Hugging Face's logo

VQA-CityU
/
kadis_yfcc_compare_new

Text Generation
Transformers
PyTorch
mplug_owl2
Inference Endpoints
Model card Files Community
H4nwei commited on
Commit
521c481
•
1 Parent(s): 92e200d

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. config.json +187 -0
  2. preprocessor_config.json +20 -0
  3. pytorch_model-00001-of-00004.bin +3 -0
  4. pytorch_model-00002-of-00004.bin +3 -0
  5. pytorch_model-00003-of-00004.bin +3 -0
  6. pytorch_model-00004-of-00004.bin +3 -0
  7. pytorch_model.bin.index.json +869 -0
  8. special_tokens_map.json +24 -0
  9. tokenizer.model +3 -0
  10. tokenizer_config.json +42 -0
  11. trainer_state.json +4230 -0
  12. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,187 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MAGAer13/mplug-owl2-llama2-7b",
3
+ "architectures": [
4
+ "MPLUGOwl2LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "freeze_vision_model": false,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "image_aspect_ratio": "pad",
14
+ "image_grid_pinpoints": null,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 11008,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "mplug_owl2",
19
+ "num_attention_heads": 32,
20
+ "num_hidden_layers": 32,
21
+ "num_key_value_heads": 32,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.36.1",
29
+ "tune_visual_abstractor": true,
30
+ "use_cache": true,
31
+ "visual_abstractor_lr": null,
32
+ "visual_config": {
33
+ "visual_abstractor": {
34
+ "_name_or_path": "",
35
+ "add_cross_attention": false,
36
+ "architectures": null,
37
+ "attention_probs_dropout_prob": 0.0,
38
+ "bad_words_ids": null,
39
+ "begin_suppress_tokens": null,
40
+ "bos_token_id": null,
41
+ "chunk_size_feed_forward": 0,
42
+ "cross_attention_hidden_size": null,
43
+ "decoder_start_token_id": null,
44
+ "diversity_penalty": 0.0,
45
+ "do_sample": false,
46
+ "early_stopping": false,
47
+ "encoder_hidden_size": 1024,
48
+ "encoder_no_repeat_ngram_size": 0,
49
+ "eos_token_id": null,
50
+ "exponential_decay_length_penalty": null,
51
+ "finetuning_task": null,
52
+ "forced_bos_token_id": null,
53
+ "forced_eos_token_id": null,
54
+ "grid_size": 32,
55
+ "hidden_size": 1024,
56
+ "id2label": {
57
+ "0": "LABEL_0",
58
+ "1": "LABEL_1"
59
+ },
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 2816,
62
+ "is_decoder": false,
63
+ "is_encoder_decoder": false,
64
+ "label2id": {
65
+ "LABEL_0": 0,
66
+ "LABEL_1": 1
67
+ },
68
+ "layer_norm_eps": 1e-06,
69
+ "length_penalty": 1.0,
70
+ "max_length": 20,
71
+ "min_length": 0,
72
+ "model_type": "mplug_owl_visual_abstract",
73
+ "no_repeat_ngram_size": 0,
74
+ "num_attention_heads": 16,
75
+ "num_beam_groups": 1,
76
+ "num_beams": 1,
77
+ "num_hidden_layers": 6,
78
+ "num_learnable_queries": 64,
79
+ "num_return_sequences": 1,
80
+ "output_attentions": false,
81
+ "output_hidden_states": false,
82
+ "output_scores": false,
83
+ "pad_token_id": null,
84
+ "prefix": null,
85
+ "problem_type": null,
86
+ "pruned_heads": {},
87
+ "remove_invalid_values": false,
88
+ "repetition_penalty": 1.0,
89
+ "return_dict": true,
90
+ "return_dict_in_generate": false,
91
+ "sep_token_id": null,
92
+ "suppress_tokens": null,
93
+ "task_specific_params": null,
94
+ "temperature": 1.0,
95
+ "tf_legacy_loss": false,
96
+ "tie_encoder_decoder": false,
97
+ "tie_word_embeddings": true,
98
+ "tokenizer_class": null,
99
+ "top_k": 50,
100
+ "top_p": 1.0,
101
+ "torch_dtype": null,
102
+ "torchscript": false,
103
+ "transformers_version": "4.28.1",
104
+ "typical_p": 1.0,
105
+ "use_bfloat16": false
106
+ },
107
+ "visual_model": {
108
+ "_name_or_path": "",
109
+ "add_cross_attention": false,
110
+ "architectures": null,
111
+ "attention_dropout": 0.0,
112
+ "bad_words_ids": null,
113
+ "begin_suppress_tokens": null,
114
+ "bos_token_id": null,
115
+ "chunk_size_feed_forward": 0,
116
+ "cross_attention_hidden_size": null,
117
+ "decoder_start_token_id": null,
118
+ "diversity_penalty": 0.0,
119
+ "do_sample": false,
120
+ "early_stopping": false,
121
+ "encoder_no_repeat_ngram_size": 0,
122
+ "eos_token_id": null,
123
+ "exponential_decay_length_penalty": null,
124
+ "finetuning_task": null,
125
+ "forced_bos_token_id": null,
126
+ "forced_eos_token_id": null,
127
+ "hidden_act": "quick_gelu",
128
+ "hidden_size": 1024,
129
+ "id2label": {
130
+ "0": "LABEL_0",
131
+ "1": "LABEL_1"
132
+ },
133
+ "image_size": 448,
134
+ "initializer_factor": 1.0,
135
+ "initializer_range": 0.02,
136
+ "intermediate_size": 4096,
137
+ "is_decoder": false,
138
+ "is_encoder_decoder": false,
139
+ "label2id": {
140
+ "LABEL_0": 0,
141
+ "LABEL_1": 1
142
+ },
143
+ "layer_norm_eps": 1e-06,
144
+ "length_penalty": 1.0,
145
+ "max_length": 20,
146
+ "min_length": 0,
147
+ "model_type": "mplug_owl_vision_model",
148
+ "no_repeat_ngram_size": 0,
149
+ "num_attention_heads": 16,
150
+ "num_beam_groups": 1,
151
+ "num_beams": 1,
152
+ "num_channels": 3,
153
+ "num_hidden_layers": 24,
154
+ "num_return_sequences": 1,
155
+ "output_attentions": false,
156
+ "output_hidden_states": false,
157
+ "output_scores": false,
158
+ "pad_token_id": null,
159
+ "patch_size": 14,
160
+ "prefix": null,
161
+ "problem_type": null,
162
+ "projection_dim": 768,
163
+ "pruned_heads": {},
164
+ "remove_invalid_values": false,
165
+ "repetition_penalty": 1.0,
166
+ "return_dict": true,
167
+ "return_dict_in_generate": false,
168
+ "sep_token_id": null,
169
+ "suppress_tokens": null,
170
+ "task_specific_params": null,
171
+ "temperature": 1.0,
172
+ "tf_legacy_loss": false,
173
+ "tie_encoder_decoder": false,
174
+ "tie_word_embeddings": true,
175
+ "tokenizer_class": null,
176
+ "top_k": 50,
177
+ "top_p": 1.0,
178
+ "torch_dtype": null,
179
+ "torchscript": false,
180
+ "transformers_version": "4.28.1",
181
+ "typical_p": 1.0,
182
+ "use_bfloat16": false,
183
+ "use_flash_attn": false
184
+ }
185
+ },
186
+ "vocab_size": 32000
187
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": 448,
3
+ "do_center_crop": true,
4
+ "do_normalize": true,
5
+ "do_resize": true,
6
+ "feature_extractor_type": "CLIPFeatureExtractor",
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "resample": 3,
18
+ "size": 448
19
+ }
20
+
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed8122250227df70b6db31033ac569b1eff18c190b1f4e11c20558470296f488
3
+ size 4981108780
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d784cfd3138bbcfafa3108f7c3ac13b8d49703ae0e709a206770237689d787d
3
+ size 4920293259
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a24467f8dcd72d610a35a5e353920952b2e6056d40435dc4f6ef2abe7d35c70
3
+ size 4989532454
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b52854fd07e4d4d55df3970f5d75f984e0164707dc2477b92b69e46f92d0238
3
+ size 1518469929
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,869 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16409100288
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00004-of-00004.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
8
+ "model.layers.0.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
9
+ "model.layers.0.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
10
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
11
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
12
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
13
+ "model.layers.0.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
14
+ "model.layers.0.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
15
+ "model.layers.0.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
16
+ "model.layers.0.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
17
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
18
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
19
+ "model.layers.0.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
20
+ "model.layers.0.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
21
+ "model.layers.1.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
22
+ "model.layers.1.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
23
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
24
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
25
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
26
+ "model.layers.1.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
27
+ "model.layers.1.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
28
+ "model.layers.1.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
29
+ "model.layers.1.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
30
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
31
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
32
+ "model.layers.1.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
33
+ "model.layers.1.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
34
+ "model.layers.10.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
35
+ "model.layers.10.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
36
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
37
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
38
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
39
+ "model.layers.10.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
40
+ "model.layers.10.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
41
+ "model.layers.10.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
42
+ "model.layers.10.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
43
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
44
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
45
+ "model.layers.10.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
46
+ "model.layers.10.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
47
+ "model.layers.11.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
48
+ "model.layers.11.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
49
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
50
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
51
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
52
+ "model.layers.11.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
53
+ "model.layers.11.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
54
+ "model.layers.11.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
55
+ "model.layers.11.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
56
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
57
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
58
+ "model.layers.11.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
59
+ "model.layers.11.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
60
+ "model.layers.12.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
61
+ "model.layers.12.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
62
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
63
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
64
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
65
+ "model.layers.12.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
66
+ "model.layers.12.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
67
+ "model.layers.12.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
68
+ "model.layers.12.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
69
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
70
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
71
+ "model.layers.12.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
72
+ "model.layers.12.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
73
+ "model.layers.13.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
74
+ "model.layers.13.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
75
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
76
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
77
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
78
+ "model.layers.13.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
79
+ "model.layers.13.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
80
+ "model.layers.13.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
81
+ "model.layers.13.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
82
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
83
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
84
+ "model.layers.13.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
85
+ "model.layers.13.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
86
+ "model.layers.14.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
87
+ "model.layers.14.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
88
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
89
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
90
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
91
+ "model.layers.14.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
92
+ "model.layers.14.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
93
+ "model.layers.14.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
94
+ "model.layers.14.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
95
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
96
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
97
+ "model.layers.14.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
98
+ "model.layers.14.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
99
+ "model.layers.15.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
100
+ "model.layers.15.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
101
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
102
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
103
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
104
+ "model.layers.15.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
105
+ "model.layers.15.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
106
+ "model.layers.15.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
107
+ "model.layers.15.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
108
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
109
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
110
+ "model.layers.15.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
111
+ "model.layers.15.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
112
+ "model.layers.16.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
113
+ "model.layers.16.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
114
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
115
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
116
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
117
+ "model.layers.16.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
118
+ "model.layers.16.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
119
+ "model.layers.16.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
120
+ "model.layers.16.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
121
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
122
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
123
+ "model.layers.16.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
124
+ "model.layers.16.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
125
+ "model.layers.17.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
126
+ "model.layers.17.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
127
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
128
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
129
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
130
+ "model.layers.17.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
131
+ "model.layers.17.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
132
+ "model.layers.17.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
133
+ "model.layers.17.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
134
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
135
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
136
+ "model.layers.17.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
137
+ "model.layers.17.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
138
+ "model.layers.18.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
139
+ "model.layers.18.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
140
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
141
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
142
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
143
+ "model.layers.18.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
144
+ "model.layers.18.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
145
+ "model.layers.18.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
146
+ "model.layers.18.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
147
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
148
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
149
+ "model.layers.18.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
150
+ "model.layers.18.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
151
+ "model.layers.19.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
152
+ "model.layers.19.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
153
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
154
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
155
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
156
+ "model.layers.19.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
157
+ "model.layers.19.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
158
+ "model.layers.19.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
159
+ "model.layers.19.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
160
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
161
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
162
+ "model.layers.19.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
163
+ "model.layers.19.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
164
+ "model.layers.2.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
165
+ "model.layers.2.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
166
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
167
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
168
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
169
+ "model.layers.2.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
170
+ "model.layers.2.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
171
+ "model.layers.2.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
172
+ "model.layers.2.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
173
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
174
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
175
+ "model.layers.2.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
176
+ "model.layers.2.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
177
+ "model.layers.20.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
178
+ "model.layers.20.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
179
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
180
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
181
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
182
+ "model.layers.20.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
183
+ "model.layers.20.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
184
+ "model.layers.20.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
185
+ "model.layers.20.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
186
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
187
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
188
+ "model.layers.20.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
189
+ "model.layers.20.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
190
+ "model.layers.21.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
191
+ "model.layers.21.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
192
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
193
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
194
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
195
+ "model.layers.21.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
196
+ "model.layers.21.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
197
+ "model.layers.21.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
198
+ "model.layers.21.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
199
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
200
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
201
+ "model.layers.21.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
202
+ "model.layers.21.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
203
+ "model.layers.22.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
