H4nwei commited on
Commit
597e1d2
1 Parent(s): fc27fd7

Upload folder using huggingface_hub

Browse files
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
+ }
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cc6a1c50876433f9b8bd1727438a2ad43fa8fc83034f7810dd3131c35766995
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:a3356f3aad867e11b2a7f56566cd62dd652dc9ebda5ca9072cd57e36287ab737
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 sha256:956824d945254c8855bdc17b2c3b6cd27ae678f827515667bd27afae3b7ebc2f
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 sha256:5eadea196ca7710872910eba964d666fa18fb1aa0b62815fbde22f934a7ecb59
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 +1,2058 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 338,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 1.8181818181818183e-06,
14
+ "loss": 1.1217,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 3.6363636363636366e-06,
20
+ "loss": 1.2009,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 5.4545454545454545e-06,
26
+ "loss": 1.1674,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 7.272727272727273e-06,
32
+ "loss": 0.8147,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 9.090909090909091e-06,
38
+ "loss": 0.4414,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "learning_rate": 1.0909090909090909e-05,
44
+ "loss": 0.2042,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.04,
49
+ "learning_rate": 1.2727272727272728e-05,
50
+ "loss": 0.1899,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.05,
55
+ "learning_rate": 1.4545454545454546e-05,
56
+ "loss": 0.3638,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.05,
61
+ "learning_rate": 1.6363636363636366e-05,
62
+ "loss": 0.2162,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.06,
67
+ "learning_rate": 1.8181818181818182e-05,
68
+ "loss": 0.1731,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.07,
73
+ "learning_rate": 2e-05,
74
+ "loss": 0.2032,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.07,
79
+ "learning_rate": 1.9999538500851633e-05,
80
+ "loss": 0.2633,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.08,
85
+ "learning_rate": 1.9998154046002822e-05,
86
+ "loss": 0.1673,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.08,
91
+ "learning_rate": 1.9995846763238514e-05,
92
+ "loss": 0.1579,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.09,
97
+ "learning_rate": 1.9992616865520515e-05,
98
+ "loss": 0.1749,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.09,
103
+ "learning_rate": 1.9988464650967834e-05,
104
+ "loss": 0.2021,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.1,
109
+ "learning_rate": 1.9983390502829168e-05,
110
+ "loss": 0.1649,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.11,
115
+ "learning_rate": 1.9977394889447526e-05,
116
+ "loss": 0.1634,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.11,
121
+ "learning_rate": 1.9970478364217e-05,
122
+ "loss": 0.1793,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.12,
127
+ "learning_rate": 1.9962641565531694e-05,
128
+ "loss": 0.1394,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.12,
133
+ "learning_rate": 1.9953885216726788e-05,
134
+ "loss": 0.1512,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.13,
139
+ "learning_rate": 1.994421012601179e-05,
140
+ "loss": 0.15,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.14,
145
+ "learning_rate": 1.9933617186395917e-05,
146
+ "loss": 0.1537,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.14,
151
+ "learning_rate": 1.99221073756057e-05,
152
+ "loss": 0.1309,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.15,
157
+ "learning_rate": 1.990968175599471e-05,
158
+ "loss": 0.1277,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.15,
163
+ "learning_rate": 1.9896341474445526e-05,
164
+ "loss": 0.1416,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.16,
169
+ "learning_rate": 1.9882087762263857e-05,
170
+ "loss": 0.1363,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.17,
175
+ "learning_rate": 1.9866921935064907e-05,
176
+ "loss": 0.1103,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.17,
181
+ "learning_rate": 1.985084539265195e-05,
182
+ "loss": 0.1149,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.18,
187
+ "learning_rate": 1.983385961888711e-05,
188
+ "loss": 0.1173,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.18,
193
+ "learning_rate": 1.9815966181554412e-05,
194
+ "loss": 0.115,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.19,
199
+ "learning_rate": 1.9797166732215078e-05,
200
+ "loss": 0.1188,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.2,
205
+ "learning_rate": 1.977746300605507e-05,
206
+ "loss": 0.134,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.2,
211
+ "learning_rate": 1.975685682172497e-05,
212
+ "loss": 0.1128,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.21,
217
+ "learning_rate": 1.973535008117207e-05,
218
+ "loss": 0.126,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.21,
223
+ "learning_rate": 1.9712944769464864e-05,
224
+ "loss": 0.1161,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.22,
229
+ "learning_rate": 1.9689642954609808e-05,
230
+ "loss": 0.1297,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.22,
235
+ "learning_rate": 1.9665446787360444e-05,
236
+ "loss": 0.1233,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.23,
241
+ "learning_rate": 1.9640358501018885e-05,
242
+ "loss": 0.1177,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.24,
247
