Hugging Face's logo

obudzecie
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
obudzecie commited on
Commit
d14032d
•
1 Parent(s): aa943e3

Training in progress, epoch 1

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-21/config.json +25 -0
  3. run-0/checkpoint-21/model.safetensors +3 -0
  4. run-0/checkpoint-21/optimizer.pt +3 -0
  5. run-0/checkpoint-21/rng_state.pth +3 -0
  6. run-0/checkpoint-21/scheduler.pt +3 -0
  7. run-0/checkpoint-21/special_tokens_map.json +7 -0
  8. run-0/checkpoint-21/tokenizer.json +0 -0
  9. run-0/checkpoint-21/tokenizer_config.json +55 -0
  10. run-0/checkpoint-21/trainer_state.json +53 -0
  11. run-0/checkpoint-21/training_args.bin +3 -0
  12. run-0/checkpoint-21/vocab.txt +0 -0
  13. run-0/checkpoint-28/model.safetensors +1 -1
  14. run-0/checkpoint-28/optimizer.pt +1 -1
  15. run-0/checkpoint-28/rng_state.pth +1 -1
  16. run-0/checkpoint-28/scheduler.pt +1 -1
  17. run-0/checkpoint-28/trainer_state.json +35 -17
  18. run-0/checkpoint-28/training_args.bin +1 -1
  19. run-1/checkpoint-107/model.safetensors +1 -1
  20. run-1/checkpoint-107/optimizer.pt +1 -1
  21. run-1/checkpoint-107/rng_state.pth +1 -1
  22. run-1/checkpoint-107/scheduler.pt +1 -1
  23. run-1/checkpoint-107/trainer_state.json +9 -9
  24. run-1/checkpoint-107/training_args.bin +1 -1
  25. run-1/checkpoint-214/model.safetensors +1 -1
  26. run-1/checkpoint-214/optimizer.pt +1 -1
  27. run-1/checkpoint-214/rng_state.pth +1 -1
  28. run-1/checkpoint-214/scheduler.pt +1 -1
  29. run-1/checkpoint-214/trainer_state.json +13 -13
  30. run-1/checkpoint-214/training_args.bin +1 -1
  31. run-1/checkpoint-321/config.json +25 -0
  32. run-1/checkpoint-321/model.safetensors +3 -0
  33. run-1/checkpoint-321/optimizer.pt +3 -0
  34. run-1/checkpoint-321/rng_state.pth +3 -0
  35. run-1/checkpoint-321/scheduler.pt +3 -0
  36. run-1/checkpoint-321/special_tokens_map.json +7 -0
  37. run-1/checkpoint-321/tokenizer.json +0 -0
  38. run-1/checkpoint-321/tokenizer_config.json +55 -0
  39. run-1/checkpoint-321/trainer_state.json +53 -0
  40. run-1/checkpoint-321/training_args.bin +3 -0
  41. run-1/checkpoint-321/vocab.txt +0 -0
  42. run-1/checkpoint-428/config.json +25 -0
  43. run-1/checkpoint-428/model.safetensors +3 -0
  44. run-1/checkpoint-428/optimizer.pt +3 -0
  45. run-1/checkpoint-428/rng_state.pth +3 -0
  46. run-1/checkpoint-428/scheduler.pt +3 -0
  47. run-1/checkpoint-428/special_tokens_map.json +7 -0
  48. run-1/checkpoint-428/tokenizer.json +0 -0
  49. run-1/checkpoint-428/tokenizer_config.json +55 -0
  50. run-1/checkpoint-428/trainer_state.json +62 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19d4241218652ba9c1b9b31915ec23920b45e79f1438a600a1a5c71050dedef8
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d251b7947fa3a1e694150ce24352e2b3a177b153736734f18d4ca6afc62dbfa1
3
  size 267832560
run-0/checkpoint-21/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-0/checkpoint-21/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fdb13c2d459c7eaeaa7562d42160bca6e046ddb60f13060d4dfe6b31cec6fb7
3
+ size 267832560
run-0/checkpoint-21/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc391d3a26533591550e94f5f3f76e45d0aa4b19b82eec86094cd4df89328b0c
3
+ size 535727290
run-0/checkpoint-21/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f76d2eab1ca3bf264e4720f841a11356cdb8787303dd383e3bfc00ff06db2fd8
3
+ size 14308
run-0/checkpoint-21/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29982e7106b394bf40f11b1451003acd8fee641ba8010d451b4d8635a53e6593
3
+ size 1064
run-0/checkpoint-21/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-21/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-21/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-21/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.20447908125390313,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-21",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 21,
