lemon-mint commited on
Commit
4cddf40
·
verified ·
1 Parent(s): b3d3554

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 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sh2orc/Llama-3.1-Korean-8B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 4096,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 14336,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 32,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 8.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.48.2",
38
+ "use_cache": false,
39
+ "vocab_size": 128256
40
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.48.2"
12
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a60604ad2a580b1732f99c07c04c722dd24821230029d6e99592b9ae584c88c5
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:939067e4e8be97bea321f037e84eb0bd61064585806121e7b78088c319befa69
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:a8af64f20144e0494afec5f7aae8e40643f931d09574e4585afab9e3525f801d
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:a8838ec03d435eebdcf3ea313b1043e10a634ceb2d9c896fd7db97c5fadad579
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
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a51b191b8b014d7784c9e79e96825e88e9fd0eab3a8bd3c849fc2d2bef1fb850
3
+ size 1704
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b66e3cc7c452b707ddac5caf0aa17618afb9bc1a0333600a22c4afb353f3165
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04dc0b956c6d1362bae0f4fc002532b721b80eb179143a973a5bd07553bade46
3
+ size 1000
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|eot_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 sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|eot_id|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
trainer_state.json ADDED
@@ -0,0 +1,3491 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 494,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004048582995951417,
13
+ "grad_norm": 0.0,
14
+ "learning_rate": 8.000000000000001e-06,
15
+ "loss": 1.3317,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.008097165991902834,
20
+ "grad_norm": 0.0,
21
+ "learning_rate": 1.6000000000000003e-05,
22
+ "loss": 1.2978,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.012145748987854251,
27
+ "grad_norm": 0.0,
28
+ "learning_rate": 2.4e-05,
29
+ "loss": 1.3281,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.016194331983805668,
34
+ "grad_norm": 0.0,
35
+ "learning_rate": 3.2000000000000005e-05,
36
+ "loss": 1.3645,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.020242914979757085,
41
+ "grad_norm": 0.0,
42
+ "learning_rate": 4e-05,
43
+ "loss": 1.3528,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.024291497975708502,
48
+ "grad_norm": 0.0,
49
+ "learning_rate": 4.8e-05,
50
+ "loss": 1.3272,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.02834008097165992,
55
+ "grad_norm": 0.0,
56
+ "learning_rate": 5.6000000000000006e-05,
57
+ "loss": 1.3524,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.032388663967611336,
62
+ "grad_norm": 0.0,
63
+ "learning_rate": 6.400000000000001e-05,
64
+ "loss": 1.3348,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.03643724696356275,
69
+ "grad_norm": 0.0,
70
+ "learning_rate": 7.2e-05,
71
+ "loss": 1.3225,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.04048582995951417,
76
+ "grad_norm": 0.0,
77
+ "learning_rate": 8e-05,
78
+ "loss": 1.3443,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.044534412955465584,
83
+ "grad_norm": 0.0,
84
+ "learning_rate": 8.800000000000001e-05,
85
+ "loss": 1.3253,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.048582995951417005,
90
+ "grad_norm": 0.0,
91
+ "learning_rate": 9.6e-05,
92
+ "loss": 1.2742,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.05263157894736842,
97
+ "grad_norm": 0.0,
98
+ "learning_rate": 0.00010400000000000001,
99
+ "loss": 1.3075,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.05668016194331984,
104
+ "grad_norm": 0.0,
105
+ "learning_rate": 0.00011200000000000001,
106
+ "loss": 1.3006,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.06072874493927125,
111
+ "grad_norm": 0.0,
112
+ "learning_rate": 0.00012,
113
+ "loss": 1.3028,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.06477732793522267,
118
+ "grad_norm": 0.0,
119
+ "learning_rate": 0.00012800000000000002,
120
+ "loss": 1.2884,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.06882591093117409,
125
+ "grad_norm": 0.0,
126
+ "learning_rate": 0.00013600000000000003,
127
+ "loss": 1.3053,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.0728744939271255,
132
+ "grad_norm": 0.0,
133
+ "learning_rate": 0.000144,
134
+ "loss": 1.269,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.07692307692307693,
139
+ "grad_norm": 0.0,
140
+ "learning_rate": 0.000152,
141
+ "loss": 1.2712,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.08097165991902834,
146
+ "grad_norm": 0.0,
147
+ "learning_rate": 0.00016,
148
+ "loss": 1.2883,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.08502024291497975,
153
+ "grad_norm": 0.0,
154
+ "learning_rate": 0.000168,
155
+ "loss": 1.2264,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.08906882591093117,
160
+ "grad_norm": 0.0,
161
+ "learning_rate": 0.00017600000000000002,
162
+ "loss": 1.2394,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.0931174089068826,
167
+ "grad_norm": 0.0,
168
+ "learning_rate": 0.00018400000000000003,
169
+ "loss": 1.2205,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.09716599190283401,
174
+ "grad_norm": 0.0,
175
+ "learning_rate": 0.000192,
176
+ "loss": 1.2784,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.10121457489878542,
181
+ "grad_norm": 0.0,
182
+ "learning_rate": 0.0002,
183
+ "loss": 1.2484,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.10526315789473684,
188
+ "grad_norm": 0.0,
189
+ "learning_rate": 0.00019999775651876987,
190
+ "loss": 1.2147,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.10931174089068826,
195
+ "grad_norm": 0.0,
196
+ "learning_rate": 0.00019999102617574365,
197
+ "loss": 1.2408,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.11336032388663968,
202
+ "grad_norm": 0.0,
203
+ "learning_rate": 0.00019997980927290927,
204
+ "loss": 1.2207,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.11740890688259109,
209
+ "grad_norm": 0.0,
210
+ "learning_rate": 0.00019996410631356498,
211
+ "loss": 1.2061,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.1214574898785425,
216
+ "grad_norm": 0.0,
217
+ "learning_rate": 0.00019994391800229666,
218
+ "loss": 1.2239,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.12550607287449392,
223
+ "grad_norm": 0.0,
224
+ "learning_rate": 0.00019991924524494627,
225
+ "loss": 1.196,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.12955465587044535,
230
+ "grad_norm": 0.0,
231
+ "learning_rate": 0.00019989008914857116,
232
+ "loss": 1.2056,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.13360323886639677,
237
+ "grad_norm": 0.0,
238
+ "learning_rate": 0.0001998564510213944,
239
+ "loss": 1.1465,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.13765182186234817,
244
+ "grad_norm": 0.0,
245
+ "learning_rate": 0.00019981833237274618,
246
+ "loss": 1.1907,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.1417004048582996,
251
+ "grad_norm": 0.0,
252
+ "learning_rate": 0.00019977573491299598,
253
+ "loss": 1.1834,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.145748987854251,
258
+ "grad_norm": 0.0,
259
+ "learning_rate": 0.00019972866055347572,
260
+ "loss": 1.1527,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.14979757085020243,
265
+ "grad_norm": 0.0,
266
+ "learning_rate": 0.0001996771114063943,
267
+ "loss": 1.1677,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.15384615384615385,
272
+ "grad_norm": 0.0,
273
+ "learning_rate": 0.00019962108978474263,
274
+ "loss": 1.1825,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.15789473684210525,
279
+ "grad_norm": 0.0,
280
+ "learning_rate": 0.00019956059820218982,
281
+ "loss": 1.1529,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.16194331983805668,
286
+ "grad_norm": 0.0,
287
+ "learning_rate": 0.00019949563937297045,
288
+ "loss": 1.1664,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.1659919028340081,
293
+ "grad_norm": 0.0,
294
+ "learning_rate": 0.00019942621621176282,
295
+ "loss": 1.1635,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.1700404858299595,
300
+ "grad_norm": 0.0,
301
+ "learning_rate": 0.0001993523318335581,
302
+ "loss": 1.1193,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.17408906882591094,
307
+ "grad_norm": 0.0,
308
+ "learning_rate": 0.00019927398955352061,
309
+ "loss": 1.167,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.17813765182186234,
314
+ "grad_norm": 0.0,
315
+ "learning_rate": 0.00019919119288683908,
316
+ "loss": 1.1568,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.18218623481781376,
321
+ "grad_norm": 0.0,
322
+ "learning_rate": 0.00019910394554856876,
323
+ "loss": 1.1376,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.1862348178137652,
328
+ "grad_norm": 0.0,
329
+ "learning_rate": 0.0001990122514534651,
330
+ "loss": 1.1422,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.1902834008097166,
335
+ "grad_norm": 0.0,
336
+ "learning_rate": 0.00019891611471580764,
337
+ "loss": 1.1757,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.19433198380566802,
342
+ "grad_norm": 0.0,
343
+ "learning_rate": 0.00019881553964921572,
344
+ "loss": 1.1157,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.19838056680161945,
349
+ "grad_norm": 0.0,
350
+ "learning_rate": 0.00019871053076645488,
351
+ "loss": 1.1522,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.20242914979757085,
356
+ "grad_norm": 0.0,
357
+ "learning_rate": 0.00019860109277923418,
358
+ "loss": 1.1093,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.20647773279352227,
363
+ "grad_norm": 0.0,
364
+ "learning_rate": 0.00019848723059799506,
365
+ "loss": 1.1341,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.21052631578947367,
370
+ "grad_norm": 0.0,
371
+ "learning_rate": 0.00019836894933169088,
372
+ "loss": 1.1087,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.2145748987854251,
377
+ "grad_norm": 0.0,
378
+ "learning_rate": 0.0001982462542875576,
379
+ "loss": 1.1469,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.21862348178137653,
384
+ "grad_norm": 0.0,
385
+ "learning_rate": 0.00019811915097087587,
386
+ "loss": 1.1397,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.22267206477732793,
391
