Hugging Face's logo

stuser2023
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
stuser2023 commited on
Commit
80b7165
•
1 Parent(s): 5e13f23

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-4/checkpoint-268/config.json +25 -0
  3. run-4/checkpoint-268/model.safetensors +3 -0
  4. run-4/checkpoint-268/optimizer.pt +3 -0
  5. run-4/checkpoint-268/rng_state.pth +3 -0
  6. run-4/checkpoint-268/scheduler.pt +3 -0
  7. run-4/checkpoint-268/special_tokens_map.json +7 -0
  8. run-4/checkpoint-268/tokenizer.json +0 -0
  9. run-4/checkpoint-268/tokenizer_config.json +55 -0
  10. run-4/checkpoint-268/trainer_state.json +56 -0
  11. run-4/checkpoint-268/training_args.bin +3 -0
  12. run-4/checkpoint-268/vocab.txt +0 -0
  13. run-5/checkpoint-1069/config.json +25 -0
  14. run-5/checkpoint-1069/model.safetensors +3 -0
  15. run-5/checkpoint-1069/optimizer.pt +3 -0
  16. run-5/checkpoint-1069/rng_state.pth +3 -0
  17. run-5/checkpoint-1069/scheduler.pt +3 -0
  18. run-5/checkpoint-1069/special_tokens_map.json +7 -0
  19. run-5/checkpoint-1069/tokenizer.json +0 -0
  20. run-5/checkpoint-1069/tokenizer_config.json +55 -0
  21. run-5/checkpoint-1069/trainer_state.json +61 -0
  22. run-5/checkpoint-1069/training_args.bin +3 -0
  23. run-5/checkpoint-1069/vocab.txt +0 -0
  24. run-5/checkpoint-2138/config.json +1 -1
  25. run-5/checkpoint-2138/model.safetensors +1 -1
  26. run-5/checkpoint-2138/optimizer.pt +1 -1
  27. run-5/checkpoint-2138/rng_state.pth +1 -1
  28. run-5/checkpoint-2138/scheduler.pt +1 -1
  29. run-5/checkpoint-2138/trainer_state.json +54 -27
  30. run-5/checkpoint-2138/training_args.bin +2 -2
  31. run-5/checkpoint-3207/config.json +25 -0
  32. run-5/checkpoint-3207/model.safetensors +3 -0
  33. run-5/checkpoint-3207/optimizer.pt +3 -0
  34. run-5/checkpoint-3207/rng_state.pth +3 -0
  35. run-5/checkpoint-3207/scheduler.pt +3 -0
  36. run-5/checkpoint-3207/special_tokens_map.json +7 -0
  37. run-5/checkpoint-3207/tokenizer.json +0 -0
  38. run-5/checkpoint-3207/tokenizer_config.json +55 -0
  39. run-5/checkpoint-3207/trainer_state.json +107 -0
  40. run-5/checkpoint-3207/training_args.bin +3 -0
  41. run-5/checkpoint-3207/vocab.txt +0 -0
  42. run-7/checkpoint-134/config.json +25 -0
  43. run-7/checkpoint-134/model.safetensors +3 -0
  44. run-7/checkpoint-134/optimizer.pt +3 -0
  45. run-7/checkpoint-134/rng_state.pth +3 -0
  46. run-7/checkpoint-134/scheduler.pt +3 -0
  47. run-7/checkpoint-134/special_tokens_map.json +7 -0
  48. run-7/checkpoint-134/tokenizer.json +0 -0
  49. run-7/checkpoint-134/tokenizer_config.json +55 -0
  50. run-7/checkpoint-134/trainer_state.json +47 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4aa7079cdad18393c657923235d5cacae351eba7b6e15c6e3d8f8fc6a38d4428
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:456ebf946f9c57857bb13b535de13c2ce67997f85051fa8d1bb00d58f7d8cb65
3
  size 267832560
run-4/checkpoint-268/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": "4.45.0",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3443218a1d9411fea66daf6f4be0fe742dec756a2d4a6fec188c875b00d92ec
3
+ size 267832560
run-4/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:980ff927d10cd6890199d22de73ae92153f18bff57f5affb68d193ed587aad39
3
+ size 535727290
run-4/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e0bcc6a5693403aad5601bb77dbf11542238a9ca99f3b78f87bc59513f391ea
3
+ size 14244
run-4/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:572f4777e56a8b51fad2b8b43c27f3836a0064748423e6086e7e49a03aa30b5b
3
+ size 1064
run-4/checkpoint-268/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-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-268/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-268/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.34672852642073776,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-268",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 268,
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": 0.5480445623397827,
14
+ "eval_matthews_correlation": 0.1315571677438866,
15
