CCChenRyan commited on
Commit
a401230
·
1 Parent(s): e9d0438

Training in progress, epoch 1

Browse files
Files changed (48) hide show
  1. model.safetensors +1 -1
  2. run-5/checkpoint-1072/config.json +25 -0
  3. run-5/checkpoint-1072/model.safetensors +3 -0
  4. run-5/checkpoint-1072/optimizer.pt +3 -0
  5. run-5/checkpoint-1072/rng_state.pth +3 -0
  6. run-5/checkpoint-1072/scheduler.pt +3 -0
  7. run-5/checkpoint-1072/special_tokens_map.json +7 -0
  8. run-5/checkpoint-1072/tokenizer.json +0 -0
  9. run-5/checkpoint-1072/tokenizer_config.json +55 -0
  10. run-5/checkpoint-1072/trainer_state.json +74 -0
  11. run-5/checkpoint-1072/training_args.bin +3 -0
  12. run-5/checkpoint-1072/vocab.txt +0 -0
  13. run-5/checkpoint-536/config.json +25 -0
  14. run-5/checkpoint-536/model.safetensors +3 -0
  15. run-5/checkpoint-536/optimizer.pt +3 -0
  16. run-5/checkpoint-536/rng_state.pth +3 -0
  17. run-5/checkpoint-536/scheduler.pt +3 -0
  18. run-5/checkpoint-536/special_tokens_map.json +7 -0
  19. run-5/checkpoint-536/tokenizer.json +0 -0
  20. run-5/checkpoint-536/tokenizer_config.json +55 -0
  21. run-5/checkpoint-536/trainer_state.json +50 -0
  22. run-5/checkpoint-536/training_args.bin +3 -0
  23. run-5/checkpoint-536/vocab.txt +0 -0
  24. run-5/checkpoint-804/config.json +25 -0
  25. run-5/checkpoint-804/model.safetensors +3 -0
  26. run-5/checkpoint-804/optimizer.pt +3 -0
  27. run-5/checkpoint-804/rng_state.pth +3 -0
  28. run-5/checkpoint-804/scheduler.pt +3 -0
  29. run-5/checkpoint-804/special_tokens_map.json +7 -0
  30. run-5/checkpoint-804/tokenizer.json +0 -0
  31. run-5/checkpoint-804/tokenizer_config.json +55 -0
  32. run-5/checkpoint-804/trainer_state.json +59 -0
  33. run-5/checkpoint-804/training_args.bin +3 -0
  34. run-5/checkpoint-804/vocab.txt +0 -0
  35. run-6/checkpoint-2138/config.json +25 -0
  36. run-6/checkpoint-2138/model.safetensors +3 -0
  37. run-6/checkpoint-2138/optimizer.pt +3 -0
  38. run-6/checkpoint-2138/rng_state.pth +3 -0
  39. run-6/checkpoint-2138/scheduler.pt +3 -0
  40. run-6/checkpoint-2138/special_tokens_map.json +7 -0
  41. run-6/checkpoint-2138/tokenizer.json +0 -0
  42. run-6/checkpoint-2138/tokenizer_config.json +55 -0
  43. run-6/checkpoint-2138/trainer_state.json +59 -0
  44. run-6/checkpoint-2138/training_args.bin +3 -0
  45. run-6/checkpoint-2138/vocab.txt +0 -0
  46. runs/Dec23_02-09-17_17d63b357dd6/events.out.tfevents.1703299674.17d63b357dd6.603.11 +3 -0
  47. runs/Dec23_02-09-17_17d63b357dd6/events.out.tfevents.1703299935.17d63b357dd6.603.12 +3 -0
  48. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25daf07409ec996fae9e57deab56fcc7473035cbcb97d8c49193cc43ba6550b3
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afd7e3f739fc725a31194e0963d57f779474df4b70a95d4c9bef9b54bf51ba58
3
  size 267832560
run-5/checkpoint-1072/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-5/checkpoint-1072/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d33edbb32be3e1c1cbbf5828a8ecee31658bbd152bcea351aa151b7dd7cabcb
3
+ size 267832560
run-5/checkpoint-1072/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c7c1757c1c8d71bdff1356e3fb31649015dd177e602cddbdf91201784758b0
3
+ size 535727290
run-5/checkpoint-1072/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3840dc50ad097623ab7fc2864dede518bceb43b090c56e2487574144aff0bb5
3
+ size 14244
run-5/checkpoint-1072/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a0be84372652c8dd640f7151e01a72438331a9b2476820f2d6ce1c45d4865ad
3
+ size 1064
run-5/checkpoint-1072/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-1072/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-1072/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-1072/trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.10385466804655791,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-1072",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1072,
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": 0.6024530529975891,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.6923,
16
+ "eval_samples_per_second": 1506.579,
17
+ "eval_steps_per_second": 95.335,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 8.802625776355687e-07,
23
+ "loss": 0.6062,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.5769068598747253,
29
+ "eval_matthews_correlation": 0.0,
30
+ "eval_runtime": 0.7747,
31