+ "grad_norm": 0.0,
392
+ "learning_rate": 0.00019798764508472373,
393
+ "loss": 1.0972,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.22672064777327935,
398
+ "grad_norm": 0.0,
399
+ "learning_rate": 0.00019785174252972092,
400
+ "loss": 1.0941,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.23076923076923078,
405
+ "grad_norm": 0.0,
406
+ "learning_rate": 0.0001977114494037641,
407
+ "loss": 1.1109,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.23481781376518218,
412
+ "grad_norm": 0.0,
413
+ "learning_rate": 0.00019756677200175315,
414
+ "loss": 1.0792,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.2388663967611336,
419
+ "grad_norm": 0.0,
420
+ "learning_rate": 0.0001974177168153088,
421
+ "loss": 1.1418,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.242914979757085,
426
+ "grad_norm": 0.0,
427
+ "learning_rate": 0.0001972642905324813,
428
+ "loss": 1.1654,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.24696356275303644,
433
+ "grad_norm": 0.0,
434
+ "learning_rate": 0.0001971065000374504,
435
+ "loss": 1.1004,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.25101214574898784,
440
+ "grad_norm": 0.0,
441
+ "learning_rate": 0.0001969443524102163,
442
+ "loss": 1.074,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.2550607287449393,
447
+ "grad_norm": 0.0,
448
+ "learning_rate": 0.0001967778549262822,
449
+ "loss": 1.1251,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.2591093117408907,
454
+ "grad_norm": 0.0,
455
+ "learning_rate": 0.00019660701505632772,
456
+ "loss": 1.0892,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.2631578947368421,
461
+ "grad_norm": 0.0,
462
+ "learning_rate": 0.0001964318404658737,
463
+ "loss": 1.1376,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.26720647773279355,
468
+ "grad_norm": 0.0,
469
+ "learning_rate": 0.00019625233901493822,
470
+ "loss": 1.0612,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.27125506072874495,
475
+ "grad_norm": 0.0,
476
+ "learning_rate": 0.000196068518757684,
477
+ "loss": 1.1087,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.27530364372469635,
482
+ "grad_norm": 0.0,
483
+ "learning_rate": 0.00019588038794205703,
484
+ "loss": 1.115,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.2793522267206478,
489
+ "grad_norm": 0.0,
490
+ "learning_rate": 0.00019568795500941635,
491
+ "loss": 1.101,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.2834008097165992,
496
+ "grad_norm": 0.0,
497
+ "learning_rate": 0.00019549122859415538,
498
+ "loss": 1.0784,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.2874493927125506,
503
+ "grad_norm": 0.0,
504
+ "learning_rate": 0.00019529021752331453,
505
+ "loss": 1.1057,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.291497975708502,
510
+ "grad_norm": 0.0,
511
+ "learning_rate": 0.00019508493081618513,
512
+ "loss": 1.0948,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.29554655870445345,
517
+ "grad_norm": 0.0,
518
+ "learning_rate": 0.00019487537768390464,
519
+ "loss": 1.1183,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.29959514170040485,
524
+ "grad_norm": 0.0,
525
+ "learning_rate": 0.00019466156752904343,
526
+ "loss": 1.1001,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.30364372469635625,
531
+ "grad_norm": 0.0,
532
+ "learning_rate": 0.0001944435099451829,
533
+ "loss": 1.0723,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.3076923076923077,
538
+ "grad_norm": 0.0,
539
+ "learning_rate": 0.00019422121471648497,
540
+ "loss": 1.0729,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.3117408906882591,
545
+ "grad_norm": 0.0,
546
+ "learning_rate": 0.0001939946918172531,
547
+ "loss": 1.0615,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.3157894736842105,
552
+ "grad_norm": 0.0,
553
+ "learning_rate": 0.00019376395141148476,
554
+ "loss": 1.0635,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.31983805668016196,
559
+ "grad_norm": 0.0,
560
+ "learning_rate": 0.00019352900385241536,
561
+ "loss": 1.0984,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.32388663967611336,
566
+ "grad_norm": 0.0,
567
+ "learning_rate": 0.0001932898596820536,
568
+ "loss": 1.084,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.32793522267206476,
573
+ "grad_norm": 0.0,
574
+ "learning_rate": 0.0001930465296307087,
575
+ "loss": 1.0703,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.3319838056680162,
580
+ "grad_norm": 0.0,
581
+ "learning_rate": 0.00019279902461650866,
582
+ "loss": 1.0835,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.3360323886639676,
587
+ "grad_norm": 0.0,
588
+ "learning_rate": 0.00019254735574491058,
589
+ "loss": 1.0518,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.340080971659919,
594
+ "grad_norm": 0.0,
595
+ "learning_rate": 0.00019229153430820232,
596
+ "loss": 1.0814,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.3441295546558704,
601
+ "grad_norm": 0.0,
602
+ "learning_rate": 0.0001920315717849956,
603
+ "loss": 1.0525,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.3481781376518219,
608
+ "grad_norm": 0.0,
609
+ "learning_rate": 0.0001917674798397113,
610
+ "loss": 1.0678,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.3522267206477733,
615
+ "grad_norm": 0.0,
616
+ "learning_rate": 0.00019149927032205587,
617
+ "loss": 1.0756,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.3562753036437247,
622
+ "grad_norm": 0.0,
623
+ "learning_rate": 0.00019122695526648968,
624
+ "loss": 1.0319,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.3603238866396761,
629
+ "grad_norm": 0.0,
630
+ "learning_rate": 0.00019095054689168705,
631
+ "loss": 1.0666,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.3643724696356275,
636
+ "grad_norm": 0.0,
637
+ "learning_rate": 0.00019067005759998797,
638
+ "loss": 1.0309,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.3684210526315789,
643
+ "grad_norm": 0.0,
644
+ "learning_rate": 0.0001903854999768417,
645
+ "loss": 1.0896,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.3724696356275304,
650
+ "grad_norm": 0.0,
651
+ "learning_rate": 0.0001900968867902419,
652
+ "loss": 1.0868,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.3765182186234818,
657
+ "grad_norm": 0.0,
658
+ "learning_rate": 0.00018980423099015402,
659
+ "loss": 1.07,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.3805668016194332,
664
+ "grad_norm": 0.0,
665
+ "learning_rate": 0.00018950754570793384,
666
+ "loss": 1.0437,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.38461538461538464,
671
+ "grad_norm": 0.0,
672
+ "learning_rate": 0.00018920684425573865,
673
+ "loss": 1.0558,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.38866396761133604,
678
+ "grad_norm": 0.0,
679
+ "learning_rate": 0.00018890214012592975,
680
+ "loss": 1.0847,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.39271255060728744,
685
+ "grad_norm": 0.0,
686
+ "learning_rate": 0.000188593446990467,
687
+ "loss": 1.0651,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.3967611336032389,
692
+ "grad_norm": 0.0,
693
+ "learning_rate": 0.00018828077870029552,
694
+ "loss": 1.0605,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.4008097165991903,
699
+ "grad_norm": 0.0,
700
+ "learning_rate": 0.00018796414928472417,
701
+ "loss": 1.0717,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.4048582995951417,
706
+ "grad_norm": 0.0,
707
+ "learning_rate": 0.0001876435729507959,
708
+ "loss": 1.0472,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.4089068825910931,
713
+ "grad_norm": 0.0,
714
+ "learning_rate": 0.0001873190640826505,
715
+ "loss": 1.0702,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.41295546558704455,
720
+ "grad_norm": 0.0,
721
+ "learning_rate": 0.00018699063724087904,
722
+ "loss": 1.024,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.41700404858299595,
727
+ "grad_norm": 0.0,
728
+ "learning_rate": 0.00018665830716187065,
729
+ "loss": 1.0162,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.42105263157894735,
734
+ "grad_norm": 0.0,
735
+ "learning_rate": 0.0001863220887571512,
736
+ "loss": 1.0504,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.4251012145748988,
741
+ "grad_norm": 0.0,
742
+ "learning_rate": 0.0001859819971127143,
743
+ "loss": 1.0588,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.4291497975708502,
748
+ "grad_norm": 0.0,
749
+ "learning_rate": 0.00018563804748834438,
750
+ "loss": 1.0377,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.4331983805668016,
755
+ "grad_norm": 0.0,
756
+ "learning_rate": 0.000185290255316932,
757
+ "loss": 1.0385,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.43724696356275305,
762
+ "grad_norm": 0.0,
763
+ "learning_rate": 0.00018493863620378122,
764
+ "loss": 1.0031,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.44129554655870445,
769
+ "grad_norm": 0.0,
770
+ "learning_rate": 0.00018458320592590975,
771
+ "loss": 1.0374,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.44534412955465585,
776
+ "grad_norm": 0.0,
777
+ "learning_rate": 0.00018422398043134067,
778
+ "loss": 1.0001,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.4493927125506073,
783
+ "grad_norm": 0.0,
784
+ "learning_rate": 0.00018386097583838714,
785
+ "loss": 1.0206,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.4534412955465587,
790
+ "grad_norm": 0.0,
791
+ "learning_rate": 0.00018349420843492888,
792
+ "loss": 1.0297,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.4574898785425101,
797
+ "grad_norm": 0.0,
798
+ "learning_rate": 0.00018312369467768166,
799
+ "loss": 1.0314,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.46153846153846156,
804
+ "grad_norm": 0.0,
805
+ "learning_rate": 0.0001827494511914587,
806
+ "loss": 1.0102,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.46558704453441296,
811
+ "grad_norm": 0.0,
812
+ "learning_rate": 0.0001823714947684247,
813
+ "loss": 1.0385,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.46963562753036436,
818
+ "grad_norm": 0.0,
819
+ "learning_rate": 0.00018198984236734246,
820
+ "loss": 1.0349,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.47368421052631576,
825
+ "grad_norm": 0.0,
826
+ "learning_rate": 0.000181604511112812,
827
+ "loss": 1.0241,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.4777327935222672,
832
+ "grad_norm": 0.0,
833
+ "learning_rate": 0.000181215518294502,
834
+ "loss": 1.0459,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.4817813765182186,
839
+ "grad_norm": 0.0,
840
+ "learning_rate": 0.00018082288136637422,
841
