Hugging Face's logo

JingyeChen22
/
textdiffuser2-full-ft

Text-to-Image
Diffusers
Safetensors
StableDiffusionPipeline
Model card Files
xet
Community
1
JingyeChen22 commited on
Commit
24c6376
·
1 Parent(s): 7d4a9c4

Delete layout_planner_m1

Browse files
Files changed (11) hide show
  1. layout_planner_m1/config.json +0 -26
  2. layout_planner_m1/generation_config.json +0 -9
  3. layout_planner_m1/pytorch_model-00001-of-00003.bin +0 -3
  4. layout_planner_m1/pytorch_model-00002-of-00003.bin +0 -3
  5. layout_planner_m1/pytorch_model-00003-of-00003.bin +0 -3
  6. layout_planner_m1/pytorch_model.bin.index.json +0 -330
  7. layout_planner_m1/special_tokens_map.json +0 -24
  8. layout_planner_m1/tokenizer.model +0 -3
  9. layout_planner_m1/tokenizer_config.json +0 -35
  10. layout_planner_m1/trainer_state.json +0 -2797
  11. layout_planner_m1/training_args.bin +0 -3
layout_planner_m1/config.json DELETED
@@ -1,26 +0,0 @@
1
- {
2
- "_name_or_path": "lmsys/vicuna-7b-v1.5",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "bos_token_id": 1,
7
- "eos_token_id": 2,
8
- "hidden_act": "silu",
9
- "hidden_size": 4096,
10
- "initializer_range": 0.02,
11
- "intermediate_size": 11008,
12
- "max_position_embeddings": 4096,
13
- "model_type": "llama",
14
- "num_attention_heads": 32,
15
- "num_hidden_layers": 32,
16
- "num_key_value_heads": 32,
17
- "pad_token_id": 0,
18
- "pretraining_tp": 1,
19
- "rms_norm_eps": 1e-05,
20
- "rope_scaling": null,
21
- "tie_word_embeddings": false,
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.28.1",
24
- "use_cache": true,
25
- "vocab_size": 32000
26
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
layout_planner_m1/generation_config.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "bos_token_id": 1,
3
- "eos_token_id": 2,
4
- "max_length": 4096,
5
- "pad_token_id": 0,
6
- "temperature": 0.9,
7
- "top_p": 0.6,
8
- "transformers_version": "4.28.1"
9
- }
 
 
 
 
 
 
 
 
 
 
layout_planner_m1/pytorch_model-00001-of-00003.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bdf47d029f2dac9dace788703e64302bbc35da51ac174836b331a6fc32b446e
3
- size 9877989586
 
 
 
 
layout_planner_m1/pytorch_model-00002-of-00003.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:899f2dffbb3988d1d5018fabb7d4f811d507ba53a49f963cb563ab0b0a85d4b3
3
- size 9894801014
 
 
 
 
layout_planner_m1/pytorch_model-00003-of-00003.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:621323abc17186718c18e1a61f70ae649002e6a2c1d71498dfb3638c777aca64
3
- size 7180990649
 
 
 
 
layout_planner_m1/pytorch_model.bin.index.json DELETED
@@ -1,330 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 26953670656
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
- "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
- "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
- "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
- "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
- "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
- "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
- "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
- "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
- "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
- "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
17
- "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
18
- "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
19
- "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
20
- "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
21
- "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
22
- "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
23
- "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
24
- "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
25
- "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
26
- "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
27
- "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
28
- "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
29
- "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
30
- "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
31
- "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
32
- "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
33
- "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
34
- "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
35
- "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
36
- "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
37
- "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
38
- "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
39
- "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
40
- "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
41
- "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
42
- "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
43
- "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
44
- "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
45
- "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
46
- "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
47
- "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
48
- "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
49
- "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
50
- "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
51
- "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
52
- "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
53
- "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
54
- "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
55
- "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
56
- "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
57
- "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
58
- "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
59
- "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
60
- "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
61
- "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
62
- "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
63
- "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
64
- "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
65
- "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
66
- "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
67
- "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
68
- "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
69
- "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
70
- "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
71
- "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
72
- "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
73
- "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
74
- "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
75
- "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
76
- "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
77
- "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
78
- "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
79
- "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
80
- "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
81
- "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
82
- "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
83
- "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
84
- "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
85
- "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
86
- "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
87
- "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
88
- "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
89
- "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
90
- "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
91
- "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
92
- "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
93
- "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
94
- "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
95
- "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
96
- "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
97
- "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
- "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
- "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
- "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
- "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
- "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
- "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
- "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
- "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
- "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
107
- "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
108
- "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
109
- "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
110
- "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
111
- "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
112
- "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
113
- "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
114
- "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
115
- "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
116
- "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
117
- "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
118
- "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
119
- "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
120
- "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
121
- "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
122
- "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
123
- "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
124
- "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
125
- "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
126
- "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
127
- "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
128
- "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
129
- "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
130
- "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
131
- "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
132
- "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
133
- "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
134
- "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
135
- "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
136
- "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
137
- "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
138
- "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
- "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
140
- "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
141
- "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
142
- "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
143
- "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
144
- "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
145
- "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
146
- "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
147
- "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
148
- "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
149
- "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
150
- "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
151
- "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
152
- "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
- "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
154
- "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
155
- "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
156
- "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
157
- "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
158
- "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
159
- "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
160
- "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
161
- "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
162
- "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
163
- "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
164
- "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
165
- "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
166
- "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
167
- "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
168
- "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
169
- "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
170
- "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
171
- "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
172
- "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
173
- "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
174
- "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
175
- "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
176
- "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
177
- "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
178
- "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
179
- "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
180
- "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
181
- "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
182
- "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
183
- "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
184
- "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
185
- "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
186
- "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
187
- "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
188
- "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
189
- "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
190
- "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
191
- "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
192
- "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
193
- "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
194
- "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
195
- "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
196
- "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
197
- "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
198
- "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
199
- "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
200
- "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
201
- "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
202
- "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
203
- "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
204
- "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
205
- "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
206
- "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
207
- "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
208
- "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
209
- "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
210
- "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
211
- "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
212
- "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
213
- "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
214
- "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
215
- "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
216
- "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
217
- "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
218
- "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
219
- "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
220
- "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
221
- "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
222
- "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
223
- "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
224
- "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
225
- "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
226
- "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
227
- "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
228
- "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
229
- "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
230
- "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
231
- "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
232
- "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
233
- "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
234
- "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
235
- "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
236
- "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
237
- "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
238
- "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
239
- "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
240
- "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
241
- "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
242
- "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
243
- "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
244
- "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
245
- "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
246
- "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
247
- "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
248
- "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
249
- "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
250
- "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
251
- "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
252
- "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
253
- "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
254
- "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
255
- "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
256
- "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
257
- "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
258
- "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
259
- "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
260
- "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
261
- "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
262
- "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
263
- "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
264
- "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
265
- "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
266
- "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
267
- "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
268
- "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
269
- "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
270
- "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
271
- "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
272
- "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
273
- "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
274
- "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
275
- "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
276
- "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
277
- "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
278
- "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
279
- "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
280
- "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
281
- "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
282
- "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
283
- "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
284
- "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
285
- "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
286
- "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
287
- "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
288
- "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
289
- "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
290
- "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
291
- "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
292
- "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
293
- "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
294
- "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
295
- "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
296
- "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
297
- "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
298
- "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
299
- "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
300
- "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
301
- "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
302
- "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
303
- "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
304
- "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
305
- "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
306
- "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
307
- "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
308
- "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
309
- "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
310
- "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
311
- "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
312
- "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
313
- "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
314
- "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
315
- "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
316
- "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
317
- "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
318
- "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
319
- "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
320
- "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
321
- "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
322
- "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
323
- "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
324
- "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
325
- "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
326
- "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
327
- "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
328
- "model.norm.weight": "pytorch_model-00003-of-00003.bin"
329
- }
330
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
layout_planner_m1/special_tokens_map.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "<unk>",
17
- "unk_token": {
18
- "content": "<unk>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
layout_planner_m1/tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
- size 499723
 
 
 
