Brown commited on
Commit
1cc32b5
·
verified ·
1 Parent(s): 512ab1e

Upload folder using huggingface_hub

Browse files
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 7122048987955200.0,
4
+ "train_loss": 0.13241534099762473,
5
+ "train_runtime": 27380.0053,
6
+ "train_samples_per_second": 19.876,
7
+ "train_steps_per_second": 0.124
8
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/apdcephfs_sh4/share_300001476/trenousqiu/models/llama3-8b-base",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 500000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.44.0",
27
+ "use_cache": false,
28
+ "vocab_size": 128256
29
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": 128001,
5
+ "max_length": 4096,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.44.0"
9
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6a5c2ed50bea4e29d697853a9072ed015852dcb780904801c0bfdb04c7a632c
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a9be6e505cff2090d01b51283d4ff42f7d4a6a270a9e8f7553230d0f85c367b
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14d05dfc7f7d3212c696c2fbe1e866cf95b9b46cf1c36b9edb37e50195770565
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:ec87a3721448f867b5feab8ceace2449e96c36c66155cca0be5d150b8e8179e3
3
+ size 1168138808
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|end_of_text|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '### Instruction:\n' + content + '\n\n### Response:\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\n\n' }}{% endif %}{% endfor %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 7122048987955200.0,
4
+ "train_loss": 0.13241534099762473,
5
+ "train_runtime": 27380.0053,
6
+ "train_samples_per_second": 19.876,
7
+ "train_steps_per_second": 0.124
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,341 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 3402, "loss": 0.4452, "learning_rate": 3.883495145631068e-06, "epoch": 0.008818342151675485, "percentage": 0.29, "elapsed_time": "0:01:36", "remaining_time": "9:06:25", "throughput": "0.00", "total_tokens": 0}
2
+ {"current_steps": 20, "total_steps": 3402, "loss": 0.3563, "learning_rate": 7.766990291262136e-06, "epoch": 0.01763668430335097, "percentage": 0.59, "elapsed_time": "0:02:56", "remaining_time": "8:17:10", "throughput": "0.00", "total_tokens": 0}
3
+ {"current_steps": 30, "total_steps": 3402, "loss": 0.2954, "learning_rate": 1.1650485436893204e-05, "epoch": 0.026455026455026454, "percentage": 0.88, "elapsed_time": "0:04:16", "remaining_time": "7:59:50", "throughput": "0.00", "total_tokens": 0}
4
+ {"current_steps": 40, "total_steps": 3402, "loss": 0.264, "learning_rate": 1.5533980582524273e-05, "epoch": 0.03527336860670194, "percentage": 1.18, "elapsed_time": "0:05:35", "remaining_time": "7:50:35", "throughput": "0.00", "total_tokens": 0}
5
+ {"current_steps": 50, "total_steps": 3402, "loss": 0.2515, "learning_rate": 1.9417475728155343e-05, "epoch": 0.04409171075837742, "percentage": 1.47, "elapsed_time": "0:06:55", "remaining_time": "7:44:27", "throughput": "0.00", "total_tokens": 0}
6
+ {"current_steps": 60, "total_steps": 3402, "loss": 0.2384, "learning_rate": 2.330097087378641e-05, "epoch": 0.05291005291005291, "percentage": 1.76, "elapsed_time": "0:08:15", "remaining_time": "7:40:00", "throughput": "0.00", "total_tokens": 0}
7
+ {"current_steps": 70, "total_steps": 3402, "loss": 0.2371, "learning_rate": 2.718446601941748e-05, "epoch": 0.06172839506172839, "percentage": 2.06, "elapsed_time": "0:09:35", "remaining_time": "7:36:24", "throughput": "0.00", "total_tokens": 0}
8
+ {"current_steps": 80, "total_steps": 3402, "loss": 0.2316, "learning_rate": 3.1067961165048545e-05, "epoch": 0.07054673721340388, "percentage": 2.35, "elapsed_time": "0:10:55", "remaining_time": "7:33:20", "throughput": "0.00", "total_tokens": 0}
9
+ {"current_steps": 90, "total_steps": 3402, "loss": 0.2243, "learning_rate": 3.4951456310679615e-05, "epoch": 0.07936507936507936, "percentage": 2.65, "elapsed_time": "0:12:14", "remaining_time": "7:30:40", "throughput": "0.00", "total_tokens": 0}
10
+ {"current_steps": 100, "total_steps": 3402, "loss": 0.2216, "learning_rate": 3.8834951456310685e-05, "epoch": 0.08818342151675485, "percentage": 2.94, "elapsed_time": "0:13:34", "remaining_time": "7:28:17", "throughput": "0.00", "total_tokens": 0}
11
+ {"current_steps": 110, "total_steps": 3402, "loss": 0.2181, "learning_rate": 3.9999555645496425e-05, "epoch": 0.09700176366843033, "percentage": 3.23, "elapsed_time": "0:14:54", "remaining_time": "7:26:05", "throughput": "0.00", "total_tokens": 0}
12
+ {"current_steps": 120, "total_steps": 3402, "loss": 0.2123, "learning_rate": 3.999737926280763e-05, "epoch": 0.10582010582010581, "percentage": 3.53, "elapsed_time": "0:16:14", "remaining_time": "7:24:02", "throughput": "0.00", "total_tokens": 0}
13
+ {"current_steps": 130, "total_steps": 3402, "loss": 0.2072, "learning_rate": 3.999338943291723e-05, "epoch": 0.1146384479717813, "percentage": 3.82, "elapsed_time": "0:17:33", "remaining_time": "7:22:05", "throughput": "0.00", "total_tokens": 0}
14
+ {"current_steps": 140, "total_steps": 3402, "loss": 0.2046, "learning_rate": 3.998758651763991e-05, "epoch": 0.12345679012345678, "percentage": 4.12, "elapsed_time": "0:18:53", "remaining_time": "7:20:15", "throughput": "0.00", "total_tokens": 0}
15
+ {"current_steps": 150, "total_steps": 3402, "loss": 0.2017, "learning_rate": 3.9979971043208656e-05, "epoch": 0.13227513227513227, "percentage": 4.41, "elapsed_time": "0:20:13", "remaining_time": "7:18:29", "throughput": "0.00", "total_tokens": 0}
16
+ {"current_steps": 160, "total_steps": 3402, "loss": 0.2026, "learning_rate": 3.997054370022701e-05, "epoch": 0.14109347442680775, "percentage": 4.7, "elapsed_time": "0:21:33", "remaining_time": "7:16:44", "throughput": "0.00", "total_tokens": 0}
17
+ {"current_steps": 170, "total_steps": 3402, "loss": 0.1972, "learning_rate": 3.995930534360642e-05, "epoch": 0.14991181657848324, "percentage": 5.0, "elapsed_time": "0:22:53", "remaining_time": "7:15:03", "throughput": "0.00", "total_tokens": 0}
18
+ {"current_steps": 180, "total_steps": 3402, "loss": 0.1947, "learning_rate": 3.994625699248876e-05, "epoch": 0.15873015873015872, "percentage": 5.29, "elapsed_time": "0:24:12", "remaining_time": "7:13:25", "throughput": "0.00", "total_tokens": 0}
19
+ {"current_steps": 190, "total_steps": 3402, "loss": 0.1971, "learning_rate": 3.993139983015388e-05, "epoch": 0.1675485008818342, "percentage": 5.58, "elapsed_time": "0:25:32", "remaining_time": "7:11:49", "throughput": "0.00", "total_tokens": 0}
20
+ {"current_steps": 200, "total_steps": 3402, "loss": 0.1925, "learning_rate": 3.9914735203912274e-05, "epoch": 0.1763668430335097, "percentage": 5.88, "elapsed_time": "0:26:52", "remaining_time": "7:10:13", "throughput": "0.00", "total_tokens": 0}
21
+ {"current_steps": 210, "total_steps": 3402, "loss": 0.192, "learning_rate": 3.989626462498299e-05, "epoch": 0.18518518518518517, "percentage": 6.17, "elapsed_time": "0:28:12", "remaining_time": "7:08:41", "throughput": "0.00", "total_tokens": 0}
22
+ {"current_steps": 220, "total_steps": 3402, "loss": 0.1868, "learning_rate": 3.9875989768356474e-05, "epoch": 0.19400352733686066, "percentage": 6.47, "elapsed_time": "0:29:31", "remaining_time": "7:07:09", "throughput": "0.00", "total_tokens": 0}
23
+ {"current_steps": 230, "total_steps": 3402, "loss": 0.1893, "learning_rate": 3.9853912472642766e-05, "epoch": 0.20282186948853614, "percentage": 6.76, "elapsed_time": "0:30:51", "remaining_time": "7:05:38", "throughput": "0.00", "total_tokens": 0}
24
+ {"current_steps": 240, "total_steps": 3402, "loss": 0.1863, "learning_rate": 3.9830034739904716e-05, "epoch": 0.21164021164021163, "percentage": 7.05, "elapsed_time": "0:32:11", "remaining_time": "7:04:10", "throughput": "0.00", "total_tokens": 0}
25
+ {"current_steps": 250, "total_steps": 3402, "loss": 0.1862, "learning_rate": 3.980435873547643e-05, "epoch": 0.2204585537918871, "percentage": 7.35, "elapsed_time": "0:33:33", "remaining_time": "7:03:08", "throughput": "0.00", "total_tokens": 0}
26
+ {"current_steps": 260, "total_steps": 3402, "loss": 0.1851, "learning_rate": 3.977688678776695e-05, "epoch": 0.2292768959435626, "percentage": 7.64, "elapsed_time": "0:34:56", "remaining_time": "7:02:21", "throughput": "0.00", "total_tokens": 0}
27
+ {"current_steps": 270, "total_steps": 3402, "loss": 0.1865, "learning_rate": 3.974762138804906e-05, "epoch": 0.23809523809523808, "percentage": 7.94, "elapsed_time": "0:36:17", "remaining_time": "7:00:58", "throughput": "0.00", "total_tokens": 0}
28
+ {"current_steps": 280, "total_steps": 3402, "loss": 0.1817, "learning_rate": 3.971656519023337e-05, "epoch": 0.24691358024691357, "percentage": 8.23, "elapsed_time": "0:37:37", "remaining_time": "6:59:32", "throughput": "0.00", "total_tokens": 0}
29
+ {"current_steps": 290, "total_steps": 3402, "loss": 0.1818, "learning_rate": 3.9683721010627666e-05, "epoch": 0.25573192239858905, "percentage": 8.52, "elapsed_time": "0:38:57", "remaining_time": "6:58:02", "throughput": "0.00", "total_tokens": 0}
30
+ {"current_steps": 300, "total_steps": 3402, "loss": 0.18, "learning_rate": 3.964909182768153e-05, "epoch": 0.26455026455026454, "percentage": 8.82, "elapsed_time": "0:40:17", "remaining_time": "6:56:34", "throughput": "0.00", "total_tokens": 0}
31
+ {"current_steps": 310, "total_steps": 3402, "loss": 0.1803, "learning_rate": 3.9612680781716203e-05, "epoch": 0.27336860670194, "percentage": 9.11, "elapsed_time": "0:41:37", "remaining_time": "6:55:06", "throughput": "0.00", "total_tokens": 0}
32
+ {"current_steps": 320, "total_steps": 3402, "loss": 0.1789, "learning_rate": 3.9574491174639824e-05, "epoch": 0.2821869488536155, "percentage": 9.41, "elapsed_time": "0:42:56", "remaining_time": "6:53:37", "throughput": "0.00", "total_tokens": 0}
33
+ {"current_steps": 330, "total_steps": 3402, "loss": 0.178, "learning_rate": 3.9534526469648e-05, "epoch": 0.291005291005291, "percentage": 9.7, "elapsed_time": "0:44:16", "remaining_time": "6:52:09", "throughput": "0.00", "total_tokens": 0}
34
+ {"current_steps": 340, "total_steps": 3402, "loss": 0.179, "learning_rate": 3.949279029090976e-05, "epoch": 0.2998236331569665, "percentage": 9.99, "elapsed_time": "0:45:36", "remaining_time": "6:50:43", "throughput": "0.00", "total_tokens": 0}
35
+ {"current_steps": 350, "total_steps": 3402, "loss": 0.1786, "learning_rate": 3.944928642323887e-05, "epoch": 0.30864197530864196, "percentage": 10.29, "elapsed_time": "0:46:56", "remaining_time": "6:49:17", "throughput": "0.00", "total_tokens": 0}
36
+ {"current_steps": 360, "total_steps": 3402, "loss": 0.18, "learning_rate": 3.940401881175065e-05, "epoch": 0.31746031746031744, "percentage": 10.58, "elapsed_time": "0:48:16", "remaining_time": "6:47:51", "throughput": "0.00", "total_tokens": 0}
37
+ {"current_steps": 370, "total_steps": 3402, "loss": 0.1776, "learning_rate": 3.9356991561504177e-05, "epoch": 0.3262786596119929, "percentage": 10.88, "elapsed_time": "0:49:35", "remaining_time": "6:46:25", "throughput": "0.00", "total_tokens": 0}
38
+ {"current_steps": 380, "total_steps": 3402, "loss": 0.1763, "learning_rate": 3.9308208937130046e-05, "epoch": 0.3350970017636684, "percentage": 11.17, "elapsed_time": "0:50:55", "remaining_time": "6:45:00", "throughput": "0.00", "total_tokens": 0}
39
+ {"current_steps": 390, "total_steps": 3402, "loss": 0.1751, "learning_rate": 3.925767536244362e-05, "epoch": 0.3439153439153439, "percentage": 11.46, "elapsed_time": "0:52:15", "remaining_time": "6:43:35", "throughput": "0.00", "total_tokens": 0}
40
+ {"current_steps": 400, "total_steps": 3402, "loss": 0.1745, "learning_rate": 3.920539542004387e-05, "epoch": 0.3527336860670194, "percentage": 11.76, "elapsed_time": "0:53:35", "remaining_time": "6:42:10", "throughput": "0.00", "total_tokens": 0}
41
+ {"current_steps": 410, "total_steps": 3402, "loss": 0.1749, "learning_rate": 3.915137385089781e-05, "epoch": 0.36155202821869487, "percentage": 12.05, "elapsed_time": "0:54:54", "remaining_time": "6:40:45", "throughput": "0.00", "total_tokens": 0}
42
+ {"current_steps": 420, "total_steps": 3402, "loss": 0.174, "learning_rate": 3.909561555391053e-05, "epoch": 0.37037037037037035, "percentage": 12.35, "elapsed_time": "0:56:14", "remaining_time": "6:39:20", "throughput": "0.00", "total_tokens": 0}
43
+ {"current_steps": 430, "total_steps": 3402, "loss": 0.1734, "learning_rate": 3.903812558548099e-05, "epoch": 0.37918871252204583, "percentage": 12.64, "elapsed_time": "0:57:34", "remaining_time": "6:37:56", "throughput": "0.00", "total_tokens": 0}
44
+ {"current_steps": 440, "total_steps": 3402, "loss": 0.174, "learning_rate": 3.8978909159043465e-05, "epoch": 0.3880070546737213, "percentage": 12.93, "elapsed_time": "0:58:54", "remaining_time": "6:36:32", "throughput": "0.00", "total_tokens": 0}
45
+ {"current_steps": 450, "total_steps": 3402, "loss": 0.1715, "learning_rate": 3.891797164459477e-05, "epoch": 0.3968253968253968, "percentage": 13.23, "elapsed_time": "1:00:14", "remaining_time": "6:35:08", "throughput": "0.00", "total_tokens": 0}
46
+ {"current_steps": 460, "total_steps": 3402, "loss": 0.1707, "learning_rate": 3.885531856820726e-05, "epoch": 0.4056437389770723, "percentage": 13.52, "elapsed_time": "1:01:33", "remaining_time": "6:33:44", "throughput": "0.00", "total_tokens": 0}
47
+ {"current_steps": 470, "total_steps": 3402, "loss": 0.1702, "learning_rate": 3.8790955611527754e-05, "epoch": 0.4144620811287478, "percentage": 13.82, "elapsed_time": "1:02:53", "remaining_time": "6:32:21", "throughput": "0.00", "total_tokens": 0}
48
+ {"current_steps": 480, "total_steps": 3402, "loss": 0.1688, "learning_rate": 3.872488861126226e-05, "epoch": 0.42328042328042326, "percentage": 14.11, "elapsed_time": "1:04:13", "remaining_time": "6:30:57", "throughput": "0.00", "total_tokens": 0}
49
+ {"current_steps": 490, "total_steps": 3402, "loss": 0.169, "learning_rate": 3.865712355864668e-05, "epoch": 0.43209876543209874, "percentage": 14.4, "elapsed_time": "1:05:33", "remaining_time": "6:29:34", "throughput": "0.00", "total_tokens": 0}
50
+ {"current_steps": 500, "total_steps": 3402, "loss": 0.1672, "learning_rate": 3.8587666598903526e-05, "epoch": 0.4409171075837742, "percentage": 14.7, "elapsed_time": "1:06:52", "remaining_time": "6:28:11", "throughput": "0.00", "total_tokens": 0}
51
+ {"current_steps": 510, "total_steps": 3402, "loss": 0.1726, "learning_rate": 3.851652403068461e-05, "epoch": 0.4497354497354497, "percentage": 14.99, "elapsed_time": "1:08:12", "remaining_time": "6:26:48", "throughput": "0.00", "total_tokens": 0}
52
+ {"current_steps": 520, "total_steps": 3402, "loss": 0.1704, "learning_rate": 3.8443702305499886e-05, "epoch": 0.4585537918871252, "percentage": 15.29, "elapsed_time": "1:09:32", "remaining_time": "6:25:25", "throughput": "0.00", "total_tokens": 0}
53
+ {"current_steps": 530, "total_steps": 3402, "loss": 0.1671, "learning_rate": 3.836920802713238e-05, "epoch": 0.4673721340388007, "percentage": 15.58, "elapsed_time": "1:10:52", "remaining_time": "6:24:02", "throughput": "0.00", "total_tokens": 0}
54
+ {"current_steps": 540, "total_steps": 3402, "loss": 0.1672, "learning_rate": 3.829304795103933e-05, "epoch": 0.47619047619047616, "percentage": 15.87, "elapsed_time": "1:12:12", "remaining_time": "6:22:39", "throughput": "0.00", "total_tokens": 0}
55
+ {"current_steps": 550, "total_steps": 3402, "loss": 0.1666, "learning_rate": 3.82152289837396e-05, "epoch": 0.48500881834215165, "percentage": 16.17, "elapsed_time": "1:13:31", "remaining_time": "6:21:17", "throughput": "0.00", "total_tokens": 0}
56
+ {"current_steps": 560, "total_steps": 3402, "loss": 0.1686, "learning_rate": 3.813575818218732e-05, "epoch": 0.49382716049382713, "percentage": 16.46, "elapsed_time": "1:14:51", "remaining_time": "6:19:54", "throughput": "0.00", "total_tokens": 0}
57
+ {"current_steps": 570, "total_steps": 3402, "loss": 0.1669, "learning_rate": 3.8054642753132e-05, "epoch": 0.5026455026455027, "percentage": 16.75, "elapsed_time": "1:16:11", "remaining_time": "6:18:32", "throughput": "0.00", "total_tokens": 0}
58
+ {"current_steps": 580, "total_steps": 3402, "loss": 0.1622, "learning_rate": 3.797189005246489e-05, "epoch": 0.5114638447971781, "percentage": 17.05, "elapsed_time": "1:17:31", "remaining_time": "6:17:10", "throughput": "0.00", "total_tokens": 0}
59
+ {"current_steps": 590, "total_steps": 3402, "loss": 0.1629, "learning_rate": 3.788750758455204e-05, "epoch": 0.5202821869488536, "percentage": 17.34, "elapsed_time": "1:18:50", "remaining_time": "6:15:48", "throughput": "0.00", "total_tokens": 0}
60
+ {"current_steps": 600, "total_steps": 3402, "loss": 0.1682, "learning_rate": 3.7801503001553664e-05, "epoch": 0.5291005291005291, "percentage": 17.64, "elapsed_time": "1:20:10", "remaining_time": "6:14:26", "throughput": "0.00", "total_tokens": 0}
61
+ {"current_steps": 610, "total_steps": 3402, "loss": 0.1672, "learning_rate": 3.771388410273027e-05, "epoch": 0.5379188712522046, "percentage": 17.93, "elapsed_time": "1:21:30", "remaining_time": "6:13:04", "throughput": "0.00", "total_tokens": 0}
62
+ {"current_steps": 620, "total_steps": 3402, "loss": 0.1618, "learning_rate": 3.762465883373539e-05, "epoch": 0.54673721340388, "percentage": 18.22, "elapsed_time": "1:22:50", "remaining_time": "6:11:41", "throughput": "0.00", "total_tokens": 0}
63
+ {"current_steps": 630, "total_steps": 3402, "loss": 0.1639, "learning_rate": 3.753383528589499e-05, "epoch": 0.5555555555555556, "percentage": 18.52, "elapsed_time": "1:24:10", "remaining_time": "6:10:20", "throughput": "0.00", "total_tokens": 0}
64
+ {"current_steps": 640, "total_steps": 3402, "loss": 0.1603, "learning_rate": 3.744142169547376e-05, "epoch": 0.564373897707231, "percentage": 18.81, "elapsed_time": "1:25:29", "remaining_time": "6:08:59", "throughput": "0.00", "total_tokens": 0}
65
+ {"current_steps": 650, "total_steps": 3402, "loss": 0.1627, "learning_rate": 3.734742644292821e-05, "epoch": 0.5731922398589065, "percentage": 19.11, "elapsed_time": "1:26:50", "remaining_time": "6:07:38", "throughput": "0.00", "total_tokens": 0}
66
+ {"current_steps": 660, "total_steps": 3402, "loss": 0.1639, "learning_rate": 3.725185805214665e-05, "epoch": 0.582010582010582, "percentage": 19.4, "elapsed_time": "1:28:09", "remaining_time": "6:06:17", "throughput": "0.00", "total_tokens": 0}
67
+ {"current_steps": 670, "total_steps": 3402, "loss": 0.1619, "learning_rate": 3.7154725189676264e-05, "epoch": 0.5908289241622575, "percentage": 19.69, "elapsed_time": "1:29:30", "remaining_time": "6:04:59", "throughput": "0.00", "total_tokens": 0}
68
+ {"current_steps": 680, "total_steps": 3402, "loss": 0.165, "learning_rate": 3.7056036663937164e-05, "epoch": 0.599647266313933, "percentage": 19.99, "elapsed_time": "1:30:53", "remaining_time": "6:03:51", "throughput": "0.00", "total_tokens": 0}
