LemTenku commited on
Commit
bc60eb7
·
verified ·
1 Parent(s): fccc3ff

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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/Meta-Llama-3.1-8B-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
+ "pad_token_id": 128004,
26
+ "pretraining_tp": 1,
27
+ "rms_norm_eps": 1e-05,
28
+ "rope_scaling": {
29
+ "factor": 8.0,
30
+ "high_freq_factor": 4.0,
31
+ "low_freq_factor": 1.0,
32
+ "original_max_position_embeddings": 8192,
33
+ "rope_type": "llama3"
34
+ },
35
+ "rope_theta": 500000.0,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "bfloat16",
38
+ "transformers_version": "4.46.1",
39
+ "unsloth_version": "2024.9",
40
+ "use_cache": false,
41
+ "vocab_size": 128256
42
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "max_length": 131072,
10
+ "pad_token_id": 128004,
11
+ "temperature": 0.6,
12
+ "top_p": 0.9,
13
+ "transformers_version": "4.46.1"
14
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6ce1450c3343a6220d20d17f6cbbcce751eadfb6e4c92ef1b99438f8aa1d273
3
+ size 4976694440
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8806491ffb3e049a4b60f56748a2f8d8545819832e07f3d15c0232d81dc764a
3
+ size 4999799520
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa080375b6d7505c64de48ccb50b1ae2f0cc370eb30bcddb8d3fcae41be542b4
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49bf72913aae1aaa62cbdad0e700661ffdd6734608e3c20c654394b80481910a
3
+ size 4221714168
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 19114090496
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-00003-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00003-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-00003-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-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-00003-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-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-00003-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-00003-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-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-00004-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00004-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-00004-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-00004-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-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-00004-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-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-00004-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00004-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-00004-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-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-00002-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-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 sha256:323e35dbf794ec9c4d73d7bb699e827c58699128d8aee09deb88dfa1b7f3791a
3
+ size 936
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67fcbf37e2292d5bb13bc3717341ad7a0a6a32c620d147778e6bb8c5a9d81ab4
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:324e4c13337d6fc191c14cd030c63f136555010f3f8ccdc2c98a498011809ae3
3
+ size 1000
special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eot_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|eom_id|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<|begin_of_text|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "<|eot_id|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": {
33
+ "content": "<|finetune_right_pad_id|>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
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 +1,2069 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [
2053
+ "<|eot_id|>",
2054
+ "<|eom_id|>"
2055
+ ],
2056
+ "bos_token": "<|begin_of_text|>",
2057
+ "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",
2058
+ "clean_up_tokenization_spaces": true,
2059
+ "eos_token": "<|eot_id|>",
2060
+ "model_input_names": [
2061
+ "input_ids",
2062
+ "attention_mask"
2063
+ ],
2064
+ "model_max_length": 8192,
2065
+ "pad_token": "<|finetune_right_pad_id|>",
2066
+ "padding_side": "right",
2067
+ "split_special_tokens": false,
2068
+ "tokenizer_class": "PreTrainedTokenizerFast"
2069
+ }
trainer_state.json ADDED
@@ -0,0 +1,3519 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.333511920707206,
5
+ "eval_steps": 500,
6
+ "global_step": 4980,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.000669702652022502,
13
+ "grad_norm": 0.0,
14
+ "learning_rate": 6.693440428380188e-07,
15
+ "loss": 2.3902,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.001339405304045004,
20
+ "grad_norm": 0.0,
21
+ "learning_rate": 1.3386880856760376e-06,
22
+ "loss": 2.4415,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.002009107956067506,
27
+ "grad_norm": 0.0,
28
+ "learning_rate": 2.0080321285140564e-06,
29
+ "loss": 2.3648,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.002678810608090008,
34
+ "grad_norm": 0.0,
35
+ "learning_rate": 2.6773761713520752e-06,
36
+ "loss": 2.2811,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.00334851326011251,
41
+ "grad_norm": 0.0,
42
+ "learning_rate": 3.346720214190094e-06,
43
+ "loss": 2.4023,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.004018215912135012,
48
+ "grad_norm": 0.0,
49
+ "learning_rate": 4.016064257028113e-06,
50
+ "loss": 2.3196,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.004687918564157514,
55
+ "grad_norm": 0.0,
56
+ "learning_rate": 4.685408299866132e-06,
57
+ "loss": 2.2711,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.005357621216180016,
62
+ "grad_norm": 0.0,
63
+ "learning_rate": 5.3547523427041504e-06,
64
+ "loss": 2.3224,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.006027323868202518,
69
+ "grad_norm": 0.0,
70
+ "learning_rate": 6.024096385542169e-06,
71
+ "loss": 2.287,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.00669702652022502,
76
+ "grad_norm": 0.0,
77
+ "learning_rate": 6.693440428380188e-06,
78
+ "loss": 2.2395,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.0073667291722475225,
83
+ "grad_norm": 0.0,
84
+ "learning_rate": 7.362784471218207e-06,
85
+ "loss": 2.3105,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.008036431824270024,
90
+ "grad_norm": 0.0,
91
+ "learning_rate": 8.032128514056226e-06,
92
+ "loss": 2.4276,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.008706134476292525,
97
+ "grad_norm": 0.0,
98
+ "learning_rate": 8.701472556894244e-06,
99
+ "loss": 2.3688,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.009375837128315028,
104
+ "grad_norm": 0.0,
105
+ "learning_rate": 9.370816599732263e-06,
106
+ "loss": 2.3826,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.01004553978033753,
111
+ "grad_norm": 0.0,
112
+ "learning_rate": 1.0040160642570281e-05,
113
+ "loss": 2.383,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.010715242432360031,
118
+ "grad_norm": 0.0,
119
+ "learning_rate": 1.0709504685408301e-05,
120
+ "loss": 2.3427,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.011384945084382534,
125
+ "grad_norm": 0.0,
126
+ "learning_rate": 1.1378848728246319e-05,
127
+ "loss": 2.2256,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.012054647736405036,
132
+ "grad_norm": 0.0,
133
+ "learning_rate": 1.2048192771084338e-05,
134
+ "loss": 2.3393,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.012724350388427539,
139
+ "grad_norm": 0.0,
140
+ "learning_rate": 1.2717536813922356e-05,
141
+ "loss": 2.3954,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.01339405304045004,
146
+ "grad_norm": 0.0,
147
+ "learning_rate": 1.3386880856760376e-05,
148
+ "loss": 2.2947,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.014063755692472542,
153
+ "grad_norm": 0.0,
154
+ "learning_rate": 1.4056224899598394e-05,
155
+ "loss": 2.2528,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.014733458344495045,
160
+ "grad_norm": 0.0,
161
+ "learning_rate": 1.4725568942436414e-05,
162
+ "loss": 2.2722,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.015403160996517546,
167
+ "grad_norm": 0.0,
168
+ "learning_rate": 1.5394912985274433e-05,
169
+ "loss": 2.3249,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.016072863648540048,
174
+ "grad_norm": 0.0,
175
+ "learning_rate": 1.606425702811245e-05,
176
+ "loss": 2.3077,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.01674256630056255,
181
+ "grad_norm": 0.0,
182
+ "learning_rate": 1.673360107095047e-05,
183
+ "loss": 2.3056,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.01741226895258505,
188
+ "grad_norm": 0.0,
189
+ "learning_rate": 1.7402945113788487e-05,
190
+ "loss": 2.3655,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.018081971604607554,
195
+ "grad_norm": 0.0,
196
+ "learning_rate": 1.8072289156626505e-05,
197
+ "loss": 2.2622,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.018751674256630057,
202
+ "grad_norm": 0.0,
203
+ "learning_rate": 1.8741633199464527e-05,
204
+ "loss": 2.2843,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.019421376908652557,
209
+ "grad_norm": 0.0,
210
+ "learning_rate": 1.9410977242302544e-05,
211
+ "loss": 2.1858,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.02009107956067506,
216
+ "grad_norm": 0.0,
217
+ "learning_rate": 2.0080321285140562e-05,
218
+ "loss": 2.3016,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.020760782212697563,
223
+ "grad_norm": 0.0,
224
+ "learning_rate": 2.074966532797858e-05,
225
+ "loss": 2.2798,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.021430484864720063,
230
+ "grad_norm": 0.0,
231
+ "learning_rate": 2.1419009370816602e-05,
232
+ "loss": 2.2639,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.022100187516742566,
237
+ "grad_norm": 0.0,
238
+ "learning_rate": 2.208835341365462e-05,
239
+ "loss": 2.2364,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.02276989016876507,
244
+ "grad_norm": 0.0,
245
+ "learning_rate": 2.2757697456492638e-05,
246
+ "loss": 2.2894,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.023439592820787572,
251
+ "grad_norm": 0.0,
252
+ "learning_rate": 2.3427041499330656e-05,
253
+ "loss": 2.3324,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.02410929547281007,
258
+ "grad_norm": 0.0,
259
+ "learning_rate": 2.4096385542168677e-05,
260
+ "loss": 2.3137,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.024778998124832575,
265
+ "grad_norm": 0.0,
266
+ "learning_rate": 2.4765729585006695e-05,
267
+ "loss": 2.2814,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.025448700776855078,
272
+ "grad_norm": 0.0,
273
+ "learning_rate": 2.5435073627844713e-05,
274
+ "loss": 2.3252,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.026118403428877578,
279
+ "grad_norm": 0.0,
280
+ "learning_rate": 2.6104417670682734e-05,
281
+ "loss": 2.3306,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.02678810608090008,
286
+ "grad_norm": 0.0,
287
+ "learning_rate": 2.6773761713520752e-05,
288
+ "loss": 2.3344,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.027457808732922584,
293
+ "grad_norm": 0.0,
294
+ "learning_rate": 2.7443105756358774e-05,
295
