Hugging Face's logo

elyziumm
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
elyziumm commited on
Commit
50676ea
•
1 Parent(s): cd46afd

End of training

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +7 -7
  2. model.safetensors +1 -1
  3. run-9/checkpoint-108/config.json +25 -0
  4. run-9/checkpoint-108/model.safetensors +3 -0
  5. run-9/checkpoint-108/optimizer.pt +3 -0
  6. run-9/checkpoint-108/rng_state.pth +3 -0
  7. run-9/checkpoint-108/scheduler.pt +3 -0
  8. run-9/checkpoint-108/special_tokens_map.json +7 -0
  9. run-9/checkpoint-108/tokenizer.json +0 -0
  10. run-9/checkpoint-108/tokenizer_config.json +55 -0
  11. run-9/checkpoint-108/trainer_state.json +62 -0
  12. run-9/checkpoint-108/training_args.bin +3 -0
  13. run-9/checkpoint-108/vocab.txt +0 -0
  14. run-9/checkpoint-135/config.json +25 -0
  15. run-9/checkpoint-135/model.safetensors +3 -0
  16. run-9/checkpoint-135/optimizer.pt +3 -0
  17. run-9/checkpoint-135/rng_state.pth +3 -0
  18. run-9/checkpoint-135/scheduler.pt +3 -0
  19. run-9/checkpoint-135/special_tokens_map.json +7 -0
  20. run-9/checkpoint-135/tokenizer.json +0 -0
  21. run-9/checkpoint-135/tokenizer_config.json +55 -0
  22. run-9/checkpoint-135/trainer_state.json +71 -0
  23. run-9/checkpoint-135/training_args.bin +3 -0
  24. run-9/checkpoint-135/vocab.txt +0 -0
  25. run-9/checkpoint-27/config.json +25 -0
  26. run-9/checkpoint-27/model.safetensors +3 -0
  27. run-9/checkpoint-27/optimizer.pt +3 -0
  28. run-9/checkpoint-27/rng_state.pth +3 -0
  29. run-9/checkpoint-27/scheduler.pt +3 -0
  30. run-9/checkpoint-27/special_tokens_map.json +7 -0
  31. run-9/checkpoint-27/tokenizer.json +0 -0
  32. run-9/checkpoint-27/tokenizer_config.json +55 -0
  33. run-9/checkpoint-27/trainer_state.json +35 -0
  34. run-9/checkpoint-27/training_args.bin +3 -0
  35. run-9/checkpoint-27/vocab.txt +0 -0
  36. run-9/checkpoint-54/config.json +25 -0
  37. run-9/checkpoint-54/model.safetensors +3 -0
  38. run-9/checkpoint-54/optimizer.pt +3 -0
  39. run-9/checkpoint-54/rng_state.pth +3 -0
  40. run-9/checkpoint-54/scheduler.pt +3 -0
  41. run-9/checkpoint-54/special_tokens_map.json +7 -0
  42. run-9/checkpoint-54/tokenizer.json +0 -0
  43. run-9/checkpoint-54/tokenizer_config.json +55 -0
  44. run-9/checkpoint-54/trainer_state.json +44 -0
  45. run-9/checkpoint-54/training_args.bin +3 -0
  46. run-9/checkpoint-54/vocab.txt +0 -0
  47. run-9/checkpoint-81/config.json +25 -0
  48. run-9/checkpoint-81/model.safetensors +3 -0
  49. run-9/checkpoint-81/optimizer.pt +3 -0
  50. run-9/checkpoint-81/rng_state.pth +3 -0
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.7625
21
- - Matthews Correlation: 0.5356
22
 
23
  ## Model description
24
 
@@ -49,11 +49,11 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
52
- | 0.5274 | 1.0 | 535 | 0.4560 | 0.4613 |
53
- | 0.374 | 2.0 | 1070 | 0.4713 | 0.5312 |
54
- | 0.2592 | 3.0 | 1605 | 0.5962 | 0.5196 |
55
- | 0.1921 | 4.0 | 2140 | 0.7600 | 0.5159 |
56
- | 0.1555 | 5.0 | 2675 | 0.7625 | 0.5356 |
57
 