+ "learning_rate": 1.9614380411229693e-05,
248
+ "loss": 0.1085,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.24,
253
+ "learning_rate": 1.9587514915766124e-05,
254
+ "loss": 0.12,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.25,
259
+ "learning_rate": 1.9559764494308838e-05,
260
+ "loss": 0.1045,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.25,
265
+ "learning_rate": 1.9531131708217005e-05,
266
+ "loss": 0.1007,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.26,
271
+ "learning_rate": 1.950161920029191e-05,
272
+ "loss": 0.1139,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.27,
277
+ "learning_rate": 1.9471229694533003e-05,
278
+ "loss": 0.1091,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.27,
283
+ "learning_rate": 1.943996599588649e-05,
284
+ "loss": 0.0999,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.28,
289
+ "learning_rate": 1.940783098998643e-05,
290
+ "loss": 0.1004,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.28,
295
+ "learning_rate": 1.93748276428884e-05,
296
+ "loss": 0.1014,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.29,
301
+ "learning_rate": 1.9340959000795707e-05,
302
+ "loss": 0.1061,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.3,
307
+ "learning_rate": 1.9306228189778255e-05,
308
+ "loss": 0.1094,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.3,
313
+ "learning_rate": 1.927063841548398e-05,
314
+ "loss": 0.0942,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.31,
319
+ "learning_rate": 1.9234192962842996e-05,
320
+ "loss": 0.1039,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.31,
325
+ "learning_rate": 1.9196895195764363e-05,
326
+ "loss": 0.1316,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.32,
331
+ "learning_rate": 1.9158748556825637e-05,
332
+ "loss": 0.1021,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.33,
337
+ "learning_rate": 1.9119756566955092e-05,
338
+ "loss": 0.1205,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.33,
343
+ "learning_rate": 1.907992282510675e-05,
344
+ "loss": 0.0894,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.34,
349
+ "learning_rate": 1.90392510079282e-05,
350
+ "loss": 0.1054,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.34,
355
+ "learning_rate": 1.8997744869421248e-05,
356
+ "loss": 0.1129,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.35,
361
+ "learning_rate": 1.8955408240595396e-05,
362
+ "loss": 0.0943,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.36,
367
+ "learning_rate": 1.891224502911428e-05,
368
+ "loss": 0.0991,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.36,
373
+ "learning_rate": 1.886825921893497e-05,
374
+ "loss": 0.1007,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.37,
379
+ "learning_rate": 1.8823454869940243e-05,
380
+ "loss": 0.1113,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.37,
385
+ "learning_rate": 1.8777836117563894e-05,
386
+ "loss": 0.1194,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.38,
391
+ "learning_rate": 1.873140717240899e-05,
392
+ "loss": 0.1055,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.38,
397
+ "learning_rate": 1.8684172319859258e-05,
398
+ "loss": 0.1119,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.39,
403
+ "learning_rate": 1.863613591968355e-05,
404
+ "loss": 0.1141,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.4,
409
+ "learning_rate": 1.858730240563342e-05,
410
+ "loss": 0.0968,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.4,
415
+ "learning_rate": 1.8537676285033886e-05,
416
+ "loss": 0.1063,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.41,
421
+ "learning_rate": 1.848726213836744e-05,
422
+ "loss": 0.1052,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.41,
427
+ "learning_rate": 1.8436064618851225e-05,
428
+ "loss": 0.1032,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.42,
433
+ "learning_rate": 1.838408845200758e-05,
434
+ "loss": 0.0995,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.43,
439
+ "learning_rate": 1.8331338435227838e-05,
440
+ "loss": 0.0901,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.43,
445
+ "learning_rate": 1.8277819437329577e-05,
446
+ "loss": 0.0979,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.44,
451
+ "learning_rate": 1.8223536398107177e-05,
452
+ "loss": 0.0928,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.44,
457
+ "learning_rate": 1.8168494327875918e-05,
458
+ "loss": 0.0914,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.45,
463
+ "learning_rate": 1.8112698307009506e-05,
464
+ "loss": 0.1037,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.46,
469
+ "learning_rate": 1.8056153485471167e-05,
470
+ "loss": 0.0904,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.46,
475
+ "learning_rate": 1.799886508233829e-05,
476
+ "loss": 0.1055,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.47,
481
+ "learning_rate": 1.7940838385320732e-05,
482
+ "loss": 0.1018,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.47,
487
+ "learning_rate": 1.788207875027274e-05,
488
+ "loss": 0.1076,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.48,
493
+ "learning_rate": 1.7822591600698632e-05,
494
+ "loss": 0.0831,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.49,
499
+ "learning_rate": 1.776238242725217e-05,
500
+ "loss": 0.1093,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.49,
505
+ "learning_rate": 1.7701456787229805e-05,
506
+ "loss": 0.0833,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.5,
511
+ "learning_rate": 1.7639820304057745e-05,
