JakeOh commited on
Commit
98fb770
·
verified ·
1 Parent(s): fea3e2d

Delete checkpoint-2115

Browse files
checkpoint-2115/config.json DELETED
@@ -1,36 +0,0 @@
1
- {
2
- "_name_or_path": "meta-llama/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
- "head_dim": 128,
11
- "hidden_act": "silu",
12
- "hidden_size": 4096,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 14336,
15
- "max_position_embeddings": 131072,
16
- "mlp_bias": false,
17
- "model_type": "llama",
18
- "num_attention_heads": 32,
19
- "num_hidden_layers": 32,
20
- "num_key_value_heads": 8,
21
- "pretraining_tp": 1,
22
- "rms_norm_eps": 1e-05,
23
- "rope_scaling": {
24
- "factor": 8.0,
25
- "high_freq_factor": 4.0,
26
- "low_freq_factor": 1.0,
27
- "original_max_position_embeddings": 8192,
28
- "rope_type": "llama3"
29
- },
30
- "rope_theta": 500000.0,
31
- "tie_word_embeddings": false,
32
- "torch_dtype": "bfloat16",
33
- "transformers_version": "4.47.1",
34
- "use_cache": false,
35
- "vocab_size": 128256
36
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2115/generation_config.json DELETED
@@ -1,9 +0,0 @@
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": "4.47.1"
9
- }
 
 
 
 
 
 
 
 
 
 
checkpoint-2115/model-00001-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7c5a2db547de10365c6a1827fb8297d823813750926008448386447084fe2aa
3
- size 4976698672
 
 
 
 
checkpoint-2115/model-00002-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9a5bff2afef408387a21969b8136aa90978a0b91dc65666bad0f000889334e2
3
- size 4999802720
 
 
 
 
checkpoint-2115/model-00003-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:35dbad3d0ba593f5626ec27dfa83febf29bc5ef9f345767104278c4b4c7cdcee
3
- size 4915916176
 
 
 
 
checkpoint-2115/model-00004-of-00004.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:af41fe96408782f123f143b1bf67df9e07af8ad15f6422cb0c98a0d9d4691aae
3
- size 1168138808
 
 
 
 
checkpoint-2115/model.safetensors.index.json DELETED
@@ -1,298 +0,0 @@
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-2115/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:49c7f47e2b473bc80ee57f716e139616dbdaa7e4910b9f0937fc4070cffd4a10
3
- size 32121299754
 
 
 
 
checkpoint-2115/rng_state_0.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:feb6462d333dbc5bb5e497ea9b0adb960f7616f79e6eea63222de6d5bd559516
3
- size 15984
 
 
 
 
checkpoint-2115/rng_state_1.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b045e1bfa728f51c8b51ab0faa20b128a4fbd350da006b9b39a19e24abdf5a74
3
- size 15984
 
 
 
 
checkpoint-2115/rng_state_2.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f76a3d058d2628a61848c2441d313f251278bd8f74ce43dc44d8cd8ad3e619a8
3
- size 15984
 
 
 
 
checkpoint-2115/rng_state_3.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7f72fc498e6eaa671cdc0e8a627a668b8ef607063a22ddb4edbc05e791be830
3
- size 15984
 
 
 
 
checkpoint-2115/rng_state_4.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:12889af98e175b734a788f4c5b8c4da91dd61ff3a05aaf61b9d4c66aa3dd8ad6
3
- size 15984
 
 
 
 
checkpoint-2115/rng_state_5.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe21a86abfceeac2cf2f48afd61a9a506cf61a287f3403f1adf391bb2ffa5a83
3
- size 15984
 
 
 
 
checkpoint-2115/rng_state_6.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:73488bec91f9dee6d8105d06f99edaf4d27b6b064250d4c7023f33285b2f3132
3
- size 15984
 
 
 
 
checkpoint-2115/rng_state_7.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:edf6ee1cc2e1325b428a21172ec4e61b7220c5489751ea11c06bb66c77a0cd08
3
- size 15984
 
 
 
 
checkpoint-2115/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:15bc5944feb40cabcfc84cf3207fd5bdf0fab87865654db09d523ce37b82fd39
3
- size 1064
 
 
 
 
checkpoint-2115/special_tokens_map.json DELETED
@@ -1,17 +0,0 @@
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-2115/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
- size 17209920
 
 
 