+ "loss": 2.2686,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.028127511384945084,
300
+ "grad_norm": 0.0,
301
+ "learning_rate": 2.8112449799196788e-05,
302
+ "loss": 2.2904,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.028797214036967587,
307
+ "grad_norm": 0.0,
308
+ "learning_rate": 2.878179384203481e-05,
309
+ "loss": 2.3387,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.02946691668899009,
314
+ "grad_norm": 0.0,
315
+ "learning_rate": 2.9451137884872827e-05,
316
+ "loss": 2.2865,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.03013661934101259,
321
+ "grad_norm": 0.0,
322
+ "learning_rate": 3.012048192771085e-05,
323
+ "loss": 2.2472,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.030806321993035093,
328
+ "grad_norm": 0.0,
329
+ "learning_rate": 3.078982597054887e-05,
330
+ "loss": 2.2773,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.031476024645057596,
335
+ "grad_norm": 0.0,
336
+ "learning_rate": 3.1459170013386885e-05,
337
+ "loss": 2.3224,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.032145727297080096,
342
+ "grad_norm": 0.0,
343
+ "learning_rate": 3.21285140562249e-05,
344
+ "loss": 2.1539,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.032815429949102595,
349
+ "grad_norm": 0.0,
350
+ "learning_rate": 3.279785809906292e-05,
351
+ "loss": 2.3025,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.0334851326011251,
356
+ "grad_norm": 0.0,
357
+ "learning_rate": 3.346720214190094e-05,
358
+ "loss": 2.2328,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.0341548352531476,
363
+ "grad_norm": 0.0,
364
+ "learning_rate": 3.413654618473896e-05,
365
+ "loss": 2.2389,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.0348245379051701,
370
+ "grad_norm": 0.0,
371
+ "learning_rate": 3.4805890227576974e-05,
372
+ "loss": 2.2465,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.03549424055719261,
377
+ "grad_norm": 0.0,
378
+ "learning_rate": 3.5475234270415e-05,
379
+ "loss": 2.2608,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.03616394320921511,
384
+ "grad_norm": 0.0,
385
+ "learning_rate": 3.614457831325301e-05,
386
+ "loss": 2.2254,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.03683364586123761,
391
+ "grad_norm": 0.0,
392
+ "learning_rate": 3.6813922356091035e-05,
393
+ "loss": 2.2041,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.037503348513260114,
398
+ "grad_norm": 0.0,
399
+ "learning_rate": 3.748326639892905e-05,
400
+ "loss": 2.3156,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.038173051165282613,
405
+ "grad_norm": 0.0,
406
+ "learning_rate": 3.815261044176707e-05,
407
+ "loss": 2.3493,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.03884275381730511,
412
+ "grad_norm": 0.0,
413
+ "learning_rate": 3.882195448460509e-05,
414
+ "loss": 2.2966,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.03951245646932762,
419
+ "grad_norm": 0.0,
420
+ "learning_rate": 3.949129852744311e-05,
421
+ "loss": 2.2741,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.04018215912135012,
426
+ "grad_norm": 0.0,
427
+ "learning_rate": 4.0160642570281125e-05,
428
+ "loss": 2.198,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.04085186177337262,
433
+ "grad_norm": 0.0,
434
+ "learning_rate": 4.082998661311915e-05,
435
+ "loss": 2.2987,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.041521564425395126,
440
+ "grad_norm": 0.0,
441
+ "learning_rate": 4.149933065595716e-05,
442
+ "loss": 2.3219,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.042191267077417625,
447
+ "grad_norm": 0.0,
448
+ "learning_rate": 4.2168674698795186e-05,
449
+ "loss": 2.2609,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.042860969729440125,
454
+ "grad_norm": 0.0,
455
+ "learning_rate": 4.2838018741633203e-05,
456
+ "loss": 2.1874,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.04353067238146263,
461
+ "grad_norm": 0.0,
462
+ "learning_rate": 4.350736278447122e-05,
463
+ "loss": 2.2077,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.04420037503348513,
468
+ "grad_norm": 0.0,
469
+ "learning_rate": 4.417670682730924e-05,
470
+ "loss": 2.187,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.04487007768550764,
475
+ "grad_norm": 0.0,
476
+ "learning_rate": 4.484605087014726e-05,
477
+ "loss": 2.2983,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.04553978033753014,
482
+ "grad_norm": 0.0,
483
+ "learning_rate": 4.5515394912985275e-05,
484
+ "loss": 2.3472,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.04620948298955264,
489
+ "grad_norm": 0.0,
490
+ "learning_rate": 4.61847389558233e-05,
491
+ "loss": 2.2707,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.046879185641575144,
496
+ "grad_norm": 0.0,
497
+ "learning_rate": 4.685408299866131e-05,
498
+ "loss": 2.3201,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.047548888293597644,
503
+ "grad_norm": 0.0,
504
+ "learning_rate": 4.7523427041499336e-05,
505
+ "loss": 2.2628,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.04821859094562014,
510
+ "grad_norm": 0.0,
511
+ "learning_rate": 4.8192771084337354e-05,
512
+ "loss": 2.3217,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.04888829359764265,
517
+ "grad_norm": 0.0,
518
+ "learning_rate": 4.886211512717537e-05,
519
+ "loss": 2.3157,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.04955799624966515,
524
+ "grad_norm": 0.0,
525
+ "learning_rate": 4.953145917001339e-05,
526
+ "loss": 2.2407,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.05022769890168765,
531
+ "grad_norm": 0.0,
532
+ "learning_rate": 5.020080321285141e-05,
533
+ "loss": 2.2607,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.050897401553710156,
538
+ "grad_norm": 0.0,
539
+ "learning_rate": 5.0870147255689426e-05,
540
+ "loss": 2.2192,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.051567104205732656,
545
+ "grad_norm": 0.0,
546
+ "learning_rate": 5.1539491298527444e-05,
547
+ "loss": 2.2501,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.052236806857755155,
552
+ "grad_norm": 0.0,
553
+ "learning_rate": 5.220883534136547e-05,
554
+ "loss": 2.2901,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.05290650950977766,
559
+ "grad_norm": 0.0,
560
+ "learning_rate": 5.2878179384203486e-05,
561
+ "loss": 2.2391,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.05357621216180016,
566
+ "grad_norm": 0.0,
567
+ "learning_rate": 5.3547523427041504e-05,
568
+ "loss": 2.2306,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.05424591481382266,
573
+ "grad_norm": 0.0,
574
+ "learning_rate": 5.4216867469879516e-05,
575
+ "loss": 2.322,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.05491561746584517,
580
+ "grad_norm": 0.0,
581
+ "learning_rate": 5.488621151271755e-05,
582
+ "loss": 2.2978,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.05558532011786767,
587
+ "grad_norm": 0.0,
588
+ "learning_rate": 5.555555555555556e-05,
589
+ "loss": 2.3016,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.05625502276989017,
594
+ "grad_norm": 0.0,
595
+ "learning_rate": 5.6224899598393576e-05,
596
+ "loss": 2.1525,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.056924725421912674,
601
+ "grad_norm": 0.0,
602
+ "learning_rate": 5.6894243641231594e-05,
603
+ "loss": 2.2663,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.057594428073935174,
608
+ "grad_norm": 0.0,
609
+ "learning_rate": 5.756358768406962e-05,
610
+ "loss": 2.2755,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.05826413072595767,
615
+ "grad_norm": 0.0,
616
+ "learning_rate": 5.823293172690764e-05,
617
+ "loss": 2.2842,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.05893383337798018,
622
+ "grad_norm": 0.0,
623
+ "learning_rate": 5.8902275769745655e-05,
624
+ "loss": 2.2635,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.05960353603000268,
629
+ "grad_norm": 0.0,
630
+ "learning_rate": 5.9571619812583666e-05,
631
+ "loss": 2.2726,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.06027323868202518,
636
+ "grad_norm": 0.0,
637
+ "learning_rate": 6.02409638554217e-05,
638
+ "loss": 2.2318,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.060942941334047686,
643
+ "grad_norm": 0.0,
644
+ "learning_rate": 6.091030789825971e-05,
645
+ "loss": 2.3523,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.061612643986070185,
650
+ "grad_norm": 0.0,
651
+ "learning_rate": 6.157965194109773e-05,
652
+ "loss": 2.317,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.062282346638092685,
657
+ "grad_norm": 0.0,
658
+ "learning_rate": 6.224899598393574e-05,
659
+ "loss": 2.1225,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.06295204929011519,
664
+ "grad_norm": 0.0,
665
+ "learning_rate": 6.291834002677377e-05,
666
+ "loss": 2.2357,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.06362175194213769,
671
+ "grad_norm": 0.0,
672
+ "learning_rate": 6.358768406961179e-05,
673
+ "loss": 2.2447,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.06429145459416019,
678
+ "grad_norm": 0.0,
679
+ "learning_rate": 6.42570281124498e-05,
680
+ "loss": 2.1638,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.06496115724618269,
685
+ "grad_norm": 0.0,
686
+ "learning_rate": 6.492637215528782e-05,
687
+ "loss": 2.1353,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.06563085989820519,
692
+ "grad_norm": 0.0,
693
+ "learning_rate": 6.559571619812584e-05,
694
+ "loss": 2.1564,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.0663005625502277,
699
+ "grad_norm": 0.0,
700
+ "learning_rate": 6.626506024096386e-05,
701
+ "loss": 2.1921,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.0669702652022502,
706
+ "grad_norm": 0.0,
707
+ "learning_rate": 6.693440428380188e-05,
708
+ "loss": 2.2064,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.0676399678542727,
713
+ "grad_norm": 0.0,
714
+ "learning_rate": 6.76037483266399e-05,
715
+ "loss": 2.223,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 0.0683096705062952,
720
+ "grad_norm": 0.0,
721
+ "learning_rate": 6.827309236947793e-05,
722
+ "loss": 2.3054,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 0.0689793731583177,
727
+ "grad_norm": 0.0,
728
+ "learning_rate": 6.894243641231593e-05,
729
+ "loss": 2.2002,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 0.0696490758103402,
734
+ "grad_norm": 0.0,
735
+ "learning_rate": 6.961178045515395e-05,
736
+ "loss": 2.249,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 0.07031877846236272,
741
+ "grad_norm": 0.0,
742
+ "learning_rate": 7.028112449799197e-05,
743
+ "loss": 2.1752,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 0.07098848111438522,
748
+ "grad_norm": 0.0,
749
+ "learning_rate": 7.095046854083e-05,
750
+ "loss": 2.2828,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 0.07165818376640772,
755
+ "grad_norm": 0.0,
756
+ "learning_rate": 7.161981258366802e-05,
757
+ "loss": 2.2456,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 0.07232788641843022,
762
+ "grad_norm": 0.0,
763
+ "learning_rate": 7.228915662650602e-05,
764
+ "loss": 2.3329,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 0.07299758907045271,
769
+ "grad_norm": 0.0,
770
+ "learning_rate": 7.295850066934404e-05,