512
+ "loss": 0.1132,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.5,
517
+ "learning_rate": 1.7577478666772886e-05,
518
+ "loss": 0.1031,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.51,
523
+ "learning_rate": 1.751443762949772e-05,
524
+ "loss": 0.1101,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.51,
529
+ "learning_rate": 1.7450703010909263e-05,
530
+ "loss": 0.1048,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.52,
535
+ "learning_rate": 1.738628069370195e-05,
536
+ "loss": 0.1122,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.53,
541
+ "learning_rate": 1.732117662404469e-05,
542
+ "loss": 0.0946,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.53,
547
+ "learning_rate": 1.7255396811032014e-05,
548
+ "loss": 0.108,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.54,
553
+ "learning_rate": 1.718894732612947e-05,
554
+ "loss": 0.1022,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.54,
559
+ "learning_rate": 1.712183430261319e-05,
560
+ "loss": 0.0947,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.55,
565
+ "learning_rate": 1.7054063935003813e-05,
566
+ "loss": 0.0979,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.56,
571
+ "learning_rate": 1.698564247849473e-05,
572
+ "loss": 0.1056,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.56,
577
+ "learning_rate": 1.691657624837472e-05,
578
+ "loss": 0.108,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.57,
583
+ "learning_rate": 1.684687161944506e-05,
584
+ "loss": 0.0886,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.57,
589
+ "learning_rate": 1.677653502543113e-05,
590
+ "loss": 0.0953,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.58,
595
+ "learning_rate": 1.6705572958388576e-05,
596
+ "loss": 0.0993,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.59,
601
+ "learning_rate": 1.6633991968104095e-05,
602
+ "loss": 0.1078,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.59,
607
+ "learning_rate": 1.6561798661490904e-05,
608
+ "loss": 0.0921,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.6,
613
+ "learning_rate": 1.6488999701978905e-05,
614
+ "loss": 0.0911,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.6,
619
+ "learning_rate": 1.6415601808899658e-05,
620
+ "loss": 0.0863,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.61,
625
+ "learning_rate": 1.63416117568662e-05,
626
+ "loss": 0.0795,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.62,
631
+ "learning_rate": 1.6267036375147728e-05,
632
+ "loss": 0.1034,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.62,
637
+ "learning_rate": 1.619188254703927e-05,
638
+ "loss": 0.1107,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.63,
643
+ "learning_rate": 1.6116157209226356e-05,
644
+ "loss": 0.0898,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.63,
649
+ "learning_rate": 1.6039867351144778e-05,
650
+ "loss": 0.0948,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.64,
655
+ "learning_rate": 1.5963020014335437e-05,
656
+ "loss": 0.0816,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.64,
661
+ "learning_rate": 1.588562229179443e-05,
662
+ "loss": 0.0856,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.65,
667
+ "learning_rate": 1.5807681327318372e-05,
668
+ "loss": 0.0867,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.66,
673
+ "learning_rate": 1.5729204314845002e-05,
674
+ "loss": 0.0828,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.66,
679
+ "learning_rate": 1.56501984977892e-05,
680
+ "loss": 0.0868,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.67,
685
+ "learning_rate": 1.557067116837444e-05,
686
+ "loss": 0.078,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.67,
691
+ "learning_rate": 1.5490629666959668e-05,
692
+ "loss": 0.0788,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.68,
697
+ "learning_rate": 1.541008138136183e-05,
698
+ "loss": 0.0838,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.69,
703
+ "learning_rate": 1.5329033746173975e-05,
704
+ "loss": 0.106,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.69,
709
+ "learning_rate": 1.5247494242079024e-05,
710
+ "loss": 0.0875,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.7,
715
+ "learning_rate": 1.5165470395159314e-05,
716
+ "loss": 0.0824,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.7,
721
+ "learning_rate": 1.5082969776201948e-05,
722
+ "loss": 0.1,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.71,
727
+ "learning_rate": 1.5000000000000002e-05,
728
+ "loss": 0.0928,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.72,
733
+ "learning_rate": 1.4916568724649688e-05,
734
+ "loss": 0.0968,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.72,
739
+ "learning_rate": 1.483268365084351e-05,
740
+ "loss": 0.0804,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.73,
745
+ "learning_rate": 1.4748352521159492e-05,
746
+ "loss": 0.0983,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.73,
751
+ "learning_rate": 1.466358311934654e-05,
752
+ "loss": 0.0795,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.74,
757
+ "learning_rate": 1.4578383269606004e-05,
758
+ "loss": 0.087,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.75,
763
+ "learning_rate": 1.4492760835869504e-05,
764
+ "loss": 0.0901,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.75,
769
+ "learning_rate": 1.4406723721073088e-05,
770
+ "loss": 0.0957,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.76,
775
+ "learning_rate": 1.4320279866427798e-05,
776