 
checkpoint-2115/tokenizer_config.json DELETED
@@ -1,2064 +0,0 @@
1
- {
2
- "added_tokens_decoder": {
3
- "128000": {
4
- "content": "<|begin_of_text|>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "128001": {
12
- "content": "<|end_of_text|>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "128002": {
20
- "content": "<|reserved_special_token_0|>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "128003": {
28
- "content": "<|reserved_special_token_1|>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "128004": {
36
- "content": "<|finetune_right_pad_id|>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "128005": {
44
- "content": "<|reserved_special_token_2|>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "128006": {
52
- "content": "<|start_header_id|>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "128007": {
60
- "content": "<|end_header_id|>",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "128008": {
68
- "content": "<|eom_id|>",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "128009": {
76
- "content": "<|eot_id|>",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": true
82
- },
83
- "128010": {
84
- "content": "<|python_tag|>",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- },
91
- "128011": {
92
- "content": "<|reserved_special_token_3|>",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": true
98
- },
99
- "128012": {
100
- "content": "<|reserved_special_token_4|>",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": true
106
- },
107
- "128013": {
108
- "content": "<|reserved_special_token_5|>",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "128014": {
116
- "content": "<|reserved_special_token_6|>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "128015": {
124
- "content": "<|reserved_special_token_7|>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "128016": {
132
- "content": "<|reserved_special_token_8|>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "128017": {
140
- "content": "<|reserved_special_token_9|>",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "128018": {
148
- "content": "<|reserved_special_token_10|>",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "128019": {
156
- "content": "<|reserved_special_token_11|>",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "128020": {
164
- "content": "<|reserved_special_token_12|>",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "128021": {
172
- "content": "<|reserved_special_token_13|>",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "128022": {
180
- "content": "<|reserved_special_token_14|>",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "128023": {
188
- "content": "<|reserved_special_token_15|>",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "128024": {
196
- "content": "<|reserved_special_token_16|>",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "128025": {
204
- "content": "<|reserved_special_token_17|>",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- },
211
- "128026": {
212
- "content": "<|reserved_special_token_18|>",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": true
218
- },
219
- "128027": {
220
- "content": "<|reserved_special_token_19|>",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "128028": {
228
- "content": "<|reserved_special_token_20|>",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "128029": {
236
- "content": "<|reserved_special_token_21|>",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "128030": {
244
- "content": "<|reserved_special_token_22|>",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "128031": {
252
- "content": "<|reserved_special_token_23|>",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "128032": {
260
- "content": "<|reserved_special_token_24|>",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "128033": {
268
- "content": "<|reserved_special_token_25|>",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": true
274
- },
275
- "128034": {
276
- "content": "<|reserved_special_token_26|>",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": true
282
- },
283
- "128035": {
284
- "content": "<|reserved_special_token_27|>",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": true
290
- },
291
- "128036": {
292
- "content": "<|reserved_special_token_28|>",
293
- "lstrip": false,
294
- "normalized": false,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": true
298
- },
299
- "128037": {
300
- "content": "<|reserved_special_token_29|>",
301
- "lstrip": false,
302
- "normalized": false,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": true
306
- },
307
- "128038": {
308
- "content": "<|reserved_special_token_30|>",
309
- "lstrip": false,
310
- "normalized": false,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": true
314
- },
315
- "128039": {
316
- "content": "<|reserved_special_token_31|>",
317
- "lstrip": false,
318
- "normalized": false,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": true
322
- },
323
- "128040": {
324
- "content": "<|reserved_special_token_32|>",
325
- "lstrip": false,
326
- "normalized": false,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": true
330
- },
331
- "128041": {
332
- "content": "<|reserved_special_token_33|>",
333
- "lstrip": false,
334
- "normalized": false,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": true
338
- },
339
- "128042": {
340
- "content": "<|reserved_special_token_34|>",
341
- "lstrip": false,
342
- "normalized": false,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": true
346
- },
347
- "128043": {
348
- "content": "<|reserved_special_token_35|>",
349
- "lstrip": false,
350
- "normalized": false,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": true
354
- },
355
- "128044": {
356
- "content": "<|reserved_special_token_36|>",
357
- "lstrip": false,
358
- "normalized": false,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": true
362
- },
363
- "128045": {
364
- "content": "<|reserved_special_token_37|>",
365
- "lstrip": false,
366
- "normalized": false,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": true
370
- },
371
- "128046": {
372
- "content": "<|reserved_special_token_38|>",
373
- "lstrip": false,
374
- "normalized": false,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": true
378
- },
379
- "128047": {
380
- "content": "<|reserved_special_token_39|>",
381
- "lstrip": false,
382
- "normalized": false,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": true
386
- },
387
- "128048": {
388
- "content": "<|reserved_special_token_40|>",
389
- "lstrip": false,
390
- "normalized": false,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": true
394
- },
395
- "128049": {
396
- "content": "<|reserved_special_token_41|>",
397
- "lstrip": false,
398
- "normalized": false,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": true
402
- },
403
- "128050": {
404
- "content": "<|reserved_special_token_42|>",
405
- "lstrip": false,
406
- "normalized": false,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": true
410
- },
411
- "128051": {
412
- "content": "<|reserved_special_token_43|>",
413
- "lstrip": false,
414
- "normalized": false,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": true
418
- },
419
- "128052": {
420
- "content": "<|reserved_special_token_44|>",
421
- "lstrip": false,
422
- "normalized": false,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": true
426
- },
427
- "128053": {
428
- "content": "<|reserved_special_token_45|>",
429
- "lstrip": false,
430
- "normalized": false,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": true
434
- },
435
- "128054": {
436
- "content": "<|reserved_special_token_46|>",
437
- "lstrip": false,
438
- "normalized": false,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": true
442
- },
443
- "128055": {
444
- "content": "<|reserved_special_token_47|>",
445
- "lstrip": false,
446
- "normalized": false,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": true
450
- },
451
- "128056": {
452
- "content": "<|reserved_special_token_48|>",
453
- "lstrip": false,
454
- "normalized": false,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": true
458
- },
459
- "128057": {
460
- "content": "<|reserved_special_token_49|>",
461
- "lstrip": false,
462
- "normalized": false,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": true
466
- },
467
- "128058": {
468
- "content": "<|reserved_special_token_50|>",
469
- "lstrip": false,
470
- "normalized": false,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": true
474
- },
475
- "128059": {
476
- "content": "<|reserved_special_token_51|>",
477
- "lstrip": false,
478
- "normalized": false,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": true
482
- },
483
- "128060": {
484
- "content": "<|reserved_special_token_52|>",
485
- "lstrip": false,
486
- "normalized": false,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": true
490
- },
491
- "128061": {
492
- "content": "<|reserved_special_token_53|>",
493
- "lstrip": false,
494
- "normalized": false,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": true
498
- },
499
- "128062": {
500
- "content": "<|reserved_special_token_54|>",
501
- "lstrip": false,
502
- "normalized": false,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": true
506
- },
507
- "128063": {
508
- "content": "<|reserved_special_token_55|>",
509
- "lstrip": false,
510
- "normalized": false,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": true
514
- },
515
- "128064": {
516
- "content": "<|reserved_special_token_56|>",
517
- "lstrip": false,
518
- "normalized": false,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": true
522
- },
523
- "128065": {
524
- "content": "<|reserved_special_token_57|>",
525
- "lstrip": false,
526
- "normalized": false,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": true
530
- },
531
- "128066": {
532
- "content": "<|reserved_special_token_58|>",
533
- "lstrip": false,
534
- "normalized": false,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": true
538
- },
539
- "128067": {
540
- "content": "<|reserved_special_token_59|>",
541
- "lstrip": false,
542
- "normalized": false,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": true
546
- },
547
- "128068": {
548
- "content": "<|reserved_special_token_60|>",
549
- "lstrip": false,
550
- "normalized": false,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": true
554
- },
555
- "128069": {
556
- "content": "<|reserved_special_token_61|>",
557
- "lstrip": false,
558
- "normalized": false,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": true
562
- },
563
- "128070": {
564
- "content": "<|reserved_special_token_62|>",
565
- "lstrip": false,
566
- "normalized": false,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": true
570
- },
571
- "128071": {
572
- "content": "<|reserved_special_token_63|>",
573
- "lstrip": false,
574
- "normalized": false,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": true
578
- },
579
- "128072": {
580
- "content": "<|reserved_special_token_64|>",
581
- "lstrip": false,
582
- "normalized": false,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": true
586
- },
587
- "128073": {
588
- "content": "<|reserved_special_token_65|>",
589
- "lstrip": false,
590
- "normalized": false,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": true
594
- },
595
- "128074": {
596
- "content": "<|reserved_special_token_66|>",
597
- "lstrip": false,
598
- "normalized": false,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": true
602
- },
603
- "128075": {
604
- "content": "<|reserved_special_token_67|>",
605
- "lstrip": false,
606
- "normalized": false,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": true
610
- },
611
- "128076": {
612
- "content": "<|reserved_special_token_68|>",
613
- "lstrip": false,
614
- "normalized": false,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": true
618
- },
619
- "128077": {
620
- "content": "<|reserved_special_token_69|>",
621
- "lstrip": false,
622
- "normalized": false,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": true
626
- },
627
- "128078": {
628
- "content": "<|reserved_special_token_70|>",
629
- "lstrip": false,
630
- "normalized": false,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": true
634
- },
635
- "128079": {
636
- "content": "<|reserved_special_token_71|>",
637
- "lstrip": false,
638
- "normalized": false,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": true
642
- },
643
- "128080": {
644
- "content": "<|reserved_special_token_72|>",
645
- "lstrip": false,
646
- "normalized": false,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": true
650
- },
651
- "128081": {
652
- "content": "<|reserved_special_token_73|>",
653
- "lstrip": false,
654
- "normalized": false,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": true
658
- },
659
- "128082": {
660
- "content": "<|reserved_special_token_74|>",
661
- "lstrip": false,
662
- "normalized": false,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": true
666
- },
667
- "128083": {
668
- "content": "<|reserved_special_token_75|>",
669
- "lstrip": false,
670
- "normalized": false,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": true
674
- },
675
- "128084": {
676
- "content": "<|reserved_special_token_76|>",
677
- "lstrip": false,
678
- "normalized": false,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": true
682
- },
683
- "128085": {
684
- "content": "<|reserved_special_token_77|>",
685
- "lstrip": false,
686
- "normalized": false,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": true
690
- },
691
- "128086": {
692
- "content": "<|reserved_special_token_78|>",
693
- "lstrip": false,
694
- "normalized": false,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": true
698
- },
699
- "128087": {
700
- "content": "<|reserved_special_token_79|>",
701
- "lstrip": false,
702
- "normalized": false,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": true
706
- },
707
- "128088": {
708
- "content": "<|reserved_special_token_80|>",
709
- "lstrip": false,
710
- "normalized": false,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": true
714
- },
715
- "128089": {
716
- "content": "<|reserved_special_token_81|>",
717
- "lstrip": false,
718
- "normalized": false,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": true
722
- },
723
- "128090": {
724
- "content": "<|reserved_special_token_82|>",
725
- "lstrip": false,
726
- "normalized": false,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": true
730
- },
731
- "128091": {
732
- "content": "<|reserved_special_token_83|>",
733
- "lstrip": false,
734
- "normalized": false,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": true
738
- },
739
- "128092": {
740
- "content": "<|reserved_special_token_84|>",
741
- "lstrip": false,
742
- "normalized": false,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": true
746
- },
747
- "128093": {
748
- "content": "<|reserved_special_token_85|>",
749
- "lstrip": false,
750
- "normalized": false,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": true
754
- },
755
- "128094": {
756
- "content": "<|reserved_special_token_86|>",
757
- "lstrip": false,
758
- "normalized": false,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": true
762
- },
763
- "128095": {
764
- "content": "<|reserved_special_token_87|>",
765
- "lstrip": false,
766
- "normalized": false,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": true
770
- },
771
- "128096": {
772
- "content": "<|reserved_special_token_88|>",
773
- "lstrip": false,
774
- "normalized": false,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": true
778
- },
779
- "128097": {
780
- "content": "<|reserved_special_token_89|>",
781
- "lstrip": false,
782
- "normalized": false,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": true
786
- },
787
- "128098": {
788
- "content": "<|reserved_special_token_90|>",
789
- "lstrip": false,
790
- "normalized": false,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": true
794
- },
795
- "128099": {
796
- "content": "<|reserved_special_token_91|>",
797
- "lstrip": false,
798
- "normalized": false,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": true
802
- },
803
- "128100": {
804
- "content": "<|reserved_special_token_92|>",
805
- "lstrip": false,
806
- "normalized": false,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": true
810
- },
811
- "128101": {
812
- "content": "<|reserved_special_token_93|>",
813
- "lstrip": false,
814
- "normalized": false,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": true
818
- },
819
- "128102": {
820
- "content": "<|reserved_special_token_94|>",
821
- "lstrip": false,
822
- "normalized": false,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": true
826
- },
827
- "128103": {
828
- "content": "<|reserved_special_token_95|>",
829
- "lstrip": false,
830
- "normalized": false,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": true
834
- },
835
- "128104": {
836
- "content": "<|reserved_special_token_96|>",
837
- "lstrip": false,
838
- "normalized": false,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": true