771
+ "loss": 2.2911,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 0.07366729172247521,
776
+ "grad_norm": 0.0,
777
+ "learning_rate": 7.362784471218207e-05,
778
+ "loss": 2.3092,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 0.07433699437449773,
783
+ "grad_norm": 0.0,
784
+ "learning_rate": 7.429718875502009e-05,
785
+ "loss": 2.3058,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 0.07500669702652023,
790
+ "grad_norm": 0.0,
791
+ "learning_rate": 7.49665327978581e-05,
792
+ "loss": 2.3024,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 0.07567639967854273,
797
+ "grad_norm": 0.0,
798
+ "learning_rate": 7.563587684069612e-05,
799
+ "loss": 2.3491,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 0.07634610233056523,
804
+ "grad_norm": 0.0,
805
+ "learning_rate": 7.630522088353414e-05,
806
+ "loss": 2.3675,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 0.07701580498258773,
811
+ "grad_norm": 0.0,
812
+ "learning_rate": 7.697456492637216e-05,
813
+ "loss": 2.3257,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 0.07768550763461023,
818
+ "grad_norm": 0.0,
819
+ "learning_rate": 7.764390896921018e-05,
820
+ "loss": 2.3037,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 0.07835521028663274,
825
+ "grad_norm": 0.0,
826
+ "learning_rate": 7.83132530120482e-05,
827
+ "loss": 2.2627,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 0.07902491293865524,
832
+ "grad_norm": 0.0,
833
+ "learning_rate": 7.898259705488621e-05,
834
+ "loss": 2.3351,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 0.07969461559067774,
839
+ "grad_norm": 0.0,
840
+ "learning_rate": 7.965194109772423e-05,
841
+ "loss": 2.2829,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 0.08036431824270024,
846
+ "grad_norm": 0.0,
847
+ "learning_rate": 8.032128514056225e-05,
848
+ "loss": 2.2612,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 0.08103402089472274,
853
+ "grad_norm": 0.0,
854
+ "learning_rate": 8.099062918340027e-05,
855
+ "loss": 2.2377,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 0.08170372354674524,
860
+ "grad_norm": 0.0,
861
+ "learning_rate": 8.16599732262383e-05,
862
+ "loss": 2.2353,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 0.08237342619876775,
867
+ "grad_norm": 0.0,
868
+ "learning_rate": 8.232931726907632e-05,
869
+ "loss": 2.2509,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 0.08304312885079025,
874
+ "grad_norm": 0.0,
875
+ "learning_rate": 8.299866131191432e-05,
876
+ "loss": 2.2449,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 0.08371283150281275,
881
+ "grad_norm": 0.0,
882
+ "learning_rate": 8.366800535475234e-05,
883
+ "loss": 2.2076,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 0.08438253415483525,
888
+ "grad_norm": 0.0,
889
+ "learning_rate": 8.433734939759037e-05,
890
+ "loss": 2.2714,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 0.08505223680685775,
895
+ "grad_norm": 0.0,
896
+ "learning_rate": 8.500669344042839e-05,
897
+ "loss": 2.2424,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 0.08572193945888025,
902
+ "grad_norm": 0.0,
903
+ "learning_rate": 8.567603748326641e-05,
904
+ "loss": 2.2711,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 0.08639164211090276,
909
+ "grad_norm": 0.0,
910
+ "learning_rate": 8.634538152610442e-05,
911
+ "loss": 2.2266,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 0.08706134476292526,
916
+ "grad_norm": 0.0,
917
+ "learning_rate": 8.701472556894244e-05,
918
+ "loss": 2.2329,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 0.08773104741494776,
923
+ "grad_norm": 0.0,
924
+ "learning_rate": 8.768406961178046e-05,
925
+ "loss": 2.2388,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 0.08840075006697026,
930
+ "grad_norm": 0.0,
931
+ "learning_rate": 8.835341365461848e-05,
932
+ "loss": 2.3047,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 0.08907045271899276,
937
+ "grad_norm": 0.0,
938
+ "learning_rate": 8.90227576974565e-05,
939
+ "loss": 2.2679,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 0.08974015537101528,
944
+ "grad_norm": 0.0,
945
+ "learning_rate": 8.969210174029451e-05,
946
+ "loss": 2.3128,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 0.09040985802303778,
951
+ "grad_norm": 0.0,
952
+ "learning_rate": 9.036144578313253e-05,
953
+ "loss": 2.2134,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 0.09107956067506028,
958
+ "grad_norm": 0.0,
959
+ "learning_rate": 9.103078982597055e-05,
960
+ "loss": 2.2883,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 0.09174926332708278,
965
+ "grad_norm": 0.0,
966
+ "learning_rate": 9.170013386880857e-05,
967
+ "loss": 2.2464,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 0.09241896597910527,
972
+ "grad_norm": 0.0,
973
+ "learning_rate": 9.23694779116466e-05,
974
+ "loss": 2.2318,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 0.09308866863112777,
979
+ "grad_norm": 0.0,
980
+ "learning_rate": 9.303882195448462e-05,
981
+ "loss": 2.229,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 0.09375837128315029,
986
+ "grad_norm": 0.0,
987
+ "learning_rate": 9.370816599732262e-05,
988
+ "loss": 2.2054,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 0.09442807393517279,
993
+ "grad_norm": 0.0,
994
+ "learning_rate": 9.437751004016064e-05,
995
+ "loss": 2.2667,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 0.09509777658719529,
1000
+ "grad_norm": 0.0,
1001
+ "learning_rate": 9.504685408299867e-05,
1002
+ "loss": 2.2674,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 0.09576747923921779,
1007
+ "grad_norm": 0.0,
1008
+ "learning_rate": 9.571619812583669e-05,
1009
+ "loss": 2.2865,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 0.09643718189124029,
1014
+ "grad_norm": 0.0,
1015
+ "learning_rate": 9.638554216867471e-05,
1016
+ "loss": 2.2337,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 0.09710688454326279,
1021
+ "grad_norm": 0.0,
1022
+ "learning_rate": 9.705488621151271e-05,
1023
+ "loss": 2.291,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 0.0977765871952853,
1028
+ "grad_norm": 0.0,
1029
+ "learning_rate": 9.772423025435074e-05,
1030
+ "loss": 2.3411,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 0.0984462898473078,
1035
+ "grad_norm": 0.0,
1036
+ "learning_rate": 9.839357429718876e-05,
1037
+ "loss": 2.1827,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 0.0991159924993303,
1042
+ "grad_norm": 0.0,
1043
+ "learning_rate": 9.906291834002678e-05,
1044
+ "loss": 2.1987,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 0.0997856951513528,
1049
+ "grad_norm": 0.0,
1050
+ "learning_rate": 9.97322623828648e-05,
1051
+ "loss": 2.2079,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 0.1004553978033753,
1056
+ "grad_norm": 0.0,
1057
+ "learning_rate": 9.999995081044314e-05,
1058
+ "loss": 2.2484,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 0.1011251004553978,
1063
+ "grad_norm": 0.0,
1064
+ "learning_rate": 9.999965020794615e-05,
1065
+ "loss": 2.3123,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 0.10179480310742031,
1070
+ "grad_norm": 0.0,
1071
+ "learning_rate": 9.99990763321247e-05,
1072
+ "loss": 2.2429,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 0.10246450575944281,
1077
+ "grad_norm": 0.0,
1078
+ "learning_rate": 9.999822918611533e-05,
1079
+ "loss": 2.2205,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 0.10313420841146531,
1084
+ "grad_norm": 0.0,
1085
+ "learning_rate": 9.999710877454811e-05,
1086
+ "loss": 2.2077,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 0.10380391106348781,
1091
+ "grad_norm": 0.0,
1092
+ "learning_rate": 9.999571510354664e-05,
1093
+ "loss": 2.3028,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 0.10447361371551031,
1098
+ "grad_norm": 0.0,
1099
+ "learning_rate": 9.999404818072808e-05,
1100
+ "loss": 2.252,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 0.10514331636753281,
1105
+ "grad_norm": 0.0,
1106
+ "learning_rate": 9.999210801520296e-05,
1107
+ "loss": 2.3754,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 0.10581301901955532,
1112
+ "grad_norm": 0.0,
1113
+ "learning_rate": 9.998989461757526e-05,
1114
+ "loss": 2.2761,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 0.10648272167157782,
1119
+ "grad_norm": 0.0,
1120
+ "learning_rate": 9.998740799994235e-05,
1121
+ "loss": 2.2168,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 0.10715242432360032,
1126
+ "grad_norm": 0.0,
1127
+ "learning_rate": 9.998464817589484e-05,
1128
+ "loss": 2.2639,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 0.10782212697562282,
1133
+ "grad_norm": 0.0,
1134
+ "learning_rate": 9.998161516051656e-05,
1135
+ "loss": 2.2687,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 0.10849182962764532,
1140
+ "grad_norm": 0.0,
1141
+ "learning_rate": 9.997830897038446e-05,
1142
+ "loss": 2.2239,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 0.10916153227966782,
1147
+ "grad_norm": 0.0,
1148
+ "learning_rate": 9.997472962356854e-05,
1149
+ "loss": 2.1802,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 0.10983123493169034,
1154
+ "grad_norm": 0.0,
1155
+ "learning_rate": 9.997087713963174e-05,
1156
+ "loss": 2.2154,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 0.11050093758371284,
1161
+ "grad_norm": 0.0,
1162
+ "learning_rate": 9.996675153962984e-05,
1163
+ "loss": 2.212,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 0.11117064023573534,
1168
+ "grad_norm": 0.0,
1169
+ "learning_rate": 9.996235284611131e-05,
1170
+ "loss": 2.251,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 0.11184034288775783,
1175
+ "grad_norm": 0.0,
1176
+ "learning_rate": 9.995768108311722e-05,
1177
+ "loss": 2.299,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 0.11251004553978033,
1182
+ "grad_norm": 0.0,
1183
+ "learning_rate": 9.995273627618116e-05,
1184
+ "loss": 2.2021,
1185
+ "step": 1680
1186
+ },
1187
+ {
1188
+ "epoch": 0.11317974819180283,
1189
+ "grad_norm": 0.0,
1190
+ "learning_rate": 9.994751845232894e-05,
1191
+ "loss": 2.244,
1192
+ "step": 1690
1193
+ },
1194
+ {
1195
+ "epoch": 0.11384945084382535,
1196
+ "grad_norm": 0.0,
1197
+ "learning_rate": 9.994202764007865e-05,
1198
+ "loss": 2.3063,
1199
+ "step": 1700
1200
+ },
1201
+ {
1202
+ "epoch": 0.11451915349584785,
1203
+ "grad_norm": 0.0,
1204
+ "learning_rate": 9.993626386944031e-05,
1205
+ "loss": 2.2809,
1206
+ "step": 1710
1207
+ },
1208
+ {
1209
+ "epoch": 0.11518885614787035,
1210
+ "grad_norm": 0.0,
1211
+ "learning_rate": 9.993022717191584e-05,
1212
+ "loss": 2.2767,
1213
+ "step": 1720
1214
+ },
1215
+ {
1216
+ "epoch": 0.11585855879989285,
1217
+ "grad_norm": 0.0,
1218
+ "learning_rate": 9.992391758049889e-05,
1219
+ "loss": 2.2354,
1220
+ "step": 1730
1221
+ },
1222
+ {
1223
+ "epoch": 0.11652826145191535,
1224
+ "grad_norm": 0.0,
1225
+ "learning_rate": 9.99173351296745e-05,
1226
+ "loss": 2.2889,
1227
+ "step": 1740
1228
+ },
1229
+ {
1230
+ "epoch": 0.11719796410393785,
1231
+ "grad_norm": 0.0,
1232
+ "learning_rate": 9.99104798554191e-05,
1233
+ "loss": 2.22,
1234
+ "step": 1750
1235
+ },
1236
+ {
1237