69
+ {"current_steps": 690, "total_steps": 3402, "loss": 0.1614, "learning_rate": 3.695580142442361e-05, "epoch": 0.6084656084656085, "percentage": 20.28, "elapsed_time": "1:32:15", "remaining_time": "6:02:38", "throughput": "0.00", "total_tokens": 0}
70
+ {"current_steps": 700, "total_steps": 3402, "loss": 0.1618, "learning_rate": 3.685402856089242e-05, "epoch": 0.6172839506172839, "percentage": 20.58, "elapsed_time": "1:33:35", "remaining_time": "6:01:17", "throughput": "0.00", "total_tokens": 0}
71
+ {"current_steps": 710, "total_steps": 3402, "loss": 0.1655, "learning_rate": 3.675072730253868e-05, "epoch": 0.6261022927689595, "percentage": 20.87, "elapsed_time": "1:34:55", "remaining_time": "5:59:55", "throughput": "0.00", "total_tokens": 0}
72
+ {"current_steps": 720, "total_steps": 3402, "loss": 0.1608, "learning_rate": 3.6645907017158814e-05, "epoch": 0.6349206349206349, "percentage": 21.16, "elapsed_time": "1:36:15", "remaining_time": "5:58:35", "throughput": "0.00", "total_tokens": 0}
73
+ {"current_steps": 730, "total_steps": 3402, "loss": 0.1606, "learning_rate": 3.653957721030107e-05, "epoch": 0.6437389770723104, "percentage": 21.46, "elapsed_time": "1:37:35", "remaining_time": "5:57:13", "throughput": "0.00", "total_tokens": 0}
74
+ {"current_steps": 740, "total_steps": 3402, "loss": 0.1624, "learning_rate": 3.64317475244035e-05, "epoch": 0.6525573192239859, "percentage": 21.75, "elapsed_time": "1:38:55", "remaining_time": "5:55:51", "throughput": "0.00", "total_tokens": 0}
75
+ {"current_steps": 750, "total_steps": 3402, "loss": 0.1605, "learning_rate": 3.632242773791952e-05, "epoch": 0.6613756613756614, "percentage": 22.05, "elapsed_time": "1:40:15", "remaining_time": "5:54:30", "throughput": "0.00", "total_tokens": 0}
76
+ {"current_steps": 760, "total_steps": 3402, "loss": 0.1597, "learning_rate": 3.621162776443125e-05, "epoch": 0.6701940035273368, "percentage": 22.34, "elapsed_time": "1:41:35", "remaining_time": "5:53:08", "throughput": "0.00", "total_tokens": 0}
77
+ {"current_steps": 770, "total_steps": 3402, "loss": 0.1609, "learning_rate": 3.60993576517504e-05, "epoch": 0.6790123456790124, "percentage": 22.63, "elapsed_time": "1:42:54", "remaining_time": "5:51:47", "throughput": "0.00", "total_tokens": 0}
78
+ {"current_steps": 780, "total_steps": 3402, "loss": 0.1607, "learning_rate": 3.598562758100716e-05, "epoch": 0.6878306878306878, "percentage": 22.93, "elapsed_time": "1:44:14", "remaining_time": "5:50:25", "throughput": "0.00", "total_tokens": 0}
79
+ {"current_steps": 790, "total_steps": 3402, "loss": 0.1606, "learning_rate": 3.5870447865726913e-05, "epoch": 0.6966490299823633, "percentage": 23.22, "elapsed_time": "1:45:34", "remaining_time": "5:49:03", "throughput": "0.00", "total_tokens": 0}
80
+ {"current_steps": 800, "total_steps": 3402, "loss": 0.161, "learning_rate": 3.575382895089495e-05, "epoch": 0.7054673721340388, "percentage": 23.52, "elapsed_time": "1:46:54", "remaining_time": "5:47:42", "throughput": "0.00", "total_tokens": 0}
81
+ {"current_steps": 810, "total_steps": 3402, "loss": 0.1592, "learning_rate": 3.563578141200929e-05, "epoch": 0.7142857142857143, "percentage": 23.81, "elapsed_time": "1:48:14", "remaining_time": "5:46:20", "throughput": "0.00", "total_tokens": 0}
82
+ {"current_steps": 820, "total_steps": 3402, "loss": 0.1596, "learning_rate": 3.551631595412164e-05, "epoch": 0.7231040564373897, "percentage": 24.1, "elapsed_time": "1:49:33", "remaining_time": "5:44:59", "throughput": "0.00", "total_tokens": 0}
83
+ {"current_steps": 830, "total_steps": 3402, "loss": 0.1565, "learning_rate": 3.539544341086663e-05, "epoch": 0.7319223985890653, "percentage": 24.4, "elapsed_time": "1:50:53", "remaining_time": "5:43:38", "throughput": "0.00", "total_tokens": 0}
84
+ {"current_steps": 840, "total_steps": 3402, "loss": 0.1581, "learning_rate": 3.5273174743479336e-05, "epoch": 0.7407407407407407, "percentage": 24.69, "elapsed_time": "1:52:13", "remaining_time": "5:42:17", "throughput": "0.00", "total_tokens": 0}
85
+ {"current_steps": 850, "total_steps": 3402, "loss": 0.1598, "learning_rate": 3.514952103980132e-05, "epoch": 0.7495590828924162, "percentage": 24.99, "elapsed_time": "1:53:33", "remaining_time": "5:40:55", "throughput": "0.00", "total_tokens": 0}
86
+ {"current_steps": 860, "total_steps": 3402, "loss": 0.1586, "learning_rate": 3.50244935132751e-05, "epoch": 0.7583774250440917, "percentage": 25.28, "elapsed_time": "1:54:53", "remaining_time": "5:39:34", "throughput": "0.00", "total_tokens": 0}
87
+ {"current_steps": 870, "total_steps": 3402, "loss": 0.1559, "learning_rate": 3.489810350192729e-05, "epoch": 0.7671957671957672, "percentage": 25.57, "elapsed_time": "1:56:12", "remaining_time": "5:38:13", "throughput": "0.00", "total_tokens": 0}
88
+ {"current_steps": 880, "total_steps": 3402, "loss": 0.1563, "learning_rate": 3.477036246734038e-05, "epoch": 0.7760141093474426, "percentage": 25.87, "elapsed_time": "1:57:32", "remaining_time": "5:36:52", "throughput": "0.00", "total_tokens": 0}
89
+ {"current_steps": 890, "total_steps": 3402, "loss": 0.1596, "learning_rate": 3.4641281993613406e-05, "epoch": 0.7848324514991182, "percentage": 26.16, "elapsed_time": "1:58:52", "remaining_time": "5:35:31", "throughput": "0.00", "total_tokens": 0}
90
+ {"current_steps": 900, "total_steps": 3402, "loss": 0.1579, "learning_rate": 3.451087378631143e-05, "epoch": 0.7936507936507936, "percentage": 26.46, "elapsed_time": "2:00:12", "remaining_time": "5:34:10", "throughput": "0.00", "total_tokens": 0}
91
+ {"current_steps": 910, "total_steps": 3402, "loss": 0.1571, "learning_rate": 3.437914967140401e-05, "epoch": 0.8024691358024691, "percentage": 26.75, "elapsed_time": "2:01:32", "remaining_time": "5:32:48", "throughput": "0.00", "total_tokens": 0}
92
+ {"current_steps": 920, "total_steps": 3402, "loss": 0.157, "learning_rate": 3.4246121594192814e-05, "epoch": 0.8112874779541446, "percentage": 27.04, "elapsed_time": "2:02:51", "remaining_time": "5:31:27", "throughput": "0.00", "total_tokens": 0}
93
+ {"current_steps": 930, "total_steps": 3402, "loss": 0.1554, "learning_rate": 3.411180161822831e-05, "epoch": 0.8201058201058201, "percentage": 27.34, "elapsed_time": "2:04:11", "remaining_time": "5:30:06", "throughput": "0.00", "total_tokens": 0}
94
+ {"current_steps": 940, "total_steps": 3402, "loss": 0.1557, "learning_rate": 3.3976201924215854e-05, "epoch": 0.8289241622574955, "percentage": 27.63, "elapsed_time": "2:05:31", "remaining_time": "5:28:45", "throughput": "0.00", "total_tokens": 0}
95
+ {"current_steps": 950, "total_steps": 3402, "loss": 0.155, "learning_rate": 3.3839334808911057e-05, "epoch": 0.8377425044091711, "percentage": 27.92, "elapsed_time": "2:06:51", "remaining_time": "5:27:24", "throughput": "0.00", "total_tokens": 0}
96
+ {"current_steps": 960, "total_steps": 3402, "loss": 0.1554, "learning_rate": 3.370121268400467e-05, "epoch": 0.8465608465608465, "percentage": 28.22, "elapsed_time": "2:08:10", "remaining_time": "5:26:03", "throughput": "0.00", "total_tokens": 0}
97
+ {"current_steps": 970, "total_steps": 3402, "loss": 0.1543, "learning_rate": 3.356184807499705e-05, "epoch": 0.855379188712522, "percentage": 28.51, "elapsed_time": "2:09:30", "remaining_time": "5:24:42", "throughput": "0.00", "total_tokens": 0}
98
+ {"current_steps": 980, "total_steps": 3402, "loss": 0.1552, "learning_rate": 3.342125362006226e-05, "epoch": 0.8641975308641975, "percentage": 28.81, "elapsed_time": "2:10:50", "remaining_time": "5:23:21", "throughput": "0.00", "total_tokens": 0}
99
+ {"current_steps": 990, "total_steps": 3402, "loss": 0.155, "learning_rate": 3.3279442068902024e-05, "epoch": 0.873015873015873, "percentage": 29.1, "elapsed_time": "2:12:10", "remaining_time": "5:22:01", "throughput": "0.00", "total_tokens": 0}
100
+ {"current_steps": 1000, "total_steps": 3402, "loss": 0.1559, "learning_rate": 3.3136426281589525e-05, "epoch": 0.8818342151675485, "percentage": 29.39, "elapsed_time": "2:13:30", "remaining_time": "5:20:40", "throughput": "0.00", "total_tokens": 0}
101
+ {"current_steps": 1010, "total_steps": 3402, "loss": 0.1555, "learning_rate": 3.299221922740318e-05, "epoch": 0.890652557319224, "percentage": 29.69, "elapsed_time": "2:14:49", "remaining_time": "5:19:19", "throughput": "0.00", "total_tokens": 0}
102
+ {"current_steps": 1020, "total_steps": 3402, "loss": 0.1544, "learning_rate": 3.284683398365053e-05, "epoch": 0.8994708994708994, "percentage": 29.98, "elapsed_time": "2:16:09", "remaining_time": "5:17:58", "throughput": "0.00", "total_tokens": 0}
103
+ {"current_steps": 1030, "total_steps": 3402, "loss": 0.156, "learning_rate": 3.270028373448237e-05, "epoch": 0.908289241622575, "percentage": 30.28, "elapsed_time": "2:17:29", "remaining_time": "5:16:38", "throughput": "0.00", "total_tokens": 0}
104
+ {"current_steps": 1040, "total_steps": 3402, "loss": 0.1525, "learning_rate": 3.255258176969711e-05, "epoch": 0.9171075837742504, "percentage": 30.57, "elapsed_time": "2:18:49", "remaining_time": "5:15:17", "throughput": "0.00", "total_tokens": 0}
105
+ {"current_steps": 1050, "total_steps": 3402, "loss": 0.1579, "learning_rate": 3.2403741483535624e-05, "epoch": 0.9259259259259259, "percentage": 30.86, "elapsed_time": "2:20:09", "remaining_time": "5:13:56", "throughput": "0.00", "total_tokens": 0}
106
+ {"current_steps": 1060, "total_steps": 3402, "loss": 0.1545, "learning_rate": 3.22537763734666e-05, "epoch": 0.9347442680776014, "percentage": 31.16, "elapsed_time": "2:21:28", "remaining_time": "5:12:35", "throughput": "0.00", "total_tokens": 0}
107
+ {"current_steps": 1070, "total_steps": 3402, "loss": 0.1523, "learning_rate": 3.210270003896254e-05, "epoch": 0.9435626102292769, "percentage": 31.45, "elapsed_time": "2:22:49", "remaining_time": "5:11:15", "throughput": "0.00", "total_tokens": 0}
108
+ {"current_steps": 1080, "total_steps": 3402, "loss": 0.1498, "learning_rate": 3.195052618026646e-05, "epoch": 0.9523809523809523, "percentage": 31.75, "elapsed_time": "2:24:08", "remaining_time": "5:09:54", "throughput": "0.00", "total_tokens": 0}
109
+ {"current_steps": 1090, "total_steps": 3402, "loss": 0.1533, "learning_rate": 3.1797268597149575e-05, "epoch": 0.9611992945326279, "percentage": 32.04, "elapsed_time": "2:25:29", "remaining_time": "5:08:36", "throughput": "0.00", "total_tokens": 0}
110
+ {"current_steps": 1100, "total_steps": 3402, "loss": 0.1505, "learning_rate": 3.1642941187659784e-05, "epoch": 0.9700176366843033, "percentage": 32.33, "elapsed_time": "2:26:50", "remaining_time": "5:07:18", "throughput": "0.00", "total_tokens": 0}
111
+ {"current_steps": 1110, "total_steps": 3402, "loss": 0.154, "learning_rate": 3.1487557946861413e-05, "epoch": 0.9788359788359788, "percentage": 32.63, "elapsed_time": "2:28:11", "remaining_time": "5:06:00", "throughput": "0.00", "total_tokens": 0}
112
+ {"current_steps": 1120, "total_steps": 3402, "loss": 0.1495, "learning_rate": 3.133113296556603e-05, "epoch": 0.9876543209876543, "percentage": 32.92, "elapsed_time": "2:29:32", "remaining_time": "5:04:41", "throughput": "0.00", "total_tokens": 0}
113
+ {"current_steps": 1130, "total_steps": 3402, "loss": 0.1517, "learning_rate": 3.117368042905466e-05, "epoch": 0.9964726631393298, "percentage": 33.22, "elapsed_time": "2:30:53", "remaining_time": "5:03:24", "throughput": "0.00", "total_tokens": 0}
114
+ {"current_steps": 1140, "total_steps": 3402, "loss": 0.1409, "learning_rate": 3.101521461579139e-05, "epoch": 1.0052910052910053, "percentage": 33.51, "elapsed_time": "2:32:50", "remaining_time": "5:03:15", "throughput": "0.00", "total_tokens": 0}
115
+ {"current_steps": 1150, "total_steps": 3402, "loss": 0.1321, "learning_rate": 3.085574989612856e-05, "epoch": 1.0141093474426808, "percentage": 33.8, "elapsed_time": "2:34:10", "remaining_time": "5:01:54", "throughput": "0.00", "total_tokens": 0}
116
+ {"current_steps": 1160, "total_steps": 3402, "loss": 0.1313, "learning_rate": 3.069530073100356e-05, "epoch": 1.0229276895943562, "percentage": 34.1, "elapsed_time": "2:35:30", "remaining_time": "5:00:32", "throughput": "0.00", "total_tokens": 0}
117
+ {"current_steps": 1170, "total_steps": 3402, "loss": 0.1321, "learning_rate": 3.053388167062747e-05, "epoch": 1.0317460317460316, "percentage": 34.39, "elapsed_time": "2:36:49", "remaining_time": "4:59:11", "throughput": "0.00", "total_tokens": 0}
118
+ {"current_steps": 1180, "total_steps": 3402, "loss": 0.1332, "learning_rate": 3.037150735316561e-05, "epoch": 1.0405643738977073, "percentage": 34.69, "elapsed_time": "2:38:09", "remaining_time": "4:57:49", "throughput": "0.00", "total_tokens": 0}
119
+ {"current_steps": 1190, "total_steps": 3402, "loss": 0.131, "learning_rate": 3.0208192503410046e-05, "epoch": 1.0493827160493827, "percentage": 34.98, "elapsed_time": "2:39:29", "remaining_time": "4:56:27", "throughput": "0.00", "total_tokens": 0}
120
+ {"current_steps": 1200, "total_steps": 3402, "loss": 0.1327, "learning_rate": 3.0043951931444302e-05, "epoch": 1.0582010582010581, "percentage": 35.27, "elapsed_time": "2:40:49", "remaining_time": "4:55:06", "throughput": "0.00", "total_tokens": 0}
121
+ {"current_steps": 1210, "total_steps": 3402, "loss": 0.1337, "learning_rate": 2.9878800531300335e-05, "epoch": 1.0670194003527338, "percentage": 35.57, "elapsed_time": "2:42:09", "remaining_time": "4:53:45", "throughput": "0.00", "total_tokens": 0}
122
+ {"current_steps": 1220, "total_steps": 3402, "loss": 0.1364, "learning_rate": 2.9712753279607852e-05, "epoch": 1.0758377425044092, "percentage": 35.86, "elapsed_time": "2:43:29", "remaining_time": "4:52:23", "throughput": "0.00", "total_tokens": 0}
123
+ {"current_steps": 1230, "total_steps": 3402, "loss": 0.1306, "learning_rate": 2.9545825234236187e-05, "epoch": 1.0846560846560847, "percentage": 36.16, "elapsed_time": "2:44:48", "remaining_time": "4:51:02", "throughput": "0.00", "total_tokens": 0}
124
+ {"current_steps": 1240, "total_steps": 3402, "loss": 0.1342, "learning_rate": 2.937803153292878e-05, "epoch": 1.09347442680776, "percentage": 36.45, "elapsed_time": "2:46:08", "remaining_time": "4:49:40", "throughput": "0.00", "total_tokens": 0}
125
+ {"current_steps": 1250, "total_steps": 3402, "loss": 0.1341, "learning_rate": 2.9209387391930425e-05, "epoch": 1.1022927689594355, "percentage": 36.74, "elapsed_time": "2:47:28", "remaining_time": "4:48:19", "throughput": "0.00", "total_tokens": 0}
126
+ {"current_steps": 1260, "total_steps": 3402, "loss": 0.1333, "learning_rate": 2.9039908104607395e-05, "epoch": 1.1111111111111112, "percentage": 37.04, "elapsed_time": "2:48:48", "remaining_time": "4:46:57", "throughput": "0.00", "total_tokens": 0}
127
+ {"current_steps": 1270, "total_steps": 3402, "loss": 0.1336, "learning_rate": 2.8869609040060572e-05, "epoch": 1.1199294532627866, "percentage": 37.33, "elapsed_time": "2:50:08", "remaining_time": "4:45:36", "throughput": "0.00", "total_tokens": 0}
128
+ {"current_steps": 1280, "total_steps": 3402, "loss": 0.1323, "learning_rate": 2.869850564173172e-05, "epoch": 1.128747795414462, "percentage": 37.62, "elapsed_time": "2:51:27", "remaining_time": "4:44:15", "throughput": "0.00", "total_tokens": 0}
129
+ {"current_steps": 1290, "total_steps": 3402, "loss": 0.1319, "learning_rate": 2.8526613426002998e-05, "epoch": 1.1375661375661377, "percentage": 37.92, "elapsed_time": "2:52:47", "remaining_time": "4:42:54", "throughput": "0.00", "total_tokens": 0}
130
+ {"current_steps": 1300, "total_steps": 3402, "loss": 0.1321, "learning_rate": 2.835394798078988e-05, "epoch": 1.146384479717813, "percentage": 38.21, "elapsed_time": "2:54:07", "remaining_time": "4:41:32", "throughput": "0.00", "total_tokens": 0}
131
+ {"current_steps": 1310, "total_steps": 3402, "loss": 0.1317, "learning_rate": 2.8180524964127573e-05, "epoch": 1.1552028218694885, "percentage": 38.51, "elapsed_time": "2:55:27", "remaining_time": "4:40:11", "throughput": "0.00", "total_tokens": 0}
132
+ {"current_steps": 1320, "total_steps": 3402, "loss": 0.1322, "learning_rate": 2.8006360102751064e-05, "epoch": 1.164021164021164, "percentage": 38.8, "elapsed_time": "2:56:47", "remaining_time": "4:38:50", "throughput": "0.00", "total_tokens": 0}
133
+ {"current_steps": 1330, "total_steps": 3402, "loss": 0.133, "learning_rate": 2.7831469190668974e-05, "epoch": 1.1728395061728394, "percentage": 39.09, "elapsed_time": "2:58:06", "remaining_time": "4:37:29", "throughput": "0.00", "total_tokens": 0}
134
+ {"current_steps": 1340, "total_steps": 3402, "loss": 0.1317, "learning_rate": 2.7655868087731295e-05, "epoch": 1.181657848324515, "percentage": 39.39, "elapsed_time": "2:59:26", "remaining_time": "4:36:07", "throughput": "0.00", "total_tokens": 0}
135
+ {"current_steps": 1350, "total_steps": 3402, "loss": 0.1333, "learning_rate": 2.7479572718191108e-05, "epoch": 1.1904761904761905, "percentage": 39.68, "elapsed_time": "3:00:46", "remaining_time": "4:34:46", "throughput": "0.00", "total_tokens": 0}
136
+ {"current_steps": 1360, "total_steps": 3402, "loss": 0.1309, "learning_rate": 2.7302599069260572e-05, "epoch": 1.199294532627866, "percentage": 39.98, "elapsed_time": "3:02:06", "remaining_time": "4:33:25", "throughput": "0.00", "total_tokens": 0}
137
+ {"current_steps": 1370, "total_steps": 3402, "loss": 0.1314, "learning_rate": 2.712496318966108e-05, "epoch": 1.2081128747795415, "percentage": 40.27, "elapsed_time": "3:03:26", "remaining_time": "4:32:04", "throughput": "0.00", "total_tokens": 0}
138
+ {"current_steps": 1380, "total_steps": 3402, "loss": 0.1334, "learning_rate": 2.69466811881679e-05, "epoch": 1.216931216931217, "percentage": 40.56, "elapsed_time": "3:04:45", "remaining_time": "4:30:43", "throughput": "0.00", "total_tokens": 0}
139
+ {"current_steps": 1390, "total_steps": 3402, "loss": 0.1331, "learning_rate": 2.67677692321494e-05, "epoch": 1.2257495590828924, "percentage": 40.86, "elapsed_time": "3:06:05", "remaining_time": "4:29:22", "throughput": "0.00", "total_tokens": 0}
140
+ {"current_steps": 1400, "total_steps": 3402, "loss": 0.1313, "learning_rate": 2.6588243546100882e-05, "epoch": 1.2345679012345678, "percentage": 41.15, "elapsed_time": "3:07:25", "remaining_time": "4:28:01", "throughput": "0.00", "total_tokens": 0}
141
+ {"current_steps": 1410, "total_steps": 3402, "loss": 0.1287, "learning_rate": 2.6408120410173296e-05, "epoch": 1.2433862433862433, "percentage": 41.45, "elapsed_time": "3:08:45", "remaining_time": "4:26:40", "throughput": "0.00", "total_tokens": 0}
142
+ {"current_steps": 1420, "total_steps": 3402, "loss": 0.1297, "learning_rate": 2.6227416158696884e-05, "epoch": 1.252204585537919, "percentage": 41.74, "elapsed_time": "3:10:05", "remaining_time": "4:25:19", "throughput": "0.00", "total_tokens": 0}
143
+ {"current_steps": 1430, "total_steps": 3402, "loss": 0.1309, "learning_rate": 2.60461471786999e-05, "epoch": 1.2610229276895943, "percentage": 42.03, "elapsed_time": "3:11:25", "remaining_time": "4:23:58", "throughput": "0.00", "total_tokens": 0}
