Ketskapow commited on
Commit
7122882
·
verified ·
1 Parent(s): 48c5f3f

Training in progress, epoch 2

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-4/checkpoint-214/config.json +25 -0
  3. run-4/checkpoint-214/model.safetensors +3 -0
  4. run-4/checkpoint-214/optimizer.pt +3 -0
  5. run-4/checkpoint-214/rng_state.pth +3 -0
  6. run-4/checkpoint-214/scheduler.pt +3 -0
  7. run-4/checkpoint-214/special_tokens_map.json +7 -0
  8. run-4/checkpoint-214/tokenizer.json +0 -0
  9. run-4/checkpoint-214/tokenizer_config.json +55 -0
  10. run-4/checkpoint-214/trainer_state.json +44 -0
  11. run-4/checkpoint-214/training_args.bin +3 -0
  12. run-4/checkpoint-214/vocab.txt +0 -0
  13. run-4/checkpoint-321/config.json +25 -0
  14. run-4/checkpoint-321/model.safetensors +3 -0
  15. run-4/checkpoint-321/optimizer.pt +3 -0
  16. run-4/checkpoint-321/rng_state.pth +3 -0
  17. run-4/checkpoint-321/scheduler.pt +3 -0
  18. run-4/checkpoint-321/special_tokens_map.json +7 -0
  19. run-4/checkpoint-321/tokenizer.json +0 -0
  20. run-4/checkpoint-321/tokenizer_config.json +55 -0
  21. run-4/checkpoint-321/trainer_state.json +53 -0
  22. run-4/checkpoint-321/training_args.bin +3 -0
  23. run-4/checkpoint-321/vocab.txt +0 -0
  24. run-8/checkpoint-108/config.json +25 -0
  25. run-8/checkpoint-108/model.safetensors +3 -0
  26. run-8/checkpoint-108/optimizer.pt +3 -0
  27. run-8/checkpoint-108/rng_state.pth +3 -0
  28. run-8/checkpoint-108/scheduler.pt +3 -0
  29. run-8/checkpoint-108/special_tokens_map.json +7 -0
  30. run-8/checkpoint-108/tokenizer.json +0 -0
  31. run-8/checkpoint-108/tokenizer_config.json +55 -0
  32. run-8/checkpoint-108/trainer_state.json +62 -0
  33. run-8/checkpoint-108/training_args.bin +3 -0
  34. run-8/checkpoint-108/vocab.txt +0 -0
  35. run-8/checkpoint-135/config.json +25 -0
  36. run-8/checkpoint-135/model.safetensors +3 -0
  37. run-8/checkpoint-135/optimizer.pt +3 -0
  38. run-8/checkpoint-135/rng_state.pth +3 -0
  39. run-8/checkpoint-135/scheduler.pt +3 -0
  40. run-8/checkpoint-135/special_tokens_map.json +7 -0
  41. run-8/checkpoint-135/tokenizer.json +0 -0
  42. run-8/checkpoint-135/tokenizer_config.json +55 -0
  43. run-8/checkpoint-135/trainer_state.json +71 -0
  44. run-8/checkpoint-135/training_args.bin +3 -0
  45. run-8/checkpoint-135/vocab.txt +0 -0
  46. run-8/checkpoint-27/config.json +25 -0
  47. run-8/checkpoint-27/model.safetensors +3 -0
  48. run-8/checkpoint-27/optimizer.pt +3 -0
  49. run-8/checkpoint-27/rng_state.pth +3 -0
  50. run-8/checkpoint-27/scheduler.pt +3 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abae716af60ef08df4cfda8630d61b2a17e55b01951217054670529e3ef70248
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77c2b7529d0fc011f1b68431931d2abd099e58914e531726ff0d1d6e228bf763
3
  size 267832560
run-4/checkpoint-214/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-214/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e4f0139b7c3cdc552269a802a493048ead5da175b3107303662e7b32c7882e0
3
+ size 267832560
run-4/checkpoint-214/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be58717a40696dded28f6d1f3ec856fd22a3ef9d249bac0a8f343ff2ba786aae
3
+ size 535727290
run-4/checkpoint-214/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1e684b224f52ebe6d621443c80e405395f81e1d76627f9c4e29b63d527940e4
3
+ size 14308
run-4/checkpoint-214/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8040697797fc04e139c6db45c3deb11e44d2e8d790bf2037c11c71d63361ed0e
3
+ size 1064
run-4/checkpoint-214/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-4/checkpoint-214/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-214/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-4/checkpoint-214/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.22572628843417145,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-214",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 214,
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_loss": 0.6111112833023071,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.6707,
16
+ "eval_samples_per_second": 1555.045,
17
+ "eval_steps_per_second": 98.402,
18
+ "step": 107
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.650396466255188,
23
+ "eval_matthews_correlation": 0.22572628843417145,
24
+ "eval_runtime": 0.753,
25
+ "eval_samples_per_second": 1385.204,
26
+ "eval_steps_per_second": 87.654,
27
+ "step": 214