+ "epoch": 0.11786766675596036,
1238
+ "grad_norm": 0.0,
1239
+ "learning_rate": 9.990335179520023e-05,
1240
+ "loss": 2.2941,
1241
+ "step": 1760
1242
+ },
1243
+ {
1244
+ "epoch": 0.11853736940798286,
1245
+ "grad_norm": 0.0,
1246
+ "learning_rate": 9.989595098797635e-05,
1247
+ "loss": 2.2584,
1248
+ "step": 1770
1249
+ },
1250
+ {
1251
+ "epoch": 0.11920707206000536,
1252
+ "grad_norm": 0.0,
1253
+ "learning_rate": 9.988827747419659e-05,
1254
+ "loss": 2.2408,
1255
+ "step": 1780
1256
+ },
1257
+ {
1258
+ "epoch": 0.11987677471202786,
1259
+ "grad_norm": 0.0,
1260
+ "learning_rate": 9.988033129580059e-05,
1261
+ "loss": 2.1831,
1262
+ "step": 1790
1263
+ },
1264
+ {
1265
+ "epoch": 0.12054647736405036,
1266
+ "grad_norm": 0.0,
1267
+ "learning_rate": 9.98721124962182e-05,
1268
+ "loss": 2.2853,
1269
+ "step": 1800
1270
+ },
1271
+ {
1272
+ "epoch": 0.12121618001607286,
1273
+ "grad_norm": 0.0,
1274
+ "learning_rate": 9.986362112036935e-05,
1275
+ "loss": 2.2537,
1276
+ "step": 1810
1277
+ },
1278
+ {
1279
+ "epoch": 0.12188588266809537,
1280
+ "grad_norm": 0.0,
1281
+ "learning_rate": 9.985485721466366e-05,
1282
+ "loss": 2.2257,
1283
+ "step": 1820
1284
+ },
1285
+ {
1286
+ "epoch": 0.12255558532011787,
1287
+ "grad_norm": 0.0,
1288
+ "learning_rate": 9.984582082700029e-05,
1289
+ "loss": 2.3031,
1290
+ "step": 1830
1291
+ },
1292
+ {
1293
+ "epoch": 0.12322528797214037,
1294
+ "grad_norm": 0.0,
1295
+ "learning_rate": 9.98365120067677e-05,
1296
+ "loss": 2.2435,
1297
+ "step": 1840
1298
+ },
1299
+ {
1300
+ "epoch": 0.12389499062416287,
1301
+ "grad_norm": 0.0,
1302
+ "learning_rate": 9.982693080484327e-05,
1303
+ "loss": 2.1834,
1304
+ "step": 1850
1305
+ },
1306
+ {
1307
+ "epoch": 0.12456469327618537,
1308
+ "grad_norm": 0.0,
1309
+ "learning_rate": 9.981707727359308e-05,
1310
+ "loss": 2.2215,
1311
+ "step": 1860
1312
+ },
1313
+ {
1314
+ "epoch": 0.12523439592820787,
1315
+ "grad_norm": 0.0,
1316
+ "learning_rate": 9.98069514668717e-05,
1317
+ "loss": 2.3128,
1318
+ "step": 1870
1319
+ },
1320
+ {
1321
+ "epoch": 0.12590409858023038,
1322
+ "grad_norm": 0.0,
1323
+ "learning_rate": 9.979655344002172e-05,
1324
+ "loss": 2.2512,
1325
+ "step": 1880
1326
+ },
1327
+ {
1328
+ "epoch": 0.12657380123225287,
1329
+ "grad_norm": 0.0,
1330
+ "learning_rate": 9.978588324987365e-05,
1331
+ "loss": 2.2278,
1332
+ "step": 1890
1333
+ },
1334
+ {
1335
+ "epoch": 0.12724350388427538,
1336
+ "grad_norm": 0.0,
1337
+ "learning_rate": 9.977494095474546e-05,
1338
+ "loss": 2.2445,
1339
+ "step": 1900
1340
+ },
1341
+ {
1342
+ "epoch": 0.1279132065362979,
1343
+ "grad_norm": 0.0,
1344
+ "learning_rate": 9.97637266144423e-05,
1345
+ "loss": 2.2834,
1346
+ "step": 1910
1347
+ },
1348
+ {
1349
+ "epoch": 0.12858290918832038,
1350
+ "grad_norm": 0.0,
1351
+ "learning_rate": 9.975224029025619e-05,
1352
+ "loss": 2.2807,
1353
+ "step": 1920
1354
+ },
1355
+ {
1356
+ "epoch": 0.1292526118403429,
1357
+ "grad_norm": 0.0,
1358
+ "learning_rate": 9.974048204496572e-05,
1359
+ "loss": 2.3837,
1360
+ "step": 1930
1361
+ },
1362
+ {
1363
+ "epoch": 0.12992231449236538,
1364
+ "grad_norm": 0.0,
1365
+ "learning_rate": 9.97284519428356e-05,
1366
+ "loss": 2.2318,
1367
+ "step": 1940
1368
+ },
1369
+ {
1370
+ "epoch": 0.1305920171443879,
1371
+ "grad_norm": 0.0,
1372
+ "learning_rate": 9.971615004961645e-05,
1373
+ "loss": 2.1961,
1374
+ "step": 1950
1375
+ },
1376
+ {
1377
+ "epoch": 0.13126171979641038,
1378
+ "grad_norm": 0.0,
1379
+ "learning_rate": 9.970357643254429e-05,
1380
+ "loss": 2.301,
1381
+ "step": 1960
1382
+ },
1383
+ {
1384
+ "epoch": 0.1319314224484329,
1385
+ "grad_norm": 0.0,
1386
+ "learning_rate": 9.96907311603403e-05,
1387
+ "loss": 2.2454,
1388
+ "step": 1970
1389
+ },
1390
+ {
1391
+ "epoch": 0.1326011251004554,
1392
+ "grad_norm": 0.0,
1393
+ "learning_rate": 9.967761430321037e-05,
1394
+ "loss": 2.2505,
1395
+ "step": 1980
1396
+ },
1397
+ {
1398
+ "epoch": 0.1332708277524779,
1399
+ "grad_norm": 0.0,
1400
+ "learning_rate": 9.966422593284474e-05,
1401
+ "loss": 2.2103,
1402
+ "step": 1990
1403
+ },
1404
+ {
1405
+ "epoch": 0.1339405304045004,
1406
+ "grad_norm": 0.0,
1407
+ "learning_rate": 9.965056612241764e-05,
1408
+ "loss": 2.3467,
1409
+ "step": 2000
1410
+ },
1411
+ {
1412
+ "epoch": 0.1346102330565229,
1413
+ "grad_norm": 0.0,
1414
+ "learning_rate": 9.963663494658681e-05,
1415
+ "loss": 2.174,
1416
+ "step": 2010
1417
+ },
1418
+ {
1419
+ "epoch": 0.1352799357085454,
1420
+ "grad_norm": 0.0,
1421
+ "learning_rate": 9.962243248149314e-05,
1422
+ "loss": 2.3771,
1423
+ "step": 2020
1424
+ },
1425
+ {
1426
+ "epoch": 0.13594963836056792,
1427
+ "grad_norm": 0.0,
1428
+ "learning_rate": 9.960795880476029e-05,
1429
+ "loss": 2.3623,
1430
+ "step": 2030
1431
+ },
1432
+ {
1433
+ "epoch": 0.1366193410125904,
1434
+ "grad_norm": 0.0,
1435
+ "learning_rate": 9.95932139954942e-05,
1436
+ "loss": 2.27,
1437
+ "step": 2040
1438
+ },
1439
+ {
1440
+ "epoch": 0.13728904366461292,
1441
+ "grad_norm": 0.0,
1442
+ "learning_rate": 9.95781981342827e-05,
1443
+ "loss": 2.2534,
1444
+ "step": 2050
1445
+ },
1446
+ {
1447
+ "epoch": 0.1379587463166354,
1448
+ "grad_norm": 0.0,
1449
+ "learning_rate": 9.956291130319506e-05,
1450
+ "loss": 2.2726,
1451
+ "step": 2060
1452
+ },
1453
+ {
1454
+ "epoch": 0.13862844896865792,
1455
+ "grad_norm": 0.0,
1456
+ "learning_rate": 9.95473535857815e-05,
1457
+ "loss": 2.3065,
1458
+ "step": 2070
1459
+ },
1460
+ {
1461
+ "epoch": 0.1392981516206804,
1462
+ "grad_norm": 0.0,
1463
+ "learning_rate": 9.953152506707283e-05,
1464
+ "loss": 2.1472,
1465
+ "step": 2080
1466
+ },
1467
+ {
1468
+ "epoch": 0.13996785427270292,
1469
+ "grad_norm": 0.0,
1470
+ "learning_rate": 9.951542583357986e-05,
1471
+ "loss": 2.2893,
1472
+ "step": 2090
1473
+ },
1474
+ {
1475
+ "epoch": 0.14063755692472543,
1476
+ "grad_norm": 0.0,
1477
+ "learning_rate": 9.949905597329306e-05,
1478
+ "loss": 2.1606,
1479
+ "step": 2100
1480
+ },
1481
+ {
1482
+ "epoch": 0.14130725957674792,
1483
+ "grad_norm": 0.0,
1484
+ "learning_rate": 9.948241557568196e-05,
1485
+ "loss": 2.2155,
1486
+ "step": 2110
1487
+ },
1488
+ {
1489
+ "epoch": 0.14197696222877043,
1490
+ "grad_norm": 0.0,
1491
+ "learning_rate": 9.946550473169474e-05,
1492
+ "loss": 2.2544,
1493
+ "step": 2120
1494
+ },
1495
+ {
1496
+ "epoch": 0.14264666488079292,
1497
+ "grad_norm": 0.0,
1498
+ "learning_rate": 9.944832353375769e-05,
1499
+ "loss": 2.2661,
1500
+ "step": 2130
1501
+ },
1502
+ {
1503
+ "epoch": 0.14331636753281543,
1504
+ "grad_norm": 0.0,
1505
+ "learning_rate": 9.943087207577473e-05,
1506
+ "loss": 2.2873,
1507
+ "step": 2140
1508
+ },
1509
+ {
1510
+ "epoch": 0.14398607018483794,
1511
+ "grad_norm": 0.0,
1512
+ "learning_rate": 9.941315045312689e-05,
1513
+ "loss": 2.2044,
1514
+ "step": 2150
1515
+ },
1516
+ {
1517
+ "epoch": 0.14465577283686043,
1518
+ "grad_norm": 0.0,
1519
+ "learning_rate": 9.939515876267178e-05,
1520
+ "loss": 2.3315,
1521
+ "step": 2160
1522
+ },
1523
+ {
1524
+ "epoch": 0.14532547548888294,
1525
+ "grad_norm": 0.0,
1526
+ "learning_rate": 9.937689710274308e-05,
1527
+ "loss": 2.2413,
1528
+ "step": 2170
1529
+ },
1530
+ {
1531
+ "epoch": 0.14599517814090543,
1532
+ "grad_norm": 0.0,
1533
+ "learning_rate": 9.935836557314995e-05,
1534
+ "loss": 2.2494,
1535
+ "step": 2180
1536
+ },
1537
+ {
1538
+ "epoch": 0.14666488079292794,
1539
+ "grad_norm": 0.0,
1540
+ "learning_rate": 9.933956427517657e-05,
1541
+ "loss": 2.2623,
1542
+ "step": 2190
1543
+ },
1544
+ {
1545
+ "epoch": 0.14733458344495043,
1546
+ "grad_norm": 0.0,
1547
+ "learning_rate": 9.932049331158153e-05,
1548
+ "loss": 2.2775,
1549
+ "step": 2200
1550
+ },
1551
+ {
1552
+ "epoch": 0.14800428609697294,
1553
+ "grad_norm": 0.0,
1554
+ "learning_rate": 9.930115278659727e-05,
1555
+ "loss": 2.1811,
1556
+ "step": 2210
1557
+ },
1558
+ {
1559
+ "epoch": 0.14867398874899546,
1560
+ "grad_norm": 0.0,
1561
+ "learning_rate": 9.928154280592952e-05,
1562
+ "loss": 2.2731,
1563
+ "step": 2220
1564
+ },
1565
+ {
1566
+ "epoch": 0.14934369140101794,
1567
+ "grad_norm": 0.0,
1568
+ "learning_rate": 9.92616634767567e-05,
1569
+ "loss": 2.2588,
1570
+ "step": 2230
1571
+ },
1572
+ {
1573
+ "epoch": 0.15001339405304046,
1574
+ "grad_norm": 0.0,
1575
+ "learning_rate": 9.924151490772942e-05,
1576
+ "loss": 2.2073,
1577
+ "step": 2240
1578
+ },
1579
+ {
1580
+ "epoch": 0.15068309670506294,
1581
+ "grad_norm": 0.0,
1582
+ "learning_rate": 9.922109720896973e-05,
1583
+ "loss": 2.2965,
1584
+ "step": 2250
1585
+ },
1586
+ {
1587
+ "epoch": 0.15135279935708545,
1588
+ "grad_norm": 0.0,
1589
+ "learning_rate": 9.92004104920707e-05,
1590
+ "loss": 2.1766,
1591
+ "step": 2260
1592
+ },
1593
+ {
1594
+ "epoch": 0.15202250200910797,
1595
+ "grad_norm": 0.0,
1596
+ "learning_rate": 9.917945487009566e-05,
1597
+ "loss": 2.2915,
1598
+ "step": 2270
1599
+ },
1600
+ {
1601
+ "epoch": 0.15269220466113045,
1602
+ "grad_norm": 0.0,
1603
+ "learning_rate": 9.915823045757765e-05,
1604
+ "loss": 2.2717,
1605
+ "step": 2280
1606
+ },
1607
+ {
1608
+ "epoch": 0.15336190731315297,
1609
+ "grad_norm": 0.0,
1610
+ "learning_rate": 9.913673737051882e-05,
1611
+ "loss": 2.2301,
1612
+ "step": 2290
1613
+ },
1614
+ {
1615
+ "epoch": 0.15403160996517545,
1616
+ "grad_norm": 0.0,
1617
+ "learning_rate": 9.911497572638973e-05,
1618
+ "loss": 2.2289,
1619
+ "step": 2300
1620
+ },
1621
+ {
1622
+ "epoch": 0.15470131261719797,
1623
+ "grad_norm": 0.0,
1624
+ "learning_rate": 9.909294564412874e-05,
1625
+ "loss": 2.3655,
1626
+ "step": 2310
1627
+ },
1628
+ {
1629
+ "epoch": 0.15537101526922045,
1630
+ "grad_norm": 0.0,
1631
+ "learning_rate": 9.907064724414139e-05,
1632
+ "loss": 2.1503,
1633
+ "step": 2320
1634
+ },
1635
+ {
1636
+ "epoch": 0.15604071792124297,
1637
+ "grad_norm": 0.0,
1638
+ "learning_rate": 9.904808064829967e-05,
1639
+ "loss": 2.2254,
1640
+ "step": 2330
1641
+ },
1642
+ {
1643
+ "epoch": 0.15671042057326548,
1644
+ "grad_norm": 0.0,
1645
+ "learning_rate": 9.902524597994143e-05,
1646
+ "loss": 2.28,
1647
+ "step": 2340
1648
+ },
1649
+ {
1650
+ "epoch": 0.15738012322528797,
1651
+ "grad_norm": 0.0,
1652
+ "learning_rate": 9.900214336386964e-05,
1653
+ "loss": 2.18,
1654
+ "step": 2350
1655
+ },
1656
+ {
1657
+ "epoch": 0.15804982587731048,
1658
+ "grad_norm": 0.0,
1659
+ "learning_rate": 9.897877292635179e-05,
1660
+ "loss": 2.3032,
1661
+ "step": 2360
1662
+ },
1663
+ {
1664
+ "epoch": 0.15871952852933296,
1665
+ "grad_norm": 0.0,
1666
+ "learning_rate": 9.895513479511907e-05,
1667
+ "loss": 2.2472,
1668
+ "step": 2370
1669
+ },
1670
+ {
1671
+ "epoch": 0.15938923118135548,
1672
+ "grad_norm": 0.0,
1673
+ "learning_rate": 9.893122909936583e-05,
1674
+ "loss": 2.1331,
1675
+ "step": 2380
1676
+ },
1677
+ {
1678
+ "epoch": 0.160058933833378,
1679
+ "grad_norm": 0.0,
1680
+ "learning_rate": 9.890705596974875e-05,
1681
+ "loss": 2.1931,
1682
+ "step": 2390
1683
+ },
1684
+ {
1685
+ "epoch": 0.16072863648540048,
1686
+ "grad_norm": 0.0,
1687
+ "learning_rate": 9.88826155383862e-05,
1688
+ "loss": 2.2551,
1689
+ "step": 2400
1690
+ },
1691
+ {
1692
+ "epoch": 0.161398339137423,
1693
+ "grad_norm": 0.0,
1694