+ "eval_runtime": 0.809,
16
+ "eval_samples_per_second": 1289.215,
17
+ "eval_steps_per_second": 81.58,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.528731644153595,
23
+ "eval_matthews_correlation": 0.34672852642073776,
24
+ "eval_runtime": 1.0218,
25
+ "eval_samples_per_second": 1020.75,
26
+ "eval_steps_per_second": 64.592,
27
+ "step": 268
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 268,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
+ "save_steps": 500,
35
+ "stateful_callbacks": {
36
+ "TrainerControl": {
37
+ "args": {
38
+ "should_epoch_stop": false,
39
+ "should_evaluate": false,
40
+ "should_log": false,
41
+ "should_save": true,
42
+ "should_training_stop": true
43
+ },
44
+ "attributes": {}
45
+ }
46
+ },
47
+ "total_flos": 0,
48
+ "train_batch_size": 64,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 7.4123504722847965e-06,
52
+ "num_train_epochs": 2,
53
+ "per_device_train_batch_size": 64,
54
+ "seed": 19
55
+ }
56
+ }
run-4/checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19cda161a8b2dbe3bebb87bfaa14d6f1770a695864450cbc067761031c985a6b
3
+ size 5304
run-4/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-1069/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": "4.45.0",
24
+ "vocab_size": 30522
25
+ }
run-5/checkpoint-1069/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a4e9960d584e041475d4be6b3a56fe707a037e0d91e6a2680daa958f628ddb0
3
+ size 267832560
run-5/checkpoint-1069/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bc273d775f2c7fcde2939610fe2c383e09b53a86adfd1774e3f750b0858d0ea
3
+ size 535727290
run-5/checkpoint-1069/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8395c8214014f21c712bfcadb3dcad1b45ae11208fe2256156f6df9ccc56b328
3
+ size 14244
run-5/checkpoint-1069/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c968b0d0c9e9e2e489510dc31e4230cd59d60d43be432ca1f5077bce7cdc223f
3
+ size 1064
run-5/checkpoint-1069/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-5/checkpoint-1069/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-1069/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-5/checkpoint-1069/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.45008318903303624,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-1069",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1069,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.4677268475210477,
13
+ "grad_norm": 4.435796737670898,
14
+ "learning_rate": 1.7076894081996187e-05,
15
+ "loss": 0.5421,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.9354536950420954,
20
+ "grad_norm": 13.997383117675781,
21
+ "learning_rate": 1.3922683871062276e-05,
22
+ "loss": 0.5008,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_loss": 0.4736253321170807,
28
+ "eval_matthews_correlation": 0.45008318903303624,
29
+ "eval_runtime": 0.7693,
30
+ "eval_samples_per_second": 1355.736,
31
+ "eval_steps_per_second": 85.79,
32
+ "step": 1069
33
+ }
34
+ ],
35
+ "logging_steps": 500,
36
+ "max_steps": 3207,
37
+ "num_input_tokens_seen": 0,
38
+ "num_train_epochs": 3,
39
+ "save_steps": 500,
40
+ "stateful_callbacks": {
41
+ "TrainerControl": {
42
+ "args": {
43
+ "should_epoch_stop": false,
44
+ "should_evaluate": false,
45
+ "should_log": false,
46
+ "should_save": true,
47
+ "should_training_stop": false
48
+ },
49
+ "attributes": {}
50
+ }
51
+ },
52
+ "total_flos": 37678695705216.0,
53
+ "train_batch_size": 8,
54
+ "trial_name": null,
55
+ "trial_params": {
56
+ "learning_rate": 2.0231104292930096e-05,
57
+ "num_train_epochs": 3,
58
+ "per_device_train_batch_size": 8,
59
+ "seed": 39
60
+ }
61
+ }
run-5/checkpoint-1069/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df0fa22c46aca8a11dbae71b270f677bbc7fe1ce3d02d40773470331a484b8b5
3
+ size 5304
run-5/checkpoint-1069/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-2138/config.json CHANGED
@@ -20,6 +20,6 @@
20
  "sinusoidal_pos_embds": false,
21
  "tie_weights_": true,
22
  "torch_dtype": "float32",
23
- "transformers_version": "4.35.2",
24
  "vocab_size": 30522
25
  }
 
