obudzecie commited on
Commit
0cbb0f0
·
verified ·
1 Parent(s): 304c11b

Training in progress, epoch 4

Browse files
Files changed (47) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-108/config.json +25 -0
  3. run-4/checkpoint-108/model.safetensors +3 -0
  4. run-4/checkpoint-108/optimizer.pt +3 -0
  5. run-4/checkpoint-108/rng_state.pth +3 -0
  6. run-4/checkpoint-108/scheduler.pt +3 -0
  7. run-4/checkpoint-108/special_tokens_map.json +7 -0
  8. run-4/checkpoint-108/tokenizer.json +0 -0
  9. run-4/checkpoint-108/tokenizer_config.json +55 -0
  10. run-4/checkpoint-108/trainer_state.json +62 -0
  11. run-4/checkpoint-108/training_args.bin +3 -0
  12. run-4/checkpoint-108/vocab.txt +0 -0
  13. run-4/checkpoint-135/config.json +25 -0
  14. run-4/checkpoint-135/model.safetensors +3 -0
  15. run-4/checkpoint-135/optimizer.pt +3 -0
  16. run-4/checkpoint-135/rng_state.pth +3 -0
  17. run-4/checkpoint-135/scheduler.pt +3 -0
  18. run-4/checkpoint-135/special_tokens_map.json +7 -0
  19. run-4/checkpoint-135/tokenizer.json +0 -0
  20. run-4/checkpoint-135/tokenizer_config.json +55 -0
  21. run-4/checkpoint-135/trainer_state.json +71 -0
  22. run-4/checkpoint-135/training_args.bin +3 -0
  23. run-4/checkpoint-135/vocab.txt +0 -0
  24. run-4/checkpoint-54/config.json +25 -0
  25. run-4/checkpoint-54/model.safetensors +3 -0
  26. run-4/checkpoint-54/optimizer.pt +3 -0
  27. run-4/checkpoint-54/rng_state.pth +3 -0
  28. run-4/checkpoint-54/scheduler.pt +3 -0
  29. run-4/checkpoint-54/special_tokens_map.json +7 -0
  30. run-4/checkpoint-54/tokenizer.json +0 -0
  31. run-4/checkpoint-54/tokenizer_config.json +55 -0
  32. run-4/checkpoint-54/trainer_state.json +44 -0
  33. run-4/checkpoint-54/training_args.bin +3 -0
  34. run-4/checkpoint-54/vocab.txt +0 -0
  35. run-4/checkpoint-81/config.json +25 -0
  36. run-4/checkpoint-81/model.safetensors +3 -0
  37. run-4/checkpoint-81/optimizer.pt +3 -0
  38. run-4/checkpoint-81/rng_state.pth +3 -0
  39. run-4/checkpoint-81/scheduler.pt +3 -0
  40. run-4/checkpoint-81/special_tokens_map.json +7 -0
  41. run-4/checkpoint-81/tokenizer.json +0 -0
  42. run-4/checkpoint-81/tokenizer_config.json +55 -0
  43. run-4/checkpoint-81/trainer_state.json +53 -0
  44. run-4/checkpoint-81/training_args.bin +3 -0
  45. run-4/checkpoint-81/vocab.txt +0 -0
  46. runs/Feb27_18-29-22_d3d09c0dfc16/events.out.tfevents.1709058583.d3d09c0dfc16.836.8 +3 -0
  47. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4542ea02296c83bed04f3c54cf00db1bc8503bfaad3f396b82b3e6187ab61d9
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97b2cb0c1d3c14e08d992a592e0ed3080678d0addf23085da45bfaa05c3b58bd
3
  size 267832560
run-4/checkpoint-108/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c122d5e5a6fdfd4af1c5a6c9c50128f4420f4a514dc14031e1579b0d2747fc33
3
+ size 267832560
run-4/checkpoint-108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53a635ac14b88f6cf683e477f2fd33302e29b80bfb68eeb3e6ecb6999401484e
3
+ size 535727290
run-4/checkpoint-108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70be097296a6d5300abe9b4baddbcd39b99a95449ff48595071bab8227787b9b
3
+ size 14244
run-4/checkpoint-108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a1a976b2339665929b9f339db9b4674f45e62a572e4f75ba95cc952f361ab29
3
+ size 1064
run-4/checkpoint-108/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-4/checkpoint-108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-108/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-4/checkpoint-108/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-27",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 108,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_loss": 0.6171508431434631,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 1.2254,
16
+ "eval_samples_per_second": 851.142,
17
+ "eval_steps_per_second": 106.903,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6099013686180115,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 1.2265,
25
+ "eval_samples_per_second": 850.398,
26
+ "eval_steps_per_second": 106.809,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6057543158531189,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 1.964,