+ "loss": 0.0886,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.76,
781
+ "learning_rate": 1.4233437250686695e-05,
782
+ "loss": 0.0997,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.77,
787
+ "learning_rate": 1.4146203889408418e-05,
788
+ "loss": 0.0859,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.78,
793
+ "learning_rate": 1.4058587834217356e-05,
794
+ "loss": 0.0854,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.78,
799
+ "learning_rate": 1.3970597172060482e-05,
800
+ "loss": 0.0915,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.79,
805
+ "learning_rate": 1.3882240024460928e-05,
806
+ "loss": 0.0792,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.79,
811
+ "learning_rate": 1.3793524546768358e-05,
812
+ "loss": 0.0848,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.8,
817
+ "learning_rate": 1.3704458927406261e-05,
818
+ "loss": 0.0915,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.8,
823
+ "learning_rate": 1.3615051387116131e-05,
824
+ "loss": 0.0739,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.81,
829
+ "learning_rate": 1.3525310178198707e-05,
830
+ "loss": 0.088,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.82,
835
+ "learning_rate": 1.3435243583752294e-05,
836
+ "loss": 0.0767,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.82,
841
+ "learning_rate": 1.3344859916908206e-05,
842
+ "loss": 0.0828,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.83,
847
+ "learning_rate": 1.325416752006351e-05,
848
+ "loss": 0.0733,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.83,
853
+ "learning_rate": 1.3163174764110985e-05,
854
+ "loss": 0.0706,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.84,
859
+ "learning_rate": 1.3071890047666498e-05,
860
+ "loss": 0.0831,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.85,
865
+ "learning_rate": 1.2980321796293838e-05,
866
+ "loss": 0.0738,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.85,
871
+ "learning_rate": 1.288847846172701e-05,
872
+ "loss": 0.071,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.86,
877
+ "learning_rate": 1.2796368521090143e-05,
878
+ "loss": 0.074,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.86,
883
+ "learning_rate": 1.2704000476115079e-05,
884
+ "loss": 0.0807,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.87,
889
+ "learning_rate": 1.2611382852356632e-05,
890
+ "loss": 0.0832,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.88,
895
+ "learning_rate": 1.2518524198405699e-05,
896
+ "loss": 0.0799,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.88,
901
+ "learning_rate": 1.2425433085100224e-05,
902
+ "loss": 0.0699,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.89,
907
+ "learning_rate": 1.233211810473411e-05,
908
+ "loss": 0.0824,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.89,
913
+ "learning_rate": 1.2238587870264152e-05,
914
+ "loss": 0.0783,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.9,
919
+ "learning_rate": 1.2144851014515055e-05,
920
+ "loss": 0.0862,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.91,
925
+ "learning_rate": 1.2050916189382646e-05,
926
+ "loss": 0.072,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.91,
931
+ "learning_rate": 1.1956792065035281e-05,
932
+ "loss": 0.0804,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.92,
937
+ "learning_rate": 1.1862487329113606e-05,
938
+ "loss": 0.0733,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.92,
943
+ "learning_rate": 1.1768010685928686e-05,
944
+ "loss": 0.0933,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.93,
949
+ "learning_rate": 1.1673370855658592e-05,
950
+ "loss": 0.0835,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.93,
955
+ "learning_rate": 1.1578576573543541e-05,
956
+ "loss": 0.077,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.94,
961
+ "learning_rate": 1.1483636589079627e-05,
962
+ "loss": 0.0658,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.95,
967
+ "learning_rate": 1.1388559665211241e-05,
968
+ "loss": 0.0807,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.95,
973
+ "learning_rate": 1.1293354577522264e-05,
974
+ "loss": 0.0728,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.96,
979
+ "learning_rate": 1.1198030113426074e-05,
980
+ "loss": 0.0699,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.96,
985
+ "learning_rate": 1.1102595071354471e-05,
986
+ "loss": 0.0736,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.97,
991
+ "learning_rate": 1.1007058259945584e-05,
992
+ "loss": 0.0841,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.98,
997
+ "learning_rate": 1.0911428497230834e-05,
998
+ "loss": 0.0723,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.98,
1003
+ "learning_rate": 1.0815714609821027e-05,
1004
+ "loss": 0.0762,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.99,
1009
+ "learning_rate": 1.0719925432091671e-05,
1010
+ "loss": 0.0728,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.99,
1015
+ "learning_rate": 1.0624069805367558e-05,
1016
+ "loss": 0.0668,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 1.0,
1021
+ "learning_rate": 1.0528156577106703e-05,
1022
+ "loss": 0.0751,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 1.01,
1027
+ "learning_rate": 1.043219460008374e-05,
1028
+ "loss": 0.0495,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 1.01,
1033
+ "learning_rate": 1.0336192731572805e-05,
1034
+ "loss": 0.069,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 1.02,
1039
+ "learning_rate": 1.0240159832530007e-05,
1040
