JavierSanzCruza commited on
Commit
73fb03b
1 Parent(s): 6486ba0

Training in progress, epoch 1

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-116/config.json +40 -0
  3. run-2/checkpoint-116/model.safetensors +3 -0
  4. run-2/checkpoint-116/optimizer.pt +3 -0
  5. run-2/checkpoint-116/rng_state.pth +3 -0
  6. run-2/checkpoint-116/scheduler.pt +3 -0
  7. run-2/checkpoint-116/special_tokens_map.json +7 -0
  8. run-2/checkpoint-116/tokenizer.json +0 -0
  9. run-2/checkpoint-116/tokenizer_config.json +57 -0
  10. run-2/checkpoint-116/trainer_state.json +62 -0
  11. run-2/checkpoint-116/training_args.bin +3 -0
  12. run-2/checkpoint-116/vocab.txt +0 -0
  13. run-2/checkpoint-145/config.json +40 -0
  14. run-2/checkpoint-145/model.safetensors +3 -0
  15. run-2/checkpoint-145/optimizer.pt +3 -0
  16. run-2/checkpoint-145/rng_state.pth +3 -0
  17. run-2/checkpoint-145/scheduler.pt +3 -0
  18. run-2/checkpoint-145/special_tokens_map.json +7 -0
  19. run-2/checkpoint-145/tokenizer.json +0 -0
  20. run-2/checkpoint-145/tokenizer_config.json +57 -0
  21. run-2/checkpoint-145/trainer_state.json +71 -0
  22. run-2/checkpoint-145/training_args.bin +3 -0
  23. run-2/checkpoint-145/vocab.txt +0 -0
  24. run-2/checkpoint-58/config.json +40 -0
  25. run-2/checkpoint-58/model.safetensors +3 -0
  26. run-2/checkpoint-58/optimizer.pt +3 -0
  27. run-2/checkpoint-58/rng_state.pth +3 -0
  28. run-2/checkpoint-58/scheduler.pt +3 -0
  29. run-2/checkpoint-58/special_tokens_map.json +7 -0
  30. run-2/checkpoint-58/tokenizer.json +0 -0
  31. run-2/checkpoint-58/tokenizer_config.json +57 -0
  32. run-2/checkpoint-58/trainer_state.json +44 -0
  33. run-2/checkpoint-58/training_args.bin +3 -0
  34. run-2/checkpoint-58/vocab.txt +0 -0
  35. run-2/checkpoint-87/config.json +40 -0
  36. run-2/checkpoint-87/model.safetensors +3 -0
  37. run-2/checkpoint-87/optimizer.pt +3 -0
  38. run-2/checkpoint-87/rng_state.pth +3 -0
  39. run-2/checkpoint-87/scheduler.pt +3 -0
  40. run-2/checkpoint-87/special_tokens_map.json +7 -0
  41. run-2/checkpoint-87/tokenizer.json +0 -0
  42. run-2/checkpoint-87/tokenizer_config.json +57 -0
  43. run-2/checkpoint-87/trainer_state.json +53 -0
  44. run-2/checkpoint-87/training_args.bin +3 -0
  45. run-2/checkpoint-87/vocab.txt +0 -0
  46. run-3/checkpoint-29/config.json +40 -0
  47. run-3/checkpoint-29/model.safetensors +3 -0
  48. run-3/checkpoint-29/optimizer.pt +3 -0
  49. run-3/checkpoint-29/rng_state.pth +3 -0
  50. run-3/checkpoint-29/scheduler.pt +3 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f477d1fbaa68e90889704dadaecbbce855a83b5b8abcfcd7bc02583b480f811c
3
  size 437967876
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efb8dee464d09473f7b3b89073600401d3be390d7e6b78b47211f577cd1f87e0
3
  size 437967876
run-2/checkpoint-116/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
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": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.36.2",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 30522
40
+ }
run-2/checkpoint-116/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47abf1bd15bfea1e0487f3546912c507e64c7ab2e0dda07511ec2779144f5cc9
3
+ size 437967876
run-2/checkpoint-116/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ab7016512f35d2f162facfb6df536c29da014cc66398c33ebb55f6f78d79247
3
+ size 876056826
run-2/checkpoint-116/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200bcf0a8c6c24d2a0d3b6b3b4f791b59d77cc3d61df9013f7f05eac35bde076
3
+ size 14308
run-2/checkpoint-116/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a18d423470bca77e99ba5fcb8f913e81d4a4bbe0d1c2149e95a51e19af85b503
3
+ size 1064
run-2/checkpoint-116/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-2/checkpoint-116/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-116/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-2/checkpoint-116/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.638961038961039,
3
+ "best_model_checkpoint": "BiomedNLP-CIViC-evidence-level-finetuned/run-2/checkpoint-87",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 116,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_f1": 0.5038961038961038,
14
+ "eval_loss": 1.1599030494689941,
15
+ "eval_runtime": 3.0362,
16
+ "eval_samples_per_second": 126.804,
17
+ "eval_steps_per_second": 8.234,
18
+ "step": 29
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_f1": 0.574025974025974,
23
+ "eval_loss": 1.0611977577209473,
24
+ "eval_runtime": 3.0481,
25
+ "eval_samples_per_second": 126.308,
26
+ "eval_steps_per_second": 8.202,
27
+ "step": 58
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_f1": 0.638961038961039,
32
+ "eval_loss": 1.00022554397583,
33
+ "eval_runtime": 3.0541,
34
+ "eval_samples_per_second": 126.06,
35
+ "eval_steps_per_second": 8.186,
36
+ "step": 87
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_f1": 0.6233766233766234,