842
- },
843
- "128105": {
844
- "content": "<|reserved_special_token_97|>",
845
- "lstrip": false,
846
- "normalized": false,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": true
850
- },
851
- "128106": {
852
- "content": "<|reserved_special_token_98|>",
853
- "lstrip": false,
854
- "normalized": false,
855
- "rstrip": false,
856
- "single_word": false,
857
- "special": true
858
- },
859
- "128107": {
860
- "content": "<|reserved_special_token_99|>",
861
- "lstrip": false,
862
- "normalized": false,
863
- "rstrip": false,
864
- "single_word": false,
865
- "special": true
866
- },
867
- "128108": {
868
- "content": "<|reserved_special_token_100|>",
869
- "lstrip": false,
870
- "normalized": false,
871
- "rstrip": false,
872
- "single_word": false,
873
- "special": true
874
- },
875
- "128109": {
876
- "content": "<|reserved_special_token_101|>",
877
- "lstrip": false,
878
- "normalized": false,
879
- "rstrip": false,
880
- "single_word": false,
881
- "special": true
882
- },
883
- "128110": {
884
- "content": "<|reserved_special_token_102|>",
885
- "lstrip": false,
886
- "normalized": false,
887
- "rstrip": false,
888
- "single_word": false,
889
- "special": true
890
- },
891
- "128111": {
892
- "content": "<|reserved_special_token_103|>",
893
- "lstrip": false,
894
- "normalized": false,
895
- "rstrip": false,
896
- "single_word": false,
897
- "special": true
898
- },
899
- "128112": {
900
- "content": "<|reserved_special_token_104|>",
901
- "lstrip": false,
902
- "normalized": false,
903
- "rstrip": false,
904
- "single_word": false,
905
- "special": true
906
- },
907
- "128113": {
908
- "content": "<|reserved_special_token_105|>",
909
- "lstrip": false,
910
- "normalized": false,
911
- "rstrip": false,
912
- "single_word": false,
913
- "special": true
914
- },
915
- "128114": {
916
- "content": "<|reserved_special_token_106|>",
917
- "lstrip": false,
918
- "normalized": false,
919
- "rstrip": false,
920
- "single_word": false,
921
- "special": true
922
- },
923
- "128115": {
924
- "content": "<|reserved_special_token_107|>",
925
- "lstrip": false,
926
- "normalized": false,
927
- "rstrip": false,
928
- "single_word": false,
929
- "special": true
930
- },
931
- "128116": {
932
- "content": "<|reserved_special_token_108|>",
933
- "lstrip": false,
934
- "normalized": false,
935
- "rstrip": false,
936
- "single_word": false,
937
- "special": true
938
- },
939
- "128117": {
940
- "content": "<|reserved_special_token_109|>",
941
- "lstrip": false,
942
- "normalized": false,
943
- "rstrip": false,
944
- "single_word": false,
945
- "special": true
946
- },
947
- "128118": {
948
- "content": "<|reserved_special_token_110|>",
949
- "lstrip": false,
950
- "normalized": false,
951
- "rstrip": false,
952
- "single_word": false,
953
- "special": true
954
- },
955
- "128119": {
956
- "content": "<|reserved_special_token_111|>",
957
- "lstrip": false,
958
- "normalized": false,
959
- "rstrip": false,
960
- "single_word": false,
961
- "special": true
962
- },
963
- "128120": {
964
- "content": "<|reserved_special_token_112|>",
965
- "lstrip": false,
966
- "normalized": false,
967
- "rstrip": false,
968
- "single_word": false,
969
- "special": true
970
- },
971
- "128121": {
972
- "content": "<|reserved_special_token_113|>",
973
- "lstrip": false,
974
- "normalized": false,
975
- "rstrip": false,
976
- "single_word": false,
977
- "special": true
978
- },
979
- "128122": {
980
- "content": "<|reserved_special_token_114|>",
981
- "lstrip": false,
982
- "normalized": false,
983
- "rstrip": false,
984
- "single_word": false,
985
- "special": true
986
- },
987
- "128123": {
988
- "content": "<|reserved_special_token_115|>",
989
- "lstrip": false,
990
- "normalized": false,
991
- "rstrip": false,
992
- "single_word": false,
993
- "special": true
994
- },
995
- "128124": {
996
- "content": "<|reserved_special_token_116|>",
997
- "lstrip": false,
998
- "normalized": false,
999
- "rstrip": false,
1000
- "single_word": false,
1001
- "special": true
1002
- },
1003
- "128125": {
1004
- "content": "<|reserved_special_token_117|>",
1005
- "lstrip": false,
1006
- "normalized": false,
1007
- "rstrip": false,
1008
- "single_word": false,
1009
- "special": true
1010
- },
1011
- "128126": {
1012
- "content": "<|reserved_special_token_118|>",
1013
- "lstrip": false,
1014
- "normalized": false,
1015
- "rstrip": false,
1016
- "single_word": false,
1017
- "special": true
1018
- },
1019
- "128127": {
1020
- "content": "<|reserved_special_token_119|>",
1021
- "lstrip": false,
1022
- "normalized": false,
1023
- "rstrip": false,
1024
- "single_word": false,
1025
- "special": true
1026
- },
1027
- "128128": {
1028
- "content": "<|reserved_special_token_120|>",
1029
- "lstrip": false,
1030
- "normalized": false,
1031
- "rstrip": false,
1032
- "single_word": false,
1033
- "special": true
1034
- },
1035
- "128129": {
1036
- "content": "<|reserved_special_token_121|>",
1037
- "lstrip": false,
1038
- "normalized": false,
1039
- "rstrip": false,
1040
- "single_word": false,
1041
- "special": true
1042
- },
1043
- "128130": {
1044
- "content": "<|reserved_special_token_122|>",
1045
- "lstrip": false,
1046
- "normalized": false,
1047
- "rstrip": false,
1048
- "single_word": false,
1049
- "special": true
1050
- },
1051
- "128131": {
1052
- "content": "<|reserved_special_token_123|>",
1053
- "lstrip": false,
1054
- "normalized": false,
1055
- "rstrip": false,
1056
- "single_word": false,
1057
- "special": true
1058
- },
1059
- "128132": {
1060
- "content": "<|reserved_special_token_124|>",
1061
- "lstrip": false,
1062
- "normalized": false,
1063
- "rstrip": false,
1064
- "single_word": false,
1065
- "special": true
1066
- },
1067
- "128133": {
1068
- "content": "<|reserved_special_token_125|>",
1069
- "lstrip": false,
1070
- "normalized": false,
1071
- "rstrip": false,
1072
- "single_word": false,
1073
- "special": true
1074
- },
1075
- "128134": {
1076
- "content": "<|reserved_special_token_126|>",
1077
- "lstrip": false,
1078
- "normalized": false,
1079
- "rstrip": false,
1080
- "single_word": false,
1081
- "special": true
1082
- },
1083
- "128135": {
1084
- "content": "<|reserved_special_token_127|>",
1085
- "lstrip": false,
1086
- "normalized": false,
1087
- "rstrip": false,
1088
- "single_word": false,
1089
- "special": true
1090
- },
1091
- "128136": {
1092
- "content": "<|reserved_special_token_128|>",
1093
- "lstrip": false,
1094
- "normalized": false,
1095
- "rstrip": false,
1096
- "single_word": false,
1097
- "special": true
1098
- },
1099
- "128137": {
1100
- "content": "<|reserved_special_token_129|>",
1101
- "lstrip": false,
1102
- "normalized": false,
1103
- "rstrip": false,
1104
- "single_word": false,
1105
- "special": true
1106
- },
1107
- "128138": {
1108
- "content": "<|reserved_special_token_130|>",
1109
- "lstrip": false,
1110
- "normalized": false,
1111
- "rstrip": false,
1112
- "single_word": false,
1113
- "special": true
1114
- },
1115
- "128139": {
1116
- "content": "<|reserved_special_token_131|>",
1117
- "lstrip": false,
1118
- "normalized": false,
1119
- "rstrip": false,
1120
- "single_word": false,
1121
- "special": true
1122
- },
1123
- "128140": {
1124
- "content": "<|reserved_special_token_132|>",
1125
- "lstrip": false,
1126
- "normalized": false,
1127
- "rstrip": false,
1128
- "single_word": false,
1129
- "special": true
1130
- },
1131
- "128141": {
1132
- "content": "<|reserved_special_token_133|>",
1133
- "lstrip": false,
1134
- "normalized": false,
1135
- "rstrip": false,
1136
- "single_word": false,
1137
- "special": true
1138
- },
1139
- "128142": {
1140
- "content": "<|reserved_special_token_134|>",
1141
- "lstrip": false,
1142
- "normalized": false,
1143
- "rstrip": false,
1144
- "single_word": false,
1145
- "special": true
1146
- },
1147
- "128143": {
1148
- "content": "<|reserved_special_token_135|>",
1149
- "lstrip": false,
1150
- "normalized": false,
1151
- "rstrip": false,
1152
- "single_word": false,
1153
- "special": true
1154
- },
1155
- "128144": {
1156
- "content": "<|reserved_special_token_136|>",
1157
- "lstrip": false,
1158
- "normalized": false,
1159
- "rstrip": false,
1160
- "single_word": false,
1161
- "special": true
1162
- },
1163
- "128145": {
1164
- "content": "<|reserved_special_token_137|>",
1165
- "lstrip": false,
1166
- "normalized": false,
1167
- "rstrip": false,
1168
- "single_word": false,
1169
- "special": true
1170
- },
1171
- "128146": {
1172
- "content": "<|reserved_special_token_138|>",
1173
- "lstrip": false,
1174
- "normalized": false,
1175
- "rstrip": false,
1176
- "single_word": false,
1177
- "special": true
1178
- },
1179
- "128147": {
1180
- "content": "<|reserved_special_token_139|>",
1181
- "lstrip": false,
1182
- "normalized": false,
1183
- "rstrip": false,
1184
- "single_word": false,
1185
- "special": true
1186
- },
1187
- "128148": {
1188
- "content": "<|reserved_special_token_140|>",
1189
- "lstrip": false,
1190
- "normalized": false,
1191
- "rstrip": false,
1192
- "single_word": false,
1193
- "special": true
1194
- },
1195
- "128149": {
1196
- "content": "<|reserved_special_token_141|>",
1197
- "lstrip": false,
1198
- "normalized": false,
1199
- "rstrip": false,
1200
- "single_word": false,
1201
- "special": true
1202
- },
1203
- "128150": {
1204
- "content": "<|reserved_special_token_142|>",
1205
- "lstrip": false,
1206
- "normalized": false,
1207
- "rstrip": false,
1208
- "single_word": false,
1209
- "special": true
1210
- },
1211
- "128151": {
1212
- "content": "<|reserved_special_token_143|>",
1213
- "lstrip": false,
1214
- "normalized": false,
1215
- "rstrip": false,
1216
- "single_word": false,
1217
- "special": true
1218
- },
1219
- "128152": {
1220
- "content": "<|reserved_special_token_144|>",
1221
- "lstrip": false,
1222
- "normalized": false,
1223
- "rstrip": false,
1224
- "single_word": false,
1225
- "special": true
1226
- },
1227
- "128153": {
1228
- "content": "<|reserved_special_token_145|>",
1229
- "lstrip": false,
1230
- "normalized": false,
1231
- "rstrip": false,
1232
- "single_word": false,
1233
- "special": true
1234
- },
1235
- "128154": {
1236
- "content": "<|reserved_special_token_146|>",
1237
- "lstrip": false,
1238
- "normalized": false,
1239
- "rstrip": false,
1240
- "single_word": false,
1241
- "special": true
1242
- },
1243
- "128155": {
1244
- "content": "<|reserved_special_token_147|>",
1245
- "lstrip": false,
1246
- "normalized": false,
1247
- "rstrip": false,
1248
- "single_word": false,
1249
- "special": true
1250
- },
1251
- "128156": {
1252
- "content": "<|reserved_special_token_148|>",
1253
- "lstrip": false,
1254
- "normalized": false,
1255
- "rstrip": false,
1256
- "single_word": false,
1257
- "special": true
1258
- },
1259
- "128157": {
1260
- "content": "<|reserved_special_token_149|>",
1261
- "lstrip": false,
1262
- "normalized": false,
1263
- "rstrip": false,
1264
- "single_word": false,
1265
- "special": true
1266
- },
1267
- "128158": {
1268
- "content": "<|reserved_special_token_150|>",
1269
- "lstrip": false,
1270
- "normalized": false,
1271
- "rstrip": false,
1272
- "single_word": false,
1273
- "special": true
1274
- },
1275
- "128159": {
1276
- "content": "<|reserved_special_token_151|>",
1277
- "lstrip": false,
1278
- "normalized": false,
1279
- "rstrip": false,
1280
- "single_word": false,
1281
- "special": true
1282
- },
1283
- "128160": {
1284
- "content": "<|reserved_special_token_152|>",
1285
- "lstrip": false,
1286
- "normalized": false,
1287
- "rstrip": false,
1288
- "single_word": false,
1289
- "special": true
1290
- },
1291
- "128161": {
1292
- "content": "<|reserved_special_token_153|>",
1293
- "lstrip": false,
1294
- "normalized": false,
1295
- "rstrip": false,
1296
- "single_word": false,
1297
- "special": true
1298
- },
1299
- "128162": {
1300
- "content": "<|reserved_special_token_154|>",
1301
- "lstrip": false,
1302
- "normalized": false,
1303
- "rstrip": false,
1304
- "single_word": false,
1305
- "special": true
1306
- },
1307
- "128163": {
1308
- "content": "<|reserved_special_token_155|>",
1309
- "lstrip": false,
1310
- "normalized": false,
1311
- "rstrip": false,
1312
- "single_word": false,
1313
- "special": true
1314
- },
1315
- "128164": {
1316
- "content": "<|reserved_special_token_156|>",
1317
- "lstrip": false,
1318
- "normalized": false,
1319
- "rstrip": false,
1320
- "single_word": false,
1321
- "special": true
1322
- },
1323
- "128165": {
1324
- "content": "<|reserved_special_token_157|>",
1325
- "lstrip": false,
1326
- "normalized": false,
1327
- "rstrip": false,
1328
- "single_word": false,
1329
- "special": true
1330
- },
1331
- "128166": {
1332
- "content": "<|reserved_special_token_158|>",
1333
- "lstrip": false,
1334
- "normalized": false,
1335
- "rstrip": false,
1336
- "single_word": false,
1337
- "special": true
1338
- },
1339
- "128167": {
1340
- "content": "<|reserved_special_token_159|>",
1341
- "lstrip": false,
1342
- "normalized": false,
1343
- "rstrip": false,
1344
- "single_word": false,
1345
- "special": true
1346
- },
1347
- "128168": {
1348
- "content": "<|reserved_special_token_160|>",
1349
- "lstrip": false,
1350
- "normalized": false,
1351
- "rstrip": false,
1352
- "single_word": false,
1353
- "special": true
1354
- },
1355
- "128169": {
1356
- "content": "<|reserved_special_token_161|>",
1357
- "lstrip": false,
1358
- "normalized": false,
1359
- "rstrip": false,
1360
- "single_word": false,
1361
- "special": true
1362
- },
1363
- "128170": {
1364
- "content": "<|reserved_special_token_162|>",
1365
- "lstrip": false,
1366
- "normalized": false,
1367
- "rstrip": false,
1368
- "single_word": false,
1369
- "special": true
1370
- },
1371
- "128171": {
1372
- "content": "<|reserved_special_token_163|>",
1373
- "lstrip": false,
1374
- "normalized": false,
1375
- "rstrip": false,
1376
- "single_word": false,
1377
- "special": true
1378
- },
1379
- "128172": {
1380
- "content": "<|reserved_special_token_164|>",
1381
- "lstrip": false,
1382
- "normalized": false,
1383
- "rstrip": false,
1384
- "single_word": false,
1385
- "special": true
1386
- },
1387
- "128173": {
1388
- "content": "<|reserved_special_token_165|>",
1389
- "lstrip": false,
1390
- "normalized": false,
1391
- "rstrip": false,
1392
- "single_word": false,
1393
- "special": true
1394
- },
1395
- "128174": {
1396
- "content": "<|reserved_special_token_166|>",
1397
- "lstrip": false,
1398
- "normalized": false,
1399
- "rstrip": false,
1400
- "single_word": false,
1401
- "special": true
1402
- },
1403
- "128175": {
1404
- "content": "<|reserved_special_token_167|>",
1405
- "lstrip": false,
1406
- "normalized": false,
1407
- "rstrip": false,
1408
- "single_word": false,
1409
- "special": true
1410
- },
1411
- "128176": {
1412
- "content": "<|reserved_special_token_168|>",
1413
- "lstrip": false,
1414
- "normalized": false,
1415
- "rstrip": false,
1416
- "single_word": false,
1417
- "special": true
1418
- },
1419
- "128177": {
1420
- "content": "<|reserved_special_token_169|>",
1421
- "lstrip": false,
1422
- "normalized": false,
1423
- "rstrip": false,
1424
- "single_word": false,
1425
- "special": true
1426
- },
1427
- "128178": {
1428
- "content": "<|reserved_special_token_170|>",
1429
- "lstrip": false,
1430
- "normalized": false,
1431
- "rstrip": false,
1432
- "single_word": false,
1433
- "special": true
1434
- },
1435
- "128179": {
1436
- "content": "<|reserved_special_token_171|>",
1437
- "lstrip": false,
1438
- "normalized": false,
1439
- "rstrip": false,
1440
- "single_word": false,
1441
- "special": true
1442
- },
1443
- "128180": {
1444
- "content": "<|reserved_special_token_172|>",
1445
- "lstrip": false,
1446
- "normalized": false,
1447
- "rstrip": false,
1448
- "single_word": false,
1449
- "special": true
1450
- },
1451
- "128181": {
1452
- "content": "<|reserved_special_token_173|>",
1453
- "lstrip": false,
1454
- "normalized": false,
1455
- "rstrip": false,
1456
- "single_word": false,
1457
- "special": true
1458
- },
1459
- "128182": {
1460
- "content": "<|reserved_special_token_174|>",
1461
- "lstrip": false,
1462
- "normalized": false,
1463
- "rstrip": false,
1464
- "single_word": false,
1465
- "special": true
1466
- },
1467
- "128183": {
1468
- "content": "<|reserved_special_token_175|>",
1469
- "lstrip": false,
1470
- "normalized": false,
1471
- "rstrip": false,
1472
- "single_word": false,
1473
- "special": true
1474
- },
1475
- "128184": {
1476
- "content": "<|reserved_special_token_176|>",
1477
- "lstrip": false,
1478
- "normalized": false,
1479
- "rstrip": false,
1480
- "single_word": false,
1481
- "special": true
1482
- },
1483
- "128185": {
1484
- "content": "<|reserved_special_token_177|>",
1485
- "lstrip": false,
1486
- "normalized": false,
1487
- "rstrip": false,
1488
- "single_word": false,
1489
- "special": true
1490
- },
1491
- "128186": {
1492
- "content": "<|reserved_special_token_178|>",
1493
- "lstrip": false,
1494
- "normalized": false,
1495
- "rstrip": false,
1496
- "single_word": false,
1497
- "special": true
1498
- },
1499
- "128187": {
1500
- "content": "<|reserved_special_token_179|>",
1501
- "lstrip": false,
1502
- "normalized": false,
1503
- "rstrip": false,