+ "loss": 0.0674,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 1.02,
1045
+ "learning_rate": 1.0144104766775574e-05,
1046
+ "loss": 0.0693,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 1.03,
1051
+ "learning_rate": 1.004803640017571e-05,
1052
+ "loss": 0.0652,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 1.04,
1057
+ "learning_rate": 9.951963599824294e-06,
1058
+ "loss": 0.0615,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 1.04,
1063
+ "learning_rate": 9.855895233224431e-06,
1064
+ "loss": 0.0595,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 1.05,
1069
+ "learning_rate": 9.759840167469995e-06,
1070
+ "loss": 0.0647,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 1.05,
1075
+ "learning_rate": 9.663807268427197e-06,
1076
+ "loss": 0.0541,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 1.06,
1081
+ "learning_rate": 9.56780539991626e-06,
1082
+ "loss": 0.0615,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 1.07,
1087
+ "learning_rate": 9.471843422893299e-06,
1088
+ "loss": 0.0536,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 1.07,
1093
+ "learning_rate": 9.375930194632447e-06,
1094
+ "loss": 0.0691,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 1.08,
1099
+ "learning_rate": 9.28007456790833e-06,
1100
+ "loss": 0.0581,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 1.08,
1105
+ "learning_rate": 9.184285390178978e-06,
1106
+ "loss": 0.0718,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 1.09,
1111
+ "learning_rate": 9.08857150276917e-06,
1112
+ "loss": 0.0702,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 1.09,
1117
+ "learning_rate": 8.992941740054418e-06,
1118
+ "loss": 0.0615,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 1.1,
1123
+ "learning_rate": 8.897404928645529e-06,
1124
+ "loss": 0.0702,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 1.11,
1129
+ "learning_rate": 8.80196988657393e-06,
1130
+ "loss": 0.0598,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 1.11,
1135
+ "learning_rate": 8.706645422477739e-06,
1136
+ "loss": 0.054,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 1.12,
1141
+ "learning_rate": 8.611440334788762e-06,
1142
+ "loss": 0.0749,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 1.12,
1147
+ "learning_rate": 8.516363410920376e-06,
1148
+ "loss": 0.0675,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 1.13,
1153
+ "learning_rate": 8.42142342645646e-06,
1154
+ "loss": 0.0705,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 1.14,
1159
+ "learning_rate": 8.326629144341408e-06,
1160
+ "loss": 0.0538,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 1.14,
1165
+ "learning_rate": 8.231989314071318e-06,
1166
+ "loss": 0.0638,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 1.15,
1171
+ "learning_rate": 8.137512670886397e-06,
1172
+ "loss": 0.0538,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 1.15,
1177
+ "learning_rate": 8.043207934964722e-06,
1178
+ "loss": 0.0506,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 1.16,
1183
+ "learning_rate": 7.949083810617358e-06,
1184
+ "loss": 0.0639,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 1.17,
1189
+ "learning_rate": 7.855148985484946e-06,
1190
+ "loss": 0.0603,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 1.17,
1195
+ "learning_rate": 7.761412129735853e-06,
1196
+ "loss": 0.0483,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 1.18,
1201
+ "learning_rate": 7.667881895265895e-06,
1202
+ "loss": 0.0555,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 1.18,
1207
+ "learning_rate": 7.574566914899779e-06,
1208
+ "loss": 0.0587,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 1.19,
1213
+ "learning_rate": 7.481475801594302e-06,
1214
+ "loss": 0.0467,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 1.2,
1219
+ "learning_rate": 7.388617147643371e-06,
1220
+ "loss": 0.0636,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 1.2,
1225
+ "learning_rate": 7.295999523884921e-06,
1226
+ "loss": 0.0555,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 1.21,
1231
+ "learning_rate": 7.203631478909857e-06,
1232
+ "loss": 0.0575,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 1.21,
1237
+ "learning_rate": 7.111521538272997e-06,
1238
+ "loss": 0.0629,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 1.22,
1243
+ "learning_rate": 7.019678203706164e-06,
1244
+ "loss": 0.0502,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 1.22,
1249
+ "learning_rate": 6.928109952333506e-06,
1250
+ "loss": 0.0727,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 1.23,
1255
+ "learning_rate": 6.83682523588902e-06,
1256
+ "loss": 0.0656,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 1.24,
1261
+ "learning_rate": 6.745832479936492e-06,
1262
+ "loss": 0.0506,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 1.24,
1267
+ "learning_rate": 6.655140083091794e-06,
1268
+ "loss": 0.065,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 1.25,
1273
+ "learning_rate": 6.564756416247712e-06,
1274
+ "loss": 0.0564,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 1.25,
1279
+ "learning_rate": 6.474689821801295e-06,
1280
+ "loss": 0.066,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 1.26,
1285
+ "learning_rate": 6.384948612883872e-06,
1286
+ "loss": 0.0516,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 1.27,
1291
+ "learning_rate": 6.2955410725937405e-06,
1292
+ "loss": 0.0573,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 1.27,
1297
+ "learning_rate": 6.206475453231644e-06,
1298
+ "loss": 0.0641,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 1.28,
