anamelchor commited on
Commit
7aec0b5
·
verified ·
1 Parent(s): 365e310

Training in progress, epoch 4

Browse files
Files changed (49) hide show
  1. config.json +1 -1
  2. model.safetensors +1 -1
  3. run-0/checkpoint-134/config.json +25 -0
  4. run-0/checkpoint-134/model.safetensors +3 -0
  5. run-0/checkpoint-134/optimizer.pt +3 -0
  6. run-0/checkpoint-134/rng_state.pth +3 -0
  7. run-0/checkpoint-134/scheduler.pt +3 -0
  8. run-0/checkpoint-134/special_tokens_map.json +7 -0
  9. run-0/checkpoint-134/tokenizer.json +0 -0
  10. run-0/checkpoint-134/tokenizer_config.json +55 -0
  11. run-0/checkpoint-134/trainer_state.json +35 -0
  12. run-0/checkpoint-134/training_args.bin +3 -0
  13. run-0/checkpoint-134/vocab.txt +0 -0
  14. run-0/checkpoint-268/config.json +25 -0
  15. run-0/checkpoint-268/model.safetensors +3 -0
  16. run-0/checkpoint-268/optimizer.pt +3 -0
  17. run-0/checkpoint-268/rng_state.pth +3 -0
  18. run-0/checkpoint-268/scheduler.pt +3 -0
  19. run-0/checkpoint-268/special_tokens_map.json +7 -0
  20. run-0/checkpoint-268/tokenizer.json +0 -0
  21. run-0/checkpoint-268/tokenizer_config.json +55 -0
  22. run-0/checkpoint-268/trainer_state.json +44 -0
  23. run-0/checkpoint-268/training_args.bin +3 -0
  24. run-0/checkpoint-268/vocab.txt +0 -0
  25. run-0/checkpoint-402/config.json +25 -0
  26. run-0/checkpoint-402/model.safetensors +3 -0
  27. run-0/checkpoint-402/optimizer.pt +3 -0
  28. run-0/checkpoint-402/rng_state.pth +3 -0
  29. run-0/checkpoint-402/scheduler.pt +3 -0
  30. run-0/checkpoint-402/special_tokens_map.json +7 -0
  31. run-0/checkpoint-402/tokenizer.json +0 -0
  32. run-0/checkpoint-402/tokenizer_config.json +55 -0
  33. run-0/checkpoint-402/trainer_state.json +53 -0
  34. run-0/checkpoint-402/training_args.bin +3 -0
  35. run-0/checkpoint-402/vocab.txt +0 -0
  36. run-0/checkpoint-536/config.json +25 -0
  37. run-0/checkpoint-536/model.safetensors +3 -0
  38. run-0/checkpoint-536/optimizer.pt +3 -0
  39. run-0/checkpoint-536/rng_state.pth +3 -0
  40. run-0/checkpoint-536/scheduler.pt +3 -0
  41. run-0/checkpoint-536/special_tokens_map.json +7 -0
  42. run-0/checkpoint-536/tokenizer.json +0 -0
  43. run-0/checkpoint-536/tokenizer_config.json +55 -0
  44. run-0/checkpoint-536/trainer_state.json +69 -0
  45. run-0/checkpoint-536/training_args.bin +3 -0
  46. run-0/checkpoint-536/vocab.txt +0 -0
  47. runs/Mar03_19-15-00_abc5bcbabcce/events.out.tfevents.1709493301.abc5bcbabcce.1176.28 +3 -0
  48. runs/Mar03_19-18-26_abc5bcbabcce/events.out.tfevents.1709493562.abc5bcbabcce.1176.29 +3 -0
  49. training_args.bin +1 -1
config.json CHANGED
@@ -20,6 +20,6 @@
20
  "sinusoidal_pos_embds": false,
21
  "tie_weights_": true,
22
  "torch_dtype": "float32",
23
- "transformers_version": "4.38.1",
24
  "vocab_size": 30522
25
  }
 
20
  "sinusoidal_pos_embds": false,
21
  "tie_weights_": true,
22
  "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
  "vocab_size": 30522
25
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30f4e9548471ed4ffad58c93aa048da4c43864ff312fefc44f489d5327cd82e9
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:514fd99d58f93378a0f7903e3c7c4320a611570187bff403a7bb27891df7320c
3
  size 267832560
run-0/checkpoint-134/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-0/checkpoint-134/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c49d1ed4e9c66ddc49cc1d45d7fc2289aa41b88aba5ecbf842f00fea48083639
3
+ size 267832560
run-0/checkpoint-134/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1416666752de715396196264bd7a1fb002f8c3dd1e4533676a45cc16e903966d
3
+ size 535727290
run-0/checkpoint-134/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a370ee2267e26c5daf7b741d62be810509ce8dc65b6212f645244047641c5af
3
+ size 14244
run-0/checkpoint-134/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a2b15eae9b4eede4556ff7be2318f195d64ee5f12e70f364b49b9a12e0fc2e4
3
+ size 1064
run-0/checkpoint-134/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-0/checkpoint-134/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-134/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-0/checkpoint-134/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-134",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 134,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_loss": 0.6058756113052368,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 1.1108,