+ "loss": 1.0141,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.48582995951417,
846
+ "grad_norm": 0.0,
847
+ "learning_rate": 0.00018042661794590023,
848
+ "loss": 1.0061,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.4898785425101215,
853
+ "grad_norm": 0.0,
854
+ "learning_rate": 0.00018002674581327094,
855
+ "loss": 0.9931,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.4939271255060729,
860
+ "grad_norm": 0.0,
861
+ "learning_rate": 0.00017962328291059888,
862
+ "loss": 1.0376,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.4979757085020243,
867
+ "grad_norm": 0.0,
868
+ "learning_rate": 0.00017921624734111292,
869
+ "loss": 1.0218,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.5020242914979757,
874
+ "grad_norm": 0.0,
875
+ "learning_rate": 0.0001788056573683464,
876
+ "loss": 1.0364,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.5060728744939271,
881
+ "grad_norm": 0.0,
882
+ "learning_rate": 0.00017839153141531718,
883
+ "loss": 1.0096,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.5101214574898786,
888
+ "grad_norm": 0.0,
889
+ "learning_rate": 0.00017797388806370132,
890
+ "loss": 1.0217,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.5141700404858299,
895
+ "grad_norm": 0.0,
896
+ "learning_rate": 0.00017755274605299923,
897
+ "loss": 0.9984,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.5182186234817814,
902
+ "grad_norm": 0.0,
903
+ "learning_rate": 0.00017712812427969485,
904
+ "loss": 1.0305,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.5222672064777328,
909
+ "grad_norm": 0.0,
910
+ "learning_rate": 0.00017670004179640774,
911
+ "loss": 1.0196,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.5263157894736842,
916
+ "grad_norm": 0.0,
917
+ "learning_rate": 0.0001762685178110382,
918
+ "loss": 0.976,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.5303643724696356,
923
+ "grad_norm": 0.0,
924
+ "learning_rate": 0.0001758335716859055,
925
+ "loss": 1.0015,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.5344129554655871,
930
+ "grad_norm": 0.0,
931
+ "learning_rate": 0.00017539522293687898,
932
+ "loss": 1.0391,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.5384615384615384,
937
+ "grad_norm": 0.0,
938
+ "learning_rate": 0.00017495349123250242,
939
+ "loss": 1.0243,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.5425101214574899,
944
+ "grad_norm": 0.0,
945
+ "learning_rate": 0.00017450839639311162,
946
+ "loss": 1.0226,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.5465587044534413,
951
+ "grad_norm": 0.0,
952
+ "learning_rate": 0.00017405995838994494,
953
+ "loss": 1.0355,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.5506072874493927,
958
+ "grad_norm": 0.0,
959
+ "learning_rate": 0.00017360819734424715,
960
+ "loss": 1.0354,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.5546558704453441,
965
+ "grad_norm": 0.0,
966
+ "learning_rate": 0.0001731531335263669,
967
+ "loss": 1.0206,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.5587044534412956,
972
+ "grad_norm": 0.0,
973
+ "learning_rate": 0.00017269478735484683,
974
+ "loss": 1.023,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.562753036437247,
979
+ "grad_norm": 0.0,
980
+ "learning_rate": 0.00017223317939550753,
981
+ "loss": 0.9907,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.5668016194331984,
986
+ "grad_norm": 0.0,
987
+ "learning_rate": 0.00017176833036052495,
988
+ "loss": 1.0207,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.5708502024291497,
993
+ "grad_norm": 0.0,
994
+ "learning_rate": 0.0001713002611075007,
995
+ "loss": 0.9978,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.5748987854251012,
1000
+ "grad_norm": 0.0,
1001
+ "learning_rate": 0.0001708289926385265,
1002
+ "loss": 1.0292,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.5789473684210527,
1007
+ "grad_norm": 0.0,
1008
+ "learning_rate": 0.0001703545460992416,
1009
+ "loss": 1.0062,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.582995951417004,
1014
+ "grad_norm": 0.0,
1015
+ "learning_rate": 0.00016987694277788417,
1016
+ "loss": 1.0625,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.5870445344129555,
1021
+ "grad_norm": 0.0,
1022
+ "learning_rate": 0.0001693962041043359,
1023
+ "loss": 1.0001,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.5910931174089069,
1028
+ "grad_norm": 0.0,
1029
+ "learning_rate": 0.00016891235164916065,
1030
+ "loss": 1.0056,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.5951417004048583,
1035
+ "grad_norm": 0.0,
1036
+ "learning_rate": 0.00016842540712263637,
1037
+ "loss": 1.0331,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.5991902834008097,
1042
+ "grad_norm": 0.0,
1043
+ "learning_rate": 0.00016793539237378128,
1044
+ "loss": 0.984,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.6032388663967612,
1049
+ "grad_norm": 0.0,
1050
+ "learning_rate": 0.00016744232938937308,
1051
+ "loss": 1.0204,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.6072874493927125,
1056
+ "grad_norm": 0.0,
1057
+ "learning_rate": 0.0001669462402929629,
1058
+ "loss": 1.0269,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.611336032388664,
1063
+ "grad_norm": 0.0,
1064
+ "learning_rate": 0.00016644714734388217,
1065
+ "loss": 1.0477,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.6153846153846154,
1070
+ "grad_norm": 0.0,
1071
+ "learning_rate": 0.00016594507293624425,
1072
+ "loss": 1.0223,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.6194331983805668,
1077
+ "grad_norm": 0.0,
1078
+ "learning_rate": 0.00016544003959793925,
1079
+ "loss": 1.0217,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.6234817813765182,
1084
+ "grad_norm": 0.0,
1085
+ "learning_rate": 0.00016493206998962354,
1086
+ "loss": 1.0026,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.6275303643724697,
1091
+ "grad_norm": 0.0,
1092
+ "learning_rate": 0.0001644211869037027,
1093
+ "loss": 0.9742,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.631578947368421,
1098
+ "grad_norm": 0.0,
1099
+ "learning_rate": 0.00016390741326330907,
1100
+ "loss": 0.9803,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.6356275303643725,
1105
+ "grad_norm": 0.0,
1106
+ "learning_rate": 0.00016339077212127294,
1107
+ "loss": 1.0126,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.6396761133603239,
1112
+ "grad_norm": 0.0,
1113
+ "learning_rate": 0.0001628712866590885,
1114
+ "loss": 1.0253,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.6437246963562753,
1119
+ "grad_norm": 0.0,
1120
+ "learning_rate": 0.00016234898018587337,
1121
+ "loss": 1.0047,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.6477732793522267,
1126
+ "grad_norm": 0.0,
1127
+ "learning_rate": 0.00016182387613732291,
1128
+ "loss": 0.9986,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.6518218623481782,
1133
+ "grad_norm": 0.0,
1134
+ "learning_rate": 0.00016129599807465875,
1135
+ "loss": 1.0011,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.6558704453441295,
1140
+ "grad_norm": 0.0,
1141
+ "learning_rate": 0.0001607653696835713,
1142
+ "loss": 0.9783,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.659919028340081,
1147
+ "grad_norm": 0.0,
1148
+ "learning_rate": 0.00016023201477315731,
1149
+ "loss": 1.0145,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.6639676113360324,
1154
+ "grad_norm": 0.0,
1155
+ "learning_rate": 0.0001596959572748514,
1156
+ "loss": 1.0195,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.6680161943319838,
1161
+ "grad_norm": 0.0,
1162
+ "learning_rate": 0.00015915722124135227,
1163
+ "loss": 1.0198,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.6720647773279352,
1168
+ "grad_norm": 0.0,
1169
+ "learning_rate": 0.00015861583084554349,
1170
+ "loss": 0.9749,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.6761133603238867,
1175
+ "grad_norm": 0.0,
1176
+ "learning_rate": 0.0001580718103794089,
1177
+ "loss": 0.9962,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.680161943319838,
1182
+ "grad_norm": 0.0,
1183
+ "learning_rate": 0.00015752518425294257,
1184
+ "loss": 1.0021,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.6842105263157895,
1189
+ "grad_norm": 0.0,
1190
+ "learning_rate": 0.00015697597699305366,
1191
+ "loss": 0.982,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.6882591093117408,
1196
+ "grad_norm": 0.0,
1197
+ "learning_rate": 0.00015642421324246568,
1198
+ "loss": 0.9877,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.6923076923076923,
1203
+ "grad_norm": 0.0,
1204
+ "learning_rate": 0.00015586991775861102,
1205
+ "loss": 0.9625,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.6963562753036437,
1210
+ "grad_norm": 0.0,
1211
+ "learning_rate": 0.00015531311541251995,
1212
+ "loss": 1.0116,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.7004048582995951,
1217
+ "grad_norm": 0.0,
1218
+ "learning_rate": 0.00015475383118770472,
1219
+ "loss": 0.9607,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.7044534412955465,
1224
+ "grad_norm": 0.0,
1225
+ "learning_rate": 0.00015419209017903852,
1226
+ "loss": 0.9899,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.708502024291498,
1231
+ "grad_norm": 0.0,
1232
+ "learning_rate": 0.0001536279175916296,
1233
+ "loss": 1.0611,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.7125506072874493,
1238
+ "grad_norm": 0.0,
1239
+ "learning_rate": 0.0001530613387396901,
1240
+ "loss": 0.9796,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.7165991902834008,
1245
+ "grad_norm": 0.0,
1246
+ "learning_rate": 0.0001524923790454004,
1247
+ "loss": 1.0002,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.7206477732793523,
1252
+ "grad_norm": 0.0,
1253
+ "learning_rate": 0.00015192106403776848,
1254
+ "loss": 0.9898,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.7246963562753036,
1259
+ "grad_norm": 0.0,
1260
+ "learning_rate": 0.0001513474193514842,
1261
+ "loss": 1.0209,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.728744939271255,
1266
+ "grad_norm": 0.0,
1267
+ "learning_rate": 0.00015077147072576933,
1268
+ "loss": 1.0319,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.7327935222672065,
1273
+ "grad_norm": 0.0,
1274
+ "learning_rate": 0.00015019324400322243,
1275
+ "loss": 0.9751,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.7368421052631579,
1280
+ "grad_norm": 0.0,
1281
+ "learning_rate": 0.00014961276512865954,
1282
+ "loss": 0.9693,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.7408906882591093,
1287
+ "grad_norm": 0.0,
1288
+ "learning_rate": 0.00014903006014794983,
1289