 
layout_planner_m1/tokenizer_config.json DELETED
@@ -1,35 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "bos_token": {
5
- "__type": "AddedToken",
6
- "content": "<s>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "clean_up_tokenization_spaces": false,
13
- "eos_token": {
14
- "__type": "AddedToken",
15
- "content": "</s>",
16
- "lstrip": false,
17
- "normalized": false,
18
- "rstrip": false,
19
- "single_word": false
20
- },
21
- "legacy": false,
22
- "model_max_length": 2048,
23
- "pad_token": null,
24
- "padding_side": "right",
25
- "sp_model_kwargs": {},
26
- "tokenizer_class": "LlamaTokenizer",
27
- "unk_token": {
28
- "__type": "AddedToken",
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false
34
- }
35
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
layout_planner_m1/trainer_state.json DELETED
@@ -1,2797 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 5.97092084006462,
5
- "global_step": 462,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.01,
12
- "learning_rate": 1.4285714285714286e-06,
13
- "loss": 2.1703,
14
- "step": 1
15
- },
16
- {
17
- "epoch": 0.03,
18
- "learning_rate": 2.8571428571428573e-06,
19
- "loss": 2.1529,
20
- "step": 2
21
- },
22
- {
23
- "epoch": 0.04,
24
- "learning_rate": 4.2857142857142855e-06,
25
- "loss": 1.4343,
26
- "step": 3
27
- },
28
- {
29
- "epoch": 0.05,
30
- "learning_rate": 5.7142857142857145e-06,
31
- "loss": 1.3822,
32
- "step": 4
33
- },
34
- {
35
- "epoch": 0.06,
36
- "learning_rate": 7.1428571428571436e-06,
37
- "loss": 1.259,
38
- "step": 5
39
- },
40
- {
41
- "epoch": 0.08,
42
- "learning_rate": 8.571428571428571e-06,
43
- "loss": 1.231,
44
- "step": 6
45
- },
46
- {
47
- "epoch": 0.09,
48
- "learning_rate": 1e-05,
49
- "loss": 1.1535,
50
- "step": 7
51
- },
52
- {
53
- "epoch": 0.1,
54
- "learning_rate": 1.1428571428571429e-05,
55
- "loss": 1.1701,
56
- "step": 8
57
- },
58
- {
59
- "epoch": 0.12,
60
- "learning_rate": 1.2857142857142859e-05,
61
- "loss": 1.1408,
62
- "step": 9
63
- },
64
- {
65
- "epoch": 0.13,
66
- "learning_rate": 1.4285714285714287e-05,
67
- "loss": 1.1468,
68
- "step": 10
69
- },
70
- {
71
- "epoch": 0.14,
72
- "learning_rate": 1.5714285714285715e-05,
73
- "loss": 1.1389,
74
- "step": 11
75
- },
76
- {
77
- "epoch": 0.16,
78
- "learning_rate": 1.7142857142857142e-05,
79
- "loss": 1.0866,
80
- "step": 12
81
- },
82
- {
83
- "epoch": 0.17,
84
- "learning_rate": 1.8571428571428575e-05,
85
- "loss": 1.0794,
86
- "step": 13
87
- },
88
- {
89
- "epoch": 0.18,
90
- "learning_rate": 2e-05,
91
- "loss": 1.0941,
92
- "step": 14
93
- },
94
- {
95
- "epoch": 0.19,
96
- "learning_rate": 1.9999754126376247e-05,
97
- "loss": 1.0402,
98
- "step": 15
99
- },
100
- {
101
- "epoch": 0.21,
102
- "learning_rate": 1.9999016517595752e-05,
103
- "loss": 1.0839,
104
- "step": 16
105
- },
106
- {
107
- "epoch": 0.22,
108
- "learning_rate": 1.9997787209930222e-05,
109
- "loss": 1.0533,
110
- "step": 17
111
- },
112
- {
113
- "epoch": 0.23,
114
- "learning_rate": 1.9996066263830533e-05,
115
- "loss": 1.0485,
116
- "step": 18
117
- },
118
- {
119
- "epoch": 0.25,
120
- "learning_rate": 1.9993853763923724e-05,
121
- "loss": 1.0572,
122
- "step": 19
123
- },
124
- {
125
- "epoch": 0.26,
126
- "learning_rate": 1.999114981900887e-05,
127
- "loss": 1.0493,
128
- "step": 20
129
- },
130
- {
131
- "epoch": 0.27,
132
- "learning_rate": 1.9987954562051724e-05,
133
- "loss": 1.077,
134
- "step": 21
135
- },
136
- {
137
- "epoch": 0.28,
138
- "learning_rate": 1.998426815017817e-05,
139
- "loss": 1.0676,
140
- "step": 22
141
- },
142
- {
143
- "epoch": 0.3,
144
- "learning_rate": 1.9980090764666486e-05,
145
- "loss": 1.0695,
146
- "step": 23
147
- },
148
- {
149
- "epoch": 0.31,
150
- "learning_rate": 1.9975422610938463e-05,
151
- "loss": 1.0383,
152
- "step": 24
153
- },
154
- {
155
- "epoch": 0.32,
156
- "learning_rate": 1.9970263918549274e-05,
157
- "loss": 1.0036,
158
- "step": 25
159
- },
160
- {
161
- "epoch": 0.34,
162
- "learning_rate": 1.9964614941176194e-05,
163
- "loss": 1.0124,
164
- "step": 26
165
- },
166
- {
167
- "epoch": 0.35,
168
- "learning_rate": 1.9958475956606133e-05,
169
- "loss": 1.0127,
170
- "step": 27
171
- },
172
- {
173
- "epoch": 0.36,
174
- "learning_rate": 1.995184726672197e-05,
175
- "loss": 0.9904,
176
- "step": 28
177
- },
178
- {
179
- "epoch": 0.37,
180
- "learning_rate": 1.9944729197487702e-05,
181
- "loss": 1.0295,
182
- "step": 29
183
- },
184
- {
185
- "epoch": 0.39,
186
- "learning_rate": 1.9937122098932428e-05,
187
- "loss": 1.0293,
188
- "step": 30
189
- },
190
- {
191
- "epoch": 0.4,
192
- "learning_rate": 1.992902634513312e-05,
193
- "loss": 0.9826,
194
- "step": 31
195
- },
196
- {
197
- "epoch": 0.41,
198
- "learning_rate": 1.9920442334196248e-05,
199
- "loss": 0.9924,
200
- "step": 32
201
- },
202
- {
203
- "epoch": 0.43,
204
- "learning_rate": 1.9911370488238185e-05,
205
- "loss": 0.9813,
206
- "step": 33
207
- },
208
- {
209
- "epoch": 0.44,
210
- "learning_rate": 1.9901811253364458e-05,
211
- "loss": 0.9965,
212
- "step": 34
213
- },
214
- {
215
- "epoch": 0.45,
216
- "learning_rate": 1.989176509964781e-05,
217
- "loss": 1.0157,
218
- "step": 35
219
- },
220
- {
221
- "epoch": 0.47,
222
- "learning_rate": 1.988123252110509e-05,
223
- "loss": 1.0625,
224
- "step": 36
225
- },
226
- {
227
- "epoch": 0.48,
228
- "learning_rate": 1.9870214035672945e-05,
229
- "loss": 1.0077,
230
- "step": 37
231
- },
232
- {
233
- "epoch": 0.49,
234
- "learning_rate": 1.985871018518236e-05,
235
- "loss": 0.9727,
236
- "step": 38
237
- },
238
- {
239
- "epoch": 0.5,
240
- "learning_rate": 1.984672153533202e-05,
241
- "loss": 0.9996,
242
- "step": 39
243
- },
244
- {
245
- "epoch": 0.52,
246
- "learning_rate": 1.9834248675660484e-05,
247
- "loss": 1.0046,
248
- "step": 40
249
- },
250
- {
251
- "epoch": 0.53,
252
- "learning_rate": 1.982129221951719e-05,
253
- "loss": 0.9891,
254
- "step": 41
255
- },
256
- {
257
- "epoch": 0.54,
258
- "learning_rate": 1.9807852804032306e-05,
259
- "loss": 1.1151,
260
- "step": 42
261
- },
262
- {
263
- "epoch": 0.56,
264
- "learning_rate": 1.9793931090085385e-05,
265
- "loss": 0.9895,
266
- "step": 43
267
- },
268
- {
269
- "epoch": 0.57,
270
- "learning_rate": 1.9779527762272877e-05,
271
- "loss": 0.9969,
272
- "step": 44
273
- },
274
- {
275
- "epoch": 0.58,
276
- "learning_rate": 1.976464352887447e-05,
277
- "loss": 0.9717,
278
- "step": 45
279
- },
280
- {
281
- "epoch": 0.59,
282
- "learning_rate": 1.9749279121818235e-05,
283
- "loss": 1.0397,
284
- "step": 46
285
- },
286
- {
287
- "epoch": 0.61,
288
- "learning_rate": 1.973343529664467e-05,
289
- "loss": 0.978,
290
- "step": 47
291
- },
292
- {
293
- "epoch": 0.62,
294
- "learning_rate": 1.971711283246951e-05,
295
- "loss": 0.9927,
296
- "step": 48
297
- },
298
- {
299
- "epoch": 0.63,
300
- "learning_rate": 1.9700312531945444e-05,
301
- "loss": 0.9446,
302
- "step": 49
303
- },
304
- {
305
- "epoch": 0.65,
306
- "learning_rate": 1.9683035221222617e-05,
307
- "loss": 0.9793,
308
- "step": 50
309
- },
310
- {
311
- "epoch": 0.66,
312
- "learning_rate": 1.9665281749908034e-05,
313
- "loss": 0.9999,
314
- "step": 51
315
- },
316
- {
317
- "epoch": 0.67,
318
- "learning_rate": 1.964705299102376e-05,
319
- "loss": 0.9607,
320
- "step": 52
321
- },
322
- {
323
- "epoch": 0.68,
324
- "learning_rate": 1.9628349840963997e-05,
325
- "loss": 0.9746,
326
- "step": 53
327
- },
328
- {
329
- "epoch": 0.7,
330
- "learning_rate": 1.9609173219450998e-05,
331
- "loss": 0.9671,
332
- "step": 54
333
- },
334
- {
335
- "epoch": 0.71,
336
- "learning_rate": 1.958952406948985e-05,
337
- "loss": 0.9879,
338
- "step": 55
339
- },
340
- {
341
- "epoch": 0.72,
342
- "learning_rate": 1.956940335732209e-05,
343
- "loss": 0.982,
344
- "step": 56
345
- },
346
- {
347
- "epoch": 0.74,
348
- "learning_rate": 1.9548812072378208e-05,
349
- "loss": 0.945,
350
- "step": 57
351
- },
352
- {
353
- "epoch": 0.75,
354
- "learning_rate": 1.9527751227228964e-05,
355
- "loss": 0.9689,
356
- "step": 58
357
- },
358
- {
359
- "epoch": 0.76,
360
- "learning_rate": 1.950622185753563e-05,
361
- "loss": 0.9955,
362
- "step": 59
363
- },
364
- {
365
- "epoch": 0.78,
366
- "learning_rate": 1.9484225021999032e-05,
367
- "loss": 0.9633,
368
- "step": 60
369
- },
370
- {
371
- "epoch": 0.79,
372
- "learning_rate": 1.9461761802307494e-05,
373
- "loss": 0.966,
374
- "step": 61
375
- },
376
- {
377
- "epoch": 0.8,
378
- "learning_rate": 1.9438833303083677e-05,
379
- "loss": 0.9962,
380
- "step": 62
381
- },
382
- {
383
- "epoch": 0.81,
384
- "learning_rate": 1.941544065183021e-05,
385
- "loss": 1.0164,
386
- "step": 63
387
- },
388
- {
389
- "epoch": 0.83,
