Poodja commited on
Commit
99f3497
·
verified ·
1 Parent(s): e88fcd4

Training in progress, epoch 1

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 +44 -0
  11. run-4/checkpoint-108/training_args.bin +3 -0
  12. run-4/checkpoint-108/vocab.txt +0 -0
  13. run-4/checkpoint-162/config.json +25 -0
  14. run-4/checkpoint-162/model.safetensors +3 -0
  15. run-4/checkpoint-162/optimizer.pt +3 -0
  16. run-4/checkpoint-162/rng_state.pth +3 -0
  17. run-4/checkpoint-162/scheduler.pt +3 -0
  18. run-4/checkpoint-162/special_tokens_map.json +7 -0
  19. run-4/checkpoint-162/tokenizer.json +0 -0
  20. run-4/checkpoint-162/tokenizer_config.json +55 -0
  21. run-4/checkpoint-162/trainer_state.json +53 -0
  22. run-4/checkpoint-162/training_args.bin +3 -0
  23. run-4/checkpoint-162/vocab.txt +0 -0
  24. run-4/checkpoint-216/config.json +25 -0
  25. run-4/checkpoint-216/model.safetensors +3 -0
  26. run-4/checkpoint-216/optimizer.pt +3 -0
  27. run-4/checkpoint-216/rng_state.pth +3 -0
  28. run-4/checkpoint-216/scheduler.pt +3 -0
  29. run-4/checkpoint-216/special_tokens_map.json +7 -0
  30. run-4/checkpoint-216/tokenizer.json +0 -0
  31. run-4/checkpoint-216/tokenizer_config.json +55 -0
  32. run-4/checkpoint-216/trainer_state.json +62 -0
  33. run-4/checkpoint-216/training_args.bin +3 -0
  34. run-4/checkpoint-216/vocab.txt +0 -0
  35. run-4/checkpoint-270/config.json +25 -0
  36. run-4/checkpoint-270/model.safetensors +3 -0
  37. run-4/checkpoint-270/optimizer.pt +3 -0
  38. run-4/checkpoint-270/rng_state.pth +3 -0
  39. run-4/checkpoint-270/scheduler.pt +3 -0
  40. run-4/checkpoint-270/special_tokens_map.json +7 -0
  41. run-4/checkpoint-270/tokenizer.json +0 -0
  42. run-4/checkpoint-270/tokenizer_config.json +55 -0
  43. run-4/checkpoint-270/trainer_state.json +71 -0
  44. run-4/checkpoint-270/training_args.bin +3 -0
  45. run-4/checkpoint-270/vocab.txt +0 -0
  46. runs/Feb27_13-20-57_4ffe06e164fd/events.out.tfevents.1709042334.4ffe06e164fd.373.7 +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:bc16e65209478886081b742b22316812399606054dd93aa03530a3c88f496fc5
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b84db3cc8dbc96de5c9d1fc8b3fd91b55765ccb7770d2d3d5e7d0ea59acd5479
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 sha256:324f394bef3d9e2a7995fb8ff2fceffdf86d61b8d96162bc2cb4a6d7687e1e54
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 sha256:9218364027bf5c2361d73d680ac435bb532cfd27d9f03ce2b97eb3797ff21ed4
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:aecc8b3a808bdc381a093781c90e3f99db1d35941ae3cbc07a4fed57f1632ff8
3
+ size 14308
run-4/checkpoint-108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5878660aedbf1896e0239421bf79e6e2d7824eb0921df8d17b2ddf025d85f5ba
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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-54",
4
+ "epoch": 2.0,
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": 0.6084455251693726,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7112,
16
+ "eval_samples_per_second": 1466.533,
17
+ "eval_steps_per_second": 92.801,
18
+ "step": 54
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5940627455711365,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7537,
25
+ "eval_samples_per_second": 1383.825,
26
+ "eval_steps_per_second": 87.567,
27
+ "step": 108
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 270,
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": 7.670979185958202e-06,
40
+ "num_train_epochs": 5,
41
+ "per_device_train_batch_size": 16,
42
+ "seed": 32
43
+ }
44
+ }
run-4/checkpoint-108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d01cc994ba3d9d3ab321de5dd591365526c0475b39b130e8cca28028d8b400
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-162/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-162/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1f00b15a8587d0065b1076e75af76ded24b6bff09b6e04eeb257fb6e753f8e0
3
+ size 267832560
run-4/checkpoint-162/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4242b7d73a82394a5296cfec33e2c548c018e4f937ad53a043876804457d3edf
3
+ size 535727290
run-4/checkpoint-162/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e1c80abe39d8ea7fd32135bf23e3ca46599dad7d3e6da5a4ed9c8c647589377
3
+ size 14308
run-4/checkpoint-162/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6207afac85661920f35e07b3dbf2b28c4f34eedc129f491785802be2c883d431
3
+ size 1064
run-4/checkpoint-162/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-162/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-162/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-162/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-54",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 162,
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": 0.6084455251693726,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7112,
16
+ "eval_samples_per_second": 1466.533,
17
+ "eval_steps_per_second": 92.801,
18
+ "step": 54
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5940627455711365,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7537,
25
+ "eval_samples_per_second": 1383.825,
26
+ "eval_steps_per_second": 87.567,
27
+ "step": 108
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5716970562934875,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.8013,
34
+ "eval_samples_per_second": 1301.587,
35
+ "eval_steps_per_second": 82.363,
36
+ "step": 162
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 270,
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": 7.670979185958202e-06,
49
+ "num_train_epochs": 5,
50
+ "per_device_train_batch_size": 16,
51
+ "seed": 32
52
+ }
53
+ }
run-4/checkpoint-162/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d01cc994ba3d9d3ab321de5dd591365526c0475b39b130e8cca28028d8b400