1504
- "single_word": false,
1505
- "special": true
1506
- },
1507
- "128188": {
1508
- "content": "<|reserved_special_token_180|>",
1509
- "lstrip": false,
1510
- "normalized": false,
1511
- "rstrip": false,
1512
- "single_word": false,
1513
- "special": true
1514
- },
1515
- "128189": {
1516
- "content": "<|reserved_special_token_181|>",
1517
- "lstrip": false,
1518
- "normalized": false,
1519
- "rstrip": false,
1520
- "single_word": false,
1521
- "special": true
1522
- },
1523
- "128190": {
1524
- "content": "<|reserved_special_token_182|>",
1525
- "lstrip": false,
1526
- "normalized": false,
1527
- "rstrip": false,
1528
- "single_word": false,
1529
- "special": true
1530
- },
1531
- "128191": {
1532
- "content": "<|reserved_special_token_183|>",
1533
- "lstrip": false,
1534
- "normalized": false,
1535
- "rstrip": false,
1536
- "single_word": false,
1537
- "special": true
1538
- },
1539
- "128192": {
1540
- "content": "<|reserved_special_token_184|>",
1541
- "lstrip": false,
1542
- "normalized": false,
1543
- "rstrip": false,
1544
- "single_word": false,
1545
- "special": true
1546
- },
1547
- "128193": {
1548
- "content": "<|reserved_special_token_185|>",
1549
- "lstrip": false,
1550
- "normalized": false,
1551
- "rstrip": false,
1552
- "single_word": false,
1553
- "special": true
1554
- },
1555
- "128194": {
1556
- "content": "<|reserved_special_token_186|>",
1557
- "lstrip": false,
1558
- "normalized": false,
1559
- "rstrip": false,
1560
- "single_word": false,
1561
- "special": true
1562
- },
1563
- "128195": {
1564
- "content": "<|reserved_special_token_187|>",
1565
- "lstrip": false,
1566
- "normalized": false,
1567
- "rstrip": false,
1568
- "single_word": false,
1569
- "special": true
1570
- },
1571
- "128196": {
1572
- "content": "<|reserved_special_token_188|>",
1573
- "lstrip": false,
1574
- "normalized": false,
1575
- "rstrip": false,
1576
- "single_word": false,
1577
- "special": true
1578
- },
1579
- "128197": {
1580
- "content": "<|reserved_special_token_189|>",
1581
- "lstrip": false,
1582
- "normalized": false,
1583
- "rstrip": false,
1584
- "single_word": false,
1585
- "special": true
1586
- },
1587
- "128198": {
1588
- "content": "<|reserved_special_token_190|>",
1589
- "lstrip": false,
1590
- "normalized": false,
1591
- "rstrip": false,
1592
- "single_word": false,
1593
- "special": true
1594
- },
1595
- "128199": {
1596
- "content": "<|reserved_special_token_191|>",
1597
- "lstrip": false,
1598
- "normalized": false,
1599
- "rstrip": false,
1600
- "single_word": false,
1601
- "special": true
1602
- },
1603
- "128200": {
1604
- "content": "<|reserved_special_token_192|>",
1605
- "lstrip": false,
1606
- "normalized": false,
1607
- "rstrip": false,
1608
- "single_word": false,
1609
- "special": true
1610
- },
1611
- "128201": {
1612
- "content": "<|reserved_special_token_193|>",
1613
- "lstrip": false,
1614
- "normalized": false,
1615
- "rstrip": false,
1616
- "single_word": false,
1617
- "special": true
1618
- },
1619
- "128202": {
1620
- "content": "<|reserved_special_token_194|>",
1621
- "lstrip": false,
1622
- "normalized": false,
1623
- "rstrip": false,
1624
- "single_word": false,
1625
- "special": true
1626
- },
1627
- "128203": {
1628
- "content": "<|reserved_special_token_195|>",
1629
- "lstrip": false,
1630
- "normalized": false,
1631
- "rstrip": false,
1632
- "single_word": false,
1633
- "special": true
1634
- },
1635
- "128204": {
1636
- "content": "<|reserved_special_token_196|>",
1637
- "lstrip": false,
1638
- "normalized": false,
1639
- "rstrip": false,
1640
- "single_word": false,
1641
- "special": true
1642
- },
1643
- "128205": {
1644
- "content": "<|reserved_special_token_197|>",
1645
- "lstrip": false,
1646
- "normalized": false,
1647
- "rstrip": false,
1648
- "single_word": false,
1649
- "special": true
1650
- },
1651
- "128206": {
1652
- "content": "<|reserved_special_token_198|>",
1653
- "lstrip": false,
1654
- "normalized": false,
1655
- "rstrip": false,
1656
- "single_word": false,
1657
- "special": true
1658
- },
1659
- "128207": {
1660
- "content": "<|reserved_special_token_199|>",
1661
- "lstrip": false,
1662
- "normalized": false,
1663
- "rstrip": false,
1664
- "single_word": false,
1665
- "special": true
1666
- },
1667
- "128208": {
1668
- "content": "<|reserved_special_token_200|>",
1669
- "lstrip": false,
1670
- "normalized": false,
1671
- "rstrip": false,
1672
- "single_word": false,
1673
- "special": true
1674
- },
1675
- "128209": {
1676
- "content": "<|reserved_special_token_201|>",
1677
- "lstrip": false,
1678
- "normalized": false,
1679
- "rstrip": false,
1680
- "single_word": false,
1681
- "special": true
1682
- },
1683
- "128210": {
1684
- "content": "<|reserved_special_token_202|>",
1685
- "lstrip": false,
1686
- "normalized": false,
1687
- "rstrip": false,
1688
- "single_word": false,
1689
- "special": true
1690
- },
1691
- "128211": {
1692
- "content": "<|reserved_special_token_203|>",
1693
- "lstrip": false,
1694
- "normalized": false,
1695
- "rstrip": false,
1696
- "single_word": false,
1697
- "special": true
1698
- },
1699
- "128212": {
1700
- "content": "<|reserved_special_token_204|>",
1701
- "lstrip": false,
1702
- "normalized": false,
1703
- "rstrip": false,
1704
- "single_word": false,
1705
- "special": true
1706
- },
1707
- "128213": {
1708
- "content": "<|reserved_special_token_205|>",
1709
- "lstrip": false,
1710
- "normalized": false,
1711
- "rstrip": false,
1712
- "single_word": false,
1713
- "special": true
1714
- },
1715
- "128214": {
1716
- "content": "<|reserved_special_token_206|>",
1717
- "lstrip": false,
1718
- "normalized": false,
1719
- "rstrip": false,
1720
- "single_word": false,
1721
- "special": true
1722
- },
1723
- "128215": {
1724
- "content": "<|reserved_special_token_207|>",
1725
- "lstrip": false,
1726
- "normalized": false,
1727
- "rstrip": false,
1728
- "single_word": false,
1729
- "special": true
1730
- },
1731
- "128216": {
1732
- "content": "<|reserved_special_token_208|>",
1733
- "lstrip": false,
1734
- "normalized": false,
1735
- "rstrip": false,
1736
- "single_word": false,
1737
- "special": true
1738
- },
1739
- "128217": {
1740
- "content": "<|reserved_special_token_209|>",
1741
- "lstrip": false,
1742
- "normalized": false,
1743
- "rstrip": false,
1744
- "single_word": false,
1745
- "special": true
1746
- },
1747
- "128218": {
1748
- "content": "<|reserved_special_token_210|>",
1749
- "lstrip": false,
1750
- "normalized": false,
1751
- "rstrip": false,
1752
- "single_word": false,
1753
- "special": true
1754
- },
1755
- "128219": {
1756
- "content": "<|reserved_special_token_211|>",
1757
- "lstrip": false,
1758
- "normalized": false,
1759
- "rstrip": false,
1760
- "single_word": false,
1761
- "special": true
1762
- },
1763
- "128220": {
1764
- "content": "<|reserved_special_token_212|>",
1765
- "lstrip": false,
1766
- "normalized": false,
1767
- "rstrip": false,
1768
- "single_word": false,
1769
- "special": true
1770
- },
1771
- "128221": {
1772
- "content": "<|reserved_special_token_213|>",
1773
- "lstrip": false,
1774
- "normalized": false,
1775
- "rstrip": false,
1776
- "single_word": false,
1777
- "special": true
1778
- },
1779
- "128222": {
1780
- "content": "<|reserved_special_token_214|>",
1781
- "lstrip": false,
1782
- "normalized": false,
1783
- "rstrip": false,
1784
- "single_word": false,
1785
- "special": true
1786
- },
1787
- "128223": {
1788
- "content": "<|reserved_special_token_215|>",
1789
- "lstrip": false,
1790
- "normalized": false,
1791
- "rstrip": false,
1792
- "single_word": false,
1793
- "special": true
1794
- },
1795
- "128224": {
1796
- "content": "<|reserved_special_token_216|>",
1797
- "lstrip": false,
1798
- "normalized": false,
1799
- "rstrip": false,
1800
- "single_word": false,
1801
- "special": true
1802
- },
1803
- "128225": {
1804
- "content": "<|reserved_special_token_217|>",
1805
- "lstrip": false,
1806
- "normalized": false,
1807
- "rstrip": false,
1808
- "single_word": false,
1809
- "special": true
1810
- },
1811
- "128226": {
1812
- "content": "<|reserved_special_token_218|>",
1813
- "lstrip": false,
1814
- "normalized": false,
1815
- "rstrip": false,
1816
- "single_word": false,
1817
- "special": true
1818
- },
1819
- "128227": {
1820
- "content": "<|reserved_special_token_219|>",
1821
- "lstrip": false,
1822
- "normalized": false,
1823
- "rstrip": false,
1824
- "single_word": false,
1825
- "special": true
1826
- },
1827
- "128228": {
1828
- "content": "<|reserved_special_token_220|>",
1829
- "lstrip": false,
1830
- "normalized": false,
1831
- "rstrip": false,
1832
- "single_word": false,
1833
- "special": true
1834
- },
1835
- "128229": {
1836
- "content": "<|reserved_special_token_221|>",
1837
- "lstrip": false,
1838
- "normalized": false,
1839
- "rstrip": false,
1840
- "single_word": false,
1841
- "special": true
1842
- },
1843
- "128230": {
1844
- "content": "<|reserved_special_token_222|>",
1845
- "lstrip": false,
1846
- "normalized": false,
1847
- "rstrip": false,
1848
- "single_word": false,
1849
- "special": true
1850
- },
1851
- "128231": {
1852
- "content": "<|reserved_special_token_223|>",
1853
- "lstrip": false,
1854
- "normalized": false,
1855
- "rstrip": false,
1856
- "single_word": false,
1857
- "special": true
1858
- },
1859
- "128232": {
1860
- "content": "<|reserved_special_token_224|>",
1861
- "lstrip": false,
1862
- "normalized": false,
1863
- "rstrip": false,
1864
- "single_word": false,
1865
- "special": true
1866
- },
1867
- "128233": {
1868
- "content": "<|reserved_special_token_225|>",
1869
- "lstrip": false,
1870
- "normalized": false,
1871
- "rstrip": false,
1872
- "single_word": false,
1873
- "special": true
1874
- },
1875
- "128234": {
1876
- "content": "<|reserved_special_token_226|>",
1877
- "lstrip": false,
1878
- "normalized": false,
1879
- "rstrip": false,
1880
- "single_word": false,
1881
- "special": true
1882
- },
1883
- "128235": {
1884
- "content": "<|reserved_special_token_227|>",
1885
- "lstrip": false,
1886
- "normalized": false,
1887
- "rstrip": false,
1888
- "single_word": false,
1889
- "special": true
1890
- },
1891
- "128236": {
1892
- "content": "<|reserved_special_token_228|>",
1893
- "lstrip": false,
1894
- "normalized": false,
1895
- "rstrip": false,
1896
- "single_word": false,
1897
- "special": true
1898
- },
1899
- "128237": {
1900
- "content": "<|reserved_special_token_229|>",
1901
- "lstrip": false,
1902
- "normalized": false,
1903
- "rstrip": false,
1904
- "single_word": false,
1905
- "special": true
1906
- },
1907
- "128238": {
1908
- "content": "<|reserved_special_token_230|>",
1909
- "lstrip": false,
1910
- "normalized": false,
1911
- "rstrip": false,
1912
- "single_word": false,
1913
- "special": true
1914
- },
1915
- "128239": {
1916
- "content": "<|reserved_special_token_231|>",
1917
- "lstrip": false,
1918
- "normalized": false,
1919
- "rstrip": false,
1920
- "single_word": false,
1921
- "special": true
1922
- },
1923
- "128240": {
1924
- "content": "<|reserved_special_token_232|>",
1925
- "lstrip": false,
1926
- "normalized": false,
1927
- "rstrip": false,
1928
- "single_word": false,
1929
- "special": true
1930
- },
1931
- "128241": {
1932
- "content": "<|reserved_special_token_233|>",
1933
- "lstrip": false,
1934
- "normalized": false,
1935
- "rstrip": false,
1936
- "single_word": false,
1937
- "special": true
1938
- },
1939
- "128242": {
1940
- "content": "<|reserved_special_token_234|>",
1941
- "lstrip": false,
1942
- "normalized": false,
1943
- "rstrip": false,
1944
- "single_word": false,
1945
- "special": true
1946
- },
1947
- "128243": {
1948
- "content": "<|reserved_special_token_235|>",
1949
- "lstrip": false,
1950
- "normalized": false,
1951
- "rstrip": false,
1952
- "single_word": false,
1953
- "special": true
1954
- },
1955
- "128244": {
1956
- "content": "<|reserved_special_token_236|>",
1957
- "lstrip": false,
1958
- "normalized": false,
1959
- "rstrip": false,
1960
- "single_word": false,
1961
- "special": true
1962
- },
1963
- "128245": {
1964
- "content": "<|reserved_special_token_237|>",
1965
- "lstrip": false,
1966
- "normalized": false,
1967
- "rstrip": false,
1968
- "single_word": false,
1969
- "special": true
1970
- },
1971
- "128246": {
1972
- "content": "<|reserved_special_token_238|>",
1973
- "lstrip": false,
1974
- "normalized": false,
1975
- "rstrip": false,
1976
- "single_word": false,
1977
- "special": true
1978
- },
1979
- "128247": {
1980
- "content": "<|reserved_special_token_239|>",
1981
- "lstrip": false,
1982
- "normalized": false,
1983
- "rstrip": false,
1984
- "single_word": false,
1985
- "special": true
1986
- },
1987
- "128248": {
1988
- "content": "<|reserved_special_token_240|>",
1989
- "lstrip": false,
1990
- "normalized": false,
1991
- "rstrip": false,
1992
- "single_word": false,
1993
- "special": true
1994
- },
1995
- "128249": {
1996
- "content": "<|reserved_special_token_241|>",
1997
- "lstrip": false,
1998
- "normalized": false,
1999
- "rstrip": false,
2000
- "single_word": false,
2001
- "special": true
2002
- },
2003
- "128250": {
2004
- "content": "<|reserved_special_token_242|>",
2005
- "lstrip": false,
2006
- "normalized": false,
2007
- "rstrip": false,
2008
- "single_word": false,
2009
- "special": true
2010
- },
2011
- "128251": {
2012
- "content": "<|reserved_special_token_243|>",
2013
- "lstrip": false,
2014
- "normalized": false,
2015
- "rstrip": false,
2016
- "single_word": false,
2017
- "special": true
2018
- },
2019
- "128252": {
2020
- "content": "<|reserved_special_token_244|>",
2021
- "lstrip": false,
2022
- "normalized": false,
2023
- "rstrip": false,
2024
- "single_word": false,
2025
- "special": true
2026
- },
2027
- "128253": {
2028
- "content": "<|reserved_special_token_245|>",
2029
- "lstrip": false,
2030
- "normalized": false,
2031
- "rstrip": false,
2032
- "single_word": false,
2033
- "special": true
2034
- },
2035
- "128254": {
2036
- "content": "<|reserved_special_token_246|>",
2037
- "lstrip": false,
2038
- "normalized": false,
2039
- "rstrip": false,
2040
- "single_word": false,
2041
- "special": true
2042
- },
2043
- "128255": {
2044
- "content": "<|reserved_special_token_247|>",
2045
- "lstrip": false,
2046
- "normalized": false,
2047
- "rstrip": false,
2048
- "single_word": false,
2049
- "special": true
2050
- }
2051
- },
2052
- "bos_token": "<|begin_of_text|>",
2053
- "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>\n' + message['content'] + eos_token + '\n' }}{% else %}{{ '<|assistant|>\n' + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% endfor %}",
2054
- "clean_up_tokenization_spaces": true,
2055
- "eos_token": "<|end_of_text|>",
2056
- "extra_special_tokens": {},
2057
- "model_input_names": [
2058
- "input_ids",
2059
- "attention_mask"
2060
- ],
2061
- "model_max_length": 131072,
2062
- "pad_token": "<|end_of_text|>",
2063
- "tokenizer_class": "PreTrainedTokenizerFast"
2064
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2115/trainer_state.json DELETED
@@ -1,3075 +0,0 @@
1
- {
2
- "best_metric": 0.25380879640579224,
3
- "best_model_checkpoint": "output/finetune/llama-3.1-8b/math/1e-5-math-v4/checkpoint-2115",
4
- "epoch": 2.70528,
5
- "eval_steps": 235,
6
- "global_step": 2115,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.0064,
13
- "grad_norm": 486.0,
14
- "learning_rate": 2.1276595744680852e-07,
15
- "loss": 4.4408,
16
- "step": 5
17
- },
18
- {
19
- "epoch": 0.0128,
20
- "grad_norm": 1056.0,
21
- "learning_rate": 4.2553191489361704e-07,
22
- "loss": 4.4854,
23
- "step": 10
24
- },
25
- {
26
- "epoch": 0.0192,
27
- "grad_norm": 612.0,
28
- "learning_rate": 6.382978723404255e-07,
29
- "loss": 4.2013,
30
- "step": 15
31
- },
32
- {
33
- "epoch": 0.0256,
34
- "grad_norm": 95.0,
35
- "learning_rate": 8.510638297872341e-07,
36
- "loss": 4.2303,
37
- "step": 20
38
- },
39
- {
40
- "epoch": 0.032,
41
- "grad_norm": 72.5,
42
- "learning_rate": 1.0638297872340427e-06,
43
- "loss": 4.1994,
44
- "step": 25
45
- },
46
- {
47
- "epoch": 0.0384,
48
- "grad_norm": 79.5,
49
- "learning_rate": 1.276595744680851e-06,
50
- "loss": 3.8422,
51
- "step": 30
52
- },
53
- {
54
- "epoch": 0.0448,
55
- "grad_norm": 87.0,
56
- "learning_rate": 1.4893617021276596e-06,
57
- "loss": 3.7225,
58
- "step": 35
59
- },
60
- {
61
- "epoch": 0.0512,
62
- "grad_norm": 56.75,
63
- "learning_rate": 1.7021276595744682e-06,
64
- "loss": 3.2795,
65
- "step": 40
66
- },
67
- {
68
- "epoch": 0.0576,
69
- "grad_norm": 46.75,
70
- "learning_rate": 1.9148936170212767e-06,
71
- "loss": 2.9605,
72
- "step": 45
73
- },
74
- {
75
- "epoch": 0.064,
76
- "grad_norm": 20.25,
77
- "learning_rate": 2.1276595744680853e-06,
78
- "loss": 2.6427,
79
- "step": 50
80
- },
81
- {
82
- "epoch": 0.0704,
83
- "grad_norm": 16.125,
84
- "learning_rate": 2.340425531914894e-06,
85
- "loss": 2.4008,
86
- "step": 55
87
- },
88
- {
89
- "epoch": 0.0768,
90
- "grad_norm": 11.0625,
91
- "learning_rate": 2.553191489361702e-06,
92
- "loss": 2.357,
93
- "step": 60
94
- },
95
- {
96
- "epoch": 0.0832,
97
- "grad_norm": 18.625,
98
- "learning_rate": 2.765957446808511e-06,
99
- "loss": 2.2674,
100
- "step": 65
101
- },
102
- {
103
- "epoch": 0.0896,