20
  "sinusoidal_pos_embds": false,
21
  "tie_weights_": true,
22
  "torch_dtype": "float32",
23
+ "transformers_version": "4.45.0",
24
  "vocab_size": 30522
25
  }
run-5/checkpoint-2138/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7146b3ca7e9468f45433de50933b7660a70608b7c97361130c3410e071d86a08
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e763d616629dbaeddb5cd6064457abddc9c33b9b67459ef28eaa712e869b2f
3
  size 267832560
run-5/checkpoint-2138/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f591ec83c2348971f4bde2e836b668159c31c59540c8341354dfc75bae910141
3
  size 535727290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da28995cca7c5c5401f3eaf91bfe4f95cb5d0c1dc1b34412e2447dd391251330
3
  size 535727290
run-5/checkpoint-2138/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf783246e80bcb5beeb8b9e6145cba98a417523250d656e55ab4fc147ef82975
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66b3e0be5c484e9708809ec948cecf9d5d44d0484b9d8f517d73c248b0dabbb8
3
  size 14244
run-5/checkpoint-2138/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd3b6c378bbc56886ff42767c6f66523c73d41186530b59dfcfd9efed220f3b9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3565a60a07f2b2d8c552ab59fcd4e0f9eafcc0b6a8fb8c5a6db162309255a7e
3
  size 1064
run-5/checkpoint-2138/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.3489786582473965,
3
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-2138",
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
  "global_step": 2138,
7
  "is_hyper_param_search": true,
@@ -9,49 +9,76 @@
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.23,
13
- "learning_rate": 2.0303810286193334e-06,
14
- "loss": 0.6094,
 
15
  "step": 500
16
  },
17
  {
18
- "epoch": 0.47,
19
- "learning_rate": 1.9043017297731252e-06,
20
- "loss": 0.5899,
 
21
  "step": 1000
22
  },
23
  {
24
- "epoch": 0.7,
25
- "learning_rate": 1.7782224309269175e-06,
26
- "loss": 0.5665,
 
 
 
 
 
 
 
 
 
 
27
  "step": 1500
28
  },
29
  {
30
- "epoch": 0.94,
31
- "learning_rate": 1.6521431320807095e-06,
32
- "loss": 0.5457,
 
33
  "step": 2000
34
  },
35
  {
36
- "epoch": 1.0,
37
- "eval_loss": 0.5572062730789185,
38
- "eval_matthews_correlation": 0.3489786582473965,
39
- "eval_runtime": 0.7167,
40
- "eval_samples_per_second": 1455.295,
41
- "eval_steps_per_second": 92.09,
42
  "step": 2138
43
  }
44
  ],
45
  "logging_steps": 500,
46
- "max_steps": 8552,
47
- "num_train_epochs": 4,
 
48
  "save_steps": 500,
49
- "total_flos": 32728761582000.0,
 
 
 
 
 
 
 
 
 
 
 
 
 
50
  "trial_name": null,
51
  "trial_params": {
52
- "learning_rate": 2.1564603274655414e-06,
53
- "num_train_epochs": 4,
54
- "per_device_train_batch_size": 4,
55
- "seed": 27
56
  }
57
  }
 
1
  {
2
+ "best_metric": 0.4778162027316995,
3
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-2138",
4
+ "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 2138,
7
  "is_hyper_param_search": true,
 