144
+ {"current_steps": 1440, "total_steps": 3402, "loss": 0.1292, "learning_rate": 2.5864329908422597e-05, "epoch": 1.2698412698412698, "percentage": 42.33, "elapsed_time": "3:12:45", "remaining_time": "4:22:37", "throughput": "0.00", "total_tokens": 0}
145
+ {"current_steps": 1450, "total_steps": 3402, "loss": 0.1295, "learning_rate": 2.5681980835826503e-05, "epoch": 1.2786596119929454, "percentage": 42.62, "elapsed_time": "3:14:05", "remaining_time": "4:21:16", "throughput": "0.00", "total_tokens": 0}
146
+ {"current_steps": 1460, "total_steps": 3402, "loss": 0.1314, "learning_rate": 2.5499116497099224e-05, "epoch": 1.2874779541446209, "percentage": 42.92, "elapsed_time": "3:15:25", "remaining_time": "4:19:57", "throughput": "0.00", "total_tokens": 0}
147
+ {"current_steps": 1470, "total_steps": 3402, "loss": 0.1318, "learning_rate": 2.531575347515492e-05, "epoch": 1.2962962962962963, "percentage": 43.21, "elapsed_time": "3:16:47", "remaining_time": "4:18:38", "throughput": "0.00", "total_tokens": 0}
148
+ {"current_steps": 1480, "total_steps": 3402, "loss": 0.1291, "learning_rate": 2.5131908398130426e-05, "epoch": 1.3051146384479717, "percentage": 43.5, "elapsed_time": "3:18:09", "remaining_time": "4:17:20", "throughput": "0.00", "total_tokens": 0}
149
+ {"current_steps": 1490, "total_steps": 3402, "loss": 0.1299, "learning_rate": 2.49475979378774e-05, "epoch": 1.3139329805996471, "percentage": 43.8, "elapsed_time": "3:19:31", "remaining_time": "4:16:01", "throughput": "0.00", "total_tokens": 0}
150
+ {"current_steps": 1500, "total_steps": 3402, "loss": 0.1333, "learning_rate": 2.476283880845042e-05, "epoch": 1.3227513227513228, "percentage": 44.09, "elapsed_time": "3:20:52", "remaining_time": "4:14:42", "throughput": "0.00", "total_tokens": 0}
151
+ {"current_steps": 1510, "total_steps": 3402, "loss": 0.1311, "learning_rate": 2.4577647764591276e-05, "epoch": 1.3315696649029982, "percentage": 44.39, "elapsed_time": "3:22:14", "remaining_time": "4:13:24", "throughput": "0.00", "total_tokens": 0}
152
+ {"current_steps": 1520, "total_steps": 3402, "loss": 0.1298, "learning_rate": 2.4392041600209608e-05, "epoch": 1.3403880070546736, "percentage": 44.68, "elapsed_time": "3:23:35", "remaining_time": "4:12:04", "throughput": "0.00", "total_tokens": 0}
153
+ {"current_steps": 1530, "total_steps": 3402, "loss": 0.1266, "learning_rate": 2.4206037146859944e-05, "epoch": 1.3492063492063493, "percentage": 44.97, "elapsed_time": "3:24:55", "remaining_time": "4:10:43", "throughput": "0.00", "total_tokens": 0}
154
+ {"current_steps": 1540, "total_steps": 3402, "loss": 0.131, "learning_rate": 2.4019651272215338e-05, "epoch": 1.3580246913580247, "percentage": 45.27, "elapsed_time": "3:26:15", "remaining_time": "4:09:23", "throughput": "0.00", "total_tokens": 0}
155
+ {"current_steps": 1550, "total_steps": 3402, "loss": 0.1327, "learning_rate": 2.383290087853775e-05, "epoch": 1.3668430335097002, "percentage": 45.56, "elapsed_time": "3:27:35", "remaining_time": "4:08:02", "throughput": "0.00", "total_tokens": 0}
156
+ {"current_steps": 1560, "total_steps": 3402, "loss": 0.1328, "learning_rate": 2.364580290114527e-05, "epoch": 1.3756613756613756, "percentage": 45.86, "elapsed_time": "3:28:55", "remaining_time": "4:06:41", "throughput": "0.00", "total_tokens": 0}
157
+ {"current_steps": 1570, "total_steps": 3402, "loss": 0.1337, "learning_rate": 2.3458374306876355e-05, "epoch": 1.384479717813051, "percentage": 46.15, "elapsed_time": "3:30:15", "remaining_time": "4:05:20", "throughput": "0.00", "total_tokens": 0}
158
+ {"current_steps": 1580, "total_steps": 3402, "loss": 0.128, "learning_rate": 2.327063209255121e-05, "epoch": 1.3932980599647267, "percentage": 46.44, "elapsed_time": "3:31:35", "remaining_time": "4:03:59", "throughput": "0.00", "total_tokens": 0}
159
+ {"current_steps": 1590, "total_steps": 3402, "loss": 0.1294, "learning_rate": 2.308259328343042e-05, "epoch": 1.402116402116402, "percentage": 46.74, "elapsed_time": "3:32:55", "remaining_time": "4:02:38", "throughput": "0.00", "total_tokens": 0}
160
+ {"current_steps": 1600, "total_steps": 3402, "loss": 0.1291, "learning_rate": 2.289427493167107e-05, "epoch": 1.4109347442680775, "percentage": 47.03, "elapsed_time": "3:34:14", "remaining_time": "4:01:17", "throughput": "0.00", "total_tokens": 0}
161
+ {"current_steps": 1610, "total_steps": 3402, "loss": 0.1274, "learning_rate": 2.270569411478033e-05, "epoch": 1.4197530864197532, "percentage": 47.33, "elapsed_time": "3:35:34", "remaining_time": "3:59:56", "throughput": "0.00", "total_tokens": 0}
162
+ {"current_steps": 1620, "total_steps": 3402, "loss": 0.1297, "learning_rate": 2.251686793406684e-05, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "3:36:54", "remaining_time": "3:58:36", "throughput": "0.00", "total_tokens": 0}
163
+ {"current_steps": 1630, "total_steps": 3402, "loss": 0.1302, "learning_rate": 2.2327813513089875e-05, "epoch": 1.437389770723104, "percentage": 47.91, "elapsed_time": "3:38:14", "remaining_time": "3:57:15", "throughput": "0.00", "total_tokens": 0}
164
+ {"current_steps": 1640, "total_steps": 3402, "loss": 0.1285, "learning_rate": 2.213854799610649e-05, "epoch": 1.4462081128747795, "percentage": 48.21, "elapsed_time": "3:39:34", "remaining_time": "3:55:54", "throughput": "0.00", "total_tokens": 0}
165
+ {"current_steps": 1650, "total_steps": 3402, "loss": 0.1289, "learning_rate": 2.194908854651683e-05, "epoch": 1.455026455026455, "percentage": 48.5, "elapsed_time": "3:40:54", "remaining_time": "3:54:33", "throughput": "0.00", "total_tokens": 0}
166
+ {"current_steps": 1660, "total_steps": 3402, "loss": 0.1275, "learning_rate": 2.1759452345307675e-05, "epoch": 1.4638447971781305, "percentage": 48.79, "elapsed_time": "3:42:14", "remaining_time": "3:53:12", "throughput": "0.00", "total_tokens": 0}
167
+ {"current_steps": 1670, "total_steps": 3402, "loss": 0.1266, "learning_rate": 2.1569656589494386e-05, "epoch": 1.472663139329806, "percentage": 49.09, "elapsed_time": "3:43:33", "remaining_time": "3:51:51", "throughput": "0.00", "total_tokens": 0}
168
+ {"current_steps": 1680, "total_steps": 3402, "loss": 0.1271, "learning_rate": 2.137971849056142e-05, "epoch": 1.4814814814814814, "percentage": 49.38, "elapsed_time": "3:44:53", "remaining_time": "3:50:31", "throughput": "0.00", "total_tokens": 0}
169
+ {"current_steps": 1690, "total_steps": 3402, "loss": 0.1288, "learning_rate": 2.1189655272901498e-05, "epoch": 1.490299823633157, "percentage": 49.68, "elapsed_time": "3:46:13", "remaining_time": "3:49:10", "throughput": "0.00", "total_tokens": 0}
170
+ {"current_steps": 1700, "total_steps": 3402, "loss": 0.1274, "learning_rate": 2.0999484172253654e-05, "epoch": 1.4991181657848325, "percentage": 49.97, "elapsed_time": "3:47:33", "remaining_time": "3:47:49", "throughput": "0.00", "total_tokens": 0}
171
+ {"current_steps": 1710, "total_steps": 3402, "loss": 0.1268, "learning_rate": 2.08092224341402e-05, "epoch": 1.507936507936508, "percentage": 50.26, "elapsed_time": "3:48:53", "remaining_time": "3:46:28", "throughput": "0.00", "total_tokens": 0}
172
+ {"current_steps": 1720, "total_steps": 3402, "loss": 0.1269, "learning_rate": 2.0618887312302838e-05, "epoch": 1.5167548500881836, "percentage": 50.56, "elapsed_time": "3:50:13", "remaining_time": "3:45:07", "throughput": "0.00", "total_tokens": 0}
173
+ {"current_steps": 1730, "total_steps": 3402, "loss": 0.1327, "learning_rate": 2.042849606713802e-05, "epoch": 1.5255731922398588, "percentage": 50.85, "elapsed_time": "3:51:32", "remaining_time": "3:43:47", "throughput": "0.00", "total_tokens": 0}
174
+ {"current_steps": 1740, "total_steps": 3402, "loss": 0.1289, "learning_rate": 2.02380659641317e-05, "epoch": 1.5343915343915344, "percentage": 51.15, "elapsed_time": "3:52:52", "remaining_time": "3:42:26", "throughput": "0.00", "total_tokens": 0}
175
+ {"current_steps": 1750, "total_steps": 3402, "loss": 0.1241, "learning_rate": 2.004761427229363e-05, "epoch": 1.5432098765432098, "percentage": 51.44, "elapsed_time": "3:54:12", "remaining_time": "3:41:05", "throughput": "0.00", "total_tokens": 0}
176
+ {"current_steps": 1760, "total_steps": 3402, "loss": 0.1283, "learning_rate": 1.985715826259131e-05, "epoch": 1.5520282186948853, "percentage": 51.73, "elapsed_time": "3:55:32", "remaining_time": "3:39:44", "throughput": "0.00", "total_tokens": 0}
177
+ {"current_steps": 1770, "total_steps": 3402, "loss": 0.1268, "learning_rate": 1.966671520638383e-05, "epoch": 1.560846560846561, "percentage": 52.03, "elapsed_time": "3:56:52", "remaining_time": "3:38:24", "throughput": "0.00", "total_tokens": 0}
178
+ {"current_steps": 1780, "total_steps": 3402, "loss": 0.1281, "learning_rate": 1.947630237385558e-05, "epoch": 1.5696649029982364, "percentage": 52.32, "elapsed_time": "3:58:11", "remaining_time": "3:37:03", "throughput": "0.00", "total_tokens": 0}
179
+ {"current_steps": 1790, "total_steps": 3402, "loss": 0.128, "learning_rate": 1.9285937032450146e-05, "epoch": 1.5784832451499118, "percentage": 52.62, "elapsed_time": "3:59:31", "remaining_time": "3:35:42", "throughput": "0.00", "total_tokens": 0}
180
+ {"current_steps": 1800, "total_steps": 3402, "loss": 0.1264, "learning_rate": 1.909563644530443e-05, "epoch": 1.5873015873015874, "percentage": 52.91, "elapsed_time": "4:00:51", "remaining_time": "3:34:21", "throughput": "0.00", "total_tokens": 0}
181
+ {"current_steps": 1810, "total_steps": 3402, "loss": 0.1268, "learning_rate": 1.8905417869683113e-05, "epoch": 1.5961199294532626, "percentage": 53.2, "elapsed_time": "4:02:11", "remaining_time": "3:33:01", "throughput": "0.00", "total_tokens": 0}
182
+ {"current_steps": 1820, "total_steps": 3402, "loss": 0.1249, "learning_rate": 1.871529855541375e-05, "epoch": 1.6049382716049383, "percentage": 53.5, "elapsed_time": "4:03:31", "remaining_time": "3:31:40", "throughput": "0.00", "total_tokens": 0}
183
+ {"current_steps": 1830, "total_steps": 3402, "loss": 0.1269, "learning_rate": 1.8525295743322453e-05, "epoch": 1.6137566137566137, "percentage": 53.79, "elapsed_time": "4:04:51", "remaining_time": "3:30:20", "throughput": "0.00", "total_tokens": 0}
184
+ {"current_steps": 1840, "total_steps": 3402, "loss": 0.1273, "learning_rate": 1.8335426663670397e-05, "epoch": 1.6225749559082892, "percentage": 54.09, "elapsed_time": "4:06:11", "remaining_time": "3:28:59", "throughput": "0.00", "total_tokens": 0}
185
+ {"current_steps": 1850, "total_steps": 3402, "loss": 0.1255, "learning_rate": 1.8145708534591377e-05, "epoch": 1.6313932980599648, "percentage": 54.38, "elapsed_time": "4:07:31", "remaining_time": "3:27:38", "throughput": "0.00", "total_tokens": 0}
186
+ {"current_steps": 1860, "total_steps": 3402, "loss": 0.1283, "learning_rate": 1.79561585605303e-05, "epoch": 1.6402116402116402, "percentage": 54.67, "elapsed_time": "4:08:51", "remaining_time": "3:26:18", "throughput": "0.00", "total_tokens": 0}
187
+ {"current_steps": 1870, "total_steps": 3402, "loss": 0.1254, "learning_rate": 1.7766793930683094e-05, "epoch": 1.6490299823633157, "percentage": 54.97, "elapsed_time": "4:10:11", "remaining_time": "3:24:58", "throughput": "0.00", "total_tokens": 0}
188
+ {"current_steps": 1880, "total_steps": 3402, "loss": 0.1244, "learning_rate": 1.7577631817437888e-05, "epoch": 1.6578483245149913, "percentage": 55.26, "elapsed_time": "4:11:32", "remaining_time": "3:23:38", "throughput": "0.00", "total_tokens": 0}
189
+ {"current_steps": 1890, "total_steps": 3402, "loss": 0.1232, "learning_rate": 1.7388689374817722e-05, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "4:12:52", "remaining_time": "3:22:18", "throughput": "0.00", "total_tokens": 0}
190
+ {"current_steps": 1900, "total_steps": 3402, "loss": 0.1259, "learning_rate": 1.719998373692499e-05, "epoch": 1.6754850088183422, "percentage": 55.85, "elapsed_time": "4:14:15", "remaining_time": "3:20:59", "throughput": "0.00", "total_tokens": 0}
191
+ {"current_steps": 1910, "total_steps": 3402, "loss": 0.1241, "learning_rate": 1.7011532016387637e-05, "epoch": 1.6843033509700176, "percentage": 56.14, "elapsed_time": "4:15:36", "remaining_time": "3:19:40", "throughput": "0.00", "total_tokens": 0}
192
+ {"current_steps": 1920, "total_steps": 3402, "loss": 0.1248, "learning_rate": 1.682335130280728e-05, "epoch": 1.693121693121693, "percentage": 56.44, "elapsed_time": "4:16:57", "remaining_time": "3:18:20", "throughput": "0.00", "total_tokens": 0}
193
+ {"current_steps": 1930, "total_steps": 3402, "loss": 0.1209, "learning_rate": 1.663545866120949e-05, "epoch": 1.7019400352733687, "percentage": 56.73, "elapsed_time": "4:18:18", "remaining_time": "3:17:00", "throughput": "0.00", "total_tokens": 0}
194
+ {"current_steps": 1940, "total_steps": 3402, "loss": 0.1239, "learning_rate": 1.6447871130496257e-05, "epoch": 1.710758377425044, "percentage": 57.03, "elapsed_time": "4:19:39", "remaining_time": "3:15:40", "throughput": "0.00", "total_tokens": 0}
195
+ {"current_steps": 1950, "total_steps": 3402, "loss": 0.1261, "learning_rate": 1.62606057219008e-05, "epoch": 1.7195767195767195, "percentage": 57.32, "elapsed_time": "4:20:59", "remaining_time": "3:14:20", "throughput": "0.00", "total_tokens": 0}
196
+ {"current_steps": 1960, "total_steps": 3402, "loss": 0.1266, "learning_rate": 1.6073679417444946e-05, "epoch": 1.7283950617283952, "percentage": 57.61, "elapsed_time": "4:22:19", "remaining_time": "3:12:59", "throughput": "0.00", "total_tokens": 0}
197
+ {"current_steps": 1970, "total_steps": 3402, "loss": 0.1225, "learning_rate": 1.588710916839914e-05, "epoch": 1.7372134038800704, "percentage": 57.91, "elapsed_time": "4:23:39", "remaining_time": "3:11:39", "throughput": "0.00", "total_tokens": 0}
198
+ {"current_steps": 1980, "total_steps": 3402, "loss": 0.1249, "learning_rate": 1.570091189374518e-05, "epoch": 1.746031746031746, "percentage": 58.2, "elapsed_time": "4:24:59", "remaining_time": "3:10:18", "throughput": "0.00", "total_tokens": 0}
199
+ {"current_steps": 1990, "total_steps": 3402, "loss": 0.1254, "learning_rate": 1.5515104478641975e-05, "epoch": 1.7548500881834215, "percentage": 58.5, "elapsed_time": "4:26:19", "remaining_time": "3:08:58", "throughput": "0.00", "total_tokens": 0}
200
+ {"current_steps": 2000, "total_steps": 3402, "loss": 0.1236, "learning_rate": 1.5329703772894327e-05, "epoch": 1.763668430335097, "percentage": 58.79, "elapsed_time": "4:27:39", "remaining_time": "3:07:37", "throughput": "0.00", "total_tokens": 0}
201
+ {"current_steps": 2010, "total_steps": 3402, "loss": 0.1242, "learning_rate": 1.51447265894249e-05, "epoch": 1.7724867724867726, "percentage": 59.08, "elapsed_time": "4:28:59", "remaining_time": "3:06:16", "throughput": "0.00", "total_tokens": 0}
202
+ {"current_steps": 2020, "total_steps": 3402, "loss": 0.1245, "learning_rate": 1.4960189702749551e-05, "epoch": 1.781305114638448, "percentage": 59.38, "elapsed_time": "4:30:18", "remaining_time": "3:04:56", "throughput": "0.00", "total_tokens": 0}
203
+ {"current_steps": 2030, "total_steps": 3402, "loss": 0.1226, "learning_rate": 1.4776109847456173e-05, "epoch": 1.7901234567901234, "percentage": 59.67, "elapsed_time": "4:31:38", "remaining_time": "3:03:35", "throughput": "0.00", "total_tokens": 0}
204
+ {"current_steps": 2040, "total_steps": 3402, "loss": 0.1243, "learning_rate": 1.4592503716687107e-05, "epoch": 1.798941798941799, "percentage": 59.96, "elapsed_time": "4:32:58", "remaining_time": "3:02:15", "throughput": "0.00", "total_tokens": 0}
205
+ {"current_steps": 2050, "total_steps": 3402, "loss": 0.1216, "learning_rate": 1.4409387960625331e-05, "epoch": 1.8077601410934743, "percentage": 60.26, "elapsed_time": "4:34:18", "remaining_time": "3:00:54", "throughput": "0.00", "total_tokens": 0}
206
+ {"current_steps": 2060, "total_steps": 3402, "loss": 0.1249, "learning_rate": 1.422677918498459e-05, "epoch": 1.81657848324515, "percentage": 60.55, "elapsed_time": "4:35:38", "remaining_time": "2:59:34", "throughput": "0.00", "total_tokens": 0}
207
+ {"current_steps": 2070, "total_steps": 3402, "loss": 0.1251, "learning_rate": 1.4044693949503465e-05, "epoch": 1.8253968253968254, "percentage": 60.85, "elapsed_time": "4:36:58", "remaining_time": "2:58:13", "throughput": "0.00", "total_tokens": 0}
208
+ {"current_steps": 2080, "total_steps": 3402, "loss": 0.1228, "learning_rate": 1.3863148766443723e-05, "epoch": 1.8342151675485008, "percentage": 61.14, "elapsed_time": "4:38:18", "remaining_time": "2:56:52", "throughput": "0.00", "total_tokens": 0}
209
+ {"current_steps": 2090, "total_steps": 3402, "loss": 0.1221, "learning_rate": 1.368216009909286e-05, "epoch": 1.8430335097001764, "percentage": 61.43, "elapsed_time": "4:39:37", "remaining_time": "2:55:32", "throughput": "0.00", "total_tokens": 0}
210
+ {"current_steps": 2100, "total_steps": 3402, "loss": 0.123, "learning_rate": 1.3501744360271177e-05, "epoch": 1.8518518518518519, "percentage": 61.73, "elapsed_time": "4:40:57", "remaining_time": "2:54:11", "throughput": "0.00", "total_tokens": 0}
211
+ {"current_steps": 2110, "total_steps": 3402, "loss": 0.1187, "learning_rate": 1.3321917910843394e-05, "epoch": 1.8606701940035273, "percentage": 62.02, "elapsed_time": "4:42:17", "remaining_time": "2:52:51", "throughput": "0.00", "total_tokens": 0}
212
+ {"current_steps": 2120, "total_steps": 3402, "loss": 0.1222, "learning_rate": 1.3142697058234952e-05, "epoch": 1.869488536155203, "percentage": 62.32, "elapsed_time": "4:43:37", "remaining_time": "2:51:30", "throughput": "0.00", "total_tokens": 0}
213
+ {"current_steps": 2130, "total_steps": 3402, "loss": 0.1205, "learning_rate": 1.2964098054953209e-05, "epoch": 1.8783068783068781, "percentage": 62.61, "elapsed_time": "4:44:57", "remaining_time": "2:50:10", "throughput": "0.00", "total_tokens": 0}
214
+ {"current_steps": 2140, "total_steps": 3402, "loss": 0.1194, "learning_rate": 1.2786137097113594e-05, "epoch": 1.8871252204585538, "percentage": 62.9, "elapsed_time": "4:46:17", "remaining_time": "2:48:49", "throughput": "0.00", "total_tokens": 0}
215
+ {"current_steps": 2150, "total_steps": 3402, "loss": 0.1234, "learning_rate": 1.2608830322970865e-05, "epoch": 1.8959435626102292, "percentage": 63.2, "elapsed_time": "4:47:36", "remaining_time": "2:47:29", "throughput": "0.00", "total_tokens": 0}
216
+ {"current_steps": 2160, "total_steps": 3402, "loss": 0.1237, "learning_rate": 1.2432193811455609e-05, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "4:48:56", "remaining_time": "2:46:08", "throughput": "0.00", "total_tokens": 0}
217
+ {"current_steps": 2170, "total_steps": 3402, "loss": 0.1216, "learning_rate": 1.2256243580716187e-05, "epoch": 1.9135802469135803, "percentage": 63.79, "elapsed_time": "4:50:16", "remaining_time": "2:44:48", "throughput": "0.00", "total_tokens": 0}
218