104
- "grad_norm": 11.5625,
105
- "learning_rate": 2.978723404255319e-06,
106
- "loss": 2.2461,
107
- "step": 70
108
- },
109
- {
110
- "epoch": 0.096,
111
- "grad_norm": 10.6875,
112
- "learning_rate": 3.191489361702128e-06,
113
- "loss": 2.0491,
114
- "step": 75
115
- },
116
- {
117
- "epoch": 0.1024,
118
- "grad_norm": 12.0625,
119
- "learning_rate": 3.4042553191489363e-06,
120
- "loss": 2.1206,
121
- "step": 80
122
- },
123
- {
124
- "epoch": 0.1088,
125
- "grad_norm": 11.125,
126
- "learning_rate": 3.6170212765957453e-06,
127
- "loss": 2.0355,
128
- "step": 85
129
- },
130
- {
131
- "epoch": 0.1152,
132
- "grad_norm": 11.375,
133
- "learning_rate": 3.8297872340425535e-06,
134
- "loss": 2.0573,
135
- "step": 90
136
- },
137
- {
138
- "epoch": 0.1216,
139
- "grad_norm": 11.5625,
140
- "learning_rate": 4.042553191489362e-06,
141
- "loss": 2.0008,
142
- "step": 95
143
- },
144
- {
145
- "epoch": 0.128,
146
- "grad_norm": 12.0625,
147
- "learning_rate": 4.255319148936171e-06,
148
- "loss": 2.0293,
149
- "step": 100
150
- },
151
- {
152
- "epoch": 0.1344,
153
- "grad_norm": 12.125,
154
- "learning_rate": 4.468085106382979e-06,
155
- "loss": 2.012,
156
- "step": 105
157
- },
158
- {
159
- "epoch": 0.1408,
160
- "grad_norm": 12.6875,
161
- "learning_rate": 4.680851063829788e-06,
162
- "loss": 2.0539,
163
- "step": 110
164
- },
165
- {
166
- "epoch": 0.1472,
167
- "grad_norm": 10.0,
168
- "learning_rate": 4.893617021276596e-06,
169
- "loss": 1.9737,
170
- "step": 115
171
- },
172
- {
173
- "epoch": 0.1536,
174
- "grad_norm": 10.5,
175
- "learning_rate": 5.106382978723404e-06,
176
- "loss": 1.894,
177
- "step": 120
178
- },
179
- {
180
- "epoch": 0.16,
181
- "grad_norm": 13.25,
182
- "learning_rate": 5.319148936170213e-06,
183
- "loss": 2.006,
184
- "step": 125
185
- },
186
- {
187
- "epoch": 0.1664,
188
- "grad_norm": 10.0625,
189
- "learning_rate": 5.531914893617022e-06,
190
- "loss": 1.9278,
191
- "step": 130
192
- },
193
- {
194
- "epoch": 0.1728,
195
- "grad_norm": 13.75,
196
- "learning_rate": 5.744680851063831e-06,
197
- "loss": 1.8879,
198
- "step": 135
199
- },
200
- {
201
- "epoch": 0.1792,
202
- "grad_norm": 10.625,
203
- "learning_rate": 5.957446808510638e-06,
204
- "loss": 1.83,
205
- "step": 140
206
- },
207
- {
208
- "epoch": 0.1856,
209
- "grad_norm": 10.875,
210
- "learning_rate": 6.170212765957447e-06,
211
- "loss": 1.8662,
212
- "step": 145
213
- },
214
- {
215
- "epoch": 0.192,
216
- "grad_norm": 10.9375,
217
- "learning_rate": 6.382978723404256e-06,
218
- "loss": 1.8412,
219
- "step": 150
220
- },
221
- {
222
- "epoch": 0.1984,
223
- "grad_norm": 13.5625,
224
- "learning_rate": 6.595744680851064e-06,
225
- "loss": 1.8421,
226
- "step": 155
227
- },
228
- {
229
- "epoch": 0.2048,
230
- "grad_norm": 12.125,
231
- "learning_rate": 6.808510638297873e-06,
232
- "loss": 1.8205,
233
- "step": 160
234
- },
235
- {
236
- "epoch": 0.2112,
237
- "grad_norm": 11.25,
238
- "learning_rate": 7.021276595744682e-06,
239
- "loss": 1.808,
240
- "step": 165
241
- },
242
- {
243
- "epoch": 0.2176,
244
- "grad_norm": 10.0625,
245
- "learning_rate": 7.234042553191491e-06,
246
- "loss": 1.7834,
247
- "step": 170
248
- },
249
- {
250
- "epoch": 0.224,
251
- "grad_norm": 10.3125,
252
- "learning_rate": 7.446808510638298e-06,
253
- "loss": 1.771,
254
- "step": 175
255
- },
256
- {
257
- "epoch": 0.2304,
258
- "grad_norm": 10.125,
259
- "learning_rate": 7.659574468085107e-06,
260
- "loss": 1.7453,
261
- "step": 180
262
- },
263
- {
264
- "epoch": 0.2368,
265
- "grad_norm": 10.6875,
266
- "learning_rate": 7.872340425531916e-06,
267
- "loss": 1.7716,
268
- "step": 185
269
- },
270
- {
271
- "epoch": 0.2432,
272
- "grad_norm": 10.75,
273
- "learning_rate": 8.085106382978723e-06,
274
- "loss": 1.8386,
275
- "step": 190
276
- },
277
- {
278
- "epoch": 0.2496,
279
- "grad_norm": 10.3125,
280
- "learning_rate": 8.297872340425532e-06,
281
- "loss": 1.7824,
282
- "step": 195
283
- },
284
- {
285
- "epoch": 0.256,
286
- "grad_norm": 10.625,
287
- "learning_rate": 8.510638297872341e-06,
288
- "loss": 1.7799,
289
- "step": 200
290
- },
291
- {
292
- "epoch": 0.2624,
293
- "grad_norm": 11.75,
294
- "learning_rate": 8.72340425531915e-06,
295
- "loss": 1.8054,
296
- "step": 205
297
- },
298
- {
299
- "epoch": 0.2688,
300
- "grad_norm": 10.75,
301
- "learning_rate": 8.936170212765958e-06,
302
- "loss": 1.8274,
303
- "step": 210
304
- },
305
- {
306
- "epoch": 0.2752,
307
- "grad_norm": 10.9375,
308
- "learning_rate": 9.148936170212767e-06,
309
- "loss": 1.7087,
310
- "step": 215
311
- },
312
- {
313
- "epoch": 0.2816,
314
- "grad_norm": 10.0,
315
- "learning_rate": 9.361702127659576e-06,
316
- "loss": 1.7527,
317
- "step": 220
318
- },
319
- {
320
- "epoch": 0.288,
321
- "grad_norm": 11.0,
322
- "learning_rate": 9.574468085106385e-06,
323
- "loss": 1.7344,
324
- "step": 225
325
- },
326
- {
327
- "epoch": 0.2944,
328
- "grad_norm": 12.3125,
329
- "learning_rate": 9.787234042553192e-06,
330
- "loss": 1.7187,
331
- "step": 230
332
- },
333
- {
334
- "epoch": 0.3008,
335
- "grad_norm": 10.5625,
336
- "learning_rate": 1e-05,
337
- "loss": 1.7051,
338
- "step": 235
339
- },
340
- {
341
- "epoch": 0.3008,
342
- "eval_loss": 0.4172936975955963,
343
- "eval_runtime": 10.5842,
344
- "eval_samples_per_second": 283.442,
345
- "eval_steps_per_second": 8.881,
346
- "step": 235
347
- },
348
- {
349
- "epoch": 0.3072,
350
- "grad_norm": 10.75,
351
- "learning_rate": 9.976280834914613e-06,
352
- "loss": 1.7006,
353
- "step": 240
354
- },
355
- {
356
- "epoch": 0.3136,
357
- "grad_norm": 12.9375,
358
- "learning_rate": 9.952561669829223e-06,
359
- "loss": 1.6624,
360
- "step": 245
361
- },
362
- {
363
- "epoch": 0.32,
364
- "grad_norm": 10.0,
365
- "learning_rate": 9.928842504743834e-06,
366
- "loss": 1.6784,
367
- "step": 250
368
- },
369
- {
370
- "epoch": 0.3264,
371
- "grad_norm": 9.875,
372
- "learning_rate": 9.905123339658444e-06,
373
- "loss": 1.5868,
374
- "step": 255
375
- },
376
- {
377
- "epoch": 0.3328,
378
- "grad_norm": 11.5,
379
- "learning_rate": 9.881404174573056e-06,
380
- "loss": 1.669,
381
- "step": 260
382
- },
383
- {
384
- "epoch": 0.3392,
385
- "grad_norm": 10.125,
386
- "learning_rate": 9.857685009487666e-06,
387
- "loss": 1.6031,
388
- "step": 265
389
- },
390
- {
391
- "epoch": 0.3456,
392
- "grad_norm": 10.625,
393
- "learning_rate": 9.833965844402278e-06,
394
- "loss": 1.6651,
395
- "step": 270
396
- },
397
- {
398
- "epoch": 0.352,
399
- "grad_norm": 10.125,
400
- "learning_rate": 9.810246679316889e-06,
401
- "loss": 1.6462,
402
- "step": 275
403
- },
404
- {
405
- "epoch": 0.3584,
406
- "grad_norm": 10.8125,
407
- "learning_rate": 9.786527514231499e-06,
408
- "loss": 1.6355,
409
- "step": 280
410
- },
411
- {
412
- "epoch": 0.3648,
413
- "grad_norm": 9.75,
414
- "learning_rate": 9.762808349146111e-06,
415
- "loss": 1.6509,
416
- "step": 285
417
- },
418
- {
419
- "epoch": 0.3712,
420
- "grad_norm": 10.375,
421
- "learning_rate": 9.739089184060721e-06,
422
- "loss": 1.5659,
423
- "step": 290
424
- },
425
- {
426
- "epoch": 0.3776,
427
- "grad_norm": 9.5625,
428
- "learning_rate": 9.715370018975334e-06,
429
- "loss": 1.5724,
430
- "step": 295
431
- },
432
- {
433
- "epoch": 0.384,
434
- "grad_norm": 10.625,
435
- "learning_rate": 9.691650853889944e-06,
436
- "loss": 1.5393,
437
- "step": 300
438
- },
439
- {
440
- "epoch": 0.3904,
441
- "grad_norm": 12.0625,
442
- "learning_rate": 9.667931688804554e-06,
443
- "loss": 1.5596,
444
- "step": 305
445
- },
446
- {
447
- "epoch": 0.3968,
448
- "grad_norm": 9.375,
449
- "learning_rate": 9.644212523719166e-06,
450
- "loss": 1.541,
451
- "step": 310
452
- },
453
- {
454
- "epoch": 0.4032,
455
- "grad_norm": 11.9375,
456
- "learning_rate": 9.620493358633777e-06,
457
- "loss": 1.5976,
458
- "step": 315
459
- },
460
- {
461
- "epoch": 0.4096,
462
- "grad_norm": 9.9375,
463
- "learning_rate": 9.596774193548389e-06,
464
- "loss": 1.5253,
465
- "step": 320
466
- },
467
- {
468
- "epoch": 0.416,
469
- "grad_norm": 10.8125,
470
- "learning_rate": 9.573055028462999e-06,
471
- "loss": 1.5369,
472
- "step": 325
473
- },
474
- {
475
- "epoch": 0.4224,
476
- "grad_norm": 11.3125,
477
- "learning_rate": 9.54933586337761e-06,
478
- "loss": 1.4769,
479
- "step": 330
480
- },
481
- {
482
- "epoch": 0.4288,
483
- "grad_norm": 11.0,
484
- "learning_rate": 9.52561669829222e-06,
485
- "loss": 1.5442,
486
- "step": 335
487
- },
488
- {
489
- "epoch": 0.4352,
490
- "grad_norm": 11.5625,
491
- "learning_rate": 9.501897533206832e-06,
492
- "loss": 1.4972,
493
- "step": 340
494
- },
495
- {
496
- "epoch": 0.4416,
497
- "grad_norm": 10.0625,
498
- "learning_rate": 9.478178368121444e-06,
499
- "loss": 1.4337,
500
- "step": 345
501
- },
502
- {
503
- "epoch": 0.448,
504
- "grad_norm": 10.4375,
505
- "learning_rate": 9.454459203036054e-06,
506
- "loss": 1.4247,
507
- "step": 350
508
- },
509
- {
510
- "epoch": 0.4544,
511
- "grad_norm": 10.4375,
512
- "learning_rate": 9.430740037950665e-06,
513
- "loss": 1.4931,
514
- "step": 355
515
- },
516
- {
517
- "epoch": 0.4608,
518
- "grad_norm": 9.625,
519
- "learning_rate": 9.407020872865275e-06,
520
- "loss": 1.5176,
521
- "step": 360
522
- },
523
- {
524
- "epoch": 0.4672,
525
- "grad_norm": 10.5,
526
- "learning_rate": 9.383301707779887e-06,
527
- "loss": 1.4712,
528
- "step": 365
529
- },
530
- {
531
- "epoch": 0.4736,
532
- "grad_norm": 9.5625,
533
- "learning_rate": 9.359582542694497e-06,
534
- "loss": 1.4675,
535
- "step": 370
536
- },
537
- {
538
- "epoch": 0.48,
539
- "grad_norm": 9.875,
540
- "learning_rate": 9.33586337760911e-06,
541
- "loss": 1.4126,
542
- "step": 375
543
- },
544
- {
545
- "epoch": 0.4864,
546
- "grad_norm": 9.1875,
547
- "learning_rate": 9.31214421252372e-06,
548
- "loss": 1.4304,
549
- "step": 380
550
- },
551
- {
552
- "epoch": 0.4928,
553
- "grad_norm": 10.0625,
554
- "learning_rate": 9.28842504743833e-06,
555
- "loss": 1.5047,
556
- "step": 385
557
- },
558
- {
559
- "epoch": 0.4992,
560
- "grad_norm": 11.1875,
561
- "learning_rate": 9.264705882352942e-06,
562
- "loss": 1.4782,
563
- "step": 390
564
- },
565
- {
566
- "epoch": 0.5056,
567
- "grad_norm": 11.375,
568
- "learning_rate": 9.240986717267552e-06,
569
- "loss": 1.4177,
570
- "step": 395
571
- },
572
- {
573
- "epoch": 0.512,
574
- "grad_norm": 10.9375,
575
- "learning_rate": 9.217267552182164e-06,
576
- "loss": 1.4651,
577
- "step": 400
578
- },
579
- {
580
- "epoch": 0.5184,
581
- "grad_norm": 11.0625,
582
- "learning_rate": 9.193548387096775e-06,
583
- "loss": 1.3854,
584
- "step": 405
585
- },
586
- {
587
- "epoch": 0.5248,
588
- "grad_norm": 11.375,
589
- "learning_rate": 9.169829222011387e-06,
590
- "loss": 1.3524,
591
- "step": 410
592
- },
593
- {
594
- "epoch": 0.5312,
595
- "grad_norm": 10.1875,
596
- "learning_rate": 9.146110056925997e-06,
597
- "loss": 1.3955,
598
- "step": 415
599
- },
600
- {
601
- "epoch": 0.5376,
602
- "grad_norm": 11.375,
603
- "learning_rate": 9.122390891840608e-06,
604
- "loss": 1.3904,
605
- "step": 420
606
- },
607
- {
608
- "epoch": 0.544,
609
- "grad_norm": 10.75,
610
- "learning_rate": 9.09867172675522e-06,
611
- "loss": 1.3237,
612
- "step": 425
613
- },
614
- {
615
- "epoch": 0.5504,
616
- "grad_norm": 11.9375,
617
- "learning_rate": 9.07495256166983e-06,
618
- "loss": 1.3736,
619
- "step": 430
620
- },
621
- {
622
- "epoch": 0.5568,
623
- "grad_norm": 12.125,
624
- "learning_rate": 9.051233396584442e-06,
625
- "loss": 1.4222,
626
- "step": 435
627
- },
628
- {
629
- "epoch": 0.5632,
630
- "grad_norm": 10.8125,
631
- "learning_rate": 9.027514231499052e-06,
632
- "loss": 1.3904,
633
- "step": 440
634
- },
635
- {
636
- "epoch": 0.5696,
637
- "grad_norm": 10.0625,
638
- "learning_rate": 9.003795066413663e-06,
639
- "loss": 1.368,
640
- "step": 445
641
- },
642
- {
643
- "epoch": 0.576,
644
- "grad_norm": 10.0625,
645
- "learning_rate": 8.980075901328273e-06,
646
- "loss": 1.322,
647
- "step": 450
648
- },
649
- {
650
- "epoch": 0.5824,
651
- "grad_norm": 11.875,
652
- "learning_rate": 8.956356736242885e-06,
653
- "loss": 1.2896,
654
- "step": 455
655
- },
656
- {
657
- "epoch": 0.5888,
658
- "grad_norm": 12.4375,
659
- "learning_rate": 8.932637571157497e-06,
660
- "loss": 1.3527,
661
- "step": 460
662
- },
663
- {
664
- "epoch": 0.5952,
665
- "grad_norm": 11.3125,
666
- "learning_rate": 8.908918406072108e-06,
667
- "loss": 1.3194,
668
- "step": 465
669
- },
670
- {
671
- "epoch": 0.6016,
672
- "grad_norm": 10.75,
673
- "learning_rate": 8.885199240986718e-06,
674
- "loss": 1.3812,
675
- "step": 470
676
- },
677
- {
678
- "epoch": 0.6016,
679
- "eval_loss": 0.32924115657806396,
680
- "eval_runtime": 10.5615,
681
- "eval_samples_per_second": 284.051,
682
- "eval_steps_per_second": 8.9,
683
- "step": 470
684
- },
685
- {
686
- "epoch": 0.608,
687
- "grad_norm": 10.375,
688
- "learning_rate": 8.861480075901328e-06,
689
- "loss": 1.3294,
690
- "step": 475
691
- },
692
- {
693
- "epoch": 0.6144,
694
- "grad_norm": 12.6875,
695
- "learning_rate": 8.83776091081594e-06,
696
- "loss": 1.2831,
697
- "step": 480
698
- },
699
- {
700
- "epoch": 0.6208,
701
- "grad_norm": 11.1875,
702
- "learning_rate": 8.81404174573055e-06,
703
- "loss": 1.3432,
704
- "step": 485
705
- },
706
- {
707
- "epoch": 0.6272,
708
- "grad_norm": 10.75,
709
- "learning_rate": 8.790322580645163e-06,
710
- "loss": 1.3443,
711
- "step": 490
712
- },
713
- {
714
- "epoch": 0.6336,
715
- "grad_norm": 13.4375,
716
- "learning_rate": 8.766603415559773e-06,
717
- "loss": 1.2725,
718
- "step": 495
719
- },
720
- {
721
- "epoch": 0.64,
722
- "grad_norm": 12.375,
723
- "learning_rate": 8.742884250474383e-06,
724
- "loss": 1.2581,
725
- "step": 500
726
- },
727
- {
728
- "epoch": 0.6464,
729
- "grad_norm": 12.6875,
730
- "learning_rate": 8.719165085388995e-06,
731
- "loss": 1.3468,
732
- "step": 505
733
- },
734
- {
735
- "epoch": 0.6528,
736
- "grad_norm": 11.1875,
737
- "learning_rate": 8.695445920303606e-06,
738
- "loss": 1.3169,
739
- "step": 510
740
- },
741
- {
742
- "epoch": 0.6592,
743
- "grad_norm": 11.875,
744
- "learning_rate": 8.671726755218218e-06,
745
- "loss": 1.3257,
746
- "step": 515
747
- },
748
- {
749
- "epoch": 0.6656,
750
- "grad_norm": 10.5625,
751
- "learning_rate": 8.648007590132828e-06,
752
- "loss": 1.2693,
753
- "step": 520
754
- },
755
- {
756
- "epoch": 0.672,
757
- "grad_norm": 11.875,
758
- "learning_rate": 8.624288425047439e-06,
759
- "loss": 1.3097,
760
- "step": 525
761
- },
762
- {
763
- "epoch": 0.6784,
764
- "grad_norm": 10.8125,
765
- "learning_rate": 8.60056925996205e-06,
766
- "loss": 1.2463,
767
- "step": 530
768
- },
769
- {
770
- "epoch": 0.6848,
771
- "grad_norm": 11.3125,
772
- "learning_rate": 8.576850094876661e-06,
773
- "loss": 1.2767,
774
- "step": 535
775
- },
776
- {
777
- "epoch": 0.6912,
778
- "grad_norm": 10.5625,
779
- "learning_rate": 8.553130929791273e-06,
780
- "loss": 1.2556,
781
- "step": 540
782
- },
783
- {
784
- "epoch": 0.6976,
785
- "grad_norm": 10.5625,
786
- "learning_rate": 8.529411764705883e-06,
787
- "loss": 1.2767,
788
- "step": 545
789
- },
790
- {
791
- "epoch": 0.704,
792
- "grad_norm": 13.4375,
793
- "learning_rate": 8.505692599620494e-06,
794
- "loss": 1.3016,
795
- "step": 550
796
- },
797
- {
798
- "epoch": 0.7104,
799
- "grad_norm": 11.6875,
800
- "learning_rate": 8.481973434535104e-06,
801
- "loss": 1.2735,
802
- "step": 555
803
- },
804
- {
805
- "epoch": 0.7168,
806
- "grad_norm": 9.8125,
807
- "learning_rate": 8.458254269449716e-06,
808
- "loss": 1.2116,
809
- "step": 560
810
- },
811
- {
812
- "epoch": 0.7232,
813
- "grad_norm": 10.8125,
814
- "learning_rate": 8.434535104364328e-06,
815
- "loss": 1.2544,
816
- "step": 565
817
- },
818
- {
819
- "epoch": 0.7296,
820
- "grad_norm": 11.1875,
821
- "learning_rate": 8.410815939278938e-06,
822
- "loss": 1.2554,
823
- "step": 570
824
- },
825
- {
826
- "epoch": 0.736,
827
- "grad_norm": 11.8125,
828
- "learning_rate": 8.387096774193549e-06,
829
- "loss": 1.2171,
830
- "step": 575
831
- },
832
- {
833
- "epoch": 0.7424,
834
- "grad_norm": 10.8125,
835
- "learning_rate": 8.363377609108159e-06,
836
- "loss": 1.1872,
837
- "step": 580
838
- },
839
- {
840
- "epoch": 0.7488,
841
- "grad_norm": 12.375,
842
- "learning_rate": 8.339658444022771e-06,
843
- "loss": 1.2747,
844
- "step": 585
845
- },
846
- {
847
- "epoch": 0.7552,
848
- "grad_norm": 11.375,
849
- "learning_rate": 8.315939278937382e-06,
850
- "loss": 1.2439,
851
- "step": 590
852
- },
853
- {
854
- "epoch": 0.7616,
855
- "grad_norm": 10.625,
856
- "learning_rate": 8.292220113851994e-06,
857
- "loss": 1.2492,
858
- "step": 595
859
- },
860
- {
861
- "epoch": 0.768,
862
- "grad_norm": 10.9375,
863
- "learning_rate": 8.268500948766604e-06,
864
- "loss": 1.274,
865
- "step": 600
866
- },
867
- {
868
- "epoch": 0.7744,
869
- "grad_norm": 10.4375,
870
- "learning_rate": 8.244781783681214e-06,
871
- "loss": 1.1692,
872
- "step": 605
873
- },
874
- {
875
- "epoch": 0.7808,
876
- "grad_norm": 11.5,
877
- "learning_rate": 8.221062618595826e-06,
878
- "loss": 1.1956,
879
- "step": 610
880
- },
881
- {
882
- "epoch": 0.7872,
883
- "grad_norm": 10.75,
884
- "learning_rate": 8.197343453510437e-06,
885