41
+ "eval_loss": 0.9825469851493835,
42
+ "eval_runtime": 3.0671,
43
+ "eval_samples_per_second": 125.524,
44
+ "eval_steps_per_second": 8.151,
45
+ "step": 116
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 145,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 5,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 4,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 1.2323346906015053e-05,
58
+ "num_train_epochs": 5,
59
+ "per_device_train_batch_size": 4,
60
+ "seed": 29
61
+ }
62
+ }
run-2/checkpoint-116/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b3ad8082a03e4c3f190076f53b72663d2faef012ff66aa71c0e32f2349565e7
3
+ size 4728
run-2/checkpoint-116/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-145/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
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": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.36.2",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 30522
40
+ }
run-2/checkpoint-145/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cc35993b6e245bf14b5c5d861056316b7ad5465be1071c3bb65c6568df1a2b5
3
+ size 437967876
run-2/checkpoint-145/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55fbf578f7a3d8cc2a251960c7c083765796ee771335bbd9b5d6e14d2e2ca3b9
3
+ size 876056826
run-2/checkpoint-145/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed97ce840f0747e58d25f083904ef2266df18d65c6ee3dd9e4a79ea0b764d1c
3
+ size 14308
run-2/checkpoint-145/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e009cc659b2c185311516a1233b3017df335f65887c4a5fcfd92a8c73acd4409
3
+ size 1064
run-2/checkpoint-145/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-2/checkpoint-145/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-145/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-2/checkpoint-145/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.638961038961039,
3
+ "best_model_checkpoint": "BiomedNLP-CIViC-evidence-level-finetuned/run-2/checkpoint-87",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 145,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_f1": 0.5038961038961038,
14
+ "eval_loss": 1.1599030494689941,
15
+ "eval_runtime": 3.0362,
16
+ "eval_samples_per_second": 126.804,
17
+ "eval_steps_per_second": 8.234,
18
+ "step": 29
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_f1": 0.574025974025974,
23
+ "eval_loss": 1.0611977577209473,
24
+ "eval_runtime": 3.0481,
25
+ "eval_samples_per_second": 126.308,
26
+ "eval_steps_per_second": 8.202,
27
+ "step": 58
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_f1": 0.638961038961039,
32
+ "eval_loss": 1.00022554397583,
33
+ "eval_runtime": 3.0541,
34
+ "eval_samples_per_second": 126.06,
35
+ "eval_steps_per_second": 8.186,
36
+ "step": 87
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_f1": 0.6233766233766234,
41
+ "eval_loss": 0.9825469851493835,
42
+ "eval_runtime": 3.0671,
43
+ "eval_samples_per_second": 125.524,
44
+ "eval_steps_per_second": 8.151,
45
+ "step": 116
46
+ },
47
+ {
48
+ "epoch": 5.0,
49
+ "eval_f1": 0.638961038961039,
50
+ "eval_loss": 0.9702814817428589,
51
+ "eval_runtime": 3.3506,
52
+ "eval_samples_per_second": 114.903,
53
+ "eval_steps_per_second": 7.461,
54
+ "step": 145
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 145,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 5,
61
+ "save_steps": 500,
62
+ "total_flos": 0,
63
+ "train_batch_size": 4,
64
+ "trial_name": null,
65
+ "trial_params": {
66
+ "learning_rate": 1.2323346906015053e-05,
67
+ "num_train_epochs": 5,
68
+ "per_device_train_batch_size": 4,
69
+ "seed": 29
70
+ }
71
+ }
run-2/checkpoint-145/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b3ad8082a03e4c3f190076f53b72663d2faef012ff66aa71c0e32f2349565e7
3
+ size 4728
run-2/checkpoint-145/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-58/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
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": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.36.2",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 30522
40
+ }
run-2/checkpoint-58/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48237df0662ea1f46fca3ff92ac36ecc5502954d6f349cf2e5f5cad2be507aca
3
+ size 437967876
run-2/checkpoint-58/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d206b7c192f8ccd8d51689ef15a0309529f22e6bb5abc348e0ccffabc97e6502
3
+ size 876056826
run-2/checkpoint-58/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4188fb36c6af1455d88af1b4bda5b12af16f7627165e44d5063e97eaaf69a464
3
+ size 14308
run-2/checkpoint-58/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04cda6ed8cc3972b06e24166925773e3b935cdf57f548421c272a569d90194cd
3
+ size 1064
run-2/checkpoint-58/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-2/checkpoint-58/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-58/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-2/checkpoint-58/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.574025974025974,