58
 
59
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.6927
21
+ - Matthews Correlation: 0.5324
22
 
23
  ## Model description
24
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
52
+ | 0.5444 | 1.0 | 535 | 0.4784 | 0.4217 |
53
+ | 0.4206 | 2.0 | 1070 | 0.4567 | 0.5146 |
54
+ | 0.3071 | 3.0 | 1605 | 0.5392 | 0.5134 |
55
+ | 0.2517 | 4.0 | 2140 | 0.6712 | 0.5154 |
56
+ | 0.2141 | 5.0 | 2675 | 0.6972 | 0.5279 |
57
 
58
 
59
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d19a0152fc77465235891ab48f9f049e5f892f66994e8316da153f457bb1af2
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93bcde6093921cb7074bd1f813355147fbd6385bf5c2a515a35681c9d9704eee
3
  size 267832560
run-9/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-9/checkpoint-108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00df94b5a84aedde46d3a8a2c41ac0e742bee00c0051285470ae4f79e7b30748
3
+ size 267832560
run-9/checkpoint-108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75efa5f035a7c7791ff2797c2310548f3ab0875c93231b2b7aa61461c0a446de
3
+ size 535724410
run-9/checkpoint-108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76bde5a2aef6ed5a0e484bca9a248559e13c8e29aa32b49dc3b549311ba76b67
3
+ size 13990
run-9/checkpoint-108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17bac47e2dd26425309801b27c06d1c050a6adfac58cf4dd86a5266eeb59f5a0
3
+ size 1064
run-9/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-9/checkpoint-108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/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-9/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-9/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": 0.6144887208938599,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.8914,
16
+ "eval_samples_per_second": 1170.101,
17
+ "eval_steps_per_second": 74.043,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6105712652206421,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.9967,
25
+ "eval_samples_per_second": 1046.411,
26
+ "eval_steps_per_second": 66.216,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6057010889053345,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.9572,
34
+ "eval_samples_per_second": 1089.585,
35
+ "eval_steps_per_second": 68.948,
36
+ "step": 81
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.5996391773223877,
41
+ "eval_matthews_correlation": 0.0,
42
+ "eval_runtime": 0.9236,
43
+ "eval_samples_per_second": 1129.323,
44
+ "eval_steps_per_second": 71.462,
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": 32,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 1.0177755080206268e-05,
58
+ "num_train_epochs": 5,
59
+ "per_device_train_batch_size": 32,
60
+ "seed": 12
61
+ }
62
+ }
run-9/checkpoint-108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb524e909b3d74efd270d4b5afce33eb2a12bcfb5df4183ecdb45c59b1d80cf
3
+ size 4920
run-9/checkpoint-108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-9/checkpoint-135/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9911ce7b90a422e8a1936d11520a1003a8ae823ea42ce36e6d1d6abde4d00c4e
3
+ size 267832560
run-9/checkpoint-135/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b921c1d615b375474531a47eefb6b2ad6c432b88eb0e359e4645c808bb3eac4b
3
+ size 535724410
run-9/checkpoint-135/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f40f67ef665c917661c94c0f6fd3399aeb0a563c9e81e7ec02a5795a0e88e1fd
3
+ size 13990
run-9/checkpoint-135/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba0debde8e00050f1b2b3431f7f03d7a482da99c8b3c29df3e27f4858db526e5
3
+ size 1064
run-9/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-9/checkpoint-135/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/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-9/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-9/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": 0.6144887208938599,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.8914,
16
+ "eval_samples_per_second": 1170.101,
17
+ "eval_steps_per_second": 74.043,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6105712652206421,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.9967,
25
+ "eval_samples_per_second": 1046.411,
26
+ "eval_steps_per_second": 66.216,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6057010889053345,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.9572,
34
+ "eval_samples_per_second": 1089.585,
35
+ "eval_steps_per_second": 68.948,
36
+ "step": 81
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.5996391773223877,
41
+ "eval_matthews_correlation": 0.0,
42
+ "eval_runtime": 0.9236,
43
+ "eval_samples_per_second": 1129.323,
44
+ "eval_steps_per_second": 71.462,
