ericflo commited on
Commit
9c83a25
1 Parent(s): 758c487

Training in progress, step 500, checkpoint

Browse files
checkpoint-500/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
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": 131072,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": {
23
+ "factor": 8.0,
24
+ "high_freq_factor": 4.0,
25
+ "low_freq_factor": 1.0,
26
+ "original_max_position_embeddings": 8192,
27
+ "rope_type": "llama3"
28
+ },
29
+ "rope_theta": 500000.0,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.44.2",
33
+ "use_cache": false,
34
+ "vocab_size": 128256
35
+ }
checkpoint-500/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.44.2"
9
+ }
checkpoint-500/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:696a83834835d9cfb4f3898af12f091ce41cb7bc917e533a94e15a6954269e6d
3
+ size 4976698672
checkpoint-500/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe0cab6eb04fbe360da573438be40528ba1f6d7824e346c0f4b4d8e7d59f9459
3
+ size 4999802720
checkpoint-500/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84848938d824dca98e68aaedc9b8dc89d706456e6fa48a1c0d32848011e6b486
3
+ size 4915916176
checkpoint-500/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46e78c16db1d430a38b2b1b23f07d75705a2c998e0f7efdcd1ae76f75195b06e
3
+ size 1168138808
checkpoint-500/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
+ }
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:073a9c27f5c1d1ef20f691d852d4d673177845f21060f8530b36e46de97f4d91
3
+ size 16092243016
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:983a4ca70134caca3d448a5d4ad8b72b0baaf98bc1854382ca50fb8e85b6f5b7
3
+ size 14308
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0646dd0ba316f9b16196fbc6de365ed95580f96de0138a012392a2f7e7a83578
3
+ size 1064
checkpoint-500/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
+ }
checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 131072,
2060
+ "pad_token": "<|end_of_text|>",
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,3533 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.005,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1e-05,
13
+ "grad_norm": 8.875,
14
+ "learning_rate": 9.999999997532599e-06,
15
+ "loss": 1.6459,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 2e-05,
20
+ "grad_norm": 4.40625,
21
+ "learning_rate": 9.999999990130395e-06,
22
+ "loss": 1.6742,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 3e-05,
27
+ "grad_norm": 4.3125,
28
+ "learning_rate": 9.99999997779339e-06,
29
+ "loss": 1.6223,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 4e-05,
34
+ "grad_norm": 4.0625,
35
+ "learning_rate": 9.999999960521582e-06,
36
+ "loss": 1.5398,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 5e-05,
41
+ "grad_norm": 3.375,
42
+ "learning_rate": 9.999999938314972e-06,
43
+ "loss": 1.5666,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 6e-05,
48
+ "grad_norm": 1.859375,
49
+ "learning_rate": 9.999999911173561e-06,
50
+ "loss": 1.5981,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 7e-05,
55
+ "grad_norm": 1.734375,
56
+ "learning_rate": 9.999999879097347e-06,
57
+ "loss": 1.644,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 8e-05,
62
+ "grad_norm": 1.796875,
63
+ "learning_rate": 9.999999842086332e-06,
64
+ "loss": 1.6331,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 9e-05,
69
+ "grad_norm": 1.3125,
70
+ "learning_rate": 9.999999800140514e-06,
71
+ "loss": 1.626,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.0001,
76
+ "grad_norm": 1.9296875,
77
+ "learning_rate": 9.999999753259893e-06,
78
+ "loss": 1.5778,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.00011,
83
+ "grad_norm": 1.34375,
84
+ "learning_rate": 9.99999970144447e-06,
85
+ "loss": 1.6286,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.00012,
90
+ "grad_norm": 1.203125,
91
+ "learning_rate": 9.999999644694247e-06,
92
+ "loss": 1.5614,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.00013,
97
+ "grad_norm": 1.015625,
98
+ "learning_rate": 9.999999583009221e-06,
99
+ "loss": 1.6447,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.00014,
104
+ "grad_norm": 1.3359375,
105
+ "learning_rate": 9.999999516389394e-06,
106
+ "loss": 1.5258,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.00015,
111
+ "grad_norm": 1.25,
112
+ "learning_rate": 9.999999444834763e-06,
113
+ "loss": 1.6336,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.00016,
118
+ "grad_norm": 1.5546875,
119
+ "learning_rate": 9.999999368345333e-06,
120
+ "loss": 1.6073,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.00017,
125
+ "grad_norm": 1.34375,
126
+ "learning_rate": 9.999999286921101e-06,
127
+ "loss": 1.5919,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.00018,
132
+ "grad_norm": 0.96875,
133
+ "learning_rate": 9.999999200562065e-06,
134
+ "loss": 1.543,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.00019,
139
+ "grad_norm": 1.6875,
140
+ "learning_rate": 9.99999910926823e-06,
141
+ "loss": 1.6101,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.0002,
146
+ "grad_norm": 1.578125,
147
+ "learning_rate": 9.999999013039593e-06,
148
+ "loss": 1.5796,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.00021,
153
+ "grad_norm": 2.578125,
154
+ "learning_rate": 9.999998911876154e-06,
155
+ "loss": 1.5748,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.00022,
160
+ "grad_norm": 1.203125,
161
+ "learning_rate": 9.999998805777915e-06,
162
+ "loss": 1.5479,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.00023,
167
+ "grad_norm": 1.4921875,
168
+ "learning_rate": 9.999998694744875e-06,
169
+ "loss": 1.5318,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.00024,
174
+ "grad_norm": 1.125,
175
+ "learning_rate": 9.999998578777036e-06,
176
+ "loss": 1.6259,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.00025,
181
+ "grad_norm": 2.21875,
182
+ "learning_rate": 9.999998457874392e-06,
183
+ "loss": 1.5525,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.00026,
188
+ "grad_norm": 3.234375,
189
+ "learning_rate": 9.99999833203695e-06,
190
+ "loss": 1.5576,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.00027,
195
+ "grad_norm": 2.046875,
196
+ "learning_rate": 9.999998201264707e-06,
197
+ "loss": 1.3934,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.00028,
202
+ "grad_norm": 3.15625,
203
+ "learning_rate": 9.999998065557664e-06,
204
+ "loss": 1.5423,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.00029,
209
+ "grad_norm": 1.2734375,
210
+ "learning_rate": 9.999997924915818e-06,
211
+ "loss": 1.5679,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.0003,
216
+ "grad_norm": 1.625,
217
+ "learning_rate": 9.999997779339175e-06,
218
+ "loss": 1.5329,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.00031,
223
+ "grad_norm": 1.2421875,
224
+ "learning_rate": 9.999997628827732e-06,
225
+ "loss": 1.4603,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.00032,
230
+ "grad_norm": 1.46875,
231
+ "learning_rate": 9.999997473381487e-06,
232
+ "loss": 1.5774,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.00033,
237
+ "grad_norm": 2.0625,
238
+ "learning_rate": 9.999997313000444e-06,
239
+ "loss": 1.5522,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.00034,
244
+ "grad_norm": 1.421875,
245
+ "learning_rate": 9.9999971476846e-06,
246
+ "loss": 1.5964,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.00035,
251
+ "grad_norm": 1.59375,
252
+ "learning_rate": 9.999996977433957e-06,
253
+ "loss": 1.6129,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.00036,
258
+ "grad_norm": 1.78125,
259
+ "learning_rate": 9.999996802248514e-06,
260
+ "loss": 1.548,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.00037,
265
+ "grad_norm": 0.94140625,
266
+ "learning_rate": 9.999996622128274e-06,
267
+ "loss": 1.5662,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.00038,
272
+ "grad_norm": 4.84375,
273
+ "learning_rate": 9.999996437073236e-06,
274
+ "loss": 1.6197,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.00039,
279
+ "grad_norm": 3.234375,
280
+ "learning_rate": 9.999996247083397e-06,
281
+ "loss": 1.5308,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.0004,
286
+ "grad_norm": 1.375,
287
+ "learning_rate": 9.99999605215876e-06,
288
+ "loss": 1.5846,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.00041,
293
+ "grad_norm": 1.34375,
294
+ "learning_rate": 9.999995852299324e-06,
295
+ "loss": 1.4274,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.00042,
300
+ "grad_norm": 1.15625,
301
+ "learning_rate": 9.999995647505092e-06,
302
+ "loss": 1.4986,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.00043,
307
+ "grad_norm": 0.94140625,
308
+ "learning_rate": 9.99999543777606e-06,
309
+ "loss": 1.5135,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.00044,
314
+ "grad_norm": 0.8125,
315
+ "learning_rate": 9.999995223112231e-06,
316
+ "loss": 1.5472,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.00045,
321
+ "grad_norm": 1.5703125,
322
+ "learning_rate": 9.999995003513605e-06,
323
+ "loss": 1.5635,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.00046,
328
+ "grad_norm": 3.34375,
329
+ "learning_rate": 9.999994778980182e-06,
330
+ "loss": 1.5506,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.00047,
335
+ "grad_norm": 5.4375,
336
+ "learning_rate": 9.99999454951196e-06,
337
+ "loss": 1.5071,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.00048,
342
+ "grad_norm": 1.578125,
343
+ "learning_rate": 9.999994315108943e-06,
344
+ "loss": 1.5532,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.00049,
349
+ "grad_norm": 1.828125,
350
+ "learning_rate": 9.999994075771128e-06,
351
+ "loss": 1.6061,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.0005,
356
+ "grad_norm": 1.4453125,
357
+ "learning_rate": 9.999993831498517e-06,
358
+ "loss": 1.5629,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.00051,
363
+ "grad_norm": 1.109375,
364
+ "learning_rate": 9.999993582291112e-06,
365
+ "loss": 1.5536,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.00052,
370
+ "grad_norm": 1.0078125,
371
+ "learning_rate": 9.999993328148909e-06,
372
+ "loss": 1.5013,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.00053,
377
+ "grad_norm": 1.171875,
378
+ "learning_rate": 9.999993069071912e-06,
379
+ "loss": 1.4943,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.00054,
384
+ "grad_norm": 1.8203125,
385
