Hugging Face's logo

karunac
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
karunac commited on
Commit
19ed4e7
·
verified ·
1 Parent(s): e602706

Training in progress, epoch 1

Browse files
Files changed (48) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-14/config.json +25 -0
  3. run-2/checkpoint-14/model.safetensors +3 -0
  4. run-2/checkpoint-14/optimizer.pt +3 -0
  5. run-2/checkpoint-14/rng_state.pth +3 -0
  6. run-2/checkpoint-14/scheduler.pt +3 -0
  7. run-2/checkpoint-14/special_tokens_map.json +7 -0
  8. run-2/checkpoint-14/tokenizer.json +0 -0
  9. run-2/checkpoint-14/tokenizer_config.json +55 -0
  10. run-2/checkpoint-14/trainer_state.json +44 -0
  11. run-2/checkpoint-14/training_args.bin +3 -0
  12. run-2/checkpoint-14/vocab.txt +0 -0
  13. run-2/checkpoint-21/config.json +25 -0
  14. run-2/checkpoint-21/model.safetensors +3 -0
  15. run-2/checkpoint-21/optimizer.pt +3 -0
  16. run-2/checkpoint-21/rng_state.pth +3 -0
  17. run-2/checkpoint-21/scheduler.pt +3 -0
  18. run-2/checkpoint-21/special_tokens_map.json +7 -0
  19. run-2/checkpoint-21/tokenizer.json +0 -0
  20. run-2/checkpoint-21/tokenizer_config.json +55 -0
  21. run-2/checkpoint-21/trainer_state.json +53 -0
  22. run-2/checkpoint-21/training_args.bin +3 -0
  23. run-2/checkpoint-21/vocab.txt +0 -0
  24. run-2/checkpoint-28/config.json +25 -0
  25. run-2/checkpoint-28/model.safetensors +3 -0
  26. run-2/checkpoint-28/optimizer.pt +3 -0
  27. run-2/checkpoint-28/rng_state.pth +3 -0
  28. run-2/checkpoint-28/scheduler.pt +3 -0
  29. run-2/checkpoint-28/special_tokens_map.json +7 -0
  30. run-2/checkpoint-28/tokenizer.json +0 -0
  31. run-2/checkpoint-28/tokenizer_config.json +55 -0
  32. run-2/checkpoint-28/trainer_state.json +62 -0
  33. run-2/checkpoint-28/training_args.bin +3 -0
  34. run-2/checkpoint-28/vocab.txt +0 -0
  35. run-3/checkpoint-7/config.json +25 -0
  36. run-3/checkpoint-7/model.safetensors +3 -0
  37. run-3/checkpoint-7/optimizer.pt +3 -0
  38. run-3/checkpoint-7/rng_state.pth +3 -0
  39. run-3/checkpoint-7/scheduler.pt +3 -0
  40. run-3/checkpoint-7/special_tokens_map.json +7 -0
  41. run-3/checkpoint-7/tokenizer.json +0 -0
  42. run-3/checkpoint-7/tokenizer_config.json +55 -0
  43. run-3/checkpoint-7/trainer_state.json +35 -0
  44. run-3/checkpoint-7/training_args.bin +3 -0
  45. run-3/checkpoint-7/vocab.txt +0 -0
  46. runs/Mar05_15-34-07_d253bcf50e04/events.out.tfevents.1709653359.d253bcf50e04.1525.5 +2 -2
  47. runs/Mar05_15-34-07_d253bcf50e04/events.out.tfevents.1709653550.d253bcf50e04.1525.6 +3 -0
  48. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9834716971b8697b905efec52f78a48282b68d9feba105400b281007ffaab202
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d2b1c82e75b663bab996c3cf580958aa0430a6a222f30a5cf82b040c031e137
3
  size 267832560
run-2/checkpoint-14/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-2/checkpoint-14/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e84725ba09e79392a1f83edc925fd1d6bf1672f90ae2084472ac372bd30f52a2
3
+ size 267832560
run-2/checkpoint-14/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe8b73fca38013b03b142765c66165c32c3b0d672e218a675d1329b420dc2ea8
3
+ size 535724410
run-2/checkpoint-14/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11af9b2e06e06ae7afd2b6ab6ce770d85dcf98ebd94e0c23db363dae05801df9
3
+ size 14054
run-2/checkpoint-14/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28f569c24cfeb1008c8aa1bf1c3e9e7957929155e04ab6ff6f69017ccbcd148d
3
+ size 1064
run-2/checkpoint-14/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-2/checkpoint-14/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-14/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-2/checkpoint-14/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-7",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 14,
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": 0.6433300971984863,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 3.8294,
16
+ "eval_samples_per_second": 26.114,
17
+ "eval_steps_per_second": 1.828,
18
+ "step": 7
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6291647553443909,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 4.4315,
25
+ "eval_samples_per_second": 22.566,
26
+ "eval_steps_per_second": 1.58,
27
+ "step": 14
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 28,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 32,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 4.73256592454282e-05,
40
+ "num_train_epochs": 4,
41
+ "per_device_train_batch_size": 32,
42
+ "seed": 26
43
+ }
44
+ }
run-2/checkpoint-14/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:253d52407ff71a08518d2da2e621a8083036731f0b83cc2a067ab7a435881691
3
+ size 4984
run-2/checkpoint-14/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-21/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df1b6af66bc37a79135b3657df66788f30d0b30b3e6159d75476c2cec69f040d
3
+ size 267832560
run-2/checkpoint-21/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6a25f0b02e23716d01bf216d6831bb8eb1b84c67c030c18ba98fa214ceaa8d8
3
+ size 535724410
run-2/checkpoint-21/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ef3a1fd88906c13bee3dddb11120d093ccd433abeb47fb5798045a8497140cb
3
+ size 14054
run-2/checkpoint-21/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83255393bf29d00a5e6e81ef1bc5ae70c37de8110e1b799dd3efa6a9964b1d6e
3
+ size 1064
run-2/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-2/checkpoint-21/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-21/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-7",
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": 0.6433300971984863,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 3.8294,
16
+ "eval_samples_per_second": 26.114,
17
+ "eval_steps_per_second": 1.828,
18
+ "step": 7