- "loss": 1.2427,
886
- "step": 615
887
- },
888
- {
889
- "epoch": 0.7936,
890
- "grad_norm": 11.25,
891
- "learning_rate": 8.173624288425049e-06,
892
- "loss": 1.1742,
893
- "step": 620
894
- },
895
- {
896
- "epoch": 0.8,
897
- "grad_norm": 10.75,
898
- "learning_rate": 8.149905123339659e-06,
899
- "loss": 1.1991,
900
- "step": 625
901
- },
902
- {
903
- "epoch": 0.8064,
904
- "grad_norm": 11.8125,
905
- "learning_rate": 8.12618595825427e-06,
906
- "loss": 1.2068,
907
- "step": 630
908
- },
909
- {
910
- "epoch": 0.8128,
911
- "grad_norm": 11.9375,
912
- "learning_rate": 8.102466793168881e-06,
913
- "loss": 1.2385,
914
- "step": 635
915
- },
916
- {
917
- "epoch": 0.8192,
918
- "grad_norm": 10.8125,
919
- "learning_rate": 8.078747628083492e-06,
920
- "loss": 1.2093,
921
- "step": 640
922
- },
923
- {
924
- "epoch": 0.8256,
925
- "grad_norm": 9.9375,
926
- "learning_rate": 8.055028462998104e-06,
927
- "loss": 1.2198,
928
- "step": 645
929
- },
930
- {
931
- "epoch": 0.832,
932
- "grad_norm": 11.75,
933
- "learning_rate": 8.031309297912714e-06,
934
- "loss": 1.1937,
935
- "step": 650
936
- },
937
- {
938
- "epoch": 0.8384,
939
- "grad_norm": 11.875,
940
- "learning_rate": 8.007590132827325e-06,
941
- "loss": 1.2434,
942
- "step": 655
943
- },
944
- {
945
- "epoch": 0.8448,
946
- "grad_norm": 12.25,
947
- "learning_rate": 7.983870967741935e-06,
948
- "loss": 1.2038,
949
- "step": 660
950
- },
951
- {
952
- "epoch": 0.8512,
953
- "grad_norm": 11.125,
954
- "learning_rate": 7.960151802656547e-06,
955
- "loss": 1.2235,
956
- "step": 665
957
- },
958
- {
959
- "epoch": 0.8576,
960
- "grad_norm": 11.875,
961
- "learning_rate": 7.936432637571159e-06,
962
- "loss": 1.2085,
963
- "step": 670
964
- },
965
- {
966
- "epoch": 0.864,
967
- "grad_norm": 10.375,
968
- "learning_rate": 7.91271347248577e-06,
969
- "loss": 1.153,
970
- "step": 675
971
- },
972
- {
973
- "epoch": 0.8704,
974
- "grad_norm": 9.9375,
975
- "learning_rate": 7.88899430740038e-06,
976
- "loss": 1.1975,
977
- "step": 680
978
- },
979
- {
980
- "epoch": 0.8768,
981
- "grad_norm": 10.1875,
982
- "learning_rate": 7.86527514231499e-06,
983
- "loss": 1.188,
984
- "step": 685
985
- },
986
- {
987
- "epoch": 0.8832,
988
- "grad_norm": 11.1875,
989
- "learning_rate": 7.841555977229602e-06,
990
- "loss": 1.151,
991
- "step": 690
992
- },
993
- {
994
- "epoch": 0.8896,
995
- "grad_norm": 11.8125,
996
- "learning_rate": 7.817836812144212e-06,
997
- "loss": 1.1662,
998
- "step": 695
999
- },
1000
- {
1001
- "epoch": 0.896,
1002
- "grad_norm": 9.8125,
1003
- "learning_rate": 7.794117647058825e-06,
1004
- "loss": 1.1651,
1005
- "step": 700
1006
- },
1007
- {
1008
- "epoch": 0.9024,
1009
- "grad_norm": 10.4375,
1010
- "learning_rate": 7.770398481973435e-06,
1011
- "loss": 1.1637,
1012
- "step": 705
1013
- },
1014
- {
1015
- "epoch": 0.9024,
1016
- "eval_loss": 0.28909003734588623,
1017
- "eval_runtime": 10.5737,
1018
- "eval_samples_per_second": 283.723,
1019
- "eval_steps_per_second": 8.89,
1020
- "step": 705
1021
- },
1022
- {
1023
- "epoch": 0.9088,
1024
- "grad_norm": 10.875,
1025
- "learning_rate": 7.746679316888045e-06,
1026
- "loss": 1.1645,
1027
- "step": 710
1028
- },
1029
- {
1030
- "epoch": 0.9152,
1031
- "grad_norm": 11.125,
1032
- "learning_rate": 7.722960151802657e-06,
1033
- "loss": 1.1143,
1034
- "step": 715
1035
- },
1036
- {
1037
- "epoch": 0.9216,
1038
- "grad_norm": 11.625,
1039
- "learning_rate": 7.699240986717268e-06,
1040
- "loss": 1.195,
1041
- "step": 720
1042
- },
1043
- {
1044
- "epoch": 0.928,
1045
- "grad_norm": 11.1875,
1046
- "learning_rate": 7.67552182163188e-06,
1047
- "loss": 1.1248,
1048
- "step": 725
1049
- },
1050
- {
1051
- "epoch": 0.9344,
1052
- "grad_norm": 10.875,
1053
- "learning_rate": 7.65180265654649e-06,
1054
- "loss": 1.0895,
1055
- "step": 730
1056
- },
1057
- {
1058
- "epoch": 0.9408,
1059
- "grad_norm": 12.75,
1060
- "learning_rate": 7.628083491461101e-06,
1061
- "loss": 1.1278,
1062
- "step": 735
1063
- },
1064
- {
1065
- "epoch": 0.9472,
1066
- "grad_norm": 11.8125,
1067
- "learning_rate": 7.604364326375712e-06,
1068
- "loss": 1.1568,
1069
- "step": 740
1070
- },
1071
- {
1072
- "epoch": 0.9536,
1073
- "grad_norm": 10.6875,
1074
- "learning_rate": 7.580645161290323e-06,
1075
- "loss": 1.1489,
1076
- "step": 745
1077
- },
1078
- {
1079
- "epoch": 0.96,
1080
- "grad_norm": 10.5,
1081
- "learning_rate": 7.556925996204935e-06,
1082
- "loss": 1.102,
1083
- "step": 750
1084
- },
1085
- {
1086
- "epoch": 0.9664,
1087
- "grad_norm": 11.9375,
1088
- "learning_rate": 7.533206831119545e-06,
1089
- "loss": 1.1292,
1090
- "step": 755
1091
- },
1092
- {
1093
- "epoch": 0.9728,
1094
- "grad_norm": 11.9375,
1095
- "learning_rate": 7.509487666034156e-06,
1096
- "loss": 1.1173,
1097
- "step": 760
1098
- },
1099
- {
1100
- "epoch": 0.9792,
1101
- "grad_norm": 11.5,
1102
- "learning_rate": 7.485768500948767e-06,
1103
- "loss": 1.1724,
1104
- "step": 765
1105
- },
1106
- {
1107
- "epoch": 0.9856,
1108
- "grad_norm": 10.6875,
1109
- "learning_rate": 7.462049335863378e-06,
1110
- "loss": 1.1497,
1111
- "step": 770
1112
- },
1113
- {
1114
- "epoch": 0.992,
1115
- "grad_norm": 11.0625,
1116
- "learning_rate": 7.438330170777988e-06,
1117
- "loss": 1.0823,
1118
- "step": 775
1119
- },
1120
- {
1121
- "epoch": 0.9984,
1122
- "grad_norm": 12.6875,
1123
- "learning_rate": 7.4146110056926e-06,
1124
- "loss": 1.0892,
1125
- "step": 780
1126
- },
1127
- {
1128
- "epoch": 1.00384,
1129
- "grad_norm": 10.9375,
1130
- "learning_rate": 7.3908918406072115e-06,
1131
- "loss": 0.8931,
1132
- "step": 785
1133
- },
1134
- {
1135
- "epoch": 1.01024,
1136
- "grad_norm": 11.4375,
1137
- "learning_rate": 7.367172675521822e-06,
1138
- "loss": 1.0372,
1139
- "step": 790
1140
- },
1141
- {
1142
- "epoch": 1.01664,
1143
- "grad_norm": 11.9375,
1144
- "learning_rate": 7.343453510436433e-06,
1145
- "loss": 0.9878,
1146
- "step": 795
1147
- },
1148
- {
1149
- "epoch": 1.02304,
1150
- "grad_norm": 11.0,
1151
- "learning_rate": 7.319734345351044e-06,
1152
- "loss": 1.0192,
1153
- "step": 800
1154
- },
1155
- {
1156
- "epoch": 1.02944,
1157
- "grad_norm": 12.0,
1158
- "learning_rate": 7.2960151802656555e-06,
1159
- "loss": 0.9759,
1160
- "step": 805
1161
- },
1162
- {
1163
- "epoch": 1.03584,
1164
- "grad_norm": 10.75,
1165
- "learning_rate": 7.272296015180266e-06,
1166
- "loss": 1.0209,
1167
- "step": 810
1168
- },
1169
- {
1170
- "epoch": 1.04224,
1171
- "grad_norm": 10.5,
1172
- "learning_rate": 7.248576850094877e-06,
1173
- "loss": 0.9981,
1174
- "step": 815
1175
- },
1176
- {
1177
- "epoch": 1.04864,
1178
- "grad_norm": 11.0,
1179
- "learning_rate": 7.224857685009489e-06,
1180
- "loss": 0.9958,
1181
- "step": 820
1182
- },
1183
- {
1184
- "epoch": 1.05504,
1185
- "grad_norm": 10.5,
1186
- "learning_rate": 7.2011385199240994e-06,
1187
- "loss": 0.9638,
1188
- "step": 825
1189
- },
1190
- {
1191
- "epoch": 1.06144,
1192
- "grad_norm": 12.75,
1193
- "learning_rate": 7.177419354838711e-06,
1194
- "loss": 0.9986,
1195
- "step": 830
1196
- },
1197
- {
1198
- "epoch": 1.06784,
1199
- "grad_norm": 10.625,
1200
- "learning_rate": 7.153700189753321e-06,
1201
- "loss": 1.0067,
1202
- "step": 835
1203
- },
1204
- {
1205
- "epoch": 1.07424,
1206
- "grad_norm": 10.6875,
1207
- "learning_rate": 7.129981024667932e-06,
1208
- "loss": 0.9462,
1209
- "step": 840
1210
- },
1211
- {
1212
- "epoch": 1.08064,
1213
- "grad_norm": 11.75,
1214
- "learning_rate": 7.1062618595825425e-06,
1215
- "loss": 1.0521,
1216
- "step": 845
1217
- },
1218
- {
1219
- "epoch": 1.08704,
1220
- "grad_norm": 12.1875,
1221
- "learning_rate": 7.082542694497155e-06,
1222
- "loss": 0.9888,
1223
- "step": 850
1224
- },
1225
- {
1226
- "epoch": 1.09344,
1227
- "grad_norm": 12.875,
1228
- "learning_rate": 7.058823529411766e-06,
1229
- "loss": 0.9953,
1230
- "step": 855
1231
- },
1232
- {
1233
- "epoch": 1.09984,
1234
- "grad_norm": 10.4375,
1235
- "learning_rate": 7.035104364326376e-06,
1236
- "loss": 0.9836,
1237
- "step": 860
1238
- },
1239
- {
1240
- "epoch": 1.1062400000000001,
1241
- "grad_norm": 11.4375,
1242
- "learning_rate": 7.011385199240987e-06,
1243
- "loss": 0.9892,
1244
- "step": 865
1245
- },
1246
- {
1247
- "epoch": 1.11264,
1248
- "grad_norm": 12.25,
1249
- "learning_rate": 6.987666034155598e-06,
1250
- "loss": 0.9801,
1251
- "step": 870
1252
- },
1253
- {
1254
- "epoch": 1.11904,
1255
- "grad_norm": 11.6875,
1256
- "learning_rate": 6.96394686907021e-06,
1257
- "loss": 0.9499,
1258
- "step": 875
1259
- },
1260
- {
1261
- "epoch": 1.12544,
1262
- "grad_norm": 11.75,
1263
- "learning_rate": 6.94022770398482e-06,
1264
- "loss": 0.9907,
1265
- "step": 880
1266
- },
1267
- {
1268
- "epoch": 1.13184,
1269
- "grad_norm": 10.6875,
1270
- "learning_rate": 6.916508538899431e-06,
1271
- "loss": 0.9449,
1272
- "step": 885
1273
- },
1274
- {
1275
- "epoch": 1.13824,
1276
- "grad_norm": 10.75,
1277
- "learning_rate": 6.8927893738140425e-06,
1278
- "loss": 0.959,
1279
- "step": 890
1280
- },
1281
- {
1282
- "epoch": 1.1446399999999999,
1283
- "grad_norm": 11.4375,
1284
- "learning_rate": 6.869070208728653e-06,
1285
- "loss": 0.9994,
1286
- "step": 895
1287
- },
1288
- {
1289
- "epoch": 1.15104,
1290
- "grad_norm": 10.6875,
1291
- "learning_rate": 6.845351043643265e-06,
1292
- "loss": 0.973,
1293
- "step": 900
1294
- },
1295
- {
1296
- "epoch": 1.15744,
1297
- "grad_norm": 11.75,
1298
- "learning_rate": 6.821631878557875e-06,
1299
- "loss": 0.9399,
1300
- "step": 905
1301
- },
1302
- {
1303
- "epoch": 1.16384,
1304
- "grad_norm": 9.9375,
1305
- "learning_rate": 6.7979127134724864e-06,
1306
- "loss": 0.939,
1307
- "step": 910
1308
- },
1309
- {
1310
- "epoch": 1.17024,
1311
- "grad_norm": 11.375,
1312
- "learning_rate": 6.774193548387097e-06,
1313
- "loss": 0.9726,
1314
- "step": 915
1315
- },
1316
- {
1317
- "epoch": 1.17664,
1318
- "grad_norm": 11.625,
1319
- "learning_rate": 6.750474383301708e-06,
1320
- "loss": 0.9701,
1321
- "step": 920
1322
- },
1323
- {
1324
- "epoch": 1.18304,
1325
- "grad_norm": 11.0,
1326
- "learning_rate": 6.72675521821632e-06,
1327
- "loss": 0.9381,
1328
- "step": 925
1329
- },
1330
- {
1331
- "epoch": 1.18944,
1332
- "grad_norm": 12.5625,
1333
- "learning_rate": 6.70303605313093e-06,
1334
- "loss": 0.9848,
1335
- "step": 930
1336
- },
1337
- {
1338
- "epoch": 1.19584,
1339
- "grad_norm": 11.4375,
1340
- "learning_rate": 6.679316888045542e-06,
1341
- "loss": 0.9948,
1342
- "step": 935
1343
- },
1344
- {
1345
- "epoch": 1.20224,
1346
- "grad_norm": 11.5,
1347
- "learning_rate": 6.655597722960152e-06,
1348
- "loss": 0.9551,
1349
- "step": 940
1350
- },
1351
- {
1352
- "epoch": 1.20224,
1353
- "eval_loss": 0.273183137178421,
1354
- "eval_runtime": 10.5806,
1355
- "eval_samples_per_second": 283.539,
1356
- "eval_steps_per_second": 8.884,
1357
- "step": 940
1358
- },
1359
- {
1360
- "epoch": 1.20864,
1361
- "grad_norm": 11.625,
1362
- "learning_rate": 6.631878557874763e-06,
1363
- "loss": 0.9938,
1364
- "step": 945
1365
- },
1366
- {
1367
- "epoch": 1.2150400000000001,
1368
- "grad_norm": 11.125,
1369
- "learning_rate": 6.608159392789374e-06,
1370
- "loss": 0.9479,
1371
- "step": 950
1372
- },
1373
- {
1374
- "epoch": 1.22144,
1375
- "grad_norm": 11.8125,
1376
- "learning_rate": 6.5844402277039855e-06,
1377
- "loss": 0.9885,
1378
- "step": 955
1379
- },
1380
- {
1381
- "epoch": 1.22784,
1382
- "grad_norm": 10.5,
1383
- "learning_rate": 6.560721062618597e-06,
1384
- "loss": 0.9429,
1385
- "step": 960
1386
- },
1387
- {
1388
- "epoch": 1.23424,
1389
- "grad_norm": 12.0625,
1390
- "learning_rate": 6.537001897533207e-06,
1391
- "loss": 0.9769,
1392
- "step": 965
1393
- },
1394
- {
1395
- "epoch": 1.24064,
1396
- "grad_norm": 10.5625,
1397
- "learning_rate": 6.513282732447819e-06,
1398
- "loss": 0.9748,
1399
- "step": 970
1400
- },
1401
- {
1402
- "epoch": 1.24704,
1403
- "grad_norm": 10.625,
1404
- "learning_rate": 6.4895635673624295e-06,
1405
- "loss": 0.9731,
1406
- "step": 975
1407
- },
1408
- {
1409
- "epoch": 1.2534399999999999,
1410
- "grad_norm": 13.25,
1411
- "learning_rate": 6.465844402277041e-06,
1412
- "loss": 0.9412,
1413
- "step": 980
1414
- },
1415
- {
1416
- "epoch": 1.25984,
1417
- "grad_norm": 11.0,
1418
- "learning_rate": 6.442125237191651e-06,
1419
- "loss": 0.9723,
1420
- "step": 985
1421
- },
1422
- {
1423
- "epoch": 1.26624,
1424
- "grad_norm": 10.5625,
1425
- "learning_rate": 6.418406072106262e-06,
1426
- "loss": 0.961,
1427
- "step": 990
1428
- },
1429
- {
1430
- "epoch": 1.27264,
1431
- "grad_norm": 10.75,
1432
- "learning_rate": 6.394686907020874e-06,
1433
- "loss": 0.9998,
1434
- "step": 995
1435
- },
1436
- {
1437
- "epoch": 1.27904,
1438
- "grad_norm": 12.0625,
1439
- "learning_rate": 6.370967741935485e-06,
1440
- "loss": 0.9766,
1441
- "step": 1000
1442
- },
1443
- {
1444
- "epoch": 1.28544,
1445
- "grad_norm": 10.625,
1446
- "learning_rate": 6.347248576850096e-06,
1447
- "loss": 0.9497,
1448
- "step": 1005
1449
- },
1450
- {
1451
- "epoch": 1.29184,
1452
- "grad_norm": 11.125,
1453
- "learning_rate": 6.323529411764706e-06,
1454
- "loss": 0.9841,
1455
- "step": 1010
1456
- },
1457
- {
1458
- "epoch": 1.29824,
1459
- "grad_norm": 10.5,
1460
- "learning_rate": 6.299810246679317e-06,
1461
- "loss": 0.9412,
1462
- "step": 1015
1463
- },
1464
- {
1465
- "epoch": 1.30464,
1466
- "grad_norm": 11.0,
1467
- "learning_rate": 6.276091081593928e-06,
1468
- "loss": 0.9148,
1469
- "step": 1020
1470
- },
1471
- {
1472
- "epoch": 1.31104,
1473
- "grad_norm": 11.125,
1474
- "learning_rate": 6.25237191650854e-06,
1475
- "loss": 0.9416,
1476
- "step": 1025
1477
- },
1478
- {
1479
- "epoch": 1.31744,
1480
- "grad_norm": 9.4375,
1481
- "learning_rate": 6.228652751423151e-06,
1482
- "loss": 0.9243,
1483
- "step": 1030
1484
- },
1485
- {
1486
- "epoch": 1.3238400000000001,
1487
- "grad_norm": 10.5625,
1488
- "learning_rate": 6.204933586337761e-06,
1489
- "loss": 0.9731,
1490
- "step": 1035
1491
- },
1492
- {
1493
- "epoch": 1.3302399999999999,
1494
- "grad_norm": 10.5625,
1495
- "learning_rate": 6.1812144212523725e-06,
1496
- "loss": 0.9551,
1497
- "step": 1040
1498
- },
1499
- {
1500
- "epoch": 1.33664,
1501
- "grad_norm": 10.75,
1502
- "learning_rate": 6.157495256166983e-06,
1503
- "loss": 0.9702,
1504
- "step": 1045
1505
- },
1506
- {
1507
- "epoch": 1.34304,
1508
- "grad_norm": 11.9375,
1509
- "learning_rate": 6.133776091081595e-06,
1510
- "loss": 0.9833,
1511
- "step": 1050
1512
- },
1513
- {
1514
- "epoch": 1.34944,
1515
- "grad_norm": 11.1875,
1516
- "learning_rate": 6.110056925996205e-06,
1517
- "loss": 0.9664,
1518
- "step": 1055
1519
- },
1520
- {
1521
- "epoch": 1.35584,
1522
- "grad_norm": 10.1875,
1523
- "learning_rate": 6.0863377609108165e-06,
1524
- "loss": 0.9624,
1525
- "step": 1060
1526
- },
1527
- {
1528
- "epoch": 1.36224,
1529
- "grad_norm": 11.25,
1530
- "learning_rate": 6.062618595825427e-06,
1531
- "loss": 0.9769,
1532
- "step": 1065
1533
- },
1534
- {
1535
- "epoch": 1.36864,
1536
- "grad_norm": 10.625,
1537
- "learning_rate": 6.038899430740038e-06,
1538
- "loss": 0.9113,
1539
- "step": 1070
1540
- },
1541
- {
1542
- "epoch": 1.37504,
1543
- "grad_norm": 10.0,
1544
- "learning_rate": 6.01518026565465e-06,
1545
- "loss": 0.9084,
1546
- "step": 1075
1547
- },
1548
- {
1549
- "epoch": 1.38144,
1550
- "grad_norm": 11.0625,
1551
- "learning_rate": 5.99146110056926e-06,
1552
- "loss": 0.9555,
1553
- "step": 1080
1554
- },
1555
- {
1556
- "epoch": 1.38784,
1557
- "grad_norm": 10.875,
1558
- "learning_rate": 5.967741935483872e-06,
1559
- "loss": 0.946,
1560
- "step": 1085
1561
- },
1562
- {
1563
- "epoch": 1.39424,
1564
- "grad_norm": 10.4375,
1565
- "learning_rate": 5.944022770398482e-06,
1566
- "loss": 0.896,
1567
- "step": 1090
1568
- },
1569
- {
1570
- "epoch": 1.40064,
1571
- "grad_norm": 10.25,
1572
- "learning_rate": 5.920303605313093e-06,
1573
- "loss": 0.9276,
1574
- "step": 1095
1575
- },
1576
- {
1577
- "epoch": 1.40704,
1578
- "grad_norm": 11.625,
1579
- "learning_rate": 5.8965844402277035e-06,
1580
- "loss": 0.9699,
1581
- "step": 1100
1582
- },
1583
- {
1584
- "epoch": 1.41344,
1585
- "grad_norm": 10.125,
1586
- "learning_rate": 5.8728652751423156e-06,
1587
- "loss": 0.9637,
1588
- "step": 1105
1589
- },
1590
- {
1591
- "epoch": 1.41984,
1592
- "grad_norm": 11.4375,
1593
- "learning_rate": 5.849146110056927e-06,
1594
- "loss": 0.9202,
1595
- "step": 1110
1596
- },
1597
- {
1598
- "epoch": 1.42624,
1599
- "grad_norm": 10.0,
1600
- "learning_rate": 5.825426944971537e-06,
1601
- "loss": 0.9483,
1602
- "step": 1115
1603
- },
1604
- {
1605
- "epoch": 1.4326400000000001,
1606
- "grad_norm": 12.0625,
1607
- "learning_rate": 5.801707779886149e-06,
1608
- "loss": 0.9664,
1609
- "step": 1120
1610
- },
1611
- {
1612
- "epoch": 1.4390399999999999,
1613
- "grad_norm": 11.4375,
1614
- "learning_rate": 5.7779886148007595e-06,
1615
- "loss": 0.9139,
1616
- "step": 1125
1617
- },
1618
- {
1619
- "epoch": 1.44544,
1620
- "grad_norm": 12.4375,
1621
- "learning_rate": 5.754269449715371e-06,
1622
- "loss": 0.9448,
1623
- "step": 1130
1624
- },
1625
- {
1626
- "epoch": 1.45184,
1627
- "grad_norm": 11.125,
1628
- "learning_rate": 5.730550284629981e-06,
1629
