Hugging Face's logo

dannychou
/
Homework01

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
dannychou commited on
Commit
1d51f0b
·
1 Parent(s): 6e147d0

Training in progress, epoch 5

Browse files
Files changed (46) hide show
  1. model.safetensors +1 -1
  2. run-3/checkpoint-1072/config.json +25 -0
  3. run-3/checkpoint-1072/model.safetensors +3 -0
  4. run-3/checkpoint-1072/optimizer.pt +3 -0
  5. run-3/checkpoint-1072/rng_state.pth +3 -0
  6. run-3/checkpoint-1072/scheduler.pt +3 -0
  7. run-3/checkpoint-1072/special_tokens_map.json +7 -0
  8. run-3/checkpoint-1072/tokenizer.json +0 -0
  9. run-3/checkpoint-1072/tokenizer_config.json +55 -0
  10. run-3/checkpoint-1072/trainer_state.json +74 -0
  11. run-3/checkpoint-1072/training_args.bin +3 -0
  12. run-3/checkpoint-1072/vocab.txt +0 -0
  13. run-3/checkpoint-268/config.json +25 -0
  14. run-3/checkpoint-268/model.safetensors +3 -0
  15. run-3/checkpoint-268/optimizer.pt +3 -0
  16. run-3/checkpoint-268/rng_state.pth +3 -0
  17. run-3/checkpoint-268/scheduler.pt +3 -0
  18. run-3/checkpoint-268/special_tokens_map.json +7 -0
  19. run-3/checkpoint-268/tokenizer.json +0 -0
  20. run-3/checkpoint-268/tokenizer_config.json +55 -0
  21. run-3/checkpoint-268/trainer_state.json +35 -0
  22. run-3/checkpoint-268/training_args.bin +3 -0
  23. run-3/checkpoint-268/vocab.txt +0 -0
  24. run-3/checkpoint-536/config.json +25 -0
  25. run-3/checkpoint-536/model.safetensors +3 -0
  26. run-3/checkpoint-536/optimizer.pt +3 -0
  27. run-3/checkpoint-536/rng_state.pth +3 -0
  28. run-3/checkpoint-536/scheduler.pt +3 -0
  29. run-3/checkpoint-536/special_tokens_map.json +7 -0
  30. run-3/checkpoint-536/tokenizer.json +0 -0
  31. run-3/checkpoint-536/tokenizer_config.json +55 -0
  32. run-3/checkpoint-536/trainer_state.json +50 -0
  33. run-3/checkpoint-536/training_args.bin +3 -0
  34. run-3/checkpoint-536/vocab.txt +0 -0
  35. run-3/checkpoint-804/config.json +25 -0
  36. run-3/checkpoint-804/model.safetensors +3 -0
  37. run-3/checkpoint-804/optimizer.pt +3 -0
  38. run-3/checkpoint-804/rng_state.pth +3 -0
  39. run-3/checkpoint-804/scheduler.pt +3 -0
  40. run-3/checkpoint-804/special_tokens_map.json +7 -0
  41. run-3/checkpoint-804/tokenizer.json +0 -0
  42. run-3/checkpoint-804/tokenizer_config.json +55 -0
  43. run-3/checkpoint-804/trainer_state.json +59 -0
  44. run-3/checkpoint-804/training_args.bin +3 -0
  45. run-3/checkpoint-804/vocab.txt +0 -0
  46. runs/Dec23_02-10-12_067bf7a71e5c/events.out.tfevents.1703298490.067bf7a71e5c.178.5 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df9da5d86d23a16eca8727d004dfe63b540561578a05c9033bcea31d05e1767e
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d747f47ecdd25c1b091c915b2013ee4bdb18de77acfb25abbd5ceb5b8190e40a
3
  size 267832560
run-3/checkpoint-1072/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-3/checkpoint-1072/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:612692b245ca538d9a6e5f6279115ccea72532d92ce833a6eba9d47249f20e76
3
+ size 267832560
run-3/checkpoint-1072/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc79440b5bd720145f5f7eb32edc941fd85898fc38b9a620a7e7cd431b4d2db1
3
+ size 535727290
run-3/checkpoint-1072/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c427b597378496e52a675cc52b7e7854560eca517bcc1a9acff185bab072c6e7
3
+ size 14308
run-3/checkpoint-1072/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:625ac2ebd4538e5d5db3ebd5483143d39404f7887dda5e6f5564668b9441bb7b
3
+ size 1064
run-3/checkpoint-1072/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-1072/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-1072/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-1072/trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5104242686414723,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-1072",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1072,