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6291647553443909,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 4.4315,
25
+ "eval_samples_per_second": 22.566,
26
+ "eval_steps_per_second": 1.58,
27
+ "step": 14
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6215782761573792,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 4.4898,
34
+ "eval_samples_per_second": 22.273,
35
+ "eval_steps_per_second": 1.559,
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": 32,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 4.73256592454282e-05,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 32,
51
+ "seed": 26
52
+ }
53
+ }
run-2/checkpoint-21/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:253d52407ff71a08518d2da2e621a8083036731f0b83cc2a067ab7a435881691
3
+ size 4984
run-2/checkpoint-21/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-28/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-2/checkpoint-28/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2de67f27a7c0f2f4cf4afa302118cf13d3617fca5f3aa50de3c6a0712b2ba3c0
3
+ size 267832560
run-2/checkpoint-28/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb184db54a72c27330a0575dd93c03362be11c1f1441bfc224a6c6cb16cd5678
3
+ size 535724410
run-2/checkpoint-28/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b7d57546f2269239853809470d1d271f2dd158ca2ddedfa10a737e9217aefa
3
+ size 14054
run-2/checkpoint-28/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f718f695fdea6861059386349503980ac7d12030f1f85d194e28c908a0ebeb39
3
+ size 1064
run-2/checkpoint-28/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-2/checkpoint-28/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-28/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-2/checkpoint-28/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-7",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 28,
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": 0.6433300971984863,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 3.8294,
16
+ "eval_samples_per_second": 26.114,
17
+ "eval_steps_per_second": 1.828,
18
+ "step": 7
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6291647553443909,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 4.4315,
25
+ "eval_samples_per_second": 22.566,
26
+ "eval_steps_per_second": 1.58,
27
+ "step": 14
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6215782761573792,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 4.4898,
34
+ "eval_samples_per_second": 22.273,
35
+ "eval_steps_per_second": 1.559,
36
+ "step": 21
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.6199344992637634,
41
+ "eval_matthews_correlation": 0.0,
42
+ "eval_runtime": 6.7933,
43
+ "eval_samples_per_second": 14.72,
44
+ "eval_steps_per_second": 1.03,
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": 32,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 4.73256592454282e-05,
58
+ "num_train_epochs": 4,
59
+ "per_device_train_batch_size": 32,
60
+ "seed": 26
61
+ }
62
+ }
run-2/checkpoint-28/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:253d52407ff71a08518d2da2e621a8083036731f0b83cc2a067ab7a435881691
3
+ size 4984
run-2/checkpoint-28/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-7/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-3/checkpoint-7/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d2b1c82e75b663bab996c3cf580958aa0430a6a222f30a5cf82b040c031e137
3
+ size 267832560
run-3/checkpoint-7/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2428abb32480e41f7e079d00165ffc555f9488b5e34ffff5aba967b163373cc2
3
+ size 535724410
run-3/checkpoint-7/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a56537571ec4312b11c97b4cf44c33bd6e02bd6f5ea175b20cd7bb911b86b9fe
3
+ size 13990
run-3/checkpoint-7/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d76f2098d13d34fdc54cd96540afe293bb90bc4c2d93299e614cda4e5d777fba
3
+ size 1064
run-3/checkpoint-7/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-3/checkpoint-7/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-7/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-3/checkpoint-7/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-7",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 7,
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": 0.6759664416313171,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 3.4071,
16
+ "eval_samples_per_second": 29.351,
17
+ "eval_steps_per_second": 2.055,
18
+ "step": 7
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 7,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 1,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 32,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 6.229562657712552e-06,
31
+ "num_train_epochs": 1,
32
+ "per_device_train_batch_size": 32,
33
+ "seed": 4
34
+ }
35
+ }
run-3/checkpoint-7/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5c946af4b73c39a32b8f32ebc30c46e3627e4751241353af36349e42813f671
3
+ size 4984
run-3/checkpoint-7/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar05_15-34-07_d253bcf50e04/events.out.tfevents.1709653359.d253bcf50e04.1525.5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08bf9a8501fc5df5dc11a7fb791b80285f90b81c1e27f7f54726f37c94f37bf2
3
- size 4870
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d810ee34e2f4491ee0900928971e866acf6e36d50320372f0d3472dd8e0fcfae
3
+ size 6205
runs/Mar05_15-34-07_d253bcf50e04/events.out.tfevents.1709653550.d253bcf50e04.1525.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f2a83ce79c21b695516d7bc60ce2faa5810e761a4822f1b4ba7d7b1ff190d26
3
+ size 5218
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:253d52407ff71a08518d2da2e621a8083036731f0b83cc2a067ab7a435881691
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5c946af4b73c39a32b8f32ebc30c46e3627e4751241353af36349e42813f671
3
  size 4984