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": 0.6069979667663574,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 1.5899,
16
+ "eval_samples_per_second": 656.018,
17
+ "eval_steps_per_second": 82.395,
18
+ "step": 7
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5834578275680542,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 2.4953,
25
+ "eval_samples_per_second": 417.989,
26
+ "eval_steps_per_second": 52.499,
27
+ "step": 14
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5535554885864258,
32
+ "eval_matthews_correlation": 0.20447908125390313,
33
+ "eval_runtime": 1.2012,
34
+ "eval_samples_per_second": 868.263,
35
+ "eval_steps_per_second": 109.053,
36
+ "step": 21
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 28,
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": 6.924004119404506e-05,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 17
52
+ }
53
+ }
run-0/checkpoint-21/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc4ef5ffcc2a39c74e8598a37e0687340047329a8f9dbf3d4c35e5148d94b74
3
+ size 4984
run-0/checkpoint-21/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-28/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6ce764070444d43068b553396eb365995d77cbcbd1914c72aa9a6c97850709b
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9abcaa3a6087a18adac8efb168a9593c10c8eaaa3b9c7b79c513e8323091db04
3
  size 267832560
run-0/checkpoint-28/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc2ebe14313b9e6c3947fd1d953eeda5d13b11ff870720b9710937950626a362
3
  size 535727290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43341f9b4b768810327412938de8ce28eba0ea6facd5f854ace8a1cf1c755861
3
  size 535727290
run-0/checkpoint-28/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c33e0c0fc4377f79ddd532f22fabff059620d2e02ddbf80b3af980df5f7875f1
3
  size 14308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff310a925b75b174a2dd13617258e77e89263d0194947ef759315e744ad0dac0
3
  size 14308
run-0/checkpoint-28/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39b41d01198466edea710d83579bcbe9782f3537fd512c2b54f81697b76e4f30
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93714386559befecb690974bee712aecf1966817ab53ce19e5f83d9fa609591c
3
  size 1064
run-0/checkpoint-28/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.0,
3
- "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-14",
4
- "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 28,
7
  "is_hyper_param_search": true,
@@ -10,35 +10,53 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 0.6425530314445496,
14
  "eval_matthews_correlation": 0.0,
15
- "eval_runtime": 0.6667,
16
- "eval_samples_per_second": 1564.434,
17
- "eval_steps_per_second": 98.996,
18
- "step": 14
19
  },
20
  {
21
  "epoch": 2.0,
22
- "eval_loss": 0.6215561628341675,
23
  "eval_matthews_correlation": 0.0,
24
- "eval_runtime": 0.7349,
25
- "eval_samples_per_second": 1419.255,
26
- "eval_steps_per_second": 89.809,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  "step": 28
28
  }
29
  ],
30
  "logging_steps": 500,
31
- "max_steps": 42,
32
  "num_input_tokens_seen": 0,
33
- "num_train_epochs": 3,
34
  "save_steps": 500,
35
  "total_flos": 0,
36
  "train_batch_size": 64,
37
  "trial_name": null,
38
  "trial_params": {
39
- "learning_rate": 5.9402286931455415e-06,
40
- "num_train_epochs": 3,
41
  "per_device_train_batch_size": 64,
42
- "seed": 33
43
  }
44
  }
 
1
  {
2
+ "best_metric": 0.278777673546003,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-28",
4
+ "epoch": 4.0,
5
  "eval_steps": 500,
6
  "global_step": 28,
7
  "is_hyper_param_search": true,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.6069979667663574,
14
  "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 1.5899,
16
+ "eval_samples_per_second": 656.018,
17
+ "eval_steps_per_second": 82.395,
18
+ "step": 7
19
  },
20
  {
21
  "epoch": 2.0,
22
+ "eval_loss": 0.5834578275680542,
23
  "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 2.4953,
25