1303
+ "learning_rate": 6.117759975539075e-06,
1304
+ "loss": 0.0537,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 1.28,
1309
+ "learning_rate": 6.029402827939519e-06,
1310
+ "loss": 0.0515,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 1.29,
1315
+ "learning_rate": 5.941412165782645e-06,
1316
+ "loss": 0.0535,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 1.3,
1321
+ "learning_rate": 5.853796110591583e-06,
1322
+ "loss": 0.0436,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 1.3,
1327
+ "learning_rate": 5.766562749313309e-06,
1328
+ "loss": 0.0569,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 1.31,
1333
+ "learning_rate": 5.6797201335722064e-06,
1334
+ "loss": 0.0677,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 1.31,
1339
+ "learning_rate": 5.593276278926912e-06,
1340
+ "loss": 0.0548,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 1.32,
1345
+ "learning_rate": 5.507239164130501e-06,
1346
+ "loss": 0.0612,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 1.33,
1351
+ "learning_rate": 5.421616730394e-06,
1352
+ "loss": 0.0578,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 1.33,
1357
+ "learning_rate": 5.336416880653461e-06,
1358
+ "loss": 0.056,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 1.34,
1363
+ "learning_rate": 5.251647478840511e-06,
1364
+ "loss": 0.0549,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 1.34,
1369
+ "learning_rate": 5.167316349156495e-06,
1370
+ "loss": 0.0381,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 1.35,
1375
+ "learning_rate": 5.083431275350312e-06,
1376
+ "loss": 0.0489,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 1.36,
1381
+ "learning_rate": 5.000000000000003e-06,
1382
+ "loss": 0.0547,
1383
+ "step": 229
1384
+ },
1385
+ {
1386
+ "epoch": 1.36,
1387
+ "learning_rate": 4.917030223798057e-06,
1388
+ "loss": 0.0641,
1389
+ "step": 230
1390
+ },
1391
+ {
1392
+ "epoch": 1.37,
1393
+ "learning_rate": 4.834529604840686e-06,
1394
+ "loss": 0.0604,
1395
+ "step": 231
1396
+ },
1397
+ {
1398
+ "epoch": 1.37,
1399
+ "learning_rate": 4.7525057579209775e-06,
1400
+ "loss": 0.0519,
1401
+ "step": 232
1402
+ },
1403
+ {
1404
+ "epoch": 1.38,
1405
+ "learning_rate": 4.670966253826027e-06,
1406
+ "loss": 0.0609,
1407
+ "step": 233
1408
+ },
1409
+ {
1410
+ "epoch": 1.38,
1411
+ "learning_rate": 4.589918618638173e-06,
1412
+ "loss": 0.0581,
1413
+ "step": 234
1414
+ },
1415
+ {
1416
+ "epoch": 1.39,
1417
+ "learning_rate": 4.5093703330403385e-06,
1418
+ "loss": 0.0524,
1419
+ "step": 235
1420
+ },
1421
+ {
1422
+ "epoch": 1.4,
1423
+ "learning_rate": 4.429328831625565e-06,
1424
+ "loss": 0.0475,
1425
+ "step": 236
1426
+ },
1427
+ {
1428
+ "epoch": 1.4,
1429
+ "learning_rate": 4.349801502210801e-06,
1430
+ "loss": 0.047,
1431
+ "step": 237
1432
+ },
1433
+ {
1434
+ "epoch": 1.41,
1435
+ "learning_rate": 4.270795685155001e-06,
1436
+ "loss": 0.0601,
1437
+ "step": 238
1438
+ },
1439
+ {
1440
+ "epoch": 1.41,
1441
+ "learning_rate": 4.192318672681631e-06,
1442
+ "loss": 0.0522,
1443
+ "step": 239
1444
+ },
1445
+ {
1446
+ "epoch": 1.42,
1447
+ "learning_rate": 4.1143777082055715e-06,
1448
+ "loss": 0.0571,
1449
+ "step": 240
1450
+ },
1451
+ {
1452
+ "epoch": 1.43,
1453
+ "learning_rate": 4.036979985664566e-06,
1454
+ "loss": 0.0444,
1455
+ "step": 241
1456
+ },
1457
+ {
1458
+ "epoch": 1.43,
1459
+ "learning_rate": 3.960132648855226e-06,
1460
+ "loss": 0.0491,
1461
+ "step": 242
1462
+ },
1463
+ {
1464
+ "epoch": 1.44,
1465
+ "learning_rate": 3.883842790773647e-06,
1466
+ "loss": 0.0453,
1467
+ "step": 243
1468
+ },
1469
+ {
1470
+ "epoch": 1.44,
1471
+ "learning_rate": 3.8081174529607346e-06,
1472
+ "loss": 0.0604,
1473
+ "step": 244
1474
+ },
1475
+ {
1476
+ "epoch": 1.45,
1477
+ "learning_rate": 3.732963624852275e-06,
1478
+ "loss": 0.0649,
1479
+ "step": 245
1480
+ },
1481
+ {
1482
+ "epoch": 1.46,
1483
+ "learning_rate": 3.6583882431338047e-06,
1484
+ "loss": 0.0535,
1485
+ "step": 246
1486
+ },
1487
+ {
1488
+ "epoch": 1.46,
1489
+ "learning_rate": 3.584398191100341e-06,
1490
+ "loss": 0.0496,
1491
+ "step": 247
1492
+ },
1493
+ {
1494
+ "epoch": 1.47,
1495
+ "learning_rate": 3.511000298021098e-06,
1496
+ "loss": 0.0498,
1497
+ "step": 248
1498
+ },
1499
+ {
1500
+ "epoch": 1.47,
1501
+ "learning_rate": 3.4382013385090985e-06,
1502
+ "loss": 0.0478,
1503
+ "step": 249
1504
+ },
1505
+ {
1506
+ "epoch": 1.48,
1507
+ "learning_rate": 3.3660080318959043e-06,
1508
+ "loss": 0.0556,
1509
+ "step": 250
1510
+ },
1511
+ {
1512
+ "epoch": 1.49,
1513
+ "learning_rate": 3.2944270416114256e-06,
1514
+ "loss": 0.0529,
1515
+ "step": 251
1516
+ },
1517
+ {
1518
+ "epoch": 1.49,
1519
+ "learning_rate": 3.223464974568874e-06,
1520
+ "loss": 0.0482,
1521
+ "step": 252
1522
+ },
1523
+ {
1524
+ "epoch": 1.5,
1525
+ "learning_rate": 3.153128380554941e-06,
1526
+ "loss": 0.0432,
1527
+ "step": 253
1528
+ },
1529
+ {
1530
+ "epoch": 1.5,
1531
+ "learning_rate": 3.0834237516252817e-06,
1532
+ "loss": 0.0535,
1533
+ "step": 254
1534
+ },
1535
+ {
1536
+ "epoch": 1.51,
1537
+ "learning_rate": 3.0143575215052732e-06,
1538
+ "loss": 0.0667,
1539
+ "step": 255
1540
+ },
1541
+ {
1542
+ "epoch": 1.51,
1543
+ "learning_rate": 2.94593606499619e-06,
1544
+ "loss": 0.0481,
1545
+ "step": 256
1546
+ },
1547
+ {
1548
+ "epoch": 1.52,
1549
+ "learning_rate": 2.878165697386812e-06,
1550
+ "loss": 0.0605,
1551
+ "step": 257
1552
+ },
1553
+ {
1554
+ "epoch": 1.53,
1555
+ "learning_rate": 2.8110526738705345e-06,
1556
+ "loss": 0.057,
1557