204
+ "model.layers.22.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
205
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
206
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
207
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
208
+ "model.layers.22.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
209
+ "model.layers.22.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
210
+ "model.layers.22.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
211
+ "model.layers.22.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
212
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
213
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
214
+ "model.layers.22.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
215
+ "model.layers.22.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
216
+ "model.layers.23.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
217
+ "model.layers.23.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
218
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
219
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
220
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
221
+ "model.layers.23.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
222
+ "model.layers.23.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
223
+ "model.layers.23.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
224
+ "model.layers.23.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
225
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
226
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
227
+ "model.layers.23.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
228
+ "model.layers.23.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
229
+ "model.layers.24.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
230
+ "model.layers.24.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
231
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
232
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
233
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
234
+ "model.layers.24.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
235
+ "model.layers.24.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
236
+ "model.layers.24.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
237
+ "model.layers.24.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
238
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
239
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
240
+ "model.layers.24.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
241
+ "model.layers.24.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
242
+ "model.layers.25.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
243
+ "model.layers.25.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
244
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
245
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
246
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
247
+ "model.layers.25.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
248
+ "model.layers.25.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
249
+ "model.layers.25.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
250
+ "model.layers.25.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
251
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
252
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
253
+ "model.layers.25.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
254
+ "model.layers.25.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
255
+ "model.layers.26.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
256
+ "model.layers.26.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
257
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
258
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
259
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
260
+ "model.layers.26.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
261
+ "model.layers.26.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
262
+ "model.layers.26.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
263
+ "model.layers.26.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
264
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
265
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
266
+ "model.layers.26.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
267
+ "model.layers.26.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
268
+ "model.layers.27.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
269
+ "model.layers.27.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
270
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
271
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
272
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
273
+ "model.layers.27.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
274
+ "model.layers.27.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
275
+ "model.layers.27.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
276
+ "model.layers.27.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
277
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
278
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
279
+ "model.layers.27.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
280
+ "model.layers.27.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
281
+ "model.layers.28.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
282
+ "model.layers.28.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
283
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
284
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
285
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
286
+ "model.layers.28.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
287
+ "model.layers.28.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
288
+ "model.layers.28.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
289
+ "model.layers.28.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
290
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
291
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
292
+ "model.layers.28.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
293
+ "model.layers.28.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
294
+ "model.layers.29.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
295
+ "model.layers.29.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
296
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
297
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
298
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
299
+ "model.layers.29.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
300
+ "model.layers.29.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
301
+ "model.layers.29.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
302
+ "model.layers.29.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
303
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
304
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
305
+ "model.layers.29.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
306
+ "model.layers.29.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
307
+ "model.layers.3.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
308
+ "model.layers.3.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
309
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
310
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
311
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
312
+ "model.layers.3.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
313
+ "model.layers.3.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
314
+ "model.layers.3.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
315
+ "model.layers.3.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
316
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
317
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
318
+ "model.layers.3.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
319
+ "model.layers.3.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
320
+ "model.layers.30.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
321
+ "model.layers.30.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
322
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
323
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
324
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
325
+ "model.layers.30.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
326
+ "model.layers.30.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
327
+ "model.layers.30.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
328
+ "model.layers.30.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
329
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
330
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
331
+ "model.layers.30.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
332
+ "model.layers.30.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
333
+ "model.layers.31.input_layernorm.multiway.0.weight": "pytorch_model-00004-of-00004.bin",
334
+ "model.layers.31.input_layernorm.multiway.1.weight": "pytorch_model-00004-of-00004.bin",
335
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
336
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
337
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
338
+ "model.layers.31.post_attention_layernorm.multiway.0.weight": "pytorch_model-00004-of-00004.bin",
339
+ "model.layers.31.post_attention_layernorm.multiway.1.weight": "pytorch_model-00004-of-00004.bin",
340
+ "model.layers.31.self_attn.k_proj.multiway.0.weight": "pytorch_model-00004-of-00004.bin",
341
+ "model.layers.31.self_attn.k_proj.multiway.1.weight": "pytorch_model-00004-of-00004.bin",
342
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
343
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
344
+ "model.layers.31.self_attn.v_proj.multiway.0.weight": "pytorch_model-00004-of-00004.bin",
345
+ "model.layers.31.self_attn.v_proj.multiway.1.weight": "pytorch_model-00004-of-00004.bin",
346
+ "model.layers.4.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
347
+ "model.layers.4.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
348
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
349
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
350
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
351
+ "model.layers.4.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
352
+ "model.layers.4.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
353
+ "model.layers.4.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
354
+ "model.layers.4.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
355
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
356
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
357
+ "model.layers.4.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
358
+ "model.layers.4.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
359
+ "model.layers.5.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
360
+ "model.layers.5.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
361
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
362
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
363
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
364
+ "model.layers.5.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
365
+ "model.layers.5.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
366
+ "model.layers.5.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
367
+ "model.layers.5.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
368
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
369
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
370
+ "model.layers.5.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
371
+ "model.layers.5.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
372
+ "model.layers.6.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
373
+ "model.layers.6.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
374
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
375
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
376
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
377
+ "model.layers.6.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
378
+ "model.layers.6.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
379
+ "model.layers.6.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
380
+ "model.layers.6.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
381
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
382
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
383
+ "model.layers.6.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
384
+ "model.layers.6.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
385
+ "model.layers.7.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
386
+ "model.layers.7.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
387
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
388
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
389
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
390
+ "model.layers.7.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
391
+ "model.layers.7.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
392
+ "model.layers.7.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
393
+ "model.layers.7.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
394
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
395
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
396
+ "model.layers.7.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
397
+ "model.layers.7.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
398
+ "model.layers.8.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
399
+ "model.layers.8.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
400
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
401
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
402
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
403
+ "model.layers.8.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
404
+ "model.layers.8.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
405
+ "model.layers.8.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
406
+ "model.layers.8.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
407
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
408
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
409
+ "model.layers.8.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
410
+ "model.layers.8.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
411
+ "model.layers.9.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
412
+ "model.layers.9.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
413
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
414
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
415
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
416
+ "model.layers.9.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
417
+ "model.layers.9.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
418
+ "model.layers.9.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
419
+ "model.layers.9.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
420
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
421
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
422
+ "model.layers.9.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
423
+ "model.layers.9.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
424
+ "model.norm.weight": "pytorch_model-00004-of-00004.bin",
425
+ "model.vision_model.embeddings.cls_token": "pytorch_model-00004-of-00004.bin",
426
+ "model.vision_model.embeddings.patch_embed.weight": "pytorch_model-00004-of-00004.bin",
427
+ "model.vision_model.embeddings.position_embedding": "pytorch_model-00004-of-00004.bin",
428
+ "model.vision_model.embeddings.pre_layernorm.bias": "pytorch_model-00004-of-00004.bin",
429
+ "model.vision_model.embeddings.pre_layernorm.weight": "pytorch_model-00004-of-00004.bin",
430
+ "model.vision_model.encoder.layers.0.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
431
+ "model.vision_model.encoder.layers.0.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
432
+ "model.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
433
+ "model.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
434
+ "model.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
435
+ "model.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
436
+ "model.vision_model.encoder.layers.0.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
437
+ "model.vision_model.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
438
+ "model.vision_model.encoder.layers.0.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
439
+ "model.vision_model.encoder.layers.0.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
440
+ "model.vision_model.encoder.layers.0.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
441
+ "model.vision_model.encoder.layers.0.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
442
+ "model.vision_model.encoder.layers.1.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
443
+ "model.vision_model.encoder.layers.1.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
444
+ "model.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
445
+ "model.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
446
+ "model.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
447
+ "model.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
448
+ "model.vision_model.encoder.layers.1.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
449
+ "model.vision_model.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
450
+ "model.vision_model.encoder.layers.1.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
451
+ "model.vision_model.encoder.layers.1.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
452
+ "model.vision_model.encoder.layers.1.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
453
+ "model.vision_model.encoder.layers.1.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
454
+ "model.vision_model.encoder.layers.10.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
455
+ "model.vision_model.encoder.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
456
+ "model.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
457
+ "model.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
458
+ "model.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
459
+ "model.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
460
+ "model.vision_model.encoder.layers.10.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
461
+ "model.vision_model.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
462
+ "model.vision_model.encoder.layers.10.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
463
+ "model.vision_model.encoder.layers.10.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
464
+ "model.vision_model.encoder.layers.10.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
465
+ "model.vision_model.encoder.layers.10.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
466
+ "model.vision_model.encoder.layers.11.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
467
+ "model.vision_model.encoder.layers.11.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
468
+ "model.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
469
+ "model.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
470
+ "model.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
471
+ "model.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
472
+ "model.vision_model.encoder.layers.11.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
473
+ "model.vision_model.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
474
+ "model.vision_model.encoder.layers.11.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
475
+ "model.vision_model.encoder.layers.11.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
476
+ "model.vision_model.encoder.layers.11.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
477
+ "model.vision_model.encoder.layers.11.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
478
+ "model.vision_model.encoder.layers.12.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
479
+ "model.vision_model.encoder.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
480
+ "model.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
481
+ "model.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
482
+ "model.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
483
+ "model.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