+ {"current_steps": 2180, "total_steps": 3402, "loss": 0.122, "learning_rate": 1.2080995586666085e-05, "epoch": 1.9223985890652557, "percentage": 64.08, "elapsed_time": "4:51:36", "remaining_time": "2:43:27", "throughput": "0.00", "total_tokens": 0}
219
+ {"current_steps": 2190, "total_steps": 3402, "loss": 0.1236, "learning_rate": 1.1906465721536984e-05, "epoch": 1.9312169312169312, "percentage": 64.37, "elapsed_time": "4:52:56", "remaining_time": "2:42:06", "throughput": "0.00", "total_tokens": 0}
220
+ {"current_steps": 2200, "total_steps": 3402, "loss": 0.1214, "learning_rate": 1.17326698124376e-05, "epoch": 1.9400352733686068, "percentage": 64.67, "elapsed_time": "4:54:15", "remaining_time": "2:40:46", "throughput": "0.00", "total_tokens": 0}
221
+ {"current_steps": 2210, "total_steps": 3402, "loss": 0.1212, "learning_rate": 1.1559623619918396e-05, "epoch": 1.948853615520282, "percentage": 64.96, "elapsed_time": "4:55:35", "remaining_time": "2:39:25", "throughput": "0.00", "total_tokens": 0}
222
+ {"current_steps": 2220, "total_steps": 3402, "loss": 0.1203, "learning_rate": 1.1387342836542353e-05, "epoch": 1.9576719576719577, "percentage": 65.26, "elapsed_time": "4:56:55", "remaining_time": "2:38:05", "throughput": "0.00", "total_tokens": 0}
223
+ {"current_steps": 2230, "total_steps": 3402, "loss": 0.1187, "learning_rate": 1.1215843085461912e-05, "epoch": 1.966490299823633, "percentage": 65.55, "elapsed_time": "4:58:15", "remaining_time": "2:36:45", "throughput": "0.00", "total_tokens": 0}
224
+ {"current_steps": 2240, "total_steps": 3402, "loss": 0.1185, "learning_rate": 1.1045139919002181e-05, "epoch": 1.9753086419753085, "percentage": 65.84, "elapsed_time": "4:59:35", "remaining_time": "2:35:24", "throughput": "0.00", "total_tokens": 0}
225
+ {"current_steps": 2250, "total_steps": 3402, "loss": 0.1223, "learning_rate": 1.087524881725059e-05, "epoch": 1.9841269841269842, "percentage": 66.14, "elapsed_time": "5:00:54", "remaining_time": "2:34:04", "throughput": "0.00", "total_tokens": 0}
226
+ {"current_steps": 2260, "total_steps": 3402, "loss": 0.1195, "learning_rate": 1.0706185186653108e-05, "epoch": 1.9929453262786596, "percentage": 66.43, "elapsed_time": "5:02:14", "remaining_time": "2:32:43", "throughput": "0.00", "total_tokens": 0}
227
+ {"current_steps": 2270, "total_steps": 3402, "loss": 0.1145, "learning_rate": 1.0537964358617114e-05, "epoch": 2.001763668430335, "percentage": 66.73, "elapsed_time": "5:04:12", "remaining_time": "2:31:42", "throughput": "0.00", "total_tokens": 0}
228
+ {"current_steps": 2280, "total_steps": 3402, "loss": 0.0971, "learning_rate": 1.0370601588121052e-05, "epoch": 2.0105820105820107, "percentage": 67.02, "elapsed_time": "5:05:34", "remaining_time": "2:30:22", "throughput": "0.00", "total_tokens": 0}
229
+ {"current_steps": 2290, "total_steps": 3402, "loss": 0.0983, "learning_rate": 1.0204112052331097e-05, "epoch": 2.019400352733686, "percentage": 67.31, "elapsed_time": "5:06:55", "remaining_time": "2:29:02", "throughput": "0.00", "total_tokens": 0}
230
+ {"current_steps": 2300, "total_steps": 3402, "loss": 0.097, "learning_rate": 1.0038510849224758e-05, "epoch": 2.0282186948853616, "percentage": 67.61, "elapsed_time": "5:08:17", "remaining_time": "2:27:42", "throughput": "0.00", "total_tokens": 0}
231
+ {"current_steps": 2310, "total_steps": 3402, "loss": 0.0942, "learning_rate": 9.87381299622181e-06, "epoch": 2.037037037037037, "percentage": 67.9, "elapsed_time": "5:09:38", "remaining_time": "2:26:22", "throughput": "0.00", "total_tokens": 0}
232
+ {"current_steps": 2320, "total_steps": 3402, "loss": 0.0952, "learning_rate": 9.710033428822368e-06, "epoch": 2.0458553791887124, "percentage": 68.2, "elapsed_time": "5:10:58", "remaining_time": "2:25:02", "throughput": "0.00", "total_tokens": 0}
233
+ {"current_steps": 2330, "total_steps": 3402, "loss": 0.0966, "learning_rate": 9.547186999252538e-06, "epoch": 2.054673721340388, "percentage": 68.49, "elapsed_time": "5:12:19", "remaining_time": "2:23:41", "throughput": "0.00", "total_tokens": 0}
234
+ {"current_steps": 2340, "total_steps": 3402, "loss": 0.0947, "learning_rate": 9.385288475117526e-06, "epoch": 2.0634920634920633, "percentage": 68.78, "elapsed_time": "5:13:40", "remaining_time": "2:22:21", "throughput": "0.00", "total_tokens": 0}
235
+ {"current_steps": 2350, "total_steps": 3402, "loss": 0.0961, "learning_rate": 9.224352538062441e-06, "epoch": 2.072310405643739, "percentage": 69.08, "elapsed_time": "5:15:01", "remaining_time": "2:21:01", "throughput": "0.00", "total_tokens": 0}
236
+ {"current_steps": 2360, "total_steps": 3402, "loss": 0.0935, "learning_rate": 9.06439378244091e-06, "epoch": 2.0811287477954146, "percentage": 69.37, "elapsed_time": "5:16:21", "remaining_time": "2:19:40", "throughput": "0.00", "total_tokens": 0}
237
+ {"current_steps": 2370, "total_steps": 3402, "loss": 0.098, "learning_rate": 8.905426713991609e-06, "epoch": 2.0899470899470898, "percentage": 69.66, "elapsed_time": "5:17:41", "remaining_time": "2:18:20", "throughput": "0.00", "total_tokens": 0}
238
+ {"current_steps": 2380, "total_steps": 3402, "loss": 0.0929, "learning_rate": 8.747465748522824e-06, "epoch": 2.0987654320987654, "percentage": 69.96, "elapsed_time": "5:19:01", "remaining_time": "2:16:59", "throughput": "0.00", "total_tokens": 0}
239
+ {"current_steps": 2390, "total_steps": 3402, "loss": 0.0938, "learning_rate": 8.590525210605125e-06, "epoch": 2.107583774250441, "percentage": 70.25, "elapsed_time": "5:20:20", "remaining_time": "2:15:38", "throughput": "0.00", "total_tokens": 0}
240
+ {"current_steps": 2400, "total_steps": 3402, "loss": 0.0933, "learning_rate": 8.434619332272412e-06, "epoch": 2.1164021164021163, "percentage": 70.55, "elapsed_time": "5:21:40", "remaining_time": "2:14:18", "throughput": "0.00", "total_tokens": 0}
241
+ {"current_steps": 2410, "total_steps": 3402, "loss": 0.0944, "learning_rate": 8.279762251731246e-06, "epoch": 2.125220458553792, "percentage": 70.84, "elapsed_time": "5:23:00", "remaining_time": "2:12:57", "throughput": "0.00", "total_tokens": 0}
242
+ {"current_steps": 2420, "total_steps": 3402, "loss": 0.092, "learning_rate": 8.125968012078745e-06, "epoch": 2.1340388007054676, "percentage": 71.13, "elapsed_time": "5:24:20", "remaining_time": "2:11:36", "throughput": "0.00", "total_tokens": 0}
243
+ {"current_steps": 2430, "total_steps": 3402, "loss": 0.0939, "learning_rate": 7.973250560029132e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "5:25:40", "remaining_time": "2:10:16", "throughput": "0.00", "total_tokens": 0}
244
+ {"current_steps": 2440, "total_steps": 3402, "loss": 0.0917, "learning_rate": 7.821623744648952e-06, "epoch": 2.1516754850088184, "percentage": 71.72, "elapsed_time": "5:27:00", "remaining_time": "2:08:55", "throughput": "0.00", "total_tokens": 0}
245
+ {"current_steps": 2450, "total_steps": 3402, "loss": 0.0942, "learning_rate": 7.671101316101172e-06, "epoch": 2.1604938271604937, "percentage": 72.02, "elapsed_time": "5:28:20", "remaining_time": "2:07:34", "throughput": "0.00", "total_tokens": 0}
246
+ {"current_steps": 2460, "total_steps": 3402, "loss": 0.0947, "learning_rate": 7.521696924398303e-06, "epoch": 2.1693121693121693, "percentage": 72.31, "elapsed_time": "5:29:39", "remaining_time": "2:06:14", "throughput": "0.00", "total_tokens": 0}
247
+ {"current_steps": 2470, "total_steps": 3402, "loss": 0.0944, "learning_rate": 7.373424118164501e-06, "epoch": 2.178130511463845, "percentage": 72.6, "elapsed_time": "5:30:59", "remaining_time": "2:04:53", "throughput": "0.00", "total_tokens": 0}
248
+ {"current_steps": 2480, "total_steps": 3402, "loss": 0.0941, "learning_rate": 7.226296343406974e-06, "epoch": 2.18694885361552, "percentage": 72.9, "elapsed_time": "5:32:19", "remaining_time": "2:03:32", "throughput": "0.00", "total_tokens": 0}
249
+ {"current_steps": 2490, "total_steps": 3402, "loss": 0.0922, "learning_rate": 7.0803269422966135e-06, "epoch": 2.195767195767196, "percentage": 73.19, "elapsed_time": "5:33:39", "remaining_time": "2:02:12", "throughput": "0.00", "total_tokens": 0}
250
+ {"current_steps": 2500, "total_steps": 3402, "loss": 0.0948, "learning_rate": 6.935529151958065e-06, "epoch": 2.204585537918871, "percentage": 73.49, "elapsed_time": "5:34:59", "remaining_time": "2:00:51", "throughput": "0.00", "total_tokens": 0}
251
+ {"current_steps": 2510, "total_steps": 3402, "loss": 0.0932, "learning_rate": 6.791916103269333e-06, "epoch": 2.2134038800705467, "percentage": 73.78, "elapsed_time": "5:36:18", "remaining_time": "1:59:31", "throughput": "0.00", "total_tokens": 0}
252
+ {"current_steps": 2520, "total_steps": 3402, "loss": 0.0955, "learning_rate": 6.649500819671047e-06, "epoch": 2.2222222222222223, "percentage": 74.07, "elapsed_time": "5:37:38", "remaining_time": "1:58:10", "throughput": "0.00", "total_tokens": 0}
253
+ {"current_steps": 2530, "total_steps": 3402, "loss": 0.0898, "learning_rate": 6.5082962159853834e-06, "epoch": 2.2310405643738975, "percentage": 74.37, "elapsed_time": "5:38:58", "remaining_time": "1:56:49", "throughput": "0.00", "total_tokens": 0}
254
+ {"current_steps": 2540, "total_steps": 3402, "loss": 0.0917, "learning_rate": 6.368315097244955e-06, "epoch": 2.239858906525573, "percentage": 74.66, "elapsed_time": "5:40:18", "remaining_time": "1:55:29", "throughput": "0.00", "total_tokens": 0}
255
+ {"current_steps": 2550, "total_steps": 3402, "loss": 0.0916, "learning_rate": 6.2295701575315594e-06, "epoch": 2.248677248677249, "percentage": 74.96, "elapsed_time": "5:41:38", "remaining_time": "1:54:08", "throughput": "0.00", "total_tokens": 0}
256
+ {"current_steps": 2560, "total_steps": 3402, "loss": 0.0927, "learning_rate": 6.092073978825022e-06, "epoch": 2.257495590828924, "percentage": 75.25, "elapsed_time": "5:42:58", "remaining_time": "1:52:48", "throughput": "0.00", "total_tokens": 0}
257
+ {"current_steps": 2570, "total_steps": 3402, "loss": 0.0946, "learning_rate": 5.955839029862245e-06, "epoch": 2.2663139329805997, "percentage": 75.54, "elapsed_time": "5:44:17", "remaining_time": "1:51:27", "throughput": "0.00", "total_tokens": 0}
258
+ {"current_steps": 2580, "total_steps": 3402, "loss": 0.0926, "learning_rate": 5.820877665006441e-06, "epoch": 2.2751322751322753, "percentage": 75.84, "elapsed_time": "5:45:37", "remaining_time": "1:50:07", "throughput": "0.00", "total_tokens": 0}
259
+ {"current_steps": 2590, "total_steps": 3402, "loss": 0.0952, "learning_rate": 5.687202123126832e-06, "epoch": 2.2839506172839505, "percentage": 76.13, "elapsed_time": "5:46:57", "remaining_time": "1:48:46", "throughput": "0.00", "total_tokens": 0}
260
+ {"current_steps": 2600, "total_steps": 3402, "loss": 0.0929, "learning_rate": 5.5548245264887515e-06, "epoch": 2.292768959435626, "percentage": 76.43, "elapsed_time": "5:48:17", "remaining_time": "1:47:26", "throughput": "0.00", "total_tokens": 0}
261
+ {"current_steps": 2610, "total_steps": 3402, "loss": 0.092, "learning_rate": 5.423756879654343e-06, "epoch": 2.3015873015873014, "percentage": 76.72, "elapsed_time": "5:49:37", "remaining_time": "1:46:05", "throughput": "0.00", "total_tokens": 0}
262
+ {"current_steps": 2620, "total_steps": 3402, "loss": 0.0932, "learning_rate": 5.294011068393945e-06, "epoch": 2.310405643738977, "percentage": 77.01, "elapsed_time": "5:50:57", "remaining_time": "1:44:44", "throughput": "0.00", "total_tokens": 0}
263
+ {"current_steps": 2630, "total_steps": 3402, "loss": 0.0944, "learning_rate": 5.1655988586082535e-06, "epoch": 2.3192239858906527, "percentage": 77.31, "elapsed_time": "5:52:17", "remaining_time": "1:43:24", "throughput": "0.00", "total_tokens": 0}
264
+ {"current_steps": 2640, "total_steps": 3402, "loss": 0.094, "learning_rate": 5.038531895261301e-06, "epoch": 2.328042328042328, "percentage": 77.6, "elapsed_time": "5:53:36", "remaining_time": "1:42:03", "throughput": "0.00", "total_tokens": 0}
265
+ {"current_steps": 2650, "total_steps": 3402, "loss": 0.0924, "learning_rate": 4.912821701324479e-06, "epoch": 2.3368606701940036, "percentage": 77.9, "elapsed_time": "5:54:56", "remaining_time": "1:40:43", "throughput": "0.00", "total_tokens": 0}
266
+ {"current_steps": 2660, "total_steps": 3402, "loss": 0.0936, "learning_rate": 4.788479676731581e-06, "epoch": 2.3456790123456788, "percentage": 78.19, "elapsed_time": "5:56:16", "remaining_time": "1:39:22", "throughput": "0.00", "total_tokens": 0}
267
+ {"current_steps": 2670, "total_steps": 3402, "loss": 0.0935, "learning_rate": 4.665517097344976e-06, "epoch": 2.3544973544973544, "percentage": 78.48, "elapsed_time": "5:57:36", "remaining_time": "1:38:02", "throughput": "0.00", "total_tokens": 0}
268
+ {"current_steps": 2680, "total_steps": 3402, "loss": 0.0931, "learning_rate": 4.543945113933099e-06, "epoch": 2.36331569664903, "percentage": 78.78, "elapsed_time": "5:58:56", "remaining_time": "1:36:42", "throughput": "0.00", "total_tokens": 0}
269
+ {"current_steps": 2690, "total_steps": 3402, "loss": 0.0937, "learning_rate": 4.423774751159247e-06, "epoch": 2.3721340388007053, "percentage": 79.07, "elapsed_time": "6:00:17", "remaining_time": "1:35:21", "throughput": "0.00", "total_tokens": 0}
270
+ {"current_steps": 2700, "total_steps": 3402, "loss": 0.0906, "learning_rate": 4.305016906581811e-06, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "6:01:39", "remaining_time": "1:34:01", "throughput": "0.00", "total_tokens": 0}
271
+ {"current_steps": 2710, "total_steps": 3402, "loss": 0.0919, "learning_rate": 4.1876823496660245e-06, "epoch": 2.3897707231040566, "percentage": 79.66, "elapsed_time": "6:03:01", "remaining_time": "1:32:41", "throughput": "0.00", "total_tokens": 0}
272
+ {"current_steps": 2720, "total_steps": 3402, "loss": 0.0929, "learning_rate": 4.071781720807375e-06, "epoch": 2.398589065255732, "percentage": 79.95, "elapsed_time": "6:04:22", "remaining_time": "1:31:21", "throughput": "0.00", "total_tokens": 0}
273
+ {"current_steps": 2730, "total_steps": 3402, "loss": 0.0911, "learning_rate": 3.9573255303666554e-06, "epoch": 2.4074074074074074, "percentage": 80.25, "elapsed_time": "6:05:42", "remaining_time": "1:30:01", "throughput": "0.00", "total_tokens": 0}
274
+ {"current_steps": 2740, "total_steps": 3402, "loss": 0.0906, "learning_rate": 3.844324157716857e-06, "epoch": 2.416225749559083, "percentage": 80.54, "elapsed_time": "6:07:03", "remaining_time": "1:28:40", "throughput": "0.00", "total_tokens": 0}
275
+ {"current_steps": 2750, "total_steps": 3402, "loss": 0.0903, "learning_rate": 3.7327878503019243e-06, "epoch": 2.4250440917107583, "percentage": 80.83, "elapsed_time": "6:08:23", "remaining_time": "1:27:20", "throughput": "0.00", "total_tokens": 0}
276
+ {"current_steps": 2760, "total_steps": 3402, "loss": 0.09, "learning_rate": 3.622726722707479e-06, "epoch": 2.433862433862434, "percentage": 81.13, "elapsed_time": "6:09:44", "remaining_time": "1:26:00", "throughput": "0.00", "total_tokens": 0}
277
+ {"current_steps": 2770, "total_steps": 3402, "loss": 0.093, "learning_rate": 3.5141507557435504e-06, "epoch": 2.442680776014109, "percentage": 81.42, "elapsed_time": "6:11:05", "remaining_time": "1:24:40", "throughput": "0.00", "total_tokens": 0}
278
+ {"current_steps": 2780, "total_steps": 3402, "loss": 0.0897, "learning_rate": 3.4070697955395326e-06, "epoch": 2.451499118165785, "percentage": 81.72, "elapsed_time": "6:12:25", "remaining_time": "1:23:19", "throughput": "0.00", "total_tokens": 0}
279
+ {"current_steps": 2790, "total_steps": 3402, "loss": 0.0922, "learning_rate": 3.3014935526512383e-06, "epoch": 2.4603174603174605, "percentage": 82.01, "elapsed_time": "6:13:45", "remaining_time": "1:21:59", "throughput": "0.00", "total_tokens": 0}
280
+ {"current_steps": 2800, "total_steps": 3402, "loss": 0.0924, "learning_rate": 3.197431601180343e-06, "epoch": 2.4691358024691357, "percentage": 82.3, "elapsed_time": "6:15:05", "remaining_time": "1:20:38", "throughput": "0.00", "total_tokens": 0}
281
+ {"current_steps": 2810, "total_steps": 3402, "loss": 0.0897, "learning_rate": 3.094893377906143e-06, "epoch": 2.4779541446208113, "percentage": 82.6, "elapsed_time": "6:16:25", "remaining_time": "1:19:18", "throughput": "0.00", "total_tokens": 0}
282
+ {"current_steps": 2820, "total_steps": 3402, "loss": 0.0901, "learning_rate": 2.9938881814298002e-06, "epoch": 2.4867724867724865, "percentage": 82.89, "elapsed_time": "6:17:44", "remaining_time": "1:17:57", "throughput": "0.00", "total_tokens": 0}
283
+ {"current_steps": 2830, "total_steps": 3402, "loss": 0.0918, "learning_rate": 2.894425171331112e-06, "epoch": 2.495590828924162, "percentage": 83.19, "elapsed_time": "6:19:04", "remaining_time": "1:16:37", "throughput": "0.00", "total_tokens": 0}
284
+ {"current_steps": 2840, "total_steps": 3402, "loss": 0.0883, "learning_rate": 2.796513367337854e-06, "epoch": 2.504409171075838, "percentage": 83.48, "elapsed_time": "6:20:24", "remaining_time": "1:15:16", "throughput": "0.00", "total_tokens": 0}
285
+ {"current_steps": 2850, "total_steps": 3402, "loss": 0.0937, "learning_rate": 2.7001616485078553e-06, "epoch": 2.5132275132275135, "percentage": 83.77, "elapsed_time": "6:21:44", "remaining_time": "1:13:56", "throughput": "0.00", "total_tokens": 0}
286
+ {"current_steps": 2860, "total_steps": 3402, "loss": 0.0881, "learning_rate": 2.6053787524238084e-06, "epoch": 2.5220458553791887, "percentage": 84.07, "elapsed_time": "6:23:04", "remaining_time": "1:12:35", "throughput": "0.00", "total_tokens": 0}
287
+ {"current_steps": 2870, "total_steps": 3402, "loss": 0.0883, "learning_rate": 2.512173274400904e-06, "epoch": 2.5308641975308643, "percentage": 84.36, "elapsed_time": "6:24:24", "remaining_time": "1:11:15", "throughput": "0.00", "total_tokens": 0}
288
+ {"current_steps": 2880, "total_steps": 3402, "loss": 0.0914, "learning_rate": 2.4205536667073572e-06, "epoch": 2.5396825396825395, "percentage": 84.66, "elapsed_time": "6:25:44", "remaining_time": "1:09:54", "throughput": "0.00", "total_tokens": 0}
289
+ {"current_steps": 2890, "total_steps": 3402, "loss": 0.0916, "learning_rate": 2.330528237797949e-06, "epoch": 2.548500881834215, "percentage": 84.95, "elapsed_time": "6:27:03", "remaining_time": "1:08:34", "throughput": "0.00", "total_tokens": 0}
290
+ {"current_steps": 2900, "total_steps": 3402, "loss": 0.0897, "learning_rate": 2.242105151560554e-06, "epoch": 2.557319223985891, "percentage": 85.24, "elapsed_time": "6:28:23", "remaining_time": "1:07:13", "throughput": "0.00", "total_tokens": 0}
291
+ {"current_steps": 2910, "total_steps": 3402, "loss": 0.0883, "learning_rate": 2.1552924265758102e-06, "epoch": 2.566137566137566, "percentage": 85.54, "elapsed_time": "6:29:43", "remaining_time": "1:05:53", "throughput": "0.00", "total_tokens": 0}
292
+ {"current_steps": 2920, "total_steps": 3402, "loss": 0.088, "learning_rate": 2.070097935389974e-06, "epoch": 2.5749559082892417, "percentage": 85.83, "elapsed_time": "6:31:03", "remaining_time": "1:04:33", "throughput": "0.00", "total_tokens": 0}
