Hugging Face's logo

Spaces:
CYF200127
/
RxnIM
Sleeping

App Files Community
CYF200127 commited on
Commit
092aa0d
·
verified ·
1 Parent(s): 3e1d9f3

Upload 12 files

Browse files
Files changed (12) hide show
  1. rxn/model/added_tokens.json +79 -0
  2. rxn/model/all_results.json +7 -0
  3. rxn/model/cfg.py +112 -0
  4. rxn/model/config.json +33 -0
  5. rxn/model/generation_config.json +10 -0
  6. rxn/model/pytorch_model.bin.index.json +873 -0
  7. rxn/model/special_tokens_map.json +24 -0
  8. rxn/model/tokenizer.model +3 -0
  9. rxn/model/tokenizer_config.json +33 -0
  10. rxn/model/train_results.json +7 -0
  11. rxn/model/trainer_state.json +1345 -0
  12. rxn/model/trainer_state.png +0 -0
rxn/model/added_tokens.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<Age>": 32011,
3
+ "<Cnd/ed>": 32007,
4
+ "<Cnd/st>": 32006,
5
+ "<ID_10>": 32025,
6
+ "<ID_11>": 32026,
7
+ "<ID_12>": 32027,
8
+ "<ID_13>": 32028,
9
+ "<ID_14>": 32029,
10
+ "<ID_15>": 32030,
11
+ "<ID_16>": 32031,
12
+ "<ID_17>": 32032,
13
+ "<ID_18>": 32033,
14
+ "<ID_19>": 32034,
15
+ "<ID_1>": 32016,
16
+ "<ID_20>": 32035,
17
+ "<ID_21>": 32036,
18
+ "<ID_22>": 32037,
19
+ "<ID_23>": 32038,
20
+ "<ID_24>": 32039,
21
+ "<ID_25>": 32040,
22
+ "<ID_26>": 32041,
23
+ "<ID_27>": 32042,
24
+ "<ID_28>": 32043,
25
+ "<ID_29>": 32044,
26
+ "<ID_2>": 32017,
27
+ "<ID_30>": 32045,
28
+ "<ID_31>": 32046,
29
+ "<ID_32>": 32047,
30
+ "<ID_33>": 32048,
31
+ "<ID_34>": 32049,
32
+ "<ID_35>": 32050,
33
+ "<ID_36>": 32051,
34
+ "<ID_37>": 32052,
35
+ "<ID_38>": 32053,
36
+ "<ID_39>": 32054,
37
+ "<ID_3>": 32018,
38
+ "<ID_40>": 32055,
39
+ "<ID_41>": 32056,
40
+ "<ID_42>": 32057,
41
+ "<ID_43>": 32058,
42
+ "<ID_44>": 32059,
43
+ "<ID_45>": 32060,
44
+ "<ID_46>": 32061,
45
+ "<ID_47>": 32062,
46
+ "<ID_48>": 32063,
47
+ "<ID_49>": 32064,
48
+ "<ID_4>": 32019,
49
+ "<ID_50>": 32065,
50
+ "<ID_5>": 32020,
51
+ "<ID_6>": 32021,
52
+ "<ID_7>": 32022,
53
+ "<ID_8>": 32023,
54
+ "<ID_9>": 32024,
55
+ "<Obj>": 32015,
56
+ "<Prd/ed>": 32005,
57
+ "<Prd/st>": 32004,
58
+ "<Prd/st> ": 32069,
59
+ "<Rct/ed>": 32003,
60
+ "<Rct/st>": 32002,
61
+ "<Rxn/ed>": 32001,
62
+ "<Rxn/st>": 32000,
63
+ "<Sol>": 32010,
64
+ "<Str>": 32008,
65
+ "<Tem>": 32012,
66
+ "<Tme>": 32013,
67
+ "<Txt>": 32009,
68
+ "<Yld>": 32014,
69
+ "<im_end>": 32068,
70
+ "<im_patch>": 32066,
71
+ "<im_start>": 32067,
72
+ "[Age]": 32073,
73
+ "[Obj]": 32076,
74
+ "[Sol]": 32072,
75
+ "[Str]": 32070,
76
+ "[Tem]": 32074,
77
+ "[Txt]": 32071,
78
+ "[Yld]": 32075
79
+ }
rxn/model/all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 50.0,
3
+ "train_loss": 0.13681490471417254,
4
+ "train_runtime": 4969.2412,
5
+ "train_samples_per_second": 13.865,
6
+ "train_steps_per_second": 0.443
7
+ }
rxn/model/cfg.py ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ DEFAULT_TEST_DATASET = dict(
2
+ flickr=dict(
3
+ filename='./reactiondata/real_test.jsonl',
4
+ image_folder='./reaction_image',
5
+ template_file='./config/_base_/dataset/template/reaction.json',
6
+ type='FlickrDataset'),
7
+ reg=dict(
8
+ filename='./reactiondata/train_OCR.jsonl',
9
+ image_folder='./reaction_image_OCR',
10
+ template_file='./config/_base_/dataset/template/OCR.json',
11
+ type='REGDataset'))
12
+ DEFAULT_TRAIN_DATASET = dict(
13
+ flickr=dict(
14
+ filename='./reactiondata/reaction_real_structed.jsonl',
15
+ image_folder='./reaction_image',
16
+ template_file='./config/_base_/dataset/template/reaction.json',
17
+ type='FlickrDataset'),
18
+ reg=dict(
19
+ filename='./reactiondata/train_OCR.jsonl',
20
+ image_folder='./reaction_image_OCR',
21
+ template_file='./config/_base_/dataset/template/OCR.json',
22
+ type='REGDataset'))
23
+ data_args = dict(
24
+ collator_kwargs=dict(max_length=1024, padding=True),
25
+ compute_metric=None,
26
+ gen_kwargs=dict(max_new_tokens=1024, num_beams=1),
27
+ test=None,
28
+ train=dict(
29
+ cfgs=[
30
+ dict(
31
+ filename='./reactiondata/train_OCR.jsonl',
32
+ image_folder='./reaction_image_OCR',
33
+ template_file='./config/_base_/dataset/template/OCR.json',
34
+ type='REGDataset'),
35
+ dict(
36
+ filename='./reactiondata/reaction_real_structed.jsonl',
37
+ image_folder='./reaction_image',
38
+ template_file='./config/_base_/dataset/template/reaction.json',
39
+ type='FlickrDataset'),
40
+ ],
41
+ probabilities=[
42
+ 0.0,
43
+ 1,
44
+ ],
45
+ seed=None,
46
+ stopping_strategy='first_exhausted',
47
+ type='InterleaveDateset'),
48
+ validation=dict(
49
+ cfgs=[
50
+ dict(
51
+ filename='./reactiondata/real_test.jsonl',
52
+ image_folder='./reaction_image',
53
+ template_file='./config/_base_/dataset/template/reaction.json',
54
+ type='FlickrDataset'),
55
+ ],
56
+ type='ConcatDatasetWithShuffle'))
57
+ model_args = dict(
58
+ cache_dir=None,
59
+ conv_args=dict(
60
+ conv_template='vicuna_v1.1',
61
+ tokenize_kwargs=dict(truncation_size=2048)),
62
+ freeze_backbone=False,
63
+ freeze_mm_mlp_adapter=False,
64
+ gen_kwargs_set_bos_token_id=True,
65
+ gen_kwargs_set_eos_token_id=True,
66
+ gen_kwargs_set_pad_token_id=True,
67
+ image_token_len=300,
68
+ mm_use_im_start_end=True,
69
+ mm_vision_select_layer=-2,
70
+ model_max_length=2048,
71
+ model_name_or_path='./exp/reaction_4.2.1',
72
+ pretrain_mm_mlp_adapter=None,
73
+ process_func_args=dict(
74
+ conv=dict(type='ShikraConvProcess'),
75
+ image=dict(type='ShikraImageProcessor'),
76
+ target=dict(type='BoxFormatProcess'),
77
+ text=dict(type='ShikraTextProcess')),
78
+ sep_image_conv_front=False,
79
+ target_processor=dict(boxes=dict(type='PlainBoxFormatter')),
80
+ tune_mm_mlp_adapter=False,
81
+ type='shikra',
82
+ version='v1',
83
+ vision_tower='SenseTime/deformable-detr')
84
+ training_args = dict(
85
+ bf16=True,
86
+ dataloader_num_workers=4,
87
+ do_eval=False,
88
+ do_predict=False,
89
+ do_train=True,
90
+ evaluation_strategy='no',
91
+ fsdp='full_shard auto_wrap',
92
+ fsdp_transformer_layer_cls_to_wrap='LlamaDecoderLayer',
93
+ gradient_accumulation_steps=1,
94
+ gradient_checkpointing=True,
95
+ learning_rate=2e-05,
96
+ logging_steps=10,
97
+ lr_scheduler_type='cosine',
98
+ num_train_epochs=50,
99
+ output_dir='./exp/reaction_4.2.2-large',
100
+ overwrite_output_dir=False,
101
+ per_device_eval_batch_size=4,
102
+ per_device_train_batch_size=4,
103
+ predict_with_generate=True,
104
+ remove_unused_columns=False,
105
+ report_to='none',
106
+ save_steps=10000,
107
+ save_strategy='steps',
108
+ save_total_limit=1,
109
+ seed=42,
110
+ tf32=True,
111
+ warmup_ratio=0.03,
112
+ weight_decay=0.05)
rxn/model/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./exp/reaction_4.2.1",
3
+ "architectures": [
4
+ "ShikraLlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "freeze_mm_mlp_adapter": false,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 4096,
14
+ "mm_hidden_size": 256,
15
+ "mm_use_im_start_end": true,
16
+ "mm_vision_select_layer": -2,
17
+ "mm_vision_tower": "SenseTime/deformable-detr",
18
+ "model_type": "shikra",
19
+ "num_attention_heads": 32,
20
+ "num_hidden_layers": 32,
21
+ "num_key_value_heads": 32,
22
+ "pad_token_id": 0,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": null,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.28.0.dev0",
29
+ "tune_mm_mlp_adapter": false,
30
+ "use_cache": false,
31
+ "use_mm_proj": true,
32
+ "vocab_size": 32077
33
+ }
rxn/model/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.28.0.dev0"
10
+ }
rxn/model/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,873 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 27120484136
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
268
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
269
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
270
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
271
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
272
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
273
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
274
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
275
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
276
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
277
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
278
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
279
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
280
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
281
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
282
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
283
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
284
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
285
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
286
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
287
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
288
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
289
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
290
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
291
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
292
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
293
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
294
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
295
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
296
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
297
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
298
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
299
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
300
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
301
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
302
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
303
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
304
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
305
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
306
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
307
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
308
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
309
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
310
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
311
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
312
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
313
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
314
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
315
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
316
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
317
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
318
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
319
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
320
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
321
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
322
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
323
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
324
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
325
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
326
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
327
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
328
+ "model.mm_projector.bias": "pytorch_model-00003-of-00003.bin",
329
+ "model.mm_projector.weight": "pytorch_model-00003-of-00003.bin",
330
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin",
331
+ "model.vision_tower.0.backbone.conv_encoder.model.bn1.bias": "pytorch_model-00003-of-00003.bin",
332
+ "model.vision_tower.0.backbone.conv_encoder.model.bn1.running_mean": "pytorch_model-00003-of-00003.bin",
333
+ "model.vision_tower.0.backbone.conv_encoder.model.bn1.running_var": "pytorch_model-00003-of-00003.bin",
334
+ "model.vision_tower.0.backbone.conv_encoder.model.bn1.weight": "pytorch_model-00003-of-00003.bin",
335
+ "model.vision_tower.0.backbone.conv_encoder.model.conv1.weight": "pytorch_model-00003-of-00003.bin",
336
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn1.bias": "pytorch_model-00003-of-00003.bin",
337
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn1.running_mean": "pytorch_model-00003-of-00003.bin",
338