484
+ "model.vision_model.encoder.layers.12.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
485
+ "model.vision_model.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
486
+ "model.vision_model.encoder.layers.12.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
487
+ "model.vision_model.encoder.layers.12.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
488
+ "model.vision_model.encoder.layers.12.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
489
+ "model.vision_model.encoder.layers.12.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
490
+ "model.vision_model.encoder.layers.13.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
491
+ "model.vision_model.encoder.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
492
+ "model.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
493
+ "model.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
494
+ "model.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
495
+ "model.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
496
+ "model.vision_model.encoder.layers.13.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
497
+ "model.vision_model.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
498
+ "model.vision_model.encoder.layers.13.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
499
+ "model.vision_model.encoder.layers.13.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
500
+ "model.vision_model.encoder.layers.13.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
501
+ "model.vision_model.encoder.layers.13.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
502
+ "model.vision_model.encoder.layers.14.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
503
+ "model.vision_model.encoder.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
504
+ "model.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
505
+ "model.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
506
+ "model.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
507
+ "model.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
508
+ "model.vision_model.encoder.layers.14.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
509
+ "model.vision_model.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
510
+ "model.vision_model.encoder.layers.14.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
511
+ "model.vision_model.encoder.layers.14.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
512
+ "model.vision_model.encoder.layers.14.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
513
+ "model.vision_model.encoder.layers.14.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
514
+ "model.vision_model.encoder.layers.15.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
515
+ "model.vision_model.encoder.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
516
+ "model.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
517
+ "model.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
518
+ "model.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
519
+ "model.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
520
+ "model.vision_model.encoder.layers.15.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
521
+ "model.vision_model.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
522
+ "model.vision_model.encoder.layers.15.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
523
+ "model.vision_model.encoder.layers.15.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
524
+ "model.vision_model.encoder.layers.15.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
525
+ "model.vision_model.encoder.layers.15.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
526
+ "model.vision_model.encoder.layers.16.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
527
+ "model.vision_model.encoder.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
528
+ "model.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
529
+ "model.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
530
+ "model.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
531
+ "model.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
532
+ "model.vision_model.encoder.layers.16.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
533
+ "model.vision_model.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
534
+ "model.vision_model.encoder.layers.16.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
535
+ "model.vision_model.encoder.layers.16.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
536
+ "model.vision_model.encoder.layers.16.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
537
+ "model.vision_model.encoder.layers.16.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
538
+ "model.vision_model.encoder.layers.17.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
539
+ "model.vision_model.encoder.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
540
+ "model.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
541
+ "model.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
542
+ "model.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
543
+ "model.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
544
+ "model.vision_model.encoder.layers.17.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
545
+ "model.vision_model.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
546
+ "model.vision_model.encoder.layers.17.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
547
+ "model.vision_model.encoder.layers.17.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
548
+ "model.vision_model.encoder.layers.17.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
549
+ "model.vision_model.encoder.layers.17.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
550
+ "model.vision_model.encoder.layers.18.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
551
+ "model.vision_model.encoder.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
552
+ "model.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
553
+ "model.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
554
+ "model.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
555
+ "model.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
556
+ "model.vision_model.encoder.layers.18.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
557
+ "model.vision_model.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
558
+ "model.vision_model.encoder.layers.18.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
559
+ "model.vision_model.encoder.layers.18.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
560
+ "model.vision_model.encoder.layers.18.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
561
+ "model.vision_model.encoder.layers.18.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
562
+ "model.vision_model.encoder.layers.19.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
563
+ "model.vision_model.encoder.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
564
+ "model.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
565
+ "model.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
566
+ "model.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
567
+ "model.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
568
+ "model.vision_model.encoder.layers.19.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
569
+ "model.vision_model.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
570
+ "model.vision_model.encoder.layers.19.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
571
+ "model.vision_model.encoder.layers.19.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
572
+ "model.vision_model.encoder.layers.19.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
573
+ "model.vision_model.encoder.layers.19.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
574
+ "model.vision_model.encoder.layers.2.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
575
+ "model.vision_model.encoder.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
576
+ "model.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
577
+ "model.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
578
+ "model.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
579
+ "model.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
580
+ "model.vision_model.encoder.layers.2.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
581
+ "model.vision_model.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
582
+ "model.vision_model.encoder.layers.2.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
583
+ "model.vision_model.encoder.layers.2.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
584
+ "model.vision_model.encoder.layers.2.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
585
+ "model.vision_model.encoder.layers.2.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
586
+ "model.vision_model.encoder.layers.20.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
587
+ "model.vision_model.encoder.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
588
+ "model.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
589
+ "model.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
590
+ "model.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
591
+ "model.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
592
+ "model.vision_model.encoder.layers.20.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
593
+ "model.vision_model.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
594
+ "model.vision_model.encoder.layers.20.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
595
+ "model.vision_model.encoder.layers.20.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
596
+ "model.vision_model.encoder.layers.20.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
597
+ "model.vision_model.encoder.layers.20.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
598
+ "model.vision_model.encoder.layers.21.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
599
+ "model.vision_model.encoder.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
600
+ "model.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
601
+ "model.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
602
+ "model.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
603
+ "model.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
604
+ "model.vision_model.encoder.layers.21.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
605
+ "model.vision_model.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
606
+ "model.vision_model.encoder.layers.21.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
607
+ "model.vision_model.encoder.layers.21.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
608
+ "model.vision_model.encoder.layers.21.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
609
+ "model.vision_model.encoder.layers.21.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
610
+ "model.vision_model.encoder.layers.22.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
611
+ "model.vision_model.encoder.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
612
+ "model.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
613
+ "model.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
614
+ "model.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
615
+ "model.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
616
+ "model.vision_model.encoder.layers.22.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
617
+ "model.vision_model.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
618
+ "model.vision_model.encoder.layers.22.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
619
+ "model.vision_model.encoder.layers.22.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
620
+ "model.vision_model.encoder.layers.22.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
621
+ "model.vision_model.encoder.layers.22.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
622
+ "model.vision_model.encoder.layers.23.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
623
+ "model.vision_model.encoder.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
624
+ "model.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
625
+ "model.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
626
+ "model.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
627
+ "model.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
628
+ "model.vision_model.encoder.layers.23.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
629
+ "model.vision_model.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
630
+ "model.vision_model.encoder.layers.23.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
631
+ "model.vision_model.encoder.layers.23.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
632
+ "model.vision_model.encoder.layers.23.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
633
+ "model.vision_model.encoder.layers.23.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
634
+ "model.vision_model.encoder.layers.3.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
635
+ "model.vision_model.encoder.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
636
+ "model.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
637
+ "model.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
638
+ "model.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
639
+ "model.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
640
+ "model.vision_model.encoder.layers.3.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
641
+ "model.vision_model.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
642
+ "model.vision_model.encoder.layers.3.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
643
+ "model.vision_model.encoder.layers.3.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
644
+ "model.vision_model.encoder.layers.3.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
645
+ "model.vision_model.encoder.layers.3.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
646
+ "model.vision_model.encoder.layers.4.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
647
+ "model.vision_model.encoder.layers.4.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
648
+ "model.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
649
+ "model.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
650
+ "model.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
651
+ "model.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
652
+ "model.vision_model.encoder.layers.4.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
653
+ "model.vision_model.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
654
+ "model.vision_model.encoder.layers.4.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
655
+ "model.vision_model.encoder.layers.4.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
656
+ "model.vision_model.encoder.layers.4.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
657
+ "model.vision_model.encoder.layers.4.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
658
+ "model.vision_model.encoder.layers.5.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
659
+ "model.vision_model.encoder.layers.5.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
660
+ "model.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
661
+ "model.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
662
+ "model.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
663
+ "model.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
664
+ "model.vision_model.encoder.layers.5.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
665
+ "model.vision_model.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
666
+ "model.vision_model.encoder.layers.5.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
667
+ "model.vision_model.encoder.layers.5.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
668
+ "model.vision_model.encoder.layers.5.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
669
+ "model.vision_model.encoder.layers.5.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
670
+ "model.vision_model.encoder.layers.6.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
671
+ "model.vision_model.encoder.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
672
+ "model.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
673
+ "model.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
674
+ "model.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
675
+ "model.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
676
+ "model.vision_model.encoder.layers.6.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
677
+ "model.vision_model.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
678
+ "model.vision_model.encoder.layers.6.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
679
+ "model.vision_model.encoder.layers.6.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
680
+ "model.vision_model.encoder.layers.6.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
681
+ "model.vision_model.encoder.layers.6.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
682
+ "model.vision_model.encoder.layers.7.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
683
+ "model.vision_model.encoder.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
684
+ "model.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
685
+ "model.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
686
+ "model.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
687
+ "model.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
688
+ "model.vision_model.encoder.layers.7.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
689
+ "model.vision_model.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
690
+ "model.vision_model.encoder.layers.7.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
691
+ "model.vision_model.encoder.layers.7.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
692
+ "model.vision_model.encoder.layers.7.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
693
+ "model.vision_model.encoder.layers.7.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
694
+ "model.vision_model.encoder.layers.8.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
695
+ "model.vision_model.encoder.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
696
+ "model.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
697
+ "model.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
698
+ "model.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
699
+ "model.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
700
+ "model.vision_model.encoder.layers.8.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
701
+ "model.vision_model.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
702
+ "model.vision_model.encoder.layers.8.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
703
+ "model.vision_model.encoder.layers.8.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
704
+ "model.vision_model.encoder.layers.8.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
705
+ "model.vision_model.encoder.layers.8.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
706
+ "model.vision_model.encoder.layers.9.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
707
+ "model.vision_model.encoder.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
708
+ "model.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
709
+ "model.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
710
+ "model.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
711
+ "model.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
712
+ "model.vision_model.encoder.layers.9.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
713
+ "model.vision_model.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
714
+ "model.vision_model.encoder.layers.9.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
715
+ "model.vision_model.encoder.layers.9.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
716
+ "model.vision_model.encoder.layers.9.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
717
+ "model.vision_model.encoder.layers.9.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
718
+ "model.vision_model.post_layernorm.bias": "pytorch_model-00004-of-00004.bin",
719
+ "model.vision_model.post_layernorm.weight": "pytorch_model-00004-of-00004.bin",
720
+ "model.visual_abstractor.encoder.layers.0.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
721
+ "model.visual_abstractor.encoder.layers.0.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
722
+ "model.visual_abstractor.encoder.layers.0.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
723