+ "eval_samples_per_second": 1346.272,
32
+ "eval_steps_per_second": 85.191,
33
+ "step": 536
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_loss": 0.5617178082466125,
38
+ "eval_matthews_correlation": 0.0463559874942472,
39
+ "eval_runtime": 0.7838,
40
+ "eval_samples_per_second": 1330.753,
41
+ "eval_steps_per_second": 84.209,
42
+ "step": 804
43
+ },
44
+ {
45
+ "epoch": 3.73,
46
+ "learning_rate": 1.1080228249958206e-07,
47
+ "loss": 0.5527,
48
+ "step": 1000
49
+ },
50
+ {
51
+ "epoch": 4.0,
52
+ "eval_loss": 0.5563742518424988,
53
+ "eval_matthews_correlation": 0.10385466804655791,
54
+ "eval_runtime": 0.7678,
55
+ "eval_samples_per_second": 1358.352,
56
+ "eval_steps_per_second": 85.955,
57
+ "step": 1072
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 1072,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 4,
64
+ "save_steps": 500,
65
+ "total_flos": 191584080010896.0,
66
+ "train_batch_size": 32,
67
+ "trial_name": null,
68
+ "trial_params": {
69
+ "learning_rate": 1.6497228727715551e-06,
70
+ "num_train_epochs": 4,
71
+ "per_device_train_batch_size": 32,
72
+ "seed": 35
73
+ }
74
+ }
run-5/checkpoint-1072/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa94f6fedd1ffd00387b8f7042c989702695491062f18c59c02dc925b47f5382
3
+ size 4792
run-5/checkpoint-1072/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-5/checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb1e7472491395b4365f32b85076e45f5bdc94926d9e29e614430abed3f750de
3
+ size 267832560
run-5/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139e5119db217c2a04b8595a60d79bb856f5f2108ce269fdfdf2bcd2204527f8
3
+ size 535727290
run-5/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:315d615170352f81a843271ac53ce46195d2c088e4fcb1224c85a000d580946a
3
+ size 14244
run-5/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d2772ef44999430c82dd4c49498e7303c21d51f6a26407679e6177f6bb3f816
3
+ size 1064
run-5/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-5/checkpoint-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-536/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-536/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-268",
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": 0.6024530529975891,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.6923,
16
+ "eval_samples_per_second": 1506.579,
17
+ "eval_steps_per_second": 95.335,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 8.802625776355687e-07,
23
+ "loss": 0.6062,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.5769068598747253,
29
+ "eval_matthews_correlation": 0.0,
30
+ "eval_runtime": 0.7747,
31
+ "eval_samples_per_second": 1346.272,
32
+ "eval_steps_per_second": 85.191,
33
+ "step": 536
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 1072,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 4,
40
+ "save_steps": 500,
41
+ "total_flos": 96433161516912.0,
42
+ "train_batch_size": 32,
43
+ "trial_name": null,
44
+ "trial_params": {
45
+ "learning_rate": 1.6497228727715551e-06,
46
+ "num_train_epochs": 4,
47
+ "per_device_train_batch_size": 32,
48
+ "seed": 35
49
+ }
50
+ }
run-5/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa94f6fedd1ffd00387b8f7042c989702695491062f18c59c02dc925b47f5382
3
+ size 4792
run-5/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-5/checkpoint-804/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a3b3d9c152ab8f971d4175471f50c230ed61e0790d40d4b6c62be0e439b21a
3
+ size 267832560
run-5/checkpoint-804/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14f7811473dc8df84b28f736c61533f881e69ae993fe5022380a31495c9156c5
3
+ size 535727290
run-5/checkpoint-804/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f81aeb423c228581f06711a778270cb378db190aea152c19862ab0ccc9c80160
3
+ size 14244
run-5/checkpoint-804/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19916f3e89e9de3f8ee279ed3070b841f4656d1eb1ecf1420f68afdb502643de
3
+ size 1064
run-5/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-5/checkpoint-804/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-804/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-804/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0463559874942472,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-804",
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": 0.6024530529975891,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.6923,