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": 0.49783048033714294,
14
+ "eval_matthews_correlation": 0.4111094454070522,
15
+ "eval_runtime": 0.7234,
16
+ "eval_samples_per_second": 1441.791,
17
+ "eval_steps_per_second": 91.235,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 7.123299677400847e-06,
23
+ "loss": 0.4894,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.5266438126564026,
29
+ "eval_matthews_correlation": 0.44722803398940786,
30
+ "eval_runtime": 0.7661,
31
+ "eval_samples_per_second": 1361.434,
32
+ "eval_steps_per_second": 86.15,
33
+ "step": 536
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_loss": 0.4729432761669159,
38
+ "eval_matthews_correlation": 0.5011490576561073,
39
+ "eval_runtime": 0.7179,
40
+ "eval_samples_per_second": 1452.841,
41
+ "eval_steps_per_second": 91.934,
42
+ "step": 804
43
+ },
44
+ {
45
+ "epoch": 3.73,
46
+ "learning_rate": 2.8832403456146286e-06,
47
+ "loss": 0.3212,
48
+ "step": 1000
49
+ },
50
+ {
51
+ "epoch": 4.0,
52
+ "eval_loss": 0.5100820064544678,
53
+ "eval_matthews_correlation": 0.5104242686414723,
54
+ "eval_runtime": 0.8168,
55
+ "eval_samples_per_second": 1276.879,
56
+ "eval_steps_per_second": 80.8,
57
+ "step": 1072
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 1340,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 5,
64
+ "save_steps": 500,
65
+ "total_flos": 190621621567536.0,
66
+ "train_batch_size": 32,
67
+ "trial_name": null,
68
+ "trial_params": {
69
+ "learning_rate": 1.1363359009187065e-05,
70
+ "num_train_epochs": 5,
71
+ "per_device_train_batch_size": 32,
72
+ "seed": 20
73
+ }
74
+ }
run-3/checkpoint-1072/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79499fe7d2034d8df2f65fc54dbfcd286a83e4c8aaa162c7b786314e484018d
3
+ size 4792
run-3/checkpoint-1072/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-3/checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df9da5d86d23a16eca8727d004dfe63b540561578a05c9033bcea31d05e1767e
3
+ size 267832560
run-3/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a679603d9a76cfdbe2781eaf220b8313e1d6d44585e9153d707f8f52e61d3e77
3
+ size 535727290
run-3/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b8cfe25a915f9cc83ad71e9d831288a4edb9a530a69cb0778e7d75bb45a8399
3
+ size 14308
run-3/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7de586a3166598384cec9203cee7749fbf217486c3e1d29520f587dfa87956c
3
+ size 1064
run-3/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-3/checkpoint-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-268/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4111094454070522,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-268",
4
+ "epoch": 1.0,
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": 0.49783048033714294,
14
+ "eval_matthews_correlation": 0.4111094454070522,
15
+ "eval_runtime": 0.7234,
16
+ "eval_samples_per_second": 1441.791,
17
+ "eval_steps_per_second": 91.235,
18
+ "step": 268
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 1340,
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": 1.1363359009187065e-05,
31
+ "num_train_epochs": 5,
32
+ "per_device_train_batch_size": 32,
33
+ "seed": 20
34
+ }
35
+ }
run-3/checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79499fe7d2034d8df2f65fc54dbfcd286a83e4c8aaa162c7b786314e484018d
3
+ size 4792
run-3/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-3/checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b344648de241011aa94f996e376817a0f10aba4078d77dba6e93a40c5e7916b5
3
+ size 267832560
run-3/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dc4362081b09b792adf0973ce8e55644289eebb37f9ea18418bdf05f5ae24e6
3
+ size 535727290
run-3/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eaf189c1b343d7c12f945cff87634b5508ec0a3a9be437fac5ba23414a097e1