+ "loss": 0.9838,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.7449392712550608,
1294
+ "grad_norm": 0.0,
1295
+ "learning_rate": 0.00014844515520684703,
1296
+ "loss": 1.0159,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.7489878542510121,
1301
+ "grad_norm": 0.0,
1302
+ "learning_rate": 0.00014785807654981627,
1303
+ "loss": 1.0361,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.7530364372469636,
1308
+ "grad_norm": 0.0,
1309
+ "learning_rate": 0.00014726885051885653,
1310
+ "loss": 0.9602,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.757085020242915,
1315
+ "grad_norm": 0.0,
1316
+ "learning_rate": 0.0001466775035523186,
1317
+ "loss": 0.968,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.7611336032388664,
1322
+ "grad_norm": 0.0,
1323
+ "learning_rate": 0.00014608406218371894,
1324
+ "loss": 1.0053,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.7651821862348178,
1329
+ "grad_norm": 0.0,
1330
+ "learning_rate": 0.00014548855304054886,
1331
+ "loss": 1.025,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.7692307692307693,
1336
+ "grad_norm": 0.0,
1337
+ "learning_rate": 0.00014489100284308017,
1338
+ "loss": 0.9322,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.7732793522267206,
1343
+ "grad_norm": 0.0,
1344
+ "learning_rate": 0.00014429143840316585,
1345
+ "loss": 1.0204,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.7773279352226721,
1350
+ "grad_norm": 0.0,
1351
+ "learning_rate": 0.00014368988662303732,
1352
+ "loss": 0.9984,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.7813765182186235,
1357
+ "grad_norm": 0.0,
1358
+ "learning_rate": 0.00014308637449409706,
1359
+ "loss": 1.0237,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.7854251012145749,
1364
+ "grad_norm": 0.0,
1365
+ "learning_rate": 0.00014248092909570774,
1366
+ "loss": 0.9797,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.7894736842105263,
1371
+ "grad_norm": 0.0,
1372
+ "learning_rate": 0.00014187357759397714,
1373
+ "loss": 0.9901,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.7935222672064778,
1378
+ "grad_norm": 0.0,
1379
+ "learning_rate": 0.00014126434724053913,
1380
+ "loss": 0.9659,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.7975708502024291,
1385
+ "grad_norm": 0.0,
1386
+ "learning_rate": 0.00014065326537133094,
1387
+ "loss": 0.9847,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.8016194331983806,
1392
+ "grad_norm": 0.0,
1393
+ "learning_rate": 0.0001400403594053667,
1394
+ "loss": 0.9878,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.805668016194332,
1399
+ "grad_norm": 0.0,
1400
+ "learning_rate": 0.00013942565684350698,
1401
+ "loss": 0.9626,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.8097165991902834,
1406
+ "grad_norm": 0.0,
1407
+ "learning_rate": 0.00013880918526722497,
1408
+ "loss": 0.9457,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.8137651821862348,
1413
+ "grad_norm": 0.0,
1414
+ "learning_rate": 0.00013819097233736888,
1415
+ "loss": 0.959,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.8178137651821862,
1420
+ "grad_norm": 0.0,
1421
+ "learning_rate": 0.00013757104579292082,
1422
+ "loss": 0.9702,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.8218623481781376,
1427
+ "grad_norm": 0.0,
1428
+ "learning_rate": 0.00013694943344975212,
1429
+ "loss": 0.9824,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.8259109311740891,
1434
+ "grad_norm": 0.0,
1435
+ "learning_rate": 0.00013632616319937522,
1436
+ "loss": 0.9589,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.8299595141700404,
1441
+ "grad_norm": 0.0,
1442
+ "learning_rate": 0.00013570126300769232,
1443
+ "loss": 0.9761,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.8340080971659919,
1448
+ "grad_norm": 0.0,
1449
+ "learning_rate": 0.0001350747609137404,
1450
+ "loss": 1.0033,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.8380566801619433,
1455
+ "grad_norm": 0.0,
1456
+ "learning_rate": 0.0001344466850284333,
1457
+ "loss": 1.0055,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.8421052631578947,
1462
+ "grad_norm": 0.0,
1463
+ "learning_rate": 0.00013381706353330014,
1464
+ "loss": 0.972,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.8461538461538461,
1469
+ "grad_norm": 0.0,
1470
+ "learning_rate": 0.0001331859246792211,
1471
+ "loss": 1.0063,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.8502024291497976,
1476
+ "grad_norm": 0.0,
1477
+ "learning_rate": 0.0001325532967851596,
1478
+ "loss": 0.9878,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.854251012145749,
1483
+ "grad_norm": 0.0,
1484
+ "learning_rate": 0.00013191920823689177,
1485
+ "loss": 0.9881,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.8582995951417004,
1490
+ "grad_norm": 0.0,
1491
+ "learning_rate": 0.00013128368748573273,
1492
+ "loss": 0.9608,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.8623481781376519,
1497
+ "grad_norm": 0.0,
1498
+ "learning_rate": 0.00013064676304726,
1499
+ "loss": 0.953,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.8663967611336032,
1504
+ "grad_norm": 0.0,
1505
+ "learning_rate": 0.0001300084635000341,
1506
+ "loss": 0.9904,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.8704453441295547,
1511
+ "grad_norm": 0.0,
1512
+ "learning_rate": 0.000129368817484316,
1513
+ "loss": 0.9877,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.8744939271255061,
1518
+ "grad_norm": 0.0,
1519
+ "learning_rate": 0.0001287278537007824,
1520
+ "loss": 0.9723,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.8785425101214575,
1525
+ "grad_norm": 0.0,
1526
+ "learning_rate": 0.00012808560090923758,
1527
+ "loss": 0.9724,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.8825910931174089,
1532
+ "grad_norm": 0.0,
1533
+ "learning_rate": 0.00012744208792732324,
1534
+ "loss": 0.9404,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.8866396761133604,
1539
+ "grad_norm": 0.0,
1540
+ "learning_rate": 0.00012679734362922528,
1541
+ "loss": 0.9661,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.8906882591093117,
1546
+ "grad_norm": 0.0,
1547
+ "learning_rate": 0.00012615139694437835,
1548
+ "loss": 1.0048,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.8947368421052632,
1553
+ "grad_norm": 0.0,
1554
+ "learning_rate": 0.00012550427685616765,
1555
+ "loss": 0.997,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.8987854251012146,
1560
+ "grad_norm": 0.0,
1561
+ "learning_rate": 0.00012485601240062869,
1562
+ "loss": 1.0128,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.902834008097166,
1567
+ "grad_norm": 0.0,
1568
+ "learning_rate": 0.00012420663266514417,
1569
+ "loss": 0.9684,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.9068825910931174,
1574
+ "grad_norm": 0.0,
1575
+ "learning_rate": 0.0001235561667871391,
1576
+ "loss": 0.9546,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.9109311740890689,
1581
+ "grad_norm": 0.0,
1582
+ "learning_rate": 0.0001229046439527732,
1583
+ "loss": 0.9762,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.9149797570850202,
1588
+ "grad_norm": 0.0,
1589
+ "learning_rate": 0.00012225209339563145,
1590
+ "loss": 0.966,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.9190283400809717,
1595
+ "grad_norm": 0.0,
1596
+ "learning_rate": 0.00012159854439541245,
1597
+ "loss": 0.9559,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.9230769230769231,
1602
+ "grad_norm": 0.0,
1603
+ "learning_rate": 0.00012094402627661447,
1604
+ "loss": 0.9333,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.9271255060728745,
1609
+ "grad_norm": 0.0,
1610
+ "learning_rate": 0.00012028856840721974,
1611
+ "loss": 0.9583,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.9311740890688259,
1616
+ "grad_norm": 0.0,
1617
+ "learning_rate": 0.00011963220019737691,
1618
+ "loss": 1.0072,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.9352226720647774,
1623
+ "grad_norm": 0.0,
1624
+ "learning_rate": 0.00011897495109808107,
1625
+ "loss": 0.9605,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.9392712550607287,
1630
+ "grad_norm": 0.0,
1631
+ "learning_rate": 0.00011831685059985262,
1632
+ "loss": 0.9691,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.9433198380566802,
1637
+ "grad_norm": 0.0,
1638
+ "learning_rate": 0.00011765792823141384,
1639
+ "loss": 0.9745,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.9473684210526315,
1644
+ "grad_norm": 0.0,
1645
+ "learning_rate": 0.00011699821355836409,
1646
+ "loss": 0.9863,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.951417004048583,
1651
+ "grad_norm": 0.0,
1652
+ "learning_rate": 0.00011633773618185302,
1653
+ "loss": 0.9542,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.9554655870445344,
1658
+ "grad_norm": 0.0,
1659
+ "learning_rate": 0.00011567652573725262,
1660
+ "loss": 0.9872,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.9595141700404858,
1665
+ "grad_norm": 0.0,
1666
+ "learning_rate": 0.00011501461189282733,
1667
+ "loss": 1.0047,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.9635627530364372,
1672
+ "grad_norm": 0.0,
1673
+ "learning_rate": 0.00011435202434840287,
1674
+ "loss": 0.9462,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.9676113360323887,
1679
+ "grad_norm": 0.0,
1680
+ "learning_rate": 0.0001136887928340336,
1681
+ "loss": 0.982,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.97165991902834,
1686
+ "grad_norm": 0.0,
1687
+ "learning_rate": 0.00011302494710866857,
1688
+ "loss": 0.9465,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.9757085020242915,
1693
+ "grad_norm": 0.0,
1694
+ "learning_rate": 0.00011236051695881633,
1695
+ "loss": 0.9978,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.979757085020243,
1700
+ "grad_norm": 0.0,
1701
+ "learning_rate": 0.00011169553219720828,
1702
+ "loss": 0.944,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.9838056680161943,
1707
+ "grad_norm": 0.0,
1708
+ "learning_rate": 0.00011103002266146096,
1709
+ "loss": 0.9887,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.9878542510121457,
1714
+ "grad_norm": 0.0,
1715
+ "learning_rate": 0.0001103640182127375,
1716
+ "loss": 0.9735,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.9919028340080972,
1721
+ "grad_norm": 0.0,
1722
+ "learning_rate": 0.00010969754873440743,
1723
+ "loss": 1.0015,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.9959514170040485,
1728
+ "grad_norm": 0.0,
1729
+ "learning_rate": 0.00010903064413070612,
1730
+ "loss": 0.9771,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 1.0,
1735
+ "grad_norm": 0.0,
1736
+ "learning_rate": 0.00010836333432539272,