293
+ {"current_steps": 2930, "total_steps": 3402, "loss": 0.09, "learning_rate": 1.9865294038009984e-06, "epoch": 2.583774250440917, "percentage": 86.13, "elapsed_time": "6:32:23", "remaining_time": "1:03:12", "throughput": "0.00", "total_tokens": 0}
294
+ {"current_steps": 2940, "total_steps": 3402, "loss": 0.0896, "learning_rate": 1.9045944101579073e-06, "epoch": 2.5925925925925926, "percentage": 86.42, "elapsed_time": "6:33:42", "remaining_time": "1:01:52", "throughput": "0.00", "total_tokens": 0}
295
+ {"current_steps": 2950, "total_steps": 3402, "loss": 0.0916, "learning_rate": 1.8243003846735807e-06, "epoch": 2.601410934744268, "percentage": 86.71, "elapsed_time": "6:35:02", "remaining_time": "1:00:31", "throughput": "0.00", "total_tokens": 0}
296
+ {"current_steps": 2960, "total_steps": 3402, "loss": 0.0882, "learning_rate": 1.7456546087509419e-06, "epoch": 2.6102292768959434, "percentage": 87.01, "elapsed_time": "6:36:22", "remaining_time": "0:59:11", "throughput": "0.00", "total_tokens": 0}
297
+ {"current_steps": 2970, "total_steps": 3402, "loss": 0.0892, "learning_rate": 1.6686642143226484e-06, "epoch": 2.619047619047619, "percentage": 87.3, "elapsed_time": "6:37:42", "remaining_time": "0:57:50", "throughput": "0.00", "total_tokens": 0}
298
+ {"current_steps": 2980, "total_steps": 3402, "loss": 0.0884, "learning_rate": 1.593336183204346e-06, "epoch": 2.6278659611992943, "percentage": 87.6, "elapsed_time": "6:39:02", "remaining_time": "0:56:30", "throughput": "0.00", "total_tokens": 0}
299
+ {"current_steps": 2990, "total_steps": 3402, "loss": 0.0902, "learning_rate": 1.5196773464615167e-06, "epoch": 2.63668430335097, "percentage": 87.89, "elapsed_time": "6:40:22", "remaining_time": "0:55:10", "throughput": "0.00", "total_tokens": 0}
300
+ {"current_steps": 3000, "total_steps": 3402, "loss": 0.0915, "learning_rate": 1.4476943837900105e-06, "epoch": 2.6455026455026456, "percentage": 88.18, "elapsed_time": "6:41:41", "remaining_time": "0:53:49", "throughput": "0.00", "total_tokens": 0}
301
+ {"current_steps": 3010, "total_steps": 3402, "loss": 0.0904, "learning_rate": 1.377393822910318e-06, "epoch": 2.6543209876543212, "percentage": 88.48, "elapsed_time": "6:43:01", "remaining_time": "0:52:29", "throughput": "0.00", "total_tokens": 0}
302
+ {"current_steps": 3020, "total_steps": 3402, "loss": 0.0883, "learning_rate": 1.30878203897558e-06, "epoch": 2.6631393298059964, "percentage": 88.77, "elapsed_time": "6:44:21", "remaining_time": "0:51:08", "throughput": "0.00", "total_tokens": 0}
303
+ {"current_steps": 3030, "total_steps": 3402, "loss": 0.0899, "learning_rate": 1.241865253993495e-06, "epoch": 2.671957671957672, "percentage": 89.07, "elapsed_time": "6:45:41", "remaining_time": "0:49:48", "throughput": "0.00", "total_tokens": 0}
304
+ {"current_steps": 3040, "total_steps": 3402, "loss": 0.09, "learning_rate": 1.1766495362620555e-06, "epoch": 2.6807760141093473, "percentage": 89.36, "elapsed_time": "6:47:01", "remaining_time": "0:48:28", "throughput": "0.00", "total_tokens": 0}
305
+ {"current_steps": 3050, "total_steps": 3402, "loss": 0.089, "learning_rate": 1.1131407998192567e-06, "epoch": 2.689594356261023, "percentage": 89.65, "elapsed_time": "6:48:20", "remaining_time": "0:47:07", "throughput": "0.00", "total_tokens": 0}
306
+ {"current_steps": 3060, "total_steps": 3402, "loss": 0.0892, "learning_rate": 1.0513448039067954e-06, "epoch": 2.6984126984126986, "percentage": 89.95, "elapsed_time": "6:49:40", "remaining_time": "0:45:47", "throughput": "0.00", "total_tokens": 0}
307
+ {"current_steps": 3070, "total_steps": 3402, "loss": 0.0878, "learning_rate": 9.91267152447779e-07, "epoch": 2.707231040564374, "percentage": 90.24, "elapsed_time": "6:51:00", "remaining_time": "0:44:26", "throughput": "0.00", "total_tokens": 0}
308
+ {"current_steps": 3080, "total_steps": 3402, "loss": 0.0899, "learning_rate": 9.329132935385577e-07, "epoch": 2.7160493827160495, "percentage": 90.53, "elapsed_time": "6:52:20", "remaining_time": "0:43:06", "throughput": "0.00", "total_tokens": 0}
309
+ {"current_steps": 3090, "total_steps": 3402, "loss": 0.0916, "learning_rate": 8.7628851895466e-07, "epoch": 2.7248677248677247, "percentage": 90.83, "elapsed_time": "6:53:40", "remaining_time": "0:41:46", "throughput": "0.00", "total_tokens": 0}
310
+ {"current_steps": 3100, "total_steps": 3402, "loss": 0.0922, "learning_rate": 8.213979636709046e-07, "epoch": 2.7336860670194003, "percentage": 91.12, "elapsed_time": "6:55:00", "remaining_time": "0:40:25", "throughput": "0.00", "total_tokens": 0}
311
+ {"current_steps": 3110, "total_steps": 3402, "loss": 0.0888, "learning_rate": 7.682466053957438e-07, "epoch": 2.742504409171076, "percentage": 91.42, "elapsed_time": "6:56:21", "remaining_time": "0:39:05", "throughput": "0.00", "total_tokens": 0}
312
+ {"current_steps": 3120, "total_steps": 3402, "loss": 0.0869, "learning_rate": 7.168392641198796e-07, "epoch": 2.751322751322751, "percentage": 91.71, "elapsed_time": "6:57:43", "remaining_time": "0:37:45", "throughput": "0.00", "total_tokens": 0}
313
+ {"current_steps": 3130, "total_steps": 3402, "loss": 0.0877, "learning_rate": 6.671806016791337e-07, "epoch": 2.760141093474427, "percentage": 92.0, "elapsed_time": "6:59:04", "remaining_time": "0:36:25", "throughput": "0.00", "total_tokens": 0}
314
+ {"current_steps": 3140, "total_steps": 3402, "loss": 0.0869, "learning_rate": 6.192751213317261e-07, "epoch": 2.768959435626102, "percentage": 92.3, "elapsed_time": "7:00:25", "remaining_time": "0:35:04", "throughput": "0.00", "total_tokens": 0}
315
+ {"current_steps": 3150, "total_steps": 3402, "loss": 0.0876, "learning_rate": 5.731271673498807e-07, "epoch": 2.7777777777777777, "percentage": 92.59, "elapsed_time": "7:01:46", "remaining_time": "0:33:44", "throughput": "0.00", "total_tokens": 0}
316
+ {"current_steps": 3160, "total_steps": 3402, "loss": 0.0867, "learning_rate": 5.287409246258724e-07, "epoch": 2.7865961199294533, "percentage": 92.89, "elapsed_time": "7:03:07", "remaining_time": "0:32:24", "throughput": "0.00", "total_tokens": 0}
317
+ {"current_steps": 3170, "total_steps": 3402, "loss": 0.0861, "learning_rate": 4.861204182925238e-07, "epoch": 2.795414462081129, "percentage": 93.18, "elapsed_time": "7:04:28", "remaining_time": "0:31:03", "throughput": "0.00", "total_tokens": 0}
318
+ {"current_steps": 3180, "total_steps": 3402, "loss": 0.0897, "learning_rate": 4.452695133581908e-07, "epoch": 2.804232804232804, "percentage": 93.47, "elapsed_time": "7:05:48", "remaining_time": "0:29:43", "throughput": "0.00", "total_tokens": 0}
319
+ {"current_steps": 3190, "total_steps": 3402, "loss": 0.0898, "learning_rate": 4.0619191435626647e-07, "epoch": 2.81305114638448, "percentage": 93.77, "elapsed_time": "7:07:08", "remaining_time": "0:28:23", "throughput": "0.00", "total_tokens": 0}
320
+ {"current_steps": 3200, "total_steps": 3402, "loss": 0.0892, "learning_rate": 3.688911650092375e-07, "epoch": 2.821869488536155, "percentage": 94.06, "elapsed_time": "7:08:28", "remaining_time": "0:27:02", "throughput": "0.00", "total_tokens": 0}
321
+ {"current_steps": 3210, "total_steps": 3402, "loss": 0.0904, "learning_rate": 3.333706479073229e-07, "epoch": 2.8306878306878307, "percentage": 94.36, "elapsed_time": "7:09:49", "remaining_time": "0:25:42", "throughput": "0.00", "total_tokens": 0}
322
+ {"current_steps": 3220, "total_steps": 3402, "loss": 0.0915, "learning_rate": 2.996335842017306e-07, "epoch": 2.8395061728395063, "percentage": 94.65, "elapsed_time": "7:11:09", "remaining_time": "0:24:22", "throughput": "0.00", "total_tokens": 0}
323
+ {"current_steps": 3230, "total_steps": 3402, "loss": 0.089, "learning_rate": 2.676830333125424e-07, "epoch": 2.8483245149911816, "percentage": 94.94, "elapsed_time": "7:12:29", "remaining_time": "0:23:01", "throughput": "0.00", "total_tokens": 0}
324
+ {"current_steps": 3240, "total_steps": 3402, "loss": 0.0868, "learning_rate": 2.3752189265128234e-07, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "7:13:48", "remaining_time": "0:21:41", "throughput": "0.00", "total_tokens": 0}
325
+ {"current_steps": 3250, "total_steps": 3402, "loss": 0.0891, "learning_rate": 2.0915289735816247e-07, "epoch": 2.8659611992945324, "percentage": 95.53, "elapsed_time": "7:15:08", "remaining_time": "0:20:21", "throughput": "0.00", "total_tokens": 0}
326
+ {"current_steps": 3260, "total_steps": 3402, "loss": 0.0898, "learning_rate": 1.8257862005404802e-07, "epoch": 2.874779541446208, "percentage": 95.83, "elapsed_time": "7:16:28", "remaining_time": "0:19:00", "throughput": "0.00", "total_tokens": 0}
327
+ {"current_steps": 3270, "total_steps": 3402, "loss": 0.0877, "learning_rate": 1.5780147060715955e-07, "epoch": 2.8835978835978837, "percentage": 96.12, "elapsed_time": "7:17:48", "remaining_time": "0:17:40", "throughput": "0.00", "total_tokens": 0}
328
+ {"current_steps": 3280, "total_steps": 3402, "loss": 0.0911, "learning_rate": 1.3482369591453882e-07, "epoch": 2.892416225749559, "percentage": 96.41, "elapsed_time": "7:19:08", "remaining_time": "0:16:20", "throughput": "0.00", "total_tokens": 0}
329
+ {"current_steps": 3290, "total_steps": 3402, "loss": 0.0909, "learning_rate": 1.1364737969829176e-07, "epoch": 2.9012345679012346, "percentage": 96.71, "elapsed_time": "7:20:27", "remaining_time": "0:14:59", "throughput": "0.00", "total_tokens": 0}
330
+ {"current_steps": 3300, "total_steps": 3402, "loss": 0.0862, "learning_rate": 9.427444231662863e-08, "epoch": 2.91005291005291, "percentage": 97.0, "elapsed_time": "7:21:47", "remaining_time": "0:13:39", "throughput": "0.00", "total_tokens": 0}
331
+ {"current_steps": 3310, "total_steps": 3402, "loss": 0.0875, "learning_rate": 7.670664058970545e-08, "epoch": 2.9188712522045854, "percentage": 97.3, "elapsed_time": "7:23:07", "remaining_time": "0:12:18", "throughput": "0.00", "total_tokens": 0}
332
+ {"current_steps": 3320, "total_steps": 3402, "loss": 0.0886, "learning_rate": 6.094556764032922e-08, "epoch": 2.927689594356261, "percentage": 97.59, "elapsed_time": "7:24:27", "remaining_time": "0:10:58", "throughput": "0.00", "total_tokens": 0}
333
+ {"current_steps": 3330, "total_steps": 3402, "loss": 0.0865, "learning_rate": 4.699265274946907e-08, "epoch": 2.9365079365079367, "percentage": 97.88, "elapsed_time": "7:25:47", "remaining_time": "0:09:38", "throughput": "0.00", "total_tokens": 0}
334
+ {"current_steps": 3340, "total_steps": 3402, "loss": 0.0889, "learning_rate": 3.484916122664883e-08, "epoch": 2.945326278659612, "percentage": 98.18, "elapsed_time": "7:27:06", "remaining_time": "0:08:17", "throughput": "0.00", "total_tokens": 0}
335
+ {"current_steps": 3350, "total_steps": 3402, "loss": 0.0899, "learning_rate": 2.4516194295205466e-08, "epoch": 2.9541446208112876, "percentage": 98.47, "elapsed_time": "7:28:26", "remaining_time": "0:06:57", "throughput": "0.00", "total_tokens": 0}
336
+ {"current_steps": 3360, "total_steps": 3402, "loss": 0.0895, "learning_rate": 1.5994688992424513e-08, "epoch": 2.962962962962963, "percentage": 98.77, "elapsed_time": "7:29:46", "remaining_time": "0:05:37", "throughput": "0.00", "total_tokens": 0}
337
+ {"current_steps": 3370, "total_steps": 3402, "loss": 0.0886, "learning_rate": 9.285418084565845e-09, "epoch": 2.9717813051146384, "percentage": 99.06, "elapsed_time": "7:31:06", "remaining_time": "0:04:17", "throughput": "0.00", "total_tokens": 0}
338
+ {"current_steps": 3380, "total_steps": 3402, "loss": 0.0886, "learning_rate": 4.3889899967797244e-09, "epoch": 2.980599647266314, "percentage": 99.35, "elapsed_time": "7:32:25", "remaining_time": "0:02:56", "throughput": "0.00", "total_tokens": 0}
339
+ {"current_steps": 3390, "total_steps": 3402, "loss": 0.0888, "learning_rate": 1.3058487579420409e-09, "epoch": 2.9894179894179893, "percentage": 99.65, "elapsed_time": "7:33:45", "remaining_time": "0:01:36", "throughput": "0.00", "total_tokens": 0}
340
+ {"current_steps": 3400, "total_steps": 3402, "loss": 0.0869, "learning_rate": 3.627396038208275e-11, "epoch": 2.998236331569665, "percentage": 99.94, "elapsed_time": "7:35:05", "remaining_time": "0:00:16", "throughput": "0.00", "total_tokens": 0}
341
+ {"current_steps": 3402, "total_steps": 3402, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "7:36:20", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
trainer_state.json ADDED
@@ -0,0 +1,2422 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3402,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008818342151675485,
13
+ "grad_norm": 1.4955648753589619,
14
+ "learning_rate": 3.883495145631068e-06,
15
+ "loss": 0.4452,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.01763668430335097,
20
+ "grad_norm": 0.8166020313583234,
21
+ "learning_rate": 7.766990291262136e-06,
22
+ "loss": 0.3563,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.026455026455026454,
27
+ "grad_norm": 1.0139812433784159,
28
+ "learning_rate": 1.1650485436893204e-05,
29
+ "loss": 0.2954,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.03527336860670194,
34
+ "grad_norm": 1.121332128031883,
35
+ "learning_rate": 1.5533980582524273e-05,
36
+ "loss": 0.264,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.04409171075837742,
41
+ "grad_norm": 1.5248485572756025,
42
+ "learning_rate": 1.9417475728155343e-05,
43
+ "loss": 0.2515,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.05291005291005291,
48
+ "grad_norm": 0.7086102688104752,
49
+ "learning_rate": 2.330097087378641e-05,
50
+ "loss": 0.2384,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.06172839506172839,
55
+ "grad_norm": 0.6620513303312378,
56
+ "learning_rate": 2.718446601941748e-05,
57
+ "loss": 0.2371,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.07054673721340388,
62
+ "grad_norm": 1.1439083265825398,
63
+ "learning_rate": 3.1067961165048545e-05,
64
+ "loss": 0.2316,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.07936507936507936,
69
+ "grad_norm": 0.8671080906528094,
70
+ "learning_rate": 3.4951456310679615e-05,
71
+ "loss": 0.2243,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.08818342151675485,
76
+ "grad_norm": 0.8521737444390105,
77
+ "learning_rate": 3.8834951456310685e-05,
78
+ "loss": 0.2216,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.09700176366843033,
83
+ "grad_norm": 0.820039351853962,
84
+ "learning_rate": 3.9999555645496425e-05,
85
+ "loss": 0.2181,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.10582010582010581,
90
+ "grad_norm": 0.4284687555753216,
91
+ "learning_rate": 3.999737926280763e-05,
92
+ "loss": 0.2123,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.1146384479717813,
97
+ "grad_norm": 1.0310561704789347,
98
+ "learning_rate": 3.999338943291723e-05,
99
+ "loss": 0.2072,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.12345679012345678,
104
+ "grad_norm": 0.48329839911504663,
105
+ "learning_rate": 3.998758651763991e-05,
106
+ "loss": 0.2046,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.13227513227513227,
111
+ "grad_norm": 0.43509409688235956,
112
+ "learning_rate": 3.9979971043208656e-05,
113
+ "loss": 0.2017,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.14109347442680775,
118
+ "grad_norm": 0.3421062202275864,
119
+ "learning_rate": 3.997054370022701e-05,
120
+ "loss": 0.2026,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.14991181657848324,
125
+ "grad_norm": 0.41797655307441983,
126
+ "learning_rate": 3.995930534360642e-05,
127
+ "loss": 0.1972,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.15873015873015872,
132
+ "grad_norm": 0.40272951427585846,
133
+ "learning_rate": 3.994625699248876e-05,
134
+ "loss": 0.1947,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.1675485008818342,
139
+ "grad_norm": 0.35340459426606163,
140
+ "learning_rate": 3.993139983015388e-05,
141
+ "loss": 0.1971,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.1763668430335097,
146
+ "grad_norm": 0.7994951274374914,
147
+ "learning_rate": 3.9914735203912274e-05,
148
+ "loss": 0.1925,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.18518518518518517,
153
+ "grad_norm": 0.40411453618039694,
154
+ "learning_rate": 3.989626462498299e-05,
155
+ "loss": 0.192,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.19400352733686066,
160
+ "grad_norm": 0.31941758385605157,
161
+ "learning_rate": 3.9875989768356474e-05,
162
+ "loss": 0.1868,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.20282186948853614,
167
+ "grad_norm": 0.3142908369196689,
168
+ "learning_rate": 3.9853912472642766e-05,
169
+ "loss": 0.1893,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.21164021164021163,
174
+ "grad_norm": 0.3241679786689458,
175
+ "learning_rate": 3.9830034739904716e-05,
176
+ "loss": 0.1863,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.2204585537918871,
181
+ "grad_norm": 0.31178995966174394,
182
+ "learning_rate": 3.980435873547643e-05,
183
+ "loss": 0.1862,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.2292768959435626,
188
+ "grad_norm": 0.47323032502490103,
189
+ "learning_rate": 3.977688678776695e-05,
190
+ "loss": 0.1851,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.23809523809523808,
195
+ "grad_norm": 0.3265364244937022,
196
+ "learning_rate": 3.974762138804906e-05,
197
+ "loss": 0.1865,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.24691358024691357,
202
+ "grad_norm": 0.34222373145685614,
203
+ "learning_rate": 3.971656519023337e-05,
204
+ "loss": 0.1817,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.25573192239858905,
209
+ "grad_norm": 0.3739773461101385,
210
+ "learning_rate": 3.9683721010627666e-05,
211
+ "loss": 0.1818,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.26455026455026454,
216
+ "grad_norm": 0.30430093336446573,
217
+ "learning_rate": 3.964909182768153e-05,
218
+ "loss": 0.18,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.27336860670194,
223
+ "grad_norm": 0.34663011155426887,
224
+ "learning_rate": 3.9612680781716203e-05,
225
+ "loss": 0.1803,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.2821869488536155,
230
+ "grad_norm": 0.298542445104257,
231
+ "learning_rate": 3.9574491174639824e-05,
232
+ "loss": 0.1789,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.291005291005291,
237
+ "grad_norm": 0.2685161967289745,
238
+ "learning_rate": 3.9534526469648e-05,
239
+ "loss": 0.178,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.2998236331569665,
244
+ "grad_norm": 0.39999602620736396,
245
+ "learning_rate": 3.949279029090976e-05,
246
+ "loss": 0.179,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.30864197530864196,
251
+ "grad_norm": 0.36622856228147127,
252
+ "learning_rate": 3.944928642323887e-05,
253
+ "loss": 0.1786,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.31746031746031744,
258
+ "grad_norm": 0.4663556460380618,
259
+ "learning_rate": 3.940401881175065e-05,
260
+ "loss": 0.18,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.3262786596119929,
