sunyyyoung commited on
Commit
27d48f6
1 Parent(s): 735a58b

Training in progress, epoch 1

Browse files
Files changed (50) hide show
  1. model.safetensors +1 -1
  2. run-7/checkpoint-268/config.json +25 -0
  3. run-7/checkpoint-268/model.safetensors +3 -0
  4. run-7/checkpoint-268/optimizer.pt +3 -0
  5. run-7/checkpoint-268/rng_state.pth +3 -0
  6. run-7/checkpoint-268/scheduler.pt +3 -0
  7. run-7/checkpoint-268/special_tokens_map.json +7 -0
  8. run-7/checkpoint-268/tokenizer.json +0 -0
  9. run-7/checkpoint-268/tokenizer_config.json +56 -0
  10. run-7/checkpoint-268/trainer_state.json +47 -0
  11. run-7/checkpoint-268/training_args.bin +3 -0
  12. run-7/checkpoint-268/vocab.txt +0 -0
  13. run-7/checkpoint-536/config.json +25 -0
  14. run-7/checkpoint-536/model.safetensors +3 -0
  15. run-7/checkpoint-536/optimizer.pt +3 -0
  16. run-7/checkpoint-536/rng_state.pth +3 -0
  17. run-7/checkpoint-536/scheduler.pt +3 -0
  18. run-7/checkpoint-536/special_tokens_map.json +7 -0
  19. run-7/checkpoint-536/tokenizer.json +0 -0
  20. run-7/checkpoint-536/tokenizer_config.json +56 -0
  21. run-7/checkpoint-536/trainer_state.json +63 -0
  22. run-7/checkpoint-536/training_args.bin +3 -0
  23. run-7/checkpoint-536/vocab.txt +0 -0
  24. run-7/checkpoint-804/config.json +25 -0
  25. run-7/checkpoint-804/model.safetensors +3 -0
  26. run-7/checkpoint-804/optimizer.pt +3 -0
  27. run-7/checkpoint-804/rng_state.pth +3 -0
  28. run-7/checkpoint-804/scheduler.pt +3 -0
  29. run-7/checkpoint-804/special_tokens_map.json +7 -0
  30. run-7/checkpoint-804/tokenizer.json +0 -0
  31. run-7/checkpoint-804/tokenizer_config.json +56 -0
  32. run-7/checkpoint-804/trainer_state.json +72 -0
  33. run-7/checkpoint-804/training_args.bin +3 -0
  34. run-7/checkpoint-804/vocab.txt +0 -0
  35. run-9/checkpoint-535/config.json +25 -0
  36. run-9/checkpoint-535/model.safetensors +3 -0
  37. run-9/checkpoint-535/optimizer.pt +3 -0
  38. run-9/checkpoint-535/rng_state.pth +3 -0
  39. run-9/checkpoint-535/scheduler.pt +3 -0
  40. run-9/checkpoint-535/special_tokens_map.json +7 -0
  41. run-9/checkpoint-535/tokenizer.json +0 -0
  42. run-9/checkpoint-535/tokenizer_config.json +56 -0
  43. run-9/checkpoint-535/trainer_state.json +54 -0
  44. run-9/checkpoint-535/training_args.bin +3 -0
  45. run-9/checkpoint-535/vocab.txt +0 -0
  46. runs/Aug12_10-26-35_sunyoungui-MacBookPro.local/events.out.tfevents.1723429406.sunyoungui-MacBookPro.local.38891.8 +3 -0
  47. runs/Aug12_10-26-35_sunyoungui-MacBookPro.local/events.out.tfevents.1723429438.sunyoungui-MacBookPro.local.38891.9 +3 -0
  48. runs/Aug12_10-26-35_sunyoungui-MacBookPro.local/events.out.tfevents.1723429627.sunyoungui-MacBookPro.local.38891.10 +3 -0
  49. runs/Aug12_10-26-35_sunyoungui-MacBookPro.local/events.out.tfevents.1723429812.sunyoungui-MacBookPro.local.38891.11 +3 -0
  50. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71fbc61b4d71e17521115b1b418e91307782657429ae63ff851d99b284583db9
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33ed3bad7df329693abffa9f26925e5c9d45276119dcab37fa716e71bb5587fd
3
  size 267832560
run-7/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": "4.44.0",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89588b09583b36927cd51fefb53e32624c756b5f7b1302e319f24276c22fd0bb
3
+ size 267832560
run-7/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:144da9b7104071c4c29a362490bc3c3b07aea00c81f0b3f27f02961e98b81e31
3
+ size 535724410
run-7/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17561bd1b409e99607864e654aa082ac523d39f8952723edca83e4f813d02954
3
+ size 13990
run-7/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03cd00ec052d4e4f401b2842f3f857dbdb066ba3e40b7217361378ebf5497867
3
+ size 1064
run-7/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-7/checkpoint-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-268/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "use_fase": true
56
+ }
run-7/checkpoint-268/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.44251427534495513,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-268",
4
+ "epoch": 1.0,
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": 0.4807068407535553,
14
+ "eval_matthews_correlation": 0.44251427534495513,
15
+ "eval_runtime": 2.9285,
16
+ "eval_samples_per_second": 356.153,
17
+ "eval_steps_per_second": 22.537,
18
+ "step": 268
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 804,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
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": false
34
+ },
35
+ "attributes": {}
36
+ }
37
+ },
38
+ "total_flos": 0,
39
+ "train_batch_size": 32,
40
+ "trial_name": null,
41
+ "trial_params": {
42
+ "learning_rate": 1.8941364810505247e-05,
43
+ "num_train_epochs": 3,
44