16
+ "eval_samples_per_second": 938.924,
17
+ "eval_steps_per_second": 59.414,
18
+ "step": 134
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 536,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 4,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 64,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 2.205579826691781e-06,
31
+ "num_train_epochs": 4,
32
+ "per_device_train_batch_size": 64,
33
+ "seed": 12
34
+ }
35
+ }
run-0/checkpoint-134/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:916762e2968c4ee34cf01bb37aa02f020d8d90cd783a83050e1144249e4fdb76
3
+ size 4984
run-0/checkpoint-134/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-0/checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ef00cc76dea411db3cd877af9d95936843ecaf98d12bb5016c296326d04fb73
3
+ size 267832560
run-0/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53ff428f99ecc35d69e57eb499b2bc357d453d727ebcf387ecf31627a3b34719
3
+ size 535727290
run-0/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2a7d2168f6f1ae4ea46d4afd75c71325902ae36a52993875e58941a85eff2df
3
+ size 14244
run-0/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f5efa340ffab5b563a69a7611173efd483e5d2ffda28af24c45ad6c1869af4d
3
+ size 1064
run-0/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-0/checkpoint-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-268/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-0/checkpoint-268/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0463559874942472,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-268",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 268,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_loss": 0.6058756113052368,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 1.1108,
16
+ "eval_samples_per_second": 938.924,
17
+ "eval_steps_per_second": 59.414,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5703422427177429,
23
+ "eval_matthews_correlation": 0.0463559874942472,
24
+ "eval_runtime": 1.1844,
25
+ "eval_samples_per_second": 880.626,
26
+ "eval_steps_per_second": 55.725,
27
+ "step": 268
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 536,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 64,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 2.205579826691781e-06,
40
+ "num_train_epochs": 4,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 12
43
+ }
44
+ }
run-0/checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:916762e2968c4ee34cf01bb37aa02f020d8d90cd783a83050e1144249e4fdb76
3
+ size 4984
run-0/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-402/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-0/checkpoint-402/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aa791a95b2e9dcc68a7a59357643049534dec3fc677c79fe3f0b350e5df841d
3
+ size 267832560
run-0/checkpoint-402/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e13536392a8ffc64161b2b41551dd589b1e0469368143554417dbd6da7318550
3
+ size 535727290
run-0/checkpoint-402/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02c947e8e524fd6b999bf8133200ff86d42c20f558cb461563419a8ec9b9acbd
3
+ size 14244
run-0/checkpoint-402/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5b28d96526a7d89d536b88dc7fd07c21f30cbb7a92d7f00c61c332103822b40
3
+ size 1064
run-0/checkpoint-402/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-0/checkpoint-402/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-402/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-0/checkpoint-402/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.13847035035325458,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-402",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 402,
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": 0.6058756113052368,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 1.1108,
16
+ "eval_samples_per_second": 938.924,
17
+ "eval_steps_per_second": 59.414,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5703422427177429,
23
+ "eval_matthews_correlation": 0.0463559874942472,
24
+ "eval_runtime": 1.1844,
