344,
1743
+ "grad_norm": 2.25,
1744
+ "learning_rate": 1.3331837085872444e-05,
1745
+ "loss": 0.3565,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 4.353455818022747,
1750
+ "grad_norm": 2.09375,
1751
+ "learning_rate": 1.3282488106860146e-05,
1752
+ "loss": 0.3613,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 4.3709536307961505,
1757
+ "grad_norm": 1.984375,
1758
+ "learning_rate": 1.323306567625788e-05,
1759
+ "loss": 0.3574,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 4.388451443569553,
1764
+ "grad_norm": 2.484375,
1765
+ "learning_rate": 1.3183571384503767e-05,
1766
+ "loss": 0.3507,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 4.405949256342957,
1771
+ "grad_norm": 1.8671875,
1772
+ "learning_rate": 1.3134006824348464e-05,
1773
+ "loss": 0.3583,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 4.42344706911636,
1778
+ "grad_norm": 2.0,
1779
+ "learning_rate": 1.3084373590803898e-05,
1780
+ "loss": 0.3567,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 4.440944881889764,
1785
+ "grad_norm": 1.96875,
1786
+ "learning_rate": 1.303467328109193e-05,
1787
+ "loss": 0.3538,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 4.458442694663167,
1792
+ "grad_norm": 2.046875,
1793
+ "learning_rate": 1.2984907494592983e-05,
1794
+ "loss": 0.3623,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 4.475940507436571,
1799
+ "grad_norm": 1.9375,
1800
+ "learning_rate": 1.2935077832794533e-05,
1801
+ "loss": 0.3649,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 4.4934383202099735,
1806
+ "grad_norm": 1.984375,
1807
+ "learning_rate": 1.2885185899239617e-05,
1808
+ "loss": 0.3551,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 4.510936132983377,
1813
+ "grad_norm": 2.140625,
1814
+ "learning_rate": 1.2835233299475192e-05,
1815
+ "loss": 0.354,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 4.52843394575678,
1820
+ "grad_norm": 2.109375,
1821
+ "learning_rate": 1.2785221641000487e-05,
1822
+ "loss": 0.3652,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 4.545931758530184,
1827
+ "grad_norm": 2.0625,
1828
+ "learning_rate": 1.2735152533215275e-05,
1829
+ "loss": 0.3597,
1830
+ "step": 2600
1831
+ },
1832
+ {
1833
+ "epoch": 4.563429571303587,
1834
+ "grad_norm": 1.9375,
1835
+ "learning_rate": 1.2685027587368072e-05,
1836
+ "loss": 0.3567,
1837
+ "step": 2610
1838
+ },
1839
+ {
1840
+ "epoch": 4.580927384076991,
1841
+ "grad_norm": 1.75,
1842
+ "learning_rate": 1.2634848416504289e-05,
1843
+ "loss": 0.3577,
1844
+ "step": 2620
1845
+ },
1846
+ {
1847
+ "epoch": 4.5984251968503935,
1848
+ "grad_norm": 1.9453125,
1849
+ "learning_rate": 1.2584616635414325e-05,
1850
+ "loss": 0.3576,
1851
+ "step": 2630
1852
+ },
1853
+ {
1854
+ "epoch": 4.615923009623797,
1855
+ "grad_norm": 1.9609375,
1856
+ "learning_rate": 1.2534333860581607e-05,
1857
+ "loss": 0.3609,
1858
+ "step": 2640
1859
+ },
1860
+ {
1861
+ "epoch": 4.6334208223972,
1862
+ "grad_norm": 2.109375,
1863
+ "learning_rate": 1.248400171013056e-05,
1864
+ "loss": 0.3525,
1865
+ "step": 2650
1866
+ },
1867
+ {
1868
+ "epoch": 4.650918635170604,
1869
+ "grad_norm": 1.7734375,
1870
+ "learning_rate": 1.2433621803774542e-05,
1871
+ "loss": 0.3567,
1872
+ "step": 2660
1873
+ },
1874
+ {
1875
+ "epoch": 4.668416447944007,
1876
+ "grad_norm": 1.921875,
1877
+ "learning_rate": 1.2383195762763718e-05,
1878
+ "loss": 0.3623,
1879
+ "step": 2670
1880
+ },
1881
+ {
1882
+ "epoch": 4.685914260717411,
1883
+ "grad_norm": 1.8046875,
1884
+ "learning_rate": 1.2332725209832892e-05,
1885
+ "loss": 0.3643,
1886
+ "step": 2680
1887
+ },
1888
+ {
1889
+ "epoch": 4.703412073490814,
1890
+ "grad_norm": 1.8828125,
1891
+ "learning_rate": 1.2282211769149283e-05,
1892
+ "loss": 0.3642,
1893
+ "step": 2690
1894
+ },
1895
+ {
1896
+ "epoch": 4.7209098862642165,
1897
+ "grad_norm": 1.96875,
1898
+ "learning_rate": 1.2231657066260261e-05,
1899
+ "loss": 0.348,
1900
+ "step": 2700
1901
+ },
1902
+ {
1903
+ "epoch": 4.73840769903762,
1904
+ "grad_norm": 2.03125,
1905
+ "learning_rate": 1.2181062728041029e-05,
1906
+ "loss": 0.3545,
1907
+ "step": 2710
1908
+ },
1909
+ {
1910
+ "epoch": 4.755905511811024,
1911
+ "grad_norm": 2.5625,
1912
+ "learning_rate": 1.2130430382642276e-05,
1913
+ "loss": 0.3624,
1914
+ "step": 2720
1915
+ },
1916
+ {
1917
+ "epoch": 4.773403324584427,
1918
+ "grad_norm": 1.984375,
1919
+ "learning_rate": 1.2079761659437781e-05,
1920
+ "loss": 0.3719,
1921
+ "step": 2730
1922
+ },
1923
+ {
1924
+ "epoch": 4.79090113735783,
1925
+ "grad_norm": 2.140625,
1926
+ "learning_rate": 1.202905818897198e-05,
1927
+ "loss": 0.362,
1928
+ "step": 2740
1929