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn1.running_var": "pytorch_model-00003-of-00003.bin",
339
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn1.weight": "pytorch_model-00003-of-00003.bin",
340
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn2.bias": "pytorch_model-00003-of-00003.bin",
341
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn2.running_mean": "pytorch_model-00003-of-00003.bin",
342
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn2.running_var": "pytorch_model-00003-of-00003.bin",
343
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn2.weight": "pytorch_model-00003-of-00003.bin",
344
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn3.bias": "pytorch_model-00003-of-00003.bin",
345
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn3.running_mean": "pytorch_model-00003-of-00003.bin",
346
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn3.running_var": "pytorch_model-00003-of-00003.bin",
347
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.bn3.weight": "pytorch_model-00003-of-00003.bin",
348
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.conv1.weight": "pytorch_model-00003-of-00003.bin",
349
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.conv2.weight": "pytorch_model-00003-of-00003.bin",
350
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.conv3.weight": "pytorch_model-00003-of-00003.bin",
351
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.downsample.0.weight": "pytorch_model-00003-of-00003.bin",
352
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.downsample.1.bias": "pytorch_model-00003-of-00003.bin",
353
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.downsample.1.num_batches_tracked": "pytorch_model-00003-of-00003.bin",
354
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.downsample.1.running_mean": "pytorch_model-00003-of-00003.bin",
355
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.downsample.1.running_var": "pytorch_model-00003-of-00003.bin",
356
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.0.downsample.1.weight": "pytorch_model-00003-of-00003.bin",
357
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn1.bias": "pytorch_model-00003-of-00003.bin",
358
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn1.running_mean": "pytorch_model-00003-of-00003.bin",
359
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn1.running_var": "pytorch_model-00003-of-00003.bin",
360
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn1.weight": "pytorch_model-00003-of-00003.bin",
361
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn2.bias": "pytorch_model-00003-of-00003.bin",
362
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn2.running_mean": "pytorch_model-00003-of-00003.bin",
363
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn2.running_var": "pytorch_model-00003-of-00003.bin",
364
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn2.weight": "pytorch_model-00003-of-00003.bin",
365
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn3.bias": "pytorch_model-00003-of-00003.bin",
366
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn3.running_mean": "pytorch_model-00003-of-00003.bin",
367
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn3.running_var": "pytorch_model-00003-of-00003.bin",
368
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.bn3.weight": "pytorch_model-00003-of-00003.bin",
369
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.conv1.weight": "pytorch_model-00003-of-00003.bin",
370
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.conv2.weight": "pytorch_model-00003-of-00003.bin",
371
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.1.conv3.weight": "pytorch_model-00003-of-00003.bin",
372
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn1.bias": "pytorch_model-00003-of-00003.bin",
373
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn1.running_mean": "pytorch_model-00003-of-00003.bin",
374
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn1.running_var": "pytorch_model-00003-of-00003.bin",
375
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn1.weight": "pytorch_model-00003-of-00003.bin",
376
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn2.bias": "pytorch_model-00003-of-00003.bin",
377
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn2.running_mean": "pytorch_model-00003-of-00003.bin",
378
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn2.running_var": "pytorch_model-00003-of-00003.bin",
379
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn2.weight": "pytorch_model-00003-of-00003.bin",
380
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn3.bias": "pytorch_model-00003-of-00003.bin",
381
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn3.running_mean": "pytorch_model-00003-of-00003.bin",
382
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn3.running_var": "pytorch_model-00003-of-00003.bin",
383
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.bn3.weight": "pytorch_model-00003-of-00003.bin",
384
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.conv1.weight": "pytorch_model-00003-of-00003.bin",
385
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.conv2.weight": "pytorch_model-00003-of-00003.bin",
386
+ "model.vision_tower.0.backbone.conv_encoder.model.layer1.2.conv3.weight": "pytorch_model-00003-of-00003.bin",
387
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn1.bias": "pytorch_model-00003-of-00003.bin",
388
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn1.running_mean": "pytorch_model-00003-of-00003.bin",
389
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn1.running_var": "pytorch_model-00003-of-00003.bin",
390
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn1.weight": "pytorch_model-00003-of-00003.bin",
391
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn2.bias": "pytorch_model-00003-of-00003.bin",
392
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn2.running_mean": "pytorch_model-00003-of-00003.bin",
393
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn2.running_var": "pytorch_model-00003-of-00003.bin",
394
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn2.weight": "pytorch_model-00003-of-00003.bin",
395
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn3.bias": "pytorch_model-00003-of-00003.bin",
396
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn3.running_mean": "pytorch_model-00003-of-00003.bin",
397
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn3.running_var": "pytorch_model-00003-of-00003.bin",
398
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.bn3.weight": "pytorch_model-00003-of-00003.bin",
399
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.conv1.weight": "pytorch_model-00003-of-00003.bin",
400
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.conv2.weight": "pytorch_model-00003-of-00003.bin",
401
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.conv3.weight": "pytorch_model-00003-of-00003.bin",
402
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.downsample.0.weight": "pytorch_model-00003-of-00003.bin",
403
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.downsample.1.bias": "pytorch_model-00003-of-00003.bin",
404
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.downsample.1.num_batches_tracked": "pytorch_model-00003-of-00003.bin",
405
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.downsample.1.running_mean": "pytorch_model-00003-of-00003.bin",
406
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.downsample.1.running_var": "pytorch_model-00003-of-00003.bin",
407
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.0.downsample.1.weight": "pytorch_model-00003-of-00003.bin",
408
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn1.bias": "pytorch_model-00003-of-00003.bin",
409
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn1.running_mean": "pytorch_model-00003-of-00003.bin",
410
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn1.running_var": "pytorch_model-00003-of-00003.bin",
411
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn1.weight": "pytorch_model-00003-of-00003.bin",
412
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn2.bias": "pytorch_model-00003-of-00003.bin",
413
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn2.running_mean": "pytorch_model-00003-of-00003.bin",
414
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn2.running_var": "pytorch_model-00003-of-00003.bin",
415
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn2.weight": "pytorch_model-00003-of-00003.bin",
416
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn3.bias": "pytorch_model-00003-of-00003.bin",
417
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn3.running_mean": "pytorch_model-00003-of-00003.bin",
418
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn3.running_var": "pytorch_model-00003-of-00003.bin",
419
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.bn3.weight": "pytorch_model-00003-of-00003.bin",
420
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.conv1.weight": "pytorch_model-00003-of-00003.bin",
421
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.conv2.weight": "pytorch_model-00003-of-00003.bin",
422
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.1.conv3.weight": "pytorch_model-00003-of-00003.bin",
423
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn1.bias": "pytorch_model-00003-of-00003.bin",
424
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn1.running_mean": "pytorch_model-00003-of-00003.bin",
425
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn1.running_var": "pytorch_model-00003-of-00003.bin",
426
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn1.weight": "pytorch_model-00003-of-00003.bin",
427
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn2.bias": "pytorch_model-00003-of-00003.bin",
428
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn2.running_mean": "pytorch_model-00003-of-00003.bin",
429
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn2.running_var": "pytorch_model-00003-of-00003.bin",
430
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn2.weight": "pytorch_model-00003-of-00003.bin",
431
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn3.bias": "pytorch_model-00003-of-00003.bin",
432
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn3.running_mean": "pytorch_model-00003-of-00003.bin",
433
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn3.running_var": "pytorch_model-00003-of-00003.bin",
434
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.bn3.weight": "pytorch_model-00003-of-00003.bin",
435
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.conv1.weight": "pytorch_model-00003-of-00003.bin",
436
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.conv2.weight": "pytorch_model-00003-of-00003.bin",
437
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.2.conv3.weight": "pytorch_model-00003-of-00003.bin",
438
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn1.bias": "pytorch_model-00003-of-00003.bin",
439
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn1.running_mean": "pytorch_model-00003-of-00003.bin",
440
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn1.running_var": "pytorch_model-00003-of-00003.bin",
441
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn1.weight": "pytorch_model-00003-of-00003.bin",
442
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn2.bias": "pytorch_model-00003-of-00003.bin",
443
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn2.running_mean": "pytorch_model-00003-of-00003.bin",
444
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn2.running_var": "pytorch_model-00003-of-00003.bin",
445
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn2.weight": "pytorch_model-00003-of-00003.bin",
446
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn3.bias": "pytorch_model-00003-of-00003.bin",
447
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn3.running_mean": "pytorch_model-00003-of-00003.bin",
448
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn3.running_var": "pytorch_model-00003-of-00003.bin",
