root commited on
Commit
3f66fdf
1 Parent(s): a58e7a9

First version of the bgc-accession model and tokenizer.

Browse files
Files changed (44) hide show
  1. checkpoint-1000/config.json +35 -0
  2. checkpoint-1000/optimizer.pt +3 -0
  3. checkpoint-1000/pytorch_model.bin +3 -0
  4. checkpoint-1000/rng_state.pth +3 -0
  5. checkpoint-1000/scheduler.pt +3 -0
  6. checkpoint-1000/trainer_state.json +28 -0
  7. checkpoint-1000/training_args.bin +3 -0
  8. checkpoint-2000/config.json +35 -0
  9. checkpoint-2000/optimizer.pt +3 -0
  10. checkpoint-2000/pytorch_model.bin +3 -0
  11. checkpoint-2000/rng_state.pth +3 -0
  12. checkpoint-2000/scheduler.pt +3 -0
  13. checkpoint-2000/trainer_state.json +40 -0
  14. checkpoint-2000/training_args.bin +3 -0
  15. checkpoint-3000/config.json +35 -0
  16. checkpoint-3000/optimizer.pt +3 -0
  17. checkpoint-3000/pytorch_model.bin +3 -0
  18. checkpoint-3000/rng_state.pth +3 -0
  19. checkpoint-3000/scheduler.pt +3 -0
  20. checkpoint-3000/trainer_state.json +52 -0
  21. checkpoint-3000/training_args.bin +3 -0
  22. checkpoint-4000/config.json +35 -0
  23. checkpoint-4000/optimizer.pt +3 -0
  24. checkpoint-4000/pytorch_model.bin +3 -0
  25. checkpoint-4000/rng_state.pth +3 -0
  26. checkpoint-4000/scheduler.pt +3 -0
  27. checkpoint-4000/trainer_state.json +64 -0
  28. checkpoint-4000/training_args.bin +3 -0
  29. checkpoint-5000/config.json +35 -0
  30. checkpoint-5000/optimizer.pt +3 -0
  31. checkpoint-5000/pytorch_model.bin +3 -0
  32. checkpoint-5000/rng_state.pth +3 -0
  33. checkpoint-5000/scheduler.pt +3 -0
  34. checkpoint-5000/trainer_state.json +76 -0
  35. checkpoint-5000/training_args.bin +3 -0
  36. config.json +35 -0
  37. eval_results.txt +9 -0
  38. pytorch_model.bin +3 -0
  39. special_tokens_map.json +1 -0
  40. test_predictions.txt +0 -0
  41. test_results.txt +8 -0
  42. tokenizer_config.json +1 -0
  43. training_args.bin +3 -0
  44. vocab.txt +0 -0
checkpoint-1000/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nfs/production/literature/maaly/emerald-master/ml/pretrain/bert/train/biomed/models/pytorch/biobert_v1.0_pubmed_pmc",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "B-bgc-accession",
13
+ "1": "I-bgc-accession",
14
+ "2": "O"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "B-bgc-accession": 0,
20
+ "I-bgc-accession": 1,
21
+ "O": 2
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.16.0.dev0",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 28996
35
+ }
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76bb6003f2a4d7cbb4f8565ea262d2bb404db66d6b6cb7e0d8038f347836094
3
+ size 861895213
checkpoint-1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8422e8f8702d140d70154547fd50eeddaffec3af7784a0280388a5d4b1e80402
3
+ size 430973751
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ac14aebf521681dcbc5f118b331d2d5a5cccd682ac27537f6273c9d3150efec
3
+ size 13560
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0ddc65aa7491c6d0ff1c766a97b779ef5cb7c61e769feff86b222261ee5b327
3
+ size 623
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.555555555555555,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.78,
12
+ "learning_rate": 3.62962962962963e-05,
13
+ "loss": 0.0119,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 5.56,
18
+ "learning_rate": 3.259259259259259e-05,
19
+ "loss": 0.0015,
20
+ "step": 1000
21
+ }
22
+ ],
23
+ "max_steps": 5400,
24
+ "num_train_epochs": 30,
25
+ "total_flos": 2082227355360000.0,
26
+ "trial_name": null,
27
+ "trial_params": null
28
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22235e2810fda58e2bc6ed9964bb6cee8e7251edd8674b13e9557da2f6b0c79a
3
+ size 3183
checkpoint-2000/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nfs/production/literature/maaly/emerald-master/ml/pretrain/bert/train/biomed/models/pytorch/biobert_v1.0_pubmed_pmc",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "B-bgc-accession",
13
+ "1": "I-bgc-accession",
14
+ "2": "O"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "B-bgc-accession": 0,
20
+ "I-bgc-accession": 1,
21
+ "O": 2
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.16.0.dev0",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 28996
35
+ }
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f477e7dde3858f639399705f359c159fa17855f1f3d2e85b31606f3d15758b9
3
+ size 861895213
checkpoint-2000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4d372e47ae63fe6daf92429f35e085b6a534703d020091519389be277f476e7
3
+ size 430973751
checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acd54eadddf5ceb12f6a1678c2073ecf1fc474bb45ce842281bc3a5476671abf
3
+ size 13560
checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ad13aef0dea48755ebce331c82f081f7b9623a8b2cd1d417ef311ca9428100d
3
+ size 623
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 11.11111111111111,
5
+ "global_step": 2000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.78,
12
+ "learning_rate": 3.62962962962963e-05,
13
+ "loss": 0.0119,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 5.56,
18
+ "learning_rate": 3.259259259259259e-05,
19