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.4677268475210477,
13
+ "grad_norm": 4.435796737670898,
14
+ "learning_rate": 1.7076894081996187e-05,
15
+ "loss": 0.5421,
16
  "step": 500
17
  },
18
  {
19
+ "epoch": 0.9354536950420954,
20
+ "grad_norm": 13.997383117675781,
21
+ "learning_rate": 1.3922683871062276e-05,
22
+ "loss": 0.5008,
23
  "step": 1000
24
  },
25
  {
26
+ "epoch": 1.0,
27
+ "eval_loss": 0.4736253321170807,
28
+ "eval_matthews_correlation": 0.45008318903303624,
29
+ "eval_runtime": 0.7693,
30
+ "eval_samples_per_second": 1355.736,
31
+ "eval_steps_per_second": 85.79,
32
+ "step": 1069
33
+ },
34
+ {
35
+ "epoch": 1.4031805425631432,
36
+ "grad_norm": 34.2601432800293,
37
+ "learning_rate": 1.0768473660128366e-05,
38
+ "loss": 0.3575,
39
  "step": 1500
40
  },
41
  {
42
+ "epoch": 1.8709073900841908,
43
+ "grad_norm": 39.75000762939453,
44
+ "learning_rate": 7.6142634491944576e-06,
45
+ "loss": 0.3442,
46
  "step": 2000
47
  },
48
  {
49
+ "epoch": 2.0,
50
+ "eval_loss": 0.6032345294952393,
51
+ "eval_matthews_correlation": 0.4778162027316995,
52
+ "eval_runtime": 0.9252,
53
+ "eval_samples_per_second": 1127.3,
54
+ "eval_steps_per_second": 71.334,
55
  "step": 2138
56
  }
57
  ],
58
  "logging_steps": 500,
59
+ "max_steps": 3207,
60
+ "num_input_tokens_seen": 0,
61
+ "num_train_epochs": 3,
62
  "save_steps": 500,
63
+ "stateful_callbacks": {
64
+ "TrainerControl": {
65
+ "args": {
66
+ "should_epoch_stop": false,
67
+ "should_evaluate": false,
68
+ "should_log": false,
69
+ "should_save": true,
70
+ "should_training_stop": false
71
+ },
72
+ "attributes": {}
73
+ }
74
+ },
75
+ "total_flos": 75157137960120.0,
76
+ "train_batch_size": 8,
77
  "trial_name": null,
78
  "trial_params": {
79
+ "learning_rate": 2.0231104292930096e-05,
80
+ "num_train_epochs": 3,
81
+ "per_device_train_batch_size": 8,
82
+ "seed": 39
83
  }
84
  }
run-5/checkpoint-2138/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:692a73347812984741a703df47072293057562dff76f25cadbe1dfeff21891ed
3
- size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df0fa22c46aca8a11dbae71b270f677bbc7fe1ce3d02d40773470331a484b8b5
3
+ size 5304
run-5/checkpoint-3207/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": "4.45.0",
24
+ "vocab_size": 30522
25
+ }
run-5/checkpoint-3207/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01a4d6625c5d2d1b972c98ec2653c22ea046701b92b3b132ebcbcabf227cd5ac
3
+ size 267832560
run-5/checkpoint-3207/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82f4a5e4507b25e6de2cf449c3c2e78916a9e577f3bad052f90e51725e3b2899
3
+ size 535727290
run-5/checkpoint-3207/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6601f7684d4e7a2ad0855c22ca646cd482ac2241181ab51ade0e67f6ea75aac9
3
+ size 14244
run-5/checkpoint-3207/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53b4e84ba3cea53b70cab2521ece4522afbe9c594e051526c717149a8711208a
3
+ size 1064
run-5/checkpoint-3207/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-5/checkpoint-3207/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-3207/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-5/checkpoint-3207/trainer_state.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.48003141444537994,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-3207",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3207,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.4677268475210477,
13
+ "grad_norm": 4.435796737670898,
14
+ "learning_rate": 1.7076894081996187e-05,
15
+ "loss": 0.5421,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.9354536950420954,
20
+ "grad_norm": 13.997383117675781,
21
+ "learning_rate": 1.3922683871062276e-05,
22
+ "loss": 0.5008,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_loss": 0.4736253321170807,
28
+ "eval_matthews_correlation": 0.45008318903303624,
29
+ "eval_runtime": 0.7693,
30
+ "eval_samples_per_second": 1355.736,
31
+ "eval_steps_per_second": 85.79,
32
+ "step": 1069
33
+ },
34
+ {
35
+ "epoch": 1.4031805425631432,
36
+ "grad_norm": 34.2601432800293,