449
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.bn3.weight": "pytorch_model-00003-of-00003.bin",
450
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.conv1.weight": "pytorch_model-00003-of-00003.bin",
451
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.conv2.weight": "pytorch_model-00003-of-00003.bin",
452
+ "model.vision_tower.0.backbone.conv_encoder.model.layer2.3.conv3.weight": "pytorch_model-00003-of-00003.bin",
453
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn1.bias": "pytorch_model-00003-of-00003.bin",
454
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn1.running_mean": "pytorch_model-00003-of-00003.bin",
455
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn1.running_var": "pytorch_model-00003-of-00003.bin",
456
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn1.weight": "pytorch_model-00003-of-00003.bin",
457
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn2.bias": "pytorch_model-00003-of-00003.bin",
458
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn2.running_mean": "pytorch_model-00003-of-00003.bin",
459
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn2.running_var": "pytorch_model-00003-of-00003.bin",
460
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn2.weight": "pytorch_model-00003-of-00003.bin",
461
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn3.bias": "pytorch_model-00003-of-00003.bin",
462
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn3.running_mean": "pytorch_model-00003-of-00003.bin",
463
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn3.running_var": "pytorch_model-00003-of-00003.bin",
464
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.bn3.weight": "pytorch_model-00003-of-00003.bin",
465
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.conv1.weight": "pytorch_model-00003-of-00003.bin",
466
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.conv2.weight": "pytorch_model-00003-of-00003.bin",
467
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.conv3.weight": "pytorch_model-00003-of-00003.bin",
468
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.downsample.0.weight": "pytorch_model-00003-of-00003.bin",
469
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.downsample.1.bias": "pytorch_model-00003-of-00003.bin",
470
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.downsample.1.num_batches_tracked": "pytorch_model-00003-of-00003.bin",
471
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.downsample.1.running_mean": "pytorch_model-00003-of-00003.bin",
472
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.downsample.1.running_var": "pytorch_model-00003-of-00003.bin",
473
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.0.downsample.1.weight": "pytorch_model-00003-of-00003.bin",
474
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn1.bias": "pytorch_model-00003-of-00003.bin",
475
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn1.running_mean": "pytorch_model-00003-of-00003.bin",
476
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn1.running_var": "pytorch_model-00003-of-00003.bin",
477
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn1.weight": "pytorch_model-00003-of-00003.bin",
478
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn2.bias": "pytorch_model-00003-of-00003.bin",
479
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn2.running_mean": "pytorch_model-00003-of-00003.bin",
480
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn2.running_var": "pytorch_model-00003-of-00003.bin",
481
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn2.weight": "pytorch_model-00003-of-00003.bin",
482
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn3.bias": "pytorch_model-00003-of-00003.bin",
483
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn3.running_mean": "pytorch_model-00003-of-00003.bin",
484
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn3.running_var": "pytorch_model-00003-of-00003.bin",
485
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.bn3.weight": "pytorch_model-00003-of-00003.bin",
486
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.conv1.weight": "pytorch_model-00003-of-00003.bin",
487
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.conv2.weight": "pytorch_model-00003-of-00003.bin",
488
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.1.conv3.weight": "pytorch_model-00003-of-00003.bin",
489
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn1.bias": "pytorch_model-00003-of-00003.bin",
490
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn1.running_mean": "pytorch_model-00003-of-00003.bin",
491
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn1.running_var": "pytorch_model-00003-of-00003.bin",
492
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn1.weight": "pytorch_model-00003-of-00003.bin",
493
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn2.bias": "pytorch_model-00003-of-00003.bin",
494
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn2.running_mean": "pytorch_model-00003-of-00003.bin",
495
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn2.running_var": "pytorch_model-00003-of-00003.bin",
496
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn2.weight": "pytorch_model-00003-of-00003.bin",
497
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn3.bias": "pytorch_model-00003-of-00003.bin",
498
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn3.running_mean": "pytorch_model-00003-of-00003.bin",
499
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn3.running_var": "pytorch_model-00003-of-00003.bin",
500
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.bn3.weight": "pytorch_model-00003-of-00003.bin",
501
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.conv1.weight": "pytorch_model-00003-of-00003.bin",
502
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.conv2.weight": "pytorch_model-00003-of-00003.bin",
503
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.2.conv3.weight": "pytorch_model-00003-of-00003.bin",
504
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn1.bias": "pytorch_model-00003-of-00003.bin",
505
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn1.running_mean": "pytorch_model-00003-of-00003.bin",
506
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn1.running_var": "pytorch_model-00003-of-00003.bin",
507
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn1.weight": "pytorch_model-00003-of-00003.bin",
508
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn2.bias": "pytorch_model-00003-of-00003.bin",
509
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn2.running_mean": "pytorch_model-00003-of-00003.bin",
510
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn2.running_var": "pytorch_model-00003-of-00003.bin",
511
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn2.weight": "pytorch_model-00003-of-00003.bin",
512
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn3.bias": "pytorch_model-00003-of-00003.bin",
513
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn3.running_mean": "pytorch_model-00003-of-00003.bin",
514
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn3.running_var": "pytorch_model-00003-of-00003.bin",
515
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.bn3.weight": "pytorch_model-00003-of-00003.bin",
516
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.conv1.weight": "pytorch_model-00003-of-00003.bin",
517
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.conv2.weight": "pytorch_model-00003-of-00003.bin",
518
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.3.conv3.weight": "pytorch_model-00003-of-00003.bin",
519
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn1.bias": "pytorch_model-00003-of-00003.bin",
520
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn1.running_mean": "pytorch_model-00003-of-00003.bin",
521
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn1.running_var": "pytorch_model-00003-of-00003.bin",
522
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn1.weight": "pytorch_model-00003-of-00003.bin",
523
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn2.bias": "pytorch_model-00003-of-00003.bin",
524
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn2.running_mean": "pytorch_model-00003-of-00003.bin",
525
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn2.running_var": "pytorch_model-00003-of-00003.bin",
526
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn2.weight": "pytorch_model-00003-of-00003.bin",
527
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn3.bias": "pytorch_model-00003-of-00003.bin",
528
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn3.running_mean": "pytorch_model-00003-of-00003.bin",
529
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn3.running_var": "pytorch_model-00003-of-00003.bin",
530
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.bn3.weight": "pytorch_model-00003-of-00003.bin",
531
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.conv1.weight": "pytorch_model-00003-of-00003.bin",
532
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.conv2.weight": "pytorch_model-00003-of-00003.bin",
533
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.4.conv3.weight": "pytorch_model-00003-of-00003.bin",
534
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn1.bias": "pytorch_model-00003-of-00003.bin",
535
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn1.running_mean": "pytorch_model-00003-of-00003.bin",
536
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn1.running_var": "pytorch_model-00003-of-00003.bin",
537
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn1.weight": "pytorch_model-00003-of-00003.bin",
538
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn2.bias": "pytorch_model-00003-of-00003.bin",
539
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn2.running_mean": "pytorch_model-00003-of-00003.bin",
540
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn2.running_var": "pytorch_model-00003-of-00003.bin",
541
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn2.weight": "pytorch_model-00003-of-00003.bin",
542
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn3.bias": "pytorch_model-00003-of-00003.bin",
543
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn3.running_mean": "pytorch_model-00003-of-00003.bin",
544
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn3.running_var": "pytorch_model-00003-of-00003.bin",
545
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.bn3.weight": "pytorch_model-00003-of-00003.bin",
546
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.conv1.weight": "pytorch_model-00003-of-00003.bin",
547
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.conv2.weight": "pytorch_model-00003-of-00003.bin",
548
+ "model.vision_tower.0.backbone.conv_encoder.model.layer3.5.conv3.weight": "pytorch_model-00003-of-00003.bin",
549
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn1.bias": "pytorch_model-00003-of-00003.bin",
550
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn1.running_mean": "pytorch_model-00003-of-00003.bin",
551
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn1.running_var": "pytorch_model-00003-of-00003.bin",
552
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn1.weight": "pytorch_model-00003-of-00003.bin",
553
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn2.bias": "pytorch_model-00003-of-00003.bin",
554
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn2.running_mean": "pytorch_model-00003-of-00003.bin",
555
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn2.running_var": "pytorch_model-00003-of-00003.bin",
556
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn2.weight": "pytorch_model-00003-of-00003.bin",
557
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn3.bias": "pytorch_model-00003-of-00003.bin",
558
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn3.running_mean": "pytorch_model-00003-of-00003.bin",
559
