Hugging Face's logo

ArtoriasXV
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files Metrics Community
ArtoriasXV commited on
Commit
1e4dfd7
·
verified ·
1 Parent(s): b83701f

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. run-7/checkpoint-107/config.json +25 -0
  2. run-7/checkpoint-107/model.safetensors +3 -0
  3. run-7/checkpoint-107/optimizer.pt +3 -0
  4. run-7/checkpoint-107/rng_state.pth +3 -0
  5. run-7/checkpoint-107/scheduler.pt +3 -0
  6. run-7/checkpoint-107/special_tokens_map.json +7 -0
  7. run-7/checkpoint-107/tokenizer.json +0 -0
  8. run-7/checkpoint-107/tokenizer_config.json +55 -0
  9. run-7/checkpoint-107/trainer_state.json +35 -0
  10. run-7/checkpoint-107/training_args.bin +3 -0
  11. run-7/checkpoint-107/vocab.txt +0 -0
  12. run-7/checkpoint-214/config.json +25 -0
  13. run-7/checkpoint-214/model.safetensors +3 -0
  14. run-7/checkpoint-214/optimizer.pt +3 -0
  15. run-7/checkpoint-214/rng_state.pth +3 -0
  16. run-7/checkpoint-214/scheduler.pt +3 -0
  17. run-7/checkpoint-214/special_tokens_map.json +7 -0
  18. run-7/checkpoint-214/tokenizer.json +0 -0
  19. run-7/checkpoint-214/tokenizer_config.json +55 -0
  20. run-7/checkpoint-214/trainer_state.json +44 -0
  21. run-7/checkpoint-214/training_args.bin +3 -0
  22. run-7/checkpoint-214/vocab.txt +0 -0
  23. run-7/checkpoint-321/config.json +25 -0
  24. run-7/checkpoint-321/model.safetensors +3 -0
  25. run-7/checkpoint-321/optimizer.pt +3 -0
  26. run-7/checkpoint-321/rng_state.pth +3 -0
  27. run-7/checkpoint-321/scheduler.pt +3 -0
  28. run-7/checkpoint-321/special_tokens_map.json +7 -0
  29. run-7/checkpoint-321/tokenizer.json +0 -0
  30. run-7/checkpoint-321/tokenizer_config.json +55 -0
  31. run-7/checkpoint-321/trainer_state.json +53 -0
  32. run-7/checkpoint-321/training_args.bin +3 -0
  33. run-7/checkpoint-321/vocab.txt +0 -0
  34. run-7/checkpoint-428/config.json +25 -0
  35. run-7/checkpoint-428/model.safetensors +3 -0
  36. run-7/checkpoint-428/optimizer.pt +3 -0
  37. run-7/checkpoint-428/rng_state.pth +3 -0
  38. run-7/checkpoint-428/scheduler.pt +3 -0
  39. run-7/checkpoint-428/special_tokens_map.json +7 -0
  40. run-7/checkpoint-428/tokenizer.json +0 -0
  41. run-7/checkpoint-428/tokenizer_config.json +55 -0
  42. run-7/checkpoint-428/trainer_state.json +62 -0
  43. run-7/checkpoint-428/training_args.bin +3 -0
  44. run-7/checkpoint-428/vocab.txt +0 -0
  45. run-7/checkpoint-535/config.json +25 -0
  46. run-7/checkpoint-535/model.safetensors +3 -0
  47. run-7/checkpoint-535/optimizer.pt +3 -0
  48. run-7/checkpoint-535/rng_state.pth +3 -0
  49. run-7/checkpoint-535/scheduler.pt +3 -0
  50. run-7/checkpoint-535/special_tokens_map.json +7 -0
run-7/checkpoint-107/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-107/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d437ba0557553d73bf13e7cfd9c98f8546c9629c982de7cccb897ccbfdad8906
3
+ size 267832560
run-7/checkpoint-107/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e336727f5448ac4bfcfddd11ec8fddbb56347301bfab127339e1a9e83c1a72
3
+ size 535727290
run-7/checkpoint-107/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be2120d1d50789132ac9f2846b83ff56a7a0eac7808c6e9fe3275091ccb640b7
3
+ size 14308
run-7/checkpoint-107/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efe82e6c9dce81a49d52a957a134e83fa0d8fe4590dbee0cd96839d46f6b911e
3
+ size 1064
run-7/checkpoint-107/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-7/checkpoint-107/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-107/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-7/checkpoint-107/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-107",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 107,
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": 0.5851200222969055,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7978,
16
+ "eval_samples_per_second": 1307.379,
17
+ "eval_steps_per_second": 82.73,
18
+ "step": 107
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 535,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 8,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 1.164598740352244e-05,
31
+ "num_train_epochs": 5,
32
+ "per_device_train_batch_size": 8,
33
+ "seed": 32
34
+ }
35
+ }
run-7/checkpoint-107/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5622bdb7172c1c8e962d591254e3206b4db43bc8557abbc9aa195dd03c32c6
3
+ size 4984
run-7/checkpoint-107/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-214/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebeaf201cb504531af3cfee83c72a54cce13ad22fedd72693e09dddc5a0bdc70
3
+ size 267832560
run-7/checkpoint-214/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92c9f54aa9b61551f0569f2bd3098787082a3b69ff41cc99bb193c8dfb6662f9
3
+ size 535727290
run-7/checkpoint-214/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13af4607fa7d24834eceba33898f42e3c67b77953d1919562f8522ecbbd578d
3
+ size 14308
run-7/checkpoint-214/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e633b92efd3aee0ee8976036ccaf5265138dd98a4912fb77c2bba140b3560e
3
+ size 1064
run-7/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-7/checkpoint-214/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/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-7/checkpoint-214/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.2275273801214544,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/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": 0.5851200222969055,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7978,
16
+ "eval_samples_per_second": 1307.379,
17
+ "eval_steps_per_second": 82.73,
18
+ "step": 107
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5744268894195557,
23
+ "eval_matthews_correlation": 0.2275273801214544,
24
+ "eval_runtime": 1.0908,
25
+ "eval_samples_per_second": 956.222,
26
+ "eval_steps_per_second": 60.509,
27
+ "step": 214
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 535,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 5,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 8,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 1.164598740352244e-05,