+ "eval_samples_per_second": 417.989,
26
+ "eval_steps_per_second": 52.499,
27
+ "step": 14
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5535554885864258,
32
+ "eval_matthews_correlation": 0.20447908125390313,
33
+ "eval_runtime": 1.2012,
34
+ "eval_samples_per_second": 868.263,
35
+ "eval_steps_per_second": 109.053,
36
+ "step": 21
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.5610475540161133,
41
+ "eval_matthews_correlation": 0.278777673546003,
42
+ "eval_runtime": 1.2979,
43
+ "eval_samples_per_second": 803.636,
44
+ "eval_steps_per_second": 100.936,
45
  "step": 28
46
  }
47
  ],
48
  "logging_steps": 500,
49
+ "max_steps": 28,
50
  "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 4,
52
  "save_steps": 500,
53
  "total_flos": 0,
54
  "train_batch_size": 64,
55
  "trial_name": null,
56
  "trial_params": {
57
+ "learning_rate": 6.924004119404506e-05,
58
+ "num_train_epochs": 4,
59
  "per_device_train_batch_size": 64,
60
+ "seed": 17
61
  }
62
  }
run-0/checkpoint-28/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3890eb403da684d0292db5dfdfff23f4d1c6bfee6a85697d4ee366d75565506
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc4ef5ffcc2a39c74e8598a37e0687340047329a8f9dbf3d4c35e5148d94b74
3
  size 4984
run-1/checkpoint-107/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b828a4daa2b8031a9a3681255c0aabbc5f768abdff88bfb6f6fa6c41b7efcbd7
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41df3acc4f087e3a98653c4401e28485559e1b388d7d2da7c91dde5931c42ca3
3
  size 267832560
run-1/checkpoint-107/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16b2a50d83bc576bfccb57053ceb245062fc59452ab4fd4ef10c517770b0c5ab
3
  size 535727290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8078c84ceb1e3377650dd6fc7e5755dde1c7affd36d0e96935a6513f27dd3601
3
  size 535727290
run-1/checkpoint-107/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5aeded5f395e9f5a2c1bef6bb1bad380e929c54cfbc8cdc92eff01e1acefe73c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccf5593f152afaadd4df4118b73ecf902ec5a8971d2eac49ae80aea4bc3a90cb
3
  size 14244
run-1/checkpoint-107/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b908ec7b37a2a9c729a1c8e02dadf0c0e005f404c0c7442b295cc3ef71da124
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a0ea298478200005becd4134793ab974ae8e7687bb33be16121fcdecf8ec82a
3
  size 1064
run-1/checkpoint-107/trainer_state.json CHANGED
@@ -10,26 +10,26 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 0.6146374940872192,
14
  "eval_matthews_correlation": 0.0,
15
- "eval_runtime": 0.9611,
16
- "eval_samples_per_second": 1085.271,
17
- "eval_steps_per_second": 136.309,
18
  "step": 107
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 214,
23
  "num_input_tokens_seen": 0,
24
- "num_train_epochs": 2,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
  "train_batch_size": 4,
28
  "trial_name": null,
29
  "trial_params": {
30
- "learning_rate": 5.953884936724958e-06,
31
- "num_train_epochs": 2,
32
  "per_device_train_batch_size": 4,
33
- "seed": 3
34
  }
35
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.6247433423995972,
14
  "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.9442,
16
+ "eval_samples_per_second": 1104.683,
17
+ "eval_steps_per_second": 138.747,
18
  "step": 107
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 428,
23
  "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 4,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
  "train_batch_size": 4,
28
  "trial_name": null,
29
  "trial_params": {
30
+ "learning_rate": 1.0170873699122056e-05,
31
+ "num_train_epochs": 4,
32
  "per_device_train_batch_size": 4,
33
+ "seed": 16
34
  }
35
  }
run-1/checkpoint-107/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ee984d70f75a2468c22cfd998312bd4d58e9705e58ec6c050f6541fd5b4a56c
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb79b974e6c474cc87583dfff5dff5d9e65017523a76923a915ff714cc13595c
3
  size 4984