+ },
1930
+ {
1931
+ "epoch": 4.808398950131234,
1932
+ "grad_norm": 2.15625,
1933
+ "learning_rate": 1.1978321602907497e-05,
1934
+ "loss": 0.3691,
1935
+ "step": 2750
1936
+ },
1937
+ {
1938
+ "epoch": 4.8258967629046365,
1939
+ "grad_norm": 1.953125,
1940
+ "learning_rate": 1.192755353397262e-05,
1941
+ "loss": 0.3611,
1942
+ "step": 2760
1943
+ },
1944
+ {
1945
+ "epoch": 4.84339457567804,
1946
+ "grad_norm": 2.21875,
1947
+ "learning_rate": 1.187675561590878e-05,
1948
+ "loss": 0.356,
1949
+ "step": 2770
1950
+ },
1951
+ {
1952
+ "epoch": 4.860892388451443,
1953
+ "grad_norm": 2.0,
1954
+ "learning_rate": 1.1825929483417975e-05,
1955
+ "loss": 0.349,
1956
+ "step": 2780
1957
+ },
1958
+ {
1959
+ "epoch": 4.878390201224847,
1960
+ "grad_norm": 2.265625,
1961
+ "learning_rate": 1.1775076772110136e-05,
1962
+ "loss": 0.3643,
1963
+ "step": 2790
1964
+ },
1965
+ {
1966
+ "epoch": 4.89588801399825,
1967
+ "grad_norm": 1.953125,
1968
+ "learning_rate": 1.1724199118450537e-05,
1969
+ "loss": 0.358,
1970
+ "step": 2800
1971
+ },
1972
+ {
1973
+ "epoch": 4.913385826771654,
1974
+ "grad_norm": 2.359375,
1975
+ "learning_rate": 1.1673298159707086e-05,
1976
+ "loss": 0.358,
1977
+ "step": 2810
1978
+ },
1979
+ {
1980
+ "epoch": 4.930883639545057,
1981
+ "grad_norm": 1.875,
1982
+ "learning_rate": 1.1622375533897683e-05,
1983
+ "loss": 0.3705,
1984
+ "step": 2820
1985
+ },
1986
+ {
1987
+ "epoch": 4.94838145231846,
1988
+ "grad_norm": 2.171875,
1989
+ "learning_rate": 1.157143287973747e-05,
1990
+ "loss": 0.3638,
1991
+ "step": 2830
1992
+ },
1993
+ {
1994
+ "epoch": 4.965879265091863,
1995
+ "grad_norm": 2.46875,
1996
+ "learning_rate": 1.1520471836586115e-05,
1997
+ "loss": 0.3417,
1998
+ "step": 2840
1999
+ },
2000
+ {
2001
+ "epoch": 4.983377077865267,
2002
+ "grad_norm": 2.21875,
2003
+ "learning_rate": 1.1469494044395055e-05,
2004
+ "loss": 0.3732,
2005
+ "step": 2850
2006
+ },
2007
+ {
2008
+ "epoch": 5.0,
2009
+ "grad_norm": 2.796875,
2010
+ "learning_rate": 1.1418501143654713e-05,
2011
+ "loss": 0.376,
2012
+ "step": 2860
2013
+ },
2014
+ {
2015
+ "epoch": 5.017497812773403,
2016
+ "grad_norm": 2.6875,
2017
+ "learning_rate": 1.1367494775341716e-05,
2018
+ "loss": 0.3109,
2019
+ "step": 2870
2020
+ },
2021
+ {
2022
+ "epoch": 5.034995625546807,
2023
+ "grad_norm": 2.265625,
2024
+ "learning_rate": 1.1316476580866091e-05,
2025
+ "loss": 0.3136,
2026
+ "step": 2880
2027
+ },
2028
+ {
2029
+ "epoch": 5.05249343832021,
2030
+ "grad_norm": 2.78125,
2031
+ "learning_rate": 1.1265448202018432e-05,
2032
+ "loss": 0.3137,
2033
+ "step": 2890
2034
+ },
2035
+ {
2036
+ "epoch": 5.069991251093613,
2037
+ "grad_norm": 2.71875,
2038
+ "learning_rate": 1.121441128091706e-05,
2039
+ "loss": 0.3082,
2040
+ "step": 2900
2041
+ },
2042
+ {
2043
+ "epoch": 5.087489063867016,
2044
+ "grad_norm": 2.109375,
2045
+ "learning_rate": 1.1163367459955208e-05,
2046
+ "loss": 0.3102,
2047
+ "step": 2910
2048
+ },
2049
+ {
2050
+ "epoch": 5.10498687664042,
2051
+ "grad_norm": 2.4375,
2052
+ "learning_rate": 1.1112318381748135e-05,
2053
+ "loss": 0.3092,
2054
+ "step": 2920
2055
+ },
2056
+ {
2057
+ "epoch": 5.122484689413823,
2058
+ "grad_norm": 2.953125,
2059
+ "learning_rate": 1.1061265689080296e-05,
2060
+ "loss": 0.3054,
2061
+ "step": 2930
2062
+ },
2063
+ {
2064
+ "epoch": 5.139982502187227,
2065
+ "grad_norm": 2.0625,
2066
+ "learning_rate": 1.1010211024852445e-05,
2067
+ "loss": 0.3165,
2068
+ "step": 2940
2069
+ },
2070
+ {
2071
+ "epoch": 5.15748031496063,
2072
+ "grad_norm": 2.078125,
2073
+ "learning_rate": 1.0959156032028789e-05,
2074
+ "loss": 0.3081,
2075
+ "step": 2950
2076
+ },
2077
+ {
2078
+ "epoch": 5.174978127734033,
2079
+ "grad_norm": 2.015625,
2080
+ "learning_rate": 1.0908102353584117e-05,
2081
+ "loss": 0.3047,
2082
+ "step": 2960
2083
+ },
2084
+ {
2085
+ "epoch": 5.192475940507436,
2086
+ "grad_norm": 2.0,
2087
+ "learning_rate": 1.0857051632450905e-05,
2088
+ "loss": 0.3016,
2089
+ "step": 2970
2090
+ },
2091
+ {
2092
+ "epoch": 5.20997375328084,
2093
+ "grad_norm": 2.1875,
2094
+ "learning_rate": 1.0806005511466478e-05,
2095
+ "loss": 0.306,
2096
+ "step": 2980
2097
+ },
2098
+ {
2099
+ "epoch": 5.227471566054243,
2100
+ "grad_norm": 2.5,
2101
+ "learning_rate": 1.075496563332011e-05,
2102
+ "loss": 0.3036,
2103
+ "step": 2990
2104
+ },
2105
+ {
2106
+ "epoch": 5.244969378827647,
2107
+ "grad_norm": 2.203125,
2108
+ "learning_rate": 1.0703933640500183e-05,
2109
+ "loss": 0.3041,
2110
+ "step": 3000
2111
+ },
2112
+ {
2113
+ "epoch": 5.26246719160105,
2114
+ "grad_norm": 2.515625,
2115
+ "learning_rate": 1.0652911175241336e-05,
2116
+ "loss": 0.3183,