+ "step": 258
1558
+ },
1559
+ {
1560
+ "epoch": 1.53,
1561
+ "learning_rate": 2.7446031889679893e-06,
1562
+ "loss": 0.0492,
1563
+ "step": 259
1564
+ },
1565
+ {
1566
+ "epoch": 1.54,
1567
+ "learning_rate": 2.678823375955314e-06,
1568
+ "loss": 0.0543,
1569
+ "step": 260
1570
+ },
1571
+ {
1572
+ "epoch": 1.54,
1573
+ "learning_rate": 2.6137193062980506e-06,
1574
+ "loss": 0.0619,
1575
+ "step": 261
1576
+ },
1577
+ {
1578
+ "epoch": 1.55,
1579
+ "learning_rate": 2.5492969890907383e-06,
1580
+ "loss": 0.0562,
1581
+ "step": 262
1582
+ },
1583
+ {
1584
+ "epoch": 1.56,
1585
+ "learning_rate": 2.485562370502279e-06,
1586
+ "loss": 0.0415,
1587
+ "step": 263
1588
+ },
1589
+ {
1590
+ "epoch": 1.56,
1591
+ "learning_rate": 2.4225213332271203e-06,
1592
+ "loss": 0.0716,
1593
+ "step": 264
1594
+ },
1595
+ {
1596
+ "epoch": 1.57,
1597
+ "learning_rate": 2.3601796959422585e-06,
1598
+ "loss": 0.0475,
1599
+ "step": 265
1600
+ },
1601
+ {
1602
+ "epoch": 1.57,
1603
+ "learning_rate": 2.2985432127701945e-06,
1604
+ "loss": 0.0562,
1605
+ "step": 266
1606
+ },
1607
+ {
1608
+ "epoch": 1.58,
1609
+ "learning_rate": 2.2376175727478346e-06,
1610
+ "loss": 0.0521,
1611
+ "step": 267
1612
+ },
1613
+ {
1614
+ "epoch": 1.59,
1615
+ "learning_rate": 2.1774083993013715e-06,
1616
+ "loss": 0.0503,
1617
+ "step": 268
1618
+ },
1619
+ {
1620
+ "epoch": 1.59,
1621
+ "learning_rate": 2.1179212497272582e-06,
1622
+ "loss": 0.0602,
1623
+ "step": 269
1624
+ },
1625
+ {
1626
+ "epoch": 1.6,
1627
+ "learning_rate": 2.0591616146792705e-06,
1628
+ "loss": 0.048,
1629
+ "step": 270
1630
+ },
1631
+ {
1632
+ "epoch": 1.6,
1633
+ "learning_rate": 2.0011349176617133e-06,
1634
+ "loss": 0.055,
1635
+ "step": 271
1636
+ },
1637
+ {
1638
+ "epoch": 1.61,
1639
+ "learning_rate": 1.9438465145288377e-06,
1640
+ "loss": 0.059,
1641
+ "step": 272
1642
+ },
1643
+ {
1644
+ "epoch": 1.62,
1645
+ "learning_rate": 1.8873016929904942e-06,
1646
+ "loss": 0.046,
1647
+ "step": 273
1648
+ },
1649
+ {
1650
+ "epoch": 1.62,
1651
+ "learning_rate": 1.8315056721240831e-06,
1652
+ "loss": 0.0581,
1653
+ "step": 274
1654
+ },
1655
+ {
1656
+ "epoch": 1.63,
1657
+ "learning_rate": 1.7764636018928249e-06,
1658
+ "loss": 0.0451,
1659
+ "step": 275
1660
+ },
1661
+ {
1662
+ "epoch": 1.63,
1663
+ "learning_rate": 1.722180562670428e-06,
1664
+ "loss": 0.0436,
1665
+ "step": 276
1666
+ },
1667
+ {
1668
+ "epoch": 1.64,
1669
+ "learning_rate": 1.6686615647721638e-06,
1670
+ "loss": 0.0468,
1671
+ "step": 277
1672
+ },
1673
+ {
1674
+ "epoch": 1.64,
1675
+ "learning_rate": 1.6159115479924259e-06,
1676
+ "loss": 0.045,
1677
+ "step": 278
1678
+ },
1679
+ {
1680
+ "epoch": 1.65,
1681
+ "learning_rate": 1.5639353811487744e-06,
1682
+ "loss": 0.0381,
1683
+ "step": 279
1684
+ },
1685
+ {
1686
+ "epoch": 1.66,
1687
+ "learning_rate": 1.5127378616325606e-06,
1688
+ "loss": 0.0442,
1689
+ "step": 280
1690
+ },
1691
+ {
1692
+ "epoch": 1.66,
1693
+ "learning_rate": 1.462323714966114e-06,
1694
+ "loss": 0.0555,
1695
+ "step": 281
1696
+ },
1697
+ {
1698
+ "epoch": 1.67,
1699
+ "learning_rate": 1.4126975943665844e-06,
1700
+ "loss": 0.0574,
1701
+ "step": 282
1702
+ },
1703
+ {
1704
+ "epoch": 1.67,
1705
+ "learning_rate": 1.3638640803164516e-06,
1706
+ "loss": 0.0629,
1707
+ "step": 283
1708
+ },
1709
+ {
1710
+ "epoch": 1.68,
1711
+ "learning_rate": 1.3158276801407432e-06,
1712
+ "loss": 0.0509,
1713
+ "step": 284
1714
+ },
1715
+ {
1716
+ "epoch": 1.69,
1717
+ "learning_rate": 1.2685928275910142e-06,
1718
+ "loss": 0.0405,
1719
+ "step": 285
1720
+ },
1721
+ {
1722
+ "epoch": 1.69,
1723
+ "learning_rate": 1.222163882436107e-06,
1724
+ "loss": 0.0591,
1725
+ "step": 286
1726
+ },
1727
+ {
1728
+ "epoch": 1.7,
1729
+ "learning_rate": 1.1765451300597574e-06,
1730
+ "loss": 0.0409,
1731
+ "step": 287
1732
+ },
1733
+ {
1734
+ "epoch": 1.7,
1735
+ "learning_rate": 1.1317407810650372e-06,
1736
+ "loss": 0.0489,
1737
+ "step": 288
1738
+ },
1739
+ {
1740
+ "epoch": 1.71,
1741
+ "learning_rate": 1.0877549708857228e-06,
1742
+ "loss": 0.0564,
1743
+ "step": 289
1744
+ },
1745
+ {
1746
+ "epoch": 1.72,
1747
+ "learning_rate": 1.0445917594046073e-06,
1748
+ "loss": 0.0528,
1749
+ "step": 290
1750
+ },
1751
+ {
1752
+ "epoch": 1.72,
1753
+ "learning_rate": 1.0022551305787564e-06,
1754
+ "loss": 0.0597,
1755
+ "step": 291
1756
+ },
1757
+ {
1758
+ "epoch": 1.73,
1759
+ "learning_rate": 9.607489920717983e-07,
1760
+ "loss": 0.0481,
1761
+ "step": 292
1762
+ },
1763
+ {
1764
+ "epoch": 1.73,
1765
+ "learning_rate": 9.200771748932513e-07,
1766
+ "loss": 0.0466,
1767
+ "step": 293
1768
+ },
1769
+ {
1770
+ "epoch": 1.74,
1771
+ "learning_rate": 8.802434330449128e-07,
1772
+ "loss": 0.049,
1773
+ "step": 294
1774
+ },
1775
+ {
1776
+ "epoch": 1.75,
1777
+ "learning_rate": 8.412514431743657e-07,
1778
+ "loss": 0.0625,
1779
+ "step": 295
1780
+ },
1781
+ {
1782
+ "epoch": 1.75,
1783
+ "learning_rate": 8.031048042356393e-07,
1784
+ "loss": 0.0564,
1785
+ "step": 296
1786
+ },
1787
+ {
1788
+ "epoch": 1.76,
1789
+ "learning_rate": 7.65807037157007e-07,
1790
+ "loss": 0.057,
1791
+ "step": 297
1792
+ },
1793
+ {
1794
+ "epoch": 1.76,
1795
+ "learning_rate": 7.293615845160196e-07,
1796
+ "loss": 0.0626,
1797
+ "step": 298
1798
+ },
1799
+ {
1800
+ "epoch": 1.77,
1801
+ "learning_rate": 6.937718102217461e-07,
1802
+ "loss": 0.0608,
1803
+ "step": 299
1804
+ },
1805
+ {
1806
+ "epoch": 1.78,
1807
+ "learning_rate": 6.590409992042957e-07,
1808
+ "loss": 0.0548,
1809
+ "step": 300
1810
+ },
1811
+ {
1812
+ "epoch": 1.78,
1813