34
+ "eval_samples_per_second": 531.065,
35
+ "eval_steps_per_second": 66.701,
36
+ "step": 81
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.6021494269371033,
41
+ "eval_matthews_correlation": 0.0,
42
+ "eval_runtime": 1.4016,
43
+ "eval_samples_per_second": 744.157,
44
+ "eval_steps_per_second": 93.466,
45
+ "step": 108
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 135,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 5,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 16,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 7.141254091425431e-06,
58
+ "num_train_epochs": 5,
59
+ "per_device_train_batch_size": 16,
60
+ "seed": 4
61
+ }
62
+ }
run-4/checkpoint-108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b272556a909ee8d46e26a918cf12e067d37cdfcdb6fc7bb9dd145e02aa9cb279
3
+ size 4984
run-4/checkpoint-108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-135/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-135/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e1639bbf816361fe13813ed70ce04625b785511e640e83868ddf226b3e4ef95
3
+ size 267832560
run-4/checkpoint-135/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0433f597b8482325984a4ddf0f4ec9ec64119ac452eb02e7e26bf2e32364f279
3
+ size 535727290
run-4/checkpoint-135/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6327434c73e0ecc6c10c0695af864992a2a330d0826e027b6f72bf8fa946f32f
3
+ size 14244
run-4/checkpoint-135/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5129fa2c636cfaa478b1a210beadd351a1a6a7b4d8f9b77536c8c3b5ba6c0f1
3
+ size 1064
run-4/checkpoint-135/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-4/checkpoint-135/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-135/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-4/checkpoint-135/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-27",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 135,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_loss": 0.6171508431434631,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 1.2254,
16
+ "eval_samples_per_second": 851.142,
17
+ "eval_steps_per_second": 106.903,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6099013686180115,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 1.2265,
25
+ "eval_samples_per_second": 850.398,
26
+ "eval_steps_per_second": 106.809,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6057543158531189,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 1.964,
34
+ "eval_samples_per_second": 531.065,
35
+ "eval_steps_per_second": 66.701,
36
+ "step": 81
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.6021494269371033,
41
+ "eval_matthews_correlation": 0.0,
42
+ "eval_runtime": 1.4016,
43
+ "eval_samples_per_second": 744.157,
44
+ "eval_steps_per_second": 93.466,
45
+ "step": 108
46
+ },
47
+ {
48
+ "epoch": 5.0,
49
+ "eval_loss": 0.6008092164993286,
50
+ "eval_matthews_correlation": 0.0,
51
+ "eval_runtime": 1.5317,
52
+ "eval_samples_per_second": 680.96,
53
+ "eval_steps_per_second": 85.528,
54
+ "step": 135
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 135,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 5,
61
+ "save_steps": 500,
62
+ "total_flos": 0,
63
+ "train_batch_size": 16,
64
+ "trial_name": null,
65
+ "trial_params": {
66
+ "learning_rate": 7.141254091425431e-06,
67
+ "num_train_epochs": 5,
68
+ "per_device_train_batch_size": 16,
69
+ "seed": 4
70
+ }
71
+ }
run-4/checkpoint-135/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b272556a909ee8d46e26a918cf12e067d37cdfcdb6fc7bb9dd145e02aa9cb279
3
+ size 4984
run-4/checkpoint-135/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-54/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-54/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ffa22d670fd8d875f0874f56277b766324b6c576424e31e03488878974f06c
3
+ size 267832560
run-4/checkpoint-54/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:711bd5c2eaa53854115a17390ce4ca1f9f8640bbf3bf3d9d3682e3ea030b8b2b
3
+ size 535727290
run-4/checkpoint-54/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7daa4263b1198655a1441081a5b33c5bce53494dcd0610b8798d313ef92eff4e