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn3.running_var": "pytorch_model-00003-of-00003.bin",
560
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.bn3.weight": "pytorch_model-00003-of-00003.bin",
561
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.conv1.weight": "pytorch_model-00003-of-00003.bin",
562
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.conv2.weight": "pytorch_model-00003-of-00003.bin",
563
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.conv3.weight": "pytorch_model-00003-of-00003.bin",
564
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.downsample.0.weight": "pytorch_model-00003-of-00003.bin",
565
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.downsample.1.bias": "pytorch_model-00003-of-00003.bin",
566
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.downsample.1.num_batches_tracked": "pytorch_model-00003-of-00003.bin",
567
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.downsample.1.running_mean": "pytorch_model-00003-of-00003.bin",
568
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.downsample.1.running_var": "pytorch_model-00003-of-00003.bin",
569
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.0.downsample.1.weight": "pytorch_model-00003-of-00003.bin",
570
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn1.bias": "pytorch_model-00003-of-00003.bin",
571
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn1.running_mean": "pytorch_model-00003-of-00003.bin",
572
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn1.running_var": "pytorch_model-00003-of-00003.bin",
573
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn1.weight": "pytorch_model-00003-of-00003.bin",
574
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn2.bias": "pytorch_model-00003-of-00003.bin",
575
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn2.running_mean": "pytorch_model-00003-of-00003.bin",
576
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn2.running_var": "pytorch_model-00003-of-00003.bin",
577
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn2.weight": "pytorch_model-00003-of-00003.bin",
578
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn3.bias": "pytorch_model-00003-of-00003.bin",
579
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn3.running_mean": "pytorch_model-00003-of-00003.bin",
580
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn3.running_var": "pytorch_model-00003-of-00003.bin",
581
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.bn3.weight": "pytorch_model-00003-of-00003.bin",
582
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.conv1.weight": "pytorch_model-00003-of-00003.bin",
583
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.conv2.weight": "pytorch_model-00003-of-00003.bin",
584
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.1.conv3.weight": "pytorch_model-00003-of-00003.bin",
585
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn1.bias": "pytorch_model-00003-of-00003.bin",
586
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn1.running_mean": "pytorch_model-00003-of-00003.bin",
587
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn1.running_var": "pytorch_model-00003-of-00003.bin",
588
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn1.weight": "pytorch_model-00003-of-00003.bin",
589
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn2.bias": "pytorch_model-00003-of-00003.bin",
590
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn2.running_mean": "pytorch_model-00003-of-00003.bin",
591
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn2.running_var": "pytorch_model-00003-of-00003.bin",
592
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn2.weight": "pytorch_model-00003-of-00003.bin",
593
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn3.bias": "pytorch_model-00003-of-00003.bin",
594
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn3.running_mean": "pytorch_model-00003-of-00003.bin",
595
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn3.running_var": "pytorch_model-00003-of-00003.bin",
596
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.bn3.weight": "pytorch_model-00003-of-00003.bin",
597
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.conv1.weight": "pytorch_model-00003-of-00003.bin",
598
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.conv2.weight": "pytorch_model-00003-of-00003.bin",
599
+ "model.vision_tower.0.backbone.conv_encoder.model.layer4.2.conv3.weight": "pytorch_model-00003-of-00003.bin",
600
+ "model.vision_tower.0.decoder.layers.0.encoder_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin",
601
+ "model.vision_tower.0.decoder.layers.0.encoder_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin",
602
+ "model.vision_tower.0.decoder.layers.0.encoder_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin",
603
+ "model.vision_tower.0.decoder.layers.0.encoder_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin",
604
+ "model.vision_tower.0.decoder.layers.0.encoder_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin",
605
+ "model.vision_tower.0.decoder.layers.0.encoder_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin",
606
+ "model.vision_tower.0.decoder.layers.0.encoder_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin",
607
+ "model.vision_tower.0.decoder.layers.0.encoder_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin",
608
+ "model.vision_tower.0.decoder.layers.0.encoder_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
609
+ "model.vision_tower.0.decoder.layers.0.encoder_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
610
+ "model.vision_tower.0.decoder.layers.0.fc1.bias": "pytorch_model-00003-of-00003.bin",
611
+ "model.vision_tower.0.decoder.layers.0.fc1.weight": "pytorch_model-00003-of-00003.bin",
612
+ "model.vision_tower.0.decoder.layers.0.fc2.bias": "pytorch_model-00003-of-00003.bin",
613
+ "model.vision_tower.0.decoder.layers.0.fc2.weight": "pytorch_model-00003-of-00003.bin",
614
+ "model.vision_tower.0.decoder.layers.0.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
615
+ "model.vision_tower.0.decoder.layers.0.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
616
+ "model.vision_tower.0.decoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
617
+ "model.vision_tower.0.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
618
+ "model.vision_tower.0.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
619
+ "model.vision_tower.0.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
620
+ "model.vision_tower.0.decoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
621
+ "model.vision_tower.0.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
622
+ "model.vision_tower.0.decoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
623
+ "model.vision_tower.0.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
624
+ "model.vision_tower.0.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
625
+ "model.vision_tower.0.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
626
+ "model.vision_tower.0.decoder.layers.1.encoder_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin",
627
+ "model.vision_tower.0.decoder.layers.1.encoder_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin",
628
+ "model.vision_tower.0.decoder.layers.1.encoder_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin",
629
+ "model.vision_tower.0.decoder.layers.1.encoder_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin",
630
+ "model.vision_tower.0.decoder.layers.1.encoder_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin",
631
+ "model.vision_tower.0.decoder.layers.1.encoder_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin",
632
+ "model.vision_tower.0.decoder.layers.1.encoder_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin",
633
+ "model.vision_tower.0.decoder.layers.1.encoder_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin",
634
+ "model.vision_tower.0.decoder.layers.1.encoder_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
635
+ "model.vision_tower.0.decoder.layers.1.encoder_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
636
+ "model.vision_tower.0.decoder.layers.1.fc1.bias": "pytorch_model-00003-of-00003.bin",
637
+ "model.vision_tower.0.decoder.layers.1.fc1.weight": "pytorch_model-00003-of-00003.bin",
638
+ "model.vision_tower.0.decoder.layers.1.fc2.bias": "pytorch_model-00003-of-00003.bin",
639
+ "model.vision_tower.0.decoder.layers.1.fc2.weight": "pytorch_model-00003-of-00003.bin",
640
+ "model.vision_tower.0.decoder.layers.1.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
641
+ "model.vision_tower.0.decoder.layers.1.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
642
+ "model.vision_tower.0.decoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
643
+ "model.vision_tower.0.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
644
+ "model.vision_tower.0.decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
645
+ "model.vision_tower.0.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
646
+ "model.vision_tower.0.decoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
647
+ "model.vision_tower.0.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
648
+ "model.vision_tower.0.decoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
649
+ "model.vision_tower.0.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
650
+ "model.vision_tower.0.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
651
+ "model.vision_tower.0.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
652
+ "model.vision_tower.0.decoder.layers.2.encoder_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin",
653
+ "model.vision_tower.0.decoder.layers.2.encoder_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin",
654
+ "model.vision_tower.0.decoder.layers.2.encoder_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin",
655
+ "model.vision_tower.0.decoder.layers.2.encoder_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin",
656
+ "model.vision_tower.0.decoder.layers.2.encoder_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin",
657
+ "model.vision_tower.0.decoder.layers.2.encoder_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin",
658
+ "model.vision_tower.0.decoder.layers.2.encoder_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin",
659
+ "model.vision_tower.0.decoder.layers.2.encoder_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin",
660
+ "model.vision_tower.0.decoder.layers.2.encoder_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
661
+ "model.vision_tower.0.decoder.layers.2.encoder_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
662
+ "model.vision_tower.0.decoder.layers.2.fc1.bias": "pytorch_model-00003-of-00003.bin",
663
+ "model.vision_tower.0.decoder.layers.2.fc1.weight": "pytorch_model-00003-of-00003.bin",
664
+ "model.vision_tower.0.decoder.layers.2.fc2.bias": "pytorch_model-00003-of-00003.bin",
665
+ "model.vision_tower.0.decoder.layers.2.fc2.weight": "pytorch_model-00003-of-00003.bin",
666
+ "model.vision_tower.0.decoder.layers.2.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
667
+ "model.vision_tower.0.decoder.layers.2.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
668
+ "model.vision_tower.0.decoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
669
+ "model.vision_tower.0.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
670
+ "model.vision_tower.0.decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
671
+ "model.vision_tower.0.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
672
+ "model.vision_tower.0.decoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
673
+ "model.vision_tower.0.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
674
+ "model.vision_tower.0.decoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
675
+ "model.vision_tower.0.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
676
+ "model.vision_tower.0.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
677
+ "model.vision_tower.0.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
678
+ "model.vision_tower.0.decoder.layers.3.encoder_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin",