390
- "learning_rate": 1.939158499887428e-05,
391
- "loss": 0.9462,
392
- "step": 64
393
- },
394
- {
395
- "epoch": 0.84,
396
- "learning_rate": 1.9367267517311057e-05,
397
- "loss": 1.0057,
398
- "step": 65
399
- },
400
- {
401
- "epoch": 0.85,
402
- "learning_rate": 1.9342489402945997e-05,
403
- "loss": 0.9601,
404
- "step": 66
405
- },
406
- {
407
- "epoch": 0.87,
408
- "learning_rate": 1.9317251874236066e-05,
409
- "loss": 0.9497,
410
- "step": 67
411
- },
412
- {
413
- "epoch": 0.88,
414
- "learning_rate": 1.9291556172229784e-05,
415
- "loss": 1.0107,
416
- "step": 68
417
- },
418
- {
419
- "epoch": 0.89,
420
- "learning_rate": 1.9265403560506223e-05,
421
- "loss": 0.951,
422
- "step": 69
423
- },
424
- {
425
- "epoch": 0.9,
426
- "learning_rate": 1.9238795325112867e-05,
427
- "loss": 0.9485,
428
- "step": 70
429
- },
430
- {
431
- "epoch": 0.92,
432
- "learning_rate": 1.9211732774502372e-05,
433
- "loss": 0.9925,
434
- "step": 71
435
- },
436
- {
437
- "epoch": 0.93,
438
- "learning_rate": 1.9184217239468213e-05,
439
- "loss": 0.9399,
440
- "step": 72
441
- },
442
- {
443
- "epoch": 0.94,
444
- "learning_rate": 1.915625007307925e-05,
445
- "loss": 0.9579,
446
- "step": 73
447
- },
448
- {
449
- "epoch": 0.96,
450
- "learning_rate": 1.912783265061319e-05,
451
- "loss": 0.9431,
452
- "step": 74
453
- },
454
- {
455
- "epoch": 0.97,
456
- "learning_rate": 1.9098966369488967e-05,
457
- "loss": 0.9758,
458
- "step": 75
459
- },
460
- {
461
- "epoch": 0.98,
462
- "learning_rate": 1.9069652649198004e-05,
463
- "loss": 0.9403,
464
- "step": 76
465
- },
466
- {
467
- "epoch": 1.0,
468
- "learning_rate": 1.9039892931234434e-05,
469
- "loss": 0.9434,
470
- "step": 77
471
- },
472
- {
473
- "epoch": 1.01,
474
- "learning_rate": 1.900968867902419e-05,
475
- "loss": 0.9028,
476
- "step": 78
477
- },
478
- {
479
- "epoch": 1.02,
480
- "learning_rate": 1.8979041377853068e-05,
481
- "loss": 0.8579,
482
- "step": 79
483
- },
484
- {
485
- "epoch": 1.03,
486
- "learning_rate": 1.8947952534793663e-05,
487
- "loss": 0.8575,
488
- "step": 80
489
- },
490
- {
491
- "epoch": 1.05,
492
- "learning_rate": 1.891642367863127e-05,
493
- "loss": 0.8453,
494
- "step": 81
495
- },
496
- {
497
- "epoch": 1.06,
498
- "learning_rate": 1.8884456359788725e-05,
499
- "loss": 0.8504,
500
- "step": 82
501
- },
502
- {
503
- "epoch": 1.07,
504
- "learning_rate": 1.8852052150250123e-05,
505
- "loss": 0.8479,
506
- "step": 83
507
- },
508
- {
509
- "epoch": 1.09,
510
- "learning_rate": 1.881921264348355e-05,
511
- "loss": 0.8473,
512
- "step": 84
513
- },
514
- {
515
- "epoch": 1.1,
516
- "learning_rate": 1.878593945436272e-05,
517
- "loss": 0.8223,
518
- "step": 85
519
- },
520
- {
521
- "epoch": 1.11,
522
- "learning_rate": 1.8752234219087538e-05,
523
- "loss": 0.8424,
524
- "step": 86
525
- },
526
- {
527
- "epoch": 1.12,
528
- "learning_rate": 1.871809859510368e-05,
529
- "loss": 0.8525,
530
- "step": 87
531
- },
532
- {
533
- "epoch": 1.14,
534
- "learning_rate": 1.8683534261021058e-05,
535
- "loss": 0.8561,
536
- "step": 88
537
- },
538
- {
539
- "epoch": 1.15,
540
- "learning_rate": 1.8648542916531283e-05,
541
- "loss": 0.8301,
542
- "step": 89
543
- },
544
- {
545
- "epoch": 1.16,
546
- "learning_rate": 1.8613126282324092e-05,
547
- "loss": 0.8174,
548
- "step": 90
549
- },
550
- {
551
- "epoch": 1.18,
552
- "learning_rate": 1.8577286100002723e-05,
553
- "loss": 0.8228,
554
- "step": 91
555
- },
556
- {
557
- "epoch": 1.19,
558
- "learning_rate": 1.8541024131998277e-05,
559
- "loss": 0.8189,
560
- "step": 92
561
- },
562
- {
563
- "epoch": 1.2,
564
- "learning_rate": 1.850434216148305e-05,
565
- "loss": 0.804,
566
- "step": 93
567
- },
568
- {
569
- "epoch": 1.21,
570
- "learning_rate": 1.8467241992282842e-05,
571
- "loss": 0.8368,
572
- "step": 94
573
- },
574
- {
575
- "epoch": 1.23,
576
- "learning_rate": 1.8429725448788267e-05,
577
- "loss": 0.8353,
578
- "step": 95
579
- },
580
- {
581
- "epoch": 1.24,
582
- "learning_rate": 1.8391794375865025e-05,
583
- "loss": 0.8153,
584
- "step": 96
585
- },
586
- {
587
- "epoch": 1.25,
588
- "learning_rate": 1.8353450638763178e-05,
589
- "loss": 0.778,
590
- "step": 97
591
- },
592
- {
593
- "epoch": 1.27,
594
- "learning_rate": 1.8314696123025456e-05,
595
- "loss": 0.8143,
596
- "step": 98
597
- },
598
- {
599
- "epoch": 1.28,
600
- "learning_rate": 1.827553273439449e-05,
601
- "loss": 0.8126,
602
- "step": 99
603
- },
604
- {
605
- "epoch": 1.29,
606
- "learning_rate": 1.823596239871915e-05,
607
- "loss": 0.7918,
608
- "step": 100
609
- },
610
- {
611
- "epoch": 1.31,
612
- "learning_rate": 1.819598706185979e-05,
613
- "loss": 0.8084,
614
- "step": 101
615
- },
616
- {
617
- "epoch": 1.32,
618
- "learning_rate": 1.8155608689592604e-05,
619
- "loss": 0.8166,
620
- "step": 102
621
- },
622
- {
623
- "epoch": 1.33,
624
- "learning_rate": 1.811482926751293e-05,
625
- "loss": 0.8211,
626
- "step": 103
627
- },
628
- {
629
- "epoch": 1.34,
630
- "learning_rate": 1.8073650800937627e-05,
631
- "loss": 0.83,
632
- "step": 104
633
- },
634
- {
635
- "epoch": 1.36,
636
- "learning_rate": 1.803207531480645e-05,
637
- "loss": 0.8166,
638
- "step": 105
639
- },
640
- {
641
- "epoch": 1.37,
642
- "learning_rate": 1.7990104853582494e-05,
643
- "loss": 0.8037,
644
- "step": 106
645
- },
646
- {
647
- "epoch": 1.38,
648
- "learning_rate": 1.7947741481151628e-05,
649
- "loss": 0.7819,
650
- "step": 107
651
- },
652
- {
653
- "epoch": 1.4,
654
- "learning_rate": 1.7904987280721037e-05,
655
- "loss": 0.781,
656
- "step": 108
657
- },
658
- {
659
- "epoch": 1.41,
660
- "learning_rate": 1.7861844354716757e-05,
661
- "loss": 0.8338,
662
- "step": 109
663
- },
664
- {
665
- "epoch": 1.42,
666
- "learning_rate": 1.78183148246803e-05,
667
- "loss": 0.8088,
668
- "step": 110
669
- },
670
- {
671
- "epoch": 1.43,
672
- "learning_rate": 1.777440083116432e-05,
673
- "loss": 0.7566,
674
- "step": 111
675
- },
676
- {
677
- "epoch": 1.45,
678
- "learning_rate": 1.773010453362737e-05,
679
- "loss": 0.786,
680
- "step": 112
681
- },
682
- {
683
- "epoch": 1.46,
684
- "learning_rate": 1.7685428110327683e-05,
685
- "loss": 0.787,
686
- "step": 113
687
- },
688
- {
689
- "epoch": 1.47,
690
- "learning_rate": 1.7640373758216075e-05,
691
- "loss": 0.7889,
692
- "step": 114
693
- },
694
- {
695
- "epoch": 1.49,
696
- "learning_rate": 1.7594943692827913e-05,
697
- "loss": 0.7934,
698
- "step": 115
699
- },
700
- {
701
- "epoch": 1.5,
702
- "learning_rate": 1.754914014817416e-05,
703
- "loss": 0.7853,
704
- "step": 116
705
- },
706
- {
707
- "epoch": 1.51,
708
- "learning_rate": 1.7502965376631515e-05,
709
- "loss": 0.807,
710
- "step": 117
711
- },
712
- {
713
- "epoch": 1.53,
714
- "learning_rate": 1.7456421648831658e-05,
715
- "loss": 0.7973,
716
- "step": 118
717
- },
718
- {
719
- "epoch": 1.54,
720
- "learning_rate": 1.7409511253549592e-05,
721
- "loss": 0.8228,
722
- "step": 119
723
- },
724
- {
725
- "epoch": 1.55,
726
- "learning_rate": 1.7362236497591097e-05,
727
- "loss": 0.7885,
728
- "step": 120
729
- },
730
- {
731
- "epoch": 1.56,
732
- "learning_rate": 1.731459970567928e-05,
733
- "loss": 0.7657,
734
- "step": 121
735
- },
736
- {
737
- "epoch": 1.58,
738
- "learning_rate": 1.7266603220340273e-05,
739
- "loss": 0.7701,
740
- "step": 122
741
- },
742
- {
743
- "epoch": 1.59,
744
- "learning_rate": 1.7218249401788033e-05,
745
- "loss": 0.7784,
746
- "step": 123
747
- },
748
- {
749
- "epoch": 1.6,
750
- "learning_rate": 1.7169540627808276e-05,
751
- "loss": 0.8019,
752
- "step": 124
753
- },
754
- {
755
- "epoch": 1.62,
756
- "learning_rate": 1.7120479293641558e-05,
757
- "loss": 0.7428,
758
- "step": 125
759
- },
760
- {
761
- "epoch": 1.63,
762
- "learning_rate": 1.7071067811865477e-05,
763
- "loss": 0.7482,
764
- "step": 126
765
- },
766
- {
767
- "epoch": 1.64,
768
- "learning_rate": 1.7021308612276056e-05,
769
- "loss": 0.7833,
770
- "step": 127
771
- },
772
- {
773
- "epoch": 1.65,
774
- "learning_rate": 1.6971204141768235e-05,
775
- "loss": 0.7865,
776
- "step": 128
777
- },
778
- {
779
- "epoch": 1.67,
780
- "learning_rate": 1.6920756864215558e-05,
781
- "loss": 0.7722,
782
- "step": 129
783
- },
784
- {
785
- "epoch": 1.68,
786
- "learning_rate": 1.686996926034902e-05,
787
- "loss": 0.7703,
788
- "step": 130
789
- },
790
- {
791
- "epoch": 1.69,
792
- "learning_rate": 1.6818843827635052e-05,
793
- "loss": 0.7667,
794
- "step": 131
795
- },
796
- {
797
- "epoch": 1.71,
798
- "learning_rate": 1.6767383080152744e-05,
799
- "loss": 0.7361,
800
- "step": 132
801
- },
802
- {
803
- "epoch": 1.72,
804
- "learning_rate": 1.6715589548470187e-05,
805
- "loss": 0.8037,
806
- "step": 133
807
- },
808