+ "learning_rate": 9.999992805060117e-06,
386
+ "loss": 1.5057,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.00055,
391
+ "grad_norm": 0.97265625,
392
+ "learning_rate": 9.99999253611353e-06,
393
+ "loss": 1.6486,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.00056,
398
+ "grad_norm": 3.765625,
399
+ "learning_rate": 9.999992262232145e-06,
400
+ "loss": 1.4421,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.00057,
405
+ "grad_norm": 2.21875,
406
+ "learning_rate": 9.999991983415968e-06,
407
+ "loss": 1.5346,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.00058,
412
+ "grad_norm": 0.953125,
413
+ "learning_rate": 9.999991699664996e-06,
414
+ "loss": 1.5433,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.00059,
419
+ "grad_norm": 3.171875,
420
+ "learning_rate": 9.99999141097923e-06,
421
+ "loss": 1.5306,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.0006,
426
+ "grad_norm": 1.0546875,
427
+ "learning_rate": 9.99999111735867e-06,
428
+ "loss": 1.4453,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.00061,
433
+ "grad_norm": 0.796875,
434
+ "learning_rate": 9.999990818803316e-06,
435
+ "loss": 1.6219,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.00062,
440
+ "grad_norm": 1.078125,
441
+ "learning_rate": 9.99999051531317e-06,
442
+ "loss": 1.5296,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.00063,
447
+ "grad_norm": 1.2109375,
448
+ "learning_rate": 9.999990206888231e-06,
449
+ "loss": 1.5165,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.00064,
454
+ "grad_norm": 1.0234375,
455
+ "learning_rate": 9.999989893528499e-06,
456
+ "loss": 1.5697,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.00065,
461
+ "grad_norm": 3.0625,
462
+ "learning_rate": 9.999989575233975e-06,
463
+ "loss": 1.5121,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.00066,
468
+ "grad_norm": 0.9296875,
469
+ "learning_rate": 9.999989252004657e-06,
470
+ "loss": 1.4815,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.00067,
475
+ "grad_norm": 1.53125,
476
+ "learning_rate": 9.999988923840551e-06,
477
+ "loss": 1.4624,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.00068,
482
+ "grad_norm": 0.80859375,
483
+ "learning_rate": 9.999988590741651e-06,
484
+ "loss": 1.5089,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.00069,
489
+ "grad_norm": 1.4453125,
490
+ "learning_rate": 9.999988252707961e-06,
491
+ "loss": 1.4864,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.0007,
496
+ "grad_norm": 2.328125,
497
+ "learning_rate": 9.999987909739481e-06,
498
+ "loss": 1.5284,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.00071,
503
+ "grad_norm": 1.4296875,
504
+ "learning_rate": 9.99998756183621e-06,
505
+ "loss": 1.4759,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.00072,
510
+ "grad_norm": 1.2890625,
511
+ "learning_rate": 9.999987208998151e-06,
512
+ "loss": 1.5659,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.00073,
517
+ "grad_norm": 3.1875,
518
+ "learning_rate": 9.9999868512253e-06,
519
+ "loss": 1.6112,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.00074,
524
+ "grad_norm": 1.09375,
525
+ "learning_rate": 9.999986488517661e-06,
526
+ "loss": 1.503,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.00075,
531
+ "grad_norm": 0.80078125,
532
+ "learning_rate": 9.999986120875233e-06,
533
+ "loss": 1.4688,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.00076,
538
+ "grad_norm": 2.09375,
539
+ "learning_rate": 9.999985748298016e-06,
540
+ "loss": 1.543,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.00077,
545
+ "grad_norm": 0.89453125,
546
+ "learning_rate": 9.999985370786011e-06,
547
+ "loss": 1.5166,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.00078,
552
+ "grad_norm": 1.859375,
553
+ "learning_rate": 9.999984988339219e-06,
554
+ "loss": 1.5451,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.00079,
559
+ "grad_norm": 1.6640625,
560
+ "learning_rate": 9.999984600957639e-06,
561
+ "loss": 1.5026,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.0008,
566
+ "grad_norm": 1.5234375,
567
+ "learning_rate": 9.999984208641271e-06,
568
+ "loss": 1.4629,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.00081,
573
+ "grad_norm": 1.0,
574
+ "learning_rate": 9.999983811390117e-06,
575
+ "loss": 1.5866,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.00082,
580
+ "grad_norm": 1.2734375,
581
+ "learning_rate": 9.999983409204178e-06,
582
+ "loss": 1.4361,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.00083,
587
+ "grad_norm": 1.9609375,
588
+ "learning_rate": 9.999983002083451e-06,
589
+ "loss": 1.5498,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.00084,
594
+ "grad_norm": 3.125,
595
+ "learning_rate": 9.999982590027942e-06,
596
+ "loss": 1.5787,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.00085,
601
+ "grad_norm": 0.9453125,
602
+ "learning_rate": 9.999982173037645e-06,
603
+ "loss": 1.5674,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.00086,
608
+ "grad_norm": 0.91015625,
609
+ "learning_rate": 9.999981751112563e-06,
610
+ "loss": 1.5676,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.00087,
615
+ "grad_norm": 1.3203125,
616
+ "learning_rate": 9.999981324252698e-06,
617
+ "loss": 1.5031,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.00088,
622
+ "grad_norm": 1.40625,
623
+ "learning_rate": 9.99998089245805e-06,
624
+ "loss": 1.5127,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.00089,
629
+ "grad_norm": 0.92578125,
630
+ "learning_rate": 9.999980455728618e-06,
631
+ "loss": 1.5867,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.0009,
636
+ "grad_norm": 1.0078125,
637
+ "learning_rate": 9.999980014064404e-06,
638
+ "loss": 1.4413,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.00091,
643
+ "grad_norm": 0.93359375,
644
+ "learning_rate": 9.999979567465405e-06,
645
+ "loss": 1.3676,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.00092,
650
+ "grad_norm": 0.9609375,
651
+ "learning_rate": 9.999979115931626e-06,
652
+ "loss": 1.5553,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.00093,
657
+ "grad_norm": 0.75,
658
+ "learning_rate": 9.999978659463065e-06,
659
+ "loss": 1.4763,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.00094,
664
+ "grad_norm": 0.6796875,
665
+ "learning_rate": 9.999978198059722e-06,
666
+ "loss": 1.4483,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.00095,
671
+ "grad_norm": 0.8046875,
672
+ "learning_rate": 9.9999777317216e-06,
673
+ "loss": 1.5449,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.00096,
678
+ "grad_norm": 1.0859375,
679
+ "learning_rate": 9.999977260448697e-06,
680
+ "loss": 1.4965,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.00097,
685
+ "grad_norm": 1.0,
686
+ "learning_rate": 9.999976784241014e-06,
687
+ "loss": 1.596,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.00098,
692
+ "grad_norm": 0.94921875,
693
+ "learning_rate": 9.999976303098552e-06,
694
+ "loss": 1.5585,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.00099,
699
+ "grad_norm": 0.921875,
700
+ "learning_rate": 9.99997581702131e-06,
701
+ "loss": 1.501,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.001,
706
+ "grad_norm": 1.8984375,
707
+ "learning_rate": 9.999975326009292e-06,
708
+ "loss": 1.4553,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.00101,
713
+ "grad_norm": 0.7890625,
714
+ "learning_rate": 9.999974830062494e-06,
715
+ "loss": 1.5695,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.00102,
720
+ "grad_norm": 0.73046875,
721
+ "learning_rate": 9.99997432918092e-06,
722
+ "loss": 1.4606,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.00103,
727
+ "grad_norm": 0.98828125,
728
+ "learning_rate": 9.999973823364568e-06,
729
+ "loss": 1.5428,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.00104,
734
+ "grad_norm": 0.90234375,
735
+ "learning_rate": 9.99997331261344e-06,
736
+ "loss": 1.5081,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.00105,
741
+ "grad_norm": 1.875,
742
+ "learning_rate": 9.999972796927537e-06,
743
+ "loss": 1.5,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.00106,
748
+ "grad_norm": 0.95703125,
749
+ "learning_rate": 9.999972276306858e-06,
750
+ "loss": 1.5322,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.00107,
755
+ "grad_norm": 1.6015625,
756
+ "learning_rate": 9.999971750751405e-06,
757
+ "loss": 1.5786,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.00108,
762
+ "grad_norm": 1.4375,
763
+ "learning_rate": 9.999971220261177e-06,
764
+ "loss": 1.4891,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.00109,
769
+ "grad_norm": 1.34375,
770
+ "learning_rate": 9.999970684836174e-06,
771
+ "loss": 1.4762,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.0011,
776
+ "grad_norm": 0.80078125,
777
+ "learning_rate": 9.9999701444764e-06,
778
+ "loss": 1.5361,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.00111,
783
+ "grad_norm": 0.88671875,
784
+ "learning_rate": 9.999969599181852e-06,
785
+ "loss": 1.4876,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.00112,
790
+ "grad_norm": 0.80078125,
791
+ "learning_rate": 9.999969048952532e-06,
792
+ "loss": 1.4864,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.00113,
797
+ "grad_norm": 0.875,
798
+ "learning_rate": 9.99996849378844e-06,
799
+ "loss": 1.5043,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.00114,
804
+ "grad_norm": 0.8515625,
805
+ "learning_rate": 9.999967933689577e-06,
806
+ "loss": 1.4646,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.00115,
811
+ "grad_norm": 0.83203125,
812
+ "learning_rate": 9.999967368655942e-06,
813
+ "loss": 1.5111,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.00116,
818
+ "grad_norm": 1.125,
819
+ "learning_rate": 9.99996679868754e-06,
820
+ "loss": 1.4959,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.00117,
825
+ "grad_norm": 0.8984375,
826
+ "learning_rate": 9.999966223784368e-06,
827
+ "loss": 1.5595,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.00118,
832
+ "grad_norm": 3.703125,
833
+ "learning_rate": 9.999965643946425e-06,
834
+ "loss": 1.1576,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.00119,
839
+ "grad_norm": 0.96484375,
840
+ "learning_rate": 9.999965059173715e-06,
841
+ "loss": 1.5184,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.0012,
846
+ "grad_norm": 0.96484375,
847
+ "learning_rate": 9.999964469466236e-06,
848