+ "per_device_train_batch_size": 32,
45
+ "seed": 9
46
+ }
47
+ }
run-7/checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66438cae448d1e6ebc679a9abf6c25a42630f333383b3a8ef58b7af1ce32a72f
3
+ size 5240
run-7/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-536/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": "4.44.0",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:869b59012b82258663e8c6ef947f3909db5e8f1b31a678b0f5e60e7a85feff10
3
+ size 267832560
run-7/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe8ed49ac7695faad03784b8ea24ba73e395cb0f4f579b841deea33344430e14
3
+ size 535724410
run-7/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2da61143788e3554e9d294e90d8ecfd5901b278b742e5a9528ea812690e29ccf
3
+ size 13990
run-7/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c92cd96121edb00f31564ef09408bf54addf24128a795cb0cfc0044cd0a05c24
3
+ size 1064
run-7/checkpoint-536/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-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-536/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "use_fase": true
56
+ }
run-7/checkpoint-536/trainer_state.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4971074930428892,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-536",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 536,
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": 0.4807068407535553,
14
+ "eval_matthews_correlation": 0.44251427534495513,
15
+ "eval_runtime": 2.9285,
16
+ "eval_samples_per_second": 356.153,
17
+ "eval_steps_per_second": 22.537,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.8656716417910446,
22
+ "grad_norm": 7.641021251678467,
23
+ "learning_rate": 7.161909082579098e-06,
24
+ "loss": 0.4547,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_loss": 0.47382214665412903,
30
+ "eval_matthews_correlation": 0.4971074930428892,
31
+ "eval_runtime": 2.8647,
32
+ "eval_samples_per_second": 364.081,
33
+ "eval_steps_per_second": 23.039,
34
+ "step": 536
35
+ }
36
+ ],
37
+ "logging_steps": 500,
38
+ "max_steps": 804,
39
+ "num_input_tokens_seen": 0,
40
+ "num_train_epochs": 3,
41
+ "save_steps": 500,
42
+ "stateful_callbacks": {
43
+ "TrainerControl": {
44
+ "args": {
45
+ "should_epoch_stop": false,
46
+ "should_evaluate": false,
47
+ "should_log": false,
48
+ "should_save": true,
49
+ "should_training_stop": false
50
+ },
51
+ "attributes": {}
52
+ }
53
+ },
54
+ "total_flos": 154401102149088.0,
55
+ "train_batch_size": 32,
56
+ "trial_name": null,
57
+ "trial_params": {
58
+ "learning_rate": 1.8941364810505247e-05,
59
+ "num_train_epochs": 3,
60
+ "per_device_train_batch_size": 32,
61
+ "seed": 9
62
+ }
63
+ }
run-7/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66438cae448d1e6ebc679a9abf6c25a42630f333383b3a8ef58b7af1ce32a72f
3
+ size 5240
run-7/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-804/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": "4.44.0",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-804/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c731f67eb66d9144d7f9c8c339157d0cff42bc970c316f509541510adab10c76
3
+ size 267832560
run-7/checkpoint-804/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b583798a39a0987f1b7c1c3186f9b55c33a1989ec3f7683f7a487fd7c2fa071
3
+ size 535724410
run-7/checkpoint-804/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ba6e078762f7af6923a7003319ffcb9926112b4d1d7815948b3177d65cb6af8
3
+ size 13990
run-7/checkpoint-804/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5c7fe36fb1eb2c498427ee73788e31cf9c48f743aa6d43f29415ed6a3bb03a9
3
+ size 1064
run-7/checkpoint-804/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-804/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-804/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "use_fase": true
56
+ }
run-7/checkpoint-804/trainer_state.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4971074930428892,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-536",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 804,
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": 0.4807068407535553,
14
+ "eval_matthews_correlation": 0.44251427534495513,
15
+ "eval_runtime": 2.9285,
16
+ "eval_samples_per_second": 356.153,
17
+ "eval_steps_per_second": 22.537,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.8656716417910446,
22
+ "grad_norm": 7.641021251678467,
23
+ "learning_rate": 7.161909082579098e-06,
24
+ "loss": 0.4547,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_loss": 0.47382214665412903,
30
+ "eval_matthews_correlation": 0.4971074930428892,
31
+ "eval_runtime": 2.8647,
32
+ "eval_samples_per_second": 364.081,
33
+ "eval_steps_per_second": 23.039,
34
+ "step": 536
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_loss": 0.5354584455490112,