679
+ "model.vision_tower.0.decoder.layers.3.encoder_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin",
680
+ "model.vision_tower.0.decoder.layers.3.encoder_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin",
681
+ "model.vision_tower.0.decoder.layers.3.encoder_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin",
682
+ "model.vision_tower.0.decoder.layers.3.encoder_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin",
683
+ "model.vision_tower.0.decoder.layers.3.encoder_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin",
684
+ "model.vision_tower.0.decoder.layers.3.encoder_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin",
685
+ "model.vision_tower.0.decoder.layers.3.encoder_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin",
686
+ "model.vision_tower.0.decoder.layers.3.encoder_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
687
+ "model.vision_tower.0.decoder.layers.3.encoder_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
688
+ "model.vision_tower.0.decoder.layers.3.fc1.bias": "pytorch_model-00003-of-00003.bin",
689
+ "model.vision_tower.0.decoder.layers.3.fc1.weight": "pytorch_model-00003-of-00003.bin",
690
+ "model.vision_tower.0.decoder.layers.3.fc2.bias": "pytorch_model-00003-of-00003.bin",
691
+ "model.vision_tower.0.decoder.layers.3.fc2.weight": "pytorch_model-00003-of-00003.bin",
692
+ "model.vision_tower.0.decoder.layers.3.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
693
+ "model.vision_tower.0.decoder.layers.3.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
694
+ "model.vision_tower.0.decoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
695
+ "model.vision_tower.0.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
696
+ "model.vision_tower.0.decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
697
+ "model.vision_tower.0.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
698
+ "model.vision_tower.0.decoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
699
+ "model.vision_tower.0.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
700
+ "model.vision_tower.0.decoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
701
+ "model.vision_tower.0.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
702
+ "model.vision_tower.0.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
703
+ "model.vision_tower.0.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
704
+ "model.vision_tower.0.decoder.layers.4.encoder_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin",
705
+ "model.vision_tower.0.decoder.layers.4.encoder_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin",
706
+ "model.vision_tower.0.decoder.layers.4.encoder_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin",
707
+ "model.vision_tower.0.decoder.layers.4.encoder_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin",
708
+ "model.vision_tower.0.decoder.layers.4.encoder_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin",
709
+ "model.vision_tower.0.decoder.layers.4.encoder_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin",
710
+ "model.vision_tower.0.decoder.layers.4.encoder_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin",
711
+ "model.vision_tower.0.decoder.layers.4.encoder_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin",
712
+ "model.vision_tower.0.decoder.layers.4.encoder_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
713
+ "model.vision_tower.0.decoder.layers.4.encoder_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
714
+ "model.vision_tower.0.decoder.layers.4.fc1.bias": "pytorch_model-00003-of-00003.bin",
715
+ "model.vision_tower.0.decoder.layers.4.fc1.weight": "pytorch_model-00003-of-00003.bin",
716
+ "model.vision_tower.0.decoder.layers.4.fc2.bias": "pytorch_model-00003-of-00003.bin",
717
+ "model.vision_tower.0.decoder.layers.4.fc2.weight": "pytorch_model-00003-of-00003.bin",
718
+ "model.vision_tower.0.decoder.layers.4.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
719
+ "model.vision_tower.0.decoder.layers.4.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
720
+ "model.vision_tower.0.decoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
721
+ "model.vision_tower.0.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
722
+ "model.vision_tower.0.decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
723
+ "model.vision_tower.0.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
724
+ "model.vision_tower.0.decoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
725
+ "model.vision_tower.0.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
726
+ "model.vision_tower.0.decoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
727
+ "model.vision_tower.0.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
728
+ "model.vision_tower.0.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
729
+ "model.vision_tower.0.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
730
+ "model.vision_tower.0.decoder.layers.5.encoder_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin",
731
+ "model.vision_tower.0.decoder.layers.5.encoder_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin",
732
+ "model.vision_tower.0.decoder.layers.5.encoder_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin",
733
+ "model.vision_tower.0.decoder.layers.5.encoder_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin",
734
+ "model.vision_tower.0.decoder.layers.5.encoder_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin",
735
+ "model.vision_tower.0.decoder.layers.5.encoder_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin",
736
+ "model.vision_tower.0.decoder.layers.5.encoder_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin",
737
+ "model.vision_tower.0.decoder.layers.5.encoder_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin",
738
+ "model.vision_tower.0.decoder.layers.5.encoder_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
739
+ "model.vision_tower.0.decoder.layers.5.encoder_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
740
+ "model.vision_tower.0.decoder.layers.5.fc1.bias": "pytorch_model-00003-of-00003.bin",
741
+ "model.vision_tower.0.decoder.layers.5.fc1.weight": "pytorch_model-00003-of-00003.bin",
742
+ "model.vision_tower.0.decoder.layers.5.fc2.bias": "pytorch_model-00003-of-00003.bin",
743
+ "model.vision_tower.0.decoder.layers.5.fc2.weight": "pytorch_model-00003-of-00003.bin",
744
+ "model.vision_tower.0.decoder.layers.5.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
745
+ "model.vision_tower.0.decoder.layers.5.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
746
+ "model.vision_tower.0.decoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
747
+ "model.vision_tower.0.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
748
+ "model.vision_tower.0.decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
749
+ "model.vision_tower.0.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
750
+ "model.vision_tower.0.decoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
751
+ "model.vision_tower.0.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
752
+ "model.vision_tower.0.decoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
753
+ "model.vision_tower.0.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
754
+ "model.vision_tower.0.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
755
+ "model.vision_tower.0.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
756
+ "model.vision_tower.0.encoder.layers.0.fc1.bias": "pytorch_model-00003-of-00003.bin",
757
+ "model.vision_tower.0.encoder.layers.0.fc1.weight": "pytorch_model-00003-of-00003.bin",
758
+ "model.vision_tower.0.encoder.layers.0.fc2.bias": "pytorch_model-00003-of-00003.bin",
759
+ "model.vision_tower.0.encoder.layers.0.fc2.weight": "pytorch_model-00003-of-00003.bin",
760
+ "model.vision_tower.0.encoder.layers.0.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
761
+ "model.vision_tower.0.encoder.layers.0.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
762
+ "model.vision_tower.0.encoder.layers.0.self_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin",
763
+ "model.vision_tower.0.encoder.layers.0.self_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin",
764
+ "model.vision_tower.0.encoder.layers.0.self_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin",
765
+ "model.vision_tower.0.encoder.layers.0.self_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin",
766
+ "model.vision_tower.0.encoder.layers.0.self_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin",
767
+ "model.vision_tower.0.encoder.layers.0.self_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin",
768
+ "model.vision_tower.0.encoder.layers.0.self_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin",
769
+ "model.vision_tower.0.encoder.layers.0.self_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin",
770
+ "model.vision_tower.0.encoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
771
+ "model.vision_tower.0.encoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
772
+ "model.vision_tower.0.encoder.layers.1.fc1.bias": "pytorch_model-00003-of-00003.bin",
773
+ "model.vision_tower.0.encoder.layers.1.fc1.weight": "pytorch_model-00003-of-00003.bin",
774
+ "model.vision_tower.0.encoder.layers.1.fc2.bias": "pytorch_model-00003-of-00003.bin",
775
+ "model.vision_tower.0.encoder.layers.1.fc2.weight": "pytorch_model-00003-of-00003.bin",
776
+ "model.vision_tower.0.encoder.layers.1.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
777
+ "model.vision_tower.0.encoder.layers.1.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
778
+ "model.vision_tower.0.encoder.layers.1.self_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin",
779
+ "model.vision_tower.0.encoder.layers.1.self_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin",
780
+ "model.vision_tower.0.encoder.layers.1.self_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin",
781
+ "model.vision_tower.0.encoder.layers.1.self_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin",
782
+ "model.vision_tower.0.encoder.layers.1.self_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin",
783
+ "model.vision_tower.0.encoder.layers.1.self_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin",
784
+ "model.vision_tower.0.encoder.layers.1.self_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin",
785
+ "model.vision_tower.0.encoder.layers.1.self_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin",
786
+ "model.vision_tower.0.encoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
787
+ "model.vision_tower.0.encoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
788
+ "model.vision_tower.0.encoder.layers.2.fc1.bias": "pytorch_model-00003-of-00003.bin",
789
+ "model.vision_tower.0.encoder.layers.2.fc1.weight": "pytorch_model-00003-of-00003.bin",
790
+ "model.vision_tower.0.encoder.layers.2.fc2.bias": "pytorch_model-00003-of-00003.bin",
791
+ "model.vision_tower.0.encoder.layers.2.fc2.weight": "pytorch_model-00003-of-00003.bin",
792
+ "model.vision_tower.0.encoder.layers.2.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
793
+ "model.vision_tower.0.encoder.layers.2.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
794
+ "model.vision_tower.0.encoder.layers.2.self_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin",
795
+ "model.vision_tower.0.encoder.layers.2.self_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin",
796
+ "model.vision_tower.0.encoder.layers.2.self_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin",
797
+ "model.vision_tower.0.encoder.layers.2.self_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin",
798
+ "model.vision_tower.0.encoder.layers.2.self_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin",
799
+ "model.vision_tower.0.encoder.layers.2.self_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin",
800
+ "model.vision_tower.0.encoder.layers.2.self_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin",
801