+ "model.visual_abstractor.encoder.layers.0.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
724
+ "model.visual_abstractor.encoder.layers.0.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
725
+ "model.visual_abstractor.encoder.layers.0.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
726
+ "model.visual_abstractor.encoder.layers.0.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
727
+ "model.visual_abstractor.encoder.layers.0.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
728
+ "model.visual_abstractor.encoder.layers.0.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
729
+ "model.visual_abstractor.encoder.layers.0.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
730
+ "model.visual_abstractor.encoder.layers.0.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
731
+ "model.visual_abstractor.encoder.layers.0.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
732
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
733
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
734
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
735
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
736
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
737
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
738
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
739
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
740
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
741
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
742
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
743
+ "model.visual_abstractor.encoder.layers.0.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
744
+ "model.visual_abstractor.encoder.layers.1.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
745
+ "model.visual_abstractor.encoder.layers.1.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
746
+ "model.visual_abstractor.encoder.layers.1.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
747
+ "model.visual_abstractor.encoder.layers.1.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
748
+ "model.visual_abstractor.encoder.layers.1.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
749
+ "model.visual_abstractor.encoder.layers.1.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
750
+ "model.visual_abstractor.encoder.layers.1.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
751
+ "model.visual_abstractor.encoder.layers.1.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
752
+ "model.visual_abstractor.encoder.layers.1.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
753
+ "model.visual_abstractor.encoder.layers.1.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
754
+ "model.visual_abstractor.encoder.layers.1.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
755
+ "model.visual_abstractor.encoder.layers.1.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
756
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
757
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
758
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
759
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
760
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
761
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
762
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
763
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
764
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
765
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
766
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
767
+ "model.visual_abstractor.encoder.layers.1.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
768
+ "model.visual_abstractor.encoder.layers.2.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
769
+ "model.visual_abstractor.encoder.layers.2.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
770
+ "model.visual_abstractor.encoder.layers.2.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
771
+ "model.visual_abstractor.encoder.layers.2.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
772
+ "model.visual_abstractor.encoder.layers.2.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
773
+ "model.visual_abstractor.encoder.layers.2.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
774
+ "model.visual_abstractor.encoder.layers.2.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
775
+ "model.visual_abstractor.encoder.layers.2.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
776
+ "model.visual_abstractor.encoder.layers.2.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
777
+ "model.visual_abstractor.encoder.layers.2.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
778
+ "model.visual_abstractor.encoder.layers.2.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
779
+ "model.visual_abstractor.encoder.layers.2.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
780
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
781
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
782
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
783
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
784
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
785
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
786
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
787
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
788
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
789
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
790
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
791
+ "model.visual_abstractor.encoder.layers.2.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
792
+ "model.visual_abstractor.encoder.layers.3.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
793
+ "model.visual_abstractor.encoder.layers.3.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
794
+ "model.visual_abstractor.encoder.layers.3.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
795
+ "model.visual_abstractor.encoder.layers.3.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
796
+ "model.visual_abstractor.encoder.layers.3.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
797
+ "model.visual_abstractor.encoder.layers.3.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
798
+ "model.visual_abstractor.encoder.layers.3.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
799
+ "model.visual_abstractor.encoder.layers.3.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
800
+ "model.visual_abstractor.encoder.layers.3.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
801
+ "model.visual_abstractor.encoder.layers.3.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
802
+ "model.visual_abstractor.encoder.layers.3.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
803
+ "model.visual_abstractor.encoder.layers.3.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
804
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
805
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
806
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
807
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
808
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
809
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
810
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
811
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
812
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
813
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
814
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
815
+ "model.visual_abstractor.encoder.layers.3.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
816
+ "model.visual_abstractor.encoder.layers.4.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
817
+ "model.visual_abstractor.encoder.layers.4.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
818
+ "model.visual_abstractor.encoder.layers.4.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
819
+ "model.visual_abstractor.encoder.layers.4.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
820
+ "model.visual_abstractor.encoder.layers.4.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
821
+ "model.visual_abstractor.encoder.layers.4.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
822
+ "model.visual_abstractor.encoder.layers.4.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
823
+ "model.visual_abstractor.encoder.layers.4.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
824
+ "model.visual_abstractor.encoder.layers.4.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
825
+ "model.visual_abstractor.encoder.layers.4.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
826
+ "model.visual_abstractor.encoder.layers.4.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
827
+ "model.visual_abstractor.encoder.layers.4.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
828
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
829
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
830
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
831
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
832
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
833
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
834
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
835
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
836
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
837
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
838
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
839
+ "model.visual_abstractor.encoder.layers.4.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
840
+ "model.visual_abstractor.encoder.layers.5.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
841
+ "model.visual_abstractor.encoder.layers.5.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
842
+ "model.visual_abstractor.encoder.layers.5.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
843
+ "model.visual_abstractor.encoder.layers.5.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
844
+ "model.visual_abstractor.encoder.layers.5.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
845
+ "model.visual_abstractor.encoder.layers.5.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
846
+ "model.visual_abstractor.encoder.layers.5.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
847
+ "model.visual_abstractor.encoder.layers.5.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
848
+ "model.visual_abstractor.encoder.layers.5.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
849
+ "model.visual_abstractor.encoder.layers.5.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
850
+ "model.visual_abstractor.encoder.layers.5.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
851
+ "model.visual_abstractor.encoder.layers.5.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
852
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
853
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
854
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
855
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
856
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
857
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
858
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
859
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
860
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
861
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
862
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
863
+ "model.visual_abstractor.encoder.layers.5.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
864
+ "model.visual_abstractor.query_embeds": "pytorch_model-00004-of-00004.bin",
865
+ "model.visual_abstractor.visual_fc.bias": "pytorch_model-00004-of-00004.bin",
866
+ "model.visual_abstractor.visual_fc.weight": "pytorch_model-00004-of-00004.bin",
867
+ "model.visual_abstractor.vit_eos": "pytorch_model-00004-of-00004.bin"
868
+ }
869
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 2048,
35
+ "pad_token": "<unk>",
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
trainer_state.json ADDED
@@ -0,0 +1,4230 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 700,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 9.523809523809525e-07,
14
+ "loss": 0.9682,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 1.904761904761905e-06,
20
+ "loss": 1.0391,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 2.8571428571428573e-06,
26
+ "loss": 1.0184,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 3.80952380952381e-06,
32
+ "loss": 0.9074,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 4.761904761904762e-06,
38
+ "loss": 0.7204,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.02,
43
+ "learning_rate": 5.7142857142857145e-06,
44
+ "loss": 0.3424,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "learning_rate": 6.666666666666667e-06,
50
+ "loss": 0.2966,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.02,
55
+ "learning_rate": 7.61904761904762e-06,
56
+ "loss": 0.2079,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.03,
61
+ "learning_rate": 8.571428571428571e-06,
62
+ "loss": 0.1443,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.03,
67
+ "learning_rate": 9.523809523809525e-06,
68
+ "loss": 0.1984,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.03,
73
+ "learning_rate": 1.0476190476190477e-05,
74
+ "loss": 0.2289,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.03,
79
+ "learning_rate": 1.1428571428571429e-05,
80
+ "loss": 0.1791,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.04,
85
+ "learning_rate": 1.2380952380952383e-05,
86
+ "loss": 0.1422,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.04,
91
+ "learning_rate": 1.3333333333333333e-05,
92
+ "loss": 0.1695,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.04,
97
+ "learning_rate": 1.4285714285714287e-05,
98
+ "loss": 0.1504,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.05,
103
+ "learning_rate": 1.523809523809524e-05,
104
+ "loss": 0.1498,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.05,
109
+ "learning_rate": 1.6190476190476193e-05,
110
+ "loss": 0.1533,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.05,
115
+ "learning_rate": 1.7142857142857142e-05,
116
+ "loss": 0.1885,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.05,
121
+ "learning_rate": 1.8095238095238097e-05,
122
+ "loss": 0.1423,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.06,
127
+ "learning_rate": 1.904761904761905e-05,
128
+ "loss": 0.1335,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.06,
133
+ "learning_rate": 2e-05,
134
+ "loss": 0.1319,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.06,
139
+ "learning_rate": 1.9999892964109543e-05,
140
+ "loss": 0.1405,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.07,
145
+ "learning_rate": 1.999957185872951e-05,
146
+ "loss": 0.1292,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.07,
151
+ "learning_rate": 1.9999036690733865e-05,
152
+ "loss": 0.1346,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.07,
157
+ "learning_rate": 1.9998287471579036e-05,
158
+ "loss": 0.1221,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.07,
163
+ "learning_rate": 1.99973242173037e-05,
164
+ "loss": 0.1244,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.08,
169
+ "learning_rate": 1.99961469485284e-05,
170
+ "loss": 0.1248,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.08,
175
+ "learning_rate": 1.9994755690455154e-05,
176
+ "loss": 0.1207,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.08,
181
+ "learning_rate": 1.9993150472866856e-05,
182
+ "loss": 0.1265,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.09,
187
+ "learning_rate": 1.9991331330126698e-05,
188
+ "loss": 0.1241,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.09,
193
+ "learning_rate": 1.9989298301177387e-05,
194
+ "loss": 0.123,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.09,
199
+ "learning_rate": 1.9987051429540335e-05,
200
+ "loss": 0.12,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.09,
205
+ "learning_rate": 1.9984590763314722e-05,
206
+ "loss": 0.1177,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.1,
211
+ "learning_rate": 1.9981916355176473e-05,
212
+ "loss": 0.12,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.1,
217
+ "learning_rate": 1.997902826237712e-05,
218
+ "loss": 0.1248,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.1,
223
+ "learning_rate": 1.9975926546742573e-05,
224
+ "loss": 0.1171,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.11,
229
+ "learning_rate": 1.9972611274671815e-05,
230
+ "loss": 0.1167,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.11,
235
+ "learning_rate": 1.9969082517135463e-05,
236
+ "loss": 0.1177,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.11,
241
+ "learning_rate": 1.9965340349674262e-05,
242
+ "loss": 0.12,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.11,
247
+ "learning_rate": 1.9961384852397456e-05,
248
+ "loss": 0.1212,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.12,
253
+ "learning_rate": 1.995721610998108e-05,
254
+ "loss": 0.1179,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.12,
259
+ "learning_rate": 1.995283421166614e-05,
260
+ "loss": 0.1165,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.12,
265
+ "learning_rate": 1.994823925125672e-05,
266
+ "loss": 0.113,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.13,
271
+ "learning_rate": 1.9943431327117955e-05,
272
+ "loss": 0.1194,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.13,
277
+ "learning_rate": 1.9938410542173937e-05,
278
+ "loss": 0.114,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.13,
283
+ "learning_rate": 1.9933177003905494e-05,
284
+ "loss": 0.119,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.13,
289
+ "learning_rate": 1.9927730824347915e-05,
290
+ "loss": 0.1158,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.14,
295
+ "learning_rate": 1.9922072120088537e-05,
296
+ "loss": 0.1151,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.14,
301
+ "learning_rate": 1.9916201012264255e-05,
302
+ "loss": 0.1182,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.14,
307
+ "learning_rate": 1.9910117626558908e-05,
308
+ "loss": 0.1149,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.15,
313
+ "learning_rate": 1.9903822093200625e-05,
314
+ "loss": 0.1166,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.15,
319
+ "learning_rate": 1.9897314546959015e-05,
320
+ "loss": 0.1158,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.15,
325
+ "learning_rate": 1.989059512714227e-05,
326
+ "loss": 0.1171,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.15,
331
+ "learning_rate": 1.988366397759421e-05,
332
+ "loss": 0.1168,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.16,
337
+ "learning_rate": 1.9876521246691183e-05,
338
+ "loss": 0.1139,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.16,
343
+ "learning_rate": 1.9869167087338908e-05,
344
+ "loss": 0.1164,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.16,
349
+ "learning_rate": 1.9861601656969185e-05,
350
+ "loss": 0.1141,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.17,
355
+ "learning_rate": 1.9853825117536522e-05,
356
+ "loss": 0.114,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.17,
361
+ "learning_rate": 1.9845837635514692e-05,
362
+ "loss": 0.1151,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.17,
367
+ "learning_rate": 1.9837639381893137e-05,
368
+ "loss": 0.1164,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.17,
373
+ "learning_rate": 1.9829230532173337e-05,
374
+ "loss": 0.1125,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.18,
379
+ "learning_rate": 1.9820611266365036e-05,
380
+ "loss": 0.1128,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.18,
385
+ "learning_rate": 1.9811781768982392e-05,
386
+ "loss": 0.1156,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.18,
391
+ "learning_rate": 1.9802742229040027e-05,
392
+ "loss": 0.1144,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.19,
397
+ "learning_rate": 1.979349284004898e-05,
398
+ "loss": 0.1161,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.19,
403
+ "learning_rate": 1.978403380001257e-05,
404
+ "loss": 0.1154,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.19,
409
+ "learning_rate": 1.9774365311422155e-05,
410
+ "loss": 0.1111,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.19,
415
+ "learning_rate": 1.9764487581252787e-05,
416
+ "loss": 0.1173,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.2,
421
+ "learning_rate": 1.9754400820958798e-05,
422
+ "loss": 0.1142,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.2,