3
+ size 14244
run-4/checkpoint-54/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab38497e119d49371b53e85f5cfb7d41c0903e3c9879e2bb0e6b7c1e0e7bff52
3
+ size 1064
run-4/checkpoint-54/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-54/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-54/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-54/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-27",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 54,
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": 0.6171508431434631,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 1.2254,
16
+ "eval_samples_per_second": 851.142,
17
+ "eval_steps_per_second": 106.903,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6099013686180115,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 1.2265,
25
+ "eval_samples_per_second": 850.398,
26
+ "eval_steps_per_second": 106.809,
27
+ "step": 54
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 135,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 5,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 16,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 7.141254091425431e-06,
40
+ "num_train_epochs": 5,
41
+ "per_device_train_batch_size": 16,
42
+ "seed": 4
43
+ }
44
+ }
run-4/checkpoint-54/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b272556a909ee8d46e26a918cf12e067d37cdfcdb6fc7bb9dd145e02aa9cb279
3
+ size 4984
run-4/checkpoint-54/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-81/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-81/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab72c7180fa214e85929e82e1af7affa89be09b002b22f007a73267be519c2e3
3
+ size 267832560
run-4/checkpoint-81/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f4e4ac854b36e3b5ba7c28aacb55f50dd9c69e4652c4f1bc69015ae4902c53
3
+ size 535727290
run-4/checkpoint-81/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df19022e6d92ec1e71a81979f3d3aaea77298d1920fcb80e82ab66be998fc6a
3
+ size 14244
run-4/checkpoint-81/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10d08f04f1684f771c07e7323039a2bc9c13900bd7c1e8accf35d26db111cc0d
3
+ size 1064
run-4/checkpoint-81/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-81/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-81/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-81/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-27",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 81,
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": 0.6171508431434631,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 1.2254,
16
+ "eval_samples_per_second": 851.142,
17
+ "eval_steps_per_second": 106.903,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6099013686180115,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 1.2265,
25
+ "eval_samples_per_second": 850.398,
26
+ "eval_steps_per_second": 106.809,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6057543158531189,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 1.964,
34
+ "eval_samples_per_second": 531.065,
35
+ "eval_steps_per_second": 66.701,
36
+ "step": 81
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 135,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 5,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 16,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 7.141254091425431e-06,
49
+ "num_train_epochs": 5,
50
+ "per_device_train_batch_size": 16,
51
+ "seed": 4
52
+ }
53
+ }
run-4/checkpoint-81/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b272556a909ee8d46e26a918cf12e067d37cdfcdb6fc7bb9dd145e02aa9cb279
3
+ size 4984
run-4/checkpoint-81/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb27_18-29-22_d3d09c0dfc16/events.out.tfevents.1709058583.d3d09c0dfc16.836.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28c1369b9ed67baff987d9a4172b814eaa06f57723e5dcf8c8603e47ae5ea1ed
3
+ size 8012
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b272556a909ee8d46e26a918cf12e067d37cdfcdb6fc7bb9dd145e02aa9cb279
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0217581794ae6950079b9eb597029b99d93d55c51b3e0e9cd50a8e181c91a58
3
  size 4984