+ "model.vision_tower.0.encoder.layers.2.self_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin",
802
+ "model.vision_tower.0.encoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
803
+ "model.vision_tower.0.encoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
804
+ "model.vision_tower.0.encoder.layers.3.fc1.bias": "pytorch_model-00003-of-00003.bin",
805
+ "model.vision_tower.0.encoder.layers.3.fc1.weight": "pytorch_model-00003-of-00003.bin",
806
+ "model.vision_tower.0.encoder.layers.3.fc2.bias": "pytorch_model-00003-of-00003.bin",
807
+ "model.vision_tower.0.encoder.layers.3.fc2.weight": "pytorch_model-00003-of-00003.bin",
808
+ "model.vision_tower.0.encoder.layers.3.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
809
+ "model.vision_tower.0.encoder.layers.3.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
810
+ "model.vision_tower.0.encoder.layers.3.self_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin",
811
+ "model.vision_tower.0.encoder.layers.3.self_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin",
812
+ "model.vision_tower.0.encoder.layers.3.self_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin",
813
+ "model.vision_tower.0.encoder.layers.3.self_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin",
814
+ "model.vision_tower.0.encoder.layers.3.self_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin",
815
+ "model.vision_tower.0.encoder.layers.3.self_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin",
816
+ "model.vision_tower.0.encoder.layers.3.self_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin",
817
+ "model.vision_tower.0.encoder.layers.3.self_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin",
818
+ "model.vision_tower.0.encoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
819
+ "model.vision_tower.0.encoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
820
+ "model.vision_tower.0.encoder.layers.4.fc1.bias": "pytorch_model-00003-of-00003.bin",
821
+ "model.vision_tower.0.encoder.layers.4.fc1.weight": "pytorch_model-00003-of-00003.bin",
822
+ "model.vision_tower.0.encoder.layers.4.fc2.bias": "pytorch_model-00003-of-00003.bin",
823
+ "model.vision_tower.0.encoder.layers.4.fc2.weight": "pytorch_model-00003-of-00003.bin",
824
+ "model.vision_tower.0.encoder.layers.4.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
825
+ "model.vision_tower.0.encoder.layers.4.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
826
+ "model.vision_tower.0.encoder.layers.4.self_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin",
827
+ "model.vision_tower.0.encoder.layers.4.self_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin",
828
+ "model.vision_tower.0.encoder.layers.4.self_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin",
829
+ "model.vision_tower.0.encoder.layers.4.self_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin",
830
+ "model.vision_tower.0.encoder.layers.4.self_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin",
831
+ "model.vision_tower.0.encoder.layers.4.self_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin",
832
+ "model.vision_tower.0.encoder.layers.4.self_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin",
833
+ "model.vision_tower.0.encoder.layers.4.self_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin",
834
+ "model.vision_tower.0.encoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
835
+ "model.vision_tower.0.encoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
836
+ "model.vision_tower.0.encoder.layers.5.fc1.bias": "pytorch_model-00003-of-00003.bin",
837
+ "model.vision_tower.0.encoder.layers.5.fc1.weight": "pytorch_model-00003-of-00003.bin",
838
+ "model.vision_tower.0.encoder.layers.5.fc2.bias": "pytorch_model-00003-of-00003.bin",
839
+ "model.vision_tower.0.encoder.layers.5.fc2.weight": "pytorch_model-00003-of-00003.bin",
840
+ "model.vision_tower.0.encoder.layers.5.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
841
+ "model.vision_tower.0.encoder.layers.5.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
842
+ "model.vision_tower.0.encoder.layers.5.self_attn.attention_weights.bias": "pytorch_model-00003-of-00003.bin",
843
+ "model.vision_tower.0.encoder.layers.5.self_attn.attention_weights.weight": "pytorch_model-00003-of-00003.bin",
844
+ "model.vision_tower.0.encoder.layers.5.self_attn.output_proj.bias": "pytorch_model-00003-of-00003.bin",
845
+ "model.vision_tower.0.encoder.layers.5.self_attn.output_proj.weight": "pytorch_model-00003-of-00003.bin",
846
+ "model.vision_tower.0.encoder.layers.5.self_attn.sampling_offsets.bias": "pytorch_model-00003-of-00003.bin",
847
+ "model.vision_tower.0.encoder.layers.5.self_attn.sampling_offsets.weight": "pytorch_model-00003-of-00003.bin",
848
+ "model.vision_tower.0.encoder.layers.5.self_attn.value_proj.bias": "pytorch_model-00003-of-00003.bin",
849
+ "model.vision_tower.0.encoder.layers.5.self_attn.value_proj.weight": "pytorch_model-00003-of-00003.bin",
850
+ "model.vision_tower.0.encoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
851
+ "model.vision_tower.0.encoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
852
+ "model.vision_tower.0.input_proj.0.0.bias": "pytorch_model-00003-of-00003.bin",
853
+ "model.vision_tower.0.input_proj.0.0.weight": "pytorch_model-00003-of-00003.bin",
854
+ "model.vision_tower.0.input_proj.0.1.bias": "pytorch_model-00003-of-00003.bin",
855
+ "model.vision_tower.0.input_proj.0.1.weight": "pytorch_model-00003-of-00003.bin",
856
+ "model.vision_tower.0.input_proj.1.0.bias": "pytorch_model-00003-of-00003.bin",
857
+ "model.vision_tower.0.input_proj.1.0.weight": "pytorch_model-00003-of-00003.bin",
858
+ "model.vision_tower.0.input_proj.1.1.bias": "pytorch_model-00003-of-00003.bin",
859
+ "model.vision_tower.0.input_proj.1.1.weight": "pytorch_model-00003-of-00003.bin",
860
+ "model.vision_tower.0.input_proj.2.0.bias": "pytorch_model-00003-of-00003.bin",
861
+ "model.vision_tower.0.input_proj.2.0.weight": "pytorch_model-00003-of-00003.bin",
862
+ "model.vision_tower.0.input_proj.2.1.bias": "pytorch_model-00003-of-00003.bin",
863
+ "model.vision_tower.0.input_proj.2.1.weight": "pytorch_model-00003-of-00003.bin",
864
+ "model.vision_tower.0.input_proj.3.0.bias": "pytorch_model-00003-of-00003.bin",
865
+ "model.vision_tower.0.input_proj.3.0.weight": "pytorch_model-00003-of-00003.bin",
866
+ "model.vision_tower.0.input_proj.3.1.bias": "pytorch_model-00003-of-00003.bin",
867
+ "model.vision_tower.0.input_proj.3.1.weight": "pytorch_model-00003-of-00003.bin",
868
+ "model.vision_tower.0.level_embed": "pytorch_model-00003-of-00003.bin",
869
+ "model.vision_tower.0.query_position_embeddings.weight": "pytorch_model-00003-of-00003.bin",
870
+ "model.vision_tower.0.reference_points.bias": "pytorch_model-00003-of-00003.bin",
871
+ "model.vision_tower.0.reference_points.weight": "pytorch_model-00003-of-00003.bin"
872
+ }
873
+ }
rxn/model/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
+ }
rxn/model/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
rxn/model/tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 2048,
21
+ "pad_token": null,
22
+ "padding_side": "right",
23
+ "special_tokens_map_file": "llama2-7b/special_tokens_map.json",
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
rxn/model/train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 50.0,
3
+ "train_loss": 0.13681490471417254,
4
+ "train_runtime": 4969.2412,
5
+ "train_samples_per_second": 13.865,
6
+ "train_steps_per_second": 0.443
7
+ }
rxn/model/trainer_state.json ADDED
@@ -0,0 +1,1345 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 50.0,
5
+ "global_step": 2200,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.23,
12
+ "learning_rate": 3.0303030303030305e-06,
13
+ "loss": 1.7297,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.45,
18
+ "learning_rate": 6.060606060606061e-06,
19
+ "loss": 0.9422,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.68,
24
+ "learning_rate": 9.090909090909091e-06,
25
+ "loss": 0.7053,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.91,
30
+ "learning_rate": 1.2121212121212122e-05,
31
+ "loss": 0.6722,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 1.14,
36
+ "learning_rate": 1.5151515151515153e-05,
37
+ "loss": 0.6335,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 1.36,
42
+ "learning_rate": 1.8181818181818182e-05,
43
+ "loss": 0.6203,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 1.59,
48
+ "learning_rate": 1.999982661974106e-05,
49
+ "loss": 0.6116,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 1.82,
54
+ "learning_rate": 1.9997876160873005e-05,
55
+ "loss": 0.6105,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 2.05,
60
+ "learning_rate": 1.9993758941929738e-05,
61
+ "loss": 0.5888,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 2.27,
66
+ "learning_rate": 1.9987475855203325e-05,
67
+ "loss": 0.5663,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 2.5,
72
+ "learning_rate": 1.997902826237712e-05,
73
+ "loss": 0.5533,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 2.73,
78
+ "learning_rate": 1.9968417994230628e-05,
79
+ "loss": 0.5662,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 2.95,
84
+ "learning_rate": 1.9955647350242765e-05,
85
+ "loss": 0.5717,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 3.18,
90
+ "learning_rate": 1.99407190980935e-05,
91
+ "loss": 0.5193,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 3.41,
96
+ "learning_rate": 1.9923636473064024e-05,
97
+ "loss": 0.4847,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 3.64,
102
+ "learning_rate": 1.990440317733561e-05,
103
+ "loss": 0.4733,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 3.86,
108
+ "learning_rate": 1.9883023379187267e-05,
109
+ "loss": 0.4801,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 4.09,
114
+ "learning_rate": 1.9859501712092374e-05,
115
+ "loss": 0.4299,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 4.32,
120
+ "learning_rate": 1.9833843273714506e-05,
121
+ "loss": 0.3846,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 4.55,
126
+ "learning_rate": 1.9806053624802667e-05,
127
+ "loss": 0.3733,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 4.77,
132
+ "learning_rate": 1.9776138787986137e-05,
133
+ "loss": 0.3646,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 5.0,
138
+ "learning_rate": 1.9744105246469264e-05,
139
+ "loss": 0.4011,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 5.23,
144
+ "learning_rate": 1.9709959942626366e-05,
145
+ "loss": 0.3151,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 5.45,
150
+ "learning_rate": 1.9673710276497207e-05,
151
+ "loss": 0.2784,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 5.68,
156
+ "learning_rate": 1.9635364104183236e-05,
157
+ "loss": 0.3248,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 5.91,
162
+ "learning_rate": 1.9594929736144978e-05,
163
+ "loss": 0.3083,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 6.14,
168
+ "learning_rate": 1.955241593540098e-05,
169
+ "loss": 0.2681,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 6.36,
174
+ "learning_rate": 1.9507831915628706e-05,
175
+ "loss": 0.2364,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 6.59,
180
+ "learning_rate": 1.9461187339167673e-05,
181
+ "loss": 0.2565,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 6.82,
186
+ "learning_rate": 1.9412492314925453e-05,
187
+ "loss": 0.2661,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 7.05,
192
+ "learning_rate": 1.9361757396186834e-05,
193
+ "loss": 0.2562,
194
+ "step": 310
195
+ },
196
+ {
197
+ "epoch": 7.27,
198
+ "learning_rate": 1.9308993578326688e-05,
199
+ "loss": 0.2189,
200
+ "step": 320
201
+ },
202
+ {
203
+ "epoch": 7.5,
204
+ "learning_rate": 1.9254212296427043e-05,
205
+ "loss": 0.1989,
206
+ "step": 330
207
+ },
208
+ {
209
+ "epoch": 7.73,
210
+ "learning_rate": 1.9197425422798832e-05,
211
+ "loss": 0.2321,
212
+ "step": 340
213
+ },
214
+ {
215
+ "epoch": 7.95,
216
+ "learning_rate": 1.9138645264408917e-05,
217
+ "loss": 0.229,
218
+ "step": 350
219
+ },