+ "loss": 0.0015,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 8.33,
24
+ "learning_rate": 2.888888888888889e-05,
25
+ "loss": 0.0007,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 11.11,
30
+ "learning_rate": 2.5185185185185187e-05,
31
+ "loss": 0.0003,
32
+ "step": 2000
33
+ }
34
+ ],
35
+ "max_steps": 5400,
36
+ "num_train_epochs": 30,
37
+ "total_flos": 4162821591225600.0,
38
+ "trial_name": null,
39
+ "trial_params": null
40
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22235e2810fda58e2bc6ed9964bb6cee8e7251edd8674b13e9557da2f6b0c79a
3
+ size 3183
checkpoint-3000/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nfs/production/literature/maaly/emerald-master/ml/pretrain/bert/train/biomed/models/pytorch/biobert_v1.0_pubmed_pmc",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "B-bgc-accession",
13
+ "1": "I-bgc-accession",
14
+ "2": "O"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "B-bgc-accession": 0,
20
+ "I-bgc-accession": 1,
21
+ "O": 2
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.16.0.dev0",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 28996
35
+ }
checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:547126905ed53f164251271a63c9edac21cca5750786f642bfaefde9cde77115
3
+ size 861895213
checkpoint-3000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4e2bd62772304de4d0b5533ae02e66be3361112aac40eaaab5a738eae48d4ce
3
+ size 430973751
checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26457ada75904aa7d7ee5217f086421dec1b5d79eba61e9059ce5e7e407fa2b7
3
+ size 13560
checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4834dde0389df834113d4ad90cbda17ddeddce27c3193d69db74822a3348efa
3
+ size 623
checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 16.666666666666668,
5
+ "global_step": 3000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.78,
12
+ "learning_rate": 3.62962962962963e-05,
13
+ "loss": 0.0119,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 5.56,
18
+ "learning_rate": 3.259259259259259e-05,
19
+ "loss": 0.0015,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 8.33,
24
+ "learning_rate": 2.888888888888889e-05,
25
+ "loss": 0.0007,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 11.11,
30
+ "learning_rate": 2.5185185185185187e-05,
31
+ "loss": 0.0003,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 13.89,
36
+ "learning_rate": 2.1481481481481485e-05,
37
+ "loss": 0.0002,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 16.67,
42
+ "learning_rate": 1.7777777777777777e-05,
43
+ "loss": 0.0001,
44
+ "step": 3000
45
+ }
46
+ ],
47
+ "max_steps": 5400,
48
+ "num_train_epochs": 30,
49
+ "total_flos": 6245048946585600.0,
50
+ "trial_name": null,
51
+ "trial_params": null
52
+ }
checkpoint-3000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22235e2810fda58e2bc6ed9964bb6cee8e7251edd8674b13e9557da2f6b0c79a
3
+ size 3183
checkpoint-4000/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nfs/production/literature/maaly/emerald-master/ml/pretrain/bert/train/biomed/models/pytorch/biobert_v1.0_pubmed_pmc",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "B-bgc-accession",
13
+ "1": "I-bgc-accession",
14
+ "2": "O"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "B-bgc-accession": 0,
20
+ "I-bgc-accession": 1,
21
+ "O": 2
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.16.0.dev0",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 28996
35
+ }
checkpoint-4000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5035bbd7b8b3db4e2a3837e92a770c18e1bdc5bf7afa72025bb1cb27e71887b
3
+ size 861895213
checkpoint-4000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2eb9f554f7db8ee9e940a7d1135852210c2ae79313f43675118cd1cfa7b9a53
3
+ size 430973751
checkpoint-4000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24169d778c0ffdfcf3507fdeecb5182ae8497009174925b7b27d8c30e1b064a6
3
+ size 13560
checkpoint-4000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9dcbf32fad32c44756c4e51d79f8f48f1fd0f93f5d72e0178779ead46918f9d
3
+ size 623
checkpoint-4000/trainer_state.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 22.22222222222222,
5
+ "global_step": 4000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.78,
12
+ "learning_rate": 3.62962962962963e-05,
13
+ "loss": 0.0119,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 5.56,
18
+ "learning_rate": 3.259259259259259e-05,
19
+ "loss": 0.0015,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 8.33,
24
+ "learning_rate": 2.888888888888889e-05,
25
+ "loss": 0.0007,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 11.11,
30
+ "learning_rate": 2.5185185185185187e-05,
31
+ "loss": 0.0003,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 13.89,
36
+ "learning_rate": 2.1481481481481485e-05,
37
+ "loss": 0.0002,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 16.67,
42
+ "learning_rate": 1.7777777777777777e-05,
43
+ "loss": 0.0001,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 19.44,
48
+ "learning_rate": 1.4074074074074075e-05,
49
+ "loss": 0.0001,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 22.22,
54
+ "learning_rate": 1.037037037037037e-05,