1737
+ "loss": 0.9546,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 1.0040485829959513,
1742
+ "grad_norm": 0.0,
1743
+ "learning_rate": 0.00010769564926040769,
1744
+ "loss": 0.935,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 1.008097165991903,
1749
+ "grad_norm": 0.0,
1750
+ "learning_rate": 0.0001070276188945293,
1751
+ "loss": 0.9799,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 1.0121457489878543,
1756
+ "grad_norm": 0.0,
1757
+ "learning_rate": 0.00010635927320202928,
1758
+ "loss": 0.9736,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 1.0161943319838056,
1763
+ "grad_norm": 0.0,
1764
+ "learning_rate": 0.00010569064217132791,
1765
+ "loss": 0.9839,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 1.0202429149797572,
1770
+ "grad_norm": 0.0,
1771
+ "learning_rate": 0.00010502175580364857,
1772
+ "loss": 0.9579,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 1.0242914979757085,
1777
+ "grad_norm": 0.0,
1778
+ "learning_rate": 0.00010435264411167148,
1779
+ "loss": 0.982,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 1.0283400809716599,
1784
+ "grad_norm": 0.0,
1785
+ "learning_rate": 0.0001036833371181871,
1786
+ "loss": 0.9826,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 1.0323886639676114,
1791
+ "grad_norm": 0.0,
1792
+ "learning_rate": 0.00010301386485474889,
1793
+ "loss": 0.9803,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 1.0364372469635628,
1798
+ "grad_norm": 0.0,
1799
+ "learning_rate": 0.00010234425736032607,
1800
+ "loss": 0.9893,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 1.040485829959514,
1805
+ "grad_norm": 0.0,
1806
+ "learning_rate": 0.00010167454467995549,
1807
+ "loss": 0.9193,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 1.0445344129554657,
1812
+ "grad_norm": 0.0,
1813
+ "learning_rate": 0.00010100475686339379,
1814
+ "loss": 0.9718,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 1.048582995951417,
1819
+ "grad_norm": 0.0,
1820
+ "learning_rate": 0.00010033492396376878,
1821
+ "loss": 0.9899,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 1.0526315789473684,
1826
+ "grad_norm": 0.0,
1827
+ "learning_rate": 9.966507603623125e-05,
1828
+ "loss": 0.9395,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 1.05668016194332,
1833
+ "grad_norm": 0.0,
1834
+ "learning_rate": 9.899524313660624e-05,
1835
+ "loss": 0.9386,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 1.0607287449392713,
1840
+ "grad_norm": 0.0,
1841
+ "learning_rate": 9.832545532004454e-05,
1842
+ "loss": 0.967,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 1.0647773279352226,
1847
+ "grad_norm": 0.0,
1848
+ "learning_rate": 9.765574263967396e-05,
1849
+ "loss": 0.9872,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 1.0688259109311742,
1854
+ "grad_norm": 0.0,
1855
+ "learning_rate": 9.698613514525116e-05,
1856
+ "loss": 0.9563,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 1.0728744939271255,
1861
+ "grad_norm": 0.0,
1862
+ "learning_rate": 9.631666288181293e-05,
1863
+ "loss": 0.9693,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 1.0769230769230769,
1868
+ "grad_norm": 0.0,
1869
+ "learning_rate": 9.564735588832856e-05,
1870
+ "loss": 0.961,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 1.0809716599190284,
1875
+ "grad_norm": 0.0,
1876
+ "learning_rate": 9.497824419635144e-05,
1877
+ "loss": 0.9801,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 1.0850202429149798,
1882
+ "grad_norm": 0.0,
1883
+ "learning_rate": 9.430935782867212e-05,
1884
+ "loss": 0.9617,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 1.0890688259109311,
1889
+ "grad_norm": 0.0,
1890
+ "learning_rate": 9.364072679797073e-05,
1891
+ "loss": 0.9403,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 1.0931174089068827,
1896
+ "grad_norm": 0.0,
1897
+ "learning_rate": 9.297238110547074e-05,
1898
+ "loss": 0.9776,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 1.097165991902834,
1903
+ "grad_norm": 0.0,
1904
+ "learning_rate": 9.230435073959232e-05,
1905
+ "loss": 0.9748,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 1.1012145748987854,
1910
+ "grad_norm": 0.0,
1911
+ "learning_rate": 9.163666567460733e-05,
1912
+ "loss": 0.9535,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 1.1052631578947367,
1917
+ "grad_norm": 0.0,
1918
+ "learning_rate": 9.096935586929392e-05,
1919
+ "loss": 0.9628,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 1.1093117408906883,
1924
+ "grad_norm": 0.0,
1925
+ "learning_rate": 9.030245126559262e-05,
1926
+ "loss": 0.9162,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 1.1133603238866396,
1931
+ "grad_norm": 0.0,
1932
+ "learning_rate": 8.963598178726254e-05,
1933
+ "loss": 0.9421,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 1.117408906882591,
1938
+ "grad_norm": 0.0,
1939
+ "learning_rate": 8.896997733853903e-05,
1940
+ "loss": 0.9406,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 1.1214574898785425,
1945
+ "grad_norm": 0.0,
1946
+ "learning_rate": 8.830446780279176e-05,
1947
+ "loss": 0.973,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 1.125506072874494,
1952
+ "grad_norm": 0.0,
1953
+ "learning_rate": 8.763948304118368e-05,
1954
+ "loss": 0.9958,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 1.1295546558704452,
1959
+ "grad_norm": 0.0,
1960
+ "learning_rate": 8.697505289133145e-05,
1961
+ "loss": 0.963,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 1.1336032388663968,
1966
+ "grad_norm": 0.0,
1967
+ "learning_rate": 8.631120716596641e-05,
1968
+ "loss": 0.9419,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 1.1376518218623481,
1973
+ "grad_norm": 0.0,
1974
+ "learning_rate": 8.564797565159714e-05,
1975
+ "loss": 0.9586,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 1.1417004048582995,
1980
+ "grad_norm": 0.0,
1981
+ "learning_rate": 8.498538810717267e-05,
1982
+ "loss": 0.9748,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 1.145748987854251,
1987
+ "grad_norm": 0.0,
1988
+ "learning_rate": 8.432347426274739e-05,
1989
+ "loss": 0.9682,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 1.1497975708502024,
1994
+ "grad_norm": 0.0,
1995
+ "learning_rate": 8.366226381814697e-05,
1996
+ "loss": 0.9807,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 1.1538461538461537,
2001
+ "grad_norm": 0.0,
2002
+ "learning_rate": 8.300178644163594e-05,
2003
+ "loss": 0.9625,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 1.1578947368421053,
2008
+ "grad_norm": 0.0,
2009
+ "learning_rate": 8.234207176858614e-05,
2010
+ "loss": 0.9902,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 1.1619433198380567,
2015
+ "grad_norm": 0.0,
2016
+ "learning_rate": 8.16831494001474e-05,
2017
+ "loss": 0.9476,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 1.165991902834008,
2022
+ "grad_norm": 0.0,
2023
+ "learning_rate": 8.102504890191892e-05,
2024
+ "loss": 0.9156,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 1.1700404858299596,
2029
+ "grad_norm": 0.0,
2030
+ "learning_rate": 8.036779980262311e-05,
2031
+ "loss": 0.9645,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 1.174089068825911,
2036
+ "grad_norm": 0.0,
2037
+ "learning_rate": 7.971143159278026e-05,
2038
+ "loss": 0.9525,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 1.1781376518218623,
2043
+ "grad_norm": 0.0,
2044
+ "learning_rate": 7.905597372338558e-05,
2045
+ "loss": 0.9573,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 1.1821862348178138,
2050
+ "grad_norm": 0.0,
2051
+ "learning_rate": 7.840145560458756e-05,
2052
+ "loss": 0.9338,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 1.1862348178137652,
2057
+ "grad_norm": 0.0,
2058
+ "learning_rate": 7.774790660436858e-05,
2059
+ "loss": 0.9812,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 1.1902834008097165,
2064
+ "grad_norm": 0.0,
2065
+ "learning_rate": 7.709535604722684e-05,
2066
+ "loss": 0.9555,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 1.194331983805668,
2071
+ "grad_norm": 0.0,
2072
+ "learning_rate": 7.644383321286094e-05,
2073
+ "loss": 0.9756,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 1.1983805668016194,
2078
+ "grad_norm": 0.0,
2079
+ "learning_rate": 7.579336733485584e-05,
2080
+ "loss": 0.9495,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 1.2024291497975708,
2085
+ "grad_norm": 0.0,
2086
+ "learning_rate": 7.514398759937135e-05,
2087
+ "loss": 0.9779,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 1.2064777327935223,
2092
+ "grad_norm": 0.0,
2093
+ "learning_rate": 7.449572314383237e-05,
2094
+ "loss": 0.9518,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 1.2105263157894737,
2099
+ "grad_norm": 0.0,
2100
+ "learning_rate": 7.384860305562172e-05,
2101
+ "loss": 0.9499,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 1.214574898785425,
2106
+ "grad_norm": 0.0,
2107
+ "learning_rate": 7.320265637077473e-05,
2108
+ "loss": 0.965,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 1.2186234817813766,
2113
+ "grad_norm": 0.0,
2114
+ "learning_rate": 7.255791207267679e-05,
2115
+ "loss": 0.9575,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 1.222672064777328,
2120
+ "grad_norm": 0.0,
2121
+ "learning_rate": 7.191439909076243e-05,
2122
+ "loss": 0.9783,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 1.2267206477732793,
2127
+ "grad_norm": 0.0,
2128
+ "learning_rate": 7.127214629921765e-05,
2129
+ "loss": 0.9665,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 1.2307692307692308,
2134
+ "grad_norm": 0.0,
2135
+ "learning_rate": 7.0631182515684e-05,
2136
+ "loss": 0.9784,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 1.2348178137651822,
2141
+ "grad_norm": 0.0,
2142
+ "learning_rate": 6.999153649996595e-05,
2143
+ "loss": 0.9475,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 1.2388663967611335,
2148
+ "grad_norm": 0.0,
2149
+ "learning_rate": 6.935323695274002e-05,
2150
+ "loss": 0.9256,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 1.242914979757085,
2155
+ "grad_norm": 0.0,
2156
+ "learning_rate": 6.871631251426728e-05,
2157
+ "loss": 0.9343,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 1.2469635627530364,
2162
+ "grad_norm": 0.0,
2163
+ "learning_rate": 6.808079176310827e-05,
2164
+ "loss": 0.9739,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 1.2510121457489878,
2169
+ "grad_norm": 0.0,
2170
+ "learning_rate": 6.744670321484043e-05,
2171
+ "loss": 0.9773,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 1.2550607287449393,
2176
+ "grad_norm": 0.0,
2177
+ "learning_rate": 6.681407532077895e-05,
2178