25
+ "eval_samples_per_second": 880.626,
26
+ "eval_steps_per_second": 55.725,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5537189245223999,
32
+ "eval_matthews_correlation": 0.13847035035325458,
33
+ "eval_runtime": 1.2327,
34
+ "eval_samples_per_second": 846.092,
35
+ "eval_steps_per_second": 53.54,
36
+ "step": 402
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 536,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 4,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 64,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 2.205579826691781e-06,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 12
52
+ }
53
+ }
run-0/checkpoint-402/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:916762e2968c4ee34cf01bb37aa02f020d8d90cd783a83050e1144249e4fdb76
3
+ size 4984
run-0/checkpoint-402/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-0/checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:514fd99d58f93378a0f7903e3c7c4320a611570187bff403a7bb27891df7320c
3
+ size 267832560
run-0/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02a7d5d3aa60eeeba7e564bc3d1f55c9bf8229c48763a9dd0d7f73e6dcdd83d3
3
+ size 535727290
run-0/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec6d8979b50971fe759c1ad46716ccaaae1f3bb4e7a1f2e688dcb1429a675919
3
+ size 14244
run-0/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c4c2a82f3e566e836e1c86f65d928eba36551c3a6fc23593e2fc0a81b22fc42
3
+ size 1064
run-0/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-0/checkpoint-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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-0/checkpoint-536/trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.19816060019544374,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-536",
4
+ "epoch": 4.0,
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": 0.6058756113052368,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 1.1108,
16
+ "eval_samples_per_second": 938.924,
17
+ "eval_steps_per_second": 59.414,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5703422427177429,
23
+ "eval_matthews_correlation": 0.0463559874942472,
24
+ "eval_runtime": 1.1844,
25
+ "eval_samples_per_second": 880.626,
26
+ "eval_steps_per_second": 55.725,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5537189245223999,
32
+ "eval_matthews_correlation": 0.13847035035325458,
33
+ "eval_runtime": 1.2327,
34
+ "eval_samples_per_second": 846.092,
35
+ "eval_steps_per_second": 53.54,
36
+ "step": 402
37
+ },
38
+ {
39
+ "epoch": 3.73,
40
+ "grad_norm": 2.2481775283813477,
41
+ "learning_rate": 1.4813595850914947e-07,
42
+ "loss": 0.5692,
43
+ "step": 500
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_loss": 0.5494163632392883,
48
+ "eval_matthews_correlation": 0.19816060019544374,
49
+ "eval_runtime": 0.7154,
50
+ "eval_samples_per_second": 1457.894,
51
+ "eval_steps_per_second": 92.254,
52
+ "step": 536
53
+ }
54
+ ],
55
+ "logging_steps": 500,
56
+ "max_steps": 536,
57
+ "num_input_tokens_seen": 0,
58
+ "num_train_epochs": 4,
59
+ "save_steps": 500,
60
+ "total_flos": 209831981626536.0,
61
+ "train_batch_size": 64,
62
+ "trial_name": null,
63
+ "trial_params": {
64
+ "learning_rate": 2.205579826691781e-06,
65
+ "num_train_epochs": 4,
66
+ "per_device_train_batch_size": 64,
67
+ "seed": 12
68
+ }
69
+ }
run-0/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:916762e2968c4ee34cf01bb37aa02f020d8d90cd783a83050e1144249e4fdb76
3
+ size 4984
run-0/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar03_19-15-00_abc5bcbabcce/events.out.tfevents.1709493301.abc5bcbabcce.1176.28 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1198878fb428b15aa8c72f35fa9fa3b43de3e3f675e6deac77016fc978e7e7ec
3
+ size 4737
runs/Mar03_19-18-26_abc5bcbabcce/events.out.tfevents.1709493562.abc5bcbabcce.1176.29 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7482cb5eda666d3a6e9d51682c994104f2c6662dc4de82d6569d4f0a754135a
3
+ size 6447
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:994323cb4d85b1be62c90aa51db25a1c278952252319cd5846250f9a6537ab3f
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:916762e2968c4ee34cf01bb37aa02f020d8d90cd783a83050e1144249e4fdb76
3
  size 4984