265
+ "grad_norm": 0.3720323085775275,
266
+ "learning_rate": 3.9356991561504177e-05,
267
+ "loss": 0.1776,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.3350970017636684,
272
+ "grad_norm": 0.302010044803705,
273
+ "learning_rate": 3.9308208937130046e-05,
274
+ "loss": 0.1763,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.3439153439153439,
279
+ "grad_norm": 0.31665097292956457,
280
+ "learning_rate": 3.925767536244362e-05,
281
+ "loss": 0.1751,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.3527336860670194,
286
+ "grad_norm": 0.3228908226384742,
287
+ "learning_rate": 3.920539542004387e-05,
288
+ "loss": 0.1745,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.36155202821869487,
293
+ "grad_norm": 0.2799415607873476,
294
+ "learning_rate": 3.915137385089781e-05,
295
+ "loss": 0.1749,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.37037037037037035,
300
+ "grad_norm": 0.24387451434550744,
301
+ "learning_rate": 3.909561555391053e-05,
302
+ "loss": 0.174,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.37918871252204583,
307
+ "grad_norm": 0.2726005390731001,
308
+ "learning_rate": 3.903812558548099e-05,
309
+ "loss": 0.1734,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.3880070546737213,
314
+ "grad_norm": 0.3028874282302824,
315
+ "learning_rate": 3.8978909159043465e-05,
316
+ "loss": 0.174,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.3968253968253968,
321
+ "grad_norm": 0.2512628489766056,
322
+ "learning_rate": 3.891797164459477e-05,
323
+ "loss": 0.1715,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.4056437389770723,
328
+ "grad_norm": 0.23809767948700475,
329
+ "learning_rate": 3.885531856820726e-05,
330
+ "loss": 0.1707,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.4144620811287478,
335
+ "grad_norm": 0.27178090104851893,
336
+ "learning_rate": 3.8790955611527754e-05,
337
+ "loss": 0.1702,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.42328042328042326,
342
+ "grad_norm": 0.3849347266422906,
343
+ "learning_rate": 3.872488861126226e-05,
344
+ "loss": 0.1688,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.43209876543209874,
349
+ "grad_norm": 0.3597097968078764,
350
+ "learning_rate": 3.865712355864668e-05,
351
+ "loss": 0.169,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.4409171075837742,
356
+ "grad_norm": 0.26535671712243575,
357
+ "learning_rate": 3.8587666598903526e-05,
358
+ "loss": 0.1672,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.4497354497354497,
363
+ "grad_norm": 0.27483599851665746,
364
+ "learning_rate": 3.851652403068461e-05,
365
+ "loss": 0.1726,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.4585537918871252,
370
+ "grad_norm": 0.27278517138668995,
371
+ "learning_rate": 3.8443702305499886e-05,
372
+ "loss": 0.1704,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.4673721340388007,
377
+ "grad_norm": 0.24988566985125385,
378
+ "learning_rate": 3.836920802713238e-05,
379
+ "loss": 0.1671,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.47619047619047616,
384
+ "grad_norm": 0.34671624980077004,
385
+ "learning_rate": 3.829304795103933e-05,
386
+ "loss": 0.1672,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.48500881834215165,
391
+ "grad_norm": 0.309822758612831,
392
+ "learning_rate": 3.82152289837396e-05,
393
+ "loss": 0.1666,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.49382716049382713,
398
+ "grad_norm": 0.2735497475576908,
399
+ "learning_rate": 3.813575818218732e-05,
400
+ "loss": 0.1686,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.5026455026455027,
405
+ "grad_norm": 0.29690091794159296,
406
+ "learning_rate": 3.8054642753132e-05,
407
+ "loss": 0.1669,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.5114638447971781,
412
+ "grad_norm": 0.25476479109627226,
413
+ "learning_rate": 3.797189005246489e-05,
414
+ "loss": 0.1622,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.5202821869488536,
419
+ "grad_norm": 0.21847320529770614,
420
+ "learning_rate": 3.788750758455204e-05,
421
+ "loss": 0.1629,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.5291005291005291,
426
+ "grad_norm": 0.22282921245577492,
427
+ "learning_rate": 3.7801503001553664e-05,
428
+ "loss": 0.1682,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.5379188712522046,
433
+ "grad_norm": 0.2964689468325172,
434
+ "learning_rate": 3.771388410273027e-05,
435
+ "loss": 0.1672,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.54673721340388,
440
+ "grad_norm": 0.2828883507477133,
441
+ "learning_rate": 3.762465883373539e-05,
442
+ "loss": 0.1618,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.5555555555555556,
447
+ "grad_norm": 0.2856702713626834,
448
+ "learning_rate": 3.753383528589499e-05,
449
+ "loss": 0.1639,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.564373897707231,
454
+ "grad_norm": 0.25603423467383013,
455
+ "learning_rate": 3.744142169547376e-05,
456
+ "loss": 0.1603,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.5731922398589065,
461
+ "grad_norm": 0.24322397045686334,
462
+ "learning_rate": 3.734742644292821e-05,
463
+ "loss": 0.1627,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.582010582010582,
468
+ "grad_norm": 0.21120093154802644,
469
+ "learning_rate": 3.725185805214665e-05,
470
+ "loss": 0.1639,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.5908289241622575,
475
+ "grad_norm": 0.2455862358583795,
476
+ "learning_rate": 3.7154725189676264e-05,
477
+ "loss": 0.1619,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.599647266313933,
482
+ "grad_norm": 0.2665765386539727,
483
+ "learning_rate": 3.7056036663937164e-05,
484
+ "loss": 0.165,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.6084656084656085,
489
+ "grad_norm": 0.23935749033120898,
490
+ "learning_rate": 3.695580142442361e-05,
491
+ "loss": 0.1614,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.6172839506172839,
496
+ "grad_norm": 0.23327066612729097,
497
+ "learning_rate": 3.685402856089242e-05,
498
+ "loss": 0.1618,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.6261022927689595,
503
+ "grad_norm": 0.2295032987661733,
504
+ "learning_rate": 3.675072730253868e-05,
505
+ "loss": 0.1655,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.6349206349206349,
510
+ "grad_norm": 0.2597641502201965,
511
+ "learning_rate": 3.6645907017158814e-05,
512
+ "loss": 0.1608,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.6437389770723104,
517
+ "grad_norm": 0.24169971877971796,
518
+ "learning_rate": 3.653957721030107e-05,
519
+ "loss": 0.1606,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.6525573192239859,
524
+ "grad_norm": 0.23805929987756733,
525
+ "learning_rate": 3.64317475244035e-05,
526
+ "loss": 0.1624,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.6613756613756614,
531
+ "grad_norm": 0.21337182553159947,
532
+ "learning_rate": 3.632242773791952e-05,
533
+ "loss": 0.1605,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.6701940035273368,
538
+ "grad_norm": 0.2086929717616856,
539
+ "learning_rate": 3.621162776443125e-05,
540
+ "loss": 0.1597,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.6790123456790124,
545
+ "grad_norm": 0.20642071715098376,
546
+ "learning_rate": 3.60993576517504e-05,
547
+ "loss": 0.1609,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.6878306878306878,
552
+ "grad_norm": 0.19167244052151497,
553
+ "learning_rate": 3.598562758100716e-05,
554
+ "loss": 0.1607,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.6966490299823633,
559
+ "grad_norm": 0.2285439297223176,
560
+ "learning_rate": 3.5870447865726913e-05,
561
+ "loss": 0.1606,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.7054673721340388,
566
+ "grad_norm": 0.2173697770388281,
567
+ "learning_rate": 3.575382895089495e-05,
568
+ "loss": 0.161,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.7142857142857143,
573
+ "grad_norm": 0.2831703519646522,
574
+ "learning_rate": 3.563578141200929e-05,
575
+ "loss": 0.1592,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.7231040564373897,
580
+ "grad_norm": 0.23525021695459578,
581
+ "learning_rate": 3.551631595412164e-05,
582
+ "loss": 0.1596,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.7319223985890653,
587
+ "grad_norm": 0.254325105892367,
588
+ "learning_rate": 3.539544341086663e-05,
589
+ "loss": 0.1565,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.7407407407407407,
594
+ "grad_norm": 0.20727493642114397,
595
+ "learning_rate": 3.5273174743479336e-05,
596
+ "loss": 0.1581,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.7495590828924162,
601
+ "grad_norm": 0.25745565286011807,
602
+ "learning_rate": 3.514952103980132e-05,
603
+ "loss": 0.1598,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.7583774250440917,
608
+ "grad_norm": 0.19482500821770854,
609
+ "learning_rate": 3.50244935132751e-05,
610
+ "loss": 0.1586,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.7671957671957672,
615
+ "grad_norm": 0.20509823998997453,
616
+ "learning_rate": 3.489810350192729e-05,
617
+ "loss": 0.1559,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.7760141093474426,
622
+ "grad_norm": 0.20895652988918806,
623
+ "learning_rate": 3.477036246734038e-05,
624
+ "loss": 0.1563,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.7848324514991182,
629
+ "grad_norm": 0.27987607099152345,
630
+ "learning_rate": 3.4641281993613406e-05,
631
+ "loss": 0.1596,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.7936507936507936,
636
+ "grad_norm": 0.19730219851608477,
637
+ "learning_rate": 3.451087378631143e-05,
638
+ "loss": 0.1579,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.8024691358024691,
643
+ "grad_norm": 0.20906456760570116,
644
+ "learning_rate": 3.437914967140401e-05,
645
+ "loss": 0.1571,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.8112874779541446,
650
+ "grad_norm": 0.22886723809980594,
651
+ "learning_rate": 3.4246121594192814e-05,
652
+ "loss": 0.157,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.8201058201058201,
657
+ "grad_norm": 0.19417100843050594,
658
+ "learning_rate": 3.411180161822831e-05,
659
+ "loss": 0.1554,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.8289241622574955,
664
+ "grad_norm": 0.26409165069315016,
665
+ "learning_rate": 3.3976201924215854e-05,
666
+ "loss": 0.1557,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.8377425044091711,
671
+ "grad_norm": 0.25269001142437164,
672
+ "learning_rate": 3.3839334808911057e-05,
673
+ "loss": 0.155,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.8465608465608465,
678
+ "grad_norm": 0.28787596764707246,
679
+ "learning_rate": 3.370121268400467e-05,
680
+ "loss": 0.1554,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.855379188712522,
685
+ "grad_norm": 0.20073900051671914,
686
+ "learning_rate": 3.356184807499705e-05,
687
+ "loss": 0.1543,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.8641975308641975,
692
+ "grad_norm": 0.19523250730479108,
693
+ "learning_rate": 3.342125362006226e-05,
694
+ "loss": 0.1552,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.873015873015873,
699
+ "grad_norm": 0.2332670363257663,
700
+ "learning_rate": 3.3279442068902024e-05,
701
+ "loss": 0.155,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.8818342151675485,
706
+ "grad_norm": 0.21314128725157566,
707
+ "learning_rate": 3.3136426281589525e-05,
708
+ "loss": 0.1559,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.890652557319224,
713
+ "grad_norm": 0.2073616768080302,
714
+ "learning_rate": 3.299221922740318e-05,
715
+ "loss": 0.1555,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 0.8994708994708994,
720
+ "grad_norm": 0.20612629267891894,
721
+ "learning_rate": 3.284683398365053e-05,
722
+ "loss": 0.1544,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 0.908289241622575,
727
+ "grad_norm": 0.192587617407336,
728
+ "learning_rate": 3.270028373448237e-05,
729
+ "loss": 0.156,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 0.9171075837742504,
734
+ "grad_norm": 0.20076697321476172,
735
+ "learning_rate": 3.255258176969711e-05,
736
+ "loss": 0.1525,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 0.9259259259259259,
741
+ "grad_norm": 0.20063292329444252,
742
+ "learning_rate": 3.2403741483535624e-05,
743
+ "loss": 0.1579,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 0.9347442680776014,
748
+ "grad_norm": 0.2188372918686337,
749
+ "learning_rate": 3.22537763734666e-05,
750
+ "loss": 0.1545,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 0.9435626102292769,
755
+ "grad_norm": 0.2348876410690357,
756
+ "learning_rate": 3.210270003896254e-05,
757
+ "loss": 0.1523,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 0.9523809523809523,
762
+ "grad_norm": 0.21610514112165158,
763
+ "learning_rate": 3.195052618026646e-05,
764
+ "loss": 0.1498,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 0.9611992945326279,
769
+ "grad_norm": 0.17805564179617644,
770
+ "learning_rate": 3.1797268597149575e-05,
771
+ "loss": 0.1533,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 0.9700176366843033,
776
+ "grad_norm": 0.19468985685608828,
777
+ "learning_rate": 3.1642941187659784e-05,
778
+ "loss": 0.1505,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 0.9788359788359788,
783
+ "grad_norm": 0.17922597209513355,
784
+ "learning_rate": 3.1487557946861413e-05,
785
+ "loss": 0.154,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 0.9876543209876543,
790
+ "grad_norm": 0.20699394719540626,
791
+ "learning_rate": 3.133113296556603e-05,
792
+ "loss": 0.1495,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 0.9964726631393298,
797
+ "grad_norm": 0.18289020763400496,
798
+ "learning_rate": 3.117368042905466e-05,
799
+ "loss": 0.1517,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 1.0052910052910053,
804
+ "grad_norm": 0.2145241959606213,
805
+ "learning_rate": 3.101521461579139e-05,
806
+ "loss": 0.1409,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 1.0141093474426808,
811
+ "grad_norm": 0.20230933218493735,
812
+ "learning_rate": 3.085574989612856e-05,
813
+ "loss": 0.1321,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 1.0229276895943562,
818
+ "grad_norm": 0.18244350688332062,
819
+ "learning_rate": 3.069530073100356e-05,
820
+ "loss": 0.1313,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 1.0317460317460316,
825
+ "grad_norm": 0.19783195547267102,
826
+ "learning_rate": 3.053388167062747e-05,
827
+ "loss": 0.1321,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 1.0405643738977073,
832
+ "grad_norm": 0.2047114005081859,
833
+ "learning_rate": 3.037150735316561e-05,
834
+ "loss": 0.1332,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 1.0493827160493827,
839
+ "grad_norm": 0.24595017471664576,
840
+ "learning_rate": 3.0208192503410046e-05,
841
+ "loss": 0.131,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 1.0582010582010581,
846
+ "grad_norm": 0.23144086447587278,
847
+ "learning_rate": 3.0043951931444302e-05,
848
+ "loss": 0.1327,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 1.0670194003527338,
853
+ "grad_norm": 0.16985629437769836,
854
+ "learning_rate": 2.9878800531300335e-05,
855
+ "loss": 0.1337,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 1.0758377425044092,
860
+ "grad_norm": 0.19256405636053653,
861
+ "learning_rate": 2.9712753279607852e-05,
862
+ "loss": 0.1364,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 1.0846560846560847,
867
+ "grad_norm": 0.18555434282413438,
868
+ "learning_rate": 2.9545825234236187e-05,
869
+ "loss": 0.1306,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 1.09347442680776,
874
+ "grad_norm": 0.1847579476124522,
875
+ "learning_rate": 2.937803153292878e-05,
876
+ "loss": 0.1342,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 1.1022927689594355,
881
+ "grad_norm": 0.1834216574450437,
882
+ "learning_rate": 2.9209387391930425e-05,
883
+ "loss": 0.1341,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 1.1111111111111112,
888
+ "grad_norm": 0.18665818389653582,
889
+ "learning_rate": 2.9039908104607395e-05,
890
+ "loss": 0.1333,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 1.1199294532627866,
895
+ "grad_norm": 0.22873933014699052,
896
+ "learning_rate": 2.8869609040060572e-05,
897
+ "loss": 0.1336,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 1.128747795414462,
902
+ "grad_norm": 0.2183113906263531,
903
+ "learning_rate": 2.869850564173172e-05,
904
+ "loss": 0.1323,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 1.1375661375661377,
909
+ "grad_norm": 0.19099060399929857,
910
+ "learning_rate": 2.8526613426002998e-05,
911
+ "loss": 0.1319,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 1.146384479717813,
916
+ "grad_norm": 0.23917372520488436,
917
+ "learning_rate": 2.835394798078988e-05,
918
+ "loss": 0.1321,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 1.1552028218694885,
923
+ "grad_norm": 0.18407428002576853,
924
+ "learning_rate": 2.8180524964127573e-05,
925
+ "loss": 0.1317,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 1.164021164021164,
930
+ "grad_norm": 0.18430803378192598,
931
+ "learning_rate": 2.8006360102751064e-05,
932
+ "loss": 0.1322,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 1.1728395061728394,
937
+ "grad_norm": 0.1865135026451199,
938
+ "learning_rate": 2.7831469190668974e-05,
939
+ "loss": 0.133,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 1.181657848324515,
944
+ "grad_norm": 0.1884073237139698,
945
+ "learning_rate": 2.7655868087731295e-05,
946
+ "loss": 0.1317,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 1.1904761904761905,
951
+ "grad_norm": 0.20367415474239536,
952
+ "learning_rate": 2.7479572718191108e-05,
953
+ "loss": 0.1333,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 1.199294532627866,
958
+ "grad_norm": 0.17284748829644184,
959
+ "learning_rate": 2.7302599069260572e-05,
960
+ "loss": 0.1309,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 1.2081128747795415,
965
+ "grad_norm": 0.19491278141231555,
966
+ "learning_rate": 2.712496318966108e-05,
967
+ "loss": 0.1314,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 1.216931216931217,
972
+ "grad_norm": 0.18728688430541293,
973
+ "learning_rate": 2.69466811881679e-05,
974
+ "loss": 0.1334,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 1.2257495590828924,
979
+ "grad_norm": 0.17142414955172516,
980
+ "learning_rate": 2.67677692321494e-05,
981
+ "loss": 0.1331,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 1.2345679012345678,
986
+ "grad_norm": 0.20066666678092135,
987
+ "learning_rate": 2.6588243546100882e-05,
988
+ "loss": 0.1313,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 1.2433862433862433,
993
+ "grad_norm": 0.17159972944285481,
994
+ "learning_rate": 2.6408120410173296e-05,
995
+ "loss": 0.1287,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 1.252204585537919,
1000