+ "learning_rate": 9.885790793885746e-05,
1695
+ "loss": 2.1717,
1696
+ "step": 2410
1697
+ },
1698
+ {
1699
+ "epoch": 0.16206804178944548,
1700
+ "grad_norm": 0.0,
1701
+ "learning_rate": 9.883293330620205e-05,
1702
+ "loss": 2.2582,
1703
+ "step": 2420
1704
+ },
1705
+ {
1706
+ "epoch": 0.162737744441468,
1707
+ "grad_norm": 0.0,
1708
+ "learning_rate": 9.880769177691892e-05,
1709
+ "loss": 2.2466,
1710
+ "step": 2430
1711
+ },
1712
+ {
1713
+ "epoch": 0.16340744709349048,
1714
+ "grad_norm": 0.0,
1715
+ "learning_rate": 9.878218348896577e-05,
1716
+ "loss": 2.2734,
1717
+ "step": 2440
1718
+ },
1719
+ {
1720
+ "epoch": 0.164077149745513,
1721
+ "grad_norm": 0.0,
1722
+ "learning_rate": 9.875640858175827e-05,
1723
+ "loss": 2.3381,
1724
+ "step": 2450
1725
+ },
1726
+ {
1727
+ "epoch": 0.1647468523975355,
1728
+ "grad_norm": 0.0,
1729
+ "learning_rate": 9.87303671961693e-05,
1730
+ "loss": 2.2529,
1731
+ "step": 2460
1732
+ },
1733
+ {
1734
+ "epoch": 0.165416555049558,
1735
+ "grad_norm": 0.0,
1736
+ "learning_rate": 9.870405947452819e-05,
1737
+ "loss": 2.2889,
1738
+ "step": 2470
1739
+ },
1740
+ {
1741
+ "epoch": 0.1660862577015805,
1742
+ "grad_norm": 0.0,
1743
+ "learning_rate": 9.86774855606199e-05,
1744
+ "loss": 2.1831,
1745
+ "step": 2480
1746
+ },
1747
+ {
1748
+ "epoch": 0.166755960353603,
1749
+ "grad_norm": 0.0,
1750
+ "learning_rate": 9.86506455996843e-05,
1751
+ "loss": 2.2241,
1752
+ "step": 2490
1753
+ },
1754
+ {
1755
+ "epoch": 0.1674256630056255,
1756
+ "grad_norm": 0.0,
1757
+ "learning_rate": 9.862353973841526e-05,
1758
+ "loss": 2.2539,
1759
+ "step": 2500
1760
+ },
1761
+ {
1762
+ "epoch": 0.16809536565764802,
1763
+ "grad_norm": 0.0,
1764
+ "learning_rate": 9.859616812496008e-05,
1765
+ "loss": 2.263,
1766
+ "step": 2510
1767
+ },
1768
+ {
1769
+ "epoch": 0.1687650683096705,
1770
+ "grad_norm": 0.0,
1771
+ "learning_rate": 9.856853090891843e-05,
1772
+ "loss": 2.2179,
1773
+ "step": 2520
1774
+ },
1775
+ {
1776
+ "epoch": 0.16943477096169302,
1777
+ "grad_norm": 0.0,
1778
+ "learning_rate": 9.854062824134159e-05,
1779
+ "loss": 2.2326,
1780
+ "step": 2530
1781
+ },
1782
+ {
1783
+ "epoch": 0.1701044736137155,
1784
+ "grad_norm": 0.0,
1785
+ "learning_rate": 9.851246027473173e-05,
1786
+ "loss": 2.3374,
1787
+ "step": 2540
1788
+ },
1789
+ {
1790
+ "epoch": 0.17077417626573801,
1791
+ "grad_norm": 0.0,
1792
+ "learning_rate": 9.848402716304106e-05,
1793
+ "loss": 2.2265,
1794
+ "step": 2550
1795
+ },
1796
+ {
1797
+ "epoch": 0.1714438789177605,
1798
+ "grad_norm": 0.0,
1799
+ "learning_rate": 9.845532906167083e-05,
1800
+ "loss": 2.1868,
1801
+ "step": 2560
1802
+ },
1803
+ {
1804
+ "epoch": 0.17211358156978301,
1805
+ "grad_norm": 0.0,
1806
+ "learning_rate": 9.842636612747069e-05,
1807
+ "loss": 2.2097,
1808
+ "step": 2570
1809
+ },
1810
+ {
1811
+ "epoch": 0.17278328422180553,
1812
+ "grad_norm": 0.0,
1813
+ "learning_rate": 9.839713851873766e-05,
1814
+ "loss": 2.2601,
1815
+ "step": 2580
1816
+ },
1817
+ {
1818
+ "epoch": 0.173452986873828,
1819
+ "grad_norm": 0.0,
1820
+ "learning_rate": 9.836764639521539e-05,
1821
+ "loss": 2.2559,
1822
+ "step": 2590
1823
+ },
1824
+ {
1825
+ "epoch": 0.17412268952585053,
1826
+ "grad_norm": 0.0,
1827
+ "learning_rate": 9.833788991809323e-05,
1828
+ "loss": 2.2896,
1829
+ "step": 2600
1830
+ },
1831
+ {
1832
+ "epoch": 0.174792392177873,
1833
+ "grad_norm": 0.0,
1834
+ "learning_rate": 9.830786925000533e-05,
1835
+ "loss": 2.2095,
1836
+ "step": 2610
1837
+ },
1838
+ {
1839
+ "epoch": 0.17546209482989553,
1840
+ "grad_norm": 0.0,
1841
+ "learning_rate": 9.827758455502978e-05,
1842
+ "loss": 2.206,
1843
+ "step": 2620
1844
+ },
1845
+ {
1846
+ "epoch": 0.17613179748191804,
1847
+ "grad_norm": 0.0,
1848
+ "learning_rate": 9.824703599868776e-05,
1849
+ "loss": 2.3201,
1850
+ "step": 2630
1851
+ },
1852
+ {
1853
+ "epoch": 0.17680150013394053,
1854
+ "grad_norm": 0.0,
1855
+ "learning_rate": 9.821622374794253e-05,
1856
+ "loss": 2.2804,
1857
+ "step": 2640
1858
+ },
1859
+ {
1860
+ "epoch": 0.17747120278596304,
1861
+ "grad_norm": 0.0,
1862
+ "learning_rate": 9.81851479711986e-05,
1863
+ "loss": 2.1435,
1864
+ "step": 2650
1865
+ },
1866
+ {
1867
+ "epoch": 0.17814090543798553,
1868
+ "grad_norm": 0.0,
1869
+ "learning_rate": 9.815380883830076e-05,
1870
+ "loss": 2.1878,
1871
+ "step": 2660
1872
+ },
1873
+ {
1874
+ "epoch": 0.17881060809000804,
1875
+ "grad_norm": 0.0,
1876
+ "learning_rate": 9.812220652053318e-05,
1877
+ "loss": 2.3302,
1878
+ "step": 2670
1879
+ },
1880
+ {
1881
+ "epoch": 0.17948031074203055,
1882
+ "grad_norm": 0.0,
1883
+ "learning_rate": 9.80903411906185e-05,
1884
+ "loss": 2.2151,
1885
+ "step": 2680
1886
+ },
1887
+ {
1888
+ "epoch": 0.18015001339405304,
1889
+ "grad_norm": 0.0,
1890
+ "learning_rate": 9.805821302271685e-05,
1891
+ "loss": 2.2155,
1892
+ "step": 2690
1893
+ },
1894
+ {
1895
+ "epoch": 0.18081971604607555,
1896
+ "grad_norm": 0.0,
1897
+ "learning_rate": 9.802582219242484e-05,
1898
+ "loss": 2.2942,
1899
+ "step": 2700
1900
+ },
1901
+ {
1902
+ "epoch": 0.18148941869809804,
1903
+ "grad_norm": 0.0,
1904
+ "learning_rate": 9.799316887677471e-05,
1905
+ "loss": 2.2229,
1906
+ "step": 2710
1907
+ },
1908
+ {
1909
+ "epoch": 0.18215912135012055,
1910
+ "grad_norm": 0.0,
1911
+ "learning_rate": 9.796025325423334e-05,
1912
+ "loss": 2.2516,
1913
+ "step": 2720
1914
+ },
1915
+ {
1916
+ "epoch": 0.18282882400214304,
1917
+ "grad_norm": 0.0,
1918
+ "learning_rate": 9.792707550470122e-05,
1919
+ "loss": 2.1446,
1920
+ "step": 2730
1921
+ },
1922
+ {
1923
+ "epoch": 0.18349852665416555,
1924
+ "grad_norm": 0.0,
1925
+ "learning_rate": 9.789363580951145e-05,
1926
+ "loss": 2.2074,
1927
+ "step": 2740
1928
+ },
1929
+ {
1930
+ "epoch": 0.18416822930618806,
1931
+ "grad_norm": 0.0,
1932
+ "learning_rate": 9.785993435142891e-05,
1933
+ "loss": 2.236,
1934
+ "step": 2750
1935
+ },
1936
+ {
1937
+ "epoch": 0.18483793195821055,
1938
+ "grad_norm": 0.0,
1939
+ "learning_rate": 9.782597131464901e-05,
1940
+ "loss": 2.2744,
1941
+ "step": 2760
1942
+ },
1943
+ {
1944
+ "epoch": 0.18550763461023306,
1945
+ "grad_norm": 0.0,
1946
+ "learning_rate": 9.779174688479693e-05,
1947
+ "loss": 2.2472,
1948
+ "step": 2770
1949
+ },
1950
+ {
1951
+ "epoch": 0.18617733726225555,
1952
+ "grad_norm": 0.0,
1953
+ "learning_rate": 9.775726124892646e-05,
1954
+ "loss": 2.4463,
1955
+ "step": 2780
1956
+ },
1957
+ {
1958
+ "epoch": 0.18684703991427806,
1959
+ "grad_norm": 0.0,
1960
+ "learning_rate": 9.772251459551897e-05,
1961
+ "loss": 2.1792,
1962
+ "step": 2790
1963
+ },
1964
+ {
1965
+ "epoch": 0.18751674256630058,
1966
+ "grad_norm": 0.0,
1967
+ "learning_rate": 9.768750711448249e-05,
1968
+ "loss": 2.2459,
1969
+ "step": 2800
1970
+ },
1971
+ {
1972
+ "epoch": 0.18818644521832306,
1973
+ "grad_norm": 0.0,
1974
+ "learning_rate": 9.765223899715054e-05,
1975
+ "loss": 2.1656,
1976
+ "step": 2810
1977
+ },
1978
+ {
1979
+ "epoch": 0.18885614787034558,
1980
+ "grad_norm": 0.0,
1981
+ "learning_rate": 9.761671043628124e-05,
1982
+ "loss": 2.3268,
1983
+ "step": 2820
1984
+ },
1985
+ {
1986
+ "epoch": 0.18952585052236806,
1987
+ "grad_norm": 0.0,
1988
+ "learning_rate": 9.758092162605604e-05,
1989
+ "loss": 2.2815,
1990
+ "step": 2830
1991
+ },
1992
+ {
1993
+ "epoch": 0.19019555317439057,
1994
+ "grad_norm": 0.0,
1995
+ "learning_rate": 9.754487276207889e-05,
1996
+ "loss": 2.2414,
1997
+ "step": 2840
1998
+ },
1999
+ {
2000
+ "epoch": 0.19086525582641306,
2001
+ "grad_norm": 0.0,
2002
+ "learning_rate": 9.750856404137502e-05,
2003
+ "loss": 2.1398,
2004
+ "step": 2850
2005
+ },
2006
+ {
2007
+ "epoch": 0.19153495847843557,
2008
+ "grad_norm": 0.0,
2009
+ "learning_rate": 9.747199566238991e-05,
2010
+ "loss": 2.2683,
2011
+ "step": 2860
2012
+ },
2013
+ {
2014
+ "epoch": 0.1922046611304581,
2015
+ "grad_norm": 0.0,
2016
+ "learning_rate": 9.743516782498822e-05,
2017
+ "loss": 2.1707,
2018
+ "step": 2870
2019
+ },
2020
+ {
2021
+ "epoch": 0.19287436378248057,
2022
+ "grad_norm": 0.0,
2023
+ "learning_rate": 9.739808073045264e-05,
2024
+ "loss": 2.3202,
2025
+ "step": 2880
2026
+ },
2027
+ {
2028
+ "epoch": 0.1935440664345031,
2029
+ "grad_norm": 0.0,
2030
+ "learning_rate": 9.73607345814829e-05,
2031
+ "loss": 2.2712,
2032
+ "step": 2890
2033
+ },
2034
+ {
2035
+ "epoch": 0.19421376908652557,
2036
+ "grad_norm": 0.0,
2037
+ "learning_rate": 9.732312958219453e-05,
2038
+ "loss": 2.2749,
2039
+ "step": 2900
2040
+ },
2041
+ {
2042
+ "epoch": 0.1948834717385481,
2043
+ "grad_norm": 0.0,
2044
+ "learning_rate": 9.728526593811783e-05,
2045
+ "loss": 2.1855,
2046
+ "step": 2910
2047
+ },
2048
+ {
2049
+ "epoch": 0.1955531743905706,
2050
+ "grad_norm": 0.0,
2051
+ "learning_rate": 9.724714385619673e-05,
2052
+ "loss": 2.1736,
2053
+ "step": 2920
2054
+ },
2055
+ {
2056
+ "epoch": 0.19622287704259309,
2057
+ "grad_norm": 0.0,
2058
+ "learning_rate": 9.720876354478765e-05,
2059
+ "loss": 2.2247,
2060
+ "step": 2930
2061
+ },
2062
+ {
2063
+ "epoch": 0.1968925796946156,
2064
+ "grad_norm": 0.0,
2065
+ "learning_rate": 9.717012521365836e-05,
2066
+ "loss": 2.2102,
2067
+ "step": 2940
2068
+ },
2069
+ {
2070
+ "epoch": 0.19756228234663809,
2071
+ "grad_norm": 0.0,
2072
+ "learning_rate": 9.713122907398686e-05,
2073
+ "loss": 2.275,
2074
+ "step": 2950
2075
+ },
2076
+ {
2077
+ "epoch": 0.1982319849986606,
2078
+ "grad_norm": 0.0,
2079
+ "learning_rate": 9.709207533836016e-05,
2080
+ "loss": 2.0444,
2081
+ "step": 2960
2082
+ },
2083
+ {
2084
+ "epoch": 0.19890168765068308,
2085
+ "grad_norm": 0.0,
2086
+ "learning_rate": 9.70526642207732e-05,
2087
+ "loss": 2.2226,
2088
+ "step": 2970
2089
+ },
2090
+ {
2091
+ "epoch": 0.1995713903027056,
2092
+ "grad_norm": 0.0,
2093
+ "learning_rate": 9.701299593662763e-05,
2094
+ "loss": 2.2936,
2095
+ "step": 2980
2096
+ },
2097
+ {
2098
+ "epoch": 0.2002410929547281,
2099
+ "grad_norm": 0.0,
2100
+ "learning_rate": 9.697307070273062e-05,
2101
+ "loss": 2.2361,
2102
+ "step": 2990
2103
+ },
2104
+ {
2105
+ "epoch": 0.2009107956067506,
2106
+ "grad_norm": 0.0,
2107
+ "learning_rate": 9.693288873729376e-05,
2108
+ "loss": 2.1928,
2109
+ "step": 3000
2110
+ },
2111
+ {
2112
+ "epoch": 0.2015804982587731,
2113
+ "grad_norm": 0.0,
2114
+ "learning_rate": 9.689245025993175e-05,
2115
+ "loss": 2.185,
2116
+ "step": 3010
2117
+ },
2118
+ {
2119
+ "epoch": 0.2022502009107956,
2120
+ "grad_norm": 0.0,
2121
+ "learning_rate": 9.68517554916613e-05,
2122
+ "loss": 2.1397,
2123
+ "step": 3020
2124
+ },
2125
+ {
2126
+ "epoch": 0.2029199035628181,
2127
+ "grad_norm": 0.0,
2128
+ "learning_rate": 9.681080465489983e-05,
2129
+ "loss": 2.3028,
2130
+ "step": 3030
2131
+ },
2132
+ {
2133
+ "epoch": 0.20358960621484062,
2134
+ "grad_norm": 0.0,
2135
+ "learning_rate": 9.676959797346435e-05,
2136
+ "loss": 2.2324,
2137
+ "step": 3040
2138
+ },
2139
+ {
2140
+ "epoch": 0.2042593088668631,
2141
+ "grad_norm": 0.0,
2142
+ "learning_rate": 9.672813567257017e-05,
2143
+ "loss": 2.2146,
2144
+ "step": 3050
2145
+ },
2146
+ {
2147
+ "epoch": 0.20492901151888562,
2148
+ "grad_norm": 0.0,
2149
+ "learning_rate": 9.668641797882969e-05,
2150
+ "loss": 2.1497,
2151
+ "step": 3060
2152