+ "loss": 1.4559,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.00121,
853
+ "grad_norm": 1.03125,
854
+ "learning_rate": 9.999963874823993e-06,
855
+ "loss": 1.5143,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.00122,
860
+ "grad_norm": 0.6640625,
861
+ "learning_rate": 9.999963275246983e-06,
862
+ "loss": 1.5526,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.00123,
867
+ "grad_norm": 0.6640625,
868
+ "learning_rate": 9.999962670735205e-06,
869
+ "loss": 1.5328,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.00124,
874
+ "grad_norm": 0.65625,
875
+ "learning_rate": 9.999962061288662e-06,
876
+ "loss": 1.5333,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.00125,
881
+ "grad_norm": 0.69140625,
882
+ "learning_rate": 9.999961446907354e-06,
883
+ "loss": 1.5423,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.00126,
888
+ "grad_norm": 0.69140625,
889
+ "learning_rate": 9.999960827591283e-06,
890
+ "loss": 1.5687,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.00127,
895
+ "grad_norm": 0.671875,
896
+ "learning_rate": 9.999960203340447e-06,
897
+ "loss": 1.5186,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.00128,
902
+ "grad_norm": 0.609375,
903
+ "learning_rate": 9.99995957415485e-06,
904
+ "loss": 1.5319,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.00129,
909
+ "grad_norm": 0.6484375,
910
+ "learning_rate": 9.99995894003449e-06,
911
+ "loss": 1.4797,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.0013,
916
+ "grad_norm": 0.734375,
917
+ "learning_rate": 9.999958300979367e-06,
918
+ "loss": 1.5232,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.00131,
923
+ "grad_norm": 0.6953125,
924
+ "learning_rate": 9.999957656989482e-06,
925
+ "loss": 1.4463,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.00132,
930
+ "grad_norm": 0.65234375,
931
+ "learning_rate": 9.99995700806484e-06,
932
+ "loss": 1.4935,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.00133,
937
+ "grad_norm": 0.6484375,
938
+ "learning_rate": 9.999956354205437e-06,
939
+ "loss": 1.6034,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.00134,
944
+ "grad_norm": 0.6171875,
945
+ "learning_rate": 9.999955695411274e-06,
946
+ "loss": 1.5081,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.00135,
951
+ "grad_norm": 0.6640625,
952
+ "learning_rate": 9.999955031682354e-06,
953
+ "loss": 1.4503,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.00136,
958
+ "grad_norm": 0.5625,
959
+ "learning_rate": 9.999954363018675e-06,
960
+ "loss": 1.3321,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.00137,
965
+ "grad_norm": 0.83203125,
966
+ "learning_rate": 9.999953689420238e-06,
967
+ "loss": 1.5462,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.00138,
972
+ "grad_norm": 0.70703125,
973
+ "learning_rate": 9.999953010887047e-06,
974
+ "loss": 1.5052,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.00139,
979
+ "grad_norm": 0.609375,
980
+ "learning_rate": 9.999952327419098e-06,
981
+ "loss": 1.3766,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.0014,
986
+ "grad_norm": 0.66796875,
987
+ "learning_rate": 9.999951639016396e-06,
988
+ "loss": 1.6074,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.00141,
993
+ "grad_norm": 0.75390625,
994
+ "learning_rate": 9.999950945678939e-06,
995
+ "loss": 1.5381,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.00142,
1000
+ "grad_norm": 0.61328125,
1001
+ "learning_rate": 9.999950247406725e-06,
1002
+ "loss": 1.5463,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.00143,
1007
+ "grad_norm": 0.625,
1008
+ "learning_rate": 9.99994954419976e-06,
1009
+ "loss": 1.5013,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.00144,
1014
+ "grad_norm": 0.61328125,
1015
+ "learning_rate": 9.999948836058045e-06,
1016
+ "loss": 1.4789,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.00145,
1021
+ "grad_norm": 0.6171875,
1022
+ "learning_rate": 9.999948122981576e-06,
1023
+ "loss": 1.4872,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.00146,
1028
+ "grad_norm": 0.609375,
1029
+ "learning_rate": 9.999947404970356e-06,
1030
+ "loss": 1.5426,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.00147,
1035
+ "grad_norm": 0.68359375,
1036
+ "learning_rate": 9.999946682024386e-06,
1037
+ "loss": 1.5073,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.00148,
1042
+ "grad_norm": 0.6015625,
1043
+ "learning_rate": 9.999945954143665e-06,
1044
+ "loss": 1.5537,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.00149,
1049
+ "grad_norm": 0.89453125,
1050
+ "learning_rate": 9.999945221328198e-06,
1051
+ "loss": 1.5759,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.0015,
1056
+ "grad_norm": 0.61328125,
1057
+ "learning_rate": 9.999944483577982e-06,
1058
+ "loss": 1.5019,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.00151,
1063
+ "grad_norm": 0.609375,
1064
+ "learning_rate": 9.999943740893017e-06,
1065
+ "loss": 1.4706,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.00152,
1070
+ "grad_norm": 0.7109375,
1071
+ "learning_rate": 9.999942993273306e-06,
1072
+ "loss": 1.5303,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.00153,
1077
+ "grad_norm": 0.61328125,
1078
+ "learning_rate": 9.99994224071885e-06,
1079
+ "loss": 1.5028,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.00154,
1084
+ "grad_norm": 0.6171875,
1085
+ "learning_rate": 9.999941483229646e-06,
1086
+ "loss": 1.5878,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.00155,
1091
+ "grad_norm": 0.609375,
1092
+ "learning_rate": 9.9999407208057e-06,
1093
+ "loss": 1.4271,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.00156,
1098
+ "grad_norm": 0.6015625,
1099
+ "learning_rate": 9.999939953447012e-06,
1100
+ "loss": 1.4115,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.00157,
1105
+ "grad_norm": 0.63671875,
1106
+ "learning_rate": 9.999939181153578e-06,
1107
+ "loss": 1.5243,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.00158,
1112
+ "grad_norm": 0.58984375,
1113
+ "learning_rate": 9.999938403925404e-06,
1114
+ "loss": 1.4749,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.00159,
1119
+ "grad_norm": 0.6015625,
1120
+ "learning_rate": 9.999937621762487e-06,
1121
+ "loss": 1.5109,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.0016,
1126
+ "grad_norm": 0.6015625,
1127
+ "learning_rate": 9.99993683466483e-06,
1128
+ "loss": 1.5235,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.00161,
1133
+ "grad_norm": 0.6328125,
1134
+ "learning_rate": 9.999936042632433e-06,
1135
+ "loss": 1.5407,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.00162,
1140
+ "grad_norm": 0.55859375,
1141
+ "learning_rate": 9.999935245665296e-06,
1142
+ "loss": 1.4664,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.00163,
1147
+ "grad_norm": 0.59375,
1148
+ "learning_rate": 9.999934443763421e-06,
1149
+ "loss": 1.6013,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.00164,
1154
+ "grad_norm": 0.60546875,
1155
+ "learning_rate": 9.99993363692681e-06,
1156
+ "loss": 1.5297,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.00165,
1161
+ "grad_norm": 0.625,
1162
+ "learning_rate": 9.999932825155462e-06,
1163
+ "loss": 1.5636,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.00166,
1168
+ "grad_norm": 0.5703125,
1169
+ "learning_rate": 9.999932008449377e-06,
1170
+ "loss": 1.4603,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.00167,
1175
+ "grad_norm": 0.59765625,
1176
+ "learning_rate": 9.999931186808558e-06,
1177
+ "loss": 1.5884,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.00168,
1182
+ "grad_norm": 0.60546875,
1183
+ "learning_rate": 9.999930360233003e-06,
1184
+ "loss": 1.4181,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.00169,
1189
+ "grad_norm": 0.85546875,
1190
+ "learning_rate": 9.999929528722716e-06,
1191
+ "loss": 1.4743,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.0017,
1196
+ "grad_norm": 0.62109375,
1197
+ "learning_rate": 9.999928692277696e-06,
1198
+ "loss": 1.6229,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.00171,
1203
+ "grad_norm": 0.64453125,
1204
+ "learning_rate": 9.999927850897944e-06,
1205
+ "loss": 1.5356,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.00172,
1210
+ "grad_norm": 0.59765625,
1211
+ "learning_rate": 9.999927004583462e-06,
1212
+ "loss": 1.5382,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.00173,
1217
+ "grad_norm": 0.78125,
1218
+ "learning_rate": 9.99992615333425e-06,
1219
+ "loss": 1.5174,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.00174,
1224
+ "grad_norm": 0.64453125,
1225
+ "learning_rate": 9.999925297150307e-06,
1226
+ "loss": 1.4997,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.00175,
1231
+ "grad_norm": 0.625,
1232
+ "learning_rate": 9.999924436031636e-06,
1233
+ "loss": 1.4769,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.00176,
1238
+ "grad_norm": 0.60546875,
1239
+ "learning_rate": 9.999923569978238e-06,
1240
+ "loss": 1.517,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.00177,
1245
+ "grad_norm": 0.6328125,
1246
+ "learning_rate": 9.999922698990112e-06,
1247
+ "loss": 1.5596,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.00178,
1252
+ "grad_norm": 0.62890625,
1253
+ "learning_rate": 9.999921823067263e-06,
1254
+ "loss": 1.5257,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.00179,
1259
+ "grad_norm": 0.7421875,
1260
+ "learning_rate": 9.999920942209686e-06,
1261
+ "loss": 1.4666,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.0018,
1266
+ "grad_norm": 0.6171875,
1267
+ "learning_rate": 9.999920056417385e-06,
1268
+ "loss": 1.493,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.00181,
1273
+ "grad_norm": 0.62109375,
1274
+ "learning_rate": 9.999919165690362e-06,
1275
+ "loss": 1.5201,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.00182,
1280
+ "grad_norm": 0.62109375,
1281
+ "learning_rate": 9.999918270028616e-06,
1282
+ "loss": 1.5152,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.00183,
1287
+ "grad_norm": 0.59765625,
1288
+ "learning_rate": 9.999917369432148e-06,
1289
+ "loss": 1.5456,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.00184,
1294
+ "grad_norm": 0.58984375,
1295
+ "learning_rate": 9.999916463900961e-06,
1296
+ "loss": 1.5257,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.00185,
1301
+ "grad_norm": 0.5859375,
1302
+ "learning_rate": 9.999915553435053e-06,
1303