+ "loss": 0.9703,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 1.2591093117408907,
2183
+ "grad_norm": 0.0,
2184
+ "learning_rate": 6.618293646669986e-05,
2185
+ "loss": 0.9476,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 1.263157894736842,
2190
+ "grad_norm": 0.0,
2191
+ "learning_rate": 6.555331497156672e-05,
2192
+ "loss": 0.9765,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 1.2672064777327936,
2197
+ "grad_norm": 0.0,
2198
+ "learning_rate": 6.492523908625959e-05,
2199
+ "loss": 1.019,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 1.271255060728745,
2204
+ "grad_norm": 0.0,
2205
+ "learning_rate": 6.42987369923077e-05,
2206
+ "loss": 1.0173,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 1.2753036437246963,
2211
+ "grad_norm": 0.0,
2212
+ "learning_rate": 6.367383680062478e-05,
2213
+ "loss": 1.0097,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 1.2793522267206479,
2218
+ "grad_norm": 0.0,
2219
+ "learning_rate": 6.30505665502479e-05,
2220
+ "loss": 0.9893,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 1.2834008097165992,
2225
+ "grad_norm": 0.0,
2226
+ "learning_rate": 6.242895420707917e-05,
2227
+ "loss": 0.9556,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 1.2874493927125505,
2232
+ "grad_norm": 0.0,
2233
+ "learning_rate": 6.180902766263113e-05,
2234
+ "loss": 0.9325,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 1.291497975708502,
2239
+ "grad_norm": 0.0,
2240
+ "learning_rate": 6.119081473277501e-05,
2241
+ "loss": 0.9661,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 1.2955465587044535,
2246
+ "grad_norm": 0.0,
2247
+ "learning_rate": 6.057434315649304e-05,
2248
+ "loss": 0.9348,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 1.2995951417004048,
2253
+ "grad_norm": 0.0,
2254
+ "learning_rate": 5.99596405946333e-05,
2255
+ "loss": 0.9276,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 1.3036437246963564,
2260
+ "grad_norm": 0.0,
2261
+ "learning_rate": 5.9346734628669065e-05,
2262
+ "loss": 0.9988,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 1.3076923076923077,
2267
+ "grad_norm": 0.0,
2268
+ "learning_rate": 5.873565275946088e-05,
2269
+ "loss": 0.9574,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 1.311740890688259,
2274
+ "grad_norm": 0.0,
2275
+ "learning_rate": 5.8126422406022885e-05,
2276
+ "loss": 0.9795,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 1.3157894736842106,
2281
+ "grad_norm": 0.0,
2282
+ "learning_rate": 5.7519070904292247e-05,
2283
+ "loss": 0.9825,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 1.319838056680162,
2288
+ "grad_norm": 0.0,
2289
+ "learning_rate": 5.691362550590297e-05,
2290
+ "loss": 0.9799,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 1.3238866396761133,
2295
+ "grad_norm": 0.0,
2296
+ "learning_rate": 5.631011337696271e-05,
2297
+ "loss": 0.9542,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 1.3279352226720649,
2302
+ "grad_norm": 0.0,
2303
+ "learning_rate": 5.570856159683418e-05,
2304
+ "loss": 0.9807,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 1.3319838056680162,
2309
+ "grad_norm": 0.0,
2310
+ "learning_rate": 5.510899715691984e-05,
2311
+ "loss": 0.984,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 1.3360323886639676,
2316
+ "grad_norm": 0.0,
2317
+ "learning_rate": 5.451144695945116e-05,
2318
+ "loss": 0.9385,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 1.3400809716599191,
2323
+ "grad_norm": 0.0,
2324
+ "learning_rate": 5.3915937816281095e-05,
2325
+ "loss": 0.9863,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 1.3441295546558705,
2330
+ "grad_norm": 0.0,
2331
+ "learning_rate": 5.3322496447681414e-05,
2332
+ "loss": 0.957,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 1.3481781376518218,
2337
+ "grad_norm": 0.0,
2338
+ "learning_rate": 5.273114948114346e-05,
2339
+ "loss": 0.9636,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 1.3522267206477734,
2344
+ "grad_norm": 0.0,
2345
+ "learning_rate": 5.214192345018374e-05,
2346
+ "loss": 0.9849,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 1.3562753036437247,
2351
+ "grad_norm": 0.0,
2352
+ "learning_rate": 5.1554844793153e-05,
2353
+ "loss": 0.9627,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 1.360323886639676,
2358
+ "grad_norm": 0.0,
2359
+ "learning_rate": 5.096993985205023e-05,
2360
+ "loss": 0.9638,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 1.3643724696356276,
2365
+ "grad_norm": 0.0,
2366
+ "learning_rate": 5.0387234871340486e-05,
2367
+ "loss": 0.9502,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 1.368421052631579,
2372
+ "grad_norm": 0.0,
2373
+ "learning_rate": 4.980675599677757e-05,
2374
+ "loss": 0.9698,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 1.3724696356275303,
2379
+ "grad_norm": 0.0,
2380
+ "learning_rate": 4.9228529274230695e-05,
2381
+ "loss": 0.9829,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 1.376518218623482,
2386
+ "grad_norm": 0.0,
2387
+ "learning_rate": 4.865258064851579e-05,
2388
+ "loss": 0.972,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 1.3805668016194332,
2393
+ "grad_norm": 0.0,
2394
+ "learning_rate": 4.807893596223152e-05,
2395
+ "loss": 0.9377,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 1.3846153846153846,
2400
+ "grad_norm": 0.0,
2401
+ "learning_rate": 4.75076209545996e-05,
2402
+ "loss": 0.9654,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 1.3886639676113361,
2407
+ "grad_norm": 0.0,
2408
+ "learning_rate": 4.693866126030995e-05,
2409
+ "loss": 0.947,
2410
+ "step": 343
2411
+ },
2412
+ {
2413
+ "epoch": 1.3927125506072875,
2414
+ "grad_norm": 0.0,
2415
+ "learning_rate": 4.637208240837042e-05,
2416
+ "loss": 0.9983,
2417
+ "step": 344
2418
+ },
2419
+ {
2420
+ "epoch": 1.3967611336032388,
2421
+ "grad_norm": 0.0,
2422
+ "learning_rate": 4.5807909820961494e-05,
2423
+ "loss": 0.9625,
2424
+ "step": 345
2425
+ },
2426
+ {
2427
+ "epoch": 1.4008097165991904,
2428
+ "grad_norm": 0.0,
2429
+ "learning_rate": 4.5246168812295286e-05,
2430
+ "loss": 0.9647,
2431
+ "step": 346
2432
+ },
2433
+ {
2434
+ "epoch": 1.4048582995951417,
2435
+ "grad_norm": 0.0,
2436
+ "learning_rate": 4.468688458748006e-05,
2437
+ "loss": 0.9718,
2438
+ "step": 347
2439
+ },
2440
+ {
2441
+ "epoch": 1.408906882591093,
2442
+ "grad_norm": 0.0,
2443
+ "learning_rate": 4.413008224138897e-05,
2444
+ "loss": 0.9967,
2445
+ "step": 348
2446
+ },
2447
+ {
2448
+ "epoch": 1.4129554655870447,
2449
+ "grad_norm": 0.0,
2450
+ "learning_rate": 4.357578675753432e-05,
2451
+ "loss": 0.9366,
2452
+ "step": 349
2453
+ },
2454
+ {
2455
+ "epoch": 1.417004048582996,
2456
+ "grad_norm": 0.0,
2457
+ "learning_rate": 4.302402300694636e-05,
2458
+ "loss": 0.9667,
2459
+ "step": 350
2460
+ },
2461
+ {
2462
+ "epoch": 1.4210526315789473,
2463
+ "grad_norm": 0.0,
2464
+ "learning_rate": 4.247481574705744e-05,
2465
+ "loss": 0.9362,
2466
+ "step": 351
2467
+ },
2468
+ {
2469
+ "epoch": 1.425101214574899,
2470
+ "grad_norm": 0.0,
2471
+ "learning_rate": 4.1928189620591116e-05,
2472
+ "loss": 0.9509,
2473
+ "step": 352
2474
+ },
2475
+ {
2476
+ "epoch": 1.4291497975708503,
2477
+ "grad_norm": 0.0,
2478
+ "learning_rate": 4.138416915445655e-05,
2479
+ "loss": 0.9744,
2480
+ "step": 353
2481
+ },
2482
+ {
2483
+ "epoch": 1.4331983805668016,
2484
+ "grad_norm": 0.0,
2485
+ "learning_rate": 4.084277875864776e-05,
2486
+ "loss": 0.9658,
2487
+ "step": 354
2488
+ },
2489
+ {
2490
+ "epoch": 1.4372469635627532,
2491
+ "grad_norm": 0.0,
2492
+ "learning_rate": 4.030404272514864e-05,
2493
+ "loss": 0.9091,
2494
+ "step": 355
2495
+ },
2496
+ {
2497
+ "epoch": 1.4412955465587045,
2498
+ "grad_norm": 0.0,
2499
+ "learning_rate": 3.9767985226842696e-05,
2500
+ "loss": 0.9631,
2501
+ "step": 356
2502
+ },
2503
+ {
2504
+ "epoch": 1.4453441295546559,
2505
+ "grad_norm": 0.0,
2506
+ "learning_rate": 3.923463031642872e-05,
2507
+ "loss": 0.9766,
2508
+ "step": 357
2509
+ },
2510
+ {
2511
+ "epoch": 1.4493927125506074,
2512
+ "grad_norm": 0.0,
2513
+ "learning_rate": 3.870400192534128e-05,
2514
+ "loss": 0.9289,
2515
+ "step": 358
2516
+ },
2517
+ {
2518
+ "epoch": 1.4534412955465588,
2519
+ "grad_norm": 0.0,
2520
+ "learning_rate": 3.81761238626771e-05,
2521
+ "loss": 0.9665,
2522
+ "step": 359
2523
+ },
2524
+ {
2525
+ "epoch": 1.45748987854251,
2526
+ "grad_norm": 0.0,
2527
+ "learning_rate": 3.7651019814126654e-05,
2528
+ "loss": 0.9473,
2529
+ "step": 360
2530
+ },
2531
+ {
2532
+ "epoch": 1.4615384615384617,
2533
+ "grad_norm": 0.0,
2534
+ "learning_rate": 3.7128713340911535e-05,
2535
+ "loss": 1.001,
2536
+ "step": 361
2537
+ },
2538
+ {
2539
+ "epoch": 1.465587044534413,
2540
+ "grad_norm": 0.0,
2541
+ "learning_rate": 3.660922787872706e-05,
2542
+ "loss": 0.9193,
2543
+ "step": 362
2544
+ },
2545
+ {
2546
+ "epoch": 1.4696356275303644,
2547
+ "grad_norm": 0.0,
2548
+ "learning_rate": 3.609258673669097e-05,
2549
+ "loss": 0.9639,
2550
+ "step": 363
2551
+ },
2552
+ {
2553
+ "epoch": 1.4736842105263157,
2554
+ "grad_norm": 0.0,
2555
+ "learning_rate": 3.557881309629729e-05,
2556
+ "loss": 0.9651,
2557
+ "step": 364
2558
+ },
2559
+ {
2560
+ "epoch": 1.4777327935222673,
2561
+ "grad_norm": 0.0,
2562
+ "learning_rate": 3.5067930010376484e-05,
2563
+ "loss": 0.974,
2564
+ "step": 365
2565
+ },
2566
+ {
2567
+ "epoch": 1.4817813765182186,
2568
+ "grad_norm": 0.0,
2569
+ "learning_rate": 3.455996040206076e-05,
2570
+ "loss": 0.9718,
2571
+ "step": 366
2572
+ },
2573
+ {
2574
+ "epoch": 1.48582995951417,
2575
+ "grad_norm": 0.0,
2576
+ "learning_rate": 3.4054927063755796e-05,
2577
+ "loss": 0.9408,
2578
+ "step": 367
2579
+ },
2580
+ {
2581
+ "epoch": 1.4898785425101215,
2582
+ "grad_norm": 0.0,
2583
+ "learning_rate": 3.355285265611784e-05,
2584
+ "loss": 0.9817,
2585
+ "step": 368
2586
+ },
2587
+ {
2588
+ "epoch": 1.4939271255060729,
2589
+ "grad_norm": 0.0,
2590
+ "learning_rate": 3.305375970703711e-05,
2591
+ "loss": 0.9591,
2592
+ "step": 369
2593
+ },
2594
+ {
2595
+ "epoch": 1.4979757085020242,
2596
+ "grad_norm": 0.0,
2597
+ "learning_rate": 3.2557670610626925e-05,
2598
+ "loss": 0.9882,
2599
+ "step": 370
2600
+ },
2601
+ {
2602
+ "epoch": 1.5020242914979756,
2603
+ "grad_norm": 0.0,
2604
+ "learning_rate": 3.206460762621873e-05,
2605
+ "loss": 0.9703,
2606
+ "step": 371
2607
+ },
2608
+ {
2609
+ "epoch": 1.5060728744939271,
2610
+ "grad_norm": 0.0,
2611
+ "learning_rate": 3.157459287736362e-05,
2612
+ "loss": 0.9722,
2613
+ "step": 372
2614
+ },
2615
+ {
2616
+ "epoch": 1.5101214574898787,
2617
+ "grad_norm": 0.0,
2618
+ "learning_rate": 3.108764835083938e-05,