427
+ "learning_rate": 1.9744105246469264e-05,
428
+ "loss": 0.1145,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.2,
433
+ "learning_rate": 1.9733601078183377e-05,
434
+ "loss": 0.1149,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.21,
439
+ "learning_rate": 1.9722888540965738e-05,
440
+ "loss": 0.1142,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.21,
445
+ "learning_rate": 1.9711967864141542e-05,
446
+ "loss": 0.1135,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.21,
451
+ "learning_rate": 1.970083928149166e-05,
452
+ "loss": 0.1149,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.21,
457
+ "learning_rate": 1.968950303124765e-05,
458
+ "loss": 0.1093,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.22,
463
+ "learning_rate": 1.967795935608663e-05,
464
+ "loss": 0.1142,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.22,
469
+ "learning_rate": 1.9666208503126115e-05,
470
+ "loss": 0.1141,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.22,
475
+ "learning_rate": 1.9654250723918706e-05,
476
+ "loss": 0.1118,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.23,
481
+ "learning_rate": 1.9642086274446713e-05,
482
+ "loss": 0.1121,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.23,
487
+ "learning_rate": 1.962971541511667e-05,
488
+ "loss": 0.1136,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.23,
493
+ "learning_rate": 1.961713841075377e-05,
494
+ "loss": 0.1182,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.23,
499
+ "learning_rate": 1.9604355530596182e-05,
500
+ "loss": 0.1138,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.24,
505
+ "learning_rate": 1.9591367048289297e-05,
506
+ "loss": 0.114,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.24,
511
+ "learning_rate": 1.957817324187987e-05,
512
+ "loss": 0.1149,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.24,
517
+ "learning_rate": 1.9564774393810068e-05,
518
+ "loss": 0.1121,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.25,
523
+ "learning_rate": 1.9551170790911415e-05,
524
+ "loss": 0.1152,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.25,
529
+ "learning_rate": 1.953736272439866e-05,
530
+ "loss": 0.1113,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.25,
535
+ "learning_rate": 1.9523350489863545e-05,
536
+ "loss": 0.1092,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.25,
541
+ "learning_rate": 1.9509134387268463e-05,
542
+ "loss": 0.1131,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.26,
547
+ "learning_rate": 1.9494714720940065e-05,
548
+ "loss": 0.1138,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.26,
553
+ "learning_rate": 1.9480091799562706e-05,
554
+ "loss": 0.1169,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.26,
559
+ "learning_rate": 1.9465265936171875e-05,
560
+ "loss": 0.1173,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.27,
565
+ "learning_rate": 1.9450237448147463e-05,
566
+ "loss": 0.1154,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.27,
571
+ "learning_rate": 1.9435006657206998e-05,
572
+ "loss": 0.1151,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.27,
577
+ "learning_rate": 1.941957388939873e-05,
578
+ "loss": 0.1166,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.27,
583
+ "learning_rate": 1.9403939475094664e-05,
584
+ "loss": 0.1153,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.28,
589
+ "learning_rate": 1.9388103748983496e-05,
590
+ "loss": 0.1157,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.28,
595
+ "learning_rate": 1.937206705006344e-05,
596
+ "loss": 0.1134,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.28,
601
+ "learning_rate": 1.9355829721634952e-05,
602
+ "loss": 0.112,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.29,
607
+ "learning_rate": 1.9339392111293425e-05,
608
+ "loss": 0.1107,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.29,
613
+ "learning_rate": 1.9322754570921713e-05,
614
+ "loss": 0.1134,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.29,
619
+ "learning_rate": 1.930591745668259e-05,
620
+ "loss": 0.108,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.29,
625
+ "learning_rate": 1.9288881129011177e-05,
626
+ "loss": 0.1107,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.3,
631
+ "learning_rate": 1.9271645952607164e-05,
632
+ "loss": 0.1059,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.3,
637
+ "learning_rate": 1.9254212296427043e-05,
638
+ "loss": 0.1062,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.3,
643
+ "learning_rate": 1.92365805336762e-05,
644
+ "loss": 0.1045,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.31,
649
+ "learning_rate": 1.921875104180092e-05,
650
+ "loss": 0.1073,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.31,
655
+ "learning_rate": 1.9200724202480305e-05,
656
+ "loss": 0.1071,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.31,
661
+ "learning_rate": 1.9182500401618122e-05,
662
+ "loss": 0.111,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.31,
667
+ "learning_rate": 1.9164080029334517e-05,
668
+ "loss": 0.1053,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.32,
673
+ "learning_rate": 1.914546347995768e-05,
674
+ "loss": 0.1068,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.32,
679
+ "learning_rate": 1.9126651152015404e-05,
680
+ "loss": 0.1051,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.32,
685
+ "learning_rate": 1.9107643448226536e-05,
686
+ "loss": 0.1014,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.33,
691
+ "learning_rate": 1.9088440775492386e-05,
692
+ "loss": 0.0971,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.33,
697
+ "learning_rate": 1.9069043544887978e-05,
698
+ "loss": 0.1099,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.33,
703
+ "learning_rate": 1.904945217165329e-05,
704
+ "loss": 0.1003,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.33,
709
+ "learning_rate": 1.9029667075184333e-05,
710
+ "loss": 0.1041,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.34,
715
+ "learning_rate": 1.900968867902419e-05,
716
+ "loss": 0.1097,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.34,
721
+ "learning_rate": 1.8989517410853956e-05,
722
+ "loss": 0.1041,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.34,
727
+ "learning_rate": 1.896915370248355e-05,
728
+ "loss": 0.0966,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.35,
733
+ "learning_rate": 1.8948597989842504e-05,
734
+ "loss": 0.1023,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.35,
739
+ "learning_rate": 1.8927850712970626e-05,
740
+ "loss": 0.1037,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.35,
745
+ "learning_rate": 1.890691231600856e-05,
746
+ "loss": 0.1021,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.35,
751
+ "learning_rate": 1.8885783247188305e-05,
752
+ "loss": 0.1063,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.36,
757
+ "learning_rate": 1.8864463958823598e-05,
758
+ "loss": 0.1032,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.36,
763
+ "learning_rate": 1.8842954907300236e-05,
764
+ "loss": 0.0982,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.36,
769
+ "learning_rate": 1.8821256553066326e-05,
770
+ "loss": 0.103,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.37,
775
+ "learning_rate": 1.8799369360622394e-05,
776
+ "loss": 0.0964,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.37,
781
+ "learning_rate": 1.8777293798511466e-05,
782
+ "loss": 0.1024,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.37,
787
+ "learning_rate": 1.8755030339309037e-05,
788
+ "loss": 0.1063,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.37,
793
+ "learning_rate": 1.8732579459612935e-05,
794
+ "loss": 0.0967,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.38,
799
+ "learning_rate": 1.8709941640033153e-05,
800
+ "loss": 0.0943,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.38,
805
+ "learning_rate": 1.8687117365181514e-05,
806
+ "loss": 0.0932,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.38,
811
+ "learning_rate": 1.8664107123661337e-05,
812
+ "loss": 0.0993,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.39,
817
+ "learning_rate": 1.8640911408056963e-05,
818
+ "loss": 0.0995,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.39,
823
+ "learning_rate": 1.861753071492321e-05,
824
+ "loss": 0.0981,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.39,
829
+ "learning_rate": 1.859396554477473e-05,
830
+ "loss": 0.1041,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.39,
835
+ "learning_rate": 1.8570216402075326e-05,
836
+ "loss": 0.0976,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.4,
841
+ "learning_rate": 1.854628379522712e-05,
842
+ "loss": 0.0956,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.4,
847
+ "learning_rate": 1.8522168236559693e-05,
848
+ "loss": 0.0985,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.4,
853
+ "learning_rate": 1.8497870242319103e-05,
854
+ "loss": 0.0995,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.41,
859
+ "learning_rate": 1.847339033265684e-05,
860
+ "loss": 0.1016,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.41,
865
+ "learning_rate": 1.8448729031618687e-05,
866
+ "loss": 0.0901,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.41,
871
+ "learning_rate": 1.842388686713351e-05,
872
+ "loss": 0.0951,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.41,
877
+ "learning_rate": 1.8398864371001945e-05,
878
+ "loss": 0.1018,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.42,
883
+ "learning_rate": 1.8373662078885028e-05,
884
+ "loss": 0.0982,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.42,
889
+ "learning_rate": 1.8348280530292712e-05,
890
+ "loss": 0.0956,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.42,
895
+ "learning_rate": 1.8322720268572333e-05,
896
+ "loss": 0.0992,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.43,
901
+ "learning_rate": 1.829698184089695e-05,
902
+ "loss": 0.086,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.43,
907
+ "learning_rate": 1.8271065798253688e-05,
908
+ "loss": 0.103,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.43,
913
+ "learning_rate": 1.8244972695431874e-05,
914
+ "loss": 0.0894,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.43,
919
+ "learning_rate": 1.8218703091011214e-05,
920
+ "loss": 0.0954,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.44,
925
+ "learning_rate": 1.8192257547349805e-05,
926
+ "loss": 0.1016,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.44,
931
+ "learning_rate": 1.816563663057211e-05,
932
+ "loss": 0.1004,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.44,
937
+ "learning_rate": 1.8138840910556836e-05,
938
+ "loss": 0.102,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.45,
943
+ "learning_rate": 1.8111870960924733e-05,
944
+ "loss": 0.0996,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.45,
949
+ "learning_rate": 1.8084727359026316e-05,
950
+ "loss": 0.092,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.45,
955
+ "learning_rate": 1.8057410685929505e-05,
956
+ "loss": 0.0948,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.45,
961
+ "learning_rate": 1.8029921526407184e-05,
962
+ "loss": 0.0914,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.46,
967
+ "learning_rate": 1.8002260468924696e-05,
968
+ "loss": 0.0905,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.46,
973
+ "learning_rate": 1.797442810562721e-05,
974
+ "loss": 0.0962,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.46,
979
+ "learning_rate": 1.794642503232709e-05,
980
+ "loss": 0.1,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.47,
985
+ "learning_rate": 1.7918251848491118e-05,
986
+ "loss": 0.0966,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.47,
991
+ "learning_rate": 1.7889909157227652e-05,
992
+ "loss": 0.1106,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.47,
997
+ "learning_rate": 1.7861397565273736e-05,
998
+ "loss": 0.1,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.47,
1003
+ "learning_rate": 1.7832717682982092e-05,
1004
+ "loss": 0.0976,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.48,
1009
+ "learning_rate": 1.780387012430807e-05,
1010
+ "loss": 0.0976,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.48,
1015
+ "learning_rate": 1.7774855506796497e-05,
1016
+ "loss": 0.0995,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.48,
1021
+ "learning_rate": 1.7745674451568454e-05,
1022
+ "loss": 0.1011,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.49,
1027
+ "learning_rate": 1.7716327583307988e-05,
1028
+ "loss": 0.1059,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.49,
1033
+ "learning_rate": 1.768681553024874e-05,
1034
+ "loss": 0.0956,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.49,
1039
+ "learning_rate": 1.765713892416048e-05,
1040
+ "loss": 0.0935,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.49,
1045
+ "learning_rate": 1.76272984003356e-05,
1046
+ "loss": 0.1022,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.5,
1051
+ "learning_rate": 1.759729459757551e-05,
1052
+ "loss": 0.0948,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.5,
1057
+ "learning_rate": 1.7567128158176955e-05,
1058
+ "loss": 0.0965,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.5,
1063
+ "learning_rate": 1.753679972791828e-05,
1064
+ "loss": 0.0905,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.51,
1069
+ "learning_rate": 1.750630995604559e-05,
1070
+ "loss": 0.0964,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.51,
1075
+ "learning_rate": 1.7475659495258864e-05,
1076
+ "loss": 0.0999,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.51,
1081
+ "learning_rate": 1.7444849001697976e-05,
1082
+ "loss": 0.091,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.51,
1087
+ "learning_rate": 1.7413879134928644e-05,
1088
+ "loss": 0.097,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.52,
1093
+ "learning_rate": 1.7382750557928323e-05,
1094
+ "loss": 0.0955,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.52,
1099
+ "learning_rate": 1.7351463937072008e-05,
1100
+ "loss": 0.099,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.52,
1105
+ "learning_rate": 1.7320019942117954e-05,
1106
+ "loss": 0.0943,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.53,
1111
+ "learning_rate": 1.7288419246193373e-05,
1112
+ "loss": 0.0892,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.53,
1117
+ "learning_rate": 1.7256662525779984e-05,
1118
+ "loss": 0.0981,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.53,
1123
+ "learning_rate": 1.7224750460699558e-05,
1124
+ "loss": 0.0912,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.53,
1129
+ "learning_rate": 1.7192683734099355e-05,
1130
+ "loss": 0.0951,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.54,
1135
+ "learning_rate": 1.71604630324375e-05,
1136
+ "loss": 0.0908,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.54,
1141
+ "learning_rate": 1.7128089045468294e-05,
1142
+ "loss": 0.0934,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.54,
1147
+ "learning_rate": 1.709556246622744e-05,
1148
+ "loss": 0.0954,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.55,
1153
+ "learning_rate": 1.7062883991017217e-05,
1154
+ "loss": 0.0995,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.55,
1159
+ "learning_rate": 1.7030054319391563e-05,
1160
+ "loss": 0.1032,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.55,
1165
+ "learning_rate": 1.6997074154141097e-05,
1166
+ "loss": 0.0919,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.55,
1171
+ "learning_rate": 1.6963944201278097e-05,
1172
+ "loss": 0.0893,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.56,
1177
+ "learning_rate": 1.6930665170021364e-05,
1178
+ "loss": 0.0967,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.56,
1183
+ "learning_rate": 1.6897237772781046e-05,
1184
+ "loss": 0.0876,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.56,
1189
+ "learning_rate": 1.6863662725143383e-05,
1190
+ "loss": 0.0921,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.57,
1195
+ "learning_rate": 1.682994074585541e-05,
1196
+ "loss": 0.0921,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.57,
1201
+ "learning_rate": 1.6796072556809536e-05,
1202
+ "loss": 0.0877,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.57,
1207
+ "learning_rate": 1.676205888302812e-05,
1208
+ "loss": 0.093,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 0.57,
1213
+ "learning_rate": 1.6727900452647925e-05,
1214
+ "loss": 0.0902,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 0.58,
1219
+ "learning_rate": 1.6693597996904566e-05,
1220
+ "loss": 0.091,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 0.58,
1225
+ "learning_rate": 1.665915225011681e-05,
1226
+ "loss": 0.0903,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 0.58,
1231
+ "learning_rate": 1.6624563949670903e-05,
1232
+ "loss": 0.0935,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 0.59,
1237
+ "learning_rate": 1.6589833836004753e-05,
1238
+ "loss": 0.0932,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 0.59,
1243
+ "learning_rate": 1.6554962652592078e-05,
1244
+ "loss": 0.0875,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 0.59,
1249
+ "learning_rate": 1.6519951145926515e-05,
1250
+ "loss": 0.0871,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 0.59,
1255
+ "learning_rate": 1.6484800065505627e-05,
1256
+ "loss": 0.1,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 0.6,
1261
+ "learning_rate": 1.6449510163814854e-05,
1262
+ "loss": 0.0986,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 0.6,
1267
+ "learning_rate": 1.6414082196311402e-05,
1268
+ "loss": 0.0872,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 0.6,
1273
+ "learning_rate": 1.6378516921408077e-05,
1274
+ "loss": 0.0942,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 0.61,
1279
+ "learning_rate": 1.6342815100457064e-05,
1280
+ "loss": 0.0948,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 0.61,
1285
+ "learning_rate": 1.630697749773359e-05,
1286
+ "loss": 0.0916,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 0.61,
1291
+ "learning_rate": 1.6271004880419606e-05,
1292
+ "loss": 0.095,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 0.61,
1297
+ "learning_rate": 1.6234898018587336e-05,
1298
+ "loss": 0.0866,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 0.62,
1303
+ "learning_rate": 1.61986576851828e-05,
1304
+ "loss": 0.0876,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 0.62,
1309
+ "learning_rate": 1.6162284656009276e-05,
1310
+ "loss": 0.0868,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 0.62,
1315
+ "learning_rate": 1.6125779709710668e-05,
1316
+ "loss": 0.0978,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 0.63,
1321
+ "learning_rate": 1.6089143627754863e-05,
1322
+ "loss": 0.0911,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 0.63,
1327
+ "learning_rate": 1.6052377194417e-05,
1328
+ "loss": 0.0874,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 0.63,
1333
+ "learning_rate": 1.6015481196762658e-05,
1334
+ "loss": 0.0825,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 0.63,
1339
+ "learning_rate": 1.5978456424631033e-05,
1340
+ "loss": 0.0928,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 0.64,
1345
+ "learning_rate": 1.5941303670618018e-05,
1346
+ "loss": 0.0883,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 0.64,
1351
+ "learning_rate": 1.5904023730059227e-05,
1352
+ "loss": 0.0889,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 0.64,
1357
+ "learning_rate": 1.5866617401012995e-05,
1358
+ "loss": 0.0997,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 0.65,
1363
+ "learning_rate": 1.5829085484243264e-05,
1364
+ "loss": 0.0845,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 0.65,
1369
+ "learning_rate": 1.5791428783202465e-05,
1370
+ "loss": 0.0892,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 0.65,
1375
+ "learning_rate": 1.57536481040143e-05,
1376
+ "loss": 0.0834,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 0.65,
1381
+ "learning_rate": 1.5715744255456497e-05,
1382
+ "loss": 0.0832,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 0.66,
1387
+ "learning_rate": 1.5677718048943495e-05,
1388
+ "loss": 0.0956,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 0.66,
1393
+ "learning_rate": 1.5639570298509067e-05,
1394
+ "loss": 0.0949,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 0.66,