220
+ {
221
+ "epoch": 8.18,
222
+ "learning_rate": 1.9077884560212885e-05,
223
+ "loss": 0.1959,
224
+ "step": 360
225
+ },
226
+ {
227
+ "epoch": 8.41,
228
+ "learning_rate": 1.901515647839425e-05,
229
+ "loss": 0.1936,
230
+ "step": 370
231
+ },
232
+ {
233
+ "epoch": 8.64,
234
+ "learning_rate": 1.8950474613510605e-05,
235
+ "loss": 0.1907,
236
+ "step": 380
237
+ },
238
+ {
239
+ "epoch": 8.86,
240
+ "learning_rate": 1.8883852983547383e-05,
241
+ "loss": 0.1959,
242
+ "step": 390
243
+ },
244
+ {
245
+ "epoch": 9.09,
246
+ "learning_rate": 1.8815306026879854e-05,
247
+ "loss": 0.1852,
248
+ "step": 400
249
+ },
250
+ {
251
+ "epoch": 9.32,
252
+ "learning_rate": 1.8744848599144027e-05,
253
+ "loss": 0.1823,
254
+ "step": 410
255
+ },
256
+ {
257
+ "epoch": 9.55,
258
+ "learning_rate": 1.8672495970017067e-05,
259
+ "loss": 0.154,
260
+ "step": 420
261
+ },
262
+ {
263
+ "epoch": 9.77,
264
+ "learning_rate": 1.859826381990806e-05,
265
+ "loss": 0.1764,
266
+ "step": 430
267
+ },
268
+ {
269
+ "epoch": 10.0,
270
+ "learning_rate": 1.8522168236559693e-05,
271
+ "loss": 0.1748,
272
+ "step": 440
273
+ },
274
+ {
275
+ "epoch": 10.23,
276
+ "learning_rate": 1.8444225711561713e-05,
277
+ "loss": 0.139,
278
+ "step": 450
279
+ },
280
+ {
281
+ "epoch": 10.45,
282
+ "learning_rate": 1.83644531367768e-05,
283
+ "loss": 0.1648,
284
+ "step": 460
285
+ },
286
+ {
287
+ "epoch": 10.68,
288
+ "learning_rate": 1.8282867800679774e-05,
289
+ "loss": 0.1677,
290
+ "step": 470
291
+ },
292
+ {
293
+ "epoch": 10.91,
294
+ "learning_rate": 1.8199487384610758e-05,
295
+ "loss": 0.1728,
296
+ "step": 480
297
+ },
298
+ {
299
+ "epoch": 11.14,
300
+ "learning_rate": 1.8114329958943272e-05,
301
+ "loss": 0.1436,
302
+ "step": 490
303
+ },
304
+ {
305
+ "epoch": 11.36,
306
+ "learning_rate": 1.8027413979167968e-05,
307
+ "loss": 0.1336,
308
+ "step": 500
309
+ },
310
+ {
311
+ "epoch": 11.59,
312
+ "learning_rate": 1.7938758281892928e-05,
313
+ "loss": 0.1426,
314
+ "step": 510
315
+ },
316
+ {
317
+ "epoch": 11.82,
318
+ "learning_rate": 1.7848382080761343e-05,
319
+ "loss": 0.1725,
320
+ "step": 520
321
+ },
322
+ {
323
+ "epoch": 12.05,
324
+ "learning_rate": 1.775630496228752e-05,
325
+ "loss": 0.1362,
326
+ "step": 530
327
+ },
328
+ {
329
+ "epoch": 12.27,
330
+ "learning_rate": 1.766254688161202e-05,
331
+ "loss": 0.1287,
332
+ "step": 540
333
+ },
334
+ {
335
+ "epoch": 12.5,
336
+ "learning_rate": 1.7567128158176955e-05,
337
+ "loss": 0.1219,
338
+ "step": 550
339
+ },
340
+ {
341
+ "epoch": 12.73,
342
+ "learning_rate": 1.7470069471322325e-05,
343
+ "loss": 0.1456,
344
+ "step": 560
345
+ },
346
+ {
347
+ "epoch": 12.95,
348
+ "learning_rate": 1.737139185580434e-05,
349
+ "loss": 0.1376,
350
+ "step": 570
351
+ },
352
+ {
353
+ "epoch": 13.18,
354
+ "learning_rate": 1.7271116697236717e-05,
355
+ "loss": 0.1209,
356
+ "step": 580
357
+ },
358
+ {
359
+ "epoch": 13.41,
360
+ "learning_rate": 1.7169265727455964e-05,
361
+ "loss": 0.1316,
362
+ "step": 590
363
+ },
364
+ {
365
+ "epoch": 13.64,
366
+ "learning_rate": 1.7065861019811598e-05,
367
+ "loss": 0.1296,
368
+ "step": 600
369
+ },
370
+ {
371
+ "epoch": 13.86,
372
+ "learning_rate": 1.6960924984382373e-05,
373
+ "loss": 0.1359,
374
+ "step": 610
375
+ },
376
+ {
377
+ "epoch": 14.09,
378
+ "learning_rate": 1.685448036311951e-05,
379
+ "loss": 0.1123,
380
+ "step": 620
381
+ },
382
+ {
383
+ "epoch": 14.32,
384
+ "learning_rate": 1.6746550224918032e-05,
385
+ "loss": 0.1227,
386
+ "step": 630
387
+ },
388
+ {
389
+ "epoch": 14.55,
390
+ "learning_rate": 1.663715796061722e-05,
391
+ "loss": 0.1282,
392
+ "step": 640
393
+ },
394
+ {
395
+ "epoch": 14.77,
396
+ "learning_rate": 1.6526327277931278e-05,
397
+ "loss": 0.1055,
398
+ "step": 650
399
+ },
400
+ {
401
+ "epoch": 15.0,
402
+ "learning_rate": 1.6414082196311402e-05,
403
+ "loss": 0.1288,
404
+ "step": 660
405
+ },
406
+ {
407
+ "epoch": 15.23,
408
+ "learning_rate": 1.630044704174018e-05,
409
+ "loss": 0.1145,
410
+ "step": 670
411
+ },
412
+ {
413
+ "epoch": 15.45,
414
+ "learning_rate": 1.6185446441459652e-05,
415
+ "loss": 0.1158,
416
+ "step": 680
417
+ },
418
+ {
419
+ "epoch": 15.68,
420
+ "learning_rate": 1.6069105318634024e-05,
421
+ "loss": 0.1119,
422
+ "step": 690
423
+ },
424
+ {
425
+ "epoch": 15.91,
426
+ "learning_rate": 1.5951448886948286e-05,
427
+ "loss": 0.1119,
428
+ "step": 700
429
+ },
430
+ {
431
+ "epoch": 16.14,
432
+ "learning_rate": 1.5832502645143837e-05,
433
+ "loss": 0.0981,
434
+ "step": 710
435
+ },
436
+ {
437
+ "epoch": 16.36,
438
+ "learning_rate": 1.571229237149235e-05,
439
+ "loss": 0.1142,
440
+ "step": 720
441
+ },
442
+ {
443
+ "epoch": 16.59,
444
+ "learning_rate": 1.5590844118209055e-05,
445
+ "loss": 0.1054,
446
+ "step": 730
447
+ },
448
+ {
449
+ "epoch": 16.82,
450
+ "learning_rate": 1.5468184205806646e-05,
451
+ "loss": 0.1012,
452
+ "step": 740
453
+ },
454
+ {
455
+ "epoch": 17.05,
456
+ "learning_rate": 1.534433921739105e-05,
457
+ "loss": 0.1047,
458
+ "step": 750
459
+ },
460
+ {
461
+ "epoch": 17.27,
462
+ "learning_rate": 1.5219335992900282e-05,
463
+ "loss": 0.0992,
464
+ "step": 760
465
+ },
466
+ {
467
+ "epoch": 17.5,
468
+ "learning_rate": 1.5093201623287631e-05,
469
+ "loss": 0.1063,
470
+ "step": 770
471
+ },
472
+ {
473
+ "epoch": 17.73,
474
+ "learning_rate": 1.4965963444650465e-05,
475
+ "loss": 0.0863,
476
+ "step": 780
477
+ },
478
+ {
479
+ "epoch": 17.95,
480
+ "learning_rate": 1.4837649032305885e-05,
481
+ "loss": 0.0949,
482
+ "step": 790
483
+ },
484
+ {
485
+ "epoch": 18.18,
486
+ "learning_rate": 1.4708286194814565e-05,
487
+ "loss": 0.0829,
488
+ "step": 800
489
+ },
490
+ {
491
+ "epoch": 18.41,
492
+ "learning_rate": 1.4577902967953995e-05,
493
+ "loss": 0.0892,
494
+ "step": 810
495
+ },
496
+ {
497
+ "epoch": 18.64,
498
+ "learning_rate": 1.4446527608642538e-05,
499
+ "loss": 0.0972,
500
+ "step": 820
501
+ },
502
+ {
503
+ "epoch": 18.86,
504
+ "learning_rate": 1.4314188588815514e-05,
505
+ "loss": 0.0848,
506
+ "step": 830
507
+ },
508
+ {
509
+ "epoch": 19.09,
510
+ "learning_rate": 1.4180914589254716e-05,
511
+ "loss": 0.0849,
512
+ "step": 840
513
+ },
514
+ {
515
+ "epoch": 19.32,
516
+ "learning_rate": 1.4046734493372646e-05,
517
+ "loss": 0.0877,
518
+ "step": 850
519
+ },
520
+ {
521
+ "epoch": 19.55,
522
+ "learning_rate": 1.3911677380952853e-05,
523
+ "loss": 0.0877,
524
+ "step": 860
525
+ },
526
+ {
527
+ "epoch": 19.77,
528
+ "learning_rate": 1.3775772521847683e-05,
529
+ "loss": 0.0754,
530
+ "step": 870
531
+ },
532
+ {
533
+ "epoch": 20.0,
534
+ "learning_rate": 1.3639049369634878e-05,
535
+ "loss": 0.0901,
536
+ "step": 880
537
+ },
538
+ {
539
+ "epoch": 20.23,
540
+ "learning_rate": 1.3501537555234323e-05,
541
+ "loss": 0.0826,
542
+ "step": 890
543
+ },
544
+ {
545
+ "epoch": 20.45,
546
+ "learning_rate": 1.3363266880486388e-05,
547
+ "loss": 0.0858,
548
+ "step": 900
549
+ },
550
+ {
551
+ "epoch": 20.68,
552
+ "learning_rate": 1.3224267311693186e-05,
553
+ "loss": 0.0791,
554
+ "step": 910
555
+ },
556
+ {
557
+ "epoch": 20.91,
558
+ "learning_rate": 1.308456897312425e-05,
559
+ "loss": 0.0756,
560
+ "step": 920
561
+ },
562
+ {
563
+ "epoch": 21.14,
564
+ "learning_rate": 1.2944202140487905e-05,
565
+ "loss": 0.0683,
566
+ "step": 930
567
+ },
568
+ {
569
+ "epoch": 21.36,
570
+ "learning_rate": 1.2803197234369878e-05,
571
+ "loss": 0.0806,
572
+ "step": 940
573
+ },
574
+ {
575
+ "epoch": 21.59,
576
+ "learning_rate": 1.2661584813640485e-05,
577
+ "loss": 0.0841,
578
+ "step": 950
579
+ },
580
+ {
581
+ "epoch": 21.82,
582
+ "learning_rate": 1.2519395568831839e-05,
583
+ "loss": 0.0917,
584
+ "step": 960
585
+ },
586
+ {
587
+ "epoch": 22.05,
588
+ "learning_rate": 1.2376660315486535e-05,
589
+ "loss": 0.0708,
590
+ "step": 970
591
+ },
592
+ {
593
+ "epoch": 22.27,
594
+ "learning_rate": 1.223340998747927e-05,
595
+ "loss": 0.0768,
596
+ "step": 980
597
+ },
598
+ {
599
+ "epoch": 22.5,
600
+ "learning_rate": 1.2089675630312755e-05,
601
+ "loss": 0.0834,
602
+ "step": 990
603
+ },
604
+ {
605
+ "epoch": 22.73,
606
+ "learning_rate": 1.1945488394389479e-05,
607
+ "loss": 0.0769,
608
+ "step": 1000
609
+ },
610
+ {
611
+ "epoch": 22.95,
612
+ "learning_rate": 1.1800879528260761e-05,
613
+ "loss": 0.0751,
614
+ "step": 1010
615
+ },
616
+ {
617
+ "epoch": 23.18,
618
+ "learning_rate": 1.1655880371854454e-05,
619
+ "loss": 0.08,
620
+ "step": 1020
621
+ },
622
+ {
623
+ "epoch": 23.41,
624
+ "learning_rate": 1.1510522349682922e-05,
625
+ "loss": 0.0603,
626
+ "step": 1030
627
+ },
628
+ {
629
+ "epoch": 23.64,
630
+ "learning_rate": 1.1364836964032658e-05,
631
+ "loss": 0.0685,
632
+ "step": 1040
633
+ },
634
+ {
635
+ "epoch": 23.86,
636
+ "learning_rate": 1.1218855788137016e-05,
637
+ "loss": 0.0735,
638
+ "step": 1050
639
+ },
640
+ {
641
+ "epoch": 24.09,
642
+ "learning_rate": 1.107261045933363e-05,
643
+ "loss": 0.0615,
644
+ "step": 1060
645
+ },
646
+ {
647
+ "epoch": 24.32,
648
+ "learning_rate": 1.092613267220788e-05,
649
+ "loss": 0.0678,
650
+ "step": 1070
651
+ },
652
+ {
653
+ "epoch": 24.55,
654
+ "learning_rate": 1.0779454171723994e-05,
655
+ "loss": 0.0687,
656
+ "step": 1080
657
+ },
658
+ {
659
+ "epoch": 24.77,
660
+ "learning_rate": 1.0632606746345203e-05,
661
+ "loss": 0.0669,
662
+ "step": 1090
663
+ },
664
+ {
665
+ "epoch": 25.0,
666
+ "learning_rate": 1.0485622221144485e-05,
667
+ "loss": 0.071,
668
+ "step": 1100
669
+ },
670
+ {
671
+ "epoch": 25.23,
672
+ "learning_rate": 1.0338532450907373e-05,
673
+ "loss": 0.0708,
674
+ "step": 1110
675
+ },
676
+ {
677
+ "epoch": 25.45,
678
+ "learning_rate": 1.0191369313228319e-05,
679
+ "loss": 0.0677,
680
+ "step": 1120
681
+ },
682
+ {
683
+ "epoch": 25.68,
684
+ "learning_rate": 1.0044164701602111e-05,
685
+ "loss": 0.0738,
686
+ "step": 1130
687
+ },
688
+ {
689
+ "epoch": 25.91,
690
+ "learning_rate": 9.896950518511863e-06,
691
+ "loss": 0.0753,
692
+ "step": 1140
693
+ },
694
+ {
695
+ "epoch": 26.14,
696
+ "learning_rate": 9.749758668515027e-06,
697
+ "loss": 0.0689,
698
+ "step": 1150
699
+ },
700
+ {
701
+ "epoch": 26.36,
702
+ "learning_rate": 9.602621051328998e-06,
703
+ "loss": 0.0688,
704
+ "step": 1160
705
+ },
706
+ {
707
+ "epoch": 26.59,
708
+ "learning_rate": 9.455569554917701e-06,
709
+ "loss": 0.0781,
710
+ "step": 1170
711
+ },
712
+ {
713
+ "epoch": 26.82,
714
+ "learning_rate": 9.308636048580813e-06,
715
+ "loss": 0.0635,
716
+ "step": 1180
717
+ },
718
+ {
719
+ "epoch": 27.05,
720
+ "learning_rate": 9.161852376046953e-06,
721
+ "loss": 0.068,
722
+ "step": 1190
723
+ },
724
+ {
725
+ "epoch": 27.27,
726
+ "learning_rate": 9.015250348572452e-06,
727
+ "loss": 0.0602,
728
+ "step": 1200
729
+ },
730
+ {
731
+ "epoch": 27.5,
732
+ "learning_rate": 8.868861738047158e-06,
733
+ "loss": 0.0502,
734
+ "step": 1210
735
+ },
736
+ {
737
+ "epoch": 27.73,
738
+ "learning_rate": 8.72271827010876e-06,
739
+ "loss": 0.0531,
740
+ "step": 1220
741
+ },
742
+ {
743
+ "epoch": 27.95,
744
+ "learning_rate": 8.576851617267151e-06,
745
+ "loss": 0.0613,
746
+ "step": 1230
747
+ },
748
+ {
749
+ "epoch": 28.18,
750
+ "learning_rate": 8.431293392040283e-06,
751
+ "loss": 0.0636,
752
+ "step": 1240
753
+ },
754
+ {
755
+ "epoch": 28.41,
756
+ "learning_rate": 8.286075140103058e-06,
757
+ "loss": 0.0618,
758
+ "step": 1250
759
+ },
760
+ {
761
+ "epoch": 28.64,
762
+ "learning_rate": 8.141228333450673e-06,
763
+ "loss": 0.0652,
764
+ "step": 1260
765
+ },
766
+ {
767
+ "epoch": 28.86,
768
+ "learning_rate": 7.99678436357794e-06,
769
+ "loss": 0.0742,
770
+ "step": 1270
771
+ },
772
+ {
773
+ "epoch": 29.09,
774
+ "learning_rate": 7.852774534676073e-06,
775
+ "loss": 0.0529,
776
+ "step": 1280
777
+ },
778
+ {
779
+ "epoch": 29.32,
780
+ "learning_rate": 7.709230056848356e-06,
781
+ "loss": 0.0441,
782
+ "step": 1290
783
+ },
784
+ {
785
+ "epoch": 29.55,
786
+ "learning_rate": 7.5661820393462605e-06,
787
+ "loss": 0.0575,
788
+ "step": 1300
789
+ },
790
+ {
791
+ "epoch": 29.77,
792
+ "learning_rate": 7.423661483827357e-06,
793
+ "loss": 0.0552,