- {
809
- "epoch": 1.73,
810
- "learning_rate": 1.6663465779520042e-05,
811
- "loss": 0.7281,
812
- "step": 134
813
- },
814
- {
815
- "epoch": 1.74,
816
- "learning_rate": 1.6611014336474303e-05,
817
- "loss": 0.7402,
818
- "step": 135
819
- },
820
- {
821
- "epoch": 1.76,
822
- "learning_rate": 1.6558237798618243e-05,
823
- "loss": 0.7343,
824
- "step": 136
825
- },
826
- {
827
- "epoch": 1.77,
828
- "learning_rate": 1.6505138761223586e-05,
829
- "loss": 0.7379,
830
- "step": 137
831
- },
832
- {
833
- "epoch": 1.78,
834
- "learning_rate": 1.645171983542088e-05,
835
- "loss": 0.7296,
836
- "step": 138
837
- },
838
- {
839
- "epoch": 1.8,
840
- "learning_rate": 1.6397983648071093e-05,
841
- "loss": 0.7136,
842
- "step": 139
843
- },
844
- {
845
- "epoch": 1.81,
846
- "learning_rate": 1.6343932841636455e-05,
847
- "loss": 0.7394,
848
- "step": 140
849
- },
850
- {
851
- "epoch": 1.82,
852
- "learning_rate": 1.6289570074050492e-05,
853
- "loss": 0.7298,
854
- "step": 141
855
- },
856
- {
857
- "epoch": 1.84,
858
- "learning_rate": 1.6234898018587336e-05,
859
- "loss": 0.7253,
860
- "step": 142
861
- },
862
- {
863
- "epoch": 1.85,
864
- "learning_rate": 1.617991936373027e-05,
865
- "loss": 0.7967,
866
- "step": 143
867
- },
868
- {
869
- "epoch": 1.86,
870
- "learning_rate": 1.6124636813039502e-05,
871
- "loss": 0.6995,
872
- "step": 144
873
- },
874
- {
875
- "epoch": 1.87,
876
- "learning_rate": 1.6069053085019258e-05,
877
- "loss": 0.7193,
878
- "step": 145
879
- },
880
- {
881
- "epoch": 1.89,
882
- "learning_rate": 1.601317091298406e-05,
883
- "loss": 0.7227,
884
- "step": 146
885
- },
886
- {
887
- "epoch": 1.9,
888
- "learning_rate": 1.5956993044924334e-05,
889
- "loss": 0.7113,
890
- "step": 147
891
- },
892
- {
893
- "epoch": 1.91,
894
- "learning_rate": 1.5900522243371283e-05,
895
- "loss": 0.7434,
896
- "step": 148
897
- },
898
- {
899
- "epoch": 1.93,
900
- "learning_rate": 1.5843761285261027e-05,
901
- "loss": 0.7252,
902
- "step": 149
903
- },
904
- {
905
- "epoch": 1.94,
906
- "learning_rate": 1.578671296179806e-05,
907
- "loss": 0.7414,
908
- "step": 150
909
- },
910
- {
911
- "epoch": 1.95,
912
- "learning_rate": 1.5729380078317982e-05,
913
- "loss": 0.6879,
914
- "step": 151
915
- },
916
- {
917
- "epoch": 1.96,
918
- "learning_rate": 1.5671765454149558e-05,
919
- "loss": 0.7181,
920
- "step": 152
921
- },
922
- {
923
- "epoch": 1.98,
924
- "learning_rate": 1.5613871922476082e-05,
925
- "loss": 0.6852,
926
- "step": 153
927
- },
928
- {
929
- "epoch": 1.99,
930
- "learning_rate": 1.5555702330196024e-05,
931
- "loss": 0.7135,
932
- "step": 154
933
- },
934
- {
935
- "epoch": 2.0,
936
- "learning_rate": 1.5497259537783084e-05,
937
- "loss": 0.682,
938
- "step": 155
939
- },
940
- {
941
- "epoch": 2.02,
942
- "learning_rate": 1.543854641914549e-05,
943
- "loss": 0.4981,
944
- "step": 156
945
- },
946
- {
947
- "epoch": 2.03,
948
- "learning_rate": 1.537956586148469e-05,
949
- "loss": 0.4879,
950
- "step": 157
951
- },
952
- {
953
- "epoch": 2.04,
954
- "learning_rate": 1.5320320765153367e-05,
955
- "loss": 0.4878,
956
- "step": 158
957
- },
958
- {
959
- "epoch": 2.05,
960
- "learning_rate": 1.5260814043512838e-05,
961
- "loss": 0.4754,
962
- "step": 159
963
- },
964
- {
965
- "epoch": 2.07,
966
- "learning_rate": 1.5201048622789747e-05,
967
- "loss": 0.4727,
968
- "step": 160
969
- },
970
- {
971
- "epoch": 2.08,
972
- "learning_rate": 1.5141027441932217e-05,
973
- "loss": 0.4714,
974
- "step": 161
975
- },
976
- {
977
- "epoch": 2.09,
978
- "learning_rate": 1.5080753452465296e-05,
979
- "loss": 0.4644,
980
- "step": 162
981
- },
982
- {
983
- "epoch": 2.11,
984
- "learning_rate": 1.502022961834582e-05,
985
- "loss": 0.4727,
986
- "step": 163
987
- },
988
- {
989
- "epoch": 2.12,
990
- "learning_rate": 1.4959458915816681e-05,
991
- "loss": 0.4385,
992
- "step": 164
993
- },
994
- {
995
- "epoch": 2.13,
996
- "learning_rate": 1.4898444333260436e-05,
997
- "loss": 0.4349,
998
- "step": 165
999
- },
1000
- {
1001
- "epoch": 2.15,
1002
- "learning_rate": 1.4837188871052399e-05,
1003
- "loss": 0.4708,
1004
- "step": 166
1005
- },
1006
- {
1007
- "epoch": 2.16,
1008
- "learning_rate": 1.4775695541413063e-05,
1009
- "loss": 0.435,
1010
- "step": 167
1011
- },
1012
- {
1013
- "epoch": 2.17,
1014
- "learning_rate": 1.4713967368259981e-05,
1015
- "loss": 0.4391,
1016
- "step": 168
1017
- },
1018
- {
1019
- "epoch": 2.18,
1020
- "learning_rate": 1.4652007387059077e-05,
1021
- "loss": 0.4417,
1022
- "step": 169
1023
- },
1024
- {
1025
- "epoch": 2.2,
1026
- "learning_rate": 1.4589818644675378e-05,
1027
- "loss": 0.4331,
1028
- "step": 170
1029
- },
1030
- {
1031
- "epoch": 2.21,
1032
- "learning_rate": 1.4527404199223173e-05,
1033
- "loss": 0.4214,
1034
- "step": 171
1035
- },
1036
- {
1037
- "epoch": 2.22,
1038
- "learning_rate": 1.446476711991563e-05,
1039
- "loss": 0.4067,
1040
- "step": 172
1041
- },
1042
- {
1043
- "epoch": 2.24,
1044
- "learning_rate": 1.4401910486913892e-05,
1045
- "loss": 0.4371,
1046
- "step": 173
1047
- },
1048
- {
1049
- "epoch": 2.25,
1050
- "learning_rate": 1.4338837391175582e-05,
1051
- "loss": 0.4318,
1052
- "step": 174
1053
- },
1054
- {
1055
- "epoch": 2.26,
1056
- "learning_rate": 1.4275550934302822e-05,
1057
- "loss": 0.4215,
1058
- "step": 175
1059
- },
1060
- {
1061
- "epoch": 2.27,
1062
- "learning_rate": 1.4212054228389712e-05,
1063
- "loss": 0.4312,
1064
- "step": 176
1065
- },
1066
- {
1067
- "epoch": 2.29,
1068
- "learning_rate": 1.4148350395869279e-05,
1069
- "loss": 0.4097,
1070
- "step": 177
1071
- },
1072
- {
1073
- "epoch": 2.3,
1074
- "learning_rate": 1.4084442569359964e-05,
1075
- "loss": 0.4094,
1076
- "step": 178
1077
- },
1078
- {
1079
- "epoch": 2.31,
1080
- "learning_rate": 1.4020333891511536e-05,
1081
- "loss": 0.4075,
1082
- "step": 179
1083
- },
1084
- {
1085
- "epoch": 2.33,
1086
- "learning_rate": 1.395602751485059e-05,
1087
- "loss": 0.4258,
1088
- "step": 180
1089
- },
1090
- {
1091
- "epoch": 2.34,
1092
- "learning_rate": 1.3891526601625492e-05,
1093
- "loss": 0.3956,
1094
- "step": 181
1095
- },
1096
- {
1097
- "epoch": 2.35,
1098
- "learning_rate": 1.3826834323650899e-05,
1099
- "loss": 0.3987,
1100
- "step": 182
1101
- },
1102
- {
1103
- "epoch": 2.37,
1104
- "learning_rate": 1.3761953862151773e-05,
1105
- "loss": 0.3987,
1106
- "step": 183
1107
- },
1108
- {
1109
- "epoch": 2.38,
1110
- "learning_rate": 1.3696888407606952e-05,
1111
- "loss": 0.3704,
1112
- "step": 184
1113
- },
1114
- {
1115
- "epoch": 2.39,
1116
- "learning_rate": 1.3631641159592253e-05,
1117
- "loss": 0.4014,
1118
- "step": 185
1119
- },
1120
- {
1121
- "epoch": 2.4,
1122
- "learning_rate": 1.3566215326623131e-05,
1123
- "loss": 0.4135,
1124
- "step": 186
1125
- },
1126
- {
1127
- "epoch": 2.42,
1128
- "learning_rate": 1.3500614125996924e-05,
1129
- "loss": 0.3753,
1130
- "step": 187
1131
- },
1132
- {
1133
- "epoch": 2.43,
1134
- "learning_rate": 1.3434840783634611e-05,
1135
- "loss": 0.3808,
1136
- "step": 188
1137
- },
1138
- {
1139
- "epoch": 2.44,
1140
- "learning_rate": 1.3368898533922202e-05,
1141
- "loss": 0.3618,
1142
- "step": 189
1143
- },
1144
- {
1145
- "epoch": 2.46,
1146
- "learning_rate": 1.3302790619551673e-05,
1147
- "loss": 0.3765,
1148
- "step": 190
1149
- },
1150
- {
1151
- "epoch": 2.47,
1152
- "learning_rate": 1.3236520291361516e-05,
1153
- "loss": 0.3512,
1154
- "step": 191
1155
- },
1156
- {
1157
- "epoch": 2.48,
1158
- "learning_rate": 1.3170090808176883e-05,
1159
- "loss": 0.3367,
1160
- "step": 192
1161
- },
1162
- {
1163
- "epoch": 2.49,
1164
- "learning_rate": 1.310350543664932e-05,
1165
- "loss": 0.3799,
1166
- "step": 193
1167
- },
1168
- {
1169
- "epoch": 2.51,
1170
- "learning_rate": 1.3036767451096148e-05,
1171
- "loss": 0.3589,
1172
- "step": 194
1173
- },
1174
- {
1175
- "epoch": 2.52,
1176
- "learning_rate": 1.2969880133339437e-05,
1177
- "loss": 0.3658,
1178
- "step": 195
1179
- },
1180
- {
1181
- "epoch": 2.53,
1182
- "learning_rate": 1.2902846772544625e-05,
1183
- "loss": 0.3567,
1184
- "step": 196
1185
- },
1186
- {
1187
- "epoch": 2.55,
1188
- "learning_rate": 1.2835670665058779e-05,
1189
- "loss": 0.3312,
1190
- "step": 197
1191
- },
1192
- {
1193
- "epoch": 2.56,
1194
- "learning_rate": 1.2768355114248493e-05,
1195
- "loss": 0.3518,
1196
- "step": 198
1197
- },
1198
- {
1199
- "epoch": 2.57,
1200
- "learning_rate": 1.2700903430337456e-05,
1201
- "loss": 0.3588,
1202
- "step": 199
1203
- },
1204
- {
1205
- "epoch": 2.58,
1206
- "learning_rate": 1.2633318930243647e-05,
1207
- "loss": 0.3709,
1208
- "step": 200
1209
- },
1210
- {
1211
- "epoch": 2.6,
1212
- "learning_rate": 1.2565604937416267e-05,
1213