+ "loss": 1.3887,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.00186,
1308
+ "grad_norm": 0.65234375,
1309
+ "learning_rate": 9.999914638034426e-06,
1310
+ "loss": 1.5393,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.00187,
1315
+ "grad_norm": 0.64453125,
1316
+ "learning_rate": 9.999913717699081e-06,
1317
+ "loss": 1.5807,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.00188,
1322
+ "grad_norm": 0.63671875,
1323
+ "learning_rate": 9.99991279242902e-06,
1324
+ "loss": 1.5917,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.00189,
1329
+ "grad_norm": 0.59765625,
1330
+ "learning_rate": 9.999911862224242e-06,
1331
+ "loss": 1.4811,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.0019,
1336
+ "grad_norm": 0.6484375,
1337
+ "learning_rate": 9.999910927084748e-06,
1338
+ "loss": 1.5421,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.00191,
1343
+ "grad_norm": 0.59765625,
1344
+ "learning_rate": 9.999909987010541e-06,
1345
+ "loss": 1.5756,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.00192,
1350
+ "grad_norm": 0.58203125,
1351
+ "learning_rate": 9.999909042001621e-06,
1352
+ "loss": 1.4599,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.00193,
1357
+ "grad_norm": 0.6015625,
1358
+ "learning_rate": 9.999908092057988e-06,
1359
+ "loss": 1.4314,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.00194,
1364
+ "grad_norm": 0.58203125,
1365
+ "learning_rate": 9.999907137179644e-06,
1366
+ "loss": 1.5985,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.00195,
1371
+ "grad_norm": 0.6875,
1372
+ "learning_rate": 9.999906177366587e-06,
1373
+ "loss": 1.5923,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.00196,
1378
+ "grad_norm": 0.640625,
1379
+ "learning_rate": 9.999905212618822e-06,
1380
+ "loss": 1.5388,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.00197,
1385
+ "grad_norm": 0.55078125,
1386
+ "learning_rate": 9.999904242936349e-06,
1387
+ "loss": 1.313,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.00198,
1392
+ "grad_norm": 0.60546875,
1393
+ "learning_rate": 9.999903268319167e-06,
1394
+ "loss": 1.5182,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.00199,
1399
+ "grad_norm": 0.60546875,
1400
+ "learning_rate": 9.99990228876728e-06,
1401
+ "loss": 1.4396,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.002,
1406
+ "grad_norm": 0.68359375,
1407
+ "learning_rate": 9.999901304280686e-06,
1408
+ "loss": 1.489,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.00201,
1413
+ "grad_norm": 0.58984375,
1414
+ "learning_rate": 9.999900314859388e-06,
1415
+ "loss": 1.4867,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.00202,
1420
+ "grad_norm": 0.5859375,
1421
+ "learning_rate": 9.999899320503386e-06,
1422
+ "loss": 1.5109,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.00203,
1427
+ "grad_norm": 0.578125,
1428
+ "learning_rate": 9.999898321212681e-06,
1429
+ "loss": 1.5289,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.00204,
1434
+ "grad_norm": 0.5859375,
1435
+ "learning_rate": 9.999897316987273e-06,
1436
+ "loss": 1.4972,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.00205,
1441
+ "grad_norm": 0.58203125,
1442
+ "learning_rate": 9.999896307827167e-06,
1443
+ "loss": 1.4926,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.00206,
1448
+ "grad_norm": 0.61328125,
1449
+ "learning_rate": 9.999895293732358e-06,
1450
+ "loss": 1.5496,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.00207,
1455
+ "grad_norm": 0.57421875,
1456
+ "learning_rate": 9.999894274702853e-06,
1457
+ "loss": 1.4316,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.00208,
1462
+ "grad_norm": 2.953125,
1463
+ "learning_rate": 9.999893250738649e-06,
1464
+ "loss": 1.5131,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.00209,
1469
+ "grad_norm": 0.59765625,
1470
+ "learning_rate": 9.999892221839747e-06,
1471
+ "loss": 1.4639,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.0021,
1476
+ "grad_norm": 0.58984375,
1477
+ "learning_rate": 9.99989118800615e-06,
1478
+ "loss": 1.5029,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.00211,
1483
+ "grad_norm": 0.6015625,
1484
+ "learning_rate": 9.999890149237857e-06,
1485
+ "loss": 1.5104,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.00212,
1490
+ "grad_norm": 0.61328125,
1491
+ "learning_rate": 9.999889105534873e-06,
1492
+ "loss": 1.5475,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.00213,
1497
+ "grad_norm": 0.59375,
1498
+ "learning_rate": 9.999888056897193e-06,
1499
+ "loss": 1.4491,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.00214,
1504
+ "grad_norm": 0.609375,
1505
+ "learning_rate": 9.999887003324825e-06,
1506
+ "loss": 1.5361,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.00215,
1511
+ "grad_norm": 0.60546875,
1512
+ "learning_rate": 9.999885944817762e-06,
1513
+ "loss": 1.5162,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.00216,
1518
+ "grad_norm": 0.61328125,
1519
+ "learning_rate": 9.999884881376012e-06,
1520
+ "loss": 1.5086,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.00217,
1525
+ "grad_norm": 0.61328125,
1526
+ "learning_rate": 9.999883812999574e-06,
1527
+ "loss": 1.4937,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.00218,
1532
+ "grad_norm": 0.609375,
1533
+ "learning_rate": 9.999882739688446e-06,
1534
+ "loss": 1.5327,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.00219,
1539
+ "grad_norm": 0.5859375,
1540
+ "learning_rate": 9.999881661442635e-06,
1541
+ "loss": 1.4829,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.0022,
1546
+ "grad_norm": 0.59765625,
1547
+ "learning_rate": 9.999880578262135e-06,
1548
+ "loss": 1.4377,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.00221,
1553
+ "grad_norm": 0.5703125,
1554
+ "learning_rate": 9.999879490146953e-06,
1555
+ "loss": 1.4425,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.00222,
1560
+ "grad_norm": 0.64453125,
1561
+ "learning_rate": 9.999878397097086e-06,
1562
+ "loss": 1.5688,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.00223,
1567
+ "grad_norm": 0.6875,
1568
+ "learning_rate": 9.999877299112539e-06,
1569
+ "loss": 1.4533,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.00224,
1574
+ "grad_norm": 0.59765625,
1575
+ "learning_rate": 9.99987619619331e-06,
1576
+ "loss": 1.5631,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.00225,
1581
+ "grad_norm": 0.58984375,
1582
+ "learning_rate": 9.999875088339401e-06,
1583
+ "loss": 1.451,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.00226,
1588
+ "grad_norm": 0.6015625,
1589
+ "learning_rate": 9.999873975550812e-06,
1590
+ "loss": 1.4725,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.00227,
1595
+ "grad_norm": 0.58984375,
1596
+ "learning_rate": 9.999872857827546e-06,
1597
+ "loss": 1.5389,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.00228,
1602
+ "grad_norm": 0.65625,
1603
+ "learning_rate": 9.999871735169603e-06,
1604
+ "loss": 1.5243,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.00229,
1609
+ "grad_norm": 0.59765625,
1610
+ "learning_rate": 9.999870607576984e-06,
1611
+ "loss": 1.5612,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.0023,
1616
+ "grad_norm": 0.59375,
1617
+ "learning_rate": 9.999869475049693e-06,
1618
+ "loss": 1.5469,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.00231,
1623
+ "grad_norm": 0.5625,
1624
+ "learning_rate": 9.999868337587725e-06,
1625
+ "loss": 1.3031,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.00232,
1630
+ "grad_norm": 0.5625,
1631
+ "learning_rate": 9.99986719519109e-06,
1632
+ "loss": 1.4403,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.00233,
1637
+ "grad_norm": 0.57421875,
1638
+ "learning_rate": 9.999866047859778e-06,
1639
+ "loss": 1.438,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.00234,
1644
+ "grad_norm": 0.60546875,
1645
+ "learning_rate": 9.999864895593799e-06,
1646
+ "loss": 1.4921,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.00235,
1651
+ "grad_norm": 0.5625,
1652
+ "learning_rate": 9.99986373839315e-06,
1653
+ "loss": 1.456,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.00236,
1658
+ "grad_norm": 0.5859375,
1659
+ "learning_rate": 9.999862576257836e-06,
1660
+ "loss": 1.4828,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.00237,
1665
+ "grad_norm": 0.6015625,
1666
+ "learning_rate": 9.999861409187851e-06,
1667
+ "loss": 1.3898,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.00238,
1672
+ "grad_norm": 0.59765625,
1673
+ "learning_rate": 9.999860237183202e-06,
1674
+ "loss": 1.5977,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.00239,
1679
+ "grad_norm": 0.609375,
1680
+ "learning_rate": 9.99985906024389e-06,
1681
+ "loss": 1.4885,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.0024,
1686
+ "grad_norm": 0.5703125,
1687
+ "learning_rate": 9.999857878369917e-06,
1688
+ "loss": 1.4311,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.00241,
1693
+ "grad_norm": 0.59765625,
1694
+ "learning_rate": 9.999856691561278e-06,
1695
+ "loss": 1.4091,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.00242,
1700
+ "grad_norm": 0.6484375,
1701
+ "learning_rate": 9.99985549981798e-06,
1702
+ "loss": 1.6187,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.00243,
1707
+ "grad_norm": 0.6328125,
1708
+ "learning_rate": 9.999854303140022e-06,
1709
+ "loss": 1.5306,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.00244,
1714
+ "grad_norm": 0.58984375,
1715
+ "learning_rate": 9.999853101527406e-06,
1716
+ "loss": 1.5455,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.00245,
1721
+ "grad_norm": 0.67578125,
1722
+ "learning_rate": 9.999851894980133e-06,
1723
+ "loss": 1.5096,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.00246,
1728
+ "grad_norm": 0.58984375,
1729
+ "learning_rate": 9.999850683498204e-06,
1730
+ "loss": 1.4124,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.00247,
1735
+ "grad_norm": 0.62109375,
1736
+ "learning_rate": 9.999849467081619e-06,
1737
+ "loss": 1.5054,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.00248,
1742
+ "grad_norm": 0.734375,
1743
+ "learning_rate": 9.999848245730382e-06,
1744
+ "loss": 1.5263,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.00249,
1749
+ "grad_norm": 0.640625,
1750
+ "learning_rate": 9.99984701944449e-06,
1751
+ "loss": 1.4857,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.0025,
1756
+ "grad_norm": 0.63671875,
1757
+ "learning_rate": 9.99984578822395e-06,