16
+ "eval_samples_per_second": 1506.579,
17
+ "eval_steps_per_second": 95.335,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 8.802625776355687e-07,
23
+ "loss": 0.6062,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.5769068598747253,
29
+ "eval_matthews_correlation": 0.0,
30
+ "eval_runtime": 0.7747,
31
+ "eval_samples_per_second": 1346.272,
32
+ "eval_steps_per_second": 85.191,
33
+ "step": 536
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_loss": 0.5617178082466125,
38
+ "eval_matthews_correlation": 0.0463559874942472,
39
+ "eval_runtime": 0.7838,
40
+ "eval_samples_per_second": 1330.753,
41
+ "eval_steps_per_second": 84.209,
42
+ "step": 804
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 1072,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 4,
49
+ "save_steps": 500,
50
+ "total_flos": 96433161516912.0,
51
+ "train_batch_size": 32,
52
+ "trial_name": null,
53
+ "trial_params": {
54
+ "learning_rate": 1.6497228727715551e-06,
55
+ "num_train_epochs": 4,
56
+ "per_device_train_batch_size": 32,
57
+ "seed": 35
58
+ }
59
+ }
run-5/checkpoint-804/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa94f6fedd1ffd00387b8f7042c989702695491062f18c59c02dc925b47f5382
3
+ size 4792
run-5/checkpoint-804/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-2138/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-2138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb2bd56e91ae38bd4eeed97895220e3c0f087098fcc046fb29f10fedd11cb74
3
+ size 267832560
run-6/checkpoint-2138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac7f62cf86e4e060c4df3192c28ff7e033d14e1f5ee48405365e9589a6f90a4e
3
+ size 535727290
run-6/checkpoint-2138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c12b402924edc75ce8556990cfab2365d12bc53c5d9ee0c5f58a63606c7c4a5
3
+ size 14308
run-6/checkpoint-2138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b667fdaf04e1bc3a96c425985b6bae791231cb806e179df8a1f3828d8c520e0
3
+ size 1064
run-6/checkpoint-2138/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-6/checkpoint-2138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-2138/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-6/checkpoint-2138/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.46718843812774224,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-2138",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2138,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.23,
13
+ "learning_rate": 1.1719121295456048e-05,
14
+ "loss": 0.5754,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 8.141855942752735e-06,
20
+ "loss": 0.5394,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 4.564590590049425e-06,
26
+ "loss": 0.5396,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 9.87325237346114e-07,
32
+ "loss": 0.5291,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 0.5313145518302917,
38
+ "eval_matthews_correlation": 0.46718843812774224,
39
+ "eval_runtime": 0.7498,
40
+ "eval_samples_per_second": 1391.059,
41
+ "eval_steps_per_second": 88.025,
42
+ "step": 2138
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 2138,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 1,
49
+ "save_steps": 500,
50
+ "total_flos": 32685295716816.0,
51
+ "train_batch_size": 4,
52
+ "trial_name": null,
53
+ "trial_params": {
54
+ "learning_rate": 1.529638664815936e-05,
55
+ "num_train_epochs": 1,
56
+ "per_device_train_batch_size": 4,
57
+ "seed": 13
58
+ }
59
+ }
run-6/checkpoint-2138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d7d8196856971d181379a337ec9149292a2f9e37f46289d0e16675da83cf607
3
+ size 4792
run-6/checkpoint-2138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-09-17_17d63b357dd6/events.out.tfevents.1703299674.17d63b357dd6.603.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c81cee7ccd6a527c884f195777661d3a037c7ebc0c9c43538a4de2a0243b4d3d
3
+ size 5662
runs/Dec23_02-09-17_17d63b357dd6/events.out.tfevents.1703299935.17d63b357dd6.603.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3764e2f65bcd3e50e2bcfc7aeafaa04820d6f765607c0181a16833f3987a3780
3
+ size 5192
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa94f6fedd1ffd00387b8f7042c989702695491062f18c59c02dc925b47f5382
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46519a6bce092ae403faec562a8ebb7c3b17199d44f00eb39244ebd8bcca25a5
3
  size 4792