run-1/checkpoint-214/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f096769a07348351c66424a96eae861b86cf5cf737bcb2f362fc890c5f507669
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53c7324d08fd9c45ad1cf8112df6e9d1bc41bf754faf223c8cc0e9af9f2d0451
3
  size 267832560
run-1/checkpoint-214/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a36d655f7c68dc7c479ac783c986d41bf89ae7bacaccaec7fa2e24b1989c9dcc
3
  size 535727290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8820a6bb240aa856e8b8e2198c55f9dba81381fd31122efc444aa9a365bf641
3
  size 535727290
run-1/checkpoint-214/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7289d6b29aa9ab85a7afa321503098b917e1616d0eebe7c14318e153361c88f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ceacee9a836f1235b0eff6af56f1cecebc9b9060cdcb253fdd90207c1a2c736
3
  size 14244
run-1/checkpoint-214/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4285d38d8f4e0e6bb0170539e0c23d3c7dc320358fe790ade66671b8168b5a7f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edd55d95f04a4cf861a732354cad9aadc05a736a70dcb0a01514d4da7b324f10
3
  size 1064
run-1/checkpoint-214/trainer_state.json CHANGED
@@ -10,35 +10,35 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 0.6146374940872192,
14
  "eval_matthews_correlation": 0.0,
15
- "eval_runtime": 0.9611,
16
- "eval_samples_per_second": 1085.271,
17
- "eval_steps_per_second": 136.309,
18
  "step": 107
19
  },
20
  {
21
  "epoch": 2.0,
22
- "eval_loss": 0.6122422218322754,
23
  "eval_matthews_correlation": 0.0,
24
- "eval_runtime": 3.3931,
25
- "eval_samples_per_second": 307.393,
26
- "eval_steps_per_second": 38.608,
27
  "step": 214
28
  }
29
  ],
30
  "logging_steps": 500,
31
- "max_steps": 214,
32
  "num_input_tokens_seen": 0,
33
- "num_train_epochs": 2,
34
  "save_steps": 500,
35
  "total_flos": 0,
36
  "train_batch_size": 4,
37
  "trial_name": null,
38
  "trial_params": {
39
- "learning_rate": 5.953884936724958e-06,
40
- "num_train_epochs": 2,
41
  "per_device_train_batch_size": 4,
42
- "seed": 3
43
  }
44
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.6247433423995972,
14
  "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.9442,
16
+ "eval_samples_per_second": 1104.683,
17
+ "eval_steps_per_second": 138.747,
18
  "step": 107
19
  },
20
  {
21
  "epoch": 2.0,
22
+ "eval_loss": 0.594637393951416,
23
  "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 1.6592,
25
+ "eval_samples_per_second": 628.629,
26
+ "eval_steps_per_second": 78.955,
27
  "step": 214
28
  }
29
  ],
30
  "logging_steps": 500,
31
+ "max_steps": 428,
32
  "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
34
  "save_steps": 500,
35
  "total_flos": 0,
36
  "train_batch_size": 4,
37
  "trial_name": null,
38
  "trial_params": {
39
+ "learning_rate": 1.0170873699122056e-05,
40
+ "num_train_epochs": 4,
41
  "per_device_train_batch_size": 4,
42
+ "seed": 16
43
  }
44
  }
run-1/checkpoint-214/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ee984d70f75a2468c22cfd998312bd4d58e9705e58ec6c050f6541fd5b4a56c
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb79b974e6c474cc87583dfff5dff5d9e65017523a76923a915ff714cc13595c
3
  size 4984
run-1/checkpoint-321/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-1/checkpoint-321/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82af6d8048d74dd47ecb120eda1080c5cdaedd66f20334ab0ae62e299e190780
3
+ size 267832560
run-1/checkpoint-321/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cf6d2ace3101d30b84e210b7816de23e28e8304b9f9a3788af95a082ece3826
3
+ size 535727290
run-1/checkpoint-321/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaf25587094f2bdc0af6ed11d99d4355cc5b15b83d3e20fbd92ea00fe1eeedcc
3
+ size 14244
run-1/checkpoint-321/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db4c3290ca680a81491924b98d0d56ca2a39798c3465b8f14fed081f17913bd3
3
+ size 1064