3
+ size 4984
run-4/checkpoint-162/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-216/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-216/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02014a77d2384132fa1f4d1c11378856ca86a5a4c8568ed6f9f543fe031009ae
3
+ size 267832560
run-4/checkpoint-216/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec527264e099780eea69288e037fd504611c68580a005e16d2603ea3f63180b1
3
+ size 535727290
run-4/checkpoint-216/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06eba3f51763c417a857ea7a877000c716e355b290312808d3ba64fe4ab29244
3
+ size 14308
run-4/checkpoint-216/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:631a7f1c8ff3bef5e65cac56036a080d8f6f4c8dd71292015ecb6ef1203bc7dd
3
+ size 1064
run-4/checkpoint-216/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-216/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-216/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-216/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0928457264044978,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-216",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 216,
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": 0.6084455251693726,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7112,
16
+ "eval_samples_per_second": 1466.533,
17
+ "eval_steps_per_second": 92.801,
18
+ "step": 54
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5940627455711365,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7537,
25
+ "eval_samples_per_second": 1383.825,
26
+ "eval_steps_per_second": 87.567,
27
+ "step": 108
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5716970562934875,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.8013,
34
+ "eval_samples_per_second": 1301.587,
35
+ "eval_steps_per_second": 82.363,
36
+ "step": 162
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.567482054233551,
41
+ "eval_matthews_correlation": 0.0928457264044978,
42
+ "eval_runtime": 0.7918,
43
+ "eval_samples_per_second": 1317.316,
44
+ "eval_steps_per_second": 83.358,
45
+ "step": 216
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 270,
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": 7.670979185958202e-06,
58
+ "num_train_epochs": 5,
59
+ "per_device_train_batch_size": 16,
60
+ "seed": 32
61
+ }
62
+ }
run-4/checkpoint-216/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d01cc994ba3d9d3ab321de5dd591365526c0475b39b130e8cca28028d8b400
3
+ size 4984
run-4/checkpoint-216/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-270/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-270/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a202c7ca61c3801e6088f6c9b1d39683378fc5ba7afd85730f04bc2f2031b7ba
3
+ size 267832560
run-4/checkpoint-270/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aa5ed351e65e3d2bf0a0e51e061ef0e4746fc6f0c92d878b9b42fdeea452e17
3
+ size 535727290
run-4/checkpoint-270/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa6977864a7adff4e3f8088468c89b4c398cd6a1b9eb4e788437a66b415ce960
3
+ size 14308
run-4/checkpoint-270/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f22e9068a2cc0f37d4e94914bb81d6e9184b4e9820868e9d3228c84122ea72d5
3
+ size 1064
run-4/checkpoint-270/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-270/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-270/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-270/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.09758197481255393,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-270",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 270,
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": 0.6084455251693726,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7112,
16
+ "eval_samples_per_second": 1466.533,
17
+ "eval_steps_per_second": 92.801,
18
+ "step": 54
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5940627455711365,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7537,
25
+ "eval_samples_per_second": 1383.825,
26
+ "eval_steps_per_second": 87.567,
27
+ "step": 108
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5716970562934875,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.8013,
34
+ "eval_samples_per_second": 1301.587,
35
+ "eval_steps_per_second": 82.363,
36
+ "step": 162
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.567482054233551,
41
+ "eval_matthews_correlation": 0.0928457264044978,
42
+ "eval_runtime": 0.7918,
43
+ "eval_samples_per_second": 1317.316,
44
+ "eval_steps_per_second": 83.358,
45
+ "step": 216
46
+ },
47
+ {
48
+ "epoch": 5.0,
49
+ "eval_loss": 0.5685351490974426,
50
+ "eval_matthews_correlation": 0.09758197481255393,
51
+ "eval_runtime": 0.7804,
52
+ "eval_samples_per_second": 1336.571,
53
+ "eval_steps_per_second": 84.577,
54
+ "step": 270
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 270,
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": 7.670979185958202e-06,
67
+ "num_train_epochs": 5,
68
+ "per_device_train_batch_size": 16,
69
+ "seed": 32
70
+ }
71
+ }
run-4/checkpoint-270/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d01cc994ba3d9d3ab321de5dd591365526c0475b39b130e8cca28028d8b400
3
+ size 4984
run-4/checkpoint-270/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb27_13-20-57_4ffe06e164fd/events.out.tfevents.1709042334.4ffe06e164fd.373.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3679df2de1413bf2a8f3d97d2b4d2168593de328f75b6e646001edede92a73ab
3
+ size 6223
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5d01cc994ba3d9d3ab321de5dd591365526c0475b39b130e8cca28028d8b400
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aaeef0b5638aa7bffa914cdba3eae3b1bd5b4b4b80b699028f568d31d6caa14
3
  size 4984