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 321,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 8,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 9.050087494888513e-05,
40
+ "num_train_epochs": 3,
41
+ "per_device_train_batch_size": 8,
42
+ "seed": 24
43
+ }
44
+ }
run-4/checkpoint-214/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e59fc4da2d33b8f536673ffdc9385a7429d46124b8cb2a495dc6969510ec995d
3
+ size 4984
run-4/checkpoint-214/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-321/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-321/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0508bdffc60258a68e62e759a60e6f8d636d93435f85b55b0c24f94878f79f55
3
+ size 267832560
run-4/checkpoint-321/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97a0c1273d1694d2b9b59f596c3eec6c59d00b6e775ae27c7d0dc7a28a844f00
3
+ size 535727290
run-4/checkpoint-321/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fdcf411aa064e6835685d69d21c63e9b81392a6ec2fadcce4e9d337b1fbdae2
3
+ size 14308
run-4/checkpoint-321/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e70c2b185b8264cccd10b048a578ff29a46b36b24a1975b4b906ba570662ad88
3
+ size 1064
run-4/checkpoint-321/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-4/checkpoint-321/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-321/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-4/checkpoint-321/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.22572628843417145,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-214",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 321,
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_loss": 0.6111112833023071,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.6707,
16
+ "eval_samples_per_second": 1555.045,
17
+ "eval_steps_per_second": 98.402,
18
+ "step": 107
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.650396466255188,
23
+ "eval_matthews_correlation": 0.22572628843417145,
24
+ "eval_runtime": 0.753,
25
+ "eval_samples_per_second": 1385.204,
26
+ "eval_steps_per_second": 87.654,
27
+ "step": 214
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 1.3015365600585938,
32
+ "eval_matthews_correlation": 0.21894626694065988,
33
+ "eval_runtime": 0.7997,
34
+ "eval_samples_per_second": 1304.27,
35
+ "eval_steps_per_second": 82.533,
36
+ "step": 321
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 321,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 3,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 8,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 9.050087494888513e-05,
49
+ "num_train_epochs": 3,
50
+ "per_device_train_batch_size": 8,
51
+ "seed": 24
52
+ }
53
+ }
run-4/checkpoint-321/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e59fc4da2d33b8f536673ffdc9385a7429d46124b8cb2a495dc6969510ec995d
3
+ size 4984
run-4/checkpoint-321/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-108/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-8/checkpoint-108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaef06a1cc1d4e112e67871fca687aafa3d24657847fa0c22c205d25b7c775ae
3
+ size 267832560
run-8/checkpoint-108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b245908c522b88cb8f7f2a511e1b243dff201706782fc4456f53df8704b2d8cb
3
+ size 535727290
run-8/checkpoint-108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8371dc77c66ec96b24e07becbfd23d83184b32b0a0b84acb61d7a72d8d68afb9
3
+ size 14180
run-8/checkpoint-108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77ca4ce0092abbb024680e1b49996d2783572933a476354c0f90e7bc9a33a0ac
3
+ size 1064
run-8/checkpoint-108/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-8/checkpoint-108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-108/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-8/checkpoint-108/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-27",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 108,
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_loss": 0.633733332157135,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.6697,
16
+ "eval_samples_per_second": 1557.488,
17
+ "eval_steps_per_second": 98.556,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6165023446083069,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7416,
25
+ "eval_samples_per_second": 1406.449,
26
+ "eval_steps_per_second": 88.999,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6124085187911987,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 1.1629,