+ },
2153
+ {
2154
+ "epoch": 0.2055987141709081,
2155
+ "grad_norm": 0.0,
2156
+ "learning_rate": 9.664444512025116e-05,
2157
+ "loss": 2.2361,
2158
+ "step": 3070
2159
+ },
2160
+ {
2161
+ "epoch": 0.20626841682293062,
2162
+ "grad_norm": 0.0,
2163
+ "learning_rate": 9.660221732623744e-05,
2164
+ "loss": 2.2336,
2165
+ "step": 3080
2166
+ },
2167
+ {
2168
+ "epoch": 0.2069381194749531,
2169
+ "grad_norm": 0.0,
2170
+ "learning_rate": 9.655973482758473e-05,
2171
+ "loss": 2.2446,
2172
+ "step": 3090
2173
+ },
2174
+ {
2175
+ "epoch": 0.20760782212697562,
2176
+ "grad_norm": 0.0,
2177
+ "learning_rate": 9.651699785648135e-05,
2178
+ "loss": 2.2724,
2179
+ "step": 3100
2180
+ },
2181
+ {
2182
+ "epoch": 0.20827752477899814,
2183
+ "grad_norm": 0.0,
2184
+ "learning_rate": 9.647400664650638e-05,
2185
+ "loss": 2.2362,
2186
+ "step": 3110
2187
+ },
2188
+ {
2189
+ "epoch": 0.20894722743102062,
2190
+ "grad_norm": 0.0,
2191
+ "learning_rate": 9.643076143262851e-05,
2192
+ "loss": 2.2481,
2193
+ "step": 3120
2194
+ },
2195
+ {
2196
+ "epoch": 0.20961693008304313,
2197
+ "grad_norm": 0.0,
2198
+ "learning_rate": 9.638726245120466e-05,
2199
+ "loss": 2.1208,
2200
+ "step": 3130
2201
+ },
2202
+ {
2203
+ "epoch": 0.21028663273506562,
2204
+ "grad_norm": 0.0,
2205
+ "learning_rate": 9.634350993997871e-05,
2206
+ "loss": 2.2085,
2207
+ "step": 3140
2208
+ },
2209
+ {
2210
+ "epoch": 0.21095633538708813,
2211
+ "grad_norm": 0.0,
2212
+ "learning_rate": 9.629950413808022e-05,
2213
+ "loss": 2.2974,
2214
+ "step": 3150
2215
+ },
2216
+ {
2217
+ "epoch": 0.21162603803911065,
2218
+ "grad_norm": 0.0,
2219
+ "learning_rate": 9.62552452860231e-05,
2220
+ "loss": 2.2781,
2221
+ "step": 3160
2222
+ },
2223
+ {
2224
+ "epoch": 0.21229574069113313,
2225
+ "grad_norm": 0.0,
2226
+ "learning_rate": 9.621073362570432e-05,
2227
+ "loss": 2.3054,
2228
+ "step": 3170
2229
+ },
2230
+ {
2231
+ "epoch": 0.21296544334315565,
2232
+ "grad_norm": 0.0,
2233
+ "learning_rate": 9.616596940040257e-05,
2234
+ "loss": 2.1255,
2235
+ "step": 3180
2236
+ },
2237
+ {
2238
+ "epoch": 0.21363514599517813,
2239
+ "grad_norm": 0.0,
2240
+ "learning_rate": 9.612095285477694e-05,
2241
+ "loss": 2.1918,
2242
+ "step": 3190
2243
+ },
2244
+ {
2245
+ "epoch": 0.21430484864720065,
2246
+ "grad_norm": 0.0,
2247
+ "learning_rate": 9.607568423486558e-05,
2248
+ "loss": 2.2317,
2249
+ "step": 3200
2250
+ },
2251
+ {
2252
+ "epoch": 0.21497455129922313,
2253
+ "grad_norm": 0.0,
2254
+ "learning_rate": 9.603016378808432e-05,
2255
+ "loss": 2.0927,
2256
+ "step": 3210
2257
+ },
2258
+ {
2259
+ "epoch": 0.21564425395124565,
2260
+ "grad_norm": 0.0,
2261
+ "learning_rate": 9.59843917632254e-05,
2262
+ "loss": 2.2694,
2263
+ "step": 3220
2264
+ },
2265
+ {
2266
+ "epoch": 0.21631395660326816,
2267
+ "grad_norm": 0.0,
2268
+ "learning_rate": 9.593836841045602e-05,
2269
+ "loss": 2.2625,
2270
+ "step": 3230
2271
+ },
2272
+ {
2273
+ "epoch": 0.21698365925529065,
2274
+ "grad_norm": 0.0,
2275
+ "learning_rate": 9.589209398131706e-05,
2276
+ "loss": 2.3238,
2277
+ "step": 3240
2278
+ },
2279
+ {
2280
+ "epoch": 0.21765336190731316,
2281
+ "grad_norm": 0.0,
2282
+ "learning_rate": 9.584556872872159e-05,
2283
+ "loss": 2.2813,
2284
+ "step": 3250
2285
+ },
2286
+ {
2287
+ "epoch": 0.21832306455933564,
2288
+ "grad_norm": 0.0,
2289
+ "learning_rate": 9.579879290695364e-05,
2290
+ "loss": 2.2298,
2291
+ "step": 3260
2292
+ },
2293
+ {
2294
+ "epoch": 0.21899276721135816,
2295
+ "grad_norm": 0.0,
2296
+ "learning_rate": 9.575176677166667e-05,
2297
+ "loss": 2.2254,
2298
+ "step": 3270
2299
+ },
2300
+ {
2301
+ "epoch": 0.21966246986338067,
2302
+ "grad_norm": 0.0,
2303
+ "learning_rate": 9.570449057988222e-05,
2304
+ "loss": 2.3366,
2305
+ "step": 3280
2306
+ },
2307
+ {
2308
+ "epoch": 0.22033217251540316,
2309
+ "grad_norm": 0.0,
2310
+ "learning_rate": 9.565696458998858e-05,
2311
+ "loss": 2.2601,
2312
+ "step": 3290
2313
+ },
2314
+ {
2315
+ "epoch": 0.22100187516742567,
2316
+ "grad_norm": 0.0,
2317
+ "learning_rate": 9.560918906173923e-05,
2318
+ "loss": 2.231,
2319
+ "step": 3300
2320
+ },
2321
+ {
2322
+ "epoch": 0.22167157781944816,
2323
+ "grad_norm": 0.0,
2324
+ "learning_rate": 9.556116425625159e-05,
2325
+ "loss": 2.2668,
2326
+ "step": 3310
2327
+ },
2328
+ {
2329
+ "epoch": 0.22234128047147067,
2330
+ "grad_norm": 0.0,
2331
+ "learning_rate": 9.551289043600542e-05,
2332
+ "loss": 2.2073,
2333
+ "step": 3320
2334
+ },
2335
+ {
2336
+ "epoch": 0.22301098312349316,
2337
+ "grad_norm": 0.0,
2338
+ "learning_rate": 9.546436786484155e-05,
2339
+ "loss": 2.3307,
2340
+ "step": 3330
2341
+ },
2342
+ {
2343
+ "epoch": 0.22368068577551567,
2344
+ "grad_norm": 0.0,
2345
+ "learning_rate": 9.541559680796029e-05,
2346
+ "loss": 2.2272,
2347
+ "step": 3340
2348
+ },
2349
+ {
2350
+ "epoch": 0.22435038842753818,
2351
+ "grad_norm": 0.0,
2352
+ "learning_rate": 9.536657753192011e-05,
2353
+ "loss": 2.2672,
2354
+ "step": 3350
2355
+ },
2356
+ {
2357
+ "epoch": 0.22502009107956067,
2358
+ "grad_norm": 0.0,
2359
+ "learning_rate": 9.531731030463607e-05,
2360
+ "loss": 2.2473,
2361
+ "step": 3360
2362
+ },
2363
+ {
2364
+ "epoch": 0.22568979373158318,
2365
+ "grad_norm": 0.0,
2366
+ "learning_rate": 9.526779539537845e-05,
2367
+ "loss": 2.2187,
2368
+ "step": 3370
2369
+ },
2370
+ {
2371
+ "epoch": 0.22635949638360567,
2372
+ "grad_norm": 0.0,
2373
+ "learning_rate": 9.52180330747712e-05,
2374
+ "loss": 2.3373,
2375
+ "step": 3380
2376
+ },
2377
+ {
2378
+ "epoch": 0.22702919903562818,
2379
+ "grad_norm": 0.0,
2380
+ "learning_rate": 9.516802361479056e-05,
2381
+ "loss": 2.1831,
2382
+ "step": 3390
2383
+ },
2384
+ {
2385
+ "epoch": 0.2276989016876507,
2386
+ "grad_norm": 0.0,
2387
+ "learning_rate": 9.511776728876341e-05,
2388
+ "loss": 2.1993,
2389
+ "step": 3400
2390
+ },
2391
+ {
2392
+ "epoch": 0.22836860433967318,
2393
+ "grad_norm": 0.0,
2394
+ "learning_rate": 9.506726437136599e-05,
2395
+ "loss": 2.1827,
2396
+ "step": 3410
2397
+ },
2398
+ {
2399
+ "epoch": 0.2290383069916957,
2400
+ "grad_norm": 0.0,
2401
+ "learning_rate": 9.501651513862222e-05,
2402
+ "loss": 2.2418,
2403
+ "step": 3420
2404
+ },
2405
+ {
2406
+ "epoch": 0.22970800964371818,
2407
+ "grad_norm": 0.0,
2408
+ "learning_rate": 9.496551986790225e-05,
2409
+ "loss": 2.1535,
2410
+ "step": 3430
2411
+ },
2412
+ {
2413
+ "epoch": 0.2303777122957407,
2414
+ "grad_norm": 0.0,
2415
+ "learning_rate": 9.4914278837921e-05,
2416
+ "loss": 2.37,
2417
+ "step": 3440
2418
+ },
2419
+ {
2420
+ "epoch": 0.23104741494776318,
2421
+ "grad_norm": 0.0,
2422
+ "learning_rate": 9.486279232873654e-05,
2423
+ "loss": 2.1839,
2424
+ "step": 3450
2425
+ },
2426
+ {
2427
+ "epoch": 0.2317171175997857,
2428
+ "grad_norm": 0.0,
2429
+ "learning_rate": 9.481106062174863e-05,
2430
+ "loss": 2.2899,
2431
+ "step": 3460
2432
+ },
2433
+ {
2434
+ "epoch": 0.2323868202518082,
2435
+ "grad_norm": 0.0,
2436
+ "learning_rate": 9.475908399969718e-05,
2437
+ "loss": 2.2152,
2438
+ "step": 3470
2439
+ },
2440
+ {
2441
+ "epoch": 0.2330565229038307,
2442
+ "grad_norm": 0.0,
2443
+ "learning_rate": 9.470686274666065e-05,
2444
+ "loss": 2.2035,
2445
+ "step": 3480
2446
+ },
2447
+ {
2448
+ "epoch": 0.2337262255558532,
2449
+ "grad_norm": 0.0,
2450
+ "learning_rate": 9.465439714805455e-05,
2451
+ "loss": 2.2696,
2452
+ "step": 3490
2453
+ },
2454
+ {
2455
+ "epoch": 0.2343959282078757,
2456
+ "grad_norm": 0.0,
2457
+ "learning_rate": 9.460168749062985e-05,
2458
+ "loss": 2.2141,
2459
+ "step": 3500
2460
+ },
2461
+ {
2462
+ "epoch": 0.2350656308598982,
2463
+ "grad_norm": 0.0,
2464
+ "learning_rate": 9.454873406247143e-05,
2465
+ "loss": 2.2786,
2466
+ "step": 3510
2467
+ },
2468
+ {
2469
+ "epoch": 0.23573533351192072,
2470
+ "grad_norm": 0.0,
2471
+ "learning_rate": 9.449553715299652e-05,
2472
+ "loss": 2.2578,
2473
+ "step": 3520
2474
+ },
2475
+ {
2476
+ "epoch": 0.2364050361639432,
2477
+ "grad_norm": 0.0,
2478
+ "learning_rate": 9.444209705295305e-05,
2479
+ "loss": 2.2044,
2480
+ "step": 3530
2481
+ },
2482
+ {
2483
+ "epoch": 0.23707473881596572,
2484
+ "grad_norm": 0.0,
2485
+ "learning_rate": 9.438841405441816e-05,
2486
+ "loss": 2.2658,
2487
+ "step": 3540
2488
+ },
2489
+ {
2490
+ "epoch": 0.2377444414679882,
2491
+ "grad_norm": 0.0,
2492
+ "learning_rate": 9.433448845079653e-05,
2493
+ "loss": 2.2988,
2494
+ "step": 3550
2495
+ },
2496
+ {
2497
+ "epoch": 0.23841414412001072,
2498
+ "grad_norm": 0.0,
2499
+ "learning_rate": 9.42803205368188e-05,
2500
+ "loss": 2.2158,
2501
+ "step": 3560
2502
+ },
2503
+ {
2504
+ "epoch": 0.2390838467720332,
2505
+ "grad_norm": 0.0,
2506
+ "learning_rate": 9.422591060853997e-05,
2507
+ "loss": 2.3033,
2508
+ "step": 3570
2509
+ },
2510
+ {
2511
+ "epoch": 0.23975354942405572,
2512
+ "grad_norm": 0.0,
2513
+ "learning_rate": 9.417125896333774e-05,
2514
+ "loss": 2.3241,
2515
+ "step": 3580
2516
+ },
2517
+ {
2518
+ "epoch": 0.24042325207607823,
2519
+ "grad_norm": 0.0,
2520
+ "learning_rate": 9.411636589991095e-05,
2521
+ "loss": 2.2695,
2522
+ "step": 3590
2523
+ },
2524
+ {
2525
+ "epoch": 0.24109295472810072,
2526
+ "grad_norm": 0.0,
2527
+ "learning_rate": 9.406123171827789e-05,
2528
+ "loss": 2.2711,
2529
+ "step": 3600
2530
+ },
2531
+ {
2532
+ "epoch": 0.24176265738012323,
2533
+ "grad_norm": 0.0,
2534
+ "learning_rate": 9.400585671977469e-05,
2535
+ "loss": 2.1886,
2536
+ "step": 3610
2537
+ },
2538
+ {
2539
+ "epoch": 0.24243236003214572,
2540
+ "grad_norm": 0.0,
2541
+ "learning_rate": 9.395024120705367e-05,
2542
+ "loss": 2.2764,
2543
+ "step": 3620
2544
+ },
2545
+ {
2546
+ "epoch": 0.24310206268416823,
2547
+ "grad_norm": 0.0,
2548
+ "learning_rate": 9.389438548408167e-05,
2549
+ "loss": 2.1141,
2550
+ "step": 3630
2551
+ },
2552
+ {
2553
+ "epoch": 0.24377176533619074,
2554
+ "grad_norm": 0.0,
2555
+ "learning_rate": 9.383828985613843e-05,
2556
+ "loss": 2.2824,
2557
+ "step": 3640
2558
+ },
2559
+ {
2560
+ "epoch": 0.24444146798821323,
2561
+ "grad_norm": 0.0,
2562
+ "learning_rate": 9.378195462981484e-05,
2563
+ "loss": 2.2951,
2564
+ "step": 3650
2565
+ },
2566
+ {
2567
+ "epoch": 0.24511117064023574,
2568
+ "grad_norm": 0.0,
2569
+ "learning_rate": 9.372538011301135e-05,
2570
+ "loss": 2.2363,
2571
+ "step": 3660
2572
+ },
2573
+ {
2574
+ "epoch": 0.24578087329225823,
2575
+ "grad_norm": 0.0,
2576
+ "learning_rate": 9.366856661493628e-05,
2577
+ "loss": 2.2701,
2578
+ "step": 3670
2579
+ },
2580
+ {
2581
+ "epoch": 0.24645057594428074,
2582
+ "grad_norm": 0.0,
2583
+ "learning_rate": 9.361151444610404e-05,
2584
+ "loss": 2.2683,
2585
+ "step": 3680
2586
+ },
2587
+ {
2588
+ "epoch": 0.24712027859630323,
2589
+ "grad_norm": 0.0,
2590
+ "learning_rate": 9.355422391833353e-05,
2591
+ "loss": 2.3463,
2592
+ "step": 3690
2593
+ },
2594
+ {
2595
+ "epoch": 0.24778998124832574,
2596
+ "grad_norm": 0.0,
2597
+ "learning_rate": 9.349669534474641e-05,
2598
+ "loss": 2.2302,
2599
+ "step": 3700
2600
+ },
2601
+ {
2602
+ "epoch": 0.24845968390034825,
2603
+ "grad_norm": 0.0,
2604
+ "learning_rate": 9.343892903976539e-05,
2605
+ "loss": 2.2496,
2606
+ "step": 3710
2607
+ },
2608
+ {
2609
+ "epoch": 0.24912938655237074,