2619
+ "loss": 0.9966,
2620
+ "step": 373
2621
+ },
2622
+ {
2623
+ "epoch": 1.5141700404858298,
2624
+ "grad_norm": 0.0,
2625
+ "learning_rate": 3.0603795895664124e-05,
2626
+ "loss": 1.0014,
2627
+ "step": 374
2628
+ },
2629
+ {
2630
+ "epoch": 1.5182186234817814,
2631
+ "grad_norm": 0.0,
2632
+ "learning_rate": 3.0123057222115836e-05,
2633
+ "loss": 0.9824,
2634
+ "step": 375
2635
+ },
2636
+ {
2637
+ "epoch": 1.522267206477733,
2638
+ "grad_norm": 0.0,
2639
+ "learning_rate": 2.964545390075841e-05,
2640
+ "loss": 0.9788,
2641
+ "step": 376
2642
+ },
2643
+ {
2644
+ "epoch": 1.526315789473684,
2645
+ "grad_norm": 0.0,
2646
+ "learning_rate": 2.9171007361473514e-05,
2647
+ "loss": 0.9224,
2648
+ "step": 377
2649
+ },
2650
+ {
2651
+ "epoch": 1.5303643724696356,
2652
+ "grad_norm": 0.0,
2653
+ "learning_rate": 2.8699738892499328e-05,
2654
+ "loss": 0.9694,
2655
+ "step": 378
2656
+ },
2657
+ {
2658
+ "epoch": 1.5344129554655872,
2659
+ "grad_norm": 0.0,
2660
+ "learning_rate": 2.8231669639475067e-05,
2661
+ "loss": 0.9831,
2662
+ "step": 379
2663
+ },
2664
+ {
2665
+ "epoch": 1.5384615384615383,
2666
+ "grad_norm": 0.0,
2667
+ "learning_rate": 2.776682060449247e-05,
2668
+ "loss": 0.9843,
2669
+ "step": 380
2670
+ },
2671
+ {
2672
+ "epoch": 1.54251012145749,
2673
+ "grad_norm": 0.0,
2674
+ "learning_rate": 2.7305212645153212e-05,
2675
+ "loss": 0.981,
2676
+ "step": 381
2677
+ },
2678
+ {
2679
+ "epoch": 1.5465587044534415,
2680
+ "grad_norm": 0.0,
2681
+ "learning_rate": 2.6846866473633125e-05,
2682
+ "loss": 0.9357,
2683
+ "step": 382
2684
+ },
2685
+ {
2686
+ "epoch": 1.5506072874493926,
2687
+ "grad_norm": 0.0,
2688
+ "learning_rate": 2.6391802655752853e-05,
2689
+ "loss": 0.9541,
2690
+ "step": 383
2691
+ },
2692
+ {
2693
+ "epoch": 1.5546558704453441,
2694
+ "grad_norm": 0.0,
2695
+ "learning_rate": 2.594004161005511e-05,
2696
+ "loss": 0.9304,
2697
+ "step": 384
2698
+ },
2699
+ {
2700
+ "epoch": 1.5587044534412957,
2701
+ "grad_norm": 0.0,
2702
+ "learning_rate": 2.549160360688838e-05,
2703
+ "loss": 0.989,
2704
+ "step": 385
2705
+ },
2706
+ {
2707
+ "epoch": 1.5627530364372468,
2708
+ "grad_norm": 0.0,
2709
+ "learning_rate": 2.50465087674976e-05,
2710
+ "loss": 0.9566,
2711
+ "step": 386
2712
+ },
2713
+ {
2714
+ "epoch": 1.5668016194331984,
2715
+ "grad_norm": 0.0,
2716
+ "learning_rate": 2.4604777063121033e-05,
2717
+ "loss": 0.921,
2718
+ "step": 387
2719
+ },
2720
+ {
2721
+ "epoch": 1.5708502024291497,
2722
+ "grad_norm": 0.0,
2723
+ "learning_rate": 2.4166428314094514e-05,
2724
+ "loss": 0.974,
2725
+ "step": 388
2726
+ },
2727
+ {
2728
+ "epoch": 1.574898785425101,
2729
+ "grad_norm": 0.0,
2730
+ "learning_rate": 2.3731482188961818e-05,
2731
+ "loss": 0.9205,
2732
+ "step": 389
2733
+ },
2734
+ {
2735
+ "epoch": 1.5789473684210527,
2736
+ "grad_norm": 0.0,
2737
+ "learning_rate": 2.32999582035923e-05,
2738
+ "loss": 0.9843,
2739
+ "step": 390
2740
+ },
2741
+ {
2742
+ "epoch": 1.582995951417004,
2743
+ "grad_norm": 0.0,
2744
+ "learning_rate": 2.287187572030516e-05,
2745
+ "loss": 0.9602,
2746
+ "step": 391
2747
+ },
2748
+ {
2749
+ "epoch": 1.5870445344129553,
2750
+ "grad_norm": 0.0,
2751
+ "learning_rate": 2.244725394700079e-05,
2752
+ "loss": 0.9536,
2753
+ "step": 392
2754
+ },
2755
+ {
2756
+ "epoch": 1.591093117408907,
2757
+ "grad_norm": 0.0,
2758
+ "learning_rate": 2.202611193629869e-05,
2759
+ "loss": 0.9845,
2760
+ "step": 393
2761
+ },
2762
+ {
2763
+ "epoch": 1.5951417004048583,
2764
+ "grad_norm": 0.0,
2765
+ "learning_rate": 2.160846858468285e-05,
2766
+ "loss": 0.9763,
2767
+ "step": 394
2768
+ },
2769
+ {
2770
+ "epoch": 1.5991902834008096,
2771
+ "grad_norm": 0.0,
2772
+ "learning_rate": 2.1194342631653607e-05,
2773
+ "loss": 0.953,
2774
+ "step": 395
2775
+ },
2776
+ {
2777
+ "epoch": 1.6032388663967612,
2778
+ "grad_norm": 0.0,
2779
+ "learning_rate": 2.0783752658887066e-05,
2780
+ "loss": 0.9446,
2781
+ "step": 396
2782
+ },
2783
+ {
2784
+ "epoch": 1.6072874493927125,
2785
+ "grad_norm": 0.0,
2786
+ "learning_rate": 2.0376717089401164e-05,
2787
+ "loss": 0.9577,
2788
+ "step": 397
2789
+ },
2790
+ {
2791
+ "epoch": 1.6113360323886639,
2792
+ "grad_norm": 0.0,
2793
+ "learning_rate": 1.9973254186729086e-05,
2794
+ "loss": 0.9772,
2795
+ "step": 398
2796
+ },
2797
+ {
2798
+ "epoch": 1.6153846153846154,
2799
+ "grad_norm": 0.0,
2800
+ "learning_rate": 1.9573382054099786e-05,
2801
+ "loss": 0.9886,
2802
+ "step": 399
2803
+ },
2804
+ {
2805
+ "epoch": 1.6194331983805668,
2806
+ "grad_norm": 0.0,
2807
+ "learning_rate": 1.9177118633625814e-05,
2808
+ "loss": 0.9702,
2809
+ "step": 400
2810
+ },
2811
+ {
2812
+ "epoch": 1.623481781376518,
2813
+ "grad_norm": 0.0,
2814
+ "learning_rate": 1.8784481705498015e-05,
2815
+ "loss": 0.9557,
2816
+ "step": 401
2817
+ },
2818
+ {
2819
+ "epoch": 1.6275303643724697,
2820
+ "grad_norm": 0.0,
2821
+ "learning_rate": 1.8395488887188005e-05,
2822
+ "loss": 0.9324,
2823
+ "step": 402
2824
+ },
2825
+ {
2826
+ "epoch": 1.631578947368421,
2827
+ "grad_norm": 0.0,
2828
+ "learning_rate": 1.8010157632657543e-05,
2829
+ "loss": 0.9749,
2830
+ "step": 403
2831
+ },
2832
+ {
2833
+ "epoch": 1.6356275303643724,
2834
+ "grad_norm": 0.0,
2835
+ "learning_rate": 1.762850523157532e-05,
2836
+ "loss": 0.95,
2837
+ "step": 404
2838
+ },
2839
+ {
2840
+ "epoch": 1.639676113360324,
2841
+ "grad_norm": 0.0,
2842
+ "learning_rate": 1.7250548808541322e-05,
2843
+ "loss": 0.9437,
2844
+ "step": 405
2845
+ },
2846
+ {
2847
+ "epoch": 1.6437246963562753,
2848
+ "grad_norm": 0.0,
2849
+ "learning_rate": 1.687630532231833e-05,
2850
+ "loss": 1.0033,
2851
+ "step": 406
2852
+ },
2853
+ {
2854
+ "epoch": 1.6477732793522266,
2855
+ "grad_norm": 0.0,
2856
+ "learning_rate": 1.6505791565071138e-05,
2857
+ "loss": 0.9441,
2858
+ "step": 407
2859
+ },
2860
+ {
2861
+ "epoch": 1.6518218623481782,
2862
+ "grad_norm": 0.0,
2863
+ "learning_rate": 1.613902416161288e-05,
2864
+ "loss": 0.9808,
2865
+ "step": 408
2866
+ },
2867
+ {
2868
+ "epoch": 1.6558704453441295,
2869
+ "grad_norm": 0.0,
2870
+ "learning_rate": 1.5776019568659338e-05,
2871
+ "loss": 0.9782,
2872
+ "step": 409
2873
+ },
2874
+ {
2875
+ "epoch": 1.6599190283400809,
2876
+ "grad_norm": 0.0,
2877
+ "learning_rate": 1.5416794074090258e-05,
2878
+ "loss": 0.9791,
2879
+ "step": 410
2880
+ },
2881
+ {
2882
+ "epoch": 1.6639676113360324,
2883
+ "grad_norm": 0.0,
2884
+ "learning_rate": 1.5061363796218785e-05,
2885
+ "loss": 0.9909,
2886
+ "step": 411
2887
+ },
2888
+ {
2889
+ "epoch": 1.6680161943319838,
2890
+ "grad_norm": 0.0,
2891
+ "learning_rate": 1.4709744683068039e-05,
2892
+ "loss": 0.9484,
2893
+ "step": 412
2894
+ },
2895
+ {
2896
+ "epoch": 1.6720647773279351,
2897
+ "grad_norm": 0.0,
2898
+ "learning_rate": 1.4361952511655618e-05,
2899
+ "loss": 0.9288,
2900
+ "step": 413
2901
+ },
2902
+ {
2903
+ "epoch": 1.6761133603238867,
2904
+ "grad_norm": 0.0,
2905
+ "learning_rate": 1.4018002887285687e-05,
2906
+ "loss": 0.977,
2907
+ "step": 414
2908
+ },
2909
+ {
2910
+ "epoch": 1.680161943319838,
2911
+ "grad_norm": 0.0,
2912
+ "learning_rate": 1.3677911242848806e-05,
2913
+ "loss": 0.9548,
2914
+ "step": 415
2915
+ },
2916
+ {
2917
+ "epoch": 1.6842105263157894,
2918
+ "grad_norm": 0.0,
2919
+ "learning_rate": 1.334169283812936e-05,
2920
+ "loss": 0.9934,
2921
+ "step": 416
2922
+ },
2923
+ {
2924
+ "epoch": 1.688259109311741,
2925
+ "grad_norm": 0.0,
2926
+ "learning_rate": 1.300936275912098e-05,
2927
+ "loss": 0.9903,
2928
+ "step": 417
2929
+ },
2930
+ {
2931
+ "epoch": 1.6923076923076923,
2932
+ "grad_norm": 0.0,
2933
+ "learning_rate": 1.2680935917349523e-05,
2934
+ "loss": 0.9378,
2935
+ "step": 418
2936
+ },
2937
+ {
2938
+ "epoch": 1.6963562753036436,
2939
+ "grad_norm": 0.0,
2940
+ "learning_rate": 1.2356427049204122e-05,
2941
+ "loss": 0.994,
2942
+ "step": 419
2943
+ },
2944
+ {
2945
+ "epoch": 1.7004048582995952,
2946
+ "grad_norm": 0.0,
2947
+ "learning_rate": 1.2035850715275865e-05,
2948
+ "loss": 0.9664,
2949
+ "step": 420
2950
+ },
2951
+ {
2952
+ "epoch": 1.7044534412955465,
2953
+ "grad_norm": 0.0,
2954
+ "learning_rate": 1.1719221299704497e-05,
2955
+ "loss": 0.9318,
2956
+ "step": 421
2957
+ },
2958
+ {
2959
+ "epoch": 1.708502024291498,
2960
+ "grad_norm": 0.0,
2961
+ "learning_rate": 1.1406553009533027e-05,
2962
+ "loss": 0.9603,
2963
+ "step": 422
2964
+ },
2965
+ {
2966
+ "epoch": 1.7125506072874495,
2967
+ "grad_norm": 0.0,
2968
+ "learning_rate": 1.1097859874070294e-05,
2969
+ "loss": 0.9195,
2970
+ "step": 423
2971
+ },
2972
+ {
2973
+ "epoch": 1.7165991902834008,
2974
+ "grad_norm": 0.0,
2975
+ "learning_rate": 1.0793155744261351e-05,
2976
+ "loss": 0.9455,
2977
+ "step": 424
2978
+ },
2979
+ {
2980
+ "epoch": 1.7206477732793521,
2981
+ "grad_norm": 0.0,
2982
+ "learning_rate": 1.0492454292066178e-05,
2983
+ "loss": 0.9387,
2984
+ "step": 425
2985
+ },
2986
+ {
2987
+ "epoch": 1.7246963562753037,
2988
+ "grad_norm": 0.0,
2989
+ "learning_rate": 1.019576900984599e-05,
2990
+ "loss": 0.9287,
2991
+ "step": 426
2992
+ },
2993
+ {
2994
+ "epoch": 1.728744939271255,
2995
+ "grad_norm": 0.0,
2996
+ "learning_rate": 9.903113209758096e-06,
2997
+ "loss": 0.9274,
2998
+ "step": 427
2999
+ },
3000
+ {
3001
+ "epoch": 1.7327935222672064,
3002
+ "grad_norm": 0.0,
3003
+ "learning_rate": 9.614500023158336e-06,
3004
+ "loss": 0.957,
3005
+ "step": 428
3006
+ },
3007
+ {
3008
+ "epoch": 1.736842105263158,
3009
+ "grad_norm": 0.0,
3010
+ "learning_rate": 9.32994240001206e-06,
3011
+ "loss": 0.9741,
3012
+ "step": 429
3013
+ },
3014
+ {
3015
+ "epoch": 1.7408906882591093,
3016
+ "grad_norm": 0.0,
3017
+ "learning_rate": 9.049453108312966e-06,
3018
+ "loss": 0.9638,
3019
+ "step": 430
3020
+ },
3021
+ {
3022
+ "epoch": 1.7449392712550607,
3023
+ "grad_norm": 0.0,
3024
+ "learning_rate": 8.773044733510338e-06,
3025
+ "loss": 0.9711,
3026
+ "step": 431
3027
+ },
3028
+ {
3029
+ "epoch": 1.7489878542510122,
3030
+ "grad_norm": 0.0,
3031
+ "learning_rate": 8.50072967794413e-06,
3032
+ "loss": 0.961,
3033
+ "step": 432
3034
+ },
3035
+ {
3036
+ "epoch": 1.7530364372469636,
3037
+ "grad_norm": 0.0,
3038
+ "learning_rate": 8.232520160288704e-06,
3039
+ "loss": 0.9734,
3040
+ "step": 433
3041
+ },
3042
+ {
3043
+ "epoch": 1.757085020242915,
3044
+ "grad_norm": 0.0,
3045
+ "learning_rate": 7.96842821500442e-06,
3046
+ "loss": 0.9437,
3047
+ "step": 434
3048
+ },
3049
+ {
3050
+ "epoch": 1.7611336032388665,
3051
+ "grad_norm": 0.0,
3052
+ "learning_rate": 7.708465691797717e-06,
3053
+ "loss": 0.9305,
3054
+ "step": 435
3055
+ },
3056
+ {
3057
+ "epoch": 1.7651821862348178,
3058