+ "grad_norm": 0.19860628522583873,
1001
+ "learning_rate": 2.6227416158696884e-05,
1002
+ "loss": 0.1297,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 1.2610229276895943,
1007
+ "grad_norm": 0.18008904396878098,
1008
+ "learning_rate": 2.60461471786999e-05,
1009
+ "loss": 0.1309,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 1.2698412698412698,
1014
+ "grad_norm": 0.19386888274171976,
1015
+ "learning_rate": 2.5864329908422597e-05,
1016
+ "loss": 0.1292,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 1.2786596119929454,
1021
+ "grad_norm": 0.17303097118338565,
1022
+ "learning_rate": 2.5681980835826503e-05,
1023
+ "loss": 0.1295,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 1.2874779541446209,
1028
+ "grad_norm": 0.2348921814277289,
1029
+ "learning_rate": 2.5499116497099224e-05,
1030
+ "loss": 0.1314,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 1.2962962962962963,
1035
+ "grad_norm": 0.1778768891302646,
1036
+ "learning_rate": 2.531575347515492e-05,
1037
+ "loss": 0.1318,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 1.3051146384479717,
1042
+ "grad_norm": 0.17862605604327308,
1043
+ "learning_rate": 2.5131908398130426e-05,
1044
+ "loss": 0.1291,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 1.3139329805996471,
1049
+ "grad_norm": 0.1840381159551672,
1050
+ "learning_rate": 2.49475979378774e-05,
1051
+ "loss": 0.1299,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 1.3227513227513228,
1056
+ "grad_norm": 0.20235876379158219,
1057
+ "learning_rate": 2.476283880845042e-05,
1058
+ "loss": 0.1333,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 1.3315696649029982,
1063
+ "grad_norm": 0.17181294480397433,
1064
+ "learning_rate": 2.4577647764591276e-05,
1065
+ "loss": 0.1311,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 1.3403880070546736,
1070
+ "grad_norm": 0.17352177231303226,
1071
+ "learning_rate": 2.4392041600209608e-05,
1072
+ "loss": 0.1298,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 1.3492063492063493,
1077
+ "grad_norm": 0.16851418392357184,
1078
+ "learning_rate": 2.4206037146859944e-05,
1079
+ "loss": 0.1266,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 1.3580246913580247,
1084
+ "grad_norm": 0.18412108629041574,
1085
+ "learning_rate": 2.4019651272215338e-05,
1086
+ "loss": 0.131,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 1.3668430335097002,
1091
+ "grad_norm": 0.1643456743151178,
1092
+ "learning_rate": 2.383290087853775e-05,
1093
+ "loss": 0.1327,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 1.3756613756613756,
1098
+ "grad_norm": 0.16300381228966188,
1099
+ "learning_rate": 2.364580290114527e-05,
1100
+ "loss": 0.1328,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 1.384479717813051,
1105
+ "grad_norm": 0.19794647549566596,
1106
+ "learning_rate": 2.3458374306876355e-05,
1107
+ "loss": 0.1337,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 1.3932980599647267,
1112
+ "grad_norm": 0.17467360938800394,
1113
+ "learning_rate": 2.327063209255121e-05,
1114
+ "loss": 0.128,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 1.402116402116402,
1119
+ "grad_norm": 0.16534045366329517,
1120
+ "learning_rate": 2.308259328343042e-05,
1121
+ "loss": 0.1294,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 1.4109347442680775,
1126
+ "grad_norm": 0.17164884564245564,
1127
+ "learning_rate": 2.289427493167107e-05,
1128
+ "loss": 0.1291,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 1.4197530864197532,
1133
+ "grad_norm": 0.17685950000349324,
1134
+ "learning_rate": 2.270569411478033e-05,
1135
+ "loss": 0.1274,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 1.4285714285714286,
1140
+ "grad_norm": 0.1831151884550037,
1141
+ "learning_rate": 2.251686793406684e-05,
1142
+ "loss": 0.1297,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 1.437389770723104,
1147
+ "grad_norm": 0.17974969366439886,
1148
+ "learning_rate": 2.2327813513089875e-05,
1149
+ "loss": 0.1302,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 1.4462081128747795,
1154
+ "grad_norm": 0.16155993308368063,
1155
+ "learning_rate": 2.213854799610649e-05,
1156
+ "loss": 0.1285,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 1.455026455026455,
1161
+ "grad_norm": 0.1654535308338956,
1162
+ "learning_rate": 2.194908854651683e-05,
1163
+ "loss": 0.1289,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 1.4638447971781305,
1168
+ "grad_norm": 0.16507648912276562,
1169
+ "learning_rate": 2.1759452345307675e-05,
1170
+ "loss": 0.1275,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 1.472663139329806,
1175
+ "grad_norm": 0.1676790489693593,
1176
+ "learning_rate": 2.1569656589494386e-05,
1177
+ "loss": 0.1266,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 1.4814814814814814,
1182
+ "grad_norm": 0.1644355202426517,
1183
+ "learning_rate": 2.137971849056142e-05,
1184
+ "loss": 0.1271,
1185
+ "step": 1680
1186
+ },
1187
+ {
1188
+ "epoch": 1.490299823633157,
1189
+ "grad_norm": 0.16767396631965428,
1190
+ "learning_rate": 2.1189655272901498e-05,
1191
+ "loss": 0.1288,
1192
+ "step": 1690
1193
+ },
1194
+ {
1195
+ "epoch": 1.4991181657848325,
1196
+ "grad_norm": 0.16721154360000728,
1197
+ "learning_rate": 2.0999484172253654e-05,
1198
+ "loss": 0.1274,
1199
+ "step": 1700
1200
+ },
1201
+ {
1202
+ "epoch": 1.507936507936508,
1203
+ "grad_norm": 0.17218284188058708,
1204
+ "learning_rate": 2.08092224341402e-05,
1205
+ "loss": 0.1268,
1206
+ "step": 1710
1207
+ },
1208
+ {
1209
+ "epoch": 1.5167548500881836,
1210
+ "grad_norm": 0.16455812323793684,
1211
+ "learning_rate": 2.0618887312302838e-05,
1212
+ "loss": 0.1269,
1213
+ "step": 1720
1214
+ },
1215
+ {
1216
+ "epoch": 1.5255731922398588,
1217
+ "grad_norm": 0.18830223142596714,
1218
+ "learning_rate": 2.042849606713802e-05,
1219
+ "loss": 0.1327,
1220
+ "step": 1730
1221
+ },
1222
+ {
1223
+ "epoch": 1.5343915343915344,
1224
+ "grad_norm": 0.16569892684919732,
1225
+ "learning_rate": 2.02380659641317e-05,
1226
+ "loss": 0.1289,
1227
+ "step": 1740
1228
+ },
1229
+ {
1230
+ "epoch": 1.5432098765432098,
1231
+ "grad_norm": 0.16686242636674062,
1232
+ "learning_rate": 2.004761427229363e-05,
1233
+ "loss": 0.1241,
1234
+ "step": 1750
1235
+ },
1236
+ {
1237
+ "epoch": 1.5520282186948853,
1238
+ "grad_norm": 0.17007064306268857,
1239
+ "learning_rate": 1.985715826259131e-05,
1240
+ "loss": 0.1283,
1241
+ "step": 1760
1242
+ },
1243
+ {
1244
+ "epoch": 1.560846560846561,
1245
+ "grad_norm": 0.17887859439191145,
1246
+ "learning_rate": 1.966671520638383e-05,
1247
+ "loss": 0.1268,
1248
+ "step": 1770
1249
+ },
1250
+ {
1251
+ "epoch": 1.5696649029982364,
1252
+ "grad_norm": 0.17041240102360516,
1253
+ "learning_rate": 1.947630237385558e-05,
1254
+ "loss": 0.1281,
1255
+ "step": 1780
1256
+ },
1257
+ {
1258
+ "epoch": 1.5784832451499118,
1259
+ "grad_norm": 0.16320063163341206,
1260
+ "learning_rate": 1.9285937032450146e-05,
1261
+ "loss": 0.128,
1262
+ "step": 1790
1263
+ },
1264
+ {
1265
+ "epoch": 1.5873015873015874,
1266
+ "grad_norm": 0.17846835386270518,
1267
+ "learning_rate": 1.909563644530443e-05,
1268
+ "loss": 0.1264,
1269
+ "step": 1800
1270
+ },
1271
+ {
1272
+ "epoch": 1.5961199294532626,
1273
+ "grad_norm": 0.1506424501330394,
1274
+ "learning_rate": 1.8905417869683113e-05,
1275
+ "loss": 0.1268,
1276
+ "step": 1810
1277
+ },
1278
+ {
1279
+ "epoch": 1.6049382716049383,
1280
+ "grad_norm": 0.15586172611133045,
1281
+ "learning_rate": 1.871529855541375e-05,
1282
+ "loss": 0.1249,
1283
+ "step": 1820
1284
+ },
1285
+ {
1286
+ "epoch": 1.6137566137566137,
1287
+ "grad_norm": 0.16774679274129406,
1288
+ "learning_rate": 1.8525295743322453e-05,
1289
+ "loss": 0.1269,
1290
+ "step": 1830
1291
+ },
1292
+ {
1293
+ "epoch": 1.6225749559082892,
1294
+ "grad_norm": 0.1727635954009701,
1295
+ "learning_rate": 1.8335426663670397e-05,
1296
+ "loss": 0.1273,
1297
+ "step": 1840
1298
+ },
1299
+ {
1300
+ "epoch": 1.6313932980599648,
1301
+ "grad_norm": 0.1892975495137155,
1302
+ "learning_rate": 1.8145708534591377e-05,
1303
+ "loss": 0.1255,
1304
+ "step": 1850
1305
+ },
1306
+ {
1307
+ "epoch": 1.6402116402116402,
1308
+ "grad_norm": 0.16857751294190276,
1309
+ "learning_rate": 1.79561585605303e-05,
1310
+ "loss": 0.1283,
1311
+ "step": 1860
1312
+ },
1313
+ {
1314
+ "epoch": 1.6490299823633157,
1315
+ "grad_norm": 0.1718737988430891,
1316
+ "learning_rate": 1.7766793930683094e-05,
1317
+ "loss": 0.1254,
1318
+ "step": 1870
1319
+ },
1320
+ {
1321
+ "epoch": 1.6578483245149913,
1322
+ "grad_norm": 0.1588131771656951,
1323
+ "learning_rate": 1.7577631817437888e-05,
1324
+ "loss": 0.1244,
1325
+ "step": 1880
1326
+ },
1327
+ {
1328
+ "epoch": 1.6666666666666665,
1329
+ "grad_norm": 0.16479791762147233,
1330
+ "learning_rate": 1.7388689374817722e-05,
1331
+ "loss": 0.1232,
1332
+ "step": 1890
1333
+ },
1334
+ {
1335
+ "epoch": 1.6754850088183422,
1336
+ "grad_norm": 0.20327562061299326,
1337
+ "learning_rate": 1.719998373692499e-05,
1338
+ "loss": 0.1259,
1339
+ "step": 1900
1340
+ },
1341
+ {
1342
+ "epoch": 1.6843033509700176,
1343
+ "grad_norm": 0.17445146984586163,
1344
+ "learning_rate": 1.7011532016387637e-05,
1345
+ "loss": 0.1241,
1346
+ "step": 1910
1347
+ },
1348
+ {
1349
+ "epoch": 1.693121693121693,
1350
+ "grad_norm": 0.15172765768609214,
1351
+ "learning_rate": 1.682335130280728e-05,
1352
+ "loss": 0.1248,
1353
+ "step": 1920
1354
+ },
1355
+ {
1356
+ "epoch": 1.7019400352733687,
1357
+ "grad_norm": 0.15540418406256226,
1358
+ "learning_rate": 1.663545866120949e-05,
1359
+ "loss": 0.1209,
1360
+ "step": 1930
1361
+ },
1362
+ {
1363
+ "epoch": 1.710758377425044,
1364
+ "grad_norm": 0.1614644793216772,
1365
+ "learning_rate": 1.6447871130496257e-05,
1366
+ "loss": 0.1239,
1367
+ "step": 1940
1368
+ },
1369
+ {
1370
+ "epoch": 1.7195767195767195,
1371
+ "grad_norm": 0.15504804793224192,
1372
+ "learning_rate": 1.62606057219008e-05,
1373
+ "loss": 0.1261,
1374
+ "step": 1950
1375
+ },
1376
+ {
1377
+ "epoch": 1.7283950617283952,
1378
+ "grad_norm": 0.17006738174447467,
1379
+ "learning_rate": 1.6073679417444946e-05,
1380
+ "loss": 0.1266,
1381
+ "step": 1960
1382
+ },
1383
+ {
1384
+ "epoch": 1.7372134038800704,
1385
+ "grad_norm": 0.17505387505969047,
1386
+ "learning_rate": 1.588710916839914e-05,
1387
+ "loss": 0.1225,
1388
+ "step": 1970
1389
+ },
1390
+ {
1391
+ "epoch": 1.746031746031746,
1392
+ "grad_norm": 0.1612549181660387,
1393
+ "learning_rate": 1.570091189374518e-05,
1394
+ "loss": 0.1249,
1395
+ "step": 1980
1396
+ },
1397
+ {
1398
+ "epoch": 1.7548500881834215,
1399
+ "grad_norm": 0.16112907861897668,
1400
+ "learning_rate": 1.5515104478641975e-05,
1401
+ "loss": 0.1254,
1402
+ "step": 1990
1403
+ },
1404
+ {
1405
+ "epoch": 1.763668430335097,
1406
+ "grad_norm": 0.15922476014447312,
1407
+ "learning_rate": 1.5329703772894327e-05,
1408
+ "loss": 0.1236,
1409
+ "step": 2000
1410
+ },
1411
+ {
1412
+ "epoch": 1.7724867724867726,
1413
+ "grad_norm": 0.17212069125892313,
1414
+ "learning_rate": 1.51447265894249e-05,
1415
+ "loss": 0.1242,
1416
+ "step": 2010
1417
+ },
1418
+ {
1419
+ "epoch": 1.781305114638448,
1420
+ "grad_norm": 0.1740636826222426,
1421
+ "learning_rate": 1.4960189702749551e-05,
1422
+ "loss": 0.1245,
1423
+ "step": 2020
1424
+ },
1425
+ {
1426
+ "epoch": 1.7901234567901234,
1427
+ "grad_norm": 0.15528067596347245,
1428
+ "learning_rate": 1.4776109847456173e-05,
1429
+ "loss": 0.1226,
1430
+ "step": 2030
1431
+ },
1432
+ {
1433
+ "epoch": 1.798941798941799,
1434
+ "grad_norm": 0.15722708188146675,
1435
+ "learning_rate": 1.4592503716687107e-05,
1436
+ "loss": 0.1243,
1437
+ "step": 2040
1438
+ },
1439
+ {
1440
+ "epoch": 1.8077601410934743,
1441
+ "grad_norm": 0.15918925574073986,
1442
+ "learning_rate": 1.4409387960625331e-05,
1443
+ "loss": 0.1216,
1444
+ "step": 2050
1445
+ },
1446
+ {
1447
+ "epoch": 1.81657848324515,
1448
+ "grad_norm": 0.1576457624630644,
1449
+ "learning_rate": 1.422677918498459e-05,
1450
+ "loss": 0.1249,
1451
+ "step": 2060
1452
+ },
1453
+ {
1454
+ "epoch": 1.8253968253968254,
1455
+ "grad_norm": 0.18618951180895943,
1456
+ "learning_rate": 1.4044693949503465e-05,
1457
+ "loss": 0.1251,
1458
+ "step": 2070
1459
+ },
1460
+ {
1461
+ "epoch": 1.8342151675485008,
1462
+ "grad_norm": 0.15865872308397924,
1463
+ "learning_rate": 1.3863148766443723e-05,
1464
+ "loss": 0.1228,
1465
+ "step": 2080
1466
+ },
1467
+ {
1468
+ "epoch": 1.8430335097001764,
1469
+ "grad_norm": 0.15045663896792358,
1470
+ "learning_rate": 1.368216009909286e-05,
1471
+ "loss": 0.1221,
1472
+ "step": 2090
1473
+ },
1474
+ {
1475
+ "epoch": 1.8518518518518519,
1476
+ "grad_norm": 0.15818210790519696,
1477
+ "learning_rate": 1.3501744360271177e-05,
1478
+ "loss": 0.123,
1479
+ "step": 2100
1480
+ },
1481
+ {
1482
+ "epoch": 1.8606701940035273,
1483
+ "grad_norm": 0.16422734107091674,
1484
+ "learning_rate": 1.3321917910843394e-05,
1485
+ "loss": 0.1187,
1486
+ "step": 2110
1487
+ },
1488
+ {
1489
+ "epoch": 1.869488536155203,
1490
+ "grad_norm": 0.15177335025772304,
1491
+ "learning_rate": 1.3142697058234952e-05,
1492
+ "loss": 0.1222,
1493
+ "step": 2120
1494
+ },
1495
+ {
1496
+ "epoch": 1.8783068783068781,
1497
+ "grad_norm": 0.15321330650093545,
1498
+ "learning_rate": 1.2964098054953209e-05,
1499
+ "loss": 0.1205,
1500
+ "step": 2130
1501
+ },
1502
+ {
1503
+ "epoch": 1.8871252204585538,
1504
+ "grad_norm": 0.16140622128902943,
1505
+ "learning_rate": 1.2786137097113594e-05,
1506
+ "loss": 0.1194,
1507
+ "step": 2140
1508
+ },
1509
+ {
1510
+ "epoch": 1.8959435626102292,
1511
+ "grad_norm": 0.15735771104485857,
1512
+ "learning_rate": 1.2608830322970865e-05,
1513
+ "loss": 0.1234,
1514
+ "step": 2150
1515
+ },
1516
+ {
1517
+ "epoch": 1.9047619047619047,
1518
+ "grad_norm": 0.15949016923062945,
1519
+ "learning_rate": 1.2432193811455609e-05,
1520
+ "loss": 0.1237,
1521
+ "step": 2160
1522
+ },
1523
+ {
1524
+ "epoch": 1.9135802469135803,
1525
+ "grad_norm": 0.16001139592539343,
1526
+ "learning_rate": 1.2256243580716187e-05,
1527
+ "loss": 0.1216,
1528
+ "step": 2170
1529
+ },
1530
+ {
1531
+ "epoch": 1.9223985890652557,
1532
+ "grad_norm": 0.14752520035248345,
1533
+ "learning_rate": 1.2080995586666085e-05,
1534
+ "loss": 0.122,
1535
+ "step": 2180
1536
+ },
1537
+ {
1538
+ "epoch": 1.9312169312169312,
1539
+ "grad_norm": 0.15247438606628488,
1540
+ "learning_rate": 1.1906465721536984e-05,
1541
+ "loss": 0.1236,
1542
+ "step": 2190
1543
+ },
1544
+ {
1545
+ "epoch": 1.9400352733686068,
1546
+ "grad_norm": 0.15289569423666619,
1547
+ "learning_rate": 1.17326698124376e-05,
1548
+ "loss": 0.1214,
1549
+ "step": 2200
1550
+ },
1551
+ {
1552
+ "epoch": 1.948853615520282,
1553
+ "grad_norm": 0.17526380738963238,
1554
+ "learning_rate": 1.1559623619918396e-05,
1555
+ "loss": 0.1212,
1556
+ "step": 2210
1557
+ },
1558
+ {
1559
+ "epoch": 1.9576719576719577,
1560
+ "grad_norm": 0.16261170275972142,
1561
+ "learning_rate": 1.1387342836542353e-05,
1562
+ "loss": 0.1203,
1563
+ "step": 2220
1564
+ },
1565
+ {
1566
+ "epoch": 1.966490299823633,
1567
+ "grad_norm": 0.16169651658483872,
1568
+ "learning_rate": 1.1215843085461912e-05,
1569
+ "loss": 0.1187,
1570
+ "step": 2230
1571
+ },
1572
+ {
1573
+ "epoch": 1.9753086419753085,
1574
+ "grad_norm": 0.1595833660103317,
1575
+ "learning_rate": 1.1045139919002181e-05,
1576
+ "loss": 0.1185,
1577
+ "step": 2240
1578
+ },
1579
+ {
1580
+ "epoch": 1.9841269841269842,
1581
+ "grad_norm": 0.15303519805668522,
1582
+ "learning_rate": 1.087524881725059e-05,
1583
+ "loss": 0.1223,
1584
+ "step": 2250
1585
+ },
1586
+ {
1587
+ "epoch": 1.9929453262786596,
1588
+ "grad_norm": 0.16239859350306318,
1589
+ "learning_rate": 1.0706185186653108e-05,
1590
+ "loss": 0.1195,
1591
+ "step": 2260
1592
+ },
1593
+ {
1594
+ "epoch": 2.001763668430335,
1595
+ "grad_norm": 0.1948721740831915,
1596
+ "learning_rate": 1.0537964358617114e-05,
1597
+ "loss": 0.1145,
1598
+ "step": 2270
1599
+ },
1600
+ {
1601
+ "epoch": 2.0105820105820107,
1602
+ "grad_norm": 0.17072323405727977,
1603
+ "learning_rate": 1.0370601588121052e-05,
1604
+ "loss": 0.0971,
1605
+ "step": 2280
1606
+ },
1607
+ {
1608
+ "epoch": 2.019400352733686,
1609
+ "grad_norm": 0.1730651246941294,
1610
+ "learning_rate": 1.0204112052331097e-05,
1611
+ "loss": 0.0983,
1612
+ "step": 2290
1613
+ },
1614
+ {
1615
+ "epoch": 2.0282186948853616,
1616
+ "grad_norm": 0.15846505516821519,
1617
+ "learning_rate": 1.0038510849224758e-05,
1618
+ "loss": 0.097,
1619
+ "step": 2300
1620
+ },
1621
+ {
1622
+ "epoch": 2.037037037037037,
1623
+ "grad_norm": 0.18557277607745912,
1624
+ "learning_rate": 9.87381299622181e-06,
1625
+ "loss": 0.0942,
1626
+ "step": 2310
1627
+ },
1628
+ {
1629
+ "epoch": 2.0458553791887124,
1630
+ "grad_norm": 0.16362091724207117,
1631
+ "learning_rate": 9.710033428822368e-06,
1632
+ "loss": 0.0952,
1633
+ "step": 2320
1634
+ },
1635
+ {
1636
+ "epoch": 2.054673721340388,
1637
+ "grad_norm": 0.16144197990009226,
1638
+ "learning_rate": 9.547186999252538e-06,
1639
+ "loss": 0.0966,
1640
+ "step": 2330
1641
+ },
1642
+ {
1643
+ "epoch": 2.0634920634920633,
1644
+ "grad_norm": 0.1703392645828158,
1645
+ "learning_rate": 9.385288475117526e-06,
1646
+ "loss": 0.0947,
1647
+ "step": 2340
1648
+ },
1649
+ {
1650
+ "epoch": 2.072310405643739,
1651
+ "grad_norm": 0.18472104722259497,
1652
+ "learning_rate": 9.224352538062441e-06,
1653
+ "loss": 0.0961,
1654
+ "step": 2350
1655
+ },
1656
+ {
1657
+ "epoch": 2.0811287477954146,
1658
+ "grad_norm": 0.16657694584089722,
1659
+ "learning_rate": 9.06439378244091e-06,
1660
+ "loss": 0.0935,
1661
+ "step": 2360
1662
+ },
1663
+ {
1664
+ "epoch": 2.0899470899470898,
1665
+ "grad_norm": 0.1640060501350356,
1666
+ "learning_rate": 8.905426713991609e-06,
1667
+ "loss": 0.098,
1668
+ "step": 2370
1669
+ },
1670
+ {
1671
+ "epoch": 2.0987654320987654,
1672
+ "grad_norm": 0.155343849676478,
1673
+ "learning_rate": 8.747465748522824e-06,
1674
+ "loss": 0.0929,
1675
+ "step": 2380
1676
+ },
1677
+ {
1678
+ "epoch": 2.107583774250441,
1679
+ "grad_norm": 0.16657876804825647,
1680
+ "learning_rate": 8.590525210605125e-06,
1681
+ "loss": 0.0938,
1682
+ "step": 2390
1683
+ },
1684
+ {
1685
+ "epoch": 2.1164021164021163,
1686
+ "grad_norm": 0.1626875240950099,
1687
+ "learning_rate": 8.434619332272412e-06,
1688
+ "loss": 0.0933,
1689
+ "step": 2400
1690
+ },
1691
+ {
1692
+ "epoch": 2.125220458553792,
1693
+ "grad_norm": 0.1613598792215022,
1694
+ "learning_rate": 8.279762251731246e-06,
1695
+ "loss": 0.0944,
1696
+ "step": 2410
1697
+ },
1698
+ {
1699
+ "epoch": 2.1340388007054676,
1700
+ "grad_norm": 0.1638238651603253,
1701
+ "learning_rate": 8.125968012078745e-06,
1702
+ "loss": 0.092,
1703
+ "step": 2420
1704
+ },
1705
+ {
1706
+ "epoch": 2.142857142857143,
1707
+ "grad_norm": 0.16977220285542402,
1708
+ "learning_rate": 7.973250560029132e-06,
1709
+ "loss": 0.0939,
1710
+ "step": 2430
1711
+ },
1712
+ {
1713
+ "epoch": 2.1516754850088184,
1714
+ "grad_norm": 0.16753471017264823,