1758
+ "loss": 1.451,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.00251,
1763
+ "grad_norm": 0.59375,
1764
+ "learning_rate": 9.999844552068759e-06,
1765
+ "loss": 1.5749,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 0.00252,
1770
+ "grad_norm": 0.58984375,
1771
+ "learning_rate": 9.999843310978919e-06,
1772
+ "loss": 1.5781,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 0.00253,
1777
+ "grad_norm": 0.60546875,
1778
+ "learning_rate": 9.99984206495443e-06,
1779
+ "loss": 1.5356,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 0.00254,
1784
+ "grad_norm": 0.69140625,
1785
+ "learning_rate": 9.999840813995296e-06,
1786
+ "loss": 1.532,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 0.00255,
1791
+ "grad_norm": 0.578125,
1792
+ "learning_rate": 9.999839558101517e-06,
1793
+ "loss": 1.513,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 0.00256,
1798
+ "grad_norm": 0.59765625,
1799
+ "learning_rate": 9.999838297273093e-06,
1800
+ "loss": 1.5514,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 0.00257,
1805
+ "grad_norm": 0.58203125,
1806
+ "learning_rate": 9.999837031510027e-06,
1807
+ "loss": 1.529,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 0.00258,
1812
+ "grad_norm": 0.62890625,
1813
+ "learning_rate": 9.99983576081232e-06,
1814
+ "loss": 1.4506,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 0.00259,
1819
+ "grad_norm": 0.5859375,
1820
+ "learning_rate": 9.999834485179974e-06,
1821
+ "loss": 1.4989,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 0.0026,
1826
+ "grad_norm": 0.63671875,
1827
+ "learning_rate": 9.999833204612988e-06,
1828
+ "loss": 1.4701,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 0.00261,
1833
+ "grad_norm": 0.625,
1834
+ "learning_rate": 9.999831919111363e-06,
1835
+ "loss": 1.4888,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 0.00262,
1840
+ "grad_norm": 0.578125,
1841
+ "learning_rate": 9.999830628675105e-06,
1842
+ "loss": 1.4784,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 0.00263,
1847
+ "grad_norm": 0.59765625,
1848
+ "learning_rate": 9.99982933330421e-06,
1849
+ "loss": 1.5459,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 0.00264,
1854
+ "grad_norm": 0.58984375,
1855
+ "learning_rate": 9.99982803299868e-06,
1856
+ "loss": 1.525,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 0.00265,
1861
+ "grad_norm": 0.578125,
1862
+ "learning_rate": 9.99982672775852e-06,
1863
+ "loss": 1.4649,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 0.00266,
1868
+ "grad_norm": 0.625,
1869
+ "learning_rate": 9.999825417583727e-06,
1870
+ "loss": 1.5024,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 0.00267,
1875
+ "grad_norm": 0.578125,
1876
+ "learning_rate": 9.999824102474304e-06,
1877
+ "loss": 1.5069,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 0.00268,
1882
+ "grad_norm": 0.83984375,
1883
+ "learning_rate": 9.999822782430253e-06,
1884
+ "loss": 1.3715,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 0.00269,
1889
+ "grad_norm": 0.609375,
1890
+ "learning_rate": 9.999821457451576e-06,
1891
+ "loss": 1.5258,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 0.0027,
1896
+ "grad_norm": 0.59765625,
1897
+ "learning_rate": 9.999820127538271e-06,
1898
+ "loss": 1.5928,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 0.00271,
1903
+ "grad_norm": 0.6328125,
1904
+ "learning_rate": 9.999818792690344e-06,
1905
+ "loss": 1.4709,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 0.00272,
1910
+ "grad_norm": 0.6015625,
1911
+ "learning_rate": 9.99981745290779e-06,
1912
+ "loss": 1.5465,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 0.00273,
1917
+ "grad_norm": 0.63671875,
1918
+ "learning_rate": 9.999816108190616e-06,
1919
+ "loss": 1.4847,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 0.00274,
1924
+ "grad_norm": 0.7890625,
1925
+ "learning_rate": 9.999814758538821e-06,
1926
+ "loss": 1.5317,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 0.00275,
1931
+ "grad_norm": 0.5703125,
1932
+ "learning_rate": 9.999813403952407e-06,
1933
+ "loss": 1.5641,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 0.00276,
1938
+ "grad_norm": 0.6328125,
1939
+ "learning_rate": 9.999812044431374e-06,
1940
+ "loss": 1.5378,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 0.00277,
1945
+ "grad_norm": 0.70703125,
1946
+ "learning_rate": 9.999810679975725e-06,
1947
+ "loss": 1.4964,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 0.00278,
1952
+ "grad_norm": 0.5546875,
1953
+ "learning_rate": 9.999809310585462e-06,
1954
+ "loss": 1.3405,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 0.00279,
1959
+ "grad_norm": 0.58984375,
1960
+ "learning_rate": 9.999807936260583e-06,
1961
+ "loss": 1.4228,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 0.0028,
1966
+ "grad_norm": 0.58984375,
1967
+ "learning_rate": 9.999806557001092e-06,
1968
+ "loss": 1.4399,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 0.00281,
1973
+ "grad_norm": 0.59765625,
1974
+ "learning_rate": 9.99980517280699e-06,
1975
+ "loss": 1.4913,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 0.00282,
1980
+ "grad_norm": 0.83203125,
1981
+ "learning_rate": 9.999803783678276e-06,
1982
+ "loss": 1.4801,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 0.00283,
1987
+ "grad_norm": 0.59375,
1988
+ "learning_rate": 9.999802389614957e-06,
1989
+ "loss": 1.5795,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 0.00284,
1994
+ "grad_norm": 0.59765625,
1995
+ "learning_rate": 9.99980099061703e-06,
1996
+ "loss": 1.5647,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 0.00285,
2001
+ "grad_norm": 0.60546875,
2002
+ "learning_rate": 9.999799586684495e-06,
2003
+ "loss": 1.4144,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 0.00286,
2008
+ "grad_norm": 0.59765625,
2009
+ "learning_rate": 9.999798177817357e-06,
2010
+ "loss": 1.5315,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 0.00287,
2015
+ "grad_norm": 0.59375,
2016
+ "learning_rate": 9.999796764015617e-06,
2017
+ "loss": 1.5143,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 0.00288,
2022
+ "grad_norm": 0.5625,
2023
+ "learning_rate": 9.999795345279273e-06,
2024
+ "loss": 1.4468,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 0.00289,
2029
+ "grad_norm": 0.7265625,
2030
+ "learning_rate": 9.999793921608331e-06,
2031
+ "loss": 1.4191,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 0.0029,
2036
+ "grad_norm": 0.60546875,
2037
+ "learning_rate": 9.99979249300279e-06,
2038
+ "loss": 1.5005,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 0.00291,
2043
+ "grad_norm": 0.578125,
2044
+ "learning_rate": 9.999791059462649e-06,
2045
+ "loss": 1.5497,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 0.00292,
2050
+ "grad_norm": 0.5703125,
2051
+ "learning_rate": 9.999789620987914e-06,
2052
+ "loss": 1.4732,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 0.00293,
2057
+ "grad_norm": 0.609375,
2058
+ "learning_rate": 9.999788177578585e-06,
2059
+ "loss": 1.5058,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 0.00294,
2064
+ "grad_norm": 0.59765625,
2065
+ "learning_rate": 9.999786729234661e-06,
2066
+ "loss": 1.5243,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 0.00295,
2071
+ "grad_norm": 0.91015625,
2072
+ "learning_rate": 9.999785275956147e-06,
2073
+ "loss": 1.5668,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 0.00296,
2078
+ "grad_norm": 0.5703125,
2079
+ "learning_rate": 9.999783817743043e-06,
2080
+ "loss": 1.4874,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 0.00297,
2085
+ "grad_norm": 0.578125,
2086
+ "learning_rate": 9.999782354595349e-06,
2087
+ "loss": 1.5466,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 0.00298,
2092
+ "grad_norm": 0.61328125,
2093
+ "learning_rate": 9.999780886513069e-06,
2094
+ "loss": 1.5114,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 0.00299,
2099
+ "grad_norm": 0.5546875,
2100
+ "learning_rate": 9.9997794134962e-06,
2101
+ "loss": 1.4656,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 0.003,
2106
+ "grad_norm": 0.578125,
2107
+ "learning_rate": 9.99977793554475e-06,
2108
+ "loss": 1.4512,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 0.00301,
2113
+ "grad_norm": 0.6015625,
2114
+ "learning_rate": 9.999776452658716e-06,
2115
+ "loss": 1.4278,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 0.00302,
2120
+ "grad_norm": 0.609375,
2121
+ "learning_rate": 9.999774964838099e-06,
2122
+ "loss": 1.4672,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 0.00303,
2127
+ "grad_norm": 0.6484375,
2128
+ "learning_rate": 9.999773472082903e-06,
2129
+ "loss": 1.5091,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 0.00304,
2134
+ "grad_norm": 0.59765625,
2135
+ "learning_rate": 9.999771974393129e-06,
2136
+ "loss": 1.4843,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 0.00305,
2141
+ "grad_norm": 0.6015625,
2142
+ "learning_rate": 9.999770471768778e-06,
2143
+ "loss": 1.424,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 0.00306,
2148
+ "grad_norm": 0.57421875,
2149
+ "learning_rate": 9.999768964209848e-06,
2150
+ "loss": 1.3624,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 0.00307,
2155
+ "grad_norm": 0.60546875,
2156
+ "learning_rate": 9.999767451716347e-06,
2157
+ "loss": 1.5685,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 0.00308,
2162
+ "grad_norm": 0.609375,
2163
+ "learning_rate": 9.999765934288272e-06,
2164
+ "loss": 1.563,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 0.00309,
2169
+ "grad_norm": 0.62890625,
2170
+ "learning_rate": 9.999764411925628e-06,
2171
+ "loss": 1.5428,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 0.0031,
2176
+ "grad_norm": 0.625,
2177
+ "learning_rate": 9.999762884628413e-06,
2178
+ "loss": 1.5119,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 0.00311,
2183
+ "grad_norm": 0.58984375,
2184
+ "learning_rate": 9.999761352396628e-06,
2185
+ "loss": 1.5343,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 0.00312,
2190
+ "grad_norm": 0.625,
2191
+ "learning_rate": 9.999759815230277e-06,
2192
+ "loss": 1.5505,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 0.00313,
2197
+ "grad_norm": 0.59375,
2198
+ "learning_rate": 9.999758273129362e-06,
2199
+ "loss": 1.4687,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 0.00314,
2204
+ "grad_norm": 0.6171875,
2205
+ "learning_rate": 9.999756726093883e-06,