1399
+ "learning_rate": 1.56013018207889e-05,
1400
+ "loss": 0.0834,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 0.67,
1405
+ "learning_rate": 1.5562913435003113e-05,
1406
+ "loss": 0.0838,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 0.67,
1411
+ "learning_rate": 1.5524405962938717e-05,
1412
+ "loss": 0.0905,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 0.67,
1417
+ "learning_rate": 1.548578022893202e-05,
1418
+ "loss": 0.0887,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 0.67,
1423
+ "learning_rate": 1.5447037059851e-05,
1424
+ "loss": 0.0868,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 0.68,
1429
+ "learning_rate": 1.5408177285077564e-05,
1430
+ "loss": 0.0899,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 0.68,
1435
+ "learning_rate": 1.536920173648984e-05,
1436
+ "loss": 0.0889,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 0.68,
1441
+ "learning_rate": 1.5330111248444332e-05,
1442
+ "loss": 0.0892,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 0.69,
1447
+ "learning_rate": 1.5290906657758085e-05,
1448
+ "loss": 0.1011,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 0.69,
1453
+ "learning_rate": 1.5251588803690753e-05,
1454
+ "loss": 0.0958,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 0.69,
1459
+ "learning_rate": 1.5212158527926635e-05,
1460
+ "loss": 0.0986,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 0.69,
1465
+ "learning_rate": 1.5172616674556673e-05,
1466
+ "loss": 0.0854,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 0.7,
1471
+ "learning_rate": 1.5132964090060358e-05,
1472
+ "loss": 0.0885,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 0.7,
1477
+ "learning_rate": 1.5093201623287631e-05,
1478
+ "loss": 0.0933,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 0.7,
1483
+ "learning_rate": 1.5053330125440701e-05,
1484
+ "loss": 0.1046,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 0.71,
1489
+ "learning_rate": 1.5013350450055821e-05,
1490
+ "loss": 0.0927,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 0.71,
1495
+ "learning_rate": 1.4973263452985023e-05,
1496
+ "loss": 0.0953,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 0.71,
1501
+ "learning_rate": 1.4933069992377793e-05,
1502
+ "loss": 0.0979,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 0.71,
1507
+ "learning_rate": 1.4892770928662699e-05,
1508
+ "loss": 0.0978,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 0.72,
1513
+ "learning_rate": 1.4852367124528975e-05,
1514
+ "loss": 0.0834,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 0.72,
1519
+ "learning_rate": 1.4811859444908053e-05,
1520
+ "loss": 0.1048,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 0.72,
1525
+ "learning_rate": 1.4771248756955042e-05,
1526
+ "loss": 0.0953,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 0.73,
1531
+ "learning_rate": 1.4730535930030172e-05,
1532
+ "loss": 0.0983,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 0.73,
1537
+ "learning_rate": 1.4689721835680183e-05,
1538
+ "loss": 0.0924,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 0.73,
1543
+ "learning_rate": 1.4648807347619662e-05,
1544
+ "loss": 0.0863,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 0.73,
1549
+ "learning_rate": 1.4607793341712336e-05,
1550
+ "loss": 0.0904,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 0.74,
1555
+ "learning_rate": 1.4566680695952333e-05,
1556
+ "loss": 0.0728,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 0.74,
1561
+ "learning_rate": 1.4525470290445392e-05,
1562
+ "loss": 0.0875,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 0.74,
1567
+ "learning_rate": 1.4484163007389991e-05,
1568
+ "loss": 0.0862,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 0.75,
1573
+ "learning_rate": 1.4442759731058502e-05,
1574
+ "loss": 0.0798,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 0.75,
1579
+ "learning_rate": 1.4401261347778235e-05,
1580
+ "loss": 0.0911,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 0.75,
1585
+ "learning_rate": 1.4359668745912472e-05,
1586
+ "loss": 0.0809,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 0.75,
1591
+ "learning_rate": 1.4317982815841442e-05,
1592
+ "loss": 0.0939,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 0.76,
1597
+ "learning_rate": 1.427620444994328e-05,
1598
+ "loss": 0.0809,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 0.76,
1603
+ "learning_rate": 1.4234334542574906e-05,
1604
+ "loss": 0.0831,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 0.76,
1609
+ "learning_rate": 1.4192373990052877e-05,
1610
+ "loss": 0.0867,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 0.77,
1615
+ "learning_rate": 1.415032369063422e-05,
1616
+ "loss": 0.0837,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 0.77,
1621
+ "learning_rate": 1.410818454449718e-05,
1622
+ "loss": 0.0868,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 0.77,
1627
+ "learning_rate": 1.4065957453721963e-05,
1628
+ "loss": 0.0901,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 0.77,
1633
+ "learning_rate": 1.4023643322271425e-05,
1634
+ "loss": 0.0928,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 0.78,
1639
+ "learning_rate": 1.3981243055971712e-05,
1640
+ "loss": 0.0876,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 0.78,
1645
+ "learning_rate": 1.3938757562492873e-05,
1646
+ "loss": 0.0864,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 0.78,
1651
+ "learning_rate": 1.3896187751329438e-05,
1652
+ "loss": 0.0827,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 0.79,
1657
+ "learning_rate": 1.3853534533780932e-05,
1658
+ "loss": 0.0784,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 0.79,
1663
+ "learning_rate": 1.381079882293238e-05,
1664
+ "loss": 0.0924,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 0.79,
1669
+ "learning_rate": 1.3767981533634755e-05,
1670
+ "loss": 0.094,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 0.79,
1675
+ "learning_rate": 1.3725083582485397e-05,
1676
+ "loss": 0.0956,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 0.8,
1681
+ "learning_rate": 1.368210588780838e-05,
1682
+ "loss": 0.0956,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 0.8,
1687
+ "learning_rate": 1.3639049369634878e-05,
1688
+ "loss": 0.0846,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 0.8,
1693
+ "learning_rate": 1.3595914949683433e-05,
1694
+ "loss": 0.0931,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 0.81,
1699
+ "learning_rate": 1.3552703551340259e-05,
1700
+ "loss": 0.0972,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 0.81,
1705
+ "learning_rate": 1.3509416099639456e-05,
1706
+ "loss": 0.0935,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 0.81,
1711
+ "learning_rate": 1.3466053521243214e-05,
1712
+ "loss": 0.0857,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 0.81,
1717
+ "learning_rate": 1.3422616744421966e-05,
1718
+ "loss": 0.0928,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 0.82,
1723
+ "learning_rate": 1.3379106699034536e-05,
1724
+ "loss": 0.09,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 0.82,
1729
+ "learning_rate": 1.3335524316508208e-05,
1730
+ "loss": 0.0892,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 0.82,
1735
+ "learning_rate": 1.3291870529818809e-05,
1736
+ "loss": 0.088,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 0.83,
1741
+ "learning_rate": 1.3248146273470725e-05,
1742
+ "loss": 0.0879,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 0.83,
1747
+ "learning_rate": 1.3204352483476898e-05,
1748
+ "loss": 0.0826,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 0.83,
1753
+ "learning_rate": 1.316049009733879e-05,
1754
+ "loss": 0.0882,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 0.83,
1759
+ "learning_rate": 1.311656005402631e-05,
1760
+ "loss": 0.0829,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 0.84,
1765
+ "learning_rate": 1.3072563293957725e-05,
1766
+ "loss": 0.0875,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 0.84,
1771
+ "learning_rate": 1.3028500758979507e-05,
1772
+ "loss": 0.0808,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 0.84,
1777
+ "learning_rate": 1.2984373392346195e-05,
1778
+ "loss": 0.0892,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 0.85,
1783
+ "learning_rate": 1.294018213870018e-05,
1784
+ "loss": 0.0827,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 0.85,
1789
+ "learning_rate": 1.2895927944051503e-05,
1790
+ "loss": 0.0873,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 0.85,
1795
+ "learning_rate": 1.2851611755757587e-05,
1796
+ "loss": 0.0991,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 0.85,
1801
+ "learning_rate": 1.280723452250297e-05,
1802
+ "loss": 0.0926,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 0.86,
1807
+ "learning_rate": 1.2762797194278984e-05,
1808
+ "loss": 0.0939,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 0.86,
1813
+ "learning_rate": 1.2718300722363431e-05,
1814
+ "loss": 0.0865,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 0.86,
1819
+ "learning_rate": 1.2673746059300209e-05,
1820
+ "loss": 0.0921,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 0.87,
1825
+ "learning_rate": 1.2629134158878919e-05,
1826
+ "loss": 0.0896,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 0.87,
1831
+ "learning_rate": 1.258446597611447e-05,
1832
+ "loss": 0.0846,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 0.87,
1837
+ "learning_rate": 1.25397424672266e-05,
1838
+ "loss": 0.0918,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 0.87,
1843
+ "learning_rate": 1.2494964589619424e-05,
1844
+ "loss": 0.0902,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 0.88,
1849
+ "learning_rate": 1.2450133301860951e-05,
1850
+ "loss": 0.0806,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 0.88,
1855
+ "learning_rate": 1.2405249563662539e-05,
1856
+ "loss": 0.0831,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 0.88,
1861
+ "learning_rate": 1.236031433585836e-05,
1862
+ "loss": 0.0902,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 0.89,
1867
+ "learning_rate": 1.2315328580384841e-05,
1868
+ "loss": 0.0878,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 0.89,
1873
+ "learning_rate": 1.2270293260260066e-05,
1874
+ "loss": 0.0897,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 0.89,
1879
+ "learning_rate": 1.2225209339563144e-05,
1880
+ "loss": 0.0905,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 0.89,
1885
+ "learning_rate": 1.2180077783413601e-05,
1886
+ "loss": 0.0864,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 0.9,
1891
+ "learning_rate": 1.21348995579507e-05,
1892
+ "loss": 0.0875,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 0.9,
1897
+ "learning_rate": 1.2089675630312755e-05,
1898
+ "loss": 0.0806,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 0.9,
1903
+ "learning_rate": 1.2044406968616433e-05,
1904
+ "loss": 0.0833,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 0.91,
1909
+ "learning_rate": 1.1999094541936047e-05,
1910
+ "loss": 0.0848,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 0.91,
1915
+ "learning_rate": 1.1953739320282778e-05,
1916
+ "loss": 0.0838,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 0.91,
1921
+ "learning_rate": 1.1908342274583937e-05,
1922
+ "loss": 0.0935,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 0.91,
1927
+ "learning_rate": 1.1862904376662167e-05,
1928
+ "loss": 0.0831,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 0.92,
1933
+ "learning_rate": 1.1817426599214637e-05,
1934
+ "loss": 0.0856,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 0.92,
1939
+ "learning_rate": 1.177190991579223e-05,
1940
+ "loss": 0.0855,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 0.92,
1945
+ "learning_rate": 1.1726355300778693e-05,
1946
+ "loss": 0.0809,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 0.93,
1951
+ "learning_rate": 1.1680763729369783e-05,
1952
+ "loss": 0.0893,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 0.93,
1957
+ "learning_rate": 1.163513617755239e-05,
1958
+ "loss": 0.0894,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 0.93,
1963
+ "learning_rate": 1.1589473622083642e-05,
1964
+ "loss": 0.0931,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 0.93,
1969
+ "learning_rate": 1.1543777040469994e-05,
1970
+ "loss": 0.0857,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 0.94,
1975
+ "learning_rate": 1.1498047410946307e-05,
1976
+ "loss": 0.0854,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 0.94,
1981
+ "learning_rate": 1.1452285712454905e-05,
1982
+ "loss": 0.0848,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 0.94,
1987
+ "learning_rate": 1.1406492924624614e-05,
1988
+ "loss": 0.0821,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 0.95,
1993
+ "learning_rate": 1.1360670027749806e-05,
1994
+ "loss": 0.0811,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 0.95,
1999
+ "learning_rate": 1.131481800276939e-05,
2000
+ "loss": 0.0857,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 0.95,
2005
+ "learning_rate": 1.126893783124583e-05,
2006
+ "loss": 0.0806,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 0.95,
2011
+ "learning_rate": 1.1223030495344127e-05,
2012
+ "loss": 0.0838,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 0.96,
2017
+ "learning_rate": 1.1177096977810803e-05,
2018
+ "loss": 0.0873,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 0.96,
2023
+ "learning_rate": 1.1131138261952845e-05,
2024
+ "loss": 0.0899,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 0.96,
2029
+ "learning_rate": 1.1085155331616664e-05,
2030
+ "loss": 0.0801,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 0.97,
2035
+ "learning_rate": 1.1039149171167046e-05,
2036
+ "loss": 0.0884,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 0.97,
2041
+ "learning_rate": 1.0993120765466056e-05,
2042
+ "loss": 0.0895,
2043
+ "step": 339
2044
+ },
2045
+ {
2046
+ "epoch": 0.97,
2047
+ "learning_rate": 1.0947071099851972e-05,
2048
+ "loss": 0.0878,
2049
+ "step": 340
2050
+ },
2051
+ {
2052
+ "epoch": 0.97,
2053
+ "learning_rate": 1.090100116011819e-05,
2054
+ "loss": 0.0887,
2055
+ "step": 341
2056
+ },
2057
+ {
2058
+ "epoch": 0.98,
2059
+ "learning_rate": 1.0854911932492114e-05,
2060
+ "loss": 0.081,
2061
+ "step": 342
2062
+ },
2063
+ {
2064
+ "epoch": 0.98,
2065
+ "learning_rate": 1.0808804403614044e-05,
2066
+ "loss": 0.0843,
2067
+ "step": 343
2068
+ },
2069
+ {
2070
+ "epoch": 0.98,
2071
+ "learning_rate": 1.0762679560516067e-05,
2072
+ "loss": 0.0887,
2073
+ "step": 344
2074
+ },
2075
+ {
2076
+ "epoch": 0.99,
2077
+ "learning_rate": 1.0716538390600908e-05,
2078
+ "loss": 0.0902,
2079
+ "step": 345
2080
+ },
2081
+ {
2082
+ "epoch": 0.99,
2083
+ "learning_rate": 1.0670381881620814e-05,
2084
+ "loss": 0.0718,
2085
+ "step": 346
2086
+ },
2087
+ {
2088
+ "epoch": 0.99,
2089
+ "learning_rate": 1.0624211021656392e-05,
2090
+ "loss": 0.082,
2091
+ "step": 347
2092
+ },
2093
+ {
2094
+ "epoch": 0.99,
2095
+ "learning_rate": 1.0578026799095464e-05,
2096
+ "loss": 0.0926,
2097
+ "step": 348
2098
+ },
2099
+ {
2100
+ "epoch": 1.0,
2101
+ "learning_rate": 1.0531830202611904e-05,
2102
+ "loss": 0.0852,
2103
+ "step": 349
2104
+ },
2105
+ {
2106
+ "epoch": 1.0,
2107
+ "learning_rate": 1.0485622221144485e-05,
2108
+ "loss": 0.0843,
2109
+ "step": 350
2110
+ },
2111
+ {
2112
+ "epoch": 1.0,
2113
+ "learning_rate": 1.043940384387569e-05,
2114
+ "loss": 0.0782,
2115
+ "step": 351
2116
+ },
2117
+ {
2118
+ "epoch": 1.01,
2119
+ "learning_rate": 1.0393176060210556e-05,
2120
+ "loss": 0.081,
2121
+ "step": 352
2122
+ },
2123
+ {
2124
+ "epoch": 1.01,
2125
+ "learning_rate": 1.0346939859755481e-05,
2126
+ "loss": 0.085,
2127
+ "step": 353
2128
+ },
2129
+ {
2130
+ "epoch": 1.01,
2131
+ "learning_rate": 1.0300696232297041e-05,
2132
+ "loss": 0.0797,
2133
+ "step": 354
2134
+ },
2135
+ {
2136
+ "epoch": 1.01,
2137
+ "learning_rate": 1.0254446167780803e-05,
2138
+ "loss": 0.0838,
2139
+ "step": 355
2140
+ },
2141
+ {
2142
+ "epoch": 1.02,
2143
+ "learning_rate": 1.0208190656290138e-05,
2144
+ "loss": 0.0845,
2145
+ "step": 356
2146
+ },
2147
+ {
2148
+ "epoch": 1.02,
2149
+ "learning_rate": 1.0161930688025018e-05,
2150
+ "loss": 0.0694,
2151
+ "step": 357
2152
+ },
2153
+ {
2154
+ "epoch": 1.02,
2155
+ "learning_rate": 1.0115667253280817e-05,
2156
+ "loss": 0.0822,
2157
+ "step": 358
2158
+ },
2159
+ {
2160
+ "epoch": 1.03,
2161
+ "learning_rate": 1.006940134242713e-05,
2162
+ "loss": 0.0697,
2163
+ "step": 359
2164
+ },
2165
+ {
2166
+ "epoch": 1.03,
2167
+ "learning_rate": 1.0023133945886545e-05,
2168
+ "loss": 0.0724,
2169
+ "step": 360
2170
+ },
2171
+ {
2172
+ "epoch": 1.03,
2173
+ "learning_rate": 9.976866054113458e-06,
2174
+ "loss": 0.0765,
2175
+ "step": 361
2176
+ },
2177
+ {
2178
+ "epoch": 1.03,
2179
+ "learning_rate": 9.930598657572874e-06,
2180
+ "loss": 0.0775,
2181
+ "step": 362
2182
+ },
2183
+ {
2184
+ "epoch": 1.04,
2185
+ "learning_rate": 9.884332746719186e-06,
2186
+ "loss": 0.079,
2187
+ "step": 363
2188
+ },
2189
+ {
2190
+ "epoch": 1.04,
2191
+ "learning_rate": 9.838069311974986e-06,
2192
+ "loss": 0.0897,
2193
+ "step": 364
2194
+ },
2195
+ {
2196
+ "epoch": 1.04,
2197
+ "learning_rate": 9.791809343709866e-06,
2198
+ "loss": 0.0909,
2199
+ "step": 365
2200
+ },
2201
+ {
2202
+ "epoch": 1.05,
2203
+ "learning_rate": 9.745553832219202e-06,
2204
+ "loss": 0.089,
2205
+ "step": 366
2206
+ },
2207
+ {
2208
+ "epoch": 1.05,
2209
+ "learning_rate": 9.699303767702964e-06,
2210
+ "loss": 0.0811,
2211
+ "step": 367
2212
+ },
2213
+ {
2214
+ "epoch": 1.05,
2215
+ "learning_rate": 9.653060140244524e-06,
2216
+ "loss": 0.0792,
2217
+ "step": 368
2218
+ },
2219
+ {
2220
+ "epoch": 1.05,
2221
+ "learning_rate": 9.606823939789449e-06,
2222
+ "loss": 0.0775,
2223
+ "step": 369
2224
+ },
2225
+ {
2226
+ "epoch": 1.06,
2227
+ "learning_rate": 9.560596156124314e-06,
2228
+ "loss": 0.0805,
2229
+ "step": 370
2230
+ },
2231
+ {
2232
+ "epoch": 1.06,
2233
+ "learning_rate": 9.514377778855521e-06,
2234
+ "loss": 0.0765,
2235
+ "step": 371
2236
+ },
2237
+ {
2238
+ "epoch": 1.06,
2239
+ "learning_rate": 9.468169797388098e-06,
2240
+ "loss": 0.0835,
2241
+ "step": 372
2242
+ },
2243
+ {
2244
+ "epoch": 1.07,
2245
+ "learning_rate": 9.421973200904538e-06,
2246
+ "loss": 0.0889,
2247
+ "step": 373
2248
+ },
2249
+ {
2250
+ "epoch": 1.07,
2251
+ "learning_rate": 9.375788978343608e-06,
2252
+ "loss": 0.0782,
2253
+ "step": 374
2254
+ },
2255
+ {
2256
+ "epoch": 1.07,
2257
+ "learning_rate": 9.329618118379187e-06,
2258
+ "loss": 0.084,
2259
+ "step": 375
2260
+ },
2261
+ {
2262
+ "epoch": 1.07,
2263
+ "learning_rate": 9.283461609399094e-06,
2264
+ "loss": 0.0843,
2265
+ "step": 376
2266
+ },
2267
+ {
2268
+ "epoch": 1.08,
2269
+ "learning_rate": 9.237320439483936e-06,
2270
+ "loss": 0.0841,
2271
+ "step": 377
2272
+ },
2273
+ {
2274
+ "epoch": 1.08,
2275
+ "learning_rate": 9.19119559638596e-06,
2276
+ "loss": 0.0868,
2277
+ "step": 378
2278
+ },
2279
+ {
2280
+ "epoch": 1.08,
2281
+ "learning_rate": 9.14508806750789e-06,
2282
+ "loss": 0.0808,
2283
+ "step": 379
2284
+ },
2285
+ {
2286
+ "epoch": 1.09,
2287
+ "learning_rate": 9.098998839881812e-06,
2288
+ "loss": 0.088,
2289
+ "step": 380
2290
+ },
2291
+ {
2292
+ "epoch": 1.09,
2293
+ "learning_rate": 9.052928900148031e-06,
2294
+ "loss": 0.0765,
2295
+ "step": 381
2296
+ },
2297
+ {
2298
+ "epoch": 1.09,
2299
+ "learning_rate": 9.006879234533948e-06,
2300
+ "loss": 0.0744,
2301
+ "step": 382
2302
+ },
2303
+ {
2304
+ "epoch": 1.09,
2305
+ "learning_rate": 8.960850828832958e-06,
2306
+ "loss": 0.0791,
2307
+ "step": 383
2308
+ },
2309
+ {
2310
+ "epoch": 1.1,
2311
+ "learning_rate": 8.91484466838334e-06,
2312
+ "loss": 0.0766,
2313
+ "step": 384
2314
+ },
2315
+ {
2316
+ "epoch": 1.1,
2317
+ "learning_rate": 8.868861738047158e-06,
2318
+ "loss": 0.0861,
2319
+ "step": 385
2320
+ },
2321
+ {
2322
+ "epoch": 1.1,
2323
+ "learning_rate": 8.8229030221892e-06,
2324
+ "loss": 0.0679,
2325
+ "step": 386
2326
+ },
2327
+ {
2328
+ "epoch": 1.11,
2329
+ "learning_rate": 8.776969504655875e-06,
2330
+ "loss": 0.0827,
2331
+ "step": 387
2332
+ },
2333
+ {
2334
+ "epoch": 1.11,
2335
+ "learning_rate": 8.731062168754174e-06,
2336
+ "loss": 0.0824,
2337
+ "step": 388
2338
+ },
2339
+ {
2340
+ "epoch": 1.11,
2341
+ "learning_rate": 8.685181997230616e-06,
2342
+ "loss": 0.0769,
2343
+ "step": 389
2344
+ },
2345
+ {
2346
+ "epoch": 1.11,
2347
+ "learning_rate": 8.639329972250199e-06,