2117
+ "step": 3010
2118
+ },
2119
+ {
2120
+ "epoch": 5.2799650043744535,
2121
+ "grad_norm": 2.515625,
2122
+ "learning_rate": 1.0601899879471593e-05,
2123
+ "loss": 0.2964,
2124
+ "step": 3020
2125
+ },
2126
+ {
2127
+ "epoch": 5.297462817147856,
2128
+ "grad_norm": 2.453125,
2129
+ "learning_rate": 1.0550901394759543e-05,
2130
+ "loss": 0.3006,
2131
+ "step": 3030
2132
+ },
2133
+ {
2134
+ "epoch": 5.31496062992126,
2135
+ "grad_norm": 2.25,
2136
+ "learning_rate": 1.0499917362261505e-05,
2137
+ "loss": 0.3146,
2138
+ "step": 3040
2139
+ },
2140
+ {
2141
+ "epoch": 5.332458442694663,
2142
+ "grad_norm": 2.421875,
2143
+ "learning_rate": 1.0448949422668729e-05,
2144
+ "loss": 0.3153,
2145
+ "step": 3050
2146
+ },
2147
+ {
2148
+ "epoch": 5.349956255468067,
2149
+ "grad_norm": 2.234375,
2150
+ "learning_rate": 1.039799921615458e-05,
2151
+ "loss": 0.3166,
2152
+ "step": 3060
2153
+ },
2154
+ {
2155
+ "epoch": 5.36745406824147,
2156
+ "grad_norm": 2.234375,
2157
+ "learning_rate": 1.0347068382321758e-05,
2158
+ "loss": 0.3069,
2159
+ "step": 3070
2160
+ },
2161
+ {
2162
+ "epoch": 5.3849518810148735,
2163
+ "grad_norm": 2.1875,
2164
+ "learning_rate": 1.0296158560149554e-05,
2165
+ "loss": 0.3031,
2166
+ "step": 3080
2167
+ },
2168
+ {
2169
+ "epoch": 5.402449693788276,
2170
+ "grad_norm": 2.75,
2171
+ "learning_rate": 1.0245271387941085e-05,
2172
+ "loss": 0.308,
2173
+ "step": 3090
2174
+ },
2175
+ {
2176
+ "epoch": 5.41994750656168,
2177
+ "grad_norm": 2.09375,
2178
+ "learning_rate": 1.0194408503270582e-05,
2179
+ "loss": 0.3081,
2180
+ "step": 3100
2181
+ },
2182
+ {
2183
+ "epoch": 5.437445319335083,
2184
+ "grad_norm": 2.25,
2185
+ "learning_rate": 1.0143571542930695e-05,
2186
+ "loss": 0.3052,
2187
+ "step": 3110
2188
+ },
2189
+ {
2190
+ "epoch": 5.454943132108486,
2191
+ "grad_norm": 2.140625,
2192
+ "learning_rate": 1.0092762142879803e-05,
2193
+ "loss": 0.3156,
2194
+ "step": 3120
2195
+ },
2196
+ {
2197
+ "epoch": 5.47244094488189,
2198
+ "grad_norm": 2.109375,
2199
+ "learning_rate": 1.0041981938189401e-05,
2200
+ "loss": 0.3076,
2201
+ "step": 3130
2202
+ },
2203
+ {
2204
+ "epoch": 5.489938757655293,
2205
+ "grad_norm": 2.171875,
2206
+ "learning_rate": 9.99123256299145e-06,
2207
+ "loss": 0.3164,
2208
+ "step": 3140
2209
+ },
2210
+ {
2211
+ "epoch": 5.5074365704286965,
2212
+ "grad_norm": 2.234375,
2213
+ "learning_rate": 9.94051565042581e-06,
2214
+ "loss": 0.3215,
2215
+ "step": 3150
2216
+ },
2217
+ {
2218
+ "epoch": 5.524934383202099,
2219
+ "grad_norm": 2.3125,
2220
+ "learning_rate": 9.889832832587667e-06,
2221
+ "loss": 0.3076,
2222
+ "step": 3160
2223
+ },
2224
+ {
2225
+ "epoch": 5.542432195975503,
2226
+ "grad_norm": 2.296875,
2227
+ "learning_rate": 9.83918574047503e-06,
2228
+ "loss": 0.288,
2229
+ "step": 3170
2230
+ },
2231
+ {
2232
+ "epoch": 5.559930008748906,
2233
+ "grad_norm": 2.25,
2234
+ "learning_rate": 9.788576003936239e-06,
2235
+ "loss": 0.3116,
2236
+ "step": 3180
2237
+ },
2238
+ {
2239
+ "epoch": 5.57742782152231,
2240
+ "grad_norm": 2.203125,
2241
+ "learning_rate": 9.738005251617508e-06,
2242
+ "loss": 0.3083,
2243
+ "step": 3190
2244
+ },
2245
+ {
2246
+ "epoch": 5.594925634295713,
2247
+ "grad_norm": 2.234375,
2248
+ "learning_rate": 9.68747511091052e-06,
2249
+ "loss": 0.3078,
2250
+ "step": 3200
2251
+ },
2252
+ {
2253
+ "epoch": 5.6124234470691166,
2254
+ "grad_norm": 2.421875,
2255
+ "learning_rate": 9.636987207900056e-06,
2256
+ "loss": 0.3131,
2257
+ "step": 3210
2258
+ },
2259
+ {
2260
+ "epoch": 5.6299212598425195,
2261
+ "grad_norm": 2.203125,
2262
+ "learning_rate": 9.58654316731167e-06,
2263
+ "loss": 0.3147,
2264
+ "step": 3220
2265
+ },
2266
+ {
2267
+ "epoch": 5.647419072615923,
2268
+ "grad_norm": 2.109375,
2269
+ "learning_rate": 9.536144612459399e-06,
2270
+ "loss": 0.3131,
2271
+ "step": 3230
2272
+ },
2273
+ {
2274
+ "epoch": 5.664916885389326,
2275
+ "grad_norm": 1.953125,
2276
+ "learning_rate": 9.485793165193531e-06,
2277
+ "loss": 0.3147,
2278
+ "step": 3240
2279
+ },
2280
+ {
2281
+ "epoch": 5.68241469816273,
2282
+ "grad_norm": 2.234375,
2283
+ "learning_rate": 9.435490445848403e-06,
2284
+ "loss": 0.3124,
2285
+ "step": 3250
2286
+ },
2287
+ {
2288
+ "epoch": 5.699912510936133,
2289
+ "grad_norm": 2.125,
2290
+ "learning_rate": 9.385238073190264e-06,
2291
+ "loss": 0.3091,
2292
+ "step": 3260
2293
+ },
2294
+ {
2295
+ "epoch": 5.717410323709537,
2296
+ "grad_norm": 2.59375,
2297
+ "learning_rate": 9.335037664365185e-06,
2298
+ "loss": 0.2988,
2299
+ "step": 3270
2300
+ },
2301
+ {
2302
+ "epoch": 5.7349081364829395,
2303
+ "grad_norm": 2.3125,
2304