2206
+ "loss": 1.4969,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 0.00315,
2211
+ "grad_norm": 0.59375,
2212
+ "learning_rate": 9.999755174123842e-06,
2213
+ "loss": 1.5959,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 0.00316,
2218
+ "grad_norm": 0.91015625,
2219
+ "learning_rate": 9.999753617219241e-06,
2220
+ "loss": 1.2334,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 0.00317,
2225
+ "grad_norm": 0.61328125,
2226
+ "learning_rate": 9.99975205538008e-06,
2227
+ "loss": 1.4491,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 0.00318,
2232
+ "grad_norm": 0.59765625,
2233
+ "learning_rate": 9.999750488606362e-06,
2234
+ "loss": 1.468,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 0.00319,
2239
+ "grad_norm": 0.61328125,
2240
+ "learning_rate": 9.999748916898088e-06,
2241
+ "loss": 1.4278,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 0.0032,
2246
+ "grad_norm": 0.60546875,
2247
+ "learning_rate": 9.99974734025526e-06,
2248
+ "loss": 1.5056,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 0.00321,
2253
+ "grad_norm": 0.578125,
2254
+ "learning_rate": 9.999745758677878e-06,
2255
+ "loss": 1.4188,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 0.00322,
2260
+ "grad_norm": 0.58203125,
2261
+ "learning_rate": 9.999744172165945e-06,
2262
+ "loss": 1.3937,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 0.00323,
2267
+ "grad_norm": 0.60546875,
2268
+ "learning_rate": 9.999742580719463e-06,
2269
+ "loss": 1.5149,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 0.00324,
2274
+ "grad_norm": 0.58984375,
2275
+ "learning_rate": 9.999740984338433e-06,
2276
+ "loss": 1.4844,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 0.00325,
2281
+ "grad_norm": 0.578125,
2282
+ "learning_rate": 9.999739383022856e-06,
2283
+ "loss": 1.4974,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 0.00326,
2288
+ "grad_norm": 0.5859375,
2289
+ "learning_rate": 9.999737776772735e-06,
2290
+ "loss": 1.4215,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 0.00327,
2295
+ "grad_norm": 0.59375,
2296
+ "learning_rate": 9.99973616558807e-06,
2297
+ "loss": 1.578,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 0.00328,
2302
+ "grad_norm": 0.6484375,
2303
+ "learning_rate": 9.999734549468863e-06,
2304
+ "loss": 1.5505,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 0.00329,
2309
+ "grad_norm": 0.54296875,
2310
+ "learning_rate": 9.999732928415115e-06,
2311
+ "loss": 1.3222,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 0.0033,
2316
+ "grad_norm": 0.60546875,
2317
+ "learning_rate": 9.999731302426829e-06,
2318
+ "loss": 1.5815,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 0.00331,
2323
+ "grad_norm": 0.58203125,
2324
+ "learning_rate": 9.999729671504007e-06,
2325
+ "loss": 1.4017,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 0.00332,
2330
+ "grad_norm": 0.58984375,
2331
+ "learning_rate": 9.999728035646648e-06,
2332
+ "loss": 1.507,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 0.00333,
2337
+ "grad_norm": 0.57421875,
2338
+ "learning_rate": 9.999726394854755e-06,
2339
+ "loss": 1.441,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 0.00334,
2344
+ "grad_norm": 0.57421875,
2345
+ "learning_rate": 9.99972474912833e-06,
2346
+ "loss": 1.5628,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 0.00335,
2351
+ "grad_norm": 0.61328125,
2352
+ "learning_rate": 9.999723098467375e-06,
2353
+ "loss": 1.464,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 0.00336,
2358
+ "grad_norm": 0.57421875,
2359
+ "learning_rate": 9.999721442871892e-06,
2360
+ "loss": 1.4567,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 0.00337,
2365
+ "grad_norm": 0.60546875,
2366
+ "learning_rate": 9.99971978234188e-06,
2367
+ "loss": 1.5087,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 0.00338,
2372
+ "grad_norm": 0.6015625,
2373
+ "learning_rate": 9.999718116877344e-06,
2374
+ "loss": 1.5264,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 0.00339,
2379
+ "grad_norm": 0.60546875,
2380
+ "learning_rate": 9.999716446478284e-06,
2381
+ "loss": 1.4069,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 0.0034,
2386
+ "grad_norm": 0.63671875,
2387
+ "learning_rate": 9.9997147711447e-06,
2388
+ "loss": 1.4323,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 0.00341,
2393
+ "grad_norm": 0.58984375,
2394
+ "learning_rate": 9.999713090876597e-06,
2395
+ "loss": 1.5584,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 0.00342,
2400
+ "grad_norm": 0.56640625,
2401
+ "learning_rate": 9.999711405673974e-06,
2402
+ "loss": 1.4787,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 0.00343,
2407
+ "grad_norm": 0.6328125,
2408
+ "learning_rate": 9.999709715536833e-06,
2409
+ "loss": 1.5732,
2410
+ "step": 343
2411
+ },
2412
+ {
2413
+ "epoch": 0.00344,
2414
+ "grad_norm": 0.609375,
2415
+ "learning_rate": 9.999708020465177e-06,
2416
+ "loss": 1.3899,
2417
+ "step": 344
2418
+ },
2419
+ {
2420
+ "epoch": 0.00345,
2421
+ "grad_norm": 1.9453125,
2422
+ "learning_rate": 9.999706320459008e-06,
2423
+ "loss": 1.3948,
2424
+ "step": 345
2425
+ },
2426
+ {
2427
+ "epoch": 0.00346,
2428
+ "grad_norm": 0.5546875,
2429
+ "learning_rate": 9.999704615518327e-06,
2430
+ "loss": 1.5258,
2431
+ "step": 346
2432
+ },
2433
+ {
2434
+ "epoch": 0.00347,
2435
+ "grad_norm": 0.578125,
2436
+ "learning_rate": 9.999702905643133e-06,
2437
+ "loss": 1.4421,
2438
+ "step": 347
2439
+ },
2440
+ {
2441
+ "epoch": 0.00348,
2442
+ "grad_norm": 0.58984375,
2443
+ "learning_rate": 9.999701190833431e-06,
2444
+ "loss": 1.5647,
2445
+ "step": 348
2446
+ },
2447
+ {
2448
+ "epoch": 0.00349,
2449
+ "grad_norm": 0.640625,
2450
+ "learning_rate": 9.999699471089223e-06,
2451
+ "loss": 1.6083,
2452
+ "step": 349
2453
+ },
2454
+ {
2455
+ "epoch": 0.0035,
2456
+ "grad_norm": 0.56640625,
2457
+ "learning_rate": 9.999697746410509e-06,
2458
+ "loss": 1.5287,
2459
+ "step": 350
2460
+ },
2461
+ {
2462
+ "epoch": 0.00351,
2463
+ "grad_norm": 0.58984375,
2464
+ "learning_rate": 9.99969601679729e-06,
2465
+ "loss": 1.4517,
2466
+ "step": 351
2467
+ },
2468
+ {
2469
+ "epoch": 0.00352,
2470
+ "grad_norm": 0.6484375,
2471
+ "learning_rate": 9.999694282249568e-06,
2472
+ "loss": 1.5041,
2473
+ "step": 352
2474
+ },
2475
+ {
2476
+ "epoch": 0.00353,
2477
+ "grad_norm": 0.57421875,
2478
+ "learning_rate": 9.999692542767347e-06,
2479
+ "loss": 1.4867,
2480
+ "step": 353
2481
+ },
2482
+ {
2483
+ "epoch": 0.00354,
2484
+ "grad_norm": 0.5859375,
2485
+ "learning_rate": 9.999690798350628e-06,
2486
+ "loss": 1.5221,
2487
+ "step": 354
2488
+ },
2489
+ {
2490
+ "epoch": 0.00355,
2491
+ "grad_norm": 0.578125,
2492
+ "learning_rate": 9.999689048999411e-06,
2493
+ "loss": 1.5112,
2494
+ "step": 355
2495
+ },
2496
+ {
2497
+ "epoch": 0.00356,
2498
+ "grad_norm": 0.58984375,
2499
+ "learning_rate": 9.999687294713697e-06,
2500
+ "loss": 1.609,
2501
+ "step": 356
2502
+ },
2503
+ {
2504
+ "epoch": 0.00357,
2505
+ "grad_norm": 5.53125,
2506
+ "learning_rate": 9.999685535493491e-06,
2507
+ "loss": 1.4672,
2508
+ "step": 357
2509
+ },
2510
+ {
2511
+ "epoch": 0.00358,
2512
+ "grad_norm": 0.57421875,
2513
+ "learning_rate": 9.999683771338794e-06,
2514
+ "loss": 1.5205,
2515
+ "step": 358
2516
+ },
2517
+ {
2518
+ "epoch": 0.00359,
2519
+ "grad_norm": 0.5859375,
2520
+ "learning_rate": 9.999682002249607e-06,
2521
+ "loss": 1.5086,
2522
+ "step": 359
2523
+ },
2524
+ {
2525
+ "epoch": 0.0036,
2526
+ "grad_norm": 0.65234375,
2527
+ "learning_rate": 9.99968022822593e-06,
2528
+ "loss": 1.5032,
2529
+ "step": 360
2530
+ },
2531
+ {
2532
+ "epoch": 0.00361,
2533
+ "grad_norm": 0.57421875,
2534
+ "learning_rate": 9.999678449267766e-06,
2535
+ "loss": 1.4734,
2536
+ "step": 361
2537
+ },
2538
+ {
2539
+ "epoch": 0.00362,
2540
+ "grad_norm": 0.64453125,
2541
+ "learning_rate": 9.99967666537512e-06,
2542
+ "loss": 1.5343,
2543
+ "step": 362
2544
+ },
2545
+ {
2546
+ "epoch": 0.00363,
2547
+ "grad_norm": 0.57421875,
2548
+ "learning_rate": 9.999674876547989e-06,
2549
+ "loss": 1.4186,
2550
+ "step": 363
2551
+ },
2552
+ {
2553
+ "epoch": 0.00364,
2554
+ "grad_norm": 0.6328125,
2555
+ "learning_rate": 9.999673082786376e-06,
2556
+ "loss": 1.386,
2557
+ "step": 364
2558
+ },
2559
+ {
2560
+ "epoch": 0.00365,
2561
+ "grad_norm": 0.578125,
2562
+ "learning_rate": 9.999671284090286e-06,
2563
+ "loss": 1.5629,
2564
+ "step": 365
2565
+ },
2566
+ {
2567
+ "epoch": 0.00366,
2568
+ "grad_norm": 0.609375,
2569
+ "learning_rate": 9.999669480459716e-06,
2570
+ "loss": 1.5062,
2571
+ "step": 366
2572
+ },
2573
+ {
2574
+ "epoch": 0.00367,
2575
+ "grad_norm": 0.6328125,
2576
+ "learning_rate": 9.99966767189467e-06,
2577
+ "loss": 1.4843,
2578
+ "step": 367
2579
+ },
2580
+ {
2581
+ "epoch": 0.00368,
2582
+ "grad_norm": 0.59375,
2583
+ "learning_rate": 9.999665858395152e-06,
2584
+ "loss": 1.5003,
2585
+ "step": 368
2586
+ },
2587
+ {
2588
+ "epoch": 0.00369,
2589
+ "grad_norm": 0.58984375,
2590
+ "learning_rate": 9.99966403996116e-06,
2591
+ "loss": 1.4893,
2592
+ "step": 369
2593
+ },
2594
+ {
2595
+ "epoch": 0.0037,
2596
+ "grad_norm": 0.609375,
2597
+ "learning_rate": 9.999662216592696e-06,
2598
+ "loss": 1.4829,
2599
+ "step": 370
2600
+ },
2601
+ {
2602
+ "epoch": 0.00371,
2603
+ "grad_norm": 0.7734375,
2604
+ "learning_rate": 9.999660388289765e-06,
2605
+ "loss": 1.4288,
2606
+ "step": 371
2607
+ },
2608
+ {
2609
+ "epoch": 0.00372,
2610
+ "grad_norm": 0.5859375,
2611
+ "learning_rate": 9.999658555052368e-06,
2612
+ "loss": 1.4853,
2613
+ "step": 372
2614
+ },
2615
+ {
2616
+ "epoch": 0.00373,
2617
+ "grad_norm": 0.58203125,
2618
+ "learning_rate": 9.999656716880504e-06,
2619
+ "loss": 1.4939,
2620
+ "step": 373
2621
+ },
2622
+ {
2623
+ "epoch": 0.00374,
2624
+ "grad_norm": 0.62109375,
2625
+ "learning_rate": 9.999654873774177e-06,
2626
+ "loss": 1.5349,
2627
+ "step": 374
2628
+ },
2629
+ {
2630
+ "epoch": 0.00375,
2631
+ "grad_norm": 0.59765625,
2632
+ "learning_rate": 9.999653025733386e-06,
2633
+ "loss": 1.5811,
2634
+ "step": 375
2635
+ },
2636
+ {
2637
+ "epoch": 0.00376,
2638
+ "grad_norm": 0.59765625,
2639
+ "learning_rate": 9.999651172758139e-06,
2640
+ "loss": 1.5546,
2641
+ "step": 376
2642
+ },
2643
+ {
2644
+ "epoch": 0.00377,
2645
+ "grad_norm": 0.60546875,
2646
+ "learning_rate": 9.999649314848432e-06,
2647
+ "loss": 1.5265,
2648
+ "step": 377
2649
+ },
2650
+ {
2651
+ "epoch": 0.00378,
2652