- "loss": 1.0057,
1630
- "step": 1135
1631
- },
1632
- {
1633
- "epoch": 1.45824,
1634
- "grad_norm": 10.1875,
1635
- "learning_rate": 5.706831119544592e-06,
1636
- "loss": 0.926,
1637
- "step": 1140
1638
- },
1639
- {
1640
- "epoch": 1.46464,
1641
- "grad_norm": 11.5,
1642
- "learning_rate": 5.683111954459204e-06,
1643
- "loss": 0.9054,
1644
- "step": 1145
1645
- },
1646
- {
1647
- "epoch": 1.47104,
1648
- "grad_norm": 15.3125,
1649
- "learning_rate": 5.659392789373815e-06,
1650
- "loss": 0.9007,
1651
- "step": 1150
1652
- },
1653
- {
1654
- "epoch": 1.47744,
1655
- "grad_norm": 10.3125,
1656
- "learning_rate": 5.635673624288426e-06,
1657
- "loss": 0.905,
1658
- "step": 1155
1659
- },
1660
- {
1661
- "epoch": 1.48384,
1662
- "grad_norm": 10.9375,
1663
- "learning_rate": 5.611954459203036e-06,
1664
- "loss": 0.9792,
1665
- "step": 1160
1666
- },
1667
- {
1668
- "epoch": 1.49024,
1669
- "grad_norm": 11.4375,
1670
- "learning_rate": 5.588235294117647e-06,
1671
- "loss": 0.9011,
1672
- "step": 1165
1673
- },
1674
- {
1675
- "epoch": 1.49664,
1676
- "grad_norm": 11.3125,
1677
- "learning_rate": 5.564516129032258e-06,
1678
- "loss": 0.9596,
1679
- "step": 1170
1680
- },
1681
- {
1682
- "epoch": 1.50304,
1683
- "grad_norm": 10.5,
1684
- "learning_rate": 5.54079696394687e-06,
1685
- "loss": 0.8945,
1686
- "step": 1175
1687
- },
1688
- {
1689
- "epoch": 1.50304,
1690
- "eval_loss": 0.26298487186431885,
1691
- "eval_runtime": 10.579,
1692
- "eval_samples_per_second": 283.58,
1693
- "eval_steps_per_second": 8.886,
1694
- "step": 1175
1695
- },
1696
- {
1697
- "epoch": 1.5094400000000001,
1698
- "grad_norm": 12.0625,
1699
- "learning_rate": 5.517077798861481e-06,
1700
- "loss": 0.9582,
1701
- "step": 1180
1702
- },
1703
- {
1704
- "epoch": 1.5158399999999999,
1705
- "grad_norm": 11.1875,
1706
- "learning_rate": 5.493358633776091e-06,
1707
- "loss": 0.9596,
1708
- "step": 1185
1709
- },
1710
- {
1711
- "epoch": 1.52224,
1712
- "grad_norm": 11.6875,
1713
- "learning_rate": 5.4696394686907026e-06,
1714
- "loss": 0.9198,
1715
- "step": 1190
1716
- },
1717
- {
1718
- "epoch": 1.52864,
1719
- "grad_norm": 12.125,
1720
- "learning_rate": 5.445920303605313e-06,
1721
- "loss": 0.9322,
1722
- "step": 1195
1723
- },
1724
- {
1725
- "epoch": 1.53504,
1726
- "grad_norm": 11.875,
1727
- "learning_rate": 5.422201138519925e-06,
1728
- "loss": 0.9112,
1729
- "step": 1200
1730
- },
1731
- {
1732
- "epoch": 1.5414400000000001,
1733
- "grad_norm": 10.75,
1734
- "learning_rate": 5.398481973434535e-06,
1735
- "loss": 0.9301,
1736
- "step": 1205
1737
- },
1738
- {
1739
- "epoch": 1.5478399999999999,
1740
- "grad_norm": 11.0625,
1741
- "learning_rate": 5.3747628083491465e-06,
1742
- "loss": 0.9628,
1743
- "step": 1210
1744
- },
1745
- {
1746
- "epoch": 1.55424,
1747
- "grad_norm": 10.875,
1748
- "learning_rate": 5.351043643263758e-06,
1749
- "loss": 0.9276,
1750
- "step": 1215
1751
- },
1752
- {
1753
- "epoch": 1.56064,
1754
- "grad_norm": 11.125,
1755
- "learning_rate": 5.327324478178368e-06,
1756
- "loss": 0.975,
1757
- "step": 1220
1758
- },
1759
- {
1760
- "epoch": 1.56704,
1761
- "grad_norm": 12.6875,
1762
- "learning_rate": 5.30360531309298e-06,
1763
- "loss": 0.9388,
1764
- "step": 1225
1765
- },
1766
- {
1767
- "epoch": 1.57344,
1768
- "grad_norm": 11.0625,
1769
- "learning_rate": 5.2798861480075905e-06,
1770
- "loss": 0.9461,
1771
- "step": 1230
1772
- },
1773
- {
1774
- "epoch": 1.57984,
1775
- "grad_norm": 11.125,
1776
- "learning_rate": 5.256166982922202e-06,
1777
- "loss": 0.9541,
1778
- "step": 1235
1779
- },
1780
- {
1781
- "epoch": 1.58624,
1782
- "grad_norm": 12.1875,
1783
- "learning_rate": 5.232447817836812e-06,
1784
- "loss": 0.9502,
1785
- "step": 1240
1786
- },
1787
- {
1788
- "epoch": 1.5926399999999998,
1789
- "grad_norm": 11.625,
1790
- "learning_rate": 5.208728652751423e-06,
1791
- "loss": 0.9616,
1792
- "step": 1245
1793
- },
1794
- {
1795
- "epoch": 1.59904,
1796
- "grad_norm": 10.8125,
1797
- "learning_rate": 5.185009487666035e-06,
1798
- "loss": 0.9205,
1799
- "step": 1250
1800
- },
1801
- {
1802
- "epoch": 1.60544,
1803
- "grad_norm": 12.25,
1804
- "learning_rate": 5.161290322580646e-06,
1805
- "loss": 0.9682,
1806
- "step": 1255
1807
- },
1808
- {
1809
- "epoch": 1.61184,
1810
- "grad_norm": 11.25,
1811
- "learning_rate": 5.137571157495257e-06,
1812
- "loss": 0.9217,
1813
- "step": 1260
1814
- },
1815
- {
1816
- "epoch": 1.6182400000000001,
1817
- "grad_norm": 11.125,
1818
- "learning_rate": 5.113851992409867e-06,
1819
- "loss": 0.9166,
1820
- "step": 1265
1821
- },
1822
- {
1823
- "epoch": 1.6246399999999999,
1824
- "grad_norm": 10.875,
1825
- "learning_rate": 5.090132827324478e-06,
1826
- "loss": 0.9077,
1827
- "step": 1270
1828
- },
1829
- {
1830
- "epoch": 1.63104,
1831
- "grad_norm": 12.8125,
1832
- "learning_rate": 5.0664136622390896e-06,
1833
- "loss": 0.9197,
1834
- "step": 1275
1835
- },
1836
- {
1837
- "epoch": 1.63744,
1838
- "grad_norm": 11.25,
1839
- "learning_rate": 5.042694497153701e-06,
1840
- "loss": 0.9677,
1841
- "step": 1280
1842
- },
1843
- {
1844
- "epoch": 1.64384,
1845
- "grad_norm": 10.5625,
1846
- "learning_rate": 5.018975332068312e-06,
1847
- "loss": 0.8955,
1848
- "step": 1285
1849
- },
1850
- {
1851
- "epoch": 1.6502400000000002,
1852
- "grad_norm": 13.0625,
1853
- "learning_rate": 4.995256166982922e-06,
1854
- "loss": 0.946,
1855
- "step": 1290
1856
- },
1857
- {
1858
- "epoch": 1.65664,
1859
- "grad_norm": 11.3125,
1860
- "learning_rate": 4.9715370018975335e-06,
1861
- "loss": 0.9445,
1862
- "step": 1295
1863
- },
1864
- {
1865
- "epoch": 1.66304,
1866
- "grad_norm": 10.25,
1867
- "learning_rate": 4.947817836812145e-06,
1868
- "loss": 0.9178,
1869
- "step": 1300
1870
- },
1871
- {
1872
- "epoch": 1.66944,
1873
- "grad_norm": 11.3125,
1874
- "learning_rate": 4.924098671726756e-06,
1875
- "loss": 0.8687,
1876
- "step": 1305
1877
- },
1878
- {
1879
- "epoch": 1.67584,
1880
- "grad_norm": 11.1875,
1881
- "learning_rate": 4.900379506641367e-06,
1882
- "loss": 0.9116,
1883
- "step": 1310
1884
- },
1885
- {
1886
- "epoch": 1.68224,
1887
- "grad_norm": 11.3125,
1888
- "learning_rate": 4.8766603415559775e-06,
1889
- "loss": 0.9677,
1890
- "step": 1315
1891
- },
1892
- {
1893
- "epoch": 1.68864,
1894
- "grad_norm": 10.6875,
1895
- "learning_rate": 4.852941176470589e-06,
1896
- "loss": 0.9362,
1897
- "step": 1320
1898
- },
1899
- {
1900
- "epoch": 1.69504,
1901
- "grad_norm": 10.75,
1902
- "learning_rate": 4.8292220113852e-06,
1903
- "loss": 0.8902,
1904
- "step": 1325
1905
- },
1906
- {
1907
- "epoch": 1.7014399999999998,
1908
- "grad_norm": 10.1875,
1909
- "learning_rate": 4.80550284629981e-06,
1910
- "loss": 0.9391,
1911
- "step": 1330
1912
- },
1913
- {
1914
- "epoch": 1.70784,
1915
- "grad_norm": 11.25,
1916
- "learning_rate": 4.781783681214421e-06,
1917
- "loss": 0.916,
1918
- "step": 1335
1919
- },
1920
- {
1921
- "epoch": 1.71424,
1922
- "grad_norm": 10.1875,
1923
- "learning_rate": 4.758064516129033e-06,
1924
- "loss": 0.9203,
1925
- "step": 1340
1926
- },
1927
- {
1928
- "epoch": 1.72064,
1929
- "grad_norm": 10.125,
1930
- "learning_rate": 4.734345351043644e-06,
1931
- "loss": 0.9062,
1932
- "step": 1345
1933
- },
1934
- {
1935
- "epoch": 1.7270400000000001,
1936
- "grad_norm": 11.25,
1937
- "learning_rate": 4.710626185958255e-06,
1938
- "loss": 0.9008,
1939
- "step": 1350
1940
- },
1941
- {
1942
- "epoch": 1.7334399999999999,
1943
- "grad_norm": 12.375,
1944
- "learning_rate": 4.686907020872865e-06,
1945
- "loss": 0.9473,
1946
- "step": 1355
1947
- },
1948
- {
1949
- "epoch": 1.73984,
1950
- "grad_norm": 11.1875,
1951
- "learning_rate": 4.6631878557874766e-06,
1952
- "loss": 0.9015,
1953
- "step": 1360
1954
- },
1955
- {
1956
- "epoch": 1.74624,
1957
- "grad_norm": 9.8125,
1958
- "learning_rate": 4.639468690702088e-06,
1959
- "loss": 0.887,
1960
- "step": 1365
1961
- },
1962
- {
1963
- "epoch": 1.75264,
1964
- "grad_norm": 11.0,
1965
- "learning_rate": 4.615749525616698e-06,
1966
- "loss": 0.9051,
1967
- "step": 1370
1968
- },
1969
- {
1970
- "epoch": 1.7590400000000002,
1971
- "grad_norm": 10.875,
1972
- "learning_rate": 4.59203036053131e-06,
1973
- "loss": 0.9529,
1974
- "step": 1375
1975
- },
1976
- {
1977
- "epoch": 1.76544,
1978
- "grad_norm": 11.375,
1979
- "learning_rate": 4.5683111954459205e-06,
1980
- "loss": 0.9153,
1981
- "step": 1380
1982
- },
1983
- {
1984
- "epoch": 1.77184,
1985
- "grad_norm": 10.5625,
1986
- "learning_rate": 4.544592030360532e-06,
1987
- "loss": 0.9092,
1988
- "step": 1385
1989
- },
1990
- {
1991
- "epoch": 1.77824,
1992
- "grad_norm": 11.625,
1993
- "learning_rate": 4.520872865275143e-06,
1994
- "loss": 0.9069,
1995
- "step": 1390
1996
- },
1997
- {
1998
- "epoch": 1.78464,
1999
- "grad_norm": 11.6875,
2000
- "learning_rate": 4.497153700189753e-06,
2001
- "loss": 0.9266,
2002
- "step": 1395
2003
- },
2004
- {
2005
- "epoch": 1.79104,
2006
- "grad_norm": 10.6875,
2007
- "learning_rate": 4.4734345351043645e-06,
2008
- "loss": 0.9016,
2009
- "step": 1400
2010
- },
2011
- {
2012
- "epoch": 1.79744,
2013
- "grad_norm": 12.8125,
2014
- "learning_rate": 4.449715370018976e-06,
2015
- "loss": 1.0036,
2016
- "step": 1405
2017
- },
2018
- {
2019
- "epoch": 1.80384,
2020
- "grad_norm": 9.75,
2021
- "learning_rate": 4.425996204933587e-06,
2022
- "loss": 0.8785,
2023
- "step": 1410
2024
- },
2025
- {
2026
- "epoch": 1.80384,
2027
- "eval_loss": 0.25665631890296936,
2028
- "eval_runtime": 10.5748,
2029
- "eval_samples_per_second": 283.694,
2030
- "eval_steps_per_second": 8.889,
2031
- "step": 1410
2032
- },
2033
- {
2034
- "epoch": 1.8102399999999998,
2035
- "grad_norm": 10.4375,
2036
- "learning_rate": 4.402277039848198e-06,
2037
- "loss": 0.9293,
2038
- "step": 1415
2039
- },
2040
- {
2041
- "epoch": 1.81664,
2042
- "grad_norm": 11.5,
2043
- "learning_rate": 4.378557874762808e-06,
2044
- "loss": 0.884,
2045
- "step": 1420
2046
- },
2047
- {
2048
- "epoch": 1.82304,
2049
- "grad_norm": 11.9375,
2050
- "learning_rate": 4.35483870967742e-06,
2051
- "loss": 0.9769,
2052
- "step": 1425
2053
- },
2054
- {
2055
- "epoch": 1.82944,
2056
- "grad_norm": 10.4375,
2057
- "learning_rate": 4.331119544592031e-06,
2058
- "loss": 0.9082,
2059
- "step": 1430
2060
- },
2061
- {
2062
- "epoch": 1.8358400000000001,
2063
- "grad_norm": 11.6875,
2064
- "learning_rate": 4.307400379506642e-06,
2065
- "loss": 0.9163,
2066
- "step": 1435
2067
- },
2068
- {
2069
- "epoch": 1.8422399999999999,
2070
- "grad_norm": 10.0,
2071
- "learning_rate": 4.283681214421252e-06,
2072
- "loss": 0.8905,
2073
- "step": 1440
2074
- },
2075
- {
2076
- "epoch": 1.84864,
2077
- "grad_norm": 11.25,
2078
- "learning_rate": 4.259962049335864e-06,
2079
- "loss": 0.9245,
2080
- "step": 1445
2081
- },
2082
- {
2083
- "epoch": 1.85504,
2084
- "grad_norm": 11.9375,
2085
- "learning_rate": 4.236242884250475e-06,
2086
- "loss": 0.8869,
2087
- "step": 1450
2088
- },
2089
- {
2090
- "epoch": 1.86144,
2091
- "grad_norm": 11.1875,
2092
- "learning_rate": 4.212523719165086e-06,
2093
- "loss": 0.8913,
2094
- "step": 1455
2095
- },
2096
- {
2097
- "epoch": 1.86784,
2098
- "grad_norm": 11.375,
2099
- "learning_rate": 4.188804554079697e-06,
2100
- "loss": 0.8945,
2101
- "step": 1460
2102
- },
2103
- {
2104
- "epoch": 1.87424,
2105
- "grad_norm": 12.625,
2106
- "learning_rate": 4.1650853889943075e-06,
2107
- "loss": 0.949,
2108
- "step": 1465
2109
- },
2110
- {
2111
- "epoch": 1.88064,
2112
- "grad_norm": 10.8125,
2113
- "learning_rate": 4.141366223908919e-06,
2114
- "loss": 0.9274,
2115
- "step": 1470
2116
- },
2117
- {
2118
- "epoch": 1.88704,
2119
- "grad_norm": 11.375,
2120
- "learning_rate": 4.11764705882353e-06,
2121
- "loss": 0.9233,
2122
- "step": 1475
2123
- },
2124
- {
2125
- "epoch": 1.89344,
2126
- "grad_norm": 10.0,
2127
- "learning_rate": 4.09392789373814e-06,
2128
- "loss": 0.9211,
2129
- "step": 1480
2130
- },
2131
- {
2132
- "epoch": 1.89984,
2133
- "grad_norm": 10.875,
2134
- "learning_rate": 4.070208728652752e-06,
2135
- "loss": 0.9166,
2136
- "step": 1485
2137
- },
2138
- {
2139
- "epoch": 1.90624,
2140
- "grad_norm": 23.5,
2141
- "learning_rate": 4.046489563567363e-06,
2142
- "loss": 0.9434,
2143
- "step": 1490
2144
- },
2145
- {
2146
- "epoch": 1.9126400000000001,
2147
- "grad_norm": 11.3125,
2148
- "learning_rate": 4.022770398481974e-06,
2149
- "loss": 0.8756,
2150
- "step": 1495
2151
- },
2152
- {
2153
- "epoch": 1.9190399999999999,
2154
- "grad_norm": 11.25,
2155
- "learning_rate": 3.999051233396585e-06,
2156
- "loss": 0.9339,
2157
- "step": 1500
2158
- },
2159
- {
2160
- "epoch": 1.92544,
2161
- "grad_norm": 10.8125,
2162
- "learning_rate": 3.975332068311195e-06,
2163
- "loss": 0.8738,
2164
- "step": 1505
2165
- },
2166
- {
2167
- "epoch": 1.93184,
2168
- "grad_norm": 10.6875,
2169
- "learning_rate": 3.951612903225807e-06,
2170
- "loss": 0.8819,
2171
- "step": 1510
2172
- },
2173
- {
2174
- "epoch": 1.93824,
2175
- "grad_norm": 11.5625,
2176
- "learning_rate": 3.927893738140418e-06,
2177
- "loss": 0.9187,
2178
- "step": 1515
2179
- },
2180
- {
2181
- "epoch": 1.9446400000000001,
2182
- "grad_norm": 10.1875,
2183
- "learning_rate": 3.904174573055029e-06,
2184
- "loss": 0.9563,
2185
- "step": 1520
2186
- },
2187
- {
2188
- "epoch": 1.9510399999999999,
2189
- "grad_norm": 11.625,
2190
- "learning_rate": 3.88045540796964e-06,
2191
- "loss": 0.9009,
2192
- "step": 1525
2193
- },
2194
- {
2195
- "epoch": 1.95744,
2196
- "grad_norm": 10.6875,
2197
- "learning_rate": 3.8567362428842505e-06,
2198
- "loss": 0.9479,
2199
- "step": 1530
2200
- },
2201
- {
2202
- "epoch": 1.96384,
2203
- "grad_norm": 11.0,
2204
- "learning_rate": 3.833017077798862e-06,
2205
- "loss": 0.8906,
2206
- "step": 1535
2207
- },
2208
- {
2209
- "epoch": 1.97024,
2210
- "grad_norm": 11.6875,
2211
- "learning_rate": 3.8092979127134725e-06,
2212
- "loss": 0.888,
2213
- "step": 1540
2214
- },
2215
- {
2216
- "epoch": 1.97664,
2217
- "grad_norm": 11.375,
2218
- "learning_rate": 3.7855787476280837e-06,
2219
- "loss": 0.8915,
2220
- "step": 1545
2221
- },
2222
- {
2223
- "epoch": 1.98304,
2224
- "grad_norm": 10.125,
2225
- "learning_rate": 3.7618595825426945e-06,
2226
- "loss": 0.9009,
2227
- "step": 1550
2228
- },
2229
- {
2230
- "epoch": 1.98944,
2231
- "grad_norm": 12.375,
2232
- "learning_rate": 3.738140417457306e-06,
2233
- "loss": 0.9272,
2234
- "step": 1555
2235
- },
2236
- {
2237
- "epoch": 1.9958399999999998,
2238
- "grad_norm": 11.625,
2239
- "learning_rate": 3.714421252371917e-06,
2240
- "loss": 0.9792,
2241
- "step": 1560
2242
- },
2243
- {
2244
- "epoch": 2.00128,
2245
- "grad_norm": 10.75,
2246
- "learning_rate": 3.690702087286528e-06,
2247
- "loss": 0.7986,
2248
- "step": 1565
2249
- },
2250
- {
2251
- "epoch": 2.00768,
2252
- "grad_norm": 11.0625,
2253
- "learning_rate": 3.666982922201139e-06,
2254
- "loss": 0.8664,
2255
- "step": 1570
2256
- },
2257
- {
2258
- "epoch": 2.01408,
2259
- "grad_norm": 11.25,
2260
- "learning_rate": 3.6432637571157496e-06,
2261
- "loss": 0.8395,
2262
- "step": 1575
2263
- },
2264
- {
2265
- "epoch": 2.02048,
2266
- "grad_norm": 12.125,
2267
- "learning_rate": 3.619544592030361e-06,
2268
- "loss": 0.8114,
2269
- "step": 1580
2270
- },
2271
- {
2272
- "epoch": 2.02688,
2273
- "grad_norm": 11.3125,
2274
- "learning_rate": 3.5958254269449716e-06,
2275
- "loss": 0.8326,
2276
- "step": 1585
2277
- },
2278
- {
2279
- "epoch": 2.03328,
2280
- "grad_norm": 11.1875,
2281
- "learning_rate": 3.5721062618595832e-06,
2282
- "loss": 0.8522,
2283
- "step": 1590
2284
- },
2285
- {
2286
- "epoch": 2.03968,
2287
- "grad_norm": 10.6875,
2288
- "learning_rate": 3.548387096774194e-06,
2289
- "loss": 0.8482,
2290
- "step": 1595
2291
- },
2292
- {
2293
- "epoch": 2.04608,
2294
- "grad_norm": 9.875,
2295
- "learning_rate": 3.524667931688805e-06,
2296
- "loss": 0.8069,
2297
- "step": 1600
2298
- },
2299
- {
2300
- "epoch": 2.05248,
2301
- "grad_norm": 11.25,
2302
- "learning_rate": 3.500948766603416e-06,
2303
- "loss": 0.8341,
2304
- "step": 1605
2305
- },
2306
- {
2307
- "epoch": 2.05888,
2308
- "grad_norm": 10.8125,
2309
- "learning_rate": 3.4772296015180268e-06,
2310
- "loss": 0.8362,
2311
- "step": 1610
2312
- },
2313
- {
2314
- "epoch": 2.06528,
2315
- "grad_norm": 10.9375,
2316
- "learning_rate": 3.4535104364326375e-06,
2317
- "loss": 0.8232,
2318
- "step": 1615
2319
- },
2320
- {
2321
- "epoch": 2.07168,
2322
- "grad_norm": 10.9375,
2323
- "learning_rate": 3.4297912713472487e-06,
2324
- "loss": 0.8433,
2325
- "step": 1620
2326
- },
2327
- {
2328
- "epoch": 2.07808,
2329
- "grad_norm": 11.4375,
2330
- "learning_rate": 3.40607210626186e-06,
2331
- "loss": 0.8636,
2332
- "step": 1625
2333
- },
2334
- {
2335
- "epoch": 2.08448,
2336
- "grad_norm": 10.8125,
2337
- "learning_rate": 3.382352941176471e-06,
2338
- "loss": 0.7975,
2339
- "step": 1630
2340
- },
2341
- {
2342
- "epoch": 2.09088,
2343
- "grad_norm": 11.3125,
2344
- "learning_rate": 3.358633776091082e-06,
2345
- "loss": 0.8238,
2346
- "step": 1635
2347
- },
2348
- {
2349
- "epoch": 2.09728,
2350
- "grad_norm": 11.0,
2351
- "learning_rate": 3.334914611005693e-06,
2352
- "loss": 0.8312,
2353
- "step": 1640
2354
- },
2355
- {
2356
- "epoch": 2.1036799999999998,