+ "learning_rate": 9.284890834847022e-06,
2305
+ "loss": 0.306,
2306
+ "step": 3280
2307
+ },
2308
+ {
2309
+ "epoch": 5.752405949256343,
2310
+ "grad_norm": 2.515625,
2311
+ "learning_rate": 9.234799198385402e-06,
2312
+ "loss": 0.3214,
2313
+ "step": 3290
2314
+ },
2315
+ {
2316
+ "epoch": 5.769903762029746,
2317
+ "grad_norm": 2.046875,
2318
+ "learning_rate": 9.184764366953831e-06,
2319
+ "loss": 0.3178,
2320
+ "step": 3300
2321
+ },
2322
+ {
2323
+ "epoch": 5.78740157480315,
2324
+ "grad_norm": 2.046875,
2325
+ "learning_rate": 9.134787950697798e-06,
2326
+ "loss": 0.3061,
2327
+ "step": 3310
2328
+ },
2329
+ {
2330
+ "epoch": 5.804899387576553,
2331
+ "grad_norm": 2.25,
2332
+ "learning_rate": 9.084871557882957e-06,
2333
+ "loss": 0.3096,
2334
+ "step": 3320
2335
+ },
2336
+ {
2337
+ "epoch": 5.822397200349956,
2338
+ "grad_norm": 2.28125,
2339
+ "learning_rate": 9.035016794843383e-06,
2340
+ "loss": 0.3131,
2341
+ "step": 3330
2342
+ },
2343
+ {
2344
+ "epoch": 5.83989501312336,
2345
+ "grad_norm": 2.09375,
2346
+ "learning_rate": 8.985225265929872e-06,
2347
+ "loss": 0.307,
2348
+ "step": 3340
2349
+ },
2350
+ {
2351
+ "epoch": 5.857392825896763,
2352
+ "grad_norm": 2.390625,
2353
+ "learning_rate": 8.93549857345831e-06,
2354
+ "loss": 0.3107,
2355
+ "step": 3350
2356
+ },
2357
+ {
2358
+ "epoch": 5.874890638670166,
2359
+ "grad_norm": 2.09375,
2360
+ "learning_rate": 8.885838317658126e-06,
2361
+ "loss": 0.3041,
2362
+ "step": 3360
2363
+ },
2364
+ {
2365
+ "epoch": 5.892388451443569,
2366
+ "grad_norm": 1.9765625,
2367
+ "learning_rate": 8.83624609662078e-06,
2368
+ "loss": 0.3123,
2369
+ "step": 3370
2370
+ },
2371
+ {
2372
+ "epoch": 5.909886264216973,
2373
+ "grad_norm": 2.234375,
2374
+ "learning_rate": 8.786723506248334e-06,
2375
+ "loss": 0.316,
2376
+ "step": 3380
2377
+ },
2378
+ {
2379
+ "epoch": 5.927384076990376,
2380
+ "grad_norm": 2.625,
2381
+ "learning_rate": 8.737272140202105e-06,
2382
+ "loss": 0.3015,
2383
+ "step": 3390
2384
+ },
2385
+ {
2386
+ "epoch": 5.94488188976378,
2387
+ "grad_norm": 2.1875,
2388
+ "learning_rate": 8.687893589851375e-06,
2389
+ "loss": 0.3216,
2390
+ "step": 3400
2391
+ },
2392
+ {
2393
+ "epoch": 5.9623797025371825,
2394
+ "grad_norm": 2.21875,
2395
+ "learning_rate": 8.638589444222191e-06,
2396
+ "loss": 0.3143,
2397
+ "step": 3410
2398
+ },
2399
+ {
2400
+ "epoch": 5.979877515310586,
2401
+ "grad_norm": 2.40625,
2402
+ "learning_rate": 8.5893612899462e-06,
2403
+ "loss": 0.3089,
2404
+ "step": 3420
2405
+ },
2406
+ {
2407
+ "epoch": 5.997375328083989,
2408
+ "grad_norm": 2.171875,
2409
+ "learning_rate": 8.540210711209626e-06,
2410
+ "loss": 0.3137,
2411
+ "step": 3430
2412
+ },
2413
+ {
2414
+ "epoch": 6.013998250218723,
2415
+ "grad_norm": 2.40625,
2416
+ "learning_rate": 8.491139289702262e-06,
2417
+ "loss": 0.2933,
2418
+ "step": 3440
2419
+ },
2420
+ {
2421
+ "epoch": 6.031496062992126,
2422
+ "grad_norm": 2.28125,
2423
+ "learning_rate": 8.442148604566598e-06,
2424
+ "loss": 0.2787,
2425
+ "step": 3450
2426
+ },
2427
+ {
2428
+ "epoch": 6.04899387576553,
2429
+ "grad_norm": 2.46875,
2430
+ "learning_rate": 8.393240232346976e-06,
2431
+ "loss": 0.2763,
2432
+ "step": 3460
2433
+ },
2434
+ {
2435
+ "epoch": 6.066491688538933,
2436
+ "grad_norm": 2.328125,
2437
+ "learning_rate": 8.34441574693887e-06,
2438
+ "loss": 0.2706,
2439
+ "step": 3470
2440
+ },
2441
+ {
2442
+ "epoch": 6.083989501312336,
2443
+ "grad_norm": 2.21875,
2444
+ "learning_rate": 8.295676719538231e-06,
2445
+ "loss": 0.2732,
2446
+ "step": 3480
2447
+ },
2448
+ {
2449
+ "epoch": 6.101487314085739,
2450
+ "grad_norm": 2.25,
2451
+ "learning_rate": 8.247024718590941e-06,
2452
+ "loss": 0.2772,
2453
+ "step": 3490
2454
+ },
2455
+ {
2456
+ "epoch": 6.118985126859142,
2457
+ "grad_norm": 2.484375,
2458
+ "learning_rate": 8.19846130974232e-06,
2459
+ "loss": 0.2791,
2460
+ "step": 3500
2461
+ },
2462
+ {
2463
+ "epoch": 6.136482939632546,
2464
+ "grad_norm": 2.484375,
2465
+ "learning_rate": 8.14998805578675e-06,
2466
+ "loss": 0.2808,
2467
+ "step": 3510
2468
+ },
2469
+ {
2470
+ "epoch": 6.153980752405949,
2471
+ "grad_norm": 2.46875,
2472
+ "learning_rate": 8.101606516617384e-06,
2473
+ "loss": 0.2908,
2474
+ "step": 3520
2475
+ },
2476
+ {
2477
+ "epoch": 6.171478565179353,
2478
+ "grad_norm": 2.359375,
2479
+ "learning_rate": 8.053318249175955e-06,
2480
+ "loss": 0.2809,
2481
+ "step": 3530
2482
+ },
2483
+ {
2484
+ "epoch": 6.188976377952756,
2485
+ "grad_norm": 2.296875,
2486
+ "learning_rate": 8.005124807402657e-06,
2487
+ "loss": 0.2708,
2488
+ "step": 3540
2489
+ },
2490
+ {
2491
+ "epoch": 6.206474190726159,
2492