+ "grad_norm": 0.59375,
2653
+ "learning_rate": 9.99964745200427e-06,
2654
+ "loss": 1.5653,
2655
+ "step": 378
2656
+ },
2657
+ {
2658
+ "epoch": 0.00379,
2659
+ "grad_norm": 0.76171875,
2660
+ "learning_rate": 9.999645584225654e-06,
2661
+ "loss": 1.3955,
2662
+ "step": 379
2663
+ },
2664
+ {
2665
+ "epoch": 0.0038,
2666
+ "grad_norm": 0.62890625,
2667
+ "learning_rate": 9.999643711512586e-06,
2668
+ "loss": 1.5375,
2669
+ "step": 380
2670
+ },
2671
+ {
2672
+ "epoch": 0.00381,
2673
+ "grad_norm": 0.58203125,
2674
+ "learning_rate": 9.999641833865065e-06,
2675
+ "loss": 1.5196,
2676
+ "step": 381
2677
+ },
2678
+ {
2679
+ "epoch": 0.00382,
2680
+ "grad_norm": 0.578125,
2681
+ "learning_rate": 9.999639951283098e-06,
2682
+ "loss": 1.4494,
2683
+ "step": 382
2684
+ },
2685
+ {
2686
+ "epoch": 0.00383,
2687
+ "grad_norm": 0.609375,
2688
+ "learning_rate": 9.99963806376668e-06,
2689
+ "loss": 1.5654,
2690
+ "step": 383
2691
+ },
2692
+ {
2693
+ "epoch": 0.00384,
2694
+ "grad_norm": 0.60546875,
2695
+ "learning_rate": 9.999636171315822e-06,
2696
+ "loss": 1.5794,
2697
+ "step": 384
2698
+ },
2699
+ {
2700
+ "epoch": 0.00385,
2701
+ "grad_norm": 0.578125,
2702
+ "learning_rate": 9.999634273930519e-06,
2703
+ "loss": 1.5123,
2704
+ "step": 385
2705
+ },
2706
+ {
2707
+ "epoch": 0.00386,
2708
+ "grad_norm": 0.61328125,
2709
+ "learning_rate": 9.999632371610775e-06,
2710
+ "loss": 1.5589,
2711
+ "step": 386
2712
+ },
2713
+ {
2714
+ "epoch": 0.00387,
2715
+ "grad_norm": 0.6015625,
2716
+ "learning_rate": 9.99963046435659e-06,
2717
+ "loss": 1.5204,
2718
+ "step": 387
2719
+ },
2720
+ {
2721
+ "epoch": 0.00388,
2722
+ "grad_norm": 0.59375,
2723
+ "learning_rate": 9.999628552167968e-06,
2724
+ "loss": 1.5047,
2725
+ "step": 388
2726
+ },
2727
+ {
2728
+ "epoch": 0.00389,
2729
+ "grad_norm": 0.6015625,
2730
+ "learning_rate": 9.999626635044911e-06,
2731
+ "loss": 1.5133,
2732
+ "step": 389
2733
+ },
2734
+ {
2735
+ "epoch": 0.0039,
2736
+ "grad_norm": 0.5859375,
2737
+ "learning_rate": 9.99962471298742e-06,
2738
+ "loss": 1.5079,
2739
+ "step": 390
2740
+ },
2741
+ {
2742
+ "epoch": 0.00391,
2743
+ "grad_norm": 0.6171875,
2744
+ "learning_rate": 9.999622785995499e-06,
2745
+ "loss": 1.525,
2746
+ "step": 391
2747
+ },
2748
+ {
2749
+ "epoch": 0.00392,
2750
+ "grad_norm": 0.5859375,
2751
+ "learning_rate": 9.999620854069148e-06,
2752
+ "loss": 1.5243,
2753
+ "step": 392
2754
+ },
2755
+ {
2756
+ "epoch": 0.00393,
2757
+ "grad_norm": 0.70703125,
2758
+ "learning_rate": 9.999618917208367e-06,
2759
+ "loss": 1.5368,
2760
+ "step": 393
2761
+ },
2762
+ {
2763
+ "epoch": 0.00394,
2764
+ "grad_norm": 0.68359375,
2765
+ "learning_rate": 9.99961697541316e-06,
2766
+ "loss": 1.5637,
2767
+ "step": 394
2768
+ },
2769
+ {
2770
+ "epoch": 0.00395,
2771
+ "grad_norm": 0.58203125,
2772
+ "learning_rate": 9.99961502868353e-06,
2773
+ "loss": 1.5719,
2774
+ "step": 395
2775
+ },
2776
+ {
2777
+ "epoch": 0.00396,
2778
+ "grad_norm": 0.58203125,
2779
+ "learning_rate": 9.999613077019477e-06,
2780
+ "loss": 1.5431,
2781
+ "step": 396
2782
+ },
2783
+ {
2784
+ "epoch": 0.00397,
2785
+ "grad_norm": 0.6171875,
2786
+ "learning_rate": 9.999611120421004e-06,
2787
+ "loss": 1.562,
2788
+ "step": 397
2789
+ },
2790
+ {
2791
+ "epoch": 0.00398,
2792
+ "grad_norm": 0.58984375,
2793
+ "learning_rate": 9.999609158888112e-06,
2794
+ "loss": 1.5388,
2795
+ "step": 398
2796
+ },
2797
+ {
2798
+ "epoch": 0.00399,
2799
+ "grad_norm": 0.578125,
2800
+ "learning_rate": 9.999607192420804e-06,
2801
+ "loss": 1.4451,
2802
+ "step": 399
2803
+ },
2804
+ {
2805
+ "epoch": 0.004,
2806
+ "grad_norm": 0.7421875,
2807
+ "learning_rate": 9.999605221019082e-06,
2808
+ "loss": 1.488,
2809
+ "step": 400
2810
+ },
2811
+ {
2812
+ "epoch": 0.00401,
2813
+ "grad_norm": 0.58203125,
2814
+ "learning_rate": 9.999603244682946e-06,
2815
+ "loss": 1.498,
2816
+ "step": 401
2817
+ },
2818
+ {
2819
+ "epoch": 0.00402,
2820
+ "grad_norm": 0.5703125,
2821
+ "learning_rate": 9.9996012634124e-06,
2822
+ "loss": 1.4949,
2823
+ "step": 402
2824
+ },
2825
+ {
2826
+ "epoch": 0.00403,
2827
+ "grad_norm": 1.28125,
2828
+ "learning_rate": 9.999599277207445e-06,
2829
+ "loss": 1.4222,
2830
+ "step": 403
2831
+ },
2832
+ {
2833
+ "epoch": 0.00404,
2834
+ "grad_norm": 0.578125,
2835
+ "learning_rate": 9.999597286068085e-06,
2836
+ "loss": 1.4637,
2837
+ "step": 404
2838
+ },
2839
+ {
2840
+ "epoch": 0.00405,
2841
+ "grad_norm": 0.6015625,
2842
+ "learning_rate": 9.99959528999432e-06,
2843
+ "loss": 1.4693,
2844
+ "step": 405
2845
+ },
2846
+ {
2847
+ "epoch": 0.00406,
2848
+ "grad_norm": 0.61328125,
2849
+ "learning_rate": 9.999593288986151e-06,
2850
+ "loss": 1.6096,
2851
+ "step": 406
2852
+ },
2853
+ {
2854
+ "epoch": 0.00407,
2855
+ "grad_norm": 0.57421875,
2856
+ "learning_rate": 9.999591283043581e-06,
2857
+ "loss": 1.4465,
2858
+ "step": 407
2859
+ },
2860
+ {
2861
+ "epoch": 0.00408,
2862
+ "grad_norm": 0.59375,
2863
+ "learning_rate": 9.999589272166614e-06,
2864
+ "loss": 1.514,
2865
+ "step": 408
2866
+ },
2867
+ {
2868
+ "epoch": 0.00409,
2869
+ "grad_norm": 0.59765625,
2870
+ "learning_rate": 9.999587256355248e-06,
2871
+ "loss": 1.4868,
2872
+ "step": 409
2873
+ },
2874
+ {
2875
+ "epoch": 0.0041,
2876
+ "grad_norm": 0.5859375,
2877
+ "learning_rate": 9.999585235609487e-06,
2878
+ "loss": 1.4936,
2879
+ "step": 410
2880
+ },
2881
+ {
2882
+ "epoch": 0.00411,
2883
+ "grad_norm": 0.57421875,
2884
+ "learning_rate": 9.999583209929335e-06,
2885
+ "loss": 1.5555,
2886
+ "step": 411
2887
+ },
2888
+ {
2889
+ "epoch": 0.00412,
2890
+ "grad_norm": 0.5859375,
2891
+ "learning_rate": 9.999581179314793e-06,
2892
+ "loss": 1.4915,
2893
+ "step": 412
2894
+ },
2895
+ {
2896
+ "epoch": 0.00413,
2897
+ "grad_norm": 0.61328125,
2898
+ "learning_rate": 9.999579143765861e-06,
2899
+ "loss": 1.5244,
2900
+ "step": 413
2901
+ },
2902
+ {
2903
+ "epoch": 0.00414,
2904
+ "grad_norm": 0.62890625,
2905
+ "learning_rate": 9.999577103282541e-06,
2906
+ "loss": 1.558,
2907
+ "step": 414
2908
+ },
2909
+ {
2910
+ "epoch": 0.00415,
2911
+ "grad_norm": 0.6328125,
2912
+ "learning_rate": 9.999575057864837e-06,
2913
+ "loss": 1.5333,
2914
+ "step": 415
2915
+ },
2916
+ {
2917
+ "epoch": 0.00416,
2918
+ "grad_norm": 0.6171875,
2919
+ "learning_rate": 9.999573007512751e-06,
2920
+ "loss": 1.5035,
2921
+ "step": 416
2922
+ },
2923
+ {
2924
+ "epoch": 0.00417,
2925
+ "grad_norm": 0.64453125,
2926
+ "learning_rate": 9.999570952226284e-06,
2927
+ "loss": 1.5245,
2928
+ "step": 417
2929
+ },
2930
+ {
2931
+ "epoch": 0.00418,
2932
+ "grad_norm": 0.578125,
2933
+ "learning_rate": 9.999568892005436e-06,
2934
+ "loss": 1.4968,
2935
+ "step": 418
2936
+ },
2937
+ {
2938
+ "epoch": 0.00419,
2939
+ "grad_norm": 0.6953125,
2940
+ "learning_rate": 9.999566826850214e-06,
2941
+ "loss": 1.4418,
2942
+ "step": 419
2943
+ },
2944
+ {
2945
+ "epoch": 0.0042,
2946
+ "grad_norm": 0.61328125,
2947
+ "learning_rate": 9.999564756760616e-06,
2948
+ "loss": 1.6185,
2949
+ "step": 420
2950
+ },
2951
+ {
2952
+ "epoch": 0.00421,
2953
+ "grad_norm": 0.57421875,
2954
+ "learning_rate": 9.999562681736645e-06,
2955
+ "loss": 1.4845,
2956
+ "step": 421
2957
+ },
2958
+ {
2959
+ "epoch": 0.00422,
2960
+ "grad_norm": 0.93359375,
2961
+ "learning_rate": 9.999560601778303e-06,
2962
+ "loss": 1.3121,
2963
+ "step": 422
2964
+ },
2965
+ {
2966
+ "epoch": 0.00423,
2967
+ "grad_norm": 0.57421875,
2968
+ "learning_rate": 9.999558516885595e-06,
2969
+ "loss": 1.5696,
2970
+ "step": 423
2971
+ },
2972
+ {
2973
+ "epoch": 0.00424,
2974
+ "grad_norm": 0.6328125,
2975
+ "learning_rate": 9.99955642705852e-06,
2976
+ "loss": 1.4734,
2977
+ "step": 424
2978
+ },
2979
+ {
2980
+ "epoch": 0.00425,
2981
+ "grad_norm": 0.58984375,
2982
+ "learning_rate": 9.999554332297079e-06,
2983
+ "loss": 1.5252,
2984
+ "step": 425
2985
+ },
2986
+ {
2987
+ "epoch": 0.00426,
2988
+ "grad_norm": 0.59765625,
2989
+ "learning_rate": 9.999552232601275e-06,
2990
+ "loss": 1.5028,
2991
+ "step": 426
2992
+ },
2993
+ {
2994
+ "epoch": 0.00427,
2995
+ "grad_norm": 0.578125,
2996
+ "learning_rate": 9.999550127971113e-06,
2997
+ "loss": 1.428,
2998
+ "step": 427
2999
+ },
3000
+ {
3001
+ "epoch": 0.00428,
3002
+ "grad_norm": 0.57421875,
3003
+ "learning_rate": 9.999548018406591e-06,
3004
+ "loss": 1.5138,
3005
+ "step": 428
3006
+ },
3007
+ {
3008
+ "epoch": 0.00429,
3009
+ "grad_norm": 0.57421875,
3010
+ "learning_rate": 9.999545903907714e-06,
3011
+ "loss": 1.5135,
3012
+ "step": 429
3013
+ },
3014
+ {
3015
+ "epoch": 0.0043,
3016
+ "grad_norm": 0.59375,
3017
+ "learning_rate": 9.999543784474484e-06,
3018
+ "loss": 1.5209,
3019
+ "step": 430
3020
+ },
3021
+ {
3022
+ "epoch": 0.00431,
3023
+ "grad_norm": 0.70703125,
3024
+ "learning_rate": 9.9995416601069e-06,
3025
+ "loss": 1.5048,
3026
+ "step": 431
3027
+ },
3028
+ {
3029
+ "epoch": 0.00432,
3030
+ "grad_norm": 0.5859375,
3031
+ "learning_rate": 9.999539530804967e-06,
3032
+ "loss": 1.5185,
3033
+ "step": 432
3034
+ },
3035
+ {
3036
+ "epoch": 0.00433,
3037
+ "grad_norm": 0.578125,
3038
+ "learning_rate": 9.999537396568685e-06,
3039
+ "loss": 1.5269,
3040
+ "step": 433
3041
+ },
3042
+ {
3043
+ "epoch": 0.00434,
3044
+ "grad_norm": 0.64453125,
3045
+ "learning_rate": 9.999535257398058e-06,
3046
+ "loss": 1.562,
3047
+ "step": 434
3048
+ },
3049
+ {
3050
+ "epoch": 0.00435,
3051
+ "grad_norm": 0.60546875,
3052
+ "learning_rate": 9.99953311329309e-06,
3053
+ "loss": 1.4944,
3054
+ "step": 435
3055
+ },
3056
+ {
3057
+ "epoch": 0.00436,
3058
+ "grad_norm": 0.62890625,
3059
+ "learning_rate": 9.99953096425378e-06,
3060
+ "loss": 1.487,
3061
+ "step": 436
3062
+ },
3063
+ {
3064
+ "epoch": 0.00437,
3065
+ "grad_norm": 0.6171875,
3066
+ "learning_rate": 9.999528810280128e-06,
3067
+ "loss": 1.5033,
3068
+ "step": 437
3069
+ },
3070
+ {
3071
+ "epoch": 0.00438,
3072
+ "grad_norm": 0.59765625,
3073
+ "learning_rate": 9.99952665137214e-06,
3074
+ "loss": 1.5232,
3075
+ "step": 438
3076
+ },
3077
+ {
3078
+ "epoch": 0.00439,
3079
+ "grad_norm": 0.62890625,
3080
+ "learning_rate": 9.999524487529817e-06,
3081
+ "loss": 1.5764,
3082
+ "step": 439
3083
+ },
3084
+ {
3085
+ "epoch": 0.0044,
3086
+ "grad_norm": 0.578125,
3087
+ "learning_rate": 9.99952231875316e-06,
3088
+ "loss": 1.5068,
3089
+ "step": 440
3090
+ },
3091
+ {
3092
+ "epoch": 0.00441,
3093
+ "grad_norm": 0.625,
3094
+ "learning_rate": 9.999520145042174e-06,
3095
+ "loss": 1.5465,
3096