- "loss": 0.3446,
1214
- "step": 201
1215
- },
1216
- {
1217
- "epoch": 2.61,
1218
- "learning_rate": 1.249776478167227e-05,
1219
- "loss": 0.363,
1220
- "step": 202
1221
- },
1222
- {
1223
- "epoch": 2.62,
1224
- "learning_rate": 1.242980179903264e-05,
1225
- "loss": 0.3603,
1226
- "step": 203
1227
- },
1228
- {
1229
- "epoch": 2.64,
1230
- "learning_rate": 1.2361719331558346e-05,
1231
- "loss": 0.3517,
1232
- "step": 204
1233
- },
1234
- {
1235
- "epoch": 2.65,
1236
- "learning_rate": 1.229352072718598e-05,
1237
- "loss": 0.3329,
1238
- "step": 205
1239
- },
1240
- {
1241
- "epoch": 2.66,
1242
- "learning_rate": 1.2225209339563144e-05,
1243
- "loss": 0.3441,
1244
- "step": 206
1245
- },
1246
- {
1247
- "epoch": 2.68,
1248
- "learning_rate": 1.2156788527883524e-05,
1249
- "loss": 0.335,
1250
- "step": 207
1251
- },
1252
- {
1253
- "epoch": 2.69,
1254
- "learning_rate": 1.20882616567217e-05,
1255
- "loss": 0.3259,
1256
- "step": 208
1257
- },
1258
- {
1259
- "epoch": 2.7,
1260
- "learning_rate": 1.2019632095867697e-05,
1261
- "loss": 0.296,
1262
- "step": 209
1263
- },
1264
- {
1265
- "epoch": 2.71,
1266
- "learning_rate": 1.1950903220161286e-05,
1267
- "loss": 0.321,
1268
- "step": 210
1269
- },
1270
- {
1271
- "epoch": 2.73,
1272
- "learning_rate": 1.1882078409326003e-05,
1273
- "loss": 0.3059,
1274
- "step": 211
1275
- },
1276
- {
1277
- "epoch": 2.74,
1278
- "learning_rate": 1.1813161047802986e-05,
1279
- "loss": 0.2979,
1280
- "step": 212
1281
- },
1282
- {
1283
- "epoch": 2.75,
1284
- "learning_rate": 1.174415452458451e-05,
1285
- "loss": 0.281,
1286
- "step": 213
1287
- },
1288
- {
1289
- "epoch": 2.77,
1290
- "learning_rate": 1.1675062233047365e-05,
1291
- "loss": 0.3029,
1292
- "step": 214
1293
- },
1294
- {
1295
- "epoch": 2.78,
1296
- "learning_rate": 1.1605887570785972e-05,
1297
- "loss": 0.3045,
1298
- "step": 215
1299
- },
1300
- {
1301
- "epoch": 2.79,
1302
- "learning_rate": 1.1536633939445302e-05,
1303
- "loss": 0.2989,
1304
- "step": 216
1305
- },
1306
- {
1307
- "epoch": 2.8,
1308
- "learning_rate": 1.1467304744553618e-05,
1309
- "loss": 0.2804,
1310
- "step": 217
1311
- },
1312
- {
1313
- "epoch": 2.82,
1314
- "learning_rate": 1.1397903395354996e-05,
1315
- "loss": 0.2852,
1316
- "step": 218
1317
- },
1318
- {
1319
- "epoch": 2.83,
1320
- "learning_rate": 1.132843330464168e-05,
1321
- "loss": 0.248,
1322
- "step": 219
1323
- },
1324
- {
1325
- "epoch": 2.84,
1326
- "learning_rate": 1.1258897888586256e-05,
1327
- "loss": 0.2822,
1328
- "step": 220
1329
- },
1330
- {
1331
- "epoch": 2.86,
1332
- "learning_rate": 1.118930056657367e-05,
1333
- "loss": 0.2713,
1334
- "step": 221
1335
- },
1336
- {
1337
- "epoch": 2.87,
1338
- "learning_rate": 1.1119644761033079e-05,
1339
- "loss": 0.2879,
1340
- "step": 222
1341
- },
1342
- {
1343
- "epoch": 2.88,
1344
- "learning_rate": 1.1049933897269547e-05,
1345
- "loss": 0.257,
1346
- "step": 223
1347
- },
1348
- {
1349
- "epoch": 2.89,
1350
- "learning_rate": 1.098017140329561e-05,
1351
- "loss": 0.2643,
1352
- "step": 224
1353
- },
1354
- {
1355
- "epoch": 2.91,
1356
- "learning_rate": 1.0910360709662701e-05,
1357
- "loss": 0.2694,
1358
- "step": 225
1359
- },
1360
- {
1361
- "epoch": 2.92,
1362
- "learning_rate": 1.0840505249292477e-05,
1363
- "loss": 0.2558,
1364
- "step": 226
1365
- },
1366
- {
1367
- "epoch": 2.93,
1368
- "learning_rate": 1.0770608457307965e-05,
1369
- "loss": 0.2547,
1370
- "step": 227
1371
- },
1372
- {
1373
- "epoch": 2.95,
1374
- "learning_rate": 1.0700673770864673e-05,
1375
- "loss": 0.2287,
1376
- "step": 228
1377
- },
1378
- {
1379
- "epoch": 2.96,
1380
- "learning_rate": 1.0630704628981561e-05,
1381
- "loss": 0.2441,
1382
- "step": 229
1383
- },
1384
- {
1385
- "epoch": 2.97,
1386
- "learning_rate": 1.0560704472371919e-05,
1387
- "loss": 0.2165,
1388
- "step": 230
1389
- },
1390
- {
1391
- "epoch": 2.99,
1392
- "learning_rate": 1.0490676743274181e-05,
1393
- "loss": 0.2302,
1394
- "step": 231
1395
- },
1396
- {
1397
- "epoch": 3.0,
1398
- "learning_rate": 1.0420624885282653e-05,
1399
- "loss": 0.2407,
1400
- "step": 232
1401
- },
1402
- {
1403
- "epoch": 3.01,
1404
- "learning_rate": 1.0350552343178164e-05,
1405
- "loss": 0.1206,
1406
- "step": 233
1407
- },
1408
- {
1409
- "epoch": 3.02,
1410
- "learning_rate": 1.028046256275869e-05,
1411
- "loss": 0.0922,
1412
- "step": 234
1413
- },
1414
- {
1415
- "epoch": 3.04,
1416
- "learning_rate": 1.0210358990669889e-05,
1417
- "loss": 0.0915,
1418
- "step": 235
1419
- },
1420
- {
1421
- "epoch": 3.05,
1422
- "learning_rate": 1.0140245074235624e-05,
1423
- "loss": 0.0834,
1424
- "step": 236
1425
- },
1426
- {
1427
- "epoch": 3.06,
1428
- "learning_rate": 1.0070124261288437e-05,
1429
- "loss": 0.0781,
1430
- "step": 237
1431
- },
1432
- {
1433
- "epoch": 3.08,
1434
- "learning_rate": 1e-05,
1435
- "loss": 0.0863,
1436
- "step": 238
1437
- },
1438
- {
1439
- "epoch": 3.09,
1440
- "learning_rate": 9.929875738711565e-06,
1441
- "loss": 0.0917,
1442
- "step": 239
1443
- },
1444
- {
1445
- "epoch": 3.1,
1446
- "learning_rate": 9.85975492576438e-06,
1447
- "loss": 0.0788,
1448
- "step": 240
1449
- },
1450
- {
1451
- "epoch": 3.11,
1452
- "learning_rate": 9.789641009330113e-06,
1453
- "loss": 0.0799,
1454
- "step": 241
1455
- },
1456
- {
1457
- "epoch": 3.13,
1458
- "learning_rate": 9.719537437241311e-06,
1459
- "loss": 0.0847,
1460
- "step": 242
1461
- },
1462
- {
1463
- "epoch": 3.14,
1464
- "learning_rate": 9.64944765682184e-06,
1465
- "loss": 0.0869,
1466
- "step": 243
1467
- },
1468
- {
1469
- "epoch": 3.15,
1470
- "learning_rate": 9.579375114717352e-06,
1471
- "loss": 0.0804,
1472
- "step": 244
1473
- },
1474
- {
1475
- "epoch": 3.17,
1476
- "learning_rate": 9.50932325672582e-06,
1477
- "loss": 0.0854,
1478
- "step": 245
1479
- },
1480
- {
1481
- "epoch": 3.18,
1482
- "learning_rate": 9.439295527628083e-06,
1483
- "loss": 0.0715,
1484
- "step": 246
1485
- },
1486
- {
1487
- "epoch": 3.19,
1488
- "learning_rate": 9.369295371018442e-06,
1489
- "loss": 0.0814,
1490
- "step": 247
1491
- },
1492
- {
1493
- "epoch": 3.21,
1494
- "learning_rate": 9.299326229135326e-06,
1495
- "loss": 0.0745,
1496
- "step": 248
1497
- },
1498
- {
1499
- "epoch": 3.22,
1500
- "learning_rate": 9.22939154269204e-06,
1501
- "loss": 0.0758,
1502
- "step": 249
1503
- },
1504
- {
1505
- "epoch": 3.23,
1506
- "learning_rate": 9.159494750707527e-06,
1507
- "loss": 0.0762,
1508
- "step": 250
1509
- },
1510
- {
1511
- "epoch": 3.24,
1512
- "learning_rate": 9.0896392903373e-06,
1513
- "loss": 0.0713,
1514
- "step": 251
1515
- },
1516
- {
1517
- "epoch": 3.26,
1518
- "learning_rate": 9.019828596704394e-06,
1519
- "loss": 0.0831,
1520
- "step": 252
1521
- },
1522
- {
1523
- "epoch": 3.27,
1524
- "learning_rate": 8.950066102730456e-06,
1525
- "loss": 0.0747,
1526
- "step": 253
1527
- },
1528
- {
1529
- "epoch": 3.28,
1530
- "learning_rate": 8.880355238966923e-06,
1531
- "loss": 0.0968,
1532
- "step": 254
1533
- },
1534
- {
1535
- "epoch": 3.3,
1536
- "learning_rate": 8.81069943342633e-06,
1537
- "loss": 0.0591,
1538
- "step": 255
1539
- },
1540
- {
1541
- "epoch": 3.31,
1542
- "learning_rate": 8.741102111413749e-06,
1543
- "loss": 0.0755,
1544
- "step": 256
1545
- },
1546
- {
1547
- "epoch": 3.32,
1548
- "learning_rate": 8.671566695358324e-06,
1549
- "loss": 0.0697,
1550
- "step": 257
1551
- },
1552
- {
1553
- "epoch": 3.33,
1554
- "learning_rate": 8.602096604645009e-06,
1555
- "loss": 0.0691,
1556
- "step": 258
1557
- },
1558
- {
1559
- "epoch": 3.35,
1560
- "learning_rate": 8.532695255446384e-06,
1561
- "loss": 0.0739,
1562
- "step": 259
1563
- },
1564
- {
1565
- "epoch": 3.36,
1566
- "learning_rate": 8.463366060554698e-06,
1567
- "loss": 0.0676,
1568
- "step": 260
1569
- },
1570
- {
1571
- "epoch": 3.37,
1572
- "learning_rate": 8.394112429214032e-06,
1573
- "loss": 0.0683,
1574
- "step": 261
1575
- },
1576
- {
1577
- "epoch": 3.39,
1578
- "learning_rate": 8.324937766952638e-06,
1579
- "loss": 0.0696,
1580
- "step": 262
1581
- },
1582
- {
1583
- "epoch": 3.4,
1584
- "learning_rate": 8.255845475415493e-06,
1585
- "loss": 0.0665,
1586
- "step": 263
1587
- },
1588
- {
1589
- "epoch": 3.41,
1590
- "learning_rate": 8.186838952197019e-06,
1591
- "loss": 0.0722,
1592
- "step": 264
1593
- },
1594
- {
1595
- "epoch": 3.42,
1596
- "learning_rate": 8.117921590674002e-06,
1597
- "loss": 0.0699,
1598
- "step": 265
1599
- },
1600
- {
1601
- "epoch": 3.44,
1602
- "learning_rate": 8.04909677983872e-06,
1603
- "loss": 0.0661,
1604
- "step": 266
1605
- },
1606
- {
1607
- "epoch": 3.45,
1608
- "learning_rate": 7.980367904132303e-06,
1609
- "loss": 0.0688,
1610
- "step": 267
1611
- },
1612
- {
1613
- "epoch": 3.46,
1614