55
+ "loss": 0.0001,
56
+ "step": 4000
57
+ }
58
+ ],
59
+ "max_steps": 5400,
60
+ "num_train_epochs": 30,
61
+ "total_flos": 8325643182451200.0,
62
+ "trial_name": null,
63
+ "trial_params": null
64
+ }
checkpoint-4000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22235e2810fda58e2bc6ed9964bb6cee8e7251edd8674b13e9557da2f6b0c79a
3
+ size 3183
checkpoint-5000/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nfs/production/literature/maaly/emerald-master/ml/pretrain/bert/train/biomed/models/pytorch/biobert_v1.0_pubmed_pmc",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "B-bgc-accession",
13
+ "1": "I-bgc-accession",
14
+ "2": "O"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "B-bgc-accession": 0,
20
+ "I-bgc-accession": 1,
21
+ "O": 2
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.16.0.dev0",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 28996
35
+ }
checkpoint-5000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae2fdc6bdf89c1f7d6a3f233f26d1fcb152f295681723c0976f70cc3d71f948b
3
+ size 861895213
checkpoint-5000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24a75bcec321d838d5fb64761632489413d95c1b2c7207d9fb3d91087da8c4ea
3
+ size 430973751
checkpoint-5000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfd7c270b1a0b468409bf2caa82bf1607500607b1a0c7805b4e4e5ceb5f7acd8
3
+ size 13560
checkpoint-5000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d99386f621cfe069e8b21f2cc84479a4cb8839dcc46b9fa0ec1ca55e95655dbc
3
+ size 623
checkpoint-5000/trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 27.77777777777778,
5
+ "global_step": 5000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.78,
12
+ "learning_rate": 3.62962962962963e-05,
13
+ "loss": 0.0119,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 5.56,
18
+ "learning_rate": 3.259259259259259e-05,
19
+ "loss": 0.0015,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 8.33,
24
+ "learning_rate": 2.888888888888889e-05,
25
+ "loss": 0.0007,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 11.11,
30
+ "learning_rate": 2.5185185185185187e-05,
31
+ "loss": 0.0003,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 13.89,
36
+ "learning_rate": 2.1481481481481485e-05,
37
+ "loss": 0.0002,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 16.67,
42
+ "learning_rate": 1.7777777777777777e-05,
43
+ "loss": 0.0001,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 19.44,
48
+ "learning_rate": 1.4074074074074075e-05,
49
+ "loss": 0.0001,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 22.22,
54
+ "learning_rate": 1.037037037037037e-05,
55
+ "loss": 0.0001,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 25.0,
60
+ "learning_rate": 6.666666666666667e-06,
61
+ "loss": 0.0,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 27.78,
66
+ "learning_rate": 2.962962962962963e-06,
67
+ "loss": 0.0,
68
+ "step": 5000
69
+ }
70
+ ],
71
+ "max_steps": 5400,
72
+ "num_train_epochs": 30,
73
+ "total_flos": 1.04078705378112e+16,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
checkpoint-5000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22235e2810fda58e2bc6ed9964bb6cee8e7251edd8674b13e9557da2f6b0c79a
3
+ size 3183
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/nfs/production/literature/maaly/emerald-master/ml/pretrain/bert/train/biomed/models/pytorch/biobert_v1.0_pubmed_pmc",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "B-bgc-accession",
13
+ "1": "I-bgc-accession",
14
+ "2": "O"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "B-bgc-accession": 0,
20
+ "I-bgc-accession": 1,
21
+ "O": 2
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.16.0.dev0",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 28996
35
+ }
eval_results.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ eval_loss = 0.002289790892973542
2
+ eval_accuracy_score = 0.9997590941941701
3
+ eval_precision = 0.9591836734693877
4
+ eval_recall = 0.9894736842105263
5
+ eval_f1 = 0.9740932642487047
6
+ eval_runtime = 96.9005
7
+ eval_samples_per_second = 6.491
8
+ eval_steps_per_second = 0.815
9
+ epoch = 30.0
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27378008f8a40b3c0c8d702436b190a73d1666c74f1fdcf8c7996949780d1c15
3
+ size 430973751
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
test_predictions.txt ADDED
The diff for this file is too large to render. See raw diff
 
test_results.txt ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ test_loss = 0.002289790892973542
2
+ test_accuracy_score = 0.9997590941941701
3
+ test_precision = 0.9591836734693877
4
+ test_recall = 0.9894736842105263
5
+ test_f1 = 0.9740932642487047
6
+ test_runtime = 93.9318
7
+ test_samples_per_second = 6.696
8
+ test_steps_per_second = 0.841
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/nfs/production/literature/maaly/emerald-master/ml/pretrain/bert/train/biomed/models/pytorch/biobert_v1.0_pubmed_pmc", "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22235e2810fda58e2bc6ed9964bb6cee8e7251edd8674b13e9557da2f6b0c79a
3
+ size 3183
vocab.txt ADDED
The diff for this file is too large to render. See raw diff