+ "grad_norm": 2.265625,
2493
+ "learning_rate": 7.957027742186153e-06,
2494
+ "loss": 0.2789,
2495
+ "step": 3550
2496
+ },
2497
+ {
2498
+ "epoch": 6.223972003499562,
2499
+ "grad_norm": 2.234375,
2500
+ "learning_rate": 7.909028601313658e-06,
2501
+ "loss": 0.2752,
2502
+ "step": 3560
2503
+ },
2504
+ {
2505
+ "epoch": 6.241469816272966,
2506
+ "grad_norm": 2.234375,
2507
+ "learning_rate": 7.861128929421133e-06,
2508
+ "loss": 0.2778,
2509
+ "step": 3570
2510
+ },
2511
+ {
2512
+ "epoch": 6.258967629046369,
2513
+ "grad_norm": 2.640625,
2514
+ "learning_rate": 7.813330267943586e-06,
2515
+ "loss": 0.2779,
2516
+ "step": 3580
2517
+ },
2518
+ {
2519
+ "epoch": 6.276465441819773,
2520
+ "grad_norm": 2.015625,
2521
+ "learning_rate": 7.765634155065451e-06,
2522
+ "loss": 0.2696,
2523
+ "step": 3590
2524
+ },
2525
+ {
2526
+ "epoch": 6.293963254593176,
2527
+ "grad_norm": 2.171875,
2528
+ "learning_rate": 7.718042125671102e-06,
2529
+ "loss": 0.2813,
2530
+ "step": 3600
2531
+ },
2532
+ {
2533
+ "epoch": 6.311461067366579,
2534
+ "grad_norm": 2.21875,
2535
+ "learning_rate": 7.670555711295446e-06,
2536
+ "loss": 0.2847,
2537
+ "step": 3610
2538
+ },
2539
+ {
2540
+ "epoch": 6.328958880139982,
2541
+ "grad_norm": 2.515625,
2542
+ "learning_rate": 7.623176440074667e-06,
2543
+ "loss": 0.2761,
2544
+ "step": 3620
2545
+ },
2546
+ {
2547
+ "epoch": 6.346456692913386,
2548
+ "grad_norm": 2.546875,
2549
+ "learning_rate": 7.575905836697008e-06,
2550
+ "loss": 0.2801,
2551
+ "step": 3630
2552
+ },
2553
+ {
2554
+ "epoch": 6.363954505686789,
2555
+ "grad_norm": 2.109375,
2556
+ "learning_rate": 7.528745422353745e-06,
2557
+ "loss": 0.2848,
2558
+ "step": 3640
2559
+ },
2560
+ {
2561
+ "epoch": 6.381452318460193,
2562
+ "grad_norm": 2.75,
2563
+ "learning_rate": 7.481696714690203e-06,
2564
+ "loss": 0.2834,
2565
+ "step": 3650
2566
+ },
2567
+ {
2568
+ "epoch": 6.398950131233596,
2569
+ "grad_norm": 2.140625,
2570
+ "learning_rate": 7.4347612277569345e-06,
2571
+ "loss": 0.2743,
2572
+ "step": 3660
2573
+ },
2574
+ {
2575
+ "epoch": 6.4164479440069995,
2576
+ "grad_norm": 2.015625,
2577
+ "learning_rate": 7.387940471961001e-06,
2578
+ "loss": 0.2794,
2579
+ "step": 3670
2580
+ },
2581
+ {
2582
+ "epoch": 6.433945756780402,
2583
+ "grad_norm": 2.234375,
2584
+ "learning_rate": 7.341235954017351e-06,
2585
+ "loss": 0.277,
2586
+ "step": 3680
2587
+ },
2588
+ {
2589
+ "epoch": 6.451443569553806,
2590
+ "grad_norm": 2.15625,
2591
+ "learning_rate": 7.294649176900344e-06,
2592
+ "loss": 0.2817,
2593
+ "step": 3690
2594
+ },
2595
+ {
2596
+ "epoch": 6.468941382327209,
2597
+ "grad_norm": 2.265625,
2598
+ "learning_rate": 7.248181639795384e-06,
2599
+ "loss": 0.2816,
2600
+ "step": 3700
2601
+ },
2602
+ {
2603
+ "epoch": 6.486439195100612,
2604
+ "grad_norm": 2.328125,
2605
+ "learning_rate": 7.201834838050668e-06,
2606
+ "loss": 0.2765,
2607
+ "step": 3710
2608
+ },
2609
+ {
2610
+ "epoch": 6.503937007874016,
2611
+ "grad_norm": 2.34375,
2612
+ "learning_rate": 7.155610263129082e-06,
2613
+ "loss": 0.2778,
2614
+ "step": 3720
2615
+ },
2616
+ {
2617
+ "epoch": 6.5214348206474195,
2618
+ "grad_norm": 2.328125,
2619
+ "learning_rate": 7.109509402560171e-06,
2620
+ "loss": 0.27,
2621
+ "step": 3730
2622
+ },
2623
+ {
2624
+ "epoch": 6.538932633420822,
2625
+ "grad_norm": 2.359375,
2626
+ "learning_rate": 7.063533739892312e-06,
2627
+ "loss": 0.2713,
2628
+ "step": 3740
2629
+ },
2630
+ {
2631
+ "epoch": 6.556430446194225,
2632
+ "grad_norm": 2.375,
2633
+ "learning_rate": 7.017684754644938e-06,
2634
+ "loss": 0.2801,
2635
+ "step": 3750
2636
+ },
2637
+ {
2638
+ "epoch": 6.573928258967629,
2639
+ "grad_norm": 2.234375,
2640
+ "learning_rate": 6.971963922260954e-06,
2641
+ "loss": 0.2893,
2642
+ "step": 3760
2643
+ },
2644
+ {
2645
+ "epoch": 6.591426071741032,
2646
+ "grad_norm": 2.71875,
2647
+ "learning_rate": 6.926372714059227e-06,
2648
+ "loss": 0.2785,
2649
+ "step": 3770
2650
+ },
2651
+ {
2652
+ "epoch": 6.608923884514436,
2653
+ "grad_norm": 2.28125,
2654
+ "learning_rate": 6.880912597187266e-06,
2655
+ "loss": 0.2762,
2656
+ "step": 3780
2657
+ },
2658
+ {
2659
+ "epoch": 6.626421697287839,
2660
+ "grad_norm": 2.421875,
2661
+ "learning_rate": 6.835585034573993e-06,
2662
+ "loss": 0.2791,
2663
+ "step": 3790
2664
+ },
2665
+ {
2666
+ "epoch": 6.6439195100612425,
2667
+ "grad_norm": 2.796875,
2668
+ "learning_rate": 6.790391484882665e-06,
2669
+ "loss": 0.2795,
2670
+ "step": 3800
2671
+ },
2672
+ {
2673
+ "epoch": 6.661417322834645,
2674
+ "grad_norm": 2.078125,
2675
+ "learning_rate": 6.745333402463944e-06,
2676
+ "loss": 0.2845,
2677
+ "step": 3810
2678