- "learning_rate": 7.911738343278303e-06,
1615
- "loss": 0.0634,
1616
- "step": 268
1617
- },
1618
- {
1619
- "epoch": 3.48,
1620
- "learning_rate": 7.843211472116476e-06,
1621
- "loss": 0.0631,
1622
- "step": 269
1623
- },
1624
- {
1625
- "epoch": 3.49,
1626
- "learning_rate": 7.774790660436857e-06,
1627
- "loss": 0.068,
1628
- "step": 270
1629
- },
1630
- {
1631
- "epoch": 3.5,
1632
- "learning_rate": 7.706479272814024e-06,
1633
- "loss": 0.0596,
1634
- "step": 271
1635
- },
1636
- {
1637
- "epoch": 3.52,
1638
- "learning_rate": 7.63828066844166e-06,
1639
- "loss": 0.0603,
1640
- "step": 272
1641
- },
1642
- {
1643
- "epoch": 3.53,
1644
- "learning_rate": 7.570198200967363e-06,
1645
- "loss": 0.0631,
1646
- "step": 273
1647
- },
1648
- {
1649
- "epoch": 3.54,
1650
- "learning_rate": 7.50223521832773e-06,
1651
- "loss": 0.0727,
1652
- "step": 274
1653
- },
1654
- {
1655
- "epoch": 3.55,
1656
- "learning_rate": 7.434395062583735e-06,
1657
- "loss": 0.0635,
1658
- "step": 275
1659
- },
1660
- {
1661
- "epoch": 3.57,
1662
- "learning_rate": 7.366681069756352e-06,
1663
- "loss": 0.0575,
1664
- "step": 276
1665
- },
1666
- {
1667
- "epoch": 3.58,
1668
- "learning_rate": 7.299096569662549e-06,
1669
- "loss": 0.0613,
1670
- "step": 277
1671
- },
1672
- {
1673
- "epoch": 3.59,
1674
- "learning_rate": 7.2316448857515076e-06,
1675
- "loss": 0.0593,
1676
- "step": 278
1677
- },
1678
- {
1679
- "epoch": 3.61,
1680
- "learning_rate": 7.164329334941225e-06,
1681
- "loss": 0.0557,
1682
- "step": 279
1683
- },
1684
- {
1685
- "epoch": 3.62,
1686
- "learning_rate": 7.097153227455379e-06,
1687
- "loss": 0.0572,
1688
- "step": 280
1689
- },
1690
- {
1691
- "epoch": 3.63,
1692
- "learning_rate": 7.030119866660565e-06,
1693
- "loss": 0.0551,
1694
- "step": 281
1695
- },
1696
- {
1697
- "epoch": 3.64,
1698
- "learning_rate": 6.963232548903853e-06,
1699
- "loss": 0.0548,
1700
- "step": 282
1701
- },
1702
- {
1703
- "epoch": 3.66,
1704
- "learning_rate": 6.896494563350681e-06,
1705
- "loss": 0.0565,
1706
- "step": 283
1707
- },
1708
- {
1709
- "epoch": 3.67,
1710
- "learning_rate": 6.829909191823121e-06,
1711
- "loss": 0.0519,
1712
- "step": 284
1713
- },
1714
- {
1715
- "epoch": 3.68,
1716
- "learning_rate": 6.763479708638485e-06,
1717
- "loss": 0.0522,
1718
- "step": 285
1719
- },
1720
- {
1721
- "epoch": 3.7,
1722
- "learning_rate": 6.697209380448333e-06,
1723
- "loss": 0.0622,
1724
- "step": 286
1725
- },
1726
- {
1727
- "epoch": 3.71,
1728
- "learning_rate": 6.631101466077801e-06,
1729
- "loss": 0.0516,
1730
- "step": 287
1731
- },
1732
- {
1733
- "epoch": 3.72,
1734
- "learning_rate": 6.5651592163653885e-06,
1735
- "loss": 0.0496,
1736
- "step": 288
1737
- },
1738
- {
1739
- "epoch": 3.74,
1740
- "learning_rate": 6.499385874003077e-06,
1741
- "loss": 0.051,
1742
- "step": 289
1743
- },
1744
- {
1745
- "epoch": 3.75,
1746
- "learning_rate": 6.43378467337687e-06,
1747
- "loss": 0.0483,
1748
- "step": 290
1749
- },
1750
- {
1751
- "epoch": 3.76,
1752
- "learning_rate": 6.368358840407754e-06,
1753
- "loss": 0.0395,
1754
- "step": 291
1755
- },
1756
- {
1757
- "epoch": 3.77,
1758
- "learning_rate": 6.303111592393051e-06,
1759
- "loss": 0.0453,
1760
- "step": 292
1761
- },
1762
- {
1763
- "epoch": 3.79,
1764
- "learning_rate": 6.23804613784823e-06,
1765
- "loss": 0.0423,
1766
- "step": 293
1767
- },
1768
- {
1769
- "epoch": 3.8,
1770
- "learning_rate": 6.173165676349103e-06,
1771
- "loss": 0.0416,
1772
- "step": 294
1773
- },
1774
- {
1775
- "epoch": 3.81,
1776
- "learning_rate": 6.108473398374509e-06,
1777
- "loss": 0.0402,
1778
- "step": 295
1779
- },
1780
- {
1781
- "epoch": 3.83,
1782
- "learning_rate": 6.043972485149414e-06,
1783
- "loss": 0.0418,
1784
- "step": 296
1785
- },
1786
- {
1787
- "epoch": 3.84,
1788
- "learning_rate": 5.979666108488464e-06,
1789
- "loss": 0.0432,
1790
- "step": 297
1791
- },
1792
- {
1793
- "epoch": 3.85,
1794
- "learning_rate": 5.91555743064004e-06,
1795
- "loss": 0.0354,
1796
- "step": 298
1797
- },
1798
- {
1799
- "epoch": 3.86,
1800
- "learning_rate": 5.851649604130723e-06,
1801
- "loss": 0.0353,
1802
- "step": 299
1803
- },
1804
- {
1805
- "epoch": 3.88,
1806
- "learning_rate": 5.787945771610296e-06,
1807
- "loss": 0.033,
1808
- "step": 300
1809
- },
1810
- {
1811
- "epoch": 3.89,
1812
- "learning_rate": 5.724449065697182e-06,
1813
- "loss": 0.0344,
1814
- "step": 301
1815
- },
1816
- {
1817
- "epoch": 3.9,
1818
- "learning_rate": 5.66116260882442e-06,
1819
- "loss": 0.0339,
1820
- "step": 302
1821
- },
1822
- {
1823
- "epoch": 3.92,
1824
- "learning_rate": 5.598089513086108e-06,
1825
- "loss": 0.034,
1826
- "step": 303
1827
- },
1828
- {
1829
- "epoch": 3.93,
1830
- "learning_rate": 5.535232880084373e-06,
1831
- "loss": 0.0348,
1832
- "step": 304
1833
- },
1834
- {
1835
- "epoch": 3.94,
1836
- "learning_rate": 5.472595800776831e-06,
1837
- "loss": 0.0345,
1838
- "step": 305
1839
- },
1840
- {
1841
- "epoch": 3.95,
1842
- "learning_rate": 5.410181355324622e-06,
1843
- "loss": 0.0312,
1844
- "step": 306
1845
- },
1846
- {
1847
- "epoch": 3.97,
1848
- "learning_rate": 5.347992612940927e-06,
1849
- "loss": 0.0336,
1850
- "step": 307
1851
- },
1852
- {
1853
- "epoch": 3.98,
1854
- "learning_rate": 5.286032631740023e-06,
1855
- "loss": 0.0369,
1856
- "step": 308
1857
- },
1858
- {
1859
- "epoch": 3.99,
1860
- "learning_rate": 5.22430445858694e-06,
1861
- "loss": 0.0285,
1862
- "step": 309
1863
- },
1864
- {
1865
- "epoch": 4.01,
1866
- "learning_rate": 5.1628111289476025e-06,
1867
- "loss": 0.0239,
1868
- "step": 310
1869
- },
1870
- {
1871
- "epoch": 4.02,
1872
- "learning_rate": 5.101555666739563e-06,
1873
- "loss": 0.0095,
1874
- "step": 311
1875
- },
1876
- {
1877
- "epoch": 4.03,
1878
- "learning_rate": 5.040541084183326e-06,
1879
- "loss": 0.0114,
1880
- "step": 312
1881
- },
1882
- {
1883
- "epoch": 4.05,
1884
- "learning_rate": 4.979770381654181e-06,
1885
- "loss": 0.0109,
1886
- "step": 313
1887
- },
1888
- {
1889
- "epoch": 4.06,
1890
- "learning_rate": 4.919246547534709e-06,
1891
- "loss": 0.0095,
1892
- "step": 314
1893
- },
1894
- {
1895
- "epoch": 4.07,
1896
- "learning_rate": 4.858972558067784e-06,
1897
- "loss": 0.0103,
1898
- "step": 315
1899
- },
1900
- {
1901
- "epoch": 4.08,
1902
- "learning_rate": 4.798951377210253e-06,
1903
- "loss": 0.0088,
1904
- "step": 316
1905
- },
1906
- {
1907
- "epoch": 4.1,
1908
- "learning_rate": 4.739185956487169e-06,
1909
- "loss": 0.0107,
1910
- "step": 317
1911
- },
1912
- {
1913
- "epoch": 4.11,
1914
- "learning_rate": 4.679679234846636e-06,
1915
- "loss": 0.0108,
1916
- "step": 318
1917
- },
1918
- {
1919
- "epoch": 4.12,
1920
- "learning_rate": 4.6204341385153186e-06,
1921
- "loss": 0.0098,
1922
- "step": 319
1923
- },
1924
- {
1925
- "epoch": 4.14,
1926
- "learning_rate": 4.561453580854516e-06,
1927
- "loss": 0.0121,
1928
- "step": 320
1929
- },
1930
- {
1931
- "epoch": 4.15,
1932
- "learning_rate": 4.502740462216919e-06,
1933
- "loss": 0.0124,
1934
- "step": 321
1935
- },
1936
- {
1937
- "epoch": 4.16,
1938
- "learning_rate": 4.444297669803981e-06,
1939
- "loss": 0.0089,
1940
- "step": 322
1941
- },
1942
- {
1943
- "epoch": 4.17,
1944
- "learning_rate": 4.386128077523923e-06,
1945
- "loss": 0.0119,
1946
- "step": 323
1947
- },
1948
- {
1949
- "epoch": 4.19,
1950
- "learning_rate": 4.328234545850441e-06,
1951
- "loss": 0.0124,
1952
- "step": 324
1953
- },
1954
- {
1955
- "epoch": 4.2,
1956
- "learning_rate": 4.270619921682019e-06,
1957
- "loss": 0.0098,
1958
- "step": 325
1959
- },
1960
- {
1961
- "epoch": 4.21,
1962
- "learning_rate": 4.213287038201943e-06,
1963
- "loss": 0.0106,
1964
- "step": 326
1965
- },
1966
- {
1967
- "epoch": 4.23,
1968
- "learning_rate": 4.156238714738974e-06,
1969
- "loss": 0.012,
1970
- "step": 327
1971
- },
1972
- {
1973
- "epoch": 4.24,
1974
- "learning_rate": 4.09947775662872e-06,
1975
- "loss": 0.0081,
1976
- "step": 328
1977
- },
1978
- {
1979
- "epoch": 4.25,
1980
- "learning_rate": 4.043006955075667e-06,
1981
- "loss": 0.0093,
1982
- "step": 329
1983
- },
1984
- {
1985
- "epoch": 4.26,
1986
- "learning_rate": 3.986829087015941e-06,
1987
- "loss": 0.0079,
1988
- "step": 330
1989
- },
1990
- {
1991
- "epoch": 4.28,
1992
- "learning_rate": 3.930946914980744e-06,
1993
- "loss": 0.0105,
1994
- "step": 331
1995
- },
1996
- {
1997
- "epoch": 4.29,
1998
- "learning_rate": 3.875363186960499e-06,
1999
- "loss": 0.0094,
2000
- "step": 332
2001
- },
2002
- {
2003
- "epoch": 4.3,
2004
- "learning_rate": 3.820080636269737e-06,
2005
- "loss": 0.0095,
2006
- "step": 333
2007
- },
2008
- {
2009
- "epoch": 4.32,
2010
- "learning_rate": 3.7651019814126656e-06,
2011
- "loss": 0.0105,
2012
- "step": 334
2013