40
+ "num_train_epochs": 5,
41
+ "per_device_train_batch_size": 8,
42
+ "seed": 32
43
+ }
44
+ }
run-7/checkpoint-214/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5622bdb7172c1c8e962d591254e3206b4db43bc8557abbc9aa195dd03c32c6
3
+ size 4984
run-7/checkpoint-214/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-321/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26d2fe9bf2022007029f7ee57238f2719831a49e014b04cf0282022f103b439d
3
+ size 267832560
run-7/checkpoint-321/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf6b141c6e3f02039388b96f72f0d991ccc919a42600e138bf30ca31ee7ba111
3
+ size 535727290
run-7/checkpoint-321/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29a1c87639ddc20dd390458355d6cc2bde0984db9fb526d5bdf87f1ef645b655
3
+ size 14308
run-7/checkpoint-321/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:897e0958225faa74b872eea6ce0866fc2d3ce274b2fc059cc556c75713a03de3
3
+ size 1064
run-7/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-7/checkpoint-321/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/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-7/checkpoint-321/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.2961784685544828,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-321",
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": 0.5851200222969055,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7978,
16
+ "eval_samples_per_second": 1307.379,
17
+ "eval_steps_per_second": 82.73,
18
+ "step": 107
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5744268894195557,
23
+ "eval_matthews_correlation": 0.2275273801214544,
24
+ "eval_runtime": 1.0908,
25
+ "eval_samples_per_second": 956.222,
26
+ "eval_steps_per_second": 60.509,
27
+ "step": 214
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6517869830131531,
32
+ "eval_matthews_correlation": 0.2961784685544828,
33
+ "eval_runtime": 0.7604,
34
+ "eval_samples_per_second": 1371.685,
35
+ "eval_steps_per_second": 86.799,
36
+ "step": 321
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 535,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 5,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 8,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 1.164598740352244e-05,
49
+ "num_train_epochs": 5,
50
+ "per_device_train_batch_size": 8,
51
+ "seed": 32
52
+ }
53
+ }
run-7/checkpoint-321/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5622bdb7172c1c8e962d591254e3206b4db43bc8557abbc9aa195dd03c32c6
3
+ size 4984
run-7/checkpoint-321/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-428/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-428/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:377a1c54ca7fe428e83fa4360a9069d69fccbbf542669d60f2bd9c11ee3bc8d0
3
+ size 267832560
run-7/checkpoint-428/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b4cfc077922e6bafc0574ffbd8c2a15c30ebb2df155325fab648229ac4794ce
3
+ size 535727290
run-7/checkpoint-428/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b14913766ca819c158e4de6a4969e3bd6d6970185b317386ef97581ac5cf22
3
+ size 14308
run-7/checkpoint-428/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e55f5854398dba02c8d18e74a742b2da8bb0cc859efa12cd1e513695e4d6858f
3
+ size 1064
run-7/checkpoint-428/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-7/checkpoint-428/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-428/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-7/checkpoint-428/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.309481632674114,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-428",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 428,
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": 0.5851200222969055,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7978,
16
+ "eval_samples_per_second": 1307.379,
17
+ "eval_steps_per_second": 82.73,
18
+ "step": 107
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5744268894195557,
23
+ "eval_matthews_correlation": 0.2275273801214544,
24
+ "eval_runtime": 1.0908,
25
+ "eval_samples_per_second": 956.222,
26
+ "eval_steps_per_second": 60.509,
27
+ "step": 214
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6517869830131531,
32
+ "eval_matthews_correlation": 0.2961784685544828,
33
+ "eval_runtime": 0.7604,
34
+ "eval_samples_per_second": 1371.685,
35
+ "eval_steps_per_second": 86.799,
36
+ "step": 321
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.680811882019043,
41
+ "eval_matthews_correlation": 0.309481632674114,
42
+ "eval_runtime": 0.8061,
43
+ "eval_samples_per_second": 1293.864,
44
+ "eval_steps_per_second": 81.874,
45
+ "step": 428
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 535,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 5,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 8,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 1.164598740352244e-05,
58
+ "num_train_epochs": 5,
59
+ "per_device_train_batch_size": 8,
60
+ "seed": 32
61
+ }
62
+ }
run-7/checkpoint-428/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5622bdb7172c1c8e962d591254e3206b4db43bc8557abbc9aa195dd03c32c6
3
+ size 4984
run-7/checkpoint-428/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-535/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-535/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4401137e29298acc741ef85d9ea53a6dccee1b8ca7bc1f815624244fdb9be4a
3
+ size 267832560
run-7/checkpoint-535/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb387c604c50fdd5ea207573e71c8a23f329d1b5b1628431ef3e7520b71b910
3
+ size 535727290
run-7/checkpoint-535/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:debc4e3288c8977ad4f5f0a162f9f158af822a12fdf326bed7284cedd6795cc9
3
+ size 14308
run-7/checkpoint-535/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b9a4617aa09b41e2a5a9d14bd3826e789d2ede9ccd3638b0795c470652c124a
3
+ size 1064
run-7/checkpoint-535/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
+ }