2610
+ "grad_norm": 0.0,
2611
+ "learning_rate": 9.338092531911245e-05,
2612
+ "loss": 2.2797,
2613
+ "step": 3720
2614
+ },
2615
+ {
2616
+ "epoch": 0.24979908920439325,
2617
+ "grad_norm": 0.0,
2618
+ "learning_rate": 9.33226844998072e-05,
2619
+ "loss": 2.2403,
2620
+ "step": 3730
2621
+ },
2622
+ {
2623
+ "epoch": 0.25046879185641574,
2624
+ "grad_norm": 0.0,
2625
+ "learning_rate": 9.326420690016513e-05,
2626
+ "loss": 2.1988,
2627
+ "step": 3740
2628
+ },
2629
+ {
2630
+ "epoch": 0.2511384945084382,
2631
+ "grad_norm": 0.0,
2632
+ "learning_rate": 9.320549283979584e-05,
2633
+ "loss": 2.249,
2634
+ "step": 3750
2635
+ },
2636
+ {
2637
+ "epoch": 0.25180819716046077,
2638
+ "grad_norm": 0.0,
2639
+ "learning_rate": 9.314654263960128e-05,
2640
+ "loss": 2.2201,
2641
+ "step": 3760
2642
+ },
2643
+ {
2644
+ "epoch": 0.25247789981248325,
2645
+ "grad_norm": 0.0,
2646
+ "learning_rate": 9.308735662177407e-05,
2647
+ "loss": 2.2789,
2648
+ "step": 3770
2649
+ },
2650
+ {
2651
+ "epoch": 0.25314760246450574,
2652
+ "grad_norm": 0.0,
2653
+ "learning_rate": 9.302793510979568e-05,
2654
+ "loss": 2.2515,
2655
+ "step": 3780
2656
+ },
2657
+ {
2658
+ "epoch": 0.2538173051165283,
2659
+ "grad_norm": 0.0,
2660
+ "learning_rate": 9.296827842843463e-05,
2661
+ "loss": 2.2134,
2662
+ "step": 3790
2663
+ },
2664
+ {
2665
+ "epoch": 0.25448700776855077,
2666
+ "grad_norm": 0.0,
2667
+ "learning_rate": 9.290838690374483e-05,
2668
+ "loss": 2.2498,
2669
+ "step": 3800
2670
+ },
2671
+ {
2672
+ "epoch": 0.25515671042057325,
2673
+ "grad_norm": 0.0,
2674
+ "learning_rate": 9.284826086306366e-05,
2675
+ "loss": 2.1802,
2676
+ "step": 3810
2677
+ },
2678
+ {
2679
+ "epoch": 0.2558264130725958,
2680
+ "grad_norm": 0.0,
2681
+ "learning_rate": 9.278790063501029e-05,
2682
+ "loss": 2.2067,
2683
+ "step": 3820
2684
+ },
2685
+ {
2686
+ "epoch": 0.2564961157246183,
2687
+ "grad_norm": 0.0,
2688
+ "learning_rate": 9.272730654948384e-05,
2689
+ "loss": 2.2824,
2690
+ "step": 3830
2691
+ },
2692
+ {
2693
+ "epoch": 0.25716581837664076,
2694
+ "grad_norm": 0.0,
2695
+ "learning_rate": 9.266647893766157e-05,
2696
+ "loss": 2.2489,
2697
+ "step": 3840
2698
+ },
2699
+ {
2700
+ "epoch": 0.25783552102866325,
2701
+ "grad_norm": 0.0,
2702
+ "learning_rate": 9.260541813199706e-05,
2703
+ "loss": 2.2607,
2704
+ "step": 3850
2705
+ },
2706
+ {
2707
+ "epoch": 0.2585052236806858,
2708
+ "grad_norm": 0.0,
2709
+ "learning_rate": 9.254412446621845e-05,
2710
+ "loss": 2.3607,
2711
+ "step": 3860
2712
+ },
2713
+ {
2714
+ "epoch": 0.2591749263327083,
2715
+ "grad_norm": 0.0,
2716
+ "learning_rate": 9.248259827532656e-05,
2717
+ "loss": 2.2326,
2718
+ "step": 3870
2719
+ },
2720
+ {
2721
+ "epoch": 0.25984462898473076,
2722
+ "grad_norm": 0.0,
2723
+ "learning_rate": 9.242083989559308e-05,
2724
+ "loss": 2.2679,
2725
+ "step": 3880
2726
+ },
2727
+ {
2728
+ "epoch": 0.2605143316367533,
2729
+ "grad_norm": 0.0,
2730
+ "learning_rate": 9.235884966455872e-05,
2731
+ "loss": 2.1288,
2732
+ "step": 3890
2733
+ },
2734
+ {
2735
+ "epoch": 0.2611840342887758,
2736
+ "grad_norm": 0.0,
2737
+ "learning_rate": 9.229662792103137e-05,
2738
+ "loss": 2.2834,
2739
+ "step": 3900
2740
+ },
2741
+ {
2742
+ "epoch": 0.2618537369407983,
2743
+ "grad_norm": 0.0,
2744
+ "learning_rate": 9.223417500508427e-05,
2745
+ "loss": 2.0785,
2746
+ "step": 3910
2747
+ },
2748
+ {
2749
+ "epoch": 0.26252343959282076,
2750
+ "grad_norm": 0.0,
2751
+ "learning_rate": 9.217149125805416e-05,
2752
+ "loss": 2.2012,
2753
+ "step": 3920
2754
+ },
2755
+ {
2756
+ "epoch": 0.2631931422448433,
2757
+ "grad_norm": 0.0,
2758
+ "learning_rate": 9.21085770225393e-05,
2759
+ "loss": 2.2774,
2760
+ "step": 3930
2761
+ },
2762
+ {
2763
+ "epoch": 0.2638628448968658,
2764
+ "grad_norm": 0.0,
2765
+ "learning_rate": 9.204543264239778e-05,
2766
+ "loss": 2.2201,
2767
+ "step": 3940
2768
+ },
2769
+ {
2770
+ "epoch": 0.2645325475488883,
2771
+ "grad_norm": 0.0,
2772
+ "learning_rate": 9.198205846274548e-05,
2773
+ "loss": 2.3057,
2774
+ "step": 3950
2775
+ },
2776
+ {
2777
+ "epoch": 0.2652022502009108,
2778
+ "grad_norm": 0.0,
2779
+ "learning_rate": 9.191845482995431e-05,
2780
+ "loss": 2.2332,
2781
+ "step": 3960
2782
+ },
2783
+ {
2784
+ "epoch": 0.2658719528529333,
2785
+ "grad_norm": 0.0,
2786
+ "learning_rate": 9.185462209165021e-05,
2787
+ "loss": 2.1952,
2788
+ "step": 3970
2789
+ },
2790
+ {
2791
+ "epoch": 0.2665416555049558,
2792
+ "grad_norm": 0.0,
2793
+ "learning_rate": 9.179056059671129e-05,
2794
+ "loss": 2.3655,
2795
+ "step": 3980
2796
+ },
2797
+ {
2798
+ "epoch": 0.26721135815697833,
2799
+ "grad_norm": 0.0,
2800
+ "learning_rate": 9.1726270695266e-05,
2801
+ "loss": 2.2544,
2802
+ "step": 3990
2803
+ },
2804
+ {
2805
+ "epoch": 0.2678810608090008,
2806
+ "grad_norm": 0.0,
2807
+ "learning_rate": 9.166175273869107e-05,
2808
+ "loss": 2.2741,
2809
+ "step": 4000
2810
+ },
2811
+ {
2812
+ "epoch": 0.2685507634610233,
2813
+ "grad_norm": 0.0,
2814
+ "learning_rate": 9.15970070796097e-05,
2815
+ "loss": 2.2881,
2816
+ "step": 4010
2817
+ },
2818
+ {
2819
+ "epoch": 0.2692204661130458,
2820
+ "grad_norm": 0.0,
2821
+ "learning_rate": 9.15320340718896e-05,
2822
+ "loss": 2.2729,
2823
+ "step": 4020
2824
+ },
2825
+ {
2826
+ "epoch": 0.26989016876506833,
2827
+ "grad_norm": 0.0,
2828
+ "learning_rate": 9.146683407064105e-05,
2829
+ "loss": 2.238,
2830
+ "step": 4030
2831
+ },
2832
+ {
2833
+ "epoch": 0.2705598714170908,
2834
+ "grad_norm": 0.0,
2835
+ "learning_rate": 9.140140743221496e-05,
2836
+ "loss": 2.3336,
2837
+ "step": 4040
2838
+ },
2839
+ {
2840
+ "epoch": 0.2712295740691133,
2841
+ "grad_norm": 0.0,
2842
+ "learning_rate": 9.133575451420093e-05,
2843
+ "loss": 2.2249,
2844
+ "step": 4050
2845
+ },
2846
+ {
2847
+ "epoch": 0.27189927672113584,
2848
+ "grad_norm": 0.0,
2849
+ "learning_rate": 9.126987567542532e-05,
2850
+ "loss": 2.2385,
2851
+ "step": 4060
2852
+ },
2853
+ {
2854
+ "epoch": 0.2725689793731583,
2855
+ "grad_norm": 0.0,
2856
+ "learning_rate": 9.12037712759492e-05,
2857
+ "loss": 2.2343,
2858
+ "step": 4070
2859
+ },
2860
+ {
2861
+ "epoch": 0.2732386820251808,
2862
+ "grad_norm": 0.0,
2863
+ "learning_rate": 9.113744167706648e-05,
2864
+ "loss": 2.2202,
2865
+ "step": 4080
2866
+ },
2867
+ {
2868
+ "epoch": 0.2739083846772033,
2869
+ "grad_norm": 0.0,
2870
+ "learning_rate": 9.107088724130192e-05,
2871
+ "loss": 2.2392,
2872
+ "step": 4090
2873
+ },
2874
+ {
2875
+ "epoch": 0.27457808732922584,
2876
+ "grad_norm": 0.0,
2877
+ "learning_rate": 9.100410833240908e-05,
2878
+ "loss": 2.2371,
2879
+ "step": 4100
2880
+ },
2881
+ {
2882
+ "epoch": 0.2752477899812483,
2883
+ "grad_norm": 0.0,
2884
+ "learning_rate": 9.093710531536842e-05,
2885
+ "loss": 2.3052,
2886
+ "step": 4110
2887
+ },
2888
+ {
2889
+ "epoch": 0.2759174926332708,
2890
+ "grad_norm": 0.0,
2891
+ "learning_rate": 9.086987855638525e-05,
2892
+ "loss": 2.1853,
2893
+ "step": 4120
2894
+ },
2895
+ {
2896
+ "epoch": 0.27658719528529335,
2897
+ "grad_norm": 0.0,
2898
+ "learning_rate": 9.08024284228877e-05,
2899
+ "loss": 2.2073,
2900
+ "step": 4130
2901
+ },
2902
+ {
2903
+ "epoch": 0.27725689793731584,
2904
+ "grad_norm": 0.0,
2905
+ "learning_rate": 9.073475528352484e-05,
2906
+ "loss": 2.1914,
2907
+ "step": 4140
2908
+ },
2909
+ {
2910
+ "epoch": 0.2779266005893383,
2911
+ "grad_norm": 0.0,
2912
+ "learning_rate": 9.066685950816451e-05,
2913
+ "loss": 2.2104,
2914
+ "step": 4150
2915
+ },
2916
+ {
2917
+ "epoch": 0.2785963032413608,
2918
+ "grad_norm": 0.0,
2919
+ "learning_rate": 9.059874146789139e-05,
2920
+ "loss": 2.1314,
2921
+ "step": 4160
2922
+ },
2923
+ {
2924
+ "epoch": 0.27926600589338335,
2925
+ "grad_norm": 0.0,
2926
+ "learning_rate": 9.053040153500496e-05,
2927
+ "loss": 2.1836,
2928
+ "step": 4170
2929
+ },
2930
+ {
2931
+ "epoch": 0.27993570854540584,
2932
+ "grad_norm": 0.0,
2933
+ "learning_rate": 9.046184008301743e-05,
2934
+ "loss": 2.2723,
2935
+ "step": 4180
2936
+ },
2937
+ {
2938
+ "epoch": 0.2806054111974283,
2939
+ "grad_norm": 0.0,
2940
+ "learning_rate": 9.039305748665176e-05,
2941
+ "loss": 2.2827,
2942
+ "step": 4190
2943
+ },
2944
+ {
2945
+ "epoch": 0.28127511384945086,
2946
+ "grad_norm": 0.0,
2947
+ "learning_rate": 9.032405412183956e-05,
2948
+ "loss": 2.1977,
2949
+ "step": 4200
2950
+ },
2951
+ {
2952
+ "epoch": 0.28194481650147335,
2953
+ "grad_norm": 0.0,
2954
+ "learning_rate": 9.025483036571902e-05,
2955
+ "loss": 2.2147,
2956
+ "step": 4210
2957
+ },
2958
+ {
2959
+ "epoch": 0.28261451915349584,
2960
+ "grad_norm": 0.0,
2961
+ "learning_rate": 9.018538659663293e-05,
2962
+ "loss": 2.2783,
2963
+ "step": 4220
2964
+ },
2965
+ {
2966
+ "epoch": 0.2832842218055184,
2967
+ "grad_norm": 0.0,
2968
+ "learning_rate": 9.01157231941265e-05,
2969
+ "loss": 2.1797,
2970
+ "step": 4230
2971
+ },
2972
+ {
2973
+ "epoch": 0.28395392445754086,
2974
+ "grad_norm": 0.0,
2975
+ "learning_rate": 9.004584053894545e-05,
2976
+ "loss": 2.2945,
2977
+ "step": 4240
2978
+ },
2979
+ {
2980
+ "epoch": 0.28462362710956335,
2981
+ "grad_norm": 0.0,
2982
+ "learning_rate": 8.997573901303372e-05,
2983
+ "loss": 2.2139,
2984
+ "step": 4250
2985
+ },
2986
+ {
2987
+ "epoch": 0.28529332976158583,
2988
+ "grad_norm": 0.0,
2989
+ "learning_rate": 8.990541899953151e-05,
2990
+ "loss": 2.2501,
2991
+ "step": 4260
2992
+ },
2993
+ {
2994
+ "epoch": 0.2859630324136084,
2995
+ "grad_norm": 0.0,
2996
+ "learning_rate": 8.983488088277323e-05,
2997
+ "loss": 2.233,
2998
+ "step": 4270
2999
+ },
3000
+ {
3001
+ "epoch": 0.28663273506563086,
3002
+ "grad_norm": 0.0,
3003
+ "learning_rate": 8.976412504828526e-05,
3004
+ "loss": 2.2957,
3005
+ "step": 4280
3006
+ },
3007
+ {
3008
+ "epoch": 0.28730243771765335,
3009
+ "grad_norm": 0.0,
3010
+ "learning_rate": 8.969315188278396e-05,
3011
+ "loss": 2.2512,
3012
+ "step": 4290
3013
+ },
3014
+ {
3015
+ "epoch": 0.2879721403696759,
3016
+ "grad_norm": 0.0,
3017
+ "learning_rate": 8.962196177417353e-05,
3018
+ "loss": 2.1994,
3019
+ "step": 4300
3020
+ },
3021
+ {
3022
+ "epoch": 0.2886418430216984,
3023
+ "grad_norm": 0.0,
3024
+ "learning_rate": 8.955055511154378e-05,
3025
+ "loss": 2.189,
3026
+ "step": 4310
3027
+ },
3028
+ {
3029
+ "epoch": 0.28931154567372086,
3030
+ "grad_norm": 0.0,
3031
+ "learning_rate": 8.947893228516821e-05,
3032
+ "loss": 2.2342,
3033
+ "step": 4320
3034
+ },
3035
+ {
3036
+ "epoch": 0.28998124832574335,
3037
+ "grad_norm": 0.0,
3038
+ "learning_rate": 8.940709368650173e-05,
3039
+ "loss": 2.1649,
3040
+ "step": 4330
3041
+ },
3042
+ {
3043
+ "epoch": 0.2906509509777659,
3044
+ "grad_norm": 0.0,
3045
+ "learning_rate": 8.933503970817849e-05,
3046
+ "loss": 2.232,
3047
+ "step": 4340
3048
+ },
3049
+ {
3050
+ "epoch": 0.2913206536297884,
3051
+ "grad_norm": 0.0,
3052
+ "learning_rate": 8.926277074400987e-05,
3053
+ "loss": 2.2633,
3054
+ "step": 4350
3055
+ },
3056
+ {
3057
+ "epoch": 0.29199035628181086,
3058
+ "grad_norm": 0.0,
3059
+ "learning_rate": 8.919028718898226e-05,
3060
+ "loss": 2.2506,
3061
+ "step": 4360
3062
+ },
3063
+ {
3064
+ "epoch": 0.2926600589338334,
3065
+ "grad_norm": 0.0,
3066
+ "learning_rate": 8.911758943925483e-05,
3067