3
+ "best_model_checkpoint": "BiomedNLP-CIViC-evidence-level-finetuned/run-2/checkpoint-58",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 58,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_f1": 0.5038961038961038,
14
+ "eval_loss": 1.1599030494689941,
15
+ "eval_runtime": 3.0362,
16
+ "eval_samples_per_second": 126.804,
17
+ "eval_steps_per_second": 8.234,
18
+ "step": 29
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_f1": 0.574025974025974,
23
+ "eval_loss": 1.0611977577209473,
24
+ "eval_runtime": 3.0481,
25
+ "eval_samples_per_second": 126.308,
26
+ "eval_steps_per_second": 8.202,
27
+ "step": 58
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 145,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 5,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 4,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 1.2323346906015053e-05,
40
+ "num_train_epochs": 5,
41
+ "per_device_train_batch_size": 4,
42
+ "seed": 29
43
+ }
44
+ }
run-2/checkpoint-58/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b3ad8082a03e4c3f190076f53b72663d2faef012ff66aa71c0e32f2349565e7
3
+ size 4728
run-2/checkpoint-58/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-87/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
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": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.36.2",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 30522
40
+ }
run-2/checkpoint-87/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:967a31261abc01af6e7e5c124e7c22403dfc338f3e9ef8fcb122e7c329806e64
3
+ size 437967876
run-2/checkpoint-87/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:698c6cd6a29d6ca93d70a7a9c4e72010f7d8a1a6b798ef1c9399d12a841c54d2
3
+ size 876056826
run-2/checkpoint-87/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe75d87ed34c1fcfb4f810615213368393d6766814f95f5be1aa3e437de60084
3
+ size 14308
run-2/checkpoint-87/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7229330a93bcf7066a62e4690e3168564117967aab2ca9bf920a2d21bc2524f
3
+ size 1064
run-2/checkpoint-87/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-2/checkpoint-87/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-87/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-2/checkpoint-87/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.638961038961039,
3
+ "best_model_checkpoint": "BiomedNLP-CIViC-evidence-level-finetuned/run-2/checkpoint-87",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 87,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_f1": 0.5038961038961038,
14
+ "eval_loss": 1.1599030494689941,
15
+ "eval_runtime": 3.0362,
16
+ "eval_samples_per_second": 126.804,
17
+ "eval_steps_per_second": 8.234,
18
+ "step": 29
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_f1": 0.574025974025974,
23
+ "eval_loss": 1.0611977577209473,
24
+ "eval_runtime": 3.0481,
25
+ "eval_samples_per_second": 126.308,
26
+ "eval_steps_per_second": 8.202,
27
+ "step": 58
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_f1": 0.638961038961039,
32
+ "eval_loss": 1.00022554397583,
33
+ "eval_runtime": 3.0541,
34
+ "eval_samples_per_second": 126.06,
35
+ "eval_steps_per_second": 8.186,
36
+ "step": 87
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 145,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 5,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 4,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 1.2323346906015053e-05,
49
+ "num_train_epochs": 5,
50
+ "per_device_train_batch_size": 4,
51
+ "seed": 29
52
+ }
53
+ }
run-2/checkpoint-87/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b3ad8082a03e4c3f190076f53b72663d2faef012ff66aa71c0e32f2349565e7
3
+ size 4728
run-2/checkpoint-87/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-29/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
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": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3,
25
+ "LABEL_4": 4
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 0,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.36.2",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 30522
40
+ }
run-3/checkpoint-29/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efb8dee464d09473f7b3b89073600401d3be390d7e6b78b47211f577cd1f87e0
3
+ size 437967876
run-3/checkpoint-29/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03f4ebedd3bc1a735871cc53fb2c8ab2fb36ca18c430f7af8f98fb226e4b624e
3
+ size 876056826
run-3/checkpoint-29/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e59a875bc8f49cc4f7e7d45da4578f39b5c81492284b8d47575ee6759d1a547a
3
+ size 14244
run-3/checkpoint-29/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b304ca17268b09c8d177c932aa928cfa870526a790569e1b75e3b85d29957efd
3
+ size 1064