34
+ "eval_samples_per_second": 896.912,
35
+ "eval_steps_per_second": 56.756,
36
+ "step": 81
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.6108661890029907,
41
+ "eval_matthews_correlation": 0.0,
42
+ "eval_runtime": 0.7826,
43
+ "eval_samples_per_second": 1332.656,
44
+ "eval_steps_per_second": 84.329,
45
+ "step": 108
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 135,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 5,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 32,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 3.31601991514513e-06,
58
+ "num_train_epochs": 5,
59
+ "per_device_train_batch_size": 32,
60
+ "seed": 10
61
+ }
62
+ }
run-8/checkpoint-108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:876f865852373c961be6839854711de35bf3d97e08e0fde070ac6f4b53432187
3
+ size 4984
run-8/checkpoint-108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-135/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-8/checkpoint-135/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a97b8b070c5c3ed33550d8d9c98ac0f5b717087c304e2d27c075b647f127147f
3
+ size 267832560
run-8/checkpoint-135/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d6efd5841a5acf584c47deed17fefdf3f785072873976e655342182e65313b5
3
+ size 535727290
run-8/checkpoint-135/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cd53b90dd5a4c271bf3850d8fe3d9864fcd30be7cb64af7d81ffd526a334aa4
3
+ size 14180
run-8/checkpoint-135/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6cb31490cf03be26cb0df4d192cf8a6d29826537255b2c44e6ae1923421423f
3
+ size 1064
run-8/checkpoint-135/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-8/checkpoint-135/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-135/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-8/checkpoint-135/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-27",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 135,
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_loss": 0.633733332157135,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.6697,
16
+ "eval_samples_per_second": 1557.488,
17
+ "eval_steps_per_second": 98.556,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6165023446083069,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7416,
25
+ "eval_samples_per_second": 1406.449,
26
+ "eval_steps_per_second": 88.999,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6124085187911987,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 1.1629,
34
+ "eval_samples_per_second": 896.912,
35
+ "eval_steps_per_second": 56.756,
36
+ "step": 81
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.6108661890029907,
41
+ "eval_matthews_correlation": 0.0,
42
+ "eval_runtime": 0.7826,
43
+ "eval_samples_per_second": 1332.656,
44
+ "eval_steps_per_second": 84.329,
45
+ "step": 108
46
+ },
47
+ {
48
+ "epoch": 5.0,
49
+ "eval_loss": 0.6103748679161072,
50
+ "eval_matthews_correlation": 0.0,
51
+ "eval_runtime": 1.0941,
52
+ "eval_samples_per_second": 953.3,
53
+ "eval_steps_per_second": 60.324,
54
+ "step": 135
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 135,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 5,
61
+ "save_steps": 500,
62
+ "total_flos": 0,
63
+ "train_batch_size": 32,
64
+ "trial_name": null,
65
+ "trial_params": {
66
+ "learning_rate": 3.31601991514513e-06,
67
+ "num_train_epochs": 5,
68
+ "per_device_train_batch_size": 32,
69
+ "seed": 10
70
+ }
71
+ }
run-8/checkpoint-135/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:876f865852373c961be6839854711de35bf3d97e08e0fde070ac6f4b53432187
3
+ size 4984
run-8/checkpoint-135/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-27/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-8/checkpoint-27/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86cab5e1e8bf70cc615f5e3eab427a5d30df34194b2a7d193ccee770db5eabe3
3
+ size 267832560
run-8/checkpoint-27/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:724aaaa5536cfc3ae2a3b5ddb577bdf4e90876847e63f45f9dca48dc7cb3801b
3
+ size 535727290
run-8/checkpoint-27/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be2e61cfb32bd0131c8524d0f66b7881e91890fc6d136be5e1c3e92c518e8271
3
+ size 14180
run-8/checkpoint-27/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70d1d5e7125cc0cda6a38bbc08512bb9d0ed1e6f604b45d474557ef44cdb6824
3
+ size 1064