45
+ "step": 108
46
+ },
47
+ {
48
+ "epoch": 5.0,
49
+ "eval_loss": 0.5960709452629089,
50
+ "eval_matthews_correlation": 0.0,
51
+ "eval_runtime": 0.8872,
52
+ "eval_samples_per_second": 1175.604,
53
+ "eval_steps_per_second": 74.391,
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": 32,
64
+ "trial_name": null,
65
+ "trial_params": {
66
+ "learning_rate": 1.0177755080206268e-05,
67
+ "num_train_epochs": 5,
68
+ "per_device_train_batch_size": 32,
69
+ "seed": 12
70
+ }
71
+ }
run-9/checkpoint-135/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb524e909b3d74efd270d4b5afce33eb2a12bcfb5df4183ecdb45c59b1d80cf
3
+ size 4920
run-9/checkpoint-135/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-27/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-9/checkpoint-27/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e90225c3f54782c719a458e612b57e880f21b5c101270f7f36b684a0da70263
3
+ size 267832560
run-9/checkpoint-27/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46c8fd0921a07a5315e9ccf8807c09977b173f9e1602e6377a067ad50cf6884b
3
+ size 535724410
run-9/checkpoint-27/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69bd2049cdc91f74479dd2bf593f368676916d904d701dad14b187e368d85407
3
+ size 13990
run-9/checkpoint-27/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15e4312a5e4a04014864ee963a8630139482f14c9c719d75a3ac05d5735d836
3
+ size 1064
run-9/checkpoint-27/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-9/checkpoint-27/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-27/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-9/checkpoint-27/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-27",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 27,
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": 0.6144887208938599,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.8914,
16
+ "eval_samples_per_second": 1170.101,
17
+ "eval_steps_per_second": 74.043,
18
+ "step": 27
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 135,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 32,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 1.0177755080206268e-05,
31
+ "num_train_epochs": 5,
32
+ "per_device_train_batch_size": 32,
33
+ "seed": 12
34
+ }
35
+ }
run-9/checkpoint-27/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb524e909b3d74efd270d4b5afce33eb2a12bcfb5df4183ecdb45c59b1d80cf
3
+ size 4920
run-9/checkpoint-27/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-9/checkpoint-54/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b95d6a53cd3cf9851d9a72187a530371ca62b48efdcb5a98a888c9dc5b402c9a
3
+ size 267832560
run-9/checkpoint-54/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e19b1b3fedc6f0891cd478c187787e71cafa41a894610d3c22227856e60c2d6e
3
+ size 535724410
run-9/checkpoint-54/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b62d6467f8b2d76d59a9606222f7bd6658470db8dfbf182c5ee453630bb4bc88
3
+ size 13990
run-9/checkpoint-54/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ec11f521fd55421a62cc26bf6be888d453dc2268855595cf5b75be21773bc2
3
+ size 1064
run-9/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-9/checkpoint-54/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/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-9/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-9/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": 0.6144887208938599,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.8914,
16
+ "eval_samples_per_second": 1170.101,
17
+ "eval_steps_per_second": 74.043,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6105712652206421,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.9967,
25
+ "eval_samples_per_second": 1046.411,
26
+ "eval_steps_per_second": 66.216,
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": 32,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 1.0177755080206268e-05,
40
+ "num_train_epochs": 5,
41
+ "per_device_train_batch_size": 32,
42
+ "seed": 12
43
+ }
44
+ }
run-9/checkpoint-54/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb524e909b3d74efd270d4b5afce33eb2a12bcfb5df4183ecdb45c59b1d80cf
3
+ size 4920
run-9/checkpoint-54/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-9/checkpoint-81/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:599a09d968cc0d2ddb1cb4c321e027da7490f3f860e3995ffd855722e009c50f
3
+ size 267832560
run-9/checkpoint-81/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:562a43bf31f744a29600d1ea893e3560c44f4877030eef7baef9fa9fe59dff8e
3
+ size 535724410
run-9/checkpoint-81/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e4a531f143f8038e235c2ea560fb6f8ad459cedb8de63e5c8619163bd6e994a
3
+ size 13990