+ },
2679
+ {
2680
+ "epoch": 6.678915135608049,
2681
+ "grad_norm": 2.46875,
2682
+ "learning_rate": 6.700412237309084e-06,
2683
+ "loss": 0.2829,
2684
+ "step": 3820
2685
+ },
2686
+ {
2687
+ "epoch": 6.696412948381452,
2688
+ "grad_norm": 2.421875,
2689
+ "learning_rate": 6.655629435003274e-06,
2690
+ "loss": 0.2814,
2691
+ "step": 3830
2692
+ },
2693
+ {
2694
+ "epoch": 6.713910761154856,
2695
+ "grad_norm": 2.515625,
2696
+ "learning_rate": 6.6109864366791225e-06,
2697
+ "loss": 0.2703,
2698
+ "step": 3840
2699
+ },
2700
+ {
2701
+ "epoch": 6.731408573928259,
2702
+ "grad_norm": 2.1875,
2703
+ "learning_rate": 6.56648467897027e-06,
2704
+ "loss": 0.2856,
2705
+ "step": 3850
2706
+ },
2707
+ {
2708
+ "epoch": 6.7489063867016625,
2709
+ "grad_norm": 2.109375,
2710
+ "learning_rate": 6.522125593965171e-06,
2711
+ "loss": 0.2766,
2712
+ "step": 3860
2713
+ },
2714
+ {
2715
+ "epoch": 6.766404199475065,
2716
+ "grad_norm": 2.546875,
2717
+ "learning_rate": 6.477910609161004e-06,
2718
+ "loss": 0.2792,
2719
+ "step": 3870
2720
+ },
2721
+ {
2722
+ "epoch": 6.783902012248469,
2723
+ "grad_norm": 2.5,
2724
+ "learning_rate": 6.433841147417717e-06,
2725
+ "loss": 0.28,
2726
+ "step": 3880
2727
+ },
2728
+ {
2729
+ "epoch": 6.801399825021872,
2730
+ "grad_norm": 2.125,
2731
+ "learning_rate": 6.389918626912277e-06,
2732
+ "loss": 0.2773,
2733
+ "step": 3890
2734
+ },
2735
+ {
2736
+ "epoch": 6.818897637795276,
2737
+ "grad_norm": 2.3125,
2738
+ "learning_rate": 6.346144461092991e-06,
2739
+ "loss": 0.2761,
2740
+ "step": 3900
2741
+ },
2742
+ {
2743
+ "epoch": 6.836395450568679,
2744
+ "grad_norm": 2.484375,
2745
+ "learning_rate": 6.302520058634057e-06,
2746
+ "loss": 0.2765,
2747
+ "step": 3910
2748
+ },
2749
+ {
2750
+ "epoch": 6.853893263342083,
2751
+ "grad_norm": 2.125,
2752
+ "learning_rate": 6.259046823390184e-06,
2753
+ "loss": 0.2746,
2754
+ "step": 3920
2755
+ },
2756
+ {
2757
+ "epoch": 6.8713910761154855,
2758
+ "grad_norm": 2.140625,
2759
+ "learning_rate": 6.2157261543514825e-06,
2760
+ "loss": 0.2832,
2761
+ "step": 3930
2762
+ },
2763
+ {
2764
+ "epoch": 6.888888888888889,
2765
+ "grad_norm": 2.171875,
2766
+ "learning_rate": 6.172559445598385e-06,
2767
+ "loss": 0.2831,
2768
+ "step": 3940
2769
+ },
2770
+ {
2771
+ "epoch": 6.906386701662292,
2772
+ "grad_norm": 2.09375,
2773
+ "learning_rate": 6.129548086256816e-06,
2774
+ "loss": 0.2821,
2775
+ "step": 3950
2776
+ },
2777
+ {
2778
+ "epoch": 6.923884514435695,
2779
+ "grad_norm": 2.421875,
2780
+ "learning_rate": 6.086693460453466e-06,
2781
+ "loss": 0.2905,
2782
+ "step": 3960
2783
+ },
2784
+ {
2785
+ "epoch": 6.941382327209099,
2786
+ "grad_norm": 2.046875,
2787
+ "learning_rate": 6.0439969472712734e-06,
2788
+ "loss": 0.2772,
2789
+ "step": 3970
2790
+ },
2791
+ {
2792
+ "epoch": 6.958880139982503,
2793
+ "grad_norm": 2.28125,
2794
+ "learning_rate": 6.001459920705046e-06,
2795
+ "loss": 0.2814,
2796
+ "step": 3980
2797
+ },
2798
+ {
2799
+ "epoch": 6.9763779527559056,
2800
+ "grad_norm": 2.59375,
2801
+ "learning_rate": 5.95908374961721e-06,
2802
+ "loss": 0.2674,
2803
+ "step": 3990
2804
+ },
2805
+ {
2806
+ "epoch": 6.9938757655293085,
2807
+ "grad_norm": 2.234375,
2808
+ "learning_rate": 5.916869797693794e-06,
2809
+ "loss": 0.2746,
2810
+ "step": 4000
2811
+ },
2812
+ {
2813
+ "epoch": 7.010498687664042,
2814
+ "grad_norm": 2.4375,
2815
+ "learning_rate": 5.874819423400538e-06,
2816
+ "loss": 0.2766,
2817
+ "step": 4010
2818
+ },
2819
+ {
2820
+ "epoch": 7.027996500437445,
2821
+ "grad_norm": 2.1875,
2822
+ "learning_rate": 5.832933979939177e-06,
2823
+ "loss": 0.257,
2824
+ "step": 4020
2825
+ },
2826
+ {
2827
+ "epoch": 7.045494313210849,
2828
+ "grad_norm": 2.328125,
2829
+ "learning_rate": 5.791214815203874e-06,
2830
+ "loss": 0.2575,
2831
+ "step": 4030
2832
+ },
2833
+ {
2834
+ "epoch": 7.062992125984252,
2835
+ "grad_norm": 2.03125,
2836
+ "learning_rate": 5.749663271737873e-06,
2837
+ "loss": 0.2589,
2838
+ "step": 4040
2839
+ },
2840
+ {
2841
+ "epoch": 7.080489938757656,
2842
+ "grad_norm": 2.046875,
2843
+ "learning_rate": 5.708280686690284e-06,
2844
+ "loss": 0.2585,
2845
+ "step": 4050
2846
+ },
2847
+ {
2848
+ "epoch": 7.0979877515310585,
2849
+ "grad_norm": 2.109375,
2850
+ "learning_rate": 5.667068391773045e-06,
2851
+ "loss": 0.2696,
2852
+ "step": 4060
2853
+ },
2854
+ {
2855
+ "epoch": 7.115485564304462,
2856
+ "grad_norm": 2.703125,
2857
+ "learning_rate": 5.62602771321808e-06,
2858
+ "loss": 0.263,
2859
+ "step": 4070
2860
+ },
2861
+ {
2862
+ "epoch": 7.132983377077865,
2863
+ "grad_norm": 2.453125,
2864
+ "learning_rate": 5.5851599717346106e-06,