1715
+ "learning_rate": 7.821623744648952e-06,
1716
+ "loss": 0.0917,
1717
+ "step": 2440
1718
+ },
1719
+ {
1720
+ "epoch": 2.1604938271604937,
1721
+ "grad_norm": 0.16181368054619877,
1722
+ "learning_rate": 7.671101316101172e-06,
1723
+ "loss": 0.0942,
1724
+ "step": 2450
1725
+ },
1726
+ {
1727
+ "epoch": 2.1693121693121693,
1728
+ "grad_norm": 0.16568414134323833,
1729
+ "learning_rate": 7.521696924398303e-06,
1730
+ "loss": 0.0947,
1731
+ "step": 2460
1732
+ },
1733
+ {
1734
+ "epoch": 2.178130511463845,
1735
+ "grad_norm": 0.15925917816119767,
1736
+ "learning_rate": 7.373424118164501e-06,
1737
+ "loss": 0.0944,
1738
+ "step": 2470
1739
+ },
1740
+ {
1741
+ "epoch": 2.18694885361552,
1742
+ "grad_norm": 0.16349944720912132,
1743
+ "learning_rate": 7.226296343406974e-06,
1744
+ "loss": 0.0941,
1745
+ "step": 2480
1746
+ },
1747
+ {
1748
+ "epoch": 2.195767195767196,
1749
+ "grad_norm": 0.16785075128125135,
1750
+ "learning_rate": 7.0803269422966135e-06,
1751
+ "loss": 0.0922,
1752
+ "step": 2490
1753
+ },
1754
+ {
1755
+ "epoch": 2.204585537918871,
1756
+ "grad_norm": 0.15912892496071598,
1757
+ "learning_rate": 6.935529151958065e-06,
1758
+ "loss": 0.0948,
1759
+ "step": 2500
1760
+ },
1761
+ {
1762
+ "epoch": 2.2134038800705467,
1763
+ "grad_norm": 0.16142401500311457,
1764
+ "learning_rate": 6.791916103269333e-06,
1765
+ "loss": 0.0932,
1766
+ "step": 2510
1767
+ },
1768
+ {
1769
+ "epoch": 2.2222222222222223,
1770
+ "grad_norm": 0.1664762727497597,
1771
+ "learning_rate": 6.649500819671047e-06,
1772
+ "loss": 0.0955,
1773
+ "step": 2520
1774
+ },
1775
+ {
1776
+ "epoch": 2.2310405643738975,
1777
+ "grad_norm": 0.16004719129428444,
1778
+ "learning_rate": 6.5082962159853834e-06,
1779
+ "loss": 0.0898,
1780
+ "step": 2530
1781
+ },
1782
+ {
1783
+ "epoch": 2.239858906525573,
1784
+ "grad_norm": 0.1615455245606165,
1785
+ "learning_rate": 6.368315097244955e-06,
1786
+ "loss": 0.0917,
1787
+ "step": 2540
1788
+ },
1789
+ {
1790
+ "epoch": 2.248677248677249,
1791
+ "grad_norm": 0.16743450359900008,
1792
+ "learning_rate": 6.2295701575315594e-06,
1793
+ "loss": 0.0916,
1794
+ "step": 2550
1795
+ },
1796
+ {
1797
+ "epoch": 2.257495590828924,
1798
+ "grad_norm": 0.16544121841662957,
1799
+ "learning_rate": 6.092073978825022e-06,
1800
+ "loss": 0.0927,
1801
+ "step": 2560
1802
+ },
1803
+ {
1804
+ "epoch": 2.2663139329805997,
1805
+ "grad_norm": 0.16180251542385612,
1806
+ "learning_rate": 5.955839029862245e-06,
1807
+ "loss": 0.0946,
1808
+ "step": 2570
1809
+ },
1810
+ {
1811
+ "epoch": 2.2751322751322753,
1812
+ "grad_norm": 0.15338708773074522,
1813
+ "learning_rate": 5.820877665006441e-06,
1814
+ "loss": 0.0926,
1815
+ "step": 2580
1816
+ },
1817
+ {
1818
+ "epoch": 2.2839506172839505,
1819
+ "grad_norm": 0.15957923017749945,
1820
+ "learning_rate": 5.687202123126832e-06,
1821
+ "loss": 0.0952,
1822
+ "step": 2590
1823
+ },
1824
+ {
1825
+ "epoch": 2.292768959435626,
1826
+ "grad_norm": 0.15484396525882926,
1827
+ "learning_rate": 5.5548245264887515e-06,
1828
+ "loss": 0.0929,
1829
+ "step": 2600
1830
+ },
1831
+ {
1832
+ "epoch": 2.3015873015873014,
1833
+ "grad_norm": 0.15944927489262736,
1834
+ "learning_rate": 5.423756879654343e-06,
1835
+ "loss": 0.092,
1836
+ "step": 2610
1837
+ },
1838
+ {
1839
+ "epoch": 2.310405643738977,
1840
+ "grad_norm": 0.1555885456859465,
1841
+ "learning_rate": 5.294011068393945e-06,
1842
+ "loss": 0.0932,
1843
+ "step": 2620
1844
+ },
1845
+ {
1846
+ "epoch": 2.3192239858906527,
1847
+ "grad_norm": 0.1616989709098896,
1848
+ "learning_rate": 5.1655988586082535e-06,
1849
+ "loss": 0.0944,
1850
+ "step": 2630
1851
+ },
1852
+ {
1853
+ "epoch": 2.328042328042328,
1854
+ "grad_norm": 0.15595636612871588,
1855
+ "learning_rate": 5.038531895261301e-06,
1856
+ "loss": 0.094,
1857
+ "step": 2640
1858
+ },
1859
+ {
1860
+ "epoch": 2.3368606701940036,
1861
+ "grad_norm": 0.1773185191439187,
1862
+ "learning_rate": 4.912821701324479e-06,
1863
+ "loss": 0.0924,
1864
+ "step": 2650
1865
+ },
1866
+ {
1867
+ "epoch": 2.3456790123456788,
1868
+ "grad_norm": 0.16579054625602957,
1869
+ "learning_rate": 4.788479676731581e-06,
1870
+ "loss": 0.0936,
1871
+ "step": 2660
1872
+ },
1873
+ {
1874
+ "epoch": 2.3544973544973544,
1875
+ "grad_norm": 0.15352554844705696,
1876
+ "learning_rate": 4.665517097344976e-06,
1877
+ "loss": 0.0935,
1878
+ "step": 2670
1879
+ },
1880
+ {
1881
+ "epoch": 2.36331569664903,
1882
+ "grad_norm": 0.15451348902863254,
1883
+ "learning_rate": 4.543945113933099e-06,
1884
+ "loss": 0.0931,
1885
+ "step": 2680
1886
+ },
1887
+ {
1888
+ "epoch": 2.3721340388007053,
1889
+ "grad_norm": 0.16299047928042187,
1890
+ "learning_rate": 4.423774751159247e-06,
1891
+ "loss": 0.0937,
1892
+ "step": 2690
1893
+ },
1894
+ {
1895
+ "epoch": 2.380952380952381,
1896
+ "grad_norm": 0.15558927808811412,
1897
+ "learning_rate": 4.305016906581811e-06,
1898
+ "loss": 0.0906,
1899
+ "step": 2700
1900
+ },
1901
+ {
1902
+ "epoch": 2.3897707231040566,
1903
+ "grad_norm": 0.15763428447923092,
1904
+ "learning_rate": 4.1876823496660245e-06,
1905
+ "loss": 0.0919,
1906
+ "step": 2710
1907
+ },
1908
+ {
1909
+ "epoch": 2.398589065255732,
1910
+ "grad_norm": 0.1614586373848465,
1911
+ "learning_rate": 4.071781720807375e-06,
1912
+ "loss": 0.0929,
1913
+ "step": 2720
1914
+ },
1915
+ {
1916
+ "epoch": 2.4074074074074074,
1917
+ "grad_norm": 0.15663328679730767,
1918
+ "learning_rate": 3.9573255303666554e-06,
1919
+ "loss": 0.0911,
1920
+ "step": 2730
1921
+ },
1922
+ {
1923
+ "epoch": 2.416225749559083,
1924
+ "grad_norm": 0.15190824093071106,
1925
+ "learning_rate": 3.844324157716857e-06,
1926
+ "loss": 0.0906,
1927
+ "step": 2740
1928
+ },
1929
+ {
1930
+ "epoch": 2.4250440917107583,
1931
+ "grad_norm": 0.15885908725225142,
1932
+ "learning_rate": 3.7327878503019243e-06,
1933
+ "loss": 0.0903,
1934
+ "step": 2750
1935
+ },
1936
+ {
1937
+ "epoch": 2.433862433862434,
1938
+ "grad_norm": 0.15186092891507827,
1939
+ "learning_rate": 3.622726722707479e-06,
1940
+ "loss": 0.09,
1941
+ "step": 2760
1942
+ },
1943
+ {
1944
+ "epoch": 2.442680776014109,
1945
+ "grad_norm": 0.15364028795008292,
1946
+ "learning_rate": 3.5141507557435504e-06,
1947
+ "loss": 0.093,
1948
+ "step": 2770
1949
+ },
1950
+ {
1951
+ "epoch": 2.451499118165785,
1952
+ "grad_norm": 0.15589229219750106,
1953
+ "learning_rate": 3.4070697955395326e-06,
1954
+ "loss": 0.0897,
1955
+ "step": 2780
1956
+ },
1957
+ {
1958
+ "epoch": 2.4603174603174605,
1959
+ "grad_norm": 0.15718297314700777,
1960
+ "learning_rate": 3.3014935526512383e-06,
1961
+ "loss": 0.0922,
1962
+ "step": 2790
1963
+ },
1964
+ {
1965
+ "epoch": 2.4691358024691357,
1966
+ "grad_norm": 0.15723729478788426,
1967
+ "learning_rate": 3.197431601180343e-06,
1968
+ "loss": 0.0924,
1969
+ "step": 2800
1970
+ },
1971
+ {
1972
+ "epoch": 2.4779541446208113,
1973
+ "grad_norm": 0.1600488009457486,
1974
+ "learning_rate": 3.094893377906143e-06,
1975
+ "loss": 0.0897,
1976
+ "step": 2810
1977
+ },
1978
+ {
1979
+ "epoch": 2.4867724867724865,
1980
+ "grad_norm": 0.1545448158355294,
1981
+ "learning_rate": 2.9938881814298002e-06,
1982
+ "loss": 0.0901,
1983
+ "step": 2820
1984
+ },
1985
+ {
1986
+ "epoch": 2.495590828924162,
1987
+ "grad_norm": 0.15517515088748454,
1988
+ "learning_rate": 2.894425171331112e-06,
1989
+ "loss": 0.0918,
1990
+ "step": 2830
1991
+ },
1992
+ {
1993
+ "epoch": 2.504409171075838,
1994
+ "grad_norm": 0.15614342046875468,
1995
+ "learning_rate": 2.796513367337854e-06,
1996
+ "loss": 0.0883,
1997
+ "step": 2840
1998
+ },
1999
+ {
2000
+ "epoch": 2.5132275132275135,
2001
+ "grad_norm": 0.1532975772545578,
2002
+ "learning_rate": 2.7001616485078553e-06,
2003
+ "loss": 0.0937,
2004
+ "step": 2850
2005
+ },
2006
+ {
2007
+ "epoch": 2.5220458553791887,
2008
+ "grad_norm": 0.15407944254916026,
2009
+ "learning_rate": 2.6053787524238084e-06,
2010
+ "loss": 0.0881,
2011
+ "step": 2860
2012
+ },
2013
+ {
2014
+ "epoch": 2.5308641975308643,
2015
+ "grad_norm": 0.15187561548545364,
2016
+ "learning_rate": 2.512173274400904e-06,
2017
+ "loss": 0.0883,
2018
+ "step": 2870
2019
+ },
2020
+ {
2021
+ "epoch": 2.5396825396825395,
2022
+ "grad_norm": 0.15129893026103466,
2023
+ "learning_rate": 2.4205536667073572e-06,
2024
+ "loss": 0.0914,
2025
+ "step": 2880
2026
+ },
2027
+ {
2028
+ "epoch": 2.548500881834215,
2029
+ "grad_norm": 0.15387910729749937,
2030
+ "learning_rate": 2.330528237797949e-06,
2031
+ "loss": 0.0916,
2032
+ "step": 2890
2033
+ },
2034
+ {
2035
+ "epoch": 2.557319223985891,
2036
+ "grad_norm": 0.15310039839687165,
2037
+ "learning_rate": 2.242105151560554e-06,
2038
+ "loss": 0.0897,
2039
+ "step": 2900
2040
+ },
2041
+ {
2042
+ "epoch": 2.566137566137566,
2043
+ "grad_norm": 0.15660569630223034,
2044
+ "learning_rate": 2.1552924265758102e-06,
2045
+ "loss": 0.0883,
2046
+ "step": 2910
2047
+ },
2048
+ {
2049
+ "epoch": 2.5749559082892417,
2050
+ "grad_norm": 0.15625668536136728,
2051
+ "learning_rate": 2.070097935389974e-06,
2052
+ "loss": 0.088,
2053
+ "step": 2920
2054
+ },
2055
+ {
2056
+ "epoch": 2.583774250440917,
2057
+ "grad_norm": 0.16440666779797036,
2058
+ "learning_rate": 1.9865294038009984e-06,
2059
+ "loss": 0.09,
2060
+ "step": 2930
2061
+ },
2062
+ {
2063
+ "epoch": 2.5925925925925926,
2064
+ "grad_norm": 0.15497386680361938,
2065
+ "learning_rate": 1.9045944101579073e-06,
2066
+ "loss": 0.0896,
2067
+ "step": 2940
2068
+ },
2069
+ {
2070
+ "epoch": 2.601410934744268,
2071
+ "grad_norm": 0.1528557591079046,
2072
+ "learning_rate": 1.8243003846735807e-06,
2073
+ "loss": 0.0916,
2074
+ "step": 2950
2075
+ },
2076
+ {
2077
+ "epoch": 2.6102292768959434,
2078
+ "grad_norm": 0.14797025757103924,
2079
+ "learning_rate": 1.7456546087509419e-06,
2080
+ "loss": 0.0882,
2081
+ "step": 2960
2082
+ },
2083
+ {
2084
+ "epoch": 2.619047619047619,
2085
+ "grad_norm": 0.15101812244580526,
2086
+ "learning_rate": 1.6686642143226484e-06,
2087
+ "loss": 0.0892,
2088
+ "step": 2970
2089
+ },
2090
+ {
2091
+ "epoch": 2.6278659611992943,
2092
+ "grad_norm": 0.14853644829002635,
2093
+ "learning_rate": 1.593336183204346e-06,
2094
+ "loss": 0.0884,
2095
+ "step": 2980
2096
+ },
2097
+ {
2098
+ "epoch": 2.63668430335097,
2099
+ "grad_norm": 0.1547300718526592,
2100
+ "learning_rate": 1.5196773464615167e-06,
2101
+ "loss": 0.0902,
2102
+ "step": 2990
2103
+ },
2104
+ {
2105
+ "epoch": 2.6455026455026456,
2106
+ "grad_norm": 0.14824004323134074,
2107
+ "learning_rate": 1.4476943837900105e-06,
2108
+ "loss": 0.0915,
2109
+ "step": 3000
2110
+ },
2111
+ {
2112
+ "epoch": 2.6543209876543212,
2113
+ "grad_norm": 0.15162108864434684,
2114
+ "learning_rate": 1.377393822910318e-06,
2115
+ "loss": 0.0904,
2116
+ "step": 3010
2117
+ },
2118
+ {
2119
+ "epoch": 2.6631393298059964,
2120
+ "grad_norm": 0.1539793202148526,
2121
+ "learning_rate": 1.30878203897558e-06,
2122
+ "loss": 0.0883,
2123
+ "step": 3020
2124
+ },
2125
+ {
2126
+ "epoch": 2.671957671957672,
2127
+ "grad_norm": 0.15086750725756884,
2128
+ "learning_rate": 1.241865253993495e-06,
2129
+ "loss": 0.0899,
2130
+ "step": 3030
2131
+ },
2132
+ {
2133
+ "epoch": 2.6807760141093473,
2134
+ "grad_norm": 0.1555053078276991,
2135
+ "learning_rate": 1.1766495362620555e-06,
2136
+ "loss": 0.09,
2137
+ "step": 3040
2138
+ },
2139
+ {
2140
+ "epoch": 2.689594356261023,
2141
+ "grad_norm": 0.15052416992823459,
2142
+ "learning_rate": 1.1131407998192567e-06,
2143
+ "loss": 0.089,
2144
+ "step": 3050
2145
+ },
2146
+ {
2147
+ "epoch": 2.6984126984126986,
2148
+ "grad_norm": 0.1504945657873999,
2149
+ "learning_rate": 1.0513448039067954e-06,
2150
+ "loss": 0.0892,
2151
+ "step": 3060
2152
+ },
2153
+ {
2154
+ "epoch": 2.707231040564374,
2155
+ "grad_norm": 0.1478376395173767,
2156
+ "learning_rate": 9.91267152447779e-07,
2157
+ "loss": 0.0878,
2158
+ "step": 3070
2159
+ },
2160
+ {
2161
+ "epoch": 2.7160493827160495,
2162
+ "grad_norm": 0.1509329096731571,
2163
+ "learning_rate": 9.329132935385577e-07,
2164
+ "loss": 0.0899,
2165
+ "step": 3080
2166
+ },
2167
+ {
2168
+ "epoch": 2.7248677248677247,
2169
+ "grad_norm": 0.15222497781820243,
2170
+ "learning_rate": 8.7628851895466e-07,
2171
+ "loss": 0.0916,
2172
+ "step": 3090
2173
+ },
2174
+ {
2175
+ "epoch": 2.7336860670194003,
2176
+ "grad_norm": 0.15030672400304343,
2177
+ "learning_rate": 8.213979636709046e-07,
2178
+ "loss": 0.0922,
2179
+ "step": 3100
2180
+ },
2181
+ {
2182
+ "epoch": 2.742504409171076,
2183
+ "grad_norm": 0.15512035164112659,
2184
+ "learning_rate": 7.682466053957438e-07,
2185
+ "loss": 0.0888,
2186
+ "step": 3110
2187
+ },
2188
+ {
2189
+ "epoch": 2.751322751322751,
2190
+ "grad_norm": 0.14852112467156292,
2191
+ "learning_rate": 7.168392641198796e-07,
2192
+ "loss": 0.0869,
2193
+ "step": 3120
2194
+ },
2195
+ {
2196
+ "epoch": 2.760141093474427,
2197
+ "grad_norm": 0.15336396025005739,
2198
+ "learning_rate": 6.671806016791337e-07,
2199
+ "loss": 0.0877,
2200
+ "step": 3130
2201
+ },
2202
+ {
2203
+ "epoch": 2.768959435626102,
2204
+ "grad_norm": 0.1503484462634625,
2205
+ "learning_rate": 6.192751213317261e-07,
2206
+ "loss": 0.0869,
2207
+ "step": 3140
2208
+ },
2209
+ {
2210
+ "epoch": 2.7777777777777777,
2211
+ "grad_norm": 0.15301298135075012,
2212
+ "learning_rate": 5.731271673498807e-07,
2213
+ "loss": 0.0876,
2214
+ "step": 3150
2215
+ },
2216
+ {
2217
+ "epoch": 2.7865961199294533,
2218
+ "grad_norm": 0.14946491260070807,
2219
+ "learning_rate": 5.287409246258724e-07,
2220
+ "loss": 0.0867,
2221
+ "step": 3160
2222
+ },
2223
+ {
2224
+ "epoch": 2.795414462081129,
2225
+ "grad_norm": 0.15544234491849743,
2226
+ "learning_rate": 4.861204182925238e-07,
2227
+ "loss": 0.0861,
2228
+ "step": 3170
2229
+ },
2230
+ {
2231
+ "epoch": 2.804232804232804,
2232
+ "grad_norm": 0.14786323558106976,
2233
+ "learning_rate": 4.452695133581908e-07,
2234
+ "loss": 0.0897,
2235
+ "step": 3180
2236
+ },
2237
+ {
2238
+ "epoch": 2.81305114638448,
2239
+ "grad_norm": 0.15035294545385944,
2240
+ "learning_rate": 4.0619191435626647e-07,
2241
+ "loss": 0.0898,
2242
+ "step": 3190
2243
+ },
2244
+ {
2245
+ "epoch": 2.821869488536155,
2246
+ "grad_norm": 0.14702281322330948,
2247
+ "learning_rate": 3.688911650092375e-07,
2248
+ "loss": 0.0892,
2249
+ "step": 3200
2250
+ },
2251
+ {
2252
+ "epoch": 2.8306878306878307,
2253
+ "grad_norm": 0.1490187614425559,
2254
+ "learning_rate": 3.333706479073229e-07,
2255
+ "loss": 0.0904,
2256
+ "step": 3210
2257
+ },
2258
+ {
2259
+ "epoch": 2.8395061728395063,
2260
+ "grad_norm": 0.14599915262723653,
2261
+ "learning_rate": 2.996335842017306e-07,
2262
+ "loss": 0.0915,
2263
+ "step": 3220
2264
+ },
2265
+ {
2266
+ "epoch": 2.8483245149911816,
2267
+ "grad_norm": 0.1472537352263344,
2268
+ "learning_rate": 2.676830333125424e-07,
2269
+ "loss": 0.089,
2270
+ "step": 3230
2271
+ },
2272
+ {
2273
+ "epoch": 2.857142857142857,
2274
+ "grad_norm": 0.1444247131200575,
2275
+ "learning_rate": 2.3752189265128234e-07,
2276
+ "loss": 0.0868,
2277
+ "step": 3240
2278
+ },
2279
+ {
2280
+ "epoch": 2.8659611992945324,
2281
+ "grad_norm": 0.15100512121725188,
2282
+ "learning_rate": 2.0915289735816247e-07,
2283
+ "loss": 0.0891,
2284
+ "step": 3250
2285
+ },
2286
+ {
2287
+ "epoch": 2.874779541446208,
2288
+ "grad_norm": 0.14909989384814895,
2289
+ "learning_rate": 1.8257862005404802e-07,
2290
+ "loss": 0.0898,
2291
+ "step": 3260
2292
+ },
2293
+ {
2294
+ "epoch": 2.8835978835978837,
2295
+ "grad_norm": 0.1501123498119351,
2296
+ "learning_rate": 1.5780147060715955e-07,
2297
+ "loss": 0.0877,
2298
+ "step": 3270
2299
+ },
2300
+ {
2301
+ "epoch": 2.892416225749559,
2302
+ "grad_norm": 0.14724312312335958,
2303
+ "learning_rate": 1.3482369591453882e-07,
2304
+ "loss": 0.0911,
2305
+ "step": 3280
2306
+ },
2307
+ {
2308
+ "epoch": 2.9012345679012346,
2309
+ "grad_norm": 0.14800693250740457,
2310
+ "learning_rate": 1.1364737969829176e-07,
2311
+ "loss": 0.0909,
2312
+ "step": 3290
2313
+ },
2314
+ {
2315
+ "epoch": 2.91005291005291,
2316
+ "grad_norm": 0.14676977153334295,
2317
+ "learning_rate": 9.427444231662863e-08,
2318
+ "loss": 0.0862,
2319
+ "step": 3300
2320
+ },
2321
+ {
2322
+ "epoch": 2.9188712522045854,
2323
+ "grad_norm": 0.14812710257168704,
2324
+ "learning_rate": 7.670664058970545e-08,
2325
+ "loss": 0.0875,
2326
+ "step": 3310
2327
+ },
2328
+ {
2329
+ "epoch": 2.927689594356261,
2330
+ "grad_norm": 0.1488187956001474,
2331
+ "learning_rate": 6.094556764032922e-08,
2332
+ "loss": 0.0886,
2333
+ "step": 3320
2334
+ },
2335
+ {
2336
+ "epoch": 2.9365079365079367,
2337
+ "grad_norm": 0.14589793378350213,
2338
+ "learning_rate": 4.699265274946907e-08,
2339
+ "loss": 0.0865,
2340
+ "step": 3330
2341
+ },
2342
+ {
2343
+ "epoch": 2.945326278659612,
2344
+ "grad_norm": 0.14997064517034403,
2345
+ "learning_rate": 3.484916122664883e-08,
2346
+ "loss": 0.0889,
2347
+ "step": 3340
2348
+ },
2349
+ {
2350
+ "epoch": 2.9541446208112876,
2351
+ "grad_norm": 0.14722441270349446,
2352
+ "learning_rate": 2.4516194295205466e-08,
2353
+ "loss": 0.0899,
2354
+ "step": 3350
2355
+ },
2356
+ {
2357
+ "epoch": 2.962962962962963,
2358
+ "grad_norm": 0.14896127171056997,
2359
+ "learning_rate": 1.5994688992424513e-08,
2360
+ "loss": 0.0895,
2361
+ "step": 3360
2362
+ },
2363
+ {
2364
+ "epoch": 2.9717813051146384,
2365
+ "grad_norm": 0.14761644929430634,
2366
+ "learning_rate": 9.285418084565845e-09,
2367
+ "loss": 0.0886,
2368
+ "step": 3370
2369
+ },
2370
+ {
2371
+ "epoch": 2.980599647266314,
2372
+ "grad_norm": 0.14489081475734752,
2373
+ "learning_rate": 4.3889899967797244e-09,
2374
+ "loss": 0.0886,
2375
+ "step": 3380
2376
+ },
2377
+ {
2378
+ "epoch": 2.9894179894179893,
2379
+ "grad_norm": 0.1482366815617573,
2380
+ "learning_rate": 1.3058487579420409e-09,
2381
+ "loss": 0.0888,
2382
+ "step": 3390
2383
+ },
2384
+ {
2385
+ "epoch": 2.998236331569665,
2386
+ "grad_norm": 0.15214422750713533,
2387
+ "learning_rate": 3.627396038208275e-11,
2388
+ "loss": 0.0869,
2389
+ "step": 3400
2390
+ },
2391
+ {
2392
+ "epoch": 3.0,
2393
+ "step": 3402,
2394
+ "total_flos": 7122048987955200.0,
2395
+ "train_loss": 0.13241534099762473,
2396
+ "train_runtime": 27380.0053,
2397
+ "train_samples_per_second": 19.876,
2398
+ "train_steps_per_second": 0.124
2399
+ }
2400
+ ],
2401
+ "logging_steps": 10,
2402
+ "max_steps": 3402,
2403
+ "num_input_tokens_seen": 0,
2404
+ "num_train_epochs": 3,
2405
+ "save_steps": 500,
2406
+ "stateful_callbacks": {
2407
+ "TrainerControl": {
2408
+ "args": {
2409
+ "should_epoch_stop": false,
2410
+ "should_evaluate": false,
2411
+ "should_log": false,
2412
+ "should_save": true,
2413
+ "should_training_stop": true
2414
+ },
2415
+ "attributes": {}
2416
+ }
2417
+ },
2418
+ "total_flos": 7122048987955200.0,
2419
+ "train_batch_size": 1,
2420
+ "trial_name": null,
2421
+ "trial_params": null
2422
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052cabaa13543e14d736d102fb95f10f59d675f74b59a6d3bc4bfee641b38202
3
+ size 7224
training_loss.png ADDED