39
+ "eval_matthews_correlation": 0.47933610275431493,
40
+ "eval_runtime": 3.1746,
41
+ "eval_samples_per_second": 328.544,
42
+ "eval_steps_per_second": 20.79,
43
+ "step": 804
44
+ }
45
+ ],
46
+ "logging_steps": 500,
47
+ "max_steps": 804,
48
+ "num_input_tokens_seen": 0,
49
+ "num_train_epochs": 3,
50
+ "save_steps": 500,
51
+ "stateful_callbacks": {
52
+ "TrainerControl": {
53
+ "args": {
54
+ "should_epoch_stop": false,
55
+ "should_evaluate": false,
56
+ "should_log": false,
57
+ "should_save": true,
58
+ "should_training_stop": true
59
+ },
60
+ "attributes": {}
61
+ }
62
+ },
63
+ "total_flos": 154401102149088.0,
64
+ "train_batch_size": 32,
65
+ "trial_name": null,
66
+ "trial_params": {
67
+ "learning_rate": 1.8941364810505247e-05,
68
+ "num_train_epochs": 3,
69
+ "per_device_train_batch_size": 32,
70
+ "seed": 9
71
+ }
72
+ }
run-7/checkpoint-804/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66438cae448d1e6ebc679a9abf6c25a42630f333383b3a8ef58b7af1ce32a72f
3
+ size 5240
run-7/checkpoint-804/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/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": "4.44.0",
24
+ "vocab_size": 30522
25
+ }
run-9/checkpoint-535/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33ed3bad7df329693abffa9f26925e5c9d45276119dcab37fa716e71bb5587fd
3
+ size 267832560
run-9/checkpoint-535/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a9cd513c8406925bfb7028d3e82ffecb01e35a9c0994984ff0150f91826ee04
3
+ size 535724410
run-9/checkpoint-535/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f7fc59c9d9470e65683d047a2afa7aeffe212060f14b18b1ea994ae1f6d983
3
+ size 13990
run-9/checkpoint-535/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc640817c6ad9b195fccb68141622ea2125c40f4f3ab478698bba0a112fc5c17
3
+ size 1064
run-9/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
+ }
run-9/checkpoint-535/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-535/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "use_fase": true
56
+ }
run-9/checkpoint-535/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.38864899256657126,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-535",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 535,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9345794392523364,
13
+ "grad_norm": 6.564955234527588,
14
+ "learning_rate": 7.548209058255054e-07,
15
+ "loss": 0.5363,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 0.5119006037712097,
21
+ "eval_matthews_correlation": 0.38864899256657126,
22
+ "eval_runtime": 3.3288,
23
+ "eval_samples_per_second": 313.33,
24
+ "eval_steps_per_second": 19.827,
25
+ "step": 535
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 535,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 1,
32
+ "save_steps": 500,
33
+ "stateful_callbacks": {
34
+ "TrainerControl": {
35
+ "args": {
36
+ "should_epoch_stop": false,
37
+ "should_evaluate": false,
38
+ "should_log": false,
39
+ "should_save": true,
40
+ "should_training_stop": true
41
+ },
42
+ "attributes": {}
43
+ }
44
+ },
45
+ "total_flos": 44866086983856.0,
46
+ "train_batch_size": 16,
47
+ "trial_name": null,
48
+ "trial_params": {
49
+ "learning_rate": 1.1537976703332727e-05,
50
+ "num_train_epochs": 1,
51
+ "per_device_train_batch_size": 16,
52
+ "seed": 22
53
+ }
54
+ }
run-9/checkpoint-535/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:531c5dfddc3550f10a6738ad73de4d85d5aeae07aa440522eb062348a152ece3
3
+ size 5240
run-9/checkpoint-535/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Aug12_10-26-35_sunyoungui-MacBookPro.local/events.out.tfevents.1723429406.sunyoungui-MacBookPro.local.38891.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ff7f8f56b5f82ea0a550104775dc1837f3cf2c4b390a99c95baa59fe7ac16d
3
+ size 5235
runs/Aug12_10-26-35_sunyoungui-MacBookPro.local/events.out.tfevents.1723429438.sunyoungui-MacBookPro.local.38891.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f05d7f34504754ffe1017c46b1ebf2266408b022950ad0bb45505ad44061329
3
+ size 6469
runs/Aug12_10-26-35_sunyoungui-MacBookPro.local/events.out.tfevents.1723429627.sunyoungui-MacBookPro.local.38891.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f9d24d6cfd15a00d3e2622fa8c1ff68c3d0904eaa7a9918b9c8a8f79f28cf85
3
+ size 6078
runs/Aug12_10-26-35_sunyoungui-MacBookPro.local/events.out.tfevents.1723429812.sunyoungui-MacBookPro.local.38891.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48c33a15804a271740c1ef568d840da4ecc3ddb55683a3e19e6987258f546394
3
+ size 5800
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9388419717ebf5648a6ebe38138f04e8e0ba5bc2a1e9b33539e4d290cbc8d79f
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:531c5dfddc3550f10a6738ad73de4d85d5aeae07aa440522eb062348a152ece3
3
  size 5240