- },
2014
- {
2015
- "epoch": 4.33,
2016
- "learning_rate": 3.7104299259495113e-06,
2017
- "loss": 0.0058,
2018
- "step": 335
2019
- },
2020
- {
2021
- "epoch": 4.34,
2022
- "learning_rate": 3.6560671583635467e-06,
2023
- "loss": 0.0071,
2024
- "step": 336
2025
- },
2026
- {
2027
- "epoch": 4.36,
2028
- "learning_rate": 3.6020163519289077e-06,
2029
- "loss": 0.009,
2030
- "step": 337
2031
- },
2032
- {
2033
- "epoch": 4.37,
2034
- "learning_rate": 3.5482801645791266e-06,
2035
- "loss": 0.0086,
2036
- "step": 338
2037
- },
2038
- {
2039
- "epoch": 4.38,
2040
- "learning_rate": 3.494861238776418e-06,
2041
- "loss": 0.0073,
2042
- "step": 339
2043
- },
2044
- {
2045
- "epoch": 4.39,
2046
- "learning_rate": 3.4417622013817597e-06,
2047
- "loss": 0.0073,
2048
- "step": 340
2049
- },
2050
- {
2051
- "epoch": 4.41,
2052
- "learning_rate": 3.3889856635257024e-06,
2053
- "loss": 0.0054,
2054
- "step": 341
2055
- },
2056
- {
2057
- "epoch": 4.42,
2058
- "learning_rate": 3.3365342204799613e-06,
2059
- "loss": 0.0061,
2060
- "step": 342
2061
- },
2062
- {
2063
- "epoch": 4.43,
2064
- "learning_rate": 3.284410451529816e-06,
2065
- "loss": 0.0055,
2066
- "step": 343
2067
- },
2068
- {
2069
- "epoch": 4.45,
2070
- "learning_rate": 3.2326169198472555e-06,
2071
- "loss": 0.0066,
2072
- "step": 344
2073
- },
2074
- {
2075
- "epoch": 4.46,
2076
- "learning_rate": 3.1811561723649496e-06,
2077
- "loss": 0.009,
2078
- "step": 345
2079
- },
2080
- {
2081
- "epoch": 4.47,
2082
- "learning_rate": 3.1300307396509833e-06,
2083
- "loss": 0.0077,
2084
- "step": 346
2085
- },
2086
- {
2087
- "epoch": 4.48,
2088
- "learning_rate": 3.0792431357844444e-06,
2089
- "loss": 0.0061,
2090
- "step": 347
2091
- },
2092
- {
2093
- "epoch": 4.5,
2094
- "learning_rate": 3.028795858231768e-06,
2095
- "loss": 0.0062,
2096
- "step": 348
2097
- },
2098
- {
2099
- "epoch": 4.51,
2100
- "learning_rate": 2.9786913877239486e-06,
2101
- "loss": 0.0058,
2102
- "step": 349
2103
- },
2104
- {
2105
- "epoch": 4.52,
2106
- "learning_rate": 2.9289321881345257e-06,
2107
- "loss": 0.0078,
2108
- "step": 350
2109
- },
2110
- {
2111
- "epoch": 4.54,
2112
- "learning_rate": 2.879520706358446e-06,
2113
- "loss": 0.0075,
2114
- "step": 351
2115
- },
2116
- {
2117
- "epoch": 4.55,
2118
- "learning_rate": 2.8304593721917283e-06,
2119
- "loss": 0.0058,
2120
- "step": 352
2121
- },
2122
- {
2123
- "epoch": 4.56,
2124
- "learning_rate": 2.7817505982119708e-06,
2125
- "loss": 0.0065,
2126
- "step": 353
2127
- },
2128
- {
2129
- "epoch": 4.58,
2130
- "learning_rate": 2.7333967796597317e-06,
2131
- "loss": 0.0058,
2132
- "step": 354
2133
- },
2134
- {
2135
- "epoch": 4.59,
2136
- "learning_rate": 2.6854002943207245e-06,
2137
- "loss": 0.0063,
2138
- "step": 355
2139
- },
2140
- {
2141
- "epoch": 4.6,
2142
- "learning_rate": 2.637763502408909e-06,
2143
- "loss": 0.0052,
2144
- "step": 356
2145
- },
2146
- {
2147
- "epoch": 4.61,
2148
- "learning_rate": 2.5904887464504115e-06,
2149
- "loss": 0.0068,
2150
- "step": 357
2151
- },
2152
- {
2153
- "epoch": 4.63,
2154
- "learning_rate": 2.5435783511683444e-06,
2155
- "loss": 0.0089,
2156
- "step": 358
2157
- },
2158
- {
2159
- "epoch": 4.64,
2160
- "learning_rate": 2.4970346233684863e-06,
2161
- "loss": 0.006,
2162
- "step": 359
2163
- },
2164
- {
2165
- "epoch": 4.65,
2166
- "learning_rate": 2.450859851825842e-06,
2167
- "loss": 0.0046,
2168
- "step": 360
2169
- },
2170
- {
2171
- "epoch": 4.67,
2172
- "learning_rate": 2.4050563071720867e-06,
2173
- "loss": 0.0055,
2174
- "step": 361
2175
- },
2176
- {
2177
- "epoch": 4.68,
2178
- "learning_rate": 2.3596262417839256e-06,
2179
- "loss": 0.0045,
2180
- "step": 362
2181
- },
2182
- {
2183
- "epoch": 4.69,
2184
- "learning_rate": 2.3145718896723204e-06,
2185
- "loss": 0.0053,
2186
- "step": 363
2187
- },
2188
- {
2189
- "epoch": 4.7,
2190
- "learning_rate": 2.26989546637263e-06,
2191
- "loss": 0.0056,
2192
- "step": 364
2193
- },
2194
- {
2195
- "epoch": 4.72,
2196
- "learning_rate": 2.225599168835677e-06,
2197
- "loss": 0.0043,
2198
- "step": 365
2199
- },
2200
- {
2201
- "epoch": 4.73,
2202
- "learning_rate": 2.1816851753197023e-06,
2203
- "loss": 0.0078,
2204
- "step": 366
2205
- },
2206
- {
2207
- "epoch": 4.74,
2208
- "learning_rate": 2.138155645283244e-06,
2209
- "loss": 0.0068,
2210
- "step": 367
2211
- },
2212
- {
2213
- "epoch": 4.76,
2214
- "learning_rate": 2.095012719278966e-06,
2215
- "loss": 0.0037,
2216
- "step": 368
2217
- },
2218
- {
2219
- "epoch": 4.77,
2220
- "learning_rate": 2.0522585188483745e-06,
2221
- "loss": 0.0038,
2222
- "step": 369
2223
- },
2224
- {
2225
- "epoch": 4.78,
2226
- "learning_rate": 2.009895146417512e-06,
2227
- "loss": 0.0044,
2228
- "step": 370
2229
- },
2230
- {
2231
- "epoch": 4.79,
2232
- "learning_rate": 1.967924685193552e-06,
2233
- "loss": 0.0059,
2234
- "step": 371
2235
- },
2236
- {
2237
- "epoch": 4.81,
2238
- "learning_rate": 1.9263491990623763e-06,
2239
- "loss": 0.005,
2240
- "step": 372
2241
- },
2242
- {
2243
- "epoch": 4.82,
2244
- "learning_rate": 1.885170732487074e-06,
2245
- "loss": 0.0041,
2246
- "step": 373
2247
- },
2248
- {
2249
- "epoch": 4.83,
2250
- "learning_rate": 1.8443913104073984e-06,
2251
- "loss": 0.004,
2252
- "step": 374
2253
- },
2254
- {
2255
- "epoch": 4.85,
2256
- "learning_rate": 1.8040129381402137e-06,
2257
- "loss": 0.0042,
2258
- "step": 375
2259
- },
2260
- {
2261
- "epoch": 4.86,
2262
- "learning_rate": 1.7640376012808536e-06,
2263
- "loss": 0.0036,
2264
- "step": 376
2265
- },
2266
- {
2267
- "epoch": 4.87,
2268
- "learning_rate": 1.7244672656055105e-06,
2269
- "loss": 0.0037,
2270
- "step": 377
2271
- },
2272
- {
2273
- "epoch": 4.89,
2274
- "learning_rate": 1.6853038769745466e-06,
2275
- "loss": 0.0043,
2276
- "step": 378
2277
- },
2278
- {
2279
- "epoch": 4.9,
2280
- "learning_rate": 1.6465493612368233e-06,
2281
- "loss": 0.0052,
2282
- "step": 379
2283
- },
2284
- {
2285
- "epoch": 4.91,
2286
- "learning_rate": 1.6082056241349787e-06,
2287
- "loss": 0.0037,
2288
- "step": 380
2289
- },
2290
- {
2291
- "epoch": 4.92,
2292
- "learning_rate": 1.5702745512117323e-06,
2293
- "loss": 0.0034,
2294
- "step": 381
2295
- },
2296
- {
2297
- "epoch": 4.94,
2298
- "learning_rate": 1.5327580077171589e-06,
2299
- "loss": 0.0044,
2300
- "step": 382
2301
- },
2302
- {
2303
- "epoch": 4.95,
2304
- "learning_rate": 1.495657838516953e-06,
2305
- "loss": 0.0029,
2306
- "step": 383
2307
- },
2308
- {
2309
- "epoch": 4.96,
2310
- "learning_rate": 1.4589758680017263e-06,
2311
- "loss": 0.0026,
2312
- "step": 384
2313
- },
2314
- {
2315
- "epoch": 4.98,
2316
- "learning_rate": 1.4227138999972801e-06,
2317
- "loss": 0.0036,
2318
- "step": 385
2319
- },
2320
- {
2321
- "epoch": 4.99,
2322
- "learning_rate": 1.3868737176759105e-06,
2323
- "loss": 0.0049,
2324
- "step": 386
2325
- },
2326
- {
2327
- "epoch": 5.0,
2328
- "learning_rate": 1.3514570834687203e-06,
2329
- "loss": 0.0031,
2330
- "step": 387
2331
- },
2332
- {
2333
- "epoch": 5.01,
2334
- "learning_rate": 1.3164657389789459e-06,
2335
- "loss": 0.0015,
2336
- "step": 388
2337
- },
2338
- {
2339
- "epoch": 5.03,
2340
- "learning_rate": 1.281901404896323e-06,
2341
- "loss": 0.0016,
2342
- "step": 389
2343
- },
2344
- {
2345
- "epoch": 5.04,
2346
- "learning_rate": 1.2477657809124632e-06,
2347
- "loss": 0.0023,
2348
- "step": 390
2349
- },
2350
- {
2351
- "epoch": 5.05,
2352
- "learning_rate": 1.2140605456372856e-06,
2353
- "loss": 0.0026,
2354
- "step": 391
2355
- },
2356
- {
2357
- "epoch": 5.07,
2358
- "learning_rate": 1.1807873565164507e-06,
2359
- "loss": 0.0018,
2360
- "step": 392
2361
- },
2362
- {
2363
- "epoch": 5.08,
2364
- "learning_rate": 1.1479478497498796e-06,
2365
- "loss": 0.0017,
2366
- "step": 393
2367
- },
2368
- {
2369
- "epoch": 5.09,
2370
- "learning_rate": 1.1155436402112785e-06,
2371
- "loss": 0.0021,
2372
- "step": 394
2373
- },
2374
- {
2375
- "epoch": 5.11,
2376
- "learning_rate": 1.08357632136873e-06,
2377
- "loss": 0.0014,
2378
- "step": 395
2379
- },
2380
- {
2381
- "epoch": 5.12,
2382
- "learning_rate": 1.0520474652063395e-06,
2383
- "loss": 0.0012,
2384
- "step": 396
2385
- },
2386
- {
2387
- "epoch": 5.13,
2388
- "learning_rate": 1.0209586221469336e-06,
2389
- "loss": 0.0019,
2390
- "step": 397
2391
- },
2392
- {
2393
- "epoch": 5.14,
2394
- "learning_rate": 9.903113209758098e-07,
2395
- "loss": 0.0014,
2396
- "step": 398
2397
- },
2398
- {
2399
- "epoch": 5.16,
2400
- "learning_rate": 9.601070687655667e-07,
2401
- "loss": 0.0024,
2402
- "step": 399
2403
- },
2404
- {
2405
- "epoch": 5.17,
2406
- "learning_rate": 9.303473508019944e-07,
2407
- "loss": 0.003,
2408
- "step": 400
2409
- },
2410
- {
2411
- "epoch": 5.18,