+ "loss": 2.2919,
3068
+ "step": 4370
3069
+ },
3070
+ {
3071
+ "epoch": 0.2933297615858559,
3072
+ "grad_norm": 0.0,
3073
+ "learning_rate": 8.904467789215751e-05,
3074
+ "loss": 2.2114,
3075
+ "step": 4380
3076
+ },
3077
+ {
3078
+ "epoch": 0.29399946423787837,
3079
+ "grad_norm": 0.0,
3080
+ "learning_rate": 8.897155294618869e-05,
3081
+ "loss": 2.2352,
3082
+ "step": 4390
3083
+ },
3084
+ {
3085
+ "epoch": 0.29466916688990086,
3086
+ "grad_norm": 0.0,
3087
+ "learning_rate": 8.88982150010131e-05,
3088
+ "loss": 2.2521,
3089
+ "step": 4400
3090
+ },
3091
+ {
3092
+ "epoch": 0.2953388695419234,
3093
+ "grad_norm": 0.0,
3094
+ "learning_rate": 8.882466445745964e-05,
3095
+ "loss": 2.2084,
3096
+ "step": 4410
3097
+ },
3098
+ {
3099
+ "epoch": 0.2960085721939459,
3100
+ "grad_norm": 0.0,
3101
+ "learning_rate": 8.875090171751915e-05,
3102
+ "loss": 2.2102,
3103
+ "step": 4420
3104
+ },
3105
+ {
3106
+ "epoch": 0.29667827484596837,
3107
+ "grad_norm": 0.0,
3108
+ "learning_rate": 8.867692718434223e-05,
3109
+ "loss": 2.1578,
3110
+ "step": 4430
3111
+ },
3112
+ {
3113
+ "epoch": 0.2973479774979909,
3114
+ "grad_norm": 0.0,
3115
+ "learning_rate": 8.860274126223705e-05,
3116
+ "loss": 2.2352,
3117
+ "step": 4440
3118
+ },
3119
+ {
3120
+ "epoch": 0.2980176801500134,
3121
+ "grad_norm": 0.0,
3122
+ "learning_rate": 8.85283443566671e-05,
3123
+ "loss": 2.2075,
3124
+ "step": 4450
3125
+ },
3126
+ {
3127
+ "epoch": 0.2986873828020359,
3128
+ "grad_norm": 0.0,
3129
+ "learning_rate": 8.845373687424903e-05,
3130
+ "loss": 2.3332,
3131
+ "step": 4460
3132
+ },
3133
+ {
3134
+ "epoch": 0.2993570854540584,
3135
+ "grad_norm": 0.0,
3136
+ "learning_rate": 8.83789192227504e-05,
3137
+ "loss": 2.1775,
3138
+ "step": 4470
3139
+ },
3140
+ {
3141
+ "epoch": 0.3000267881060809,
3142
+ "grad_norm": 0.0,
3143
+ "learning_rate": 8.83038918110874e-05,
3144
+ "loss": 2.2348,
3145
+ "step": 4480
3146
+ },
3147
+ {
3148
+ "epoch": 0.3006964907581034,
3149
+ "grad_norm": 0.0,
3150
+ "learning_rate": 8.822865504932275e-05,
3151
+ "loss": 2.1897,
3152
+ "step": 4490
3153
+ },
3154
+ {
3155
+ "epoch": 0.3013661934101259,
3156
+ "grad_norm": 0.0,
3157
+ "learning_rate": 8.815320934866329e-05,
3158
+ "loss": 2.2539,
3159
+ "step": 4500
3160
+ },
3161
+ {
3162
+ "epoch": 0.3020358960621484,
3163
+ "grad_norm": 0.0,
3164
+ "learning_rate": 8.807755512145788e-05,
3165
+ "loss": 2.2351,
3166
+ "step": 4510
3167
+ },
3168
+ {
3169
+ "epoch": 0.3027055987141709,
3170
+ "grad_norm": 0.0,
3171
+ "learning_rate": 8.800169278119503e-05,
3172
+ "loss": 2.3542,
3173
+ "step": 4520
3174
+ },
3175
+ {
3176
+ "epoch": 0.3033753013661934,
3177
+ "grad_norm": 0.0,
3178
+ "learning_rate": 8.792562274250075e-05,
3179
+ "loss": 2.2724,
3180
+ "step": 4530
3181
+ },
3182
+ {
3183
+ "epoch": 0.30404500401821594,
3184
+ "grad_norm": 0.0,
3185
+ "learning_rate": 8.784934542113617e-05,
3186
+ "loss": 2.204,
3187
+ "step": 4540
3188
+ },
3189
+ {
3190
+ "epoch": 0.3047147066702384,
3191
+ "grad_norm": 0.0,
3192
+ "learning_rate": 8.777286123399536e-05,
3193
+ "loss": 2.2944,
3194
+ "step": 4550
3195
+ },
3196
+ {
3197
+ "epoch": 0.3053844093222609,
3198
+ "grad_norm": 0.0,
3199
+ "learning_rate": 8.7696170599103e-05,
3200
+ "loss": 2.1318,
3201
+ "step": 4560
3202
+ },
3203
+ {
3204
+ "epoch": 0.3060541119742834,
3205
+ "grad_norm": 0.0,
3206
+ "learning_rate": 8.761927393561214e-05,
3207
+ "loss": 2.1441,
3208
+ "step": 4570
3209
+ },
3210
+ {
3211
+ "epoch": 0.30672381462630594,
3212
+ "grad_norm": 0.0,
3213
+ "learning_rate": 8.754217166380184e-05,
3214
+ "loss": 2.303,
3215
+ "step": 4580
3216
+ },
3217
+ {
3218
+ "epoch": 0.3073935172783284,
3219
+ "grad_norm": 0.0,
3220
+ "learning_rate": 8.746486420507491e-05,
3221
+ "loss": 2.2769,
3222
+ "step": 4590
3223
+ },
3224
+ {
3225
+ "epoch": 0.3080632199303509,
3226
+ "grad_norm": 0.0,
3227
+ "learning_rate": 8.738735198195566e-05,
3228
+ "loss": 2.3048,
3229
+ "step": 4600
3230
+ },
3231
+ {
3232
+ "epoch": 0.30873292258237345,
3233
+ "grad_norm": 0.0,
3234
+ "learning_rate": 8.73096354180875e-05,
3235
+ "loss": 2.2582,
3236
+ "step": 4610
3237
+ },
3238
+ {
3239
+ "epoch": 0.30940262523439593,
3240
+ "grad_norm": 0.0,
3241
+ "learning_rate": 8.72317149382307e-05,
3242
+ "loss": 2.3533,
3243
+ "step": 4620
3244
+ },
3245
+ {
3246
+ "epoch": 0.3100723278864184,
3247
+ "grad_norm": 0.0,
3248
+ "learning_rate": 8.715359096825999e-05,
3249
+ "loss": 2.2417,
3250
+ "step": 4630
3251
+ },
3252
+ {
3253
+ "epoch": 0.3107420305384409,
3254
+ "grad_norm": 0.0,
3255
+ "learning_rate": 8.707526393516228e-05,
3256
+ "loss": 2.215,
3257
+ "step": 4640
3258
+ },
3259
+ {
3260
+ "epoch": 0.31141173319046345,
3261
+ "grad_norm": 0.0,
3262
+ "learning_rate": 8.699673426703436e-05,
3263
+ "loss": 2.1881,
3264
+ "step": 4650
3265
+ },
3266
+ {
3267
+ "epoch": 0.31208143584248593,
3268
+ "grad_norm": 0.0,
3269
+ "learning_rate": 8.691800239308052e-05,
3270
+ "loss": 2.2907,
3271
+ "step": 4660
3272
+ },
3273
+ {
3274
+ "epoch": 0.3127511384945084,
3275
+ "grad_norm": 0.0,
3276
+ "learning_rate": 8.683906874361017e-05,
3277
+ "loss": 2.221,
3278
+ "step": 4670
3279
+ },
3280
+ {
3281
+ "epoch": 0.31342084114653096,
3282
+ "grad_norm": 0.0,
3283
+ "learning_rate": 8.675993375003553e-05,
3284
+ "loss": 2.1868,
3285
+ "step": 4680
3286
+ },
3287
+ {
3288
+ "epoch": 0.31409054379855345,
3289
+ "grad_norm": 0.0,
3290
+ "learning_rate": 8.668059784486929e-05,
3291
+ "loss": 2.244,
3292
+ "step": 4690
3293
+ },
3294
+ {
3295
+ "epoch": 0.31476024645057593,
3296
+ "grad_norm": 0.0,
3297
+ "learning_rate": 8.660106146172223e-05,
3298
+ "loss": 2.2294,
3299
+ "step": 4700
3300
+ },
3301
+ {
3302
+ "epoch": 0.3154299491025985,
3303
+ "grad_norm": 0.0,
3304
+ "learning_rate": 8.652132503530082e-05,
3305
+ "loss": 2.2347,
3306
+ "step": 4710
3307
+ },
3308
+ {
3309
+ "epoch": 0.31609965175462096,
3310
+ "grad_norm": 0.0,
3311
+ "learning_rate": 8.644138900140485e-05,
3312
+ "loss": 2.2633,
3313
+ "step": 4720
3314
+ },
3315
+ {
3316
+ "epoch": 0.31676935440664344,
3317
+ "grad_norm": 0.0,
3318
+ "learning_rate": 8.636125379692515e-05,
3319
+ "loss": 2.2383,
3320
+ "step": 4730
3321
+ },
3322
+ {
3323
+ "epoch": 0.31743905705866593,
3324
+ "grad_norm": 0.0,
3325
+ "learning_rate": 8.628091985984099e-05,
3326
+ "loss": 2.2282,
3327
+ "step": 4740
3328
+ },
3329
+ {
3330
+ "epoch": 0.31810875971068847,
3331
+ "grad_norm": 0.0,
3332
+ "learning_rate": 8.620038762921794e-05,
3333
+ "loss": 2.172,
3334
+ "step": 4750
3335
+ },
3336
+ {
3337
+ "epoch": 0.31877846236271096,
3338
+ "grad_norm": 0.0,
3339
+ "learning_rate": 8.611965754520526e-05,
3340
+ "loss": 2.2849,
3341
+ "step": 4760
3342
+ },
3343
+ {
3344
+ "epoch": 0.31944816501473344,
3345
+ "grad_norm": 0.0,
3346
+ "learning_rate": 8.60387300490336e-05,
3347
+ "loss": 2.3451,
3348
+ "step": 4770
3349
+ },
3350
+ {
3351
+ "epoch": 0.320117867666756,
3352
+ "grad_norm": 0.0,
3353
+ "learning_rate": 8.595760558301257e-05,
3354
+ "loss": 2.2314,
3355
+ "step": 4780
3356
+ },
3357
+ {
3358
+ "epoch": 0.32078757031877847,
3359
+ "grad_norm": 0.0,
3360
+ "learning_rate": 8.587628459052834e-05,
3361
+ "loss": 2.155,
3362
+ "step": 4790
3363
+ },
3364
+ {
3365
+ "epoch": 0.32145727297080096,
3366
+ "grad_norm": 0.0,
3367
+ "learning_rate": 8.579476751604119e-05,
3368
+ "loss": 2.2874,
3369
+ "step": 4800
3370
+ },
3371
+ {
3372
+ "epoch": 0.32212697562282344,
3373
+ "grad_norm": 0.0,
3374
+ "learning_rate": 8.571305480508302e-05,
3375
+ "loss": 2.2094,
3376
+ "step": 4810
3377
+ },
3378
+ {
3379
+ "epoch": 0.322796678274846,
3380
+ "grad_norm": 0.0,
3381
+ "learning_rate": 8.563114690425511e-05,
3382
+ "loss": 2.2631,
3383
+ "step": 4820
3384
+ },
3385
+ {
3386
+ "epoch": 0.32346638092686847,
3387
+ "grad_norm": 0.0,
3388
+ "learning_rate": 8.554904426122543e-05,
3389
+ "loss": 2.287,
3390
+ "step": 4830
3391
+ },
3392
+ {
3393
+ "epoch": 0.32413608357889095,
3394
+ "grad_norm": 0.0,
3395
+ "learning_rate": 8.546674732472638e-05,
3396
+ "loss": 2.2728,
3397
+ "step": 4840
3398
+ },
3399
+ {
3400
+ "epoch": 0.3248057862309135,
3401
+ "grad_norm": 0.0,
3402
+ "learning_rate": 8.538425654455225e-05,
3403
+ "loss": 2.2106,
3404
+ "step": 4850
3405
+ },
3406
+ {
3407
+ "epoch": 0.325475488882936,
3408
+ "grad_norm": 0.0,
3409
+ "learning_rate": 8.530157237155681e-05,
3410
+ "loss": 2.2396,
3411
+ "step": 4860
3412
+ },
3413
+ {
3414
+ "epoch": 0.32614519153495847,
3415
+ "grad_norm": 0.0,
3416
+ "learning_rate": 8.521869525765076e-05,
3417
+ "loss": 2.2975,
3418
+ "step": 4870
3419
+ },
3420
+ {
3421
+ "epoch": 0.32681489418698095,
3422
+ "grad_norm": 0.0,
3423
+ "learning_rate": 8.513562565579936e-05,
3424
+ "loss": 2.2552,
3425
+ "step": 4880
3426
+ },
3427
+ {
3428
+ "epoch": 0.3274845968390035,
3429
+ "grad_norm": 0.0,
3430
+ "learning_rate": 8.505236402001996e-05,
3431
+ "loss": 2.2631,
3432
+ "step": 4890
3433
+ },
3434
+ {
3435
+ "epoch": 0.328154299491026,
3436
+ "grad_norm": 0.0,
3437
+ "learning_rate": 8.496891080537939e-05,
3438
+ "loss": 2.1826,
3439
+ "step": 4900
3440
+ },
3441
+ {
3442
+ "epoch": 0.32882400214304847,
3443
+ "grad_norm": 0.0,
3444
+ "learning_rate": 8.488526646799158e-05,
3445
+ "loss": 2.2127,
3446
+ "step": 4910
3447
+ },
3448
+ {
3449
+ "epoch": 0.329493704795071,
3450
+ "grad_norm": 0.0,
3451
+ "learning_rate": 8.480143146501506e-05,
3452
+ "loss": 2.1991,
3453
+ "step": 4920
3454
+ },
3455
+ {
3456
+ "epoch": 0.3301634074470935,
3457
+ "grad_norm": 0.0,
3458
+ "learning_rate": 8.471740625465044e-05,
3459
+ "loss": 2.2428,
3460
+ "step": 4930
3461
+ },
3462
+ {
3463
+ "epoch": 0.330833110099116,
3464
+ "grad_norm": 0.0,
3465
+ "learning_rate": 8.463319129613791e-05,
3466
+ "loss": 2.2601,
3467
+ "step": 4940
3468
+ },
3469
+ {
3470
+ "epoch": 0.3315028127511385,
3471
+ "grad_norm": 0.0,
3472
+ "learning_rate": 8.45487870497547e-05,
3473
+ "loss": 2.2814,
3474
+ "step": 4950
3475
+ },
3476
+ {
3477
+ "epoch": 0.332172515403161,
3478
+ "grad_norm": 0.0,
3479
+ "learning_rate": 8.446419397681265e-05,
3480
+ "loss": 2.1667,
3481
+ "step": 4960
3482
+ },
3483
+ {
3484
+ "epoch": 0.3328422180551835,
3485
+ "grad_norm": 0.0,
3486
+ "learning_rate": 8.437941253965558e-05,
3487
+ "loss": 2.3395,
3488
+ "step": 4970
3489
+ },
3490
+ {
3491
+ "epoch": 0.333511920707206,
3492
+ "grad_norm": 0.0,
3493
+ "learning_rate": 8.429444320165683e-05,
3494
+ "loss": 2.2234,
3495
+ "step": 4980
3496
+ }
3497
+ ],
3498
+ "logging_steps": 10,
3499
+ "max_steps": 14932,
3500
+ "num_input_tokens_seen": 0,
3501
+ "num_train_epochs": 9223372036854775807,
3502
+ "save_steps": 1660,
3503
+ "stateful_callbacks": {
3504
+ "TrainerControl": {
3505
+ "args": {
3506
+ "should_epoch_stop": false,
3507
+ "should_evaluate": false,
3508
+ "should_log": false,
3509
+ "should_save": true,
3510
+ "should_training_stop": false
3511
+ },
3512
+ "attributes": {}
3513
+ }
3514
+ },
3515
+ "total_flos": 1.837032646241157e+18,
3516
+ "train_batch_size": 1,
3517
+ "trial_name": null,
3518
+ "trial_params": null
3519
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd813c0229d498f9045c7d3652be68d89786413bc9a07060caf83fa3b1e15e15
3
+ size 5560