run-1/checkpoint-321/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-1/checkpoint-321/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-321/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-1/checkpoint-321/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.06558874629318973,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-321",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 321,
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": 0.6247433423995972,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.9442,
16
+ "eval_samples_per_second": 1104.683,
17
+ "eval_steps_per_second": 138.747,
18
+ "step": 107
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.594637393951416,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 1.6592,
25
+ "eval_samples_per_second": 628.629,
26
+ "eval_steps_per_second": 78.955,
27
+ "step": 214
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5852178335189819,
32
+ "eval_matthews_correlation": 0.06558874629318973,
33
+ "eval_runtime": 1.8931,
34
+ "eval_samples_per_second": 550.962,
35
+ "eval_steps_per_second": 69.2,
36
+ "step": 321
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 428,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 4,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 4,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 1.0170873699122056e-05,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 4,
51
+ "seed": 16
52
+ }
53
+ }
run-1/checkpoint-321/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb79b974e6c474cc87583dfff5dff5d9e65017523a76923a915ff714cc13595c
3
+ size 4984
run-1/checkpoint-321/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-428/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-1/checkpoint-428/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb9d921ef5d0b8b2d709a310f3c49ce88d241832039fe45c1780b8f480ce00d5
3
+ size 267832560
run-1/checkpoint-428/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de59784640193a5356e7271edd0e06ac185dc721cdf37d18c9e943d1dde67df1
3
+ size 535727290
run-1/checkpoint-428/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1f0824dcbf96502ae1479ac2a5b3c2a6f98705593143ab177979d89dfc7360f
3
+ size 14244
run-1/checkpoint-428/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0fa6fc80316b53544dc4b4036705f294285ce9e9268639b67efb2e9a5ca0917
3
+ size 1064
run-1/checkpoint-428/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-1/checkpoint-428/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-428/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-1/checkpoint-428/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.1504867919191043,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-428",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 428,
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": 0.6247433423995972,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.9442,
16
+ "eval_samples_per_second": 1104.683,
17
+ "eval_steps_per_second": 138.747,
18
+ "step": 107
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.594637393951416,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 1.6592,
25
+ "eval_samples_per_second": 628.629,
26
+ "eval_steps_per_second": 78.955,
27
+ "step": 214
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5852178335189819,
32
+ "eval_matthews_correlation": 0.06558874629318973,
33
+ "eval_runtime": 1.8931,
34
+ "eval_samples_per_second": 550.962,
35
+ "eval_steps_per_second": 69.2,
36
+ "step": 321
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.5880192518234253,
41
+ "eval_matthews_correlation": 0.1504867919191043,
42
+ "eval_runtime": 2.5682,
43
+ "eval_samples_per_second": 406.123,
44
+ "eval_steps_per_second": 51.009,
45
+ "step": 428
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 428,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 4,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 4,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 1.0170873699122056e-05,
58
+ "num_train_epochs": 4,
59
+ "per_device_train_batch_size": 4,
60
+ "seed": 16
61
+ }
62
+ }