+ "grad_norm": 0.0,
3059
+ "learning_rate": 7.452644255089425e-06,
3060
+ "loss": 0.9363,
3061
+ "step": 436
3062
+ },
3063
+ {
3064
+ "epoch": 1.7692307692307692,
3065
+ "grad_norm": 0.0,
3066
+ "learning_rate": 7.20097538349136e-06,
3067
+ "loss": 0.9579,
3068
+ "step": 437
3069
+ },
3070
+ {
3071
+ "epoch": 1.7732793522267207,
3072
+ "grad_norm": 0.0,
3073
+ "learning_rate": 6.953470369291348e-06,
3074
+ "loss": 0.9426,
3075
+ "step": 438
3076
+ },
3077
+ {
3078
+ "epoch": 1.777327935222672,
3079
+ "grad_norm": 0.0,
3080
+ "learning_rate": 6.710140317946423e-06,
3081
+ "loss": 0.9935,
3082
+ "step": 439
3083
+ },
3084
+ {
3085
+ "epoch": 1.7813765182186234,
3086
+ "grad_norm": 0.0,
3087
+ "learning_rate": 6.470996147584685e-06,
3088
+ "loss": 0.9767,
3089
+ "step": 440
3090
+ },
3091
+ {
3092
+ "epoch": 1.785425101214575,
3093
+ "grad_norm": 0.0,
3094
+ "learning_rate": 6.236048588515242e-06,
3095
+ "loss": 0.9366,
3096
+ "step": 441
3097
+ },
3098
+ {
3099
+ "epoch": 1.7894736842105263,
3100
+ "grad_norm": 0.0,
3101
+ "learning_rate": 6.0053081827469045e-06,
3102
+ "loss": 0.9881,
3103
+ "step": 442
3104
+ },
3105
+ {
3106
+ "epoch": 1.7935222672064777,
3107
+ "grad_norm": 0.0,
3108
+ "learning_rate": 5.778785283515053e-06,
3109
+ "loss": 0.9478,
3110
+ "step": 443
3111
+ },
3112
+ {
3113
+ "epoch": 1.7975708502024292,
3114
+ "grad_norm": 0.0,
3115
+ "learning_rate": 5.556490054817132e-06,
3116
+ "loss": 0.9514,
3117
+ "step": 444
3118
+ },
3119
+ {
3120
+ "epoch": 1.8016194331983806,
3121
+ "grad_norm": 0.0,
3122
+ "learning_rate": 5.338432470956589e-06,
3123
+ "loss": 0.9651,
3124
+ "step": 445
3125
+ },
3126
+ {
3127
+ "epoch": 1.805668016194332,
3128
+ "grad_norm": 0.0,
3129
+ "learning_rate": 5.1246223160953845e-06,
3130
+ "loss": 0.9288,
3131
+ "step": 446
3132
+ },
3133
+ {
3134
+ "epoch": 1.8097165991902835,
3135
+ "grad_norm": 0.0,
3136
+ "learning_rate": 4.91506918381488e-06,
3137
+ "loss": 0.9232,
3138
+ "step": 447
3139
+ },
3140
+ {
3141
+ "epoch": 1.8137651821862348,
3142
+ "grad_norm": 0.0,
3143
+ "learning_rate": 4.7097824766854756e-06,
3144
+ "loss": 0.949,
3145
+ "step": 448
3146
+ },
3147
+ {
3148
+ "epoch": 1.8178137651821862,
3149
+ "grad_norm": 0.0,
3150
+ "learning_rate": 4.508771405844636e-06,
3151
+ "loss": 0.9276,
3152
+ "step": 449
3153
+ },
3154
+ {
3155
+ "epoch": 1.8218623481781377,
3156
+ "grad_norm": 0.0,
3157
+ "learning_rate": 4.312044990583675e-06,
3158
+ "loss": 0.9634,
3159
+ "step": 450
3160
+ },
3161
+ {
3162
+ "epoch": 1.825910931174089,
3163
+ "grad_norm": 0.0,
3164
+ "learning_rate": 4.119612057942978e-06,
3165
+ "loss": 0.9266,
3166
+ "step": 451
3167
+ },
3168
+ {
3169
+ "epoch": 1.8299595141700404,
3170
+ "grad_norm": 0.0,
3171
+ "learning_rate": 3.931481242315993e-06,
3172
+ "loss": 0.9582,
3173
+ "step": 452
3174
+ },
3175
+ {
3176
+ "epoch": 1.834008097165992,
3177
+ "grad_norm": 0.0,
3178
+ "learning_rate": 3.747660985061785e-06,
3179
+ "loss": 0.9732,
3180
+ "step": 453
3181
+ },
3182
+ {
3183
+ "epoch": 1.8380566801619433,
3184
+ "grad_norm": 0.0,
3185
+ "learning_rate": 3.568159534126314e-06,
3186
+ "loss": 0.9855,
3187
+ "step": 454
3188
+ },
3189
+ {
3190
+ "epoch": 1.8421052631578947,
3191
+ "grad_norm": 0.0,
3192
+ "learning_rate": 3.3929849436722728e-06,
3193
+ "loss": 0.9803,
3194
+ "step": 455
3195
+ },
3196
+ {
3197
+ "epoch": 1.8461538461538463,
3198
+ "grad_norm": 0.0,
3199
+ "learning_rate": 3.2221450737178083e-06,
3200
+ "loss": 0.9656,
3201
+ "step": 456
3202
+ },
3203
+ {
3204
+ "epoch": 1.8502024291497976,
3205
+ "grad_norm": 0.0,
3206
+ "learning_rate": 3.0556475897837166e-06,
3207
+ "loss": 0.9432,
3208
+ "step": 457
3209
+ },
3210
+ {
3211
+ "epoch": 1.854251012145749,
3212
+ "grad_norm": 0.0,
3213
+ "learning_rate": 2.8934999625496282e-06,
3214
+ "loss": 0.9857,
3215
+ "step": 458
3216
+ },
3217
+ {
3218
+ "epoch": 1.8582995951417005,
3219
+ "grad_norm": 0.0,
3220
+ "learning_rate": 2.735709467518699e-06,
3221
+ "loss": 0.9566,
3222
+ "step": 459
3223
+ },
3224
+ {
3225
+ "epoch": 1.8623481781376519,
3226
+ "grad_norm": 0.0,
3227
+ "learning_rate": 2.5822831846912033e-06,
3228
+ "loss": 0.9533,
3229
+ "step": 460
3230
+ },
3231
+ {
3232
+ "epoch": 1.8663967611336032,
3233
+ "grad_norm": 0.0,
3234
+ "learning_rate": 2.4332279982468453e-06,
3235
+ "loss": 0.9373,
3236
+ "step": 461
3237
+ },
3238
+ {
3239
+ "epoch": 1.8704453441295548,
3240
+ "grad_norm": 0.0,
3241
+ "learning_rate": 2.2885505962359054e-06,
3242
+ "loss": 0.9489,
3243
+ "step": 462
3244
+ },
3245
+ {
3246
+ "epoch": 1.874493927125506,
3247
+ "grad_norm": 0.0,
3248
+ "learning_rate": 2.1482574702790803e-06,
3249
+ "loss": 0.9526,
3250
+ "step": 463
3251
+ },
3252
+ {
3253
+ "epoch": 1.8785425101214575,
3254
+ "grad_norm": 0.0,
3255
+ "learning_rate": 2.0123549152762823e-06,
3256
+ "loss": 0.9642,
3257
+ "step": 464
3258
+ },
3259
+ {
3260
+ "epoch": 1.882591093117409,
3261
+ "grad_norm": 0.0,
3262
+ "learning_rate": 1.8808490291241432e-06,
3263
+ "loss": 0.9639,
3264
+ "step": 465
3265
+ },
3266
+ {
3267
+ "epoch": 1.8866396761133604,
3268
+ "grad_norm": 0.0,
3269
+ "learning_rate": 1.7537457124423895e-06,
3270
+ "loss": 0.9577,
3271
+ "step": 466
3272
+ },
3273
+ {
3274
+ "epoch": 1.8906882591093117,
3275
+ "grad_norm": 0.0,
3276
+ "learning_rate": 1.631050668309131e-06,
3277
+ "loss": 0.9664,
3278
+ "step": 467
3279
+ },
3280
+ {
3281
+ "epoch": 1.8947368421052633,
3282
+ "grad_norm": 0.0,
3283
+ "learning_rate": 1.5127694020049432e-06,
3284
+ "loss": 0.9768,
3285
+ "step": 468
3286
+ },
3287
+ {
3288
+ "epoch": 1.8987854251012146,
3289
+ "grad_norm": 0.0,
3290
+ "learning_rate": 1.3989072207658328e-06,
3291
+ "loss": 0.9251,
3292
+ "step": 469
3293
+ },
3294
+ {
3295
+ "epoch": 1.902834008097166,
3296
+ "grad_norm": 0.0,
3297
+ "learning_rate": 1.2894692335451375e-06,
3298
+ "loss": 0.9535,
3299
+ "step": 470
3300
+ },
3301
+ {
3302
+ "epoch": 1.9068825910931175,
3303
+ "grad_norm": 0.0,
3304
+ "learning_rate": 1.1844603507842668e-06,
3305
+ "loss": 0.9544,
3306
+ "step": 471
3307
+ },
3308
+ {
3309
+ "epoch": 1.9109311740890689,
3310
+ "grad_norm": 0.0,
3311
+ "learning_rate": 1.083885284192354e-06,
3312
+ "loss": 0.9298,
3313
+ "step": 472
3314
+ },
3315
+ {
3316
+ "epoch": 1.9149797570850202,
3317
+ "grad_norm": 0.0,
3318
+ "learning_rate": 9.877485465349058e-07,
3319
+ "loss": 0.9646,
3320
+ "step": 473
3321
+ },
3322
+ {
3323
+ "epoch": 1.9190283400809718,
3324
+ "grad_norm": 0.0,
3325
+ "learning_rate": 8.960544514312275e-07,
3326
+ "loss": 0.9435,
3327
+ "step": 474
3328
+ },
3329
+ {
3330
+ "epoch": 1.9230769230769231,
3331
+ "grad_norm": 0.0,
3332
+ "learning_rate": 8.088071131609587e-07,
3333
+ "loss": 0.9375,
3334
+ "step": 475
3335
+ },
3336
+ {
3337
+ "epoch": 1.9271255060728745,
3338
+ "grad_norm": 0.0,
3339
+ "learning_rate": 7.26010446479397e-07,
3340
+ "loss": 0.925,
3341
+ "step": 476
3342
+ },
3343
+ {
3344
+ "epoch": 1.931174089068826,
3345
+ "grad_norm": 0.0,
3346
+ "learning_rate": 6.476681664419171e-07,
3347
+ "loss": 0.9919,
3348
+ "step": 477
3349
+ },
3350
+ {
3351
+ "epoch": 1.9352226720647774,
3352
+ "grad_norm": 0.0,
3353
+ "learning_rate": 5.737837882371922e-07,
3354
+ "loss": 0.9715,
3355
+ "step": 478
3356
+ },
3357
+ {
3358
+ "epoch": 1.9392712550607287,
3359
+ "grad_norm": 0.0,
3360
+ "learning_rate": 5.043606270295654e-07,
3361
+ "loss": 0.9596,
3362
+ "step": 479
3363
+ },
3364
+ {
3365
+ "epoch": 1.9433198380566803,
3366
+ "grad_norm": 0.0,
3367
+ "learning_rate": 4.3940179781019055e-07,
3368
+ "loss": 1.0135,
3369
+ "step": 480
3370
+ },
3371
+ {
3372
+ "epoch": 1.9473684210526314,
3373
+ "grad_norm": 0.0,
3374
+ "learning_rate": 3.789102152573665e-07,
3375
+ "loss": 0.9596,
3376
+ "step": 481
3377
+ },
3378
+ {
3379
+ "epoch": 1.951417004048583,
3380
+ "grad_norm": 0.0,
3381
+ "learning_rate": 3.228885936056858e-07,
3382
+ "loss": 0.9634,
3383
+ "step": 482
3384
+ },
3385
+ {
3386
+ "epoch": 1.9554655870445345,
3387
+ "grad_norm": 0.0,
3388
+ "learning_rate": 2.713394465242991e-07,
3389
+ "loss": 0.9619,
3390
+ "step": 483
3391
+ },
3392
+ {
3393
+ "epoch": 1.9595141700404857,
3394
+ "grad_norm": 0.0,
3395
+ "learning_rate": 2.242650870040497e-07,
3396
+ "loss": 0.9596,
3397
+ "step": 484
3398
+ },
3399
+ {
3400
+ "epoch": 1.9635627530364372,
3401
+ "grad_norm": 0.0,
3402
+ "learning_rate": 1.8166762725381203e-07,
3403
+ "loss": 0.9773,
3404
+ "step": 485
3405
+ },
3406
+ {
3407
+ "epoch": 1.9676113360323888,
3408
+ "grad_norm": 0.0,
3409
+ "learning_rate": 1.4354897860558992e-07,
3410
+ "loss": 0.9575,
3411
+ "step": 486
3412
+ },
3413
+ {
3414
+ "epoch": 1.97165991902834,
3415
+ "grad_norm": 0.0,
3416
+ "learning_rate": 1.0991085142886271e-07,
3417
+ "loss": 0.9505,
3418
+ "step": 487
3419
+ },
3420
+ {
3421
+ "epoch": 1.9757085020242915,
3422
+ "grad_norm": 0.0,
3423
+ "learning_rate": 8.075475505373575e-08,
3424
+ "loss": 0.9865,
3425
+ "step": 488
3426
+ },
3427
+ {
3428
+ "epoch": 1.979757085020243,
3429
+ "grad_norm": 0.0,
3430
+ "learning_rate": 5.608199770334999e-08,
3431
+ "loss": 0.9465,
3432
+ "step": 489
3433
+ },
3434
+ {
3435
+ "epoch": 1.9838056680161942,
3436
+ "grad_norm": 0.0,
3437
+ "learning_rate": 3.5893686435029e-08,
3438
+ "loss": 0.946,
3439
+ "step": 490
3440
+ },
3441
+ {
3442
+ "epoch": 1.9878542510121457,
3443
+ "grad_norm": 0.0,
3444
+ "learning_rate": 2.019072709074088e-08,
3445
+ "loss": 0.958,
3446
+ "step": 491
3447
+ },
3448
+ {
3449
+ "epoch": 1.9919028340080973,
3450
+ "grad_norm": 0.0,
3451
+ "learning_rate": 8.973824256364171e-09,
3452
+ "loss": 0.9399,
3453
+ "step": 492
3454
+ },
3455
+ {
3456
+ "epoch": 1.9959514170040484,
3457
+ "grad_norm": 0.0,
3458
+ "learning_rate": 2.2434812301352913e-09,
3459
+ "loss": 0.9116,
3460
+ "step": 493
3461
+ },
3462
+ {
3463
+ "epoch": 2.0,
3464
+ "grad_norm": 0.0,
3465
+ "learning_rate": 0.0,
3466
+ "loss": 0.9969,
3467
+ "step": 494
3468
+ }
3469
+ ],
3470
+ "logging_steps": 1,
3471
+ "max_steps": 494,
3472
+ "num_input_tokens_seen": 0,
3473
+ "num_train_epochs": 2,
3474
+ "save_steps": 100,
3475
+ "stateful_callbacks": {
3476
+ "TrainerControl": {
3477
+ "args": {
3478
+ "should_epoch_stop": false,
3479
+ "should_evaluate": false,
3480
+ "should_log": false,
3481
+ "should_save": true,
3482
+ "should_training_stop": true
3483
+ },
3484
+ "attributes": {}
3485
+ }
3486
+ },
3487
+ "total_flos": 2.9112171976175124e+18,
3488
+ "train_batch_size": 8,
3489
+ "trial_name": null,
3490
+ "trial_params": null
3491
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9cc4e6f4f6b959edca35448deccd3db394c4b3ff732c886ce1dec9613bc4d64
3
+ size 5624