2865
+ "loss": 0.2598,
2866
+ "step": 4080
2867
+ },
2868
+ {
2869
+ "epoch": 7.150481189851269,
2870
+ "grad_norm": 2.421875,
2871
+ "learning_rate": 5.5444664824666594e-06,
2872
+ "loss": 0.2683,
2873
+ "step": 4090
2874
+ },
2875
+ {
2876
+ "epoch": 7.167979002624672,
2877
+ "grad_norm": 2.3125,
2878
+ "learning_rate": 5.503948554950727e-06,
2879
+ "loss": 0.2669,
2880
+ "step": 4100
2881
+ },
2882
+ {
2883
+ "epoch": 7.185476815398075,
2884
+ "grad_norm": 2.328125,
2885
+ "learning_rate": 5.4636074930736525e-06,
2886
+ "loss": 0.2546,
2887
+ "step": 4110
2888
+ },
2889
+ {
2890
+ "epoch": 7.202974628171479,
2891
+ "grad_norm": 2.328125,
2892
+ "learning_rate": 5.423444595030648e-06,
2893
+ "loss": 0.262,
2894
+ "step": 4120
2895
+ },
2896
+ {
2897
+ "epoch": 7.2204724409448815,
2898
+ "grad_norm": 2.21875,
2899
+ "learning_rate": 5.383461153283529e-06,
2900
+ "loss": 0.2772,
2901
+ "step": 4130
2902
+ },
2903
+ {
2904
+ "epoch": 7.237970253718285,
2905
+ "grad_norm": 2.203125,
2906
+ "learning_rate": 5.343658454519113e-06,
2907
+ "loss": 0.2584,
2908
+ "step": 4140
2909
+ },
2910
+ {
2911
+ "epoch": 7.255468066491688,
2912
+ "grad_norm": 2.3125,
2913
+ "learning_rate": 5.3040377796078295e-06,
2914
+ "loss": 0.2626,
2915
+ "step": 4150
2916
+ },
2917
+ {
2918
+ "epoch": 7.272965879265092,
2919
+ "grad_norm": 2.09375,
2920
+ "learning_rate": 5.264600403562482e-06,
2921
+ "loss": 0.2643,
2922
+ "step": 4160
2923
+ },
2924
+ {
2925
+ "epoch": 7.290463692038495,
2926
+ "grad_norm": 2.1875,
2927
+ "learning_rate": 5.225347595497234e-06,
2928
+ "loss": 0.2598,
2929
+ "step": 4170
2930
+ },
2931
+ {
2932
+ "epoch": 7.307961504811899,
2933
+ "grad_norm": 2.09375,
2934
+ "learning_rate": 5.186280618586752e-06,
2935
+ "loss": 0.2584,
2936
+ "step": 4180
2937
+ },
2938
+ {
2939
+ "epoch": 7.3254593175853016,
2940
+ "grad_norm": 2.421875,
2941
+ "learning_rate": 5.147400730025567e-06,
2942
+ "loss": 0.2551,
2943
+ "step": 4190
2944
+ },
2945
+ {
2946
+ "epoch": 7.342957130358705,
2947
+ "grad_norm": 2.03125,
2948
+ "learning_rate": 5.108709180987623e-06,
2949
+ "loss": 0.2573,
2950
+ "step": 4200
2951
+ },
2952
+ {
2953
+ "epoch": 7.360454943132108,
2954
+ "grad_norm": 2.09375,
2955
+ "learning_rate": 5.070207216586e-06,
2956
+ "loss": 0.2546,
2957
+ "step": 4210
2958
+ },
2959
+ {
2960
+ "epoch": 7.377952755905512,
2961
+ "grad_norm": 2.203125,
2962
+ "learning_rate": 5.031896075832846e-06,
2963
+ "loss": 0.2503,
2964
+ "step": 4220
2965
+ },
2966
+ {
2967
+ "epoch": 7.395450568678915,
2968
+ "grad_norm": 2.171875,
2969
+ "learning_rate": 4.993776991599511e-06,
2970
+ "loss": 0.2612,
2971
+ "step": 4230
2972
+ },
2973
+ {
2974
+ "epoch": 7.412948381452319,
2975
+ "grad_norm": 2.40625,
2976
+ "learning_rate": 4.955851190576886e-06,
2977
+ "loss": 0.2624,
2978
+ "step": 4240
2979
+ },
2980
+ {
2981
+ "epoch": 7.430446194225722,
2982
+ "grad_norm": 2.328125,
2983
+ "learning_rate": 4.918119893235894e-06,
2984
+ "loss": 0.2627,
2985
+ "step": 4250
2986
+ },
2987
+ {
2988
+ "epoch": 7.447944006999125,
2989
+ "grad_norm": 2.390625,
2990
+ "learning_rate": 4.880584313788245e-06,
2991
+ "loss": 0.2505,
2992
+ "step": 4260
2993
+ },
2994
+ {
2995
+ "epoch": 7.465441819772528,
2996
+ "grad_norm": 2.546875,
2997
+ "learning_rate": 4.843245660147346e-06,
2998
+ "loss": 0.2545,
2999
+ "step": 4270
3000
+ },
3001
+ {
3002
+ "epoch": 7.482939632545932,
3003
+ "grad_norm": 2.3125,
3004
+ "learning_rate": 4.806105133889444e-06,
3005
+ "loss": 0.265,
3006
+ "step": 4280
3007
+ },
3008
+ {
3009
+ "epoch": 7.500437445319335,
3010
+ "grad_norm": 2.046875,
3011
+ "learning_rate": 4.7691639302149365e-06,
3012
+ "loss": 0.2661,
3013
+ "step": 4290
3014
+ },
3015
+ {
3016
+ "epoch": 7.517935258092739,
3017
+ "grad_norm": 2.203125,
3018
+ "learning_rate": 4.732423237909929e-06,
3019
+ "loss": 0.2628,
3020
+ "step": 4300
3021
+ },
3022
+ {
3023
+ "epoch": 7.535433070866142,
3024
+ "grad_norm": 2.140625,
3025
+ "learning_rate": 4.695884239307972e-06,
3026
+ "loss": 0.2691,
3027
+ "step": 4310
3028
+ },
3029
+ {
3030
+ "epoch": 7.5529308836395455,
3031
+ "grad_norm": 2.296875,
3032
+ "learning_rate": 4.659548110252012e-06,
3033
+ "loss": 0.2632,
3034
+ "step": 4320
3035
+ },
3036
+ {
3037
+ "epoch": 7.570428696412948,
3038
+ "grad_norm": 2.71875,
3039
+ "learning_rate": 4.623416020056556e-06,
3040
+ "loss": 0.2625,
3041
+ "step": 4330
3042
+ },
3043
+ {
3044
+ "epoch": 7.587926509186351,
3045
+ "grad_norm": 2.296875,
3046
+ "learning_rate": 4.587489131470039e-06,
3047
+ "loss": 0.2514,
3048
+ "step": 4340
3049
+ },
3050
+ {
3051
+ "epoch": 7.605424321959755,
3052
+ "grad_norm": 2.21875,