+ "step": 441
3097
+ },
3098
+ {
3099
+ "epoch": 0.00442,
3100
+ "grad_norm": 0.609375,
3101
+ "learning_rate": 9.999517966396859e-06,
3102
+ "loss": 1.5235,
3103
+ "step": 442
3104
+ },
3105
+ {
3106
+ "epoch": 0.00443,
3107
+ "grad_norm": 0.58984375,
3108
+ "learning_rate": 9.999515782817217e-06,
3109
+ "loss": 1.5467,
3110
+ "step": 443
3111
+ },
3112
+ {
3113
+ "epoch": 0.00444,
3114
+ "grad_norm": 0.59375,
3115
+ "learning_rate": 9.999513594303251e-06,
3116
+ "loss": 1.4685,
3117
+ "step": 444
3118
+ },
3119
+ {
3120
+ "epoch": 0.00445,
3121
+ "grad_norm": 0.7109375,
3122
+ "learning_rate": 9.999511400854964e-06,
3123
+ "loss": 1.5144,
3124
+ "step": 445
3125
+ },
3126
+ {
3127
+ "epoch": 0.00446,
3128
+ "grad_norm": 0.5859375,
3129
+ "learning_rate": 9.999509202472356e-06,
3130
+ "loss": 1.5127,
3131
+ "step": 446
3132
+ },
3133
+ {
3134
+ "epoch": 0.00447,
3135
+ "grad_norm": 0.73828125,
3136
+ "learning_rate": 9.99950699915543e-06,
3137
+ "loss": 1.4352,
3138
+ "step": 447
3139
+ },
3140
+ {
3141
+ "epoch": 0.00448,
3142
+ "grad_norm": 0.6015625,
3143
+ "learning_rate": 9.99950479090419e-06,
3144
+ "loss": 1.568,
3145
+ "step": 448
3146
+ },
3147
+ {
3148
+ "epoch": 0.00449,
3149
+ "grad_norm": 0.57421875,
3150
+ "learning_rate": 9.999502577718634e-06,
3151
+ "loss": 1.4572,
3152
+ "step": 449
3153
+ },
3154
+ {
3155
+ "epoch": 0.0045,
3156
+ "grad_norm": 0.61328125,
3157
+ "learning_rate": 9.999500359598769e-06,
3158
+ "loss": 1.4915,
3159
+ "step": 450
3160
+ },
3161
+ {
3162
+ "epoch": 0.00451,
3163
+ "grad_norm": 0.5859375,
3164
+ "learning_rate": 9.999498136544594e-06,
3165
+ "loss": 1.5833,
3166
+ "step": 451
3167
+ },
3168
+ {
3169
+ "epoch": 0.00452,
3170
+ "grad_norm": 0.59375,
3171
+ "learning_rate": 9.999495908556112e-06,
3172
+ "loss": 1.5356,
3173
+ "step": 452
3174
+ },
3175
+ {
3176
+ "epoch": 0.00453,
3177
+ "grad_norm": 0.63671875,
3178
+ "learning_rate": 9.999493675633325e-06,
3179
+ "loss": 1.4961,
3180
+ "step": 453
3181
+ },
3182
+ {
3183
+ "epoch": 0.00454,
3184
+ "grad_norm": 0.59375,
3185
+ "learning_rate": 9.999491437776236e-06,
3186
+ "loss": 1.4887,
3187
+ "step": 454
3188
+ },
3189
+ {
3190
+ "epoch": 0.00455,
3191
+ "grad_norm": 0.62890625,
3192
+ "learning_rate": 9.999489194984846e-06,
3193
+ "loss": 1.5002,
3194
+ "step": 455
3195
+ },
3196
+ {
3197
+ "epoch": 0.00456,
3198
+ "grad_norm": 0.5703125,
3199
+ "learning_rate": 9.999486947259159e-06,
3200
+ "loss": 1.5023,
3201
+ "step": 456
3202
+ },
3203
+ {
3204
+ "epoch": 0.00457,
3205
+ "grad_norm": 0.61328125,
3206
+ "learning_rate": 9.999484694599174e-06,
3207
+ "loss": 1.5351,
3208
+ "step": 457
3209
+ },
3210
+ {
3211
+ "epoch": 0.00458,
3212
+ "grad_norm": 0.5625,
3213
+ "learning_rate": 9.999482437004898e-06,
3214
+ "loss": 1.45,
3215
+ "step": 458
3216
+ },
3217
+ {
3218
+ "epoch": 0.00459,
3219
+ "grad_norm": 0.61328125,
3220
+ "learning_rate": 9.99948017447633e-06,
3221
+ "loss": 1.496,
3222
+ "step": 459
3223
+ },
3224
+ {
3225
+ "epoch": 0.0046,
3226
+ "grad_norm": 0.59765625,
3227
+ "learning_rate": 9.999477907013473e-06,
3228
+ "loss": 1.6283,
3229
+ "step": 460
3230
+ },
3231
+ {
3232
+ "epoch": 0.00461,
3233
+ "grad_norm": 0.578125,
3234
+ "learning_rate": 9.999475634616328e-06,
3235
+ "loss": 1.419,
3236
+ "step": 461
3237
+ },
3238
+ {
3239
+ "epoch": 0.00462,
3240
+ "grad_norm": 0.66015625,
3241
+ "learning_rate": 9.999473357284898e-06,
3242
+ "loss": 1.6006,
3243
+ "step": 462
3244
+ },
3245
+ {
3246
+ "epoch": 0.00463,
3247
+ "grad_norm": 0.55859375,
3248
+ "learning_rate": 9.999471075019188e-06,
3249
+ "loss": 1.5436,
3250
+ "step": 463
3251
+ },
3252
+ {
3253
+ "epoch": 0.00464,
3254
+ "grad_norm": 0.58203125,
3255
+ "learning_rate": 9.999468787819195e-06,
3256
+ "loss": 1.5771,
3257
+ "step": 464
3258
+ },
3259
+ {
3260
+ "epoch": 0.00465,
3261
+ "grad_norm": 0.61328125,
3262
+ "learning_rate": 9.999466495684926e-06,
3263
+ "loss": 1.4976,
3264
+ "step": 465
3265
+ },
3266
+ {
3267
+ "epoch": 0.00466,
3268
+ "grad_norm": 0.6171875,
3269
+ "learning_rate": 9.999464198616381e-06,
3270
+ "loss": 1.4614,
3271
+ "step": 466
3272
+ },
3273
+ {
3274
+ "epoch": 0.00467,
3275
+ "grad_norm": 0.59375,
3276
+ "learning_rate": 9.999461896613563e-06,
3277
+ "loss": 1.573,
3278
+ "step": 467
3279
+ },
3280
+ {
3281
+ "epoch": 0.00468,
3282
+ "grad_norm": 0.578125,
3283
+ "learning_rate": 9.999459589676473e-06,
3284
+ "loss": 1.5366,
3285
+ "step": 468
3286
+ },
3287
+ {
3288
+ "epoch": 0.00469,
3289
+ "grad_norm": 0.5859375,
3290
+ "learning_rate": 9.999457277805113e-06,
3291
+ "loss": 1.4971,
3292
+ "step": 469
3293
+ },
3294
+ {
3295
+ "epoch": 0.0047,
3296
+ "grad_norm": 0.58203125,
3297
+ "learning_rate": 9.999454960999488e-06,
3298
+ "loss": 1.5383,
3299
+ "step": 470
3300
+ },
3301
+ {
3302
+ "epoch": 0.00471,
3303
+ "grad_norm": 0.58984375,
3304
+ "learning_rate": 9.999452639259599e-06,
3305
+ "loss": 1.5175,
3306
+ "step": 471
3307
+ },
3308
+ {
3309
+ "epoch": 0.00472,
3310
+ "grad_norm": 0.5625,
3311
+ "learning_rate": 9.999450312585449e-06,
3312
+ "loss": 1.481,
3313
+ "step": 472
3314
+ },
3315
+ {
3316
+ "epoch": 0.00473,
3317
+ "grad_norm": 0.60546875,
3318
+ "learning_rate": 9.999447980977037e-06,
3319
+ "loss": 1.501,
3320
+ "step": 473
3321
+ },
3322
+ {
3323
+ "epoch": 0.00474,
3324
+ "grad_norm": 0.8046875,
3325
+ "learning_rate": 9.99944564443437e-06,
3326
+ "loss": 1.5477,
3327
+ "step": 474
3328
+ },
3329
+ {
3330
+ "epoch": 0.00475,
3331
+ "grad_norm": 0.6015625,
3332
+ "learning_rate": 9.999443302957446e-06,
3333
+ "loss": 1.5133,
3334
+ "step": 475
3335
+ },
3336
+ {
3337
+ "epoch": 0.00476,
3338
+ "grad_norm": 0.6328125,
3339
+ "learning_rate": 9.99944095654627e-06,
3340
+ "loss": 1.5842,
3341
+ "step": 476
3342
+ },
3343
+ {
3344
+ "epoch": 0.00477,
3345
+ "grad_norm": 0.59375,
3346
+ "learning_rate": 9.999438605200841e-06,
3347
+ "loss": 1.4929,
3348
+ "step": 477
3349
+ },
3350
+ {
3351
+ "epoch": 0.00478,
3352
+ "grad_norm": 0.5703125,
3353
+ "learning_rate": 9.999436248921167e-06,
3354
+ "loss": 1.4826,
3355
+ "step": 478
3356
+ },
3357
+ {
3358
+ "epoch": 0.00479,
3359
+ "grad_norm": 0.578125,
3360
+ "learning_rate": 9.999433887707246e-06,
3361
+ "loss": 1.5088,
3362
+ "step": 479
3363
+ },
3364
+ {
3365
+ "epoch": 0.0048,
3366
+ "grad_norm": 0.578125,
3367
+ "learning_rate": 9.999431521559081e-06,
3368
+ "loss": 1.5755,
3369
+ "step": 480
3370
+ },
3371
+ {
3372
+ "epoch": 0.00481,
3373
+ "grad_norm": 0.578125,
3374
+ "learning_rate": 9.999429150476678e-06,
3375
+ "loss": 1.5071,
3376
+ "step": 481
3377
+ },
3378
+ {
3379
+ "epoch": 0.00482,
3380
+ "grad_norm": 0.59765625,
3381
+ "learning_rate": 9.999426774460032e-06,
3382
+ "loss": 1.6016,
3383
+ "step": 482
3384
+ },
3385
+ {
3386
+ "epoch": 0.00483,
3387
+ "grad_norm": 0.5859375,
3388
+ "learning_rate": 9.999424393509153e-06,
3389
+ "loss": 1.5384,
3390
+ "step": 483
3391
+ },
3392
+ {
3393
+ "epoch": 0.00484,
3394
+ "grad_norm": 0.61328125,
3395
+ "learning_rate": 9.999422007624038e-06,
3396
+ "loss": 1.4805,
3397
+ "step": 484
3398
+ },
3399
+ {
3400
+ "epoch": 0.00485,
3401
+ "grad_norm": 0.5859375,
3402
+ "learning_rate": 9.999419616804693e-06,
3403
+ "loss": 1.4774,
3404
+ "step": 485
3405
+ },
3406
+ {
3407
+ "epoch": 0.00486,
3408
+ "grad_norm": 0.58984375,
3409
+ "learning_rate": 9.999417221051116e-06,
3410
+ "loss": 1.4592,
3411
+ "step": 486
3412
+ },
3413
+ {
3414
+ "epoch": 0.00487,
3415
+ "grad_norm": 0.59375,
3416
+ "learning_rate": 9.999414820363313e-06,
3417
+ "loss": 1.5434,
3418
+ "step": 487
3419
+ },
3420
+ {
3421
+ "epoch": 0.00488,
3422
+ "grad_norm": 0.7421875,
3423
+ "learning_rate": 9.999412414741286e-06,
3424
+ "loss": 1.5352,
3425
+ "step": 488
3426
+ },
3427
+ {
3428
+ "epoch": 0.00489,
3429
+ "grad_norm": 0.64453125,
3430
+ "learning_rate": 9.999410004185038e-06,
3431
+ "loss": 1.4044,
3432
+ "step": 489
3433
+ },
3434
+ {
3435
+ "epoch": 0.0049,
3436
+ "grad_norm": 0.58984375,
3437
+ "learning_rate": 9.999407588694568e-06,
3438
+ "loss": 1.4273,
3439
+ "step": 490
3440
+ },
3441
+ {
3442
+ "epoch": 0.00491,
3443
+ "grad_norm": 0.58203125,
3444
+ "learning_rate": 9.99940516826988e-06,
3445
+ "loss": 1.5409,
3446
+ "step": 491
3447
+ },
3448
+ {
3449
+ "epoch": 0.00492,
3450
+ "grad_norm": 0.6015625,
3451
+ "learning_rate": 9.999402742910977e-06,
3452
+ "loss": 1.5455,
3453
+ "step": 492
3454
+ },
3455
+ {
3456
+ "epoch": 0.00493,
3457
+ "grad_norm": 0.62890625,
3458
+ "learning_rate": 9.999400312617863e-06,
3459
+ "loss": 1.461,
3460
+ "step": 493
3461
+ },
3462
+ {
3463
+ "epoch": 0.00494,
3464
+ "grad_norm": 0.60546875,
3465
+ "learning_rate": 9.999397877390538e-06,
3466
+ "loss": 1.446,
3467
+ "step": 494
3468
+ },
3469
+ {
3470
+ "epoch": 0.00495,
3471
+ "grad_norm": 0.58984375,
3472
+ "learning_rate": 9.999395437229004e-06,
3473
+ "loss": 1.5338,
3474
+ "step": 495
3475
+ },
3476
+ {
3477
+ "epoch": 0.00496,
3478
+ "grad_norm": 0.5859375,
3479
+ "learning_rate": 9.999392992133265e-06,
3480
+ "loss": 1.5947,
3481
+ "step": 496
3482
+ },
3483
+ {
3484
+ "epoch": 0.00497,
3485
+ "grad_norm": 0.58984375,
3486
+ "learning_rate": 9.999390542103325e-06,
3487
+ "loss": 1.5632,
3488
+ "step": 497
3489
+ },
3490
+ {
3491
+ "epoch": 0.00498,
3492
+ "grad_norm": 0.5703125,
3493
+ "learning_rate": 9.999388087139182e-06,
3494
+ "loss": 1.441,
3495
+ "step": 498
3496
+ },
3497
+ {
3498
+ "epoch": 0.00499,
3499
+ "grad_norm": 0.62109375,
3500
+ "learning_rate": 9.99938562724084e-06,
3501
+ "loss": 1.5702,
3502
+ "step": 499
3503
+ },
3504
+ {
3505
+ "epoch": 0.005,
3506
+ "grad_norm": 0.60546875,
3507
+ "learning_rate": 9.999383162408303e-06,
3508
+ "loss": 1.5134,
3509
+ "step": 500
3510
+ }
3511
+ ],
3512
+ "logging_steps": 1.0,
3513
+ "max_steps": 100000,
3514
+ "num_input_tokens_seen": 0,
3515
+ "num_train_epochs": 9223372036854775807,
3516
+ "save_steps": 50,
3517
+ "stateful_callbacks": {
3518
+ "TrainerControl": {
3519
+ "args": {
3520
+ "should_epoch_stop": false,
3521
+ "should_evaluate": false,
3522
+ "should_log": false,
3523
+ "should_save": true,
3524
+ "should_training_stop": false
3525
+ },
3526
+ "attributes": {}
3527
+ }
3528
+ },
3529
+ "total_flos": 1.1527564296192e+19,
3530
+ "train_batch_size": 1,
3531
+ "trial_name": null,
3532
+ "trial_params": null
3533
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:489201d0ef80ec44754ed9b7096bc634ab56fa8d1c361078d73aa8493edb9c66
3
+ size 5752