37
+ "learning_rate": 1.0768473660128366e-05,
38
+ "loss": 0.3575,
39
+ "step": 1500
40
+ },
41
+ {
42
+ "epoch": 1.8709073900841908,
43
+ "grad_norm": 39.75000762939453,
44
+ "learning_rate": 7.6142634491944576e-06,
45
+ "loss": 0.3442,
46
+ "step": 2000
47
+ },
48
+ {
49
+ "epoch": 2.0,
50
+ "eval_loss": 0.6032345294952393,
51
+ "eval_matthews_correlation": 0.4778162027316995,
52
+ "eval_runtime": 0.9252,
53
+ "eval_samples_per_second": 1127.3,
54
+ "eval_steps_per_second": 71.334,
55
+ "step": 2138
56
+ },
57
+ {
58
+ "epoch": 2.3386342376052385,
59
+ "grad_norm": 0.1156700998544693,
60
+ "learning_rate": 4.460053238260548e-06,
61
+ "loss": 0.2621,
62
+ "step": 2500
63
+ },
64
+ {
65
+ "epoch": 2.8063610851262863,
66
+ "grad_norm": 3.392853021621704,
67
+ "learning_rate": 1.3058430273266387e-06,
68
+ "loss": 0.2509,
69
+ "step": 3000
70
+ },
71
+ {
72
+ "epoch": 3.0,
73
+ "eval_loss": 0.8523973226547241,
74
+ "eval_matthews_correlation": 0.48003141444537994,
75
+ "eval_runtime": 1.072,
76
+ "eval_samples_per_second": 972.973,
77
+ "eval_steps_per_second": 61.569,
78
+ "step": 3207
79
+ }
80
+ ],
81
+ "logging_steps": 500,
82
+ "max_steps": 3207,
83
+ "num_input_tokens_seen": 0,
84
+ "num_train_epochs": 3,
85
+ "save_steps": 500,
86
+ "stateful_callbacks": {
87
+ "TrainerControl": {
88
+ "args": {
89
+ "should_epoch_stop": false,
90
+ "should_evaluate": false,
91
+ "should_log": false,
92
+ "should_save": true,
93
+ "should_training_stop": true
94
+ },
95
+ "attributes": {}
96
+ }
97
+ },
98
+ "total_flos": 112881369333624.0,
99
+ "train_batch_size": 8,
100
+ "trial_name": null,
101
+ "trial_params": {
102
+ "learning_rate": 2.0231104292930096e-05,
103
+ "num_train_epochs": 3,
104
+ "per_device_train_batch_size": 8,
105
+ "seed": 39
106
+ }
107
+ }
run-5/checkpoint-3207/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df0fa22c46aca8a11dbae71b270f677bbc7fe1ce3d02d40773470331a484b8b5
3
+ size 5304
run-5/checkpoint-3207/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-134/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": "4.45.0",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-134/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:456ebf946f9c57857bb13b535de13c2ce67997f85051fa8d1bb00d58f7d8cb65
3
+ size 267832560
run-7/checkpoint-134/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c58c0bca7f11d21ce9ed4f95ea8748093c8f78a598bad9d4f17cae8f11ccf37
3
+ size 535727290
run-7/checkpoint-134/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad23b78aed3c9e79501df8a355f560bf8a354f592b58b86387748de54e336feb
3
+ size 14244
run-7/checkpoint-134/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa51227af516c2f2e07542bdaae34bb0aa514e3c23ca871ae341c22d4632bb33
3
+ size 1064
run-7/checkpoint-134/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-134/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-134/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-134/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3897915466490148,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-134",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 134,
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": 0.5055169463157654,
14
+ "eval_matthews_correlation": 0.3897915466490148,
15
+ "eval_runtime": 0.9284,
16
+ "eval_samples_per_second": 1123.385,
17
+ "eval_steps_per_second": 71.087,
18
+ "step": 134
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 134,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 1,
25
+ "save_steps": 500,
26
+ "stateful_callbacks": {
27
+ "TrainerControl": {
28
+ "args": {
29
+ "should_epoch_stop": false,
30
+ "should_evaluate": false,
31
+ "should_log": false,
32
+ "should_save": true,
33
+ "should_training_stop": true
34
+ },
35
+ "attributes": {}
36
+ }
37
+ },
38
+ "total_flos": 0,
39
+ "train_batch_size": 64,
40
+ "trial_name": null,
41
+ "trial_params": {
42
+ "learning_rate": 3.156019559410918e-05,
43
+ "num_train_epochs": 1,
44
+ "per_device_train_batch_size": 64,
45
+ "seed": 22
46
+ }
47
+ }