2412
- "learning_rate": 9.010336305110345e-07,
2413
- "loss": 0.0029,
2414
- "step": 401
2415
- },
2416
- {
2417
- "epoch": 5.2,
2418
- "learning_rate": 8.721673493868111e-07,
2419
- "loss": 0.0014,
2420
- "step": 402
2421
- },
2422
- {
2423
- "epoch": 5.21,
2424
- "learning_rate": 8.437499269207538e-07,
2425
- "loss": 0.0018,
2426
- "step": 403
2427
- },
2428
- {
2429
- "epoch": 5.22,
2430
- "learning_rate": 8.157827605317892e-07,
2431
- "loss": 0.0013,
2432
- "step": 404
2433
- },
2434
- {
2435
- "epoch": 5.23,
2436
- "learning_rate": 7.882672254976298e-07,
2437
- "loss": 0.0014,
2438
- "step": 405
2439
- },
2440
- {
2441
- "epoch": 5.25,
2442
- "learning_rate": 7.612046748871327e-07,
2443
- "loss": 0.0014,
2444
- "step": 406
2445
- },
2446
- {
2447
- "epoch": 5.26,
2448
- "learning_rate": 7.345964394937788e-07,
2449
- "loss": 0.002,
2450
- "step": 407
2451
- },
2452
- {
2453
- "epoch": 5.27,
2454
- "learning_rate": 7.084438277702188e-07,
2455
- "loss": 0.0021,
2456
- "step": 408
2457
- },
2458
- {
2459
- "epoch": 5.29,
2460
- "learning_rate": 6.827481257639346e-07,
2461
- "loss": 0.0014,
2462
- "step": 409
2463
- },
2464
- {
2465
- "epoch": 5.3,
2466
- "learning_rate": 6.57510597054003e-07,
2467
- "loss": 0.0012,
2468
- "step": 410
2469
- },
2470
- {
2471
- "epoch": 5.31,
2472
- "learning_rate": 6.327324826889469e-07,
2473
- "loss": 0.002,
2474
- "step": 411
2475
- },
2476
- {
2477
- "epoch": 5.32,
2478
- "learning_rate": 6.084150011257239e-07,
2479
- "loss": 0.0014,
2480
- "step": 412
2481
- },
2482
- {
2483
- "epoch": 5.34,
2484
- "learning_rate": 5.845593481697931e-07,
2485
- "loss": 0.0011,
2486
- "step": 413
2487
- },
2488
- {
2489
- "epoch": 5.35,
2490
- "learning_rate": 5.611666969163243e-07,
2491
- "loss": 0.0025,
2492
- "step": 414
2493
- },
2494
- {
2495
- "epoch": 5.36,
2496
- "learning_rate": 5.382381976925044e-07,
2497
- "loss": 0.0013,
2498
- "step": 415
2499
- },
2500
- {
2501
- "epoch": 5.38,
2502
- "learning_rate": 5.157749780009735e-07,
2503
- "loss": 0.0014,
2504
- "step": 416
2505
- },
2506
- {
2507
- "epoch": 5.39,
2508
- "learning_rate": 4.937781424643728e-07,
2509
- "loss": 0.0014,
2510
- "step": 417
2511
- },
2512
- {
2513
- "epoch": 5.4,
2514
- "learning_rate": 4.7224877277103673e-07,
2515
- "loss": 0.0012,
2516
- "step": 418
2517
- },
2518
- {
2519
- "epoch": 5.42,
2520
- "learning_rate": 4.511879276217967e-07,
2521
- "loss": 0.0014,
2522
- "step": 419
2523
- },
2524
- {
2525
- "epoch": 5.43,
2526
- "learning_rate": 4.305966426779118e-07,
2527
- "loss": 0.0016,
2528
- "step": 420
2529
- },
2530
- {
2531
- "epoch": 5.44,
2532
- "learning_rate": 4.1047593051015245e-07,
2533
- "loss": 0.0012,
2534
- "step": 421
2535
- },
2536
- {
2537
- "epoch": 5.45,
2538
- "learning_rate": 3.908267805490051e-07,
2539
- "loss": 0.0024,
2540
- "step": 422
2541
- },
2542
- {
2543
- "epoch": 5.47,
2544
- "learning_rate": 3.7165015903600553e-07,
2545
- "loss": 0.0012,
2546
- "step": 423
2547
- },
2548
- {
2549
- "epoch": 5.48,
2550
- "learning_rate": 3.529470089762421e-07,
2551
- "loss": 0.0014,
2552
- "step": 424
2553
- },
2554
- {
2555
- "epoch": 5.49,
2556
- "learning_rate": 3.347182500919677e-07,
2557
- "loss": 0.0014,
2558
- "step": 425
2559
- },
2560
- {
2561
- "epoch": 5.51,
2562
- "learning_rate": 3.1696477877738664e-07,
2563
- "loss": 0.0021,
2564
- "step": 426
2565
- },
2566
- {
2567
- "epoch": 5.52,
2568
- "learning_rate": 2.996874680545603e-07,
2569
- "loss": 0.002,
2570
- "step": 427
2571
- },
2572
- {
2573
- "epoch": 5.53,
2574
- "learning_rate": 2.8288716753049007e-07,
2575
- "loss": 0.0013,
2576
- "step": 428
2577
- },
2578
- {
2579
- "epoch": 5.54,
2580
- "learning_rate": 2.665647033553309e-07,
2581
- "loss": 0.0014,
2582
- "step": 429
2583
- },
2584
- {
2585
- "epoch": 5.56,
2586
- "learning_rate": 2.507208781817638e-07,
2587
- "loss": 0.0012,
2588
- "step": 430
2589
- },
2590
- {
2591
- "epoch": 5.57,
2592
- "learning_rate": 2.3535647112553295e-07,
2593
- "loss": 0.0018,
2594
- "step": 431
2595
- },
2596
- {
2597
- "epoch": 5.58,
2598
- "learning_rate": 2.20472237727124e-07,
2599
- "loss": 0.0014,
2600
- "step": 432
2601
- },
2602
- {
2603
- "epoch": 5.6,
2604
- "learning_rate": 2.0606890991461737e-07,
2605
- "loss": 0.0011,
2606
- "step": 433
2607
- },
2608
- {
2609
- "epoch": 5.61,
2610
- "learning_rate": 1.921471959676957e-07,
2611
- "loss": 0.0012,
2612
- "step": 434
2613
- },
2614
- {
2615
- "epoch": 5.62,
2616
- "learning_rate": 1.787077804828097e-07,
2617
- "loss": 0.0012,
2618
- "step": 435
2619
- },
2620
- {
2621
- "epoch": 5.63,
2622
- "learning_rate": 1.657513243395159e-07,
2623
- "loss": 0.0014,
2624
- "step": 436
2625
- },
2626
- {
2627
- "epoch": 5.65,
2628
- "learning_rate": 1.5327846466797857e-07,
2629
- "loss": 0.0013,
2630
- "step": 437
2631
- },
2632
- {
2633
- "epoch": 5.66,
2634
- "learning_rate": 1.4128981481764115e-07,
2635
- "loss": 0.0012,
2636
- "step": 438
2637
- },
2638
- {
2639
- "epoch": 5.67,
2640
- "learning_rate": 1.2978596432705826e-07,
2641
- "loss": 0.0013,
2642
- "step": 439
2643
- },
2644
- {
2645
- "epoch": 5.69,
2646
- "learning_rate": 1.1876747889491225e-07,
2647
- "loss": 0.0017,
2648
- "step": 440
2649
- },
2650
- {
2651
- "epoch": 5.7,
2652
- "learning_rate": 1.0823490035218986e-07,
2653
- "loss": 0.0014,
2654
- "step": 441
2655
- },
2656
- {
2657
- "epoch": 5.71,
2658
- "learning_rate": 9.818874663554356e-08,
2659
- "loss": 0.0021,
2660
- "step": 442
2661
- },
2662
- {
2663
- "epoch": 5.73,
2664
- "learning_rate": 8.862951176181744e-08,
2665
- "loss": 0.0011,
2666
- "step": 443
2667
- },
2668
- {
2669
- "epoch": 5.74,
2670
- "learning_rate": 7.955766580375334e-08,
2671
- "loss": 0.0013,
2672
- "step": 444
2673
- },
2674
- {
2675
- "epoch": 5.75,
2676
- "learning_rate": 7.097365486688158e-08,
2677
- "loss": 0.0014,
2678
- "step": 445
2679
- },
2680
- {
2681
- "epoch": 5.76,
2682
- "learning_rate": 6.287790106757396e-08,
2683
- "loss": 0.0012,
2684
- "step": 446
2685
- },
2686
- {
2687
- "epoch": 5.78,
2688
- "learning_rate": 5.527080251229833e-08,
2689
- "loss": 0.0013,
2690
- "step": 447
2691
- },
2692
- {
2693
- "epoch": 5.79,
2694
- "learning_rate": 4.815273327803183e-08,
2695
- "loss": 0.0013,
2696
- "step": 448
2697
- },
2698
- {
2699
- "epoch": 5.8,
2700
- "learning_rate": 4.152404339386795e-08,
2701
- "loss": 0.0023,
2702
- "step": 449
2703
- },
2704
- {
2705
- "epoch": 5.82,
2706
- "learning_rate": 3.538505882380916e-08,
2707
- "loss": 0.0014,
2708
- "step": 450
2709
- },
2710
- {
2711
- "epoch": 5.83,
2712
- "learning_rate": 2.9736081450730813e-08,
2713
- "loss": 0.0013,
2714
- "step": 451
2715
- },
2716
- {
2717
- "epoch": 5.84,
2718
- "learning_rate": 2.4577389061539724e-08,
2719
- "loss": 0.0015,
2720
- "step": 452
2721
- },
2722
- {
2723
- "epoch": 5.85,
2724
- "learning_rate": 1.9909235333517296e-08,
2725
- "loss": 0.0013,
2726
- "step": 453
2727
- },
2728
- {
2729
- "epoch": 5.87,
2730
- "learning_rate": 1.5731849821833955e-08,
2731
- "loss": 0.0012,
2732
- "step": 454
2733
- },
2734
- {
2735
- "epoch": 5.88,
2736
- "learning_rate": 1.2045437948275952e-08,
2737
- "loss": 0.0012,
2738
- "step": 455
2739
- },
2740
- {
2741
- "epoch": 5.89,
2742
- "learning_rate": 8.850180991131219e-09,
2743
- "loss": 0.0013,
2744
- "step": 456
2745
- },
2746
- {
2747
- "epoch": 5.91,
2748
- "learning_rate": 6.146236076279843e-09,
2749
- "loss": 0.0013,
2750
- "step": 457
2751
- },
2752
- {
2753
- "epoch": 5.92,
2754
- "learning_rate": 3.933736169471347e-09,
2755
- "loss": 0.0019,
2756
- "step": 458
2757
- },
2758
- {
2759
- "epoch": 5.93,
2760
- "learning_rate": 2.2127900697777038e-09,
2761
- "loss": 0.0012,
2762
- "step": 459
2763
- },
2764
- {
2765
- "epoch": 5.95,
2766
- "learning_rate": 9.83482404249836e-10,
2767
- "loss": 0.0011,
2768
- "step": 460
2769
- },
2770
- {
2771
- "epoch": 5.96,
2772
- "learning_rate": 2.45873623754278e-10,
2773
- "loss": 0.0014,
2774
- "step": 461
2775
- },
2776
- {
2777
- "epoch": 5.97,
2778
- "learning_rate": 0.0,
2779
- "loss": 0.0012,
2780
- "step": 462
2781
- },
2782
- {
2783
- "epoch": 5.97,
2784
- "step": 462,
2785
- "total_flos": 1.223725601702019e+18,
2786
- "train_loss": 0.3808029658807184,
2787
- "train_runtime": 10388.2603,
2788
- "train_samples_per_second": 11.435,
2789
- "train_steps_per_second": 0.044
2790
- }
2791
- ],
2792
- "max_steps": 462,
2793
- "num_train_epochs": 6,
2794
- "total_flos": 1.223725601702019e+18,
2795
- "trial_name": null,
2796
- "trial_params": null
2797
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
layout_planner_m1/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:43e7d0290e998eeed248ddf3776fd5ab72c8137d4cfaaba831ad08a833afbd4a
3
- size 3707