2357
- "grad_norm": 11.125,
2358
- "learning_rate": 3.311195445920304e-06,
2359
- "loss": 0.8267,
2360
- "step": 1645
2361
- },
2362
- {
2363
- "epoch": 2.1036799999999998,
2364
- "eval_loss": 0.25601503252983093,
2365
- "eval_runtime": 10.58,
2366
- "eval_samples_per_second": 283.553,
2367
- "eval_steps_per_second": 8.885,
2368
- "step": 1645
2369
- },
2370
- {
2371
- "epoch": 2.11008,
2372
- "grad_norm": 12.9375,
2373
- "learning_rate": 3.2874762808349147e-06,
2374
- "loss": 0.8218,
2375
- "step": 1650
2376
- },
2377
- {
2378
- "epoch": 2.11648,
2379
- "grad_norm": 11.0,
2380
- "learning_rate": 3.263757115749526e-06,
2381
- "loss": 0.8254,
2382
- "step": 1655
2383
- },
2384
- {
2385
- "epoch": 2.12288,
2386
- "grad_norm": 12.875,
2387
- "learning_rate": 3.2400379506641366e-06,
2388
- "loss": 0.8359,
2389
- "step": 1660
2390
- },
2391
- {
2392
- "epoch": 2.12928,
2393
- "grad_norm": 10.3125,
2394
- "learning_rate": 3.2163187855787483e-06,
2395
- "loss": 0.8418,
2396
- "step": 1665
2397
- },
2398
- {
2399
- "epoch": 2.13568,
2400
- "grad_norm": 11.375,
2401
- "learning_rate": 3.192599620493359e-06,
2402
- "loss": 0.871,
2403
- "step": 1670
2404
- },
2405
- {
2406
- "epoch": 2.14208,
2407
- "grad_norm": 10.5625,
2408
- "learning_rate": 3.16888045540797e-06,
2409
- "loss": 0.8083,
2410
- "step": 1675
2411
- },
2412
- {
2413
- "epoch": 2.14848,
2414
- "grad_norm": 10.5,
2415
- "learning_rate": 3.145161290322581e-06,
2416
- "loss": 0.8607,
2417
- "step": 1680
2418
- },
2419
- {
2420
- "epoch": 2.15488,
2421
- "grad_norm": 11.0,
2422
- "learning_rate": 3.1214421252371918e-06,
2423
- "loss": 0.854,
2424
- "step": 1685
2425
- },
2426
- {
2427
- "epoch": 2.16128,
2428
- "grad_norm": 11.5,
2429
- "learning_rate": 3.0977229601518026e-06,
2430
- "loss": 0.833,
2431
- "step": 1690
2432
- },
2433
- {
2434
- "epoch": 2.16768,
2435
- "grad_norm": 10.4375,
2436
- "learning_rate": 3.0740037950664138e-06,
2437
- "loss": 0.8545,
2438
- "step": 1695
2439
- },
2440
- {
2441
- "epoch": 2.17408,
2442
- "grad_norm": 10.625,
2443
- "learning_rate": 3.050284629981025e-06,
2444
- "loss": 0.8632,
2445
- "step": 1700
2446
- },
2447
- {
2448
- "epoch": 2.18048,
2449
- "grad_norm": 12.375,
2450
- "learning_rate": 3.026565464895636e-06,
2451
- "loss": 0.8491,
2452
- "step": 1705
2453
- },
2454
- {
2455
- "epoch": 2.18688,
2456
- "grad_norm": 11.25,
2457
- "learning_rate": 3.002846299810247e-06,
2458
- "loss": 0.8213,
2459
- "step": 1710
2460
- },
2461
- {
2462
- "epoch": 2.19328,
2463
- "grad_norm": 11.0625,
2464
- "learning_rate": 2.979127134724858e-06,
2465
- "loss": 0.8302,
2466
- "step": 1715
2467
- },
2468
- {
2469
- "epoch": 2.19968,
2470
- "grad_norm": 11.9375,
2471
- "learning_rate": 2.955407969639469e-06,
2472
- "loss": 0.8304,
2473
- "step": 1720
2474
- },
2475
- {
2476
- "epoch": 2.20608,
2477
- "grad_norm": 11.9375,
2478
- "learning_rate": 2.9316888045540797e-06,
2479
- "loss": 0.8355,
2480
- "step": 1725
2481
- },
2482
- {
2483
- "epoch": 2.2124800000000002,
2484
- "grad_norm": 10.125,
2485
- "learning_rate": 2.907969639468691e-06,
2486
- "loss": 0.8197,
2487
- "step": 1730
2488
- },
2489
- {
2490
- "epoch": 2.21888,
2491
- "grad_norm": 10.375,
2492
- "learning_rate": 2.884250474383302e-06,
2493
- "loss": 0.8152,
2494
- "step": 1735
2495
- },
2496
- {
2497
- "epoch": 2.22528,
2498
- "grad_norm": 10.9375,
2499
- "learning_rate": 2.8605313092979133e-06,
2500
- "loss": 0.8431,
2501
- "step": 1740
2502
- },
2503
- {
2504
- "epoch": 2.23168,
2505
- "grad_norm": 10.5,
2506
- "learning_rate": 2.836812144212524e-06,
2507
- "loss": 0.8695,
2508
- "step": 1745
2509
- },
2510
- {
2511
- "epoch": 2.23808,
2512
- "grad_norm": 10.25,
2513
- "learning_rate": 2.813092979127135e-06,
2514
- "loss": 0.8148,
2515
- "step": 1750
2516
- },
2517
- {
2518
- "epoch": 2.24448,
2519
- "grad_norm": 11.0625,
2520
- "learning_rate": 2.789373814041746e-06,
2521
- "loss": 0.8559,
2522
- "step": 1755
2523
- },
2524
- {
2525
- "epoch": 2.25088,
2526
- "grad_norm": 10.8125,
2527
- "learning_rate": 2.765654648956357e-06,
2528
- "loss": 0.8777,
2529
- "step": 1760
2530
- },
2531
- {
2532
- "epoch": 2.25728,
2533
- "grad_norm": 10.0,
2534
- "learning_rate": 2.7419354838709676e-06,
2535
- "loss": 0.8607,
2536
- "step": 1765
2537
- },
2538
- {
2539
- "epoch": 2.26368,
2540
- "grad_norm": 10.375,
2541
- "learning_rate": 2.718216318785579e-06,
2542
- "loss": 0.8301,
2543
- "step": 1770
2544
- },
2545
- {
2546
- "epoch": 2.27008,
2547
- "grad_norm": 10.375,
2548
- "learning_rate": 2.69449715370019e-06,
2549
- "loss": 0.8315,
2550
- "step": 1775
2551
- },
2552
- {
2553
- "epoch": 2.27648,
2554
- "grad_norm": 11.25,
2555
- "learning_rate": 2.670777988614801e-06,
2556
- "loss": 0.8083,
2557
- "step": 1780
2558
- },
2559
- {
2560
- "epoch": 2.28288,
2561
- "grad_norm": 12.375,
2562
- "learning_rate": 2.647058823529412e-06,
2563
- "loss": 0.8362,
2564
- "step": 1785
2565
- },
2566
- {
2567
- "epoch": 2.2892799999999998,
2568
- "grad_norm": 12.0625,
2569
- "learning_rate": 2.6233396584440227e-06,
2570
- "loss": 0.8162,
2571
- "step": 1790
2572
- },
2573
- {
2574
- "epoch": 2.29568,
2575
- "grad_norm": 10.75,
2576
- "learning_rate": 2.599620493358634e-06,
2577
- "loss": 0.8662,
2578
- "step": 1795
2579
- },
2580
- {
2581
- "epoch": 2.30208,
2582
- "grad_norm": 12.0625,
2583
- "learning_rate": 2.5759013282732447e-06,
2584
- "loss": 0.8538,
2585
- "step": 1800
2586
- },
2587
- {
2588
- "epoch": 2.30848,
2589
- "grad_norm": 12.8125,
2590
- "learning_rate": 2.552182163187856e-06,
2591
- "loss": 0.8508,
2592
- "step": 1805
2593
- },
2594
- {
2595
- "epoch": 2.31488,
2596
- "grad_norm": 11.3125,
2597
- "learning_rate": 2.528462998102467e-06,
2598
- "loss": 0.9202,
2599
- "step": 1810
2600
- },
2601
- {
2602
- "epoch": 2.32128,
2603
- "grad_norm": 10.9375,
2604
- "learning_rate": 2.5047438330170783e-06,
2605
- "loss": 0.8008,
2606
- "step": 1815
2607
- },
2608
- {
2609
- "epoch": 2.32768,
2610
- "grad_norm": 11.75,
2611
- "learning_rate": 2.481024667931689e-06,
2612
- "loss": 0.8479,
2613
- "step": 1820
2614
- },
2615
- {
2616
- "epoch": 2.33408,
2617
- "grad_norm": 10.25,
2618
- "learning_rate": 2.4573055028463e-06,
2619
- "loss": 0.8138,
2620
- "step": 1825
2621
- },
2622
- {
2623
- "epoch": 2.34048,
2624
- "grad_norm": 10.9375,
2625
- "learning_rate": 2.433586337760911e-06,
2626
- "loss": 0.8237,
2627
- "step": 1830
2628
- },
2629
- {
2630
- "epoch": 2.34688,
2631
- "grad_norm": 12.0625,
2632
- "learning_rate": 2.4098671726755223e-06,
2633
- "loss": 0.8329,
2634
- "step": 1835
2635
- },
2636
- {
2637
- "epoch": 2.35328,
2638
- "grad_norm": 10.5,
2639
- "learning_rate": 2.386148007590133e-06,
2640
- "loss": 0.8131,
2641
- "step": 1840
2642
- },
2643
- {
2644
- "epoch": 2.35968,
2645
- "grad_norm": 10.3125,
2646
- "learning_rate": 2.362428842504744e-06,
2647
- "loss": 0.7882,
2648
- "step": 1845
2649
- },
2650
- {
2651
- "epoch": 2.36608,
2652
- "grad_norm": 11.6875,
2653
- "learning_rate": 2.338709677419355e-06,
2654
- "loss": 0.8035,
2655
- "step": 1850
2656
- },
2657
- {
2658
- "epoch": 2.37248,
2659
- "grad_norm": 11.5,
2660
- "learning_rate": 2.314990512333966e-06,
2661
- "loss": 0.8228,
2662
- "step": 1855
2663
- },
2664
- {
2665
- "epoch": 2.37888,
2666
- "grad_norm": 12.0625,
2667
- "learning_rate": 2.291271347248577e-06,
2668
- "loss": 0.8659,
2669
- "step": 1860
2670
- },
2671
- {
2672
- "epoch": 2.38528,
2673
- "grad_norm": 10.625,
2674
- "learning_rate": 2.2675521821631878e-06,
2675
- "loss": 0.7836,
2676
- "step": 1865
2677
- },
2678
- {
2679
- "epoch": 2.39168,
2680
- "grad_norm": 10.25,
2681
- "learning_rate": 2.243833017077799e-06,
2682
- "loss": 0.8444,
2683
- "step": 1870
2684
- },
2685
- {
2686
- "epoch": 2.39808,
2687
- "grad_norm": 10.375,
2688
- "learning_rate": 2.22011385199241e-06,
2689
- "loss": 0.8045,
2690
- "step": 1875
2691
- },
2692
- {
2693
- "epoch": 2.40448,
2694
- "grad_norm": 11.5,
2695
- "learning_rate": 2.196394686907021e-06,
2696
- "loss": 0.8304,
2697
- "step": 1880
2698
- },
2699
- {
2700
- "epoch": 2.40448,
2701
- "eval_loss": 0.2543569803237915,
2702
- "eval_runtime": 10.5822,
2703
- "eval_samples_per_second": 283.496,
2704
- "eval_steps_per_second": 8.883,
2705
- "step": 1880
2706
- },
2707
- {
2708
- "epoch": 2.41088,
2709
- "grad_norm": 10.5625,
2710
- "learning_rate": 2.172675521821632e-06,
2711
- "loss": 0.8291,
2712
- "step": 1885
2713
- },
2714
- {
2715
- "epoch": 2.41728,
2716
- "grad_norm": 11.375,
2717
- "learning_rate": 2.1489563567362433e-06,
2718
- "loss": 0.8204,
2719
- "step": 1890
2720
- },
2721
- {
2722
- "epoch": 2.42368,
2723
- "grad_norm": 10.3125,
2724
- "learning_rate": 2.125237191650854e-06,
2725
- "loss": 0.8508,
2726
- "step": 1895
2727
- },
2728
- {
2729
- "epoch": 2.4300800000000002,
2730
- "grad_norm": 11.625,
2731
- "learning_rate": 2.101518026565465e-06,
2732
- "loss": 0.8331,
2733
- "step": 1900
2734
- },
2735
- {
2736
- "epoch": 2.43648,
2737
- "grad_norm": 10.125,
2738
- "learning_rate": 2.077798861480076e-06,
2739
- "loss": 0.8018,
2740
- "step": 1905
2741
- },
2742
- {
2743
- "epoch": 2.44288,
2744
- "grad_norm": 11.875,
2745
- "learning_rate": 2.0540796963946873e-06,
2746
- "loss": 0.8022,
2747
- "step": 1910
2748
- },
2749
- {
2750
- "epoch": 2.44928,
2751
- "grad_norm": 11.0,
2752
- "learning_rate": 2.030360531309298e-06,
2753
- "loss": 0.7974,
2754
- "step": 1915
2755
- },
2756
- {
2757
- "epoch": 2.45568,
2758
- "grad_norm": 9.75,
2759
- "learning_rate": 2.006641366223909e-06,
2760
- "loss": 0.8264,
2761
- "step": 1920
2762
- },
2763
- {
2764
- "epoch": 2.46208,
2765
- "grad_norm": 11.25,
2766
- "learning_rate": 1.98292220113852e-06,
2767
- "loss": 0.862,
2768
- "step": 1925
2769
- },
2770
- {
2771
- "epoch": 2.46848,
2772
- "grad_norm": 10.25,
2773
- "learning_rate": 1.9592030360531312e-06,
2774
- "loss": 0.8111,
2775
- "step": 1930
2776
- },
2777
- {
2778
- "epoch": 2.47488,
2779
- "grad_norm": 10.5625,
2780
- "learning_rate": 1.935483870967742e-06,
2781
- "loss": 0.8225,
2782
- "step": 1935
2783
- },
2784
- {
2785
- "epoch": 2.48128,
2786
- "grad_norm": 10.5,
2787
- "learning_rate": 1.9117647058823528e-06,
2788
- "loss": 0.8366,
2789
- "step": 1940
2790
- },
2791
- {
2792
- "epoch": 2.48768,
2793
- "grad_norm": 11.125,
2794
- "learning_rate": 1.8880455407969642e-06,
2795
- "loss": 0.8294,
2796
- "step": 1945
2797
- },
2798
- {
2799
- "epoch": 2.49408,
2800
- "grad_norm": 11.375,
2801
- "learning_rate": 1.8643263757115752e-06,
2802
- "loss": 0.8724,
2803
- "step": 1950
2804
- },
2805
- {
2806
- "epoch": 2.50048,
2807
- "grad_norm": 12.1875,
2808
- "learning_rate": 1.840607210626186e-06,
2809
- "loss": 0.8309,
2810
- "step": 1955
2811
- },
2812
- {
2813
- "epoch": 2.5068799999999998,
2814
- "grad_norm": 10.625,
2815
- "learning_rate": 1.8168880455407971e-06,
2816
- "loss": 0.8024,
2817
- "step": 1960
2818
- },
2819
- {
2820
- "epoch": 2.51328,
2821
- "grad_norm": 11.25,
2822
- "learning_rate": 1.7931688804554081e-06,
2823
- "loss": 0.8397,
2824
- "step": 1965
2825
- },
2826
- {
2827
- "epoch": 2.51968,
2828
- "grad_norm": 11.1875,
2829
- "learning_rate": 1.7694497153700191e-06,
2830
- "loss": 0.876,
2831
- "step": 1970
2832
- },
2833
- {
2834
- "epoch": 2.52608,
2835
- "grad_norm": 11.6875,
2836
- "learning_rate": 1.7457305502846301e-06,
2837
- "loss": 0.8141,
2838
- "step": 1975
2839
- },
2840
- {
2841
- "epoch": 2.53248,
2842
- "grad_norm": 10.6875,
2843
- "learning_rate": 1.7220113851992413e-06,
2844
- "loss": 0.8428,
2845
- "step": 1980
2846
- },
2847
- {
2848
- "epoch": 2.53888,
2849
- "grad_norm": 10.1875,
2850
- "learning_rate": 1.698292220113852e-06,
2851
- "loss": 0.8223,
2852
- "step": 1985
2853
- },
2854
- {
2855
- "epoch": 2.54528,
2856
- "grad_norm": 11.125,
2857
- "learning_rate": 1.674573055028463e-06,
2858
- "loss": 0.8292,
2859
- "step": 1990
2860
- },
2861
- {
2862
- "epoch": 2.55168,
2863
- "grad_norm": 11.1875,
2864
- "learning_rate": 1.6508538899430743e-06,
2865
- "loss": 0.8279,
2866
- "step": 1995
2867
- },
2868
- {
2869
- "epoch": 2.55808,
2870
- "grad_norm": 10.875,
2871
- "learning_rate": 1.6271347248576853e-06,
2872
- "loss": 0.85,
2873
- "step": 2000
2874
- },
2875
- {
2876
- "epoch": 2.56448,
2877
- "grad_norm": 11.0625,
2878
- "learning_rate": 1.603415559772296e-06,
2879
- "loss": 0.8005,
2880
- "step": 2005
2881
- },
2882
- {
2883
- "epoch": 2.57088,
2884
- "grad_norm": 11.125,
2885
- "learning_rate": 1.579696394686907e-06,
2886
- "loss": 0.8473,
2887
- "step": 2010
2888
- },
2889
- {
2890
- "epoch": 2.57728,
2891
- "grad_norm": 11.9375,
2892
- "learning_rate": 1.5559772296015182e-06,
2893
- "loss": 0.8601,
2894
- "step": 2015
2895
- },
2896
- {
2897
- "epoch": 2.58368,
2898
- "grad_norm": 10.8125,
2899
- "learning_rate": 1.5322580645161292e-06,
2900
- "loss": 0.834,
2901
- "step": 2020
2902
- },
2903
- {
2904
- "epoch": 2.59008,
2905
- "grad_norm": 10.9375,
2906
- "learning_rate": 1.5085388994307402e-06,
2907
- "loss": 0.821,
2908
- "step": 2025
2909
- },
2910
- {
2911
- "epoch": 2.59648,
2912
- "grad_norm": 10.6875,
2913
- "learning_rate": 1.484819734345351e-06,
2914
- "loss": 0.817,
2915
- "step": 2030
2916
- },
2917
- {
2918
- "epoch": 2.60288,
2919
- "grad_norm": 11.0625,
2920
- "learning_rate": 1.4611005692599622e-06,
2921
- "loss": 0.8708,
2922
- "step": 2035
2923
- },
2924
- {
2925
- "epoch": 2.60928,
2926
- "grad_norm": 9.6875,
2927
- "learning_rate": 1.4373814041745732e-06,
2928
- "loss": 0.8206,
2929
- "step": 2040
2930
- },
2931
- {
2932
- "epoch": 2.6156800000000002,
2933
- "grad_norm": 12.625,
2934
- "learning_rate": 1.4136622390891841e-06,
2935
- "loss": 0.8189,
2936
- "step": 2045
2937
- },
2938
- {
2939
- "epoch": 2.62208,
2940
- "grad_norm": 12.1875,
2941
- "learning_rate": 1.3899430740037953e-06,
2942
- "loss": 0.8502,
2943
- "step": 2050
2944
- },
2945
- {
2946
- "epoch": 2.62848,
2947
- "grad_norm": 12.375,
2948
- "learning_rate": 1.3662239089184063e-06,
2949
- "loss": 0.8526,
2950
- "step": 2055
2951
- },
2952
- {
2953
- "epoch": 2.63488,
2954
- "grad_norm": 10.8125,
2955
- "learning_rate": 1.342504743833017e-06,
2956
- "loss": 0.8339,
2957
- "step": 2060
2958
- },
2959
- {
2960
- "epoch": 2.64128,
2961
- "grad_norm": 11.0,
2962
- "learning_rate": 1.318785578747628e-06,
2963
- "loss": 0.8204,
2964
- "step": 2065
2965
- },
2966
- {
2967
- "epoch": 2.6476800000000003,
2968
- "grad_norm": 10.6875,
2969
- "learning_rate": 1.2950664136622393e-06,
2970
- "loss": 0.8494,
2971
- "step": 2070
2972
- },
2973
- {
2974
- "epoch": 2.65408,
2975
- "grad_norm": 11.375,
2976
- "learning_rate": 1.2713472485768503e-06,
2977
- "loss": 0.8293,
2978
- "step": 2075
2979
- },
2980
- {
2981
- "epoch": 2.6604799999999997,
2982
- "grad_norm": 11.8125,
2983
- "learning_rate": 1.247628083491461e-06,
2984
- "loss": 0.8421,
2985
- "step": 2080
2986
- },
2987
- {
2988
- "epoch": 2.66688,
2989
- "grad_norm": 11.125,
2990
- "learning_rate": 1.2239089184060723e-06,
2991
- "loss": 0.825,
2992
- "step": 2085
2993
- },
2994
- {
2995
- "epoch": 2.67328,
2996
- "grad_norm": 10.625,
2997
- "learning_rate": 1.2001897533206832e-06,
2998
- "loss": 0.8053,
2999
- "step": 2090
3000
- },
3001
- {
3002
- "epoch": 2.67968,
3003
- "grad_norm": 11.375,
3004
- "learning_rate": 1.1764705882352942e-06,
3005
- "loss": 0.8085,
3006
- "step": 2095
3007
- },
3008
- {
3009
- "epoch": 2.68608,
3010
- "grad_norm": 12.0,
3011
- "learning_rate": 1.1527514231499052e-06,
3012
- "loss": 0.8437,
3013
- "step": 2100
3014
- },
3015
- {
3016
- "epoch": 2.6924799999999998,
3017
- "grad_norm": 11.75,
3018
- "learning_rate": 1.1290322580645162e-06,
3019
- "loss": 0.8694,
3020
- "step": 2105
3021
- },
3022
- {
3023
- "epoch": 2.69888,
3024
- "grad_norm": 11.8125,
3025
- "learning_rate": 1.1053130929791272e-06,
3026
- "loss": 0.8392,
3027
- "step": 2110
3028
- },
3029
- {
3030
- "epoch": 2.70528,
3031
- "grad_norm": 11.4375,
3032
- "learning_rate": 1.0815939278937382e-06,
3033
- "loss": 0.7962,
3034
- "step": 2115
3035
- },
3036
- {
3037
- "epoch": 2.70528,
3038
- "eval_loss": 0.25380879640579224,
3039
- "eval_runtime": 10.5748,
3040
- "eval_samples_per_second": 283.694,
3041
- "eval_steps_per_second": 8.889,
3042
- "step": 2115
3043
- }
3044
- ],
3045
- "logging_steps": 5,
3046
- "max_steps": 2343,
3047
- "num_input_tokens_seen": 0,
3048
- "num_train_epochs": 3,
3049
- "save_steps": 235,
3050
- "stateful_callbacks": {
3051
- "EarlyStoppingCallback": {
3052
- "args": {
3053
- "early_stopping_patience": 2,
3054
- "early_stopping_threshold": 0.0
3055
- },
3056
- "attributes": {
3057
- "early_stopping_patience_counter": 0
3058
- }
3059
- },
3060
- "TrainerControl": {
3061
- "args": {
3062
- "should_epoch_stop": false,
3063
- "should_evaluate": false,
3064
- "should_log": false,
3065
- "should_save": true,
3066
- "should_training_stop": false
3067
- },
3068
- "attributes": {}
3069
- }
3070
- },
3071
- "total_flos": 1.934075373662765e+18,
3072
- "train_batch_size": 2,
3073
- "trial_name": null,
3074
- "trial_params": null
3075
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2115/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa720bf74892db7f1a10bd6bd7158e5f8b89b5460f2b088b49c1ac7e0048256b
3
- size 5496