Hugging Face's logo

ireneli1024
/
biobart-v2-base-plos-finetuned

Text2Text Generation
Transformers
PyTorch
bart
Inference Endpoints
Model card Files Community
ireneli1024 commited on
Commit
9777aa6
•
1 Parent(s): e393bb9

Upload 13 files

Browse files
Files changed (13) hide show
  1. config.json +74 -0
  2. generation_config.json +12 -0
  3. merges.txt +0 -0
  4. optimizer.pt +3 -0
  5. pytorch_model.bin +3 -0
  6. rng_state.pth +3 -0
  7. scheduler.pt +3 -0
  8. special_tokens_map.json +51 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +64 -0
  11. trainer_state.json +136 -0
  12. training_args.bin +3 -0
  13. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "GanjinZero/biobart-v2-base",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 2,
27
+ "forced_eos_token_id": 2,
28
+ "gradient_checkpointing": false,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1",
32
+ "2": "LABEL_2"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_position_embeddings": 1024,
42
+ "model_type": "bart",
43
+ "no_repeat_ngram_size": 3,
44
+ "normalize_before": false,
45
+ "normalize_embedding": true,
46
+ "num_beams": 4,
47
+ "num_hidden_layers": 6,
48
+ "pad_token_id": 1,
49
+ "scale_embedding": false,
50
+ "task_specific_params": {
51
+ "summarization": {
52
+ "length_penalty": 1.0,
53
+ "max_length": 128,
54
+ "min_length": 12,
55
+ "num_beams": 4
56
+ },
57
+ "summarization_cnn": {
58
+ "length_penalty": 2.0,
59
+ "max_length": 142,
60
+ "min_length": 56,
61
+ "num_beams": 4
62
+ },
63
+ "summarization_xsum": {
64
+ "length_penalty": 1.0,
65
+ "max_length": 62,
66
+ "min_length": 11,
67
+ "num_beams": 6
68
+ }
69
+ },
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.28.0",
72
+ "use_cache": true,
73
+ "vocab_size": 85401
74
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_eos_token_id": 2,
8
+ "no_repeat_ngram_size": 3,
9
+ "num_beams": 4,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.28.0"
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0394927c3e6df4de26611dcd4dce905969eae492665948c1f6ba5f13c5c999ac
3
+ size 1331390917
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49fef4b26fbce5412bd8ee21c20c97471fb089cf6ad8fc75fea1e9b3653a05b2
3
+ size 666049565
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0145c66437dd6173b231d6d239841a3d2c11ae680bc59ccbe360bf1141f22e36
3
+ size 15597
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdb3a07d02472a0c7263892683f16fb010db062c726c2f5630f74b29bd08c4bc
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "mask_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<mask>",
32
+ "lstrip": true,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "tokenizer_class": "BartTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": {
57
+ "__type": "AddedToken",
58
+ "content": "<unk>",
59
+ "lstrip": false,
60
+ "normalized": true,
61
+ "rstrip": false,
62
+ "single_word": false
63
+ }
64
+ }
trainer_state.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.4188034188034186,
5
+ "global_step": 10000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.17,
12
+ "learning_rate": 1e-05,
13
+ "loss": 2.4983,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.34,
18
+ "learning_rate": 2e-05,
19
+ "loss": 2.0999,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.51,
24
+ "learning_rate": 1.888888888888889e-05,
25
+ "loss": 2.0854,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.68,
30
+ "learning_rate": 1.7777777777777777e-05,
31
+ "loss": 2.0504,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.85,
36
+ "learning_rate": 1.6666666666666667e-05,
37
+ "loss": 2.0294,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.03,
42
+ "learning_rate": 1.555555555555556e-05,
43
+ "loss": 2.0237,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.2,
48
+ "learning_rate": 1.4444444444444446e-05,
49
+ "loss": 1.9665,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.37,
54
+ "learning_rate": 1.3333333333333333e-05,
55
+ "loss": 1.9558,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.54,
60
+ "learning_rate": 1.2222222222222224e-05,
61
+ "loss": 1.9567,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.71,
66
+ "learning_rate": 1.1111111111111113e-05,
67
+ "loss": 1.9556,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.88,
72
+ "learning_rate": 1e-05,
73
+ "loss": 1.9408,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 2.05,
78
+ "learning_rate": 8.888888888888888e-06,
79
+ "loss": 1.9263,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 2.22,
84
+ "learning_rate": 7.77777777777778e-06,
85
+ "loss": 1.9023,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 2.39,
90
+ "learning_rate": 6.666666666666667e-06,
91
+ "loss": 1.9022,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 2.56,
96
+ "learning_rate": 5.555555555555557e-06,
97
+ "loss": 1.895,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 2.74,
102
+ "learning_rate": 4.444444444444444e-06,
103
+ "loss": 1.8941,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 2.91,
108
+ "learning_rate": 3.3333333333333333e-06,
109
+ "loss": 1.8867,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 3.08,
114
+ "learning_rate": 2.222222222222222e-06,
115
+ "loss": 1.8749,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 3.25,
120
+ "learning_rate": 1.111111111111111e-06,
121
+ "loss": 1.8601,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 3.42,
126
+ "learning_rate": 0.0,
127
+ "loss": 1.8586,
128
+ "step": 10000
129
+ }
130
+ ],
131
+ "max_steps": 10000,
132
+ "num_train_epochs": 4,
133
+ "total_flos": 4.877342903107584e+16,
134
+ "trial_name": null,
135
+ "trial_params": null
136
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50bee18ac07441f63578faf16f2e847c9763f55954b7c4b3fb2f00bd78438b1c
3
+ size 3771
vocab.json ADDED
The diff for this file is too large to render. See raw diff