3053
+ "learning_rate": 4.551768600637407e-06,
3054
+ "loss": 0.2686,
3055
+ "step": 4350
3056
+ },
3057
+ {
3058
+ "epoch": 7.622922134733159,
3059
+ "grad_norm": 2.515625,
3060
+ "learning_rate": 4.516255577062913e-06,
3061
+ "loss": 0.2701,
3062
+ "step": 4360
3063
+ },
3064
+ {
3065
+ "epoch": 7.640419947506562,
3066
+ "grad_norm": 2.265625,
3067
+ "learning_rate": 4.48095120357312e-06,
3068
+ "loss": 0.2617,
3069
+ "step": 4370
3070
+ },
3071
+ {
3072
+ "epoch": 7.657917760279965,
3073
+ "grad_norm": 2.09375,
3074
+ "learning_rate": 4.445856616280136e-06,
3075
+ "loss": 0.2597,
3076
+ "step": 4380
3077
+ },
3078
+ {
3079
+ "epoch": 7.675415573053368,
3080
+ "grad_norm": 2.140625,
3081
+ "learning_rate": 4.410972944545041e-06,
3082
+ "loss": 0.2695,
3083
+ "step": 4390
3084
+ },
3085
+ {
3086
+ "epoch": 7.692913385826771,
3087
+ "grad_norm": 2.21875,
3088
+ "learning_rate": 4.376301310941552e-06,
3089
+ "loss": 0.2632,
3090
+ "step": 4400
3091
+ },
3092
+ {
3093
+ "epoch": 7.710411198600175,
3094
+ "grad_norm": 2.484375,
3095
+ "learning_rate": 4.3418428312198835e-06,
3096
+ "loss": 0.2629,
3097
+ "step": 4410
3098
+ },
3099
+ {
3100
+ "epoch": 7.727909011373578,
3101
+ "grad_norm": 2.203125,
3102
+ "learning_rate": 4.307598614270871e-06,
3103
+ "loss": 0.2505,
3104
+ "step": 4420
3105
+ },
3106
+ {
3107
+ "epoch": 7.745406824146982,
3108
+ "grad_norm": 2.171875,
3109
+ "learning_rate": 4.273569762090261e-06,
3110
+ "loss": 0.2695,
3111
+ "step": 4430
3112
+ },
3113
+ {
3114
+ "epoch": 7.762904636920385,
3115
+ "grad_norm": 2.296875,
3116
+ "learning_rate": 4.239757369743248e-06,
3117
+ "loss": 0.2636,
3118
+ "step": 4440
3119
+ },
3120
+ {
3121
+ "epoch": 7.7804024496937885,
3122
+ "grad_norm": 2.5,
3123
+ "learning_rate": 4.2061625253292484e-06,
3124
+ "loss": 0.257,
3125
+ "step": 4450
3126
+ },
3127
+ {
3128
+ "epoch": 7.797900262467191,
3129
+ "grad_norm": 2.265625,
3130
+ "learning_rate": 4.172786309946885e-06,
3131
+ "loss": 0.2672,
3132
+ "step": 4460
3133
+ },
3134
+ {
3135
+ "epoch": 7.815398075240595,
3136
+ "grad_norm": 2.40625,
3137
+ "learning_rate": 4.139629797659188e-06,
3138
+ "loss": 0.2641,
3139
+ "step": 4470
3140
+ },
3141
+ {
3142
+ "epoch": 7.832895888013998,
3143
+ "grad_norm": 2.1875,
3144
+ "learning_rate": 4.106694055459023e-06,
3145
+ "loss": 0.2654,
3146
+ "step": 4480
3147
+ },
3148
+ {
3149
+ "epoch": 7.850393700787402,
3150
+ "grad_norm": 2.671875,
3151
+ "learning_rate": 4.073980143234777e-06,
3152
+ "loss": 0.2606,
3153
+ "step": 4490
3154
+ },
3155
+ {
3156
+ "epoch": 7.867891513560805,
3157
+ "grad_norm": 2.421875,
3158
+ "learning_rate": 4.041489113736244e-06,
3159
+ "loss": 0.2669,
3160
+ "step": 4500
3161
+ },
3162
+ {
3163
+ "epoch": 7.8853893263342085,
3164
+ "grad_norm": 2.125,
3165
+ "learning_rate": 4.009222012540725e-06,
3166
+ "loss": 0.274,
3167
+ "step": 4510
3168
+ },
3169
+ {
3170
+ "epoch": 7.902887139107611,
3171
+ "grad_norm": 2.125,
3172
+ "learning_rate": 3.977179878019412e-06,
3173
+ "loss": 0.259,
3174
+ "step": 4520
3175
+ },
3176
+ {
3177
+ "epoch": 7.920384951881015,
3178
+ "grad_norm": 2.53125,
3179
+ "learning_rate": 3.9453637413039536e-06,
3180
+ "loss": 0.2611,
3181
+ "step": 4530
3182
+ },
3183
+ {
3184
+ "epoch": 7.937882764654418,
3185
+ "grad_norm": 2.40625,
3186
+ "learning_rate": 3.913774626253279e-06,
3187
+ "loss": 0.2541,
3188
+ "step": 4540
3189
+ },
3190
+ {
3191
+ "epoch": 7.955380577427822,
3192
+ "grad_norm": 2.171875,
3193
+ "learning_rate": 3.882413549420649e-06,
3194
+ "loss": 0.2657,
3195
+ "step": 4550
3196
+ },
3197
+ {
3198
+ "epoch": 7.972878390201225,
3199
+ "grad_norm": 2.3125,
3200
+ "learning_rate": 3.851281520020941e-06,
3201
+ "loss": 0.2671,
3202
+ "step": 4560
3203
+ },
3204
+ {
3205
+ "epoch": 7.990376202974629,
3206
+ "grad_norm": 1.9921875,
3207
+ "learning_rate": 3.820379539898173e-06,
3208
+ "loss": 0.271,
3209
+ "step": 4570
3210
+ }
3211
+ ],
3212
+ "logging_steps": 10,
3213
+ "max_steps": 5710,
3214
+ "num_input_tokens_seen": 0,
3215
+ "num_train_epochs": 10,
3216
+ "save_steps": 500,
3217
+ "stateful_callbacks": {
3218
+ "TrainerControl": {
3219
+ "args": {
3220
+ "should_epoch_stop": false,
3221
+ "should_evaluate": false,
3222
+ "should_log": false,
3223
+ "should_save": true,
3224
+ "should_training_stop": false
3225
+ },
3226
+ "attributes": {}
3227
+ }
3228
+ },
3229
+ "total_flos": 1.2912807922064032e+19,
3230
+ "train_batch_size": 1,
3231
+ "trial_name": null,
3232
+ "trial_params": null
3233
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:030d0cf12590d3cb65458381e232ceaa011f4b7ee702c9d830a907f272e50382
3
+ size 5688