2348
+ "loss": 0.0799,
2349
+ "step": 390
2350
+ },
2351
+ {
2352
+ "epoch": 1.12,
2353
+ "learning_rate": 8.593507075375388e-06,
2354
+ "loss": 0.0752,
2355
+ "step": 391
2356
+ },
2357
+ {
2358
+ "epoch": 1.12,
2359
+ "learning_rate": 8.5477142875451e-06,
2360
+ "loss": 0.0861,
2361
+ "step": 392
2362
+ },
2363
+ {
2364
+ "epoch": 1.12,
2365
+ "learning_rate": 8.501952589053694e-06,
2366
+ "loss": 0.077,
2367
+ "step": 393
2368
+ },
2369
+ {
2370
+ "epoch": 1.13,
2371
+ "learning_rate": 8.456222959530008e-06,
2372
+ "loss": 0.08,
2373
+ "step": 394
2374
+ },
2375
+ {
2376
+ "epoch": 1.13,
2377
+ "learning_rate": 8.41052637791636e-06,
2378
+ "loss": 0.0769,
2379
+ "step": 395
2380
+ },
2381
+ {
2382
+ "epoch": 1.13,
2383
+ "learning_rate": 8.364863822447612e-06,
2384
+ "loss": 0.0784,
2385
+ "step": 396
2386
+ },
2387
+ {
2388
+ "epoch": 1.13,
2389
+ "learning_rate": 8.319236270630218e-06,
2390
+ "loss": 0.0769,
2391
+ "step": 397
2392
+ },
2393
+ {
2394
+ "epoch": 1.14,
2395
+ "learning_rate": 8.273644699221309e-06,
2396
+ "loss": 0.0784,
2397
+ "step": 398
2398
+ },
2399
+ {
2400
+ "epoch": 1.14,
2401
+ "learning_rate": 8.228090084207773e-06,
2402
+ "loss": 0.0804,
2403
+ "step": 399
2404
+ },
2405
+ {
2406
+ "epoch": 1.14,
2407
+ "learning_rate": 8.182573400785367e-06,
2408
+ "loss": 0.0788,
2409
+ "step": 400
2410
+ },
2411
+ {
2412
+ "epoch": 1.15,
2413
+ "learning_rate": 8.137095623337836e-06,
2414
+ "loss": 0.0736,
2415
+ "step": 401
2416
+ },
2417
+ {
2418
+ "epoch": 1.15,
2419
+ "learning_rate": 8.091657725416065e-06,
2420
+ "loss": 0.0788,
2421
+ "step": 402
2422
+ },
2423
+ {
2424
+ "epoch": 1.15,
2425
+ "learning_rate": 8.046260679717225e-06,
2426
+ "loss": 0.0816,
2427
+ "step": 403
2428
+ },
2429
+ {
2430
+ "epoch": 1.15,
2431
+ "learning_rate": 8.000905458063956e-06,
2432
+ "loss": 0.0802,
2433
+ "step": 404
2434
+ },
2435
+ {
2436
+ "epoch": 1.16,
2437
+ "learning_rate": 7.95559303138357e-06,
2438
+ "loss": 0.0728,
2439
+ "step": 405
2440
+ },
2441
+ {
2442
+ "epoch": 1.16,
2443
+ "learning_rate": 7.91032436968725e-06,
2444
+ "loss": 0.0861,
2445
+ "step": 406
2446
+ },
2447
+ {
2448
+ "epoch": 1.16,
2449
+ "learning_rate": 7.865100442049302e-06,
2450
+ "loss": 0.0685,
2451
+ "step": 407
2452
+ },
2453
+ {
2454
+ "epoch": 1.17,
2455
+ "learning_rate": 7.8199222165864e-06,
2456
+ "loss": 0.086,
2457
+ "step": 408
2458
+ },
2459
+ {
2460
+ "epoch": 1.17,
2461
+ "learning_rate": 7.774790660436857e-06,
2462
+ "loss": 0.0797,
2463
+ "step": 409
2464
+ },
2465
+ {
2466
+ "epoch": 1.17,
2467
+ "learning_rate": 7.729706739739939e-06,
2468
+ "loss": 0.0827,
2469
+ "step": 410
2470
+ },
2471
+ {
2472
+ "epoch": 1.17,
2473
+ "learning_rate": 7.684671419615164e-06,
2474
+ "loss": 0.0799,
2475
+ "step": 411
2476
+ },
2477
+ {
2478
+ "epoch": 1.18,
2479
+ "learning_rate": 7.639685664141644e-06,
2480
+ "loss": 0.0799,
2481
+ "step": 412
2482
+ },
2483
+ {
2484
+ "epoch": 1.18,
2485
+ "learning_rate": 7.594750436337467e-06,
2486
+ "loss": 0.0783,
2487
+ "step": 413
2488
+ },
2489
+ {
2490
+ "epoch": 1.18,
2491
+ "learning_rate": 7.549866698139048e-06,
2492
+ "loss": 0.0831,
2493
+ "step": 414
2494
+ },
2495
+ {
2496
+ "epoch": 1.19,
2497
+ "learning_rate": 7.505035410380574e-06,
2498
+ "loss": 0.0754,
2499
+ "step": 415
2500
+ },
2501
+ {
2502
+ "epoch": 1.19,
2503
+ "learning_rate": 7.4602575327734004e-06,
2504
+ "loss": 0.0849,
2505
+ "step": 416
2506
+ },
2507
+ {
2508
+ "epoch": 1.19,
2509
+ "learning_rate": 7.415534023885529e-06,
2510
+ "loss": 0.091,
2511
+ "step": 417
2512
+ },
2513
+ {
2514
+ "epoch": 1.19,
2515
+ "learning_rate": 7.37086584112108e-06,
2516
+ "loss": 0.0751,
2517
+ "step": 418
2518
+ },
2519
+ {
2520
+ "epoch": 1.2,
2521
+ "learning_rate": 7.326253940699795e-06,
2522
+ "loss": 0.0795,
2523
+ "step": 419
2524
+ },
2525
+ {
2526
+ "epoch": 1.2,
2527
+ "learning_rate": 7.2816992776365714e-06,
2528
+ "loss": 0.0743,
2529
+ "step": 420
2530
+ },
2531
+ {
2532
+ "epoch": 1.2,
2533
+ "learning_rate": 7.23720280572102e-06,
2534
+ "loss": 0.0835,
2535
+ "step": 421
2536
+ },
2537
+ {
2538
+ "epoch": 1.21,
2539
+ "learning_rate": 7.192765477497032e-06,
2540
+ "loss": 0.0752,
2541
+ "step": 422
2542
+ },
2543
+ {
2544
+ "epoch": 1.21,
2545
+ "learning_rate": 7.148388244242414e-06,
2546
+ "loss": 0.0845,
2547
+ "step": 423
2548
+ },
2549
+ {
2550
+ "epoch": 1.21,
2551
+ "learning_rate": 7.1040720559485e-06,
2552
+ "loss": 0.0711,
2553
+ "step": 424
2554
+ },
2555
+ {
2556
+ "epoch": 1.21,
2557
+ "learning_rate": 7.05981786129982e-06,
2558
+ "loss": 0.0823,
2559
+ "step": 425
2560
+ },
2561
+ {
2562
+ "epoch": 1.22,
2563
+ "learning_rate": 7.015626607653807e-06,
2564
+ "loss": 0.0814,
2565
+ "step": 426
2566
+ },
2567
+ {
2568
+ "epoch": 1.22,
2569
+ "learning_rate": 6.971499241020495e-06,
2570
+ "loss": 0.0785,
2571
+ "step": 427
2572
+ },
2573
+ {
2574
+ "epoch": 1.22,
2575
+ "learning_rate": 6.927436706042276e-06,
2576
+ "loss": 0.0684,
2577
+ "step": 428
2578
+ },
2579
+ {
2580
+ "epoch": 1.23,
2581
+ "learning_rate": 6.883439945973692e-06,
2582
+ "loss": 0.0772,
2583
+ "step": 429
2584
+ },
2585
+ {
2586
+ "epoch": 1.23,
2587
+ "learning_rate": 6.839509902661215e-06,
2588
+ "loss": 0.0811,
2589
+ "step": 430
2590
+ },
2591
+ {
2592
+ "epoch": 1.23,
2593
+ "learning_rate": 6.795647516523107e-06,
2594
+ "loss": 0.0674,
2595
+ "step": 431
2596
+ },
2597
+ {
2598
+ "epoch": 1.23,
2599
+ "learning_rate": 6.75185372652928e-06,
2600
+ "loss": 0.0766,
2601
+ "step": 432
2602
+ },
2603
+ {
2604
+ "epoch": 1.24,
2605
+ "learning_rate": 6.708129470181197e-06,
2606
+ "loss": 0.0845,
2607
+ "step": 433
2608
+ },
2609
+ {
2610
+ "epoch": 1.24,
2611
+ "learning_rate": 6.664475683491797e-06,
2612
+ "loss": 0.0816,
2613
+ "step": 434
2614
+ },
2615
+ {
2616
+ "epoch": 1.24,
2617
+ "learning_rate": 6.620893300965465e-06,
2618
+ "loss": 0.0761,
2619
+ "step": 435
2620
+ },
2621
+ {
2622
+ "epoch": 1.25,
2623
+ "learning_rate": 6.577383255578034e-06,
2624
+ "loss": 0.0774,
2625
+ "step": 436
2626
+ },
2627
+ {
2628
+ "epoch": 1.25,
2629
+ "learning_rate": 6.533946478756789e-06,
2630
+ "loss": 0.0788,
2631
+ "step": 437
2632
+ },
2633
+ {
2634
+ "epoch": 1.25,
2635
+ "learning_rate": 6.490583900360543e-06,
2636
+ "loss": 0.0819,
2637
+ "step": 438
2638
+ },
2639
+ {
2640
+ "epoch": 1.25,
2641
+ "learning_rate": 6.447296448659744e-06,
2642
+ "loss": 0.0784,
2643
+ "step": 439
2644
+ },
2645
+ {
2646
+ "epoch": 1.26,
2647
+ "learning_rate": 6.404085050316568e-06,
2648
+ "loss": 0.0796,
2649
+ "step": 440
2650
+ },
2651
+ {
2652
+ "epoch": 1.26,
2653
+ "learning_rate": 6.360950630365126e-06,
2654
+ "loss": 0.0808,
2655
+ "step": 441
2656
+ },
2657
+ {
2658
+ "epoch": 1.26,
2659
+ "learning_rate": 6.317894112191621e-06,
2660
+ "loss": 0.081,
2661
+ "step": 442
2662
+ },
2663
+ {
2664
+ "epoch": 1.27,
2665
+ "learning_rate": 6.274916417514605e-06,
2666
+ "loss": 0.0755,
2667
+ "step": 443
2668
+ },
2669
+ {
2670
+ "epoch": 1.27,
2671
+ "learning_rate": 6.232018466365247e-06,
2672
+ "loss": 0.0792,
2673
+ "step": 444
2674
+ },
2675
+ {
2676
+ "epoch": 1.27,
2677
+ "learning_rate": 6.189201177067623e-06,
2678
+ "loss": 0.0845,
2679
+ "step": 445
2680
+ },
2681
+ {
2682
+ "epoch": 1.27,
2683
+ "learning_rate": 6.146465466219072e-06,
2684
+ "loss": 0.0771,
2685
+ "step": 446
2686
+ },
2687
+ {
2688
+ "epoch": 1.28,
2689
+ "learning_rate": 6.103812248670567e-06,
2690
+ "loss": 0.0778,
2691
+ "step": 447
2692
+ },
2693
+ {
2694
+ "epoch": 1.28,
2695
+ "learning_rate": 6.061242437507131e-06,
2696
+ "loss": 0.0804,
2697
+ "step": 448
2698
+ },
2699
+ {
2700
+ "epoch": 1.28,
2701
+ "learning_rate": 6.018756944028291e-06,
2702
+ "loss": 0.0804,
2703
+ "step": 449
2704
+ },
2705
+ {
2706
+ "epoch": 1.29,
2707
+ "learning_rate": 5.976356677728578e-06,
2708
+ "loss": 0.0704,
2709
+ "step": 450
2710
+ },
2711
+ {
2712
+ "epoch": 1.29,
2713
+ "learning_rate": 5.9340425462780405e-06,
2714
+ "loss": 0.0887,
2715
+ "step": 451
2716
+ },
2717
+ {
2718
+ "epoch": 1.29,
2719
+ "learning_rate": 5.891815455502824e-06,
2720
+ "loss": 0.0749,
2721
+ "step": 452
2722
+ },
2723
+ {
2724
+ "epoch": 1.29,
2725
+ "learning_rate": 5.849676309365786e-06,
2726
+ "loss": 0.0838,
2727
+ "step": 453
2728
+ },
2729
+ {
2730
+ "epoch": 1.3,
2731
+ "learning_rate": 5.807626009947127e-06,
2732
+ "loss": 0.0795,
2733
+ "step": 454
2734
+ },
2735
+ {
2736
+ "epoch": 1.3,
2737
+ "learning_rate": 5.765665457425102e-06,
2738
+ "loss": 0.088,
2739
+ "step": 455
2740
+ },
2741
+ {
2742
+ "epoch": 1.3,
2743
+ "learning_rate": 5.723795550056721e-06,
2744
+ "loss": 0.082,
2745
+ "step": 456
2746
+ },
2747
+ {
2748
+ "epoch": 1.31,
2749
+ "learning_rate": 5.682017184158562e-06,
2750
+ "loss": 0.0831,
2751
+ "step": 457
2752
+ },
2753
+ {
2754
+ "epoch": 1.31,
2755
+ "learning_rate": 5.6403312540875325e-06,
2756
+ "loss": 0.0752,
2757
+ "step": 458
2758
+ },
2759
+ {
2760
+ "epoch": 1.31,
2761
+ "learning_rate": 5.5987386522217645e-06,
2762
+ "loss": 0.0751,
2763
+ "step": 459
2764
+ },
2765
+ {
2766
+ "epoch": 1.31,
2767
+ "learning_rate": 5.557240268941497e-06,
2768
+ "loss": 0.0851,
2769
+ "step": 460
2770
+ },
2771
+ {
2772
+ "epoch": 1.32,
2773
+ "learning_rate": 5.515836992610011e-06,
2774
+ "loss": 0.0833,
2775
+ "step": 461
2776
+ },
2777
+ {
2778
+ "epoch": 1.32,
2779
+ "learning_rate": 5.4745297095546125e-06,
2780
+ "loss": 0.0795,
2781
+ "step": 462
2782
+ },
2783
+ {
2784
+ "epoch": 1.32,
2785
+ "learning_rate": 5.433319304047666e-06,
2786
+ "loss": 0.082,
2787
+ "step": 463
2788
+ },
2789
+ {
2790
+ "epoch": 1.33,
2791
+ "learning_rate": 5.3922066582876685e-06,
2792
+ "loss": 0.0841,
2793
+ "step": 464
2794
+ },
2795
+ {
2796
+ "epoch": 1.33,
2797
+ "learning_rate": 5.351192652380341e-06,
2798
+ "loss": 0.0721,
2799
+ "step": 465
2800
+ },
2801
+ {
2802
+ "epoch": 1.33,
2803
+ "learning_rate": 5.310278164319816e-06,
2804
+ "loss": 0.074,
2805
+ "step": 466
2806
+ },
2807
+ {
2808
+ "epoch": 1.33,
2809
+ "learning_rate": 5.26946406996983e-06,
2810
+ "loss": 0.0753,
2811
+ "step": 467
2812
+ },
2813
+ {
2814
+ "epoch": 1.34,
2815
+ "learning_rate": 5.228751243044961e-06,
2816
+ "loss": 0.085,
2817
+ "step": 468
2818
+ },
2819
+ {
2820
+ "epoch": 1.34,
2821
+ "learning_rate": 5.18814055509195e-06,
2822
+ "loss": 0.0705,
2823
+ "step": 469
2824
+ },
2825
+ {
2826
+ "epoch": 1.34,
2827
+ "learning_rate": 5.1476328754710295e-06,
2828
+ "loss": 0.0852,
2829
+ "step": 470
2830
+ },
2831
+ {
2832
+ "epoch": 1.35,
2833
+ "learning_rate": 5.1072290713373056e-06,
2834
+ "loss": 0.0762,
2835
+ "step": 471
2836
+ },
2837
+ {
2838
+ "epoch": 1.35,
2839
+ "learning_rate": 5.066930007622209e-06,
2840
+ "loss": 0.0824,
2841
+ "step": 472
2842
+ },
2843
+ {
2844
+ "epoch": 1.35,
2845
+ "learning_rate": 5.026736547014981e-06,
2846
+ "loss": 0.0865,
2847
+ "step": 473
2848
+ },
2849
+ {
2850
+ "epoch": 1.35,
2851
+ "learning_rate": 4.9866495499441824e-06,
2852
+ "loss": 0.0691,
2853
+ "step": 474
2854
+ },
2855
+ {
2856
+ "epoch": 1.36,
2857
+ "learning_rate": 4.946669874559301e-06,
2858
+ "loss": 0.0807,
2859
+ "step": 475
2860
+ },
2861
+ {
2862
+ "epoch": 1.36,
2863
+ "learning_rate": 4.9067983767123736e-06,
2864
+ "loss": 0.0795,
2865
+ "step": 476
2866
+ },
2867
+ {
2868
+ "epoch": 1.36,
2869
+ "learning_rate": 4.8670359099396466e-06,
2870
+ "loss": 0.0764,
2871
+ "step": 477
2872
+ },
2873
+ {
2874
+ "epoch": 1.37,
2875
+ "learning_rate": 4.827383325443331e-06,
2876
+ "loss": 0.0844,
2877
+ "step": 478
2878
+ },
2879
+ {
2880
+ "epoch": 1.37,
2881
+ "learning_rate": 4.787841472073366e-06,
2882
+ "loss": 0.08,
2883
+ "step": 479
2884
+ },
2885
+ {
2886
+ "epoch": 1.37,
2887
+ "learning_rate": 4.748411196309248e-06,
2888
+ "loss": 0.0783,
2889
+ "step": 480
2890
+ },
2891
+ {
2892
+ "epoch": 1.37,
2893
+ "learning_rate": 4.709093342241917e-06,
2894
+ "loss": 0.0733,
2895
+ "step": 481
2896
+ },
2897
+ {
2898
+ "epoch": 1.38,
2899
+ "learning_rate": 4.669888751555669e-06,
2900
+ "loss": 0.0679,
2901
+ "step": 482
2902
+ },
2903
+ {
2904
+ "epoch": 1.38,
2905
+ "learning_rate": 4.630798263510162e-06,
2906
+ "loss": 0.0769,
2907
+ "step": 483
2908
+ },
2909
+ {
2910
+ "epoch": 1.38,
2911
+ "learning_rate": 4.591822714922441e-06,
2912
+ "loss": 0.0744,
2913
+ "step": 484
2914
+ },
2915
+ {
2916
+ "epoch": 1.39,
2917
+ "learning_rate": 4.552962940149005e-06,
2918
+ "loss": 0.0823,
2919
+ "step": 485
2920
+ },
2921
+ {
2922
+ "epoch": 1.39,
2923
+ "learning_rate": 4.51421977106798e-06,
2924
+ "loss": 0.0767,
2925
+ "step": 486
2926
+ },
2927
+ {
2928
+ "epoch": 1.39,
2929
+ "learning_rate": 4.475594037061285e-06,
2930
+ "loss": 0.0781,
2931
+ "step": 487
2932
+ },
2933
+ {
2934
+ "epoch": 1.39,
2935
+ "learning_rate": 4.437086564996891e-06,
2936
+ "loss": 0.0767,
2937
+ "step": 488
2938
+ },
2939
+ {
2940
+ "epoch": 1.4,
2941
+ "learning_rate": 4.398698179211103e-06,
2942
+ "loss": 0.0842,
2943
+ "step": 489
2944
+ },
2945
+ {
2946
+ "epoch": 1.4,
2947
+ "learning_rate": 4.360429701490935e-06,
2948
+ "loss": 0.0799,
2949
+ "step": 490
2950
+ },
2951
+ {
2952
+ "epoch": 1.4,
2953
+ "learning_rate": 4.3222819510565085e-06,
2954
+ "loss": 0.0788,
2955
+ "step": 491
2956
+ },
2957
+ {
2958
+ "epoch": 1.41,
2959
+ "learning_rate": 4.284255744543505e-06,
2960
+ "loss": 0.076,
2961
+ "step": 492
2962
+ },
2963
+ {
2964
+ "epoch": 1.41,
2965
+ "learning_rate": 4.246351895985702e-06,
2966
+ "loss": 0.0823,
2967
+ "step": 493
2968
+ },
2969
+ {
2970
+ "epoch": 1.41,
2971
+ "learning_rate": 4.208571216797539e-06,
2972
+ "loss": 0.0784,
2973
+ "step": 494
2974
+ },
2975
+ {
2976
+ "epoch": 1.41,
2977
+ "learning_rate": 4.170914515756738e-06,
2978
+ "loss": 0.0705,
2979
+ "step": 495
2980
+ },
2981
+ {
2982
+ "epoch": 1.42,
2983
+ "learning_rate": 4.133382598987007e-06,
2984
+ "loss": 0.0838,
2985
+ "step": 496
2986
+ },
2987
+ {
2988
+ "epoch": 1.42,
2989
+ "learning_rate": 4.095976269940777e-06,
2990
+ "loss": 0.0758,
2991
+ "step": 497
2992
+ },
2993
+ {
2994
+ "epoch": 1.42,
2995
+ "learning_rate": 4.058696329381987e-06,
2996
+ "loss": 0.0662,
2997
+ "step": 498
2998
+ },
2999
+ {
3000
+ "epoch": 1.43,
3001
+ "learning_rate": 4.021543575368968e-06,
3002
+ "loss": 0.0799,
3003
+ "step": 499
3004
+ },
3005
+ {
3006
+ "epoch": 1.43,
3007
+ "learning_rate": 3.984518803237343e-06,
3008
+ "loss": 0.0826,
3009
+ "step": 500
3010
+ },
3011
+ {
3012
+ "epoch": 1.43,
3013
+ "learning_rate": 3.9476228055830015e-06,
3014
+ "loss": 0.0692,
3015
+ "step": 501
3016
+ },
3017
+ {
3018
+ "epoch": 1.43,
3019
+ "learning_rate": 3.910856372245139e-06,
3020
+ "loss": 0.0684,
3021
+ "step": 502
3022
+ },
3023
+ {
3024
+ "epoch": 1.44,
3025
+ "learning_rate": 3.874220290289337e-06,
3026
+ "loss": 0.0812,
3027
+ "step": 503
3028
+ },
3029
+ {
3030
+ "epoch": 1.44,
3031
+ "learning_rate": 3.837715343990727e-06,
3032
+ "loss": 0.0719,
3033
+ "step": 504
3034
+ },
3035
+ {
3036
+ "epoch": 1.44,
3037
+ "learning_rate": 3.801342314817201e-06,
3038
+ "loss": 0.0806,
3039
+ "step": 505
3040
+ },
3041
+ {
3042
+ "epoch": 1.45,
3043
+ "learning_rate": 3.7651019814126656e-06,
3044
+ "loss": 0.0824,
3045
+ "step": 506
3046
+ },
3047
+ {
3048
+ "epoch": 1.45,
3049
+ "learning_rate": 3.7289951195803954e-06,
3050
+ "loss": 0.0762,
3051
+ "step": 507
3052
+ },
3053
+ {
3054
+ "epoch": 1.45,
3055
+ "learning_rate": 3.6930225022664136e-06,
3056
+ "loss": 0.0794,
3057
+ "step": 508
3058
+ },
3059
+ {
3060
+ "epoch": 1.45,
3061
+ "learning_rate": 3.6571848995429404e-06,
3062
+ "loss": 0.0755,
3063
+ "step": 509
3064
+ },
3065
+ {
3066
+ "epoch": 1.46,
3067
+ "learning_rate": 3.621483078591923e-06,
3068
+ "loss": 0.0853,
3069
+ "step": 510
3070
+ },
3071
+ {
3072
+ "epoch": 1.46,
3073
+ "learning_rate": 3.585917803688603e-06,
3074
+ "loss": 0.0807,
3075
+ "step": 511
3076
+ },
3077
+ {
3078
+ "epoch": 1.46,
3079
+ "learning_rate": 3.5504898361851492e-06,
3080
+ "loss": 0.0778,
3081
+ "step": 512
3082
+ },
3083
+ {
3084
+ "epoch": 1.47,
3085
+ "learning_rate": 3.515199934494373e-06,
3086
+ "loss": 0.0788,
3087
+ "step": 513
3088
+ },
3089
+ {
3090
+ "epoch": 1.47,
3091
+ "learning_rate": 3.4800488540734857e-06,
3092
+ "loss": 0.0736,
3093
+ "step": 514
3094
+ },
3095
+ {
3096
+ "epoch": 1.47,
3097
+ "learning_rate": 3.4450373474079278e-06,
3098
+ "loss": 0.0733,
3099
+ "step": 515
3100
+ },
3101
+ {
3102
+ "epoch": 1.47,
3103
+ "learning_rate": 3.4101661639952533e-06,
3104
+ "loss": 0.0798,
3105
+ "step": 516
3106
+ },
3107
+ {
3108
+ "epoch": 1.48,
3109
+ "learning_rate": 3.3754360503290973e-06,
3110
+ "loss": 0.0725,
3111
+ "step": 517
3112
+ },
3113
+ {
3114
+ "epoch": 1.48,
3115
+ "learning_rate": 3.3408477498831917e-06,
3116
+ "loss": 0.0804,
3117
+ "step": 518
3118
+ },
3119
+ {
3120
+ "epoch": 1.48,
3121
+ "learning_rate": 3.306402003095438e-06,
3122
+ "loss": 0.0854,
3123
+ "step": 519
3124
+ },
3125
+ {
3126
+ "epoch": 1.49,
3127
+ "learning_rate": 3.2720995473520766e-06,
3128
+ "loss": 0.0868,
3129
+ "step": 520
3130
+ },
3131
+ {
3132
+ "epoch": 1.49,
3133
+ "learning_rate": 3.2379411169718844e-06,
3134
+ "loss": 0.0809,
3135
+ "step": 521
3136
+ },
3137
+ {
3138
+ "epoch": 1.49,
3139
+ "learning_rate": 3.2039274431904643e-06,
3140
+ "loss": 0.0712,
3141
+ "step": 522
3142
+ },
3143
+ {
3144
+ "epoch": 1.49,
3145
+ "learning_rate": 3.170059254144593e-06,
3146
+ "loss": 0.0645,
3147
+ "step": 523
3148
+ },
3149
+ {
3150
+ "epoch": 1.5,
3151
+ "learning_rate": 3.136337274856618e-06,
3152
+ "loss": 0.0734,
3153
+ "step": 524
3154
+ },
3155
+ {
3156
+ "epoch": 1.5,
3157
+ "learning_rate": 3.1027622272189572e-06,
3158
+ "loss": 0.0852,
3159
+ "step": 525
3160
+ },
3161
+ {
3162
+ "epoch": 1.5,
3163
+ "learning_rate": 3.0693348299786407e-06,
3164
+ "loss": 0.0855,
3165
+ "step": 526
3166
+ },
3167
+ {
3168
+ "epoch": 1.51,
3169
+ "learning_rate": 3.0360557987219054e-06,
3170
+ "loss": 0.0869,
3171
+ "step": 527
3172
+ },
3173
+ {
3174
+ "epoch": 1.51,
3175
+ "learning_rate": 3.002925845858905e-06,
3176
+ "loss": 0.0795,
3177
+ "step": 528
3178
+ },
3179
+ {
3180
+ "epoch": 1.51,
3181
+ "learning_rate": 2.9699456806084427e-06,
3182
+ "loss": 0.0722,
3183
+ "step": 529
3184
+ },
3185
+ {
3186
+ "epoch": 1.51,
3187
+ "learning_rate": 2.9371160089827842e-06,
3188
+ "loss": 0.0776,
3189
+ "step": 530
3190
+ },
3191
+ {
3192
+ "epoch": 1.52,
3193
+ "learning_rate": 2.9044375337725595e-06,
3194
+ "loss": 0.0808,
3195
+ "step": 531
3196
+ },
3197
+ {
3198
+ "epoch": 1.52,
3199
+ "learning_rate": 2.8719109545317102e-06,
3200
+ "loss": 0.0732,
3201
+ "step": 532
3202
+ },
3203
+ {
3204
+ "epoch": 1.52,
3205
+ "learning_rate": 2.839536967562504e-06,
3206
+ "loss": 0.0745,
3207
+ "step": 533
3208
+ },
3209
+ {
3210
+ "epoch": 1.53,
3211
+ "learning_rate": 2.807316265900649e-06,
3212
+ "loss": 0.0833,
3213
+ "step": 534
3214
+ },
3215
+ {
3216
+ "epoch": 1.53,
3217
+ "learning_rate": 2.7752495393004476e-06,
3218
+ "loss": 0.0783,
3219
+ "step": 535
3220
+ },
3221
+ {
3222
+ "epoch": 1.53,
3223
+ "learning_rate": 2.743337474220019e-06,
3224
+ "loss": 0.0799,
3225
+ "step": 536
3226
+ },
3227
+ {
3228
+ "epoch": 1.53,
3229
+ "learning_rate": 2.71158075380663e-06,
3230
+ "loss": 0.0751,
3231
+ "step": 537
3232
+ },
3233
+ {
3234
+ "epoch": 1.54,
3235
+ "learning_rate": 2.679980057882049e-06,
3236
+ "loss": 0.0752,
3237
+ "step": 538
3238
+ },
3239
+ {
3240
+ "epoch": 1.54,
3241
+ "learning_rate": 2.648536062927999e-06,
3242
+ "loss": 0.0811,
3243
+ "step": 539
3244
+ },
3245
+ {
3246
+ "epoch": 1.54,
3247
+ "learning_rate": 2.61724944207168e-06,
3248
+ "loss": 0.0718,
3249
+ "step": 540
3250
+ },
3251
+ {
3252
+ "epoch": 1.55,
3253
+ "learning_rate": 2.5861208650713586e-06,
3254
+ "loss": 0.073,
3255
+ "step": 541
3256
+ },
3257
+ {
3258
+ "epoch": 1.55,
3259
+ "learning_rate": 2.555150998302026e-06,
3260
+ "loss": 0.0654,
3261
+ "step": 542
3262
+ },
3263
+ {
3264
+ "epoch": 1.55,
3265
+ "learning_rate": 2.5243405047411353e-06,
3266
+ "loss": 0.0806,
3267
+ "step": 543
3268
+ },
3269
+ {
3270
+ "epoch": 1.55,
3271
+ "learning_rate": 2.493690043954411e-06,
3272
+ "loss": 0.0721,
3273
+ "step": 544
3274
+ },
3275
+ {
3276
+ "epoch": 1.56,
3277
+ "learning_rate": 2.4632002720817227e-06,
3278
+ "loss": 0.081,
3279
+ "step": 545
3280
+ },
3281
+ {
3282
+ "epoch": 1.56,
3283
+ "learning_rate": 2.432871841823047e-06,
3284
+ "loss": 0.0814,
3285
+ "step": 546
3286
+ },
3287
+ {
3288
+ "epoch": 1.56,
3289
+ "learning_rate": 2.4027054024244954e-06,
3290
+ "loss": 0.0707,
3291
+ "step": 547
3292
+ },
3293
+ {
3294
+ "epoch": 1.57,
3295