+ "learning_rate": 6.251723571116031e-07,
1814
+ "loss": 0.0573,
1815
+ "step": 301
1816
+ },
1817
+ {
1818
+ "epoch": 1.79,
1819
+ "learning_rate": 5.921690100135713e-07,
1820
+ "loss": 0.042,
1821
+ "step": 302
1822
+ },
1823
+ {
1824
+ "epoch": 1.79,
1825
+ "learning_rate": 5.600340041135133e-07,
1826
+ "loss": 0.0435,
1827
+ "step": 303
1828
+ },
1829
+ {
1830
+ "epoch": 1.8,
1831
+ "learning_rate": 5.287703054670012e-07,
1832
+ "loss": 0.0456,
1833
+ "step": 304
1834
+ },
1835
+ {
1836
+ "epoch": 1.8,
1837
+ "learning_rate": 4.983807997080925e-07,
1838
+ "loss": 0.0499,
1839
+ "step": 305
1840
+ },
1841
+ {
1842
+ "epoch": 1.81,
1843
+ "learning_rate": 4.6886829178299676e-07,
1844
+ "loss": 0.0474,
1845
+ "step": 306
1846
+ },
1847
+ {
1848
+ "epoch": 1.82,
1849
+ "learning_rate": 4.402355056911656e-07,
1850
+ "loss": 0.0539,
1851
+ "step": 307
1852
+ },
1853
+ {
1854
+ "epoch": 1.82,
1855
+ "learning_rate": 4.124850842338779e-07,
1856
+ "loss": 0.0523,
1857
+ "step": 308
1858
+ },
1859
+ {
1860
+ "epoch": 1.83,
1861
+ "learning_rate": 3.8561958877030957e-07,
1862
+ "loss": 0.0493,
1863
+ "step": 309
1864
+ },
1865
+ {
1866
+ "epoch": 1.83,
1867
+ "learning_rate": 3.5964149898111587e-07,
1868
+ "loss": 0.0439,
1869
+ "step": 310
1870
+ },
1871
+ {
1872
+ "epoch": 1.84,
1873
+ "learning_rate": 3.345532126395579e-07,
1874
+ "loss": 0.0385,
1875
+ "step": 311
1876
+ },
1877
+ {
1878
+ "epoch": 1.85,
1879
+ "learning_rate": 3.1035704539019384e-07,
1880
+ "loss": 0.0493,
1881
+ "step": 312
1882
+ },
1883
+ {
1884
+ "epoch": 1.85,
1885
+ "learning_rate": 2.870552305351382e-07,
1886
+ "loss": 0.05,
1887
+ "step": 313
1888
+ },
1889
+ {
1890
+ "epoch": 1.86,
1891
+ "learning_rate": 2.646499188279328e-07,
1892
+ "loss": 0.0387,
1893
+ "step": 314
1894
+ },
1895
+ {
1896
+ "epoch": 1.86,
1897
+ "learning_rate": 2.4314317827503375e-07,
1898
+ "loss": 0.0607,
1899
+ "step": 315
1900
+ },
1901
+ {
1902
+ "epoch": 1.87,
1903
+ "learning_rate": 2.2253699394493066e-07,
1904
+ "loss": 0.0454,
1905
+ "step": 316
1906
+ },
1907
+ {
1908
+ "epoch": 1.88,
1909
+ "learning_rate": 2.028332677849254e-07,
1910
+ "loss": 0.048,
1911
+ "step": 317
1912
+ },
1913
+ {
1914
+ "epoch": 1.88,
1915
+ "learning_rate": 1.840338184455881e-07,
1916
+ "loss": 0.057,
1917
+ "step": 318
1918
+ },
1919
+ {
1920
+ "epoch": 1.89,
1921
+ "learning_rate": 1.6614038111289034e-07,
1922
+ "loss": 0.0585,
1923
+ "step": 319
1924
+ },
1925
+ {
1926
+ "epoch": 1.89,
1927
+ "learning_rate": 1.49154607348051e-07,
1928
+ "loss": 0.0408,
1929
+ "step": 320
1930
+ },
1931
+ {
1932
+ "epoch": 1.9,
1933
+ "learning_rate": 1.330780649350938e-07,
1934
+ "loss": 0.0444,
1935
+ "step": 321
1936
+ },
1937
+ {
1938
+ "epoch": 1.91,
1939
+ "learning_rate": 1.1791223773614635e-07,
1940
+ "loss": 0.0568,
1941
+ "step": 322
1942
+ },
1943
+ {
1944
+ "epoch": 1.91,
1945
+ "learning_rate": 1.0365852555447642e-07,
1946
+ "loss": 0.0401,
1947
+ "step": 323
1948
+ },
1949
+ {
1950
+ "epoch": 1.92,
1951
+ "learning_rate": 9.031824400528854e-08,
1952
+ "loss": 0.044,
1953
+ "step": 324
1954
+ },
1955
+ {
1956
+ "epoch": 1.92,
1957
+ "learning_rate": 7.789262439430012e-08,
1958
+ "loss": 0.0446,
1959
+ "step": 325
1960
+ },
1961
+ {
1962
+ "epoch": 1.93,
1963
+ "learning_rate": 6.638281360408339e-08,
1964
+ "loss": 0.039,
1965
+ "step": 326
1966
+ },
1967
+ {
1968
+ "epoch": 1.93,
1969
+ "learning_rate": 5.578987398821345e-08,
1970
+ "loss": 0.0482,
1971
+ "step": 327
1972
+ },
1973
+ {
1974
+ "epoch": 1.94,
1975
+ "learning_rate": 4.6114783273213395e-08,
1976
+ "loss": 0.0474,
1977
+ "step": 328
1978
+ },
1979
+ {
1980
+ "epoch": 1.95,
1981
+ "learning_rate": 3.735843446830867e-08,
1982
+ "loss": 0.0552,
1983
+ "step": 329
1984
+ },
1985
+ {
1986
+ "epoch": 1.95,
1987
+ "learning_rate": 2.9521635783001932e-08,
1988
+ "loss": 0.0462,
1989
+ "step": 330
1990
+ },
1991
+ {
1992
+ "epoch": 1.96,
1993
+ "learning_rate": 2.2605110552477162e-08,
1994
+ "loss": 0.0471,
1995
+ "step": 331
1996
+ },
1997
+ {
1998
+ "epoch": 1.96,
1999
+ "learning_rate": 1.6609497170834154e-08,
2000
+ "loss": 0.0442,
2001
+ "step": 332
2002
+ },
2003
+ {
2004
+ "epoch": 1.97,
2005
+ "learning_rate": 1.1535349032167908e-08,
2006
+ "loss": 0.0472,
2007
+ "step": 333
2008
+ },
2009
+ {
2010
+ "epoch": 1.98,
2011
+ "learning_rate": 7.3831344794872415e-09,
2012
+ "loss": 0.0465,
2013
+ "step": 334
2014
+ },
2015
+ {
2016
+ "epoch": 1.98,
2017
+ "learning_rate": 4.153236761488266e-09,
2018
+ "loss": 0.0512,
2019
+ "step": 335
2020
+ },
2021
+ {
2022
+ "epoch": 1.99,
2023
+ "learning_rate": 1.8459539971804608e-09,
2024
+ "loss": 0.0502,
2025
+ "step": 336
2026
+ },
2027
+ {
2028
+ "epoch": 1.99,
2029
+ "learning_rate": 4.614991483686826e-10,
2030
+ "loss": 0.0502,
2031
+ "step": 337
2032
+ },
2033
+ {
2034
+ "epoch": 2.0,
2035
+ "learning_rate": 0.0,
2036
+ "loss": 0.0527,
2037
+ "step": 338
2038
+ },
2039
+ {
2040
+ "epoch": 2.0,
2041
+ "step": 338,
2042
+ "total_flos": 14257366695936.0,
2043
+ "train_loss": 0.09267861297982331,
2044
+ "train_runtime": 3911.5726,
2045
+ "train_samples_per_second": 9.661,
2046
+ "train_steps_per_second": 0.086
2047
+ }
2048
+ ],
2049
+ "logging_steps": 1.0,
2050
+ "max_steps": 338,
2051
+ "num_input_tokens_seen": 0,
2052
+ "num_train_epochs": 2,
2053
+ "save_steps": 2718,
2054
+ "total_flos": 14257366695936.0,
2055
+ "train_batch_size": 16,
2056
+ "trial_name": null,
2057
+ "trial_params": null
2058
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f76bd9bb6bab8ffbe0e632726489b5cd8ef0fc2a1ad0a240bb9ce19a5b9d9498
3
+ size 6139