794
+ "step": 1310
795
+ },
796
+ {
797
+ "epoch": 30.0,
798
+ "learning_rate": 7.2816992776365714e-06,
799
+ "loss": 0.0518,
800
+ "step": 1320
801
+ },
802
+ {
803
+ "epoch": 30.23,
804
+ "learning_rate": 7.1403261871122466e-06,
805
+ "loss": 0.0631,
806
+ "step": 1330
807
+ },
808
+ {
809
+ "epoch": 30.45,
810
+ "learning_rate": 6.999572850918357e-06,
811
+ "loss": 0.0496,
812
+ "step": 1340
813
+ },
814
+ {
815
+ "epoch": 30.68,
816
+ "learning_rate": 6.859469773404471e-06,
817
+ "loss": 0.0575,
818
+ "step": 1350
819
+ },
820
+ {
821
+ "epoch": 30.91,
822
+ "learning_rate": 6.720047317994775e-06,
823
+ "loss": 0.0547,
824
+ "step": 1360
825
+ },
826
+ {
827
+ "epoch": 31.14,
828
+ "learning_rate": 6.581335700607632e-06,
829
+ "loss": 0.0537,
830
+ "step": 1370
831
+ },
832
+ {
833
+ "epoch": 31.36,
834
+ "learning_rate": 6.443364983107156e-06,
835
+ "loss": 0.0531,
836
+ "step": 1380
837
+ },
838
+ {
839
+ "epoch": 31.59,
840
+ "learning_rate": 6.306165066788121e-06,
841
+ "loss": 0.0525,
842
+ "step": 1390
843
+ },
844
+ {
845
+ "epoch": 31.82,
846
+ "learning_rate": 6.169765685895703e-06,
847
+ "loss": 0.0512,
848
+ "step": 1400
849
+ },
850
+ {
851
+ "epoch": 32.05,
852
+ "learning_rate": 6.034196401181414e-06,
853
+ "loss": 0.0506,
854
+ "step": 1410
855
+ },
856
+ {
857
+ "epoch": 32.27,
858
+ "learning_rate": 5.899486593496625e-06,
859
+ "loss": 0.0472,
860
+ "step": 1420
861
+ },
862
+ {
863
+ "epoch": 32.5,
864
+ "learning_rate": 5.765665457425102e-06,
865
+ "loss": 0.0538,
866
+ "step": 1430
867
+ },
868
+ {
869
+ "epoch": 32.73,
870
+ "learning_rate": 5.6327619949558806e-06,
871
+ "loss": 0.0565,
872
+ "step": 1440
873
+ },
874
+ {
875
+ "epoch": 32.95,
876
+ "learning_rate": 5.500805009197916e-06,
877
+ "loss": 0.042,
878
+ "step": 1450
879
+ },
880
+ {
881
+ "epoch": 33.18,
882
+ "learning_rate": 5.369823098137803e-06,
883
+ "loss": 0.04,
884
+ "step": 1460
885
+ },
886
+ {
887
+ "epoch": 33.41,
888
+ "learning_rate": 5.23984464844195e-06,
889
+ "loss": 0.0512,
890
+ "step": 1470
891
+ },
892
+ {
893
+ "epoch": 33.64,
894
+ "learning_rate": 5.1108978293045915e-06,
895
+ "loss": 0.0399,
896
+ "step": 1480
897
+ },
898
+ {
899
+ "epoch": 33.86,
900
+ "learning_rate": 4.983010586342876e-06,
901
+ "loss": 0.0493,
902
+ "step": 1490
903
+ },
904
+ {
905
+ "epoch": 34.09,
906
+ "learning_rate": 4.856210635540452e-06,
907
+ "loss": 0.0454,
908
+ "step": 1500
909
+ },
910
+ {
911
+ "epoch": 34.32,
912
+ "learning_rate": 4.730525457240796e-06,
913
+ "loss": 0.0414,
914
+ "step": 1510
915
+ },
916
+ {
917
+ "epoch": 34.55,
918
+ "learning_rate": 4.605982290191623e-06,
919
+ "loss": 0.045,
920
+ "step": 1520
921
+ },
922
+ {
923
+ "epoch": 34.77,
924
+ "learning_rate": 4.482608125641633e-06,
925
+ "loss": 0.0505,
926
+ "step": 1530
927
+ },
928
+ {
929
+ "epoch": 35.0,
930
+ "learning_rate": 4.360429701490935e-06,
931
+ "loss": 0.0483,
932
+ "step": 1540
933
+ },
934
+ {
935
+ "epoch": 35.23,
936
+ "learning_rate": 4.239473496496345e-06,
937
+ "loss": 0.0458,
938
+ "step": 1550
939
+ },
940
+ {
941
+ "epoch": 35.45,
942
+ "learning_rate": 4.119765724532843e-06,
943
+ "loss": 0.0391,
944
+ "step": 1560
945
+ },
946
+ {
947
+ "epoch": 35.68,
948
+ "learning_rate": 4.001332328912475e-06,
949
+ "loss": 0.0434,
950
+ "step": 1570
951
+ },
952
+ {
953
+ "epoch": 35.91,
954
+ "learning_rate": 3.884198976761846e-06,
955
+ "loss": 0.0516,
956
+ "step": 1580
957
+ },
958
+ {
959
+ "epoch": 36.14,
960
+ "learning_rate": 3.7683910534594957e-06,
961
+ "loss": 0.0438,
962
+ "step": 1590
963
+ },
964
+ {
965
+ "epoch": 36.36,
966
+ "learning_rate": 3.6539336571343177e-06,
967
+ "loss": 0.0424,
968
+ "step": 1600
969
+ },
970
+ {
971
+ "epoch": 36.59,
972
+ "learning_rate": 3.540851593226261e-06,
973
+ "loss": 0.0468,
974
+ "step": 1610
975
+ },
976
+ {
977
+ "epoch": 36.82,
978
+ "learning_rate": 3.429169369110422e-06,
979
+ "loss": 0.0413,
980
+ "step": 1620
981
+ },
982
+ {
983
+ "epoch": 37.05,
984
+ "learning_rate": 3.3189111887857773e-06,
985
+ "loss": 0.0479,
986
+ "step": 1630
987
+ },
988
+ {
989
+ "epoch": 37.27,
990
+ "learning_rate": 3.2101009476296306e-06,
991
+ "loss": 0.0402,
992
+ "step": 1640
993
+ },
994
+ {
995
+ "epoch": 37.5,
996
+ "learning_rate": 3.1027622272189572e-06,
997
+ "loss": 0.0428,
998
+ "step": 1650
999
+ },
1000
+ {
1001
+ "epoch": 37.73,
1002
+ "learning_rate": 2.996918290219769e-06,
1003
+ "loss": 0.0394,
1004
+ "step": 1660
1005
+ },
1006
+ {
1007
+ "epoch": 37.95,
1008
+ "learning_rate": 2.8925920753455625e-06,
1009
+ "loss": 0.0359,
1010
+ "step": 1670
1011
+ },
1012
+ {
1013
+ "epoch": 38.18,
1014
+ "learning_rate": 2.7898061923860153e-06,
1015
+ "loss": 0.0404,
1016
+ "step": 1680
1017
+ },
1018
+ {
1019
+ "epoch": 38.41,
1020
+ "learning_rate": 2.688582917306938e-06,
1021
+ "loss": 0.0439,
1022
+ "step": 1690
1023
+ },
1024
+ {
1025
+ "epoch": 38.64,
1026
+ "learning_rate": 2.5889441874225676e-06,
1027
+ "loss": 0.0396,
1028
+ "step": 1700
1029
+ },
1030
+ {
1031
+ "epoch": 38.86,
1032
+ "learning_rate": 2.4909115966412957e-06,
1033
+ "loss": 0.0462,
1034
+ "step": 1710
1035
+ },
1036
+ {
1037
+ "epoch": 39.09,
1038
+ "learning_rate": 2.3945063907857647e-06,
1039
+ "loss": 0.0466,
1040
+ "step": 1720
1041
+ },
1042
+ {
1043
+ "epoch": 39.32,
1044
+ "learning_rate": 2.299749462988451e-06,
1045
+ "loss": 0.031,
1046
+ "step": 1730
1047
+ },
1048
+ {
1049
+ "epoch": 39.55,
1050
+ "learning_rate": 2.2066613491636568e-06,
1051
+ "loss": 0.0409,
1052
+ "step": 1740
1053
+ },
1054
+ {
1055
+ "epoch": 39.77,
1056
+ "learning_rate": 2.115262223556912e-06,
1057
+ "loss": 0.0449,
1058
+ "step": 1750
1059
+ },
1060
+ {
1061
+ "epoch": 40.0,
1062
+ "learning_rate": 2.025571894372794e-06,
1063
+ "loss": 0.0373,
1064
+ "step": 1760
1065
+ },
1066
+ {
1067
+ "epoch": 40.23,
1068
+ "learning_rate": 1.9376097994820286e-06,
1069
+ "loss": 0.0422,
1070
+ "step": 1770
1071
+ },
1072
+ {
1073
+ "epoch": 40.45,
1074
+ "learning_rate": 1.8513950022088966e-06,
1075
+ "loss": 0.0508,
1076
+ "step": 1780
1077
+ },
1078
+ {
1079
+ "epoch": 40.68,
1080
+ "learning_rate": 1.7669461871997817e-06,
1081
+ "loss": 0.0424,
1082
+ "step": 1790
1083
+ },
1084
+ {
1085
+ "epoch": 40.91,
1086
+ "learning_rate": 1.6842816563737875e-06,
1087
+ "loss": 0.0403,
1088
+ "step": 1800
1089
+ },
1090
+ {
1091
+ "epoch": 41.14,
1092
+ "learning_rate": 1.603419324956328e-06,
1093
+ "loss": 0.0419,
1094
+ "step": 1810
1095
+ },
1096
+ {
1097
+ "epoch": 41.36,
1098
+ "learning_rate": 1.5243767175964818e-06,
1099
+ "loss": 0.0334,
1100
+ "step": 1820
1101
+ },
1102
+ {
1103
+ "epoch": 41.59,
1104
+ "learning_rate": 1.4471709645690336e-06,
1105
+ "loss": 0.0304,
1106
+ "step": 1830
1107
+ },
1108
+ {
1109
+ "epoch": 41.82,
1110
+ "learning_rate": 1.3718187980619557e-06,
1111
+ "loss": 0.0413,
1112
+ "step": 1840
1113
+ },
1114
+ {
1115
+ "epoch": 42.05,
1116
+ "learning_rate": 1.298336548550172e-06,
1117
+ "loss": 0.0423,
1118
+ "step": 1850
1119
+ },
1120
+ {
1121
+ "epoch": 42.27,
1122
+ "learning_rate": 1.226740141256395e-06,
1123
+ "loss": 0.0378,
1124
+ "step": 1860
1125
+ },
1126
+ {
1127
+ "epoch": 42.5,
1128
+ "learning_rate": 1.1570450926997657e-06,
1129
+ "loss": 0.0316,
1130
+ "step": 1870
1131
+ },
1132
+ {
1133
+ "epoch": 42.73,
1134
+ "learning_rate": 1.0892665073330932e-06,
1135
+ "loss": 0.0366,
1136
+ "step": 1880
1137
+ },
1138
+ {
1139
+ "epoch": 42.95,
1140
+ "learning_rate": 1.023419074269384e-06,
1141
+ "loss": 0.0335,
1142
+ "step": 1890
1143
+ },
1144
+ {
1145
+ "epoch": 43.18,
1146
+ "learning_rate": 9.595170640983786e-07,
1147
+ "loss": 0.0352,
1148
+ "step": 1900
1149
+ },
1150
+ {
1151
+ "epoch": 43.41,
1152
+ "learning_rate": 8.975743257938186e-07,
1153
+ "loss": 0.0399,
1154
+ "step": 1910
1155
+ },
1156
+ {
1157
+ "epoch": 43.64,
1158
+ "learning_rate": 8.37604283712048e-07,
1159
+ "loss": 0.0344,
1160
+ "step": 1920
1161
+ },
1162
+ {
1163
+ "epoch": 43.86,
1164
+ "learning_rate": 7.796199346826727e-07,
1165
+ "loss": 0.04,
1166
+ "step": 1930
1167
+ },
1168
+ {
1169
+ "epoch": 44.09,
1170
+ "learning_rate": 7.236338451918634e-07,
1171
+ "loss": 0.0355,
1172
+ "step": 1940
1173
+ },
1174
+ {
1175
+ "epoch": 44.32,
1176
+ "learning_rate": 6.696581486589071e-07,
1177
+ "loss": 0.0363,
1178
+ "step": 1950
1179
+ },
1180
+ {
1181
+ "epoch": 44.55,
1182
+ "learning_rate": 6.177045428066397e-07,
1183
+ "loss": 0.0266,
1184
+ "step": 1960
1185
+ },
1186
+ {
1187
+ "epoch": 44.77,
1188
+ "learning_rate": 5.677842871262895e-07,
1189
+ "loss": 0.0303,
1190
+ "step": 1970
1191
+ },
1192
+ {
1193
+ "epoch": 45.0,
1194
+ "learning_rate": 5.199082004372958e-07,
1195
+ "loss": 0.0318,
1196
+ "step": 1980
1197
+ },
1198
+ {
1199
+ "epoch": 45.23,
1200
+ "learning_rate": 4.7408665854263067e-07,
1201
+ "loss": 0.0297,
1202
+ "step": 1990
1203
+ },
1204
+ {
1205
+ "epoch": 45.45,
1206
+ "learning_rate": 4.3032959198013646e-07,
1207
+ "loss": 0.0346,
1208
+ "step": 2000
1209
+ },
1210
+ {
1211
+ "epoch": 45.68,
1212
+ "learning_rate": 3.8864648387036074e-07,
1213
+ "loss": 0.0359,
1214
+ "step": 2010
1215
+ },
1216
+ {
1217
+ "epoch": 45.91,
1218
+ "learning_rate": 3.490463678613487e-07,
1219
+ "loss": 0.0348,
1220
+ "step": 2020
1221
+ },
1222
+ {
1223
+ "epoch": 46.14,
1224
+ "learning_rate": 3.1153782617086126e-07,
1225
+ "loss": 0.0387,
1226
+ "step": 2030
1227
+ },
1228
+ {
1229
+ "epoch": 46.36,
1230
+ "learning_rate": 2.761289877264139e-07,
1231
+ "loss": 0.0304,
1232
+ "step": 2040
1233
+ },
1234
+ {
1235
+ "epoch": 46.59,
1236
+ "learning_rate": 2.4282752640355846e-07,
1237
+ "loss": 0.0337,
1238
+ "step": 2050
1239
+ },
1240
+ {
1241
+ "epoch": 46.82,
1242
+ "learning_rate": 2.1164065936278732e-07,
1243
+ "loss": 0.0432,
1244
+ "step": 2060
1245
+ },
1246
+ {
1247
+ "epoch": 47.05,
1248
+ "learning_rate": 1.8257514548541632e-07,
1249
+ "loss": 0.0298,
1250
+ "step": 2070
1251
+ },
1252
+ {
1253
+ "epoch": 47.27,
1254
+ "learning_rate": 1.5563728390878496e-07,
1255
+ "loss": 0.0322,
1256
+ "step": 2080
1257
+ },
1258
+ {
1259
+ "epoch": 47.5,
1260
+ "learning_rate": 1.30832912661093e-07,
1261
+ "loss": 0.0305,
1262
+ "step": 2090
1263
+ },
1264
+ {
1265
+ "epoch": 47.73,
1266
+ "learning_rate": 1.0816740739617471e-07,
1267
+ "loss": 0.0333,
1268
+ "step": 2100
1269
+ },
1270
+ {
1271
+ "epoch": 47.95,
1272
+ "learning_rate": 8.764568022847198e-08,
1273
+ "loss": 0.0293,
1274
+ "step": 2110
1275
+ },
1276
+ {
1277
+ "epoch": 48.18,
1278
+ "learning_rate": 6.92721786684769e-08,
1279
+ "loss": 0.0428,
1280
+ "step": 2120
1281
+ },
1282
+ {
1283
+ "epoch": 48.41,
1284
+ "learning_rate": 5.305088465885067e-08,
1285
+ "loss": 0.0363,
1286
+ "step": 2130
1287
+ },
1288
+ {
1289
+ "epoch": 48.64,
1290
+ "learning_rate": 3.898531371145597e-08,
1291
+ "loss": 0.0329,
1292
+ "step": 2140
1293
+ },
1294
+ {
1295
+ "epoch": 48.86,
1296
+ "learning_rate": 2.7078514145459924e-08,
1297
+ "loss": 0.0308,
1298
+ "step": 2150
1299
+ },
1300
+ {
1301
+ "epoch": 49.09,
1302
+ "learning_rate": 1.7333066426706845e-08,
1303
+ "loss": 0.0318,
1304
+ "step": 2160
1305
+ },
1306
+ {
1307
+ "epoch": 49.32,
1308
+ "learning_rate": 9.75108260846569e-09,
1309
+ "loss": 0.03,
1310
+ "step": 2170
1311
+ },
1312
+ {
1313
+ "epoch": 49.55,
1314
+ "learning_rate": 4.334205873705033e-09,
1315
+ "loss": 0.0302,
1316
+ "step": 2180
1317
+ },
1318
+ {
1319
+ "epoch": 49.77,
1320
+ "learning_rate": 1.0836101789768462e-09,
1321
+ "loss": 0.0264,
1322
+ "step": 2190
1323
+ },
1324
+ {
1325
+ "epoch": 50.0,
1326
+ "learning_rate": 0.0,
1327
+ "loss": 0.0382,
1328
+ "step": 2200
1329
+ },
1330
+ {
1331
+ "epoch": 50.0,
1332
+ "step": 2200,
1333
+ "total_flos": 3.745171436910674e+17,
1334
+ "train_loss": 0.13681490471417254,
1335
+ "train_runtime": 4969.2412,
1336
+ "train_samples_per_second": 13.865,
1337
+ "train_steps_per_second": 0.443
1338
+ }
1339
+ ],
1340
+ "max_steps": 2200,
1341
+ "num_train_epochs": 50,
1342
+ "total_flos": 3.745171436910674e+17,
1343
+ "trial_name": null,
1344
+ "trial_params": null
1345
+ }
rxn/model/trainer_state.png ADDED