+ "learning_rate": 2.3727015996644043e-06,
3296
+ "loss": 0.0731,
3297
+ "step": 548
3298
+ },
3299
+ {
3300
+ "epoch": 1.57,
3301
+ "learning_rate": 2.342861075839523e-06,
3302
+ "loss": 0.0751,
3303
+ "step": 549
3304
+ },
3305
+ {
3306
+ "epoch": 1.57,
3307
+ "learning_rate": 2.313184469751265e-06,
3308
+ "loss": 0.0907,
3309
+ "step": 550
3310
+ },
3311
+ {
3312
+ "epoch": 1.57,
3313
+ "learning_rate": 2.2836724166920134e-06,
3314
+ "loss": 0.0785,
3315
+ "step": 551
3316
+ },
3317
+ {
3318
+ "epoch": 1.58,
3319
+ "learning_rate": 2.2543255484315486e-06,
3320
+ "loss": 0.0796,
3321
+ "step": 552
3322
+ },
3323
+ {
3324
+ "epoch": 1.58,
3325
+ "learning_rate": 2.2251444932035094e-06,
3326
+ "loss": 0.0846,
3327
+ "step": 553
3328
+ },
3329
+ {
3330
+ "epoch": 1.58,
3331
+ "learning_rate": 2.1961298756919337e-06,
3332
+ "loss": 0.0764,
3333
+ "step": 554
3334
+ },
3335
+ {
3336
+ "epoch": 1.59,
3337
+ "learning_rate": 2.16728231701791e-06,
3338
+ "loss": 0.0739,
3339
+ "step": 555
3340
+ },
3341
+ {
3342
+ "epoch": 1.59,
3343
+ "learning_rate": 2.1386024347262692e-06,
3344
+ "loss": 0.075,
3345
+ "step": 556
3346
+ },
3347
+ {
3348
+ "epoch": 1.59,
3349
+ "learning_rate": 2.11009084277235e-06,
3350
+ "loss": 0.0787,
3351
+ "step": 557
3352
+ },
3353
+ {
3354
+ "epoch": 1.59,
3355
+ "learning_rate": 2.081748151508883e-06,
3356
+ "loss": 0.0712,
3357
+ "step": 558
3358
+ },
3359
+ {
3360
+ "epoch": 1.6,
3361
+ "learning_rate": 2.0535749676729123e-06,
3362
+ "loss": 0.0774,
3363
+ "step": 559
3364
+ },
3365
+ {
3366
+ "epoch": 1.6,
3367
+ "learning_rate": 2.025571894372794e-06,
3368
+ "loss": 0.0796,
3369
+ "step": 560
3370
+ },
3371
+ {
3372
+ "epoch": 1.6,
3373
+ "learning_rate": 1.9977395310753087e-06,
3374
+ "loss": 0.0738,
3375
+ "step": 561
3376
+ },
3377
+ {
3378
+ "epoch": 1.61,
3379
+ "learning_rate": 1.970078473592817e-06,
3380
+ "loss": 0.0846,
3381
+ "step": 562
3382
+ },
3383
+ {
3384
+ "epoch": 1.61,
3385
+ "learning_rate": 1.942589314070494e-06,
3386
+ "loss": 0.0718,
3387
+ "step": 563
3388
+ },
3389
+ {
3390
+ "epoch": 1.61,
3391
+ "learning_rate": 1.9152726409736834e-06,
3392
+ "loss": 0.0766,
3393
+ "step": 564
3394
+ },
3395
+ {
3396
+ "epoch": 1.61,
3397
+ "learning_rate": 1.8881290390752682e-06,
3398
+ "loss": 0.0784,
3399
+ "step": 565
3400
+ },
3401
+ {
3402
+ "epoch": 1.62,
3403
+ "learning_rate": 1.8611590894431653e-06,
3404
+ "loss": 0.0871,
3405
+ "step": 566
3406
+ },
3407
+ {
3408
+ "epoch": 1.62,
3409
+ "learning_rate": 1.8343633694278895e-06,
3410
+ "loss": 0.0712,
3411
+ "step": 567
3412
+ },
3413
+ {
3414
+ "epoch": 1.62,
3415
+ "learning_rate": 1.8077424526501964e-06,
3416
+ "loss": 0.0808,
3417
+ "step": 568
3418
+ },
3419
+ {
3420
+ "epoch": 1.63,
3421
+ "learning_rate": 1.7812969089887867e-06,
3422
+ "loss": 0.0767,
3423
+ "step": 569
3424
+ },
3425
+ {
3426
+ "epoch": 1.63,
3427
+ "learning_rate": 1.7550273045681243e-06,
3428
+ "loss": 0.0823,
3429
+ "step": 570
3430
+ },
3431
+ {
3432
+ "epoch": 1.63,
3433
+ "learning_rate": 1.728934201746314e-06,
3434
+ "loss": 0.0741,
3435
+ "step": 571
3436
+ },
3437
+ {
3438
+ "epoch": 1.63,
3439
+ "learning_rate": 1.7030181591030493e-06,
3440
+ "loss": 0.073,
3441
+ "step": 572
3442
+ },
3443
+ {
3444
+ "epoch": 1.64,
3445
+ "learning_rate": 1.6772797314276712e-06,
3446
+ "loss": 0.0753,
3447
+ "step": 573
3448
+ },
3449
+ {
3450
+ "epoch": 1.64,
3451
+ "learning_rate": 1.6517194697072903e-06,
3452
+ "loss": 0.0809,
3453
+ "step": 574
3454
+ },
3455
+ {
3456
+ "epoch": 1.64,
3457
+ "learning_rate": 1.6263379211149733e-06,
3458
+ "loss": 0.0869,
3459
+ "step": 575
3460
+ },
3461
+ {
3462
+ "epoch": 1.65,
3463
+ "learning_rate": 1.6011356289980562e-06,
3464
+ "loss": 0.0772,
3465
+ "step": 576
3466
+ },
3467
+ {
3468
+ "epoch": 1.65,
3469
+ "learning_rate": 1.5761131328664946e-06,
3470
+ "loss": 0.0707,
3471
+ "step": 577
3472
+ },
3473
+ {
3474
+ "epoch": 1.65,
3475
+ "learning_rate": 1.5512709683813165e-06,
3476
+ "loss": 0.0781,
3477
+ "step": 578
3478
+ },
3479
+ {
3480
+ "epoch": 1.65,
3481
+ "learning_rate": 1.526609667343163e-06,
3482
+ "loss": 0.0761,
3483
+ "step": 579
3484
+ },
3485
+ {
3486
+ "epoch": 1.66,
3487
+ "learning_rate": 1.5021297576809002e-06,
3488
+ "loss": 0.07,
3489
+ "step": 580
3490
+ },
3491
+ {
3492
+ "epoch": 1.66,
3493
+ "learning_rate": 1.4778317634403082e-06,
3494
+ "loss": 0.0773,
3495
+ "step": 581
3496
+ },
3497
+ {
3498
+ "epoch": 1.66,
3499
+ "learning_rate": 1.4537162047728804e-06,
3500
+ "loss": 0.0696,
3501
+ "step": 582
3502
+ },
3503
+ {
3504
+ "epoch": 1.67,
3505
+ "learning_rate": 1.4297835979246777e-06,
3506
+ "loss": 0.0804,
3507
+ "step": 583
3508
+ },
3509
+ {
3510
+ "epoch": 1.67,
3511
+ "learning_rate": 1.4060344552252702e-06,
3512
+ "loss": 0.0639,
3513
+ "step": 584
3514
+ },
3515
+ {
3516
+ "epoch": 1.67,
3517
+ "learning_rate": 1.3824692850767928e-06,
3518
+ "loss": 0.0724,
3519
+ "step": 585
3520
+ },
3521
+ {
3522
+ "epoch": 1.67,
3523
+ "learning_rate": 1.3590885919430385e-06,
3524
+ "loss": 0.0745,
3525
+ "step": 586
3526
+ },
3527
+ {
3528
+ "epoch": 1.68,
3529
+ "learning_rate": 1.3358928763386647e-06,
3530
+ "loss": 0.0746,
3531
+ "step": 587
3532
+ },
3533
+ {
3534
+ "epoch": 1.68,
3535
+ "learning_rate": 1.3128826348184886e-06,
3536
+ "loss": 0.0813,
3537
+ "step": 588
3538
+ },
3539
+ {
3540
+ "epoch": 1.68,
3541
+ "learning_rate": 1.2900583599668515e-06,
3542
+ "loss": 0.0656,
3543
+ "step": 589
3544
+ },
3545
+ {
3546
+ "epoch": 1.69,
3547
+ "learning_rate": 1.2674205403870643e-06,
3548
+ "loss": 0.0716,
3549
+ "step": 590
3550
+ },
3551
+ {
3552
+ "epoch": 1.69,
3553
+ "learning_rate": 1.2449696606909656e-06,
3554
+ "loss": 0.0691,
3555
+ "step": 591
3556
+ },
3557
+ {
3558
+ "epoch": 1.69,
3559
+ "learning_rate": 1.222706201488536e-06,
3560
+ "loss": 0.0727,
3561
+ "step": 592
3562
+ },
3563
+ {
3564
+ "epoch": 1.69,
3565
+ "learning_rate": 1.200630639377609e-06,
3566
+ "loss": 0.0809,
3567
+ "step": 593
3568
+ },
3569
+ {
3570
+ "epoch": 1.7,
3571
+ "learning_rate": 1.1787434469336767e-06,
3572
+ "loss": 0.0709,
3573
+ "step": 594
3574
+ },
3575
+ {
3576
+ "epoch": 1.7,
3577
+ "learning_rate": 1.1570450926997657e-06,
3578
+ "loss": 0.0728,
3579
+ "step": 595
3580
+ },
3581
+ {
3582
+ "epoch": 1.7,
3583
+ "learning_rate": 1.135536041176406e-06,
3584
+ "loss": 0.0765,
3585
+ "step": 596
3586
+ },
3587
+ {
3588
+ "epoch": 1.71,
3589
+ "learning_rate": 1.1142167528116965e-06,
3590
+ "loss": 0.0714,
3591
+ "step": 597
3592
+ },
3593
+ {
3594
+ "epoch": 1.71,
3595
+ "learning_rate": 1.0930876839914418e-06,
3596
+ "loss": 0.0678,
3597
+ "step": 598
3598
+ },
3599
+ {
3600
+ "epoch": 1.71,
3601
+ "learning_rate": 1.072149287029377e-06,
3602
+ "loss": 0.0807,
3603
+ "step": 599
3604
+ },
3605
+ {
3606
+ "epoch": 1.71,
3607
+ "learning_rate": 1.0514020101574974e-06,
3608
+ "loss": 0.0745,
3609
+ "step": 600
3610
+ },
3611
+ {
3612
+ "epoch": 1.72,
3613
+ "learning_rate": 1.0308462975164547e-06,
3614
+ "loss": 0.0742,
3615
+ "step": 601
3616
+ },
3617
+ {
3618
+ "epoch": 1.72,
3619
+ "learning_rate": 1.010482589146048e-06,
3620
+ "loss": 0.081,
3621
+ "step": 602
3622
+ },
3623
+ {
3624
+ "epoch": 1.72,
3625
+ "learning_rate": 9.903113209758098e-07,
3626
+ "loss": 0.0771,
3627
+ "step": 603
3628
+ },
3629
+ {
3630
+ "epoch": 1.73,
3631
+ "learning_rate": 9.703329248156712e-07,
3632
+ "loss": 0.0781,
3633
+ "step": 604
3634
+ },
3635
+ {
3636
+ "epoch": 1.73,
3637
+ "learning_rate": 9.505478283467129e-07,
3638
+ "loss": 0.0672,
3639
+ "step": 605
3640
+ },
3641
+ {
3642
+ "epoch": 1.73,
3643
+ "learning_rate": 9.309564551120254e-07,
3644
+ "loss": 0.0744,
3645
+ "step": 606
3646
+ },
3647
+ {
3648
+ "epoch": 1.73,
3649
+ "learning_rate": 9.115592245076177e-07,
3650
+ "loss": 0.0765,
3651
+ "step": 607
3652
+ },
3653
+ {
3654
+ "epoch": 1.74,
3655
+ "learning_rate": 8.923565517734633e-07,
3656
+ "loss": 0.079,
3657
+ "step": 608
3658
+ },
3659
+ {
3660
+ "epoch": 1.74,
3661
+ "learning_rate": 8.733488479845997e-07,
3662
+ "loss": 0.0705,
3663
+ "step": 609
3664
+ },
3665
+ {
3666
+ "epoch": 1.74,
3667
+ "learning_rate": 8.545365200423216e-07,
3668
+ "loss": 0.0766,
3669
+ "step": 610
3670
+ },
3671
+ {
3672
+ "epoch": 1.75,
3673
+ "learning_rate": 8.359199706654852e-07,
3674
+ "loss": 0.0625,
3675
+ "step": 611
3676
+ },
3677
+ {
3678
+ "epoch": 1.75,
3679
+ "learning_rate": 8.174995983818801e-07,
3680
+ "loss": 0.0653,
3681
+ "step": 612
3682
+ },
3683
+ {
3684
+ "epoch": 1.75,
3685
+ "learning_rate": 7.992757975196974e-07,
3686
+ "loss": 0.0719,
3687
+ "step": 613
3688
+ },
3689
+ {
3690
+ "epoch": 1.75,
3691
+ "learning_rate": 7.812489581990846e-07,
3692
+ "loss": 0.0766,
3693
+ "step": 614
3694
+ },
3695
+ {
3696
+ "epoch": 1.76,
3697
+ "learning_rate": 7.634194663238015e-07,
3698
+ "loss": 0.0826,
3699
+ "step": 615
3700
+ },
3701
+ {
3702
+ "epoch": 1.76,
3703
+ "learning_rate": 7.457877035729588e-07,
3704
+ "loss": 0.0797,
3705
+ "step": 616
3706
+ },
3707
+ {
3708
+ "epoch": 1.76,
3709
+ "learning_rate": 7.283540473928386e-07,
3710
+ "loss": 0.0673,
3711
+ "step": 617
3712
+ },
3713
+ {
3714
+ "epoch": 1.77,
3715
+ "learning_rate": 7.11118870988825e-07,
3716
+ "loss": 0.0831,
3717
+ "step": 618
3718
+ },
3719
+ {
3720
+ "epoch": 1.77,
3721
+ "learning_rate": 6.940825433174103e-07,
3722
+ "loss": 0.0725,
3723
+ "step": 619
3724
+ },
3725
+ {
3726
+ "epoch": 1.77,
3727
+ "learning_rate": 6.772454290782926e-07,
3728
+ "loss": 0.0767,
3729
+ "step": 620
3730
+ },
3731
+ {
3732
+ "epoch": 1.77,
3733
+ "learning_rate": 6.606078887065748e-07,
3734
+ "loss": 0.0766,
3735
+ "step": 621
3736
+ },
3737
+ {
3738
+ "epoch": 1.78,
3739
+ "learning_rate": 6.441702783650494e-07,
3740
+ "loss": 0.0652,
3741
+ "step": 622
3742
+ },
3743
+ {
3744
+ "epoch": 1.78,
3745
+ "learning_rate": 6.279329499365649e-07,
3746
+ "loss": 0.0707,
3747
+ "step": 623
3748
+ },
3749
+ {
3750
+ "epoch": 1.78,
3751
+ "learning_rate": 6.118962510165039e-07,
3752
+ "loss": 0.0751,
3753
+ "step": 624
3754
+ },
3755
+ {
3756
+ "epoch": 1.79,
3757
+ "learning_rate": 5.960605249053386e-07,
3758
+ "loss": 0.0747,
3759
+ "step": 625
3760
+ },
3761
+ {
3762
+ "epoch": 1.79,
3763
+ "learning_rate": 5.804261106012732e-07,
3764
+ "loss": 0.0688,
3765
+ "step": 626
3766
+ },
3767
+ {
3768
+ "epoch": 1.79,
3769
+ "learning_rate": 5.649933427930043e-07,
3770
+ "loss": 0.0811,
3771
+ "step": 627
3772
+ },
3773
+ {
3774
+ "epoch": 1.79,
3775
+ "learning_rate": 5.497625518525374e-07,
3776
+ "loss": 0.0755,
3777
+ "step": 628
3778
+ },
3779
+ {
3780
+ "epoch": 1.8,
3781
+ "learning_rate": 5.347340638281273e-07,
3782
+ "loss": 0.0761,
3783
+ "step": 629
3784
+ },
3785
+ {
3786
+ "epoch": 1.8,
3787
+ "learning_rate": 5.199082004372958e-07,
3788
+ "loss": 0.0843,
3789
+ "step": 630
3790
+ },
3791
+ {
3792
+ "epoch": 1.8,
3793
+ "learning_rate": 5.052852790599383e-07,
3794
+ "loss": 0.0751,
3795
+ "step": 631
3796
+ },
3797
+ {
3798
+ "epoch": 1.81,
3799
+ "learning_rate": 4.908656127315359e-07,
3800
+ "loss": 0.0658,
3801
+ "step": 632
3802
+ },
3803
+ {
3804
+ "epoch": 1.81,
3805
+ "learning_rate": 4.7664951013645875e-07,
3806
+ "loss": 0.08,
3807
+ "step": 633
3808
+ },
3809
+ {
3810
+ "epoch": 1.81,
3811
+ "learning_rate": 4.6263727560134086e-07,
3812
+ "loss": 0.0734,
3813
+ "step": 634
3814
+ },
3815
+ {
3816
+ "epoch": 1.81,
3817
+ "learning_rate": 4.4882920908858595e-07,
3818
+ "loss": 0.075,
3819
+ "step": 635
3820
+ },
3821
+ {
3822
+ "epoch": 1.82,
3823
+ "learning_rate": 4.352256061899329e-07,
3824
+ "loss": 0.0844,
3825
+ "step": 636
3826
+ },
3827
+ {
3828
+ "epoch": 1.82,
3829
+ "learning_rate": 4.218267581201296e-07,
3830
+ "loss": 0.075,
3831
+ "step": 637
3832
+ },
3833
+ {
3834
+ "epoch": 1.82,
3835
+ "learning_rate": 4.086329517107046e-07,
3836
+ "loss": 0.0811,
3837
+ "step": 638
3838
+ },
3839
+ {
3840
+ "epoch": 1.83,
3841
+ "learning_rate": 3.9564446940382087e-07,
3842
+ "loss": 0.0645,
3843
+ "step": 639
3844
+ },
3845
+ {
3846
+ "epoch": 1.83,
3847
+ "learning_rate": 3.8286158924623287e-07,
3848
+ "loss": 0.0746,
3849
+ "step": 640
3850
+ },
3851
+ {
3852
+ "epoch": 1.83,
3853
+ "learning_rate": 3.702845848833314e-07,
3854
+ "loss": 0.073,
3855
+ "step": 641
3856
+ },
3857
+ {
3858
+ "epoch": 1.83,
3859
+ "learning_rate": 3.579137255532894e-07,
3860
+ "loss": 0.0732,
3861
+ "step": 642
3862
+ },
3863
+ {
3864
+ "epoch": 1.84,
3865
+ "learning_rate": 3.457492760812975e-07,
3866
+ "loss": 0.0753,
3867
+ "step": 643
3868
+ },
3869
+ {
3870
+ "epoch": 1.84,
3871
+ "learning_rate": 3.3379149687388866e-07,
3872
+ "loss": 0.0854,
3873
+ "step": 644
3874
+ },
3875
+ {
3876
+ "epoch": 1.84,
3877
+ "learning_rate": 3.2204064391337277e-07,
3878
+ "loss": 0.0822,
3879
+ "step": 645
3880
+ },
3881
+ {
3882
+ "epoch": 1.85,
3883
+ "learning_rate": 3.1049696875235515e-07,
3884
+ "loss": 0.0791,
3885
+ "step": 646
3886
+ },
3887
+ {
3888
+ "epoch": 1.85,
3889
+ "learning_rate": 2.9916071850834004e-07,
3890
+ "loss": 0.0717,
3891
+ "step": 647
3892
+ },
3893
+ {
3894
+ "epoch": 1.85,
3895
+ "learning_rate": 2.8803213585846036e-07,
3896
+ "loss": 0.0735,
3897
+ "step": 648
3898
+ },
3899
+ {
3900
+ "epoch": 1.85,
3901
+ "learning_rate": 2.7711145903426494e-07,
3902
+ "loss": 0.0862,
3903
+ "step": 649
3904
+ },
3905
+ {
3906
+ "epoch": 1.86,
3907
+ "learning_rate": 2.6639892181662744e-07,
3908
+ "loss": 0.0741,
3909
+ "step": 650
3910
+ },
3911
+ {
3912
+ "epoch": 1.86,
3913
+ "learning_rate": 2.5589475353073987e-07,
3914
+ "loss": 0.0751,
3915
+ "step": 651
3916
+ },
3917
+ {
3918
+ "epoch": 1.86,
3919
+ "learning_rate": 2.4559917904120266e-07,
3920
+ "loss": 0.0689,
3921
+ "step": 652
3922
+ },
3923
+ {
3924
+ "epoch": 1.87,
3925
+ "learning_rate": 2.3551241874721353e-07,
3926
+ "loss": 0.0771,
3927
+ "step": 653
3928
+ },
3929
+ {
3930
+ "epoch": 1.87,
3931
+ "learning_rate": 2.256346885778482e-07,
3932
+ "loss": 0.0807,
3933
+ "step": 654
3934
+ },
3935
+ {
3936
+ "epoch": 1.87,
3937
+ "learning_rate": 2.1596619998743075e-07,
3938
+ "loss": 0.0752,
3939
+ "step": 655
3940
+ },
3941
+ {
3942
+ "epoch": 1.87,
3943
+ "learning_rate": 2.0650715995102266e-07,
3944
+ "loss": 0.0706,
3945
+ "step": 656
3946
+ },
3947
+ {
3948
+ "epoch": 1.88,
3949
+ "learning_rate": 1.9725777095997655e-07,
3950
+ "loss": 0.0718,
3951
+ "step": 657
3952
+ },
3953
+ {
3954
+ "epoch": 1.88,
3955
+ "learning_rate": 1.8821823101760949e-07,
3956
+ "loss": 0.0716,
3957
+ "step": 658
3958
+ },
3959
+ {
3960
+ "epoch": 1.88,
3961
+ "learning_rate": 1.7938873363496422e-07,
3962
+ "loss": 0.0733,
3963
+ "step": 659
3964
+ },
3965
+ {
3966
+ "epoch": 1.89,
3967
+ "learning_rate": 1.707694678266636e-07,
3968
+ "loss": 0.0739,
3969
+ "step": 660
3970
+ },
3971
+ {
3972
+ "epoch": 1.89,
3973
+ "learning_rate": 1.6236061810686488e-07,
3974
+ "loss": 0.0736,
3975
+ "step": 661
3976
+ },
3977
+ {
3978
+ "epoch": 1.89,
3979
+ "learning_rate": 1.5416236448531075e-07,
3980
+ "loss": 0.0745,
3981
+ "step": 662
3982
+ },
3983
+ {
3984
+ "epoch": 1.89,
3985
+ "learning_rate": 1.4617488246348012e-07,
3986
+ "loss": 0.0764,
3987
+ "step": 663
3988
+ },
3989
+ {
3990
+ "epoch": 1.9,
3991
+ "learning_rate": 1.383983430308189e-07,
3992
+ "loss": 0.072,
3993
+ "step": 664
3994
+ },
3995
+ {
3996
+ "epoch": 1.9,
3997
+ "learning_rate": 1.30832912661093e-07,
3998
+ "loss": 0.0693,
3999
+ "step": 665
4000
+ },
4001
+ {
4002
+ "epoch": 1.9,
4003
+ "learning_rate": 1.2347875330881886e-07,
4004
+ "loss": 0.0622,
4005
+ "step": 666
4006
+ },
4007
+ {
4008
+ "epoch": 1.91,
4009
+ "learning_rate": 1.1633602240579522e-07,
4010
+ "loss": 0.0677,
4011
+ "step": 667
4012
+ },
4013
+ {
4014
+ "epoch": 1.91,
4015
+ "learning_rate": 1.094048728577346e-07,
4016
+ "loss": 0.0741,
4017
+ "step": 668
4018
+ },
4019
+ {
4020
+ "epoch": 1.91,
4021
+ "learning_rate": 1.026854530409882e-07,
4022
+ "loss": 0.0775,
4023
+ "step": 669
4024
+ },
4025
+ {
4026
+ "epoch": 1.91,
4027
+ "learning_rate": 9.617790679937288e-08,
4028
+ "loss": 0.071,
4029
+ "step": 670
4030
+ },
4031
+ {
4032
+ "epoch": 1.92,
4033
+ "learning_rate": 8.988237344109251e-08,
4034
+ "loss": 0.0736,
4035
+ "step": 671
4036
+ },
4037
+ {
4038
+ "epoch": 1.92,
4039
+ "learning_rate": 8.379898773574924e-08,
4040
+ "loss": 0.0682,
4041
+ "step": 672
4042
+ },
4043
+ {
4044
+ "epoch": 1.92,
4045
+ "learning_rate": 7.792787991146356e-08,
4046
+ "loss": 0.073,
4047
+ "step": 673
4048
+ },
4049
+ {
4050
+ "epoch": 1.93,
4051
+ "learning_rate": 7.226917565208658e-08,
4052
+ "loss": 0.0671,
4053
+ "step": 674
4054
+ },
4055
+ {
4056
+ "epoch": 1.93,
4057
+ "learning_rate": 6.682299609450993e-08,
4058
+ "loss": 0.0696,
4059
+ "step": 675
4060
+ },
4061
+ {
4062
+ "epoch": 1.93,
4063
+ "learning_rate": 6.158945782606674e-08,
4064
+ "loss": 0.0723,
4065
+ "step": 676
4066
+ },
4067
+ {
4068
+ "epoch": 1.93,
4069
+ "learning_rate": 5.6568672882043595e-08,
4070
+ "loss": 0.0814,
4071
+ "step": 677
4072
+ },
4073
+ {
4074
+ "epoch": 1.94,
4075
+ "learning_rate": 5.176074874327919e-08,
4076
+ "loss": 0.069,
4077
+ "step": 678
4078
+ },
4079
+ {
4080
+ "epoch": 1.94,
4081
+ "learning_rate": 4.716578833386054e-08,
4082
+ "loss": 0.0745,
4083
+ "step": 679
4084
+ },
4085
+ {
4086
+ "epoch": 1.94,
4087
+ "learning_rate": 4.278389001892369e-08,
4088
+ "loss": 0.0698,
4089
+ "step": 680
4090
+ },
4091
+ {
4092
+ "epoch": 1.95,
4093
+ "learning_rate": 3.861514760254648e-08,
4094
+ "loss": 0.0729,
4095
+ "step": 681
4096
+ },
4097
+ {
4098
+ "epoch": 1.95,
4099
+ "learning_rate": 3.465965032574015e-08,
4100
+ "loss": 0.076,
4101
+ "step": 682
4102
+ },
4103
+ {
4104
+ "epoch": 1.95,
4105
+ "learning_rate": 3.091748286453866e-08,
4106
+ "loss": 0.0838,
4107
+ "step": 683
4108
+ },
4109
+ {
4110
+ "epoch": 1.95,
4111
+ "learning_rate": 2.7388725328189036e-08,
4112
+ "loss": 0.0723,
4113
+ "step": 684
4114
+ },
4115
+ {
4116
+ "epoch": 1.96,
4117
+ "learning_rate": 2.407345325743049e-08,
4118
+ "loss": 0.0795,
4119
+ "step": 685
4120
+ },
4121
+ {
4122
+ "epoch": 1.96,
4123
+ "learning_rate": 2.0971737622883515e-08,
4124
+ "loss": 0.0699,
4125
+ "step": 686
4126
+ },
4127
+ {
4128
+ "epoch": 1.96,
4129
+ "learning_rate": 1.8083644823526645e-08,
4130
+ "loss": 0.074,
4131
+ "step": 687
4132
+ },
4133
+ {
4134
+ "epoch": 1.97,
4135
+ "learning_rate": 1.5409236685277608e-08,
4136
+ "loss": 0.0708,
4137
+ "step": 688
4138
+ },
4139
+ {
4140
+ "epoch": 1.97,
4141
+ "learning_rate": 1.2948570459667687e-08,
4142
+ "loss": 0.0722,
4143
+ "step": 689
4144
+ },
4145
+ {
4146
+ "epoch": 1.97,
4147
+ "learning_rate": 1.070169882261496e-08,
4148
+ "loss": 0.0751,
4149
+ "step": 690
4150
+ },
4151
+ {
4152
+ "epoch": 1.97,
4153
+ "learning_rate": 8.668669873304058e-09,
4154
+ "loss": 0.0698,
4155
+ "step": 691
4156
+ },
4157
+ {
4158
+ "epoch": 1.98,
4159
+ "learning_rate": 6.849527133144795e-09,
4160
+ "loss": 0.0782,
4161
+ "step": 692
4162
+ },
4163
+ {
4164
+ "epoch": 1.98,
4165
+ "learning_rate": 5.2443095448506674e-09,
4166
+ "loss": 0.0755,
4167
+ "step": 693
4168
+ },
4169
+ {
4170
+ "epoch": 1.98,
4171
+ "learning_rate": 3.853051471601754e-09,
4172
+ "loss": 0.0715,
4173
+ "step": 694
4174
+ },
4175
+ {
4176
+ "epoch": 1.99,
4177
+ "learning_rate": 2.675782696305307e-09,
4178
+ "loss": 0.072,
4179
+ "step": 695
4180
+ },
4181
+ {
4182
+ "epoch": 1.99,
4183
+ "learning_rate": 1.712528420966253e-09,
4184
+ "loss": 0.0851,
4185
+ "step": 696
4186
+ },
4187
+ {
4188
+ "epoch": 1.99,
4189
+ "learning_rate": 9.633092661376353e-10,
4190
+ "loss": 0.0758,
4191
+ "step": 697
4192
+ },
4193
+ {
4194
+ "epoch": 1.99,
4195
+ "learning_rate": 4.2814127048873553e-10,
4196
+ "loss": 0.0763,
4197
+ "step": 698
4198
+ },
4199
+ {
4200
+ "epoch": 2.0,
4201
+ "learning_rate": 1.070358904564639e-10,
4202
+ "loss": 0.0725,
4203
+ "step": 699
4204
+ },
4205
+ {
4206
+ "epoch": 2.0,
4207
+ "learning_rate": 0.0,
4208
+ "loss": 0.0676,
4209
+ "step": 700
4210
+ },
4211
+ {
4212
+ "epoch": 2.0,
4213
+ "step": 700,
4214
+ "total_flos": 35619982540800.0,
4215
+ "train_loss": 0.0957284898098026,
4216
+ "train_runtime": 9340.1654,
4217
+ "train_samples_per_second": 8.39,
4218
+ "train_steps_per_second": 0.075
4219
+ }
4220
+ ],
4221
+ "logging_steps": 1.0,
4222
+ "max_steps": 700,
4223
+ "num_input_tokens_seen": 0,
4224
+ "num_train_epochs": 2,
4225
+ "save_steps": 188888,
4226
+ "total_flos": 35619982540800.0,
4227
+ "train_batch_size": 16,
4228
+ "trial_name": null,
4229
+ "trial_params": null
4230
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a00ff0fc9a0358c43be66a7470ab5e8e2d13bbf2a6fbd2d7ec3ef210b76e1a6
3
+ size 6139