3
+ size 14308
run-3/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42eb6a22f790c1818f6be136a2bf2f7a3374076047162452f27ed2546d14018d
3
+ size 1064
run-3/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-3/checkpoint-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-536/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.44722803398940786,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-536",
4
+ "epoch": 2.0,
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": 0.49783048033714294,
14
+ "eval_matthews_correlation": 0.4111094454070522,
15
+ "eval_runtime": 0.7234,
16
+ "eval_samples_per_second": 1441.791,
17
+ "eval_steps_per_second": 91.235,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 7.123299677400847e-06,
23
+ "loss": 0.4894,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.5266438126564026,
29
+ "eval_matthews_correlation": 0.44722803398940786,
30
+ "eval_runtime": 0.7661,
31
+ "eval_samples_per_second": 1361.434,
32
+ "eval_steps_per_second": 86.15,
33
+ "step": 536
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 1340,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 5,
40
+ "save_steps": 500,
41
+ "total_flos": 95454144648720.0,
42
+ "train_batch_size": 32,
43
+ "trial_name": null,
44
+ "trial_params": {
45
+ "learning_rate": 1.1363359009187065e-05,
46
+ "num_train_epochs": 5,
47
+ "per_device_train_batch_size": 32,
48
+ "seed": 20
49
+ }
50
+ }
run-3/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79499fe7d2034d8df2f65fc54dbfcd286a83e4c8aaa162c7b786314e484018d
3
+ size 4792
run-3/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-804/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-3/checkpoint-804/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6018f5193f2bd259e1a5abc21969c8bdcc49733862c8d736396bd9e7ac48d58
3
+ size 267832560
run-3/checkpoint-804/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21192d208e889d8d0fb1853a20d4782a456acc266cd685f883aa64a953ce599a
3
+ size 535727290
run-3/checkpoint-804/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b41f2ce534f4fadba8f6290aab1b81abd8b58681428b6205d4ea30dd7c33ae74
3
+ size 14308
run-3/checkpoint-804/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82343c51c4eb7f4880e03f8be75b76daf228610277755fe29fbef7a7e4487f81
3
+ size 1064
run-3/checkpoint-804/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-804/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-804/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-804/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5011490576561073,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-804",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 804,
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": 0.49783048033714294,
14
+ "eval_matthews_correlation": 0.4111094454070522,
15
+ "eval_runtime": 0.7234,
16
+ "eval_samples_per_second": 1441.791,
17
+ "eval_steps_per_second": 91.235,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 7.123299677400847e-06,
23
+ "loss": 0.4894,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.5266438126564026,
29
+ "eval_matthews_correlation": 0.44722803398940786,
30
+ "eval_runtime": 0.7661,
31
+ "eval_samples_per_second": 1361.434,
32
+ "eval_steps_per_second": 86.15,
33
+ "step": 536
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_loss": 0.4729432761669159,
38
+ "eval_matthews_correlation": 0.5011490576561073,
39
+ "eval_runtime": 0.7179,
40
+ "eval_samples_per_second": 1452.841,
41
+ "eval_steps_per_second": 91.934,
42
+ "step": 804
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 1340,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 5,
49
+ "save_steps": 500,
50
+ "total_flos": 95454144648720.0,
51
+ "train_batch_size": 32,
52
+ "trial_name": null,
53
+ "trial_params": {
54
+ "learning_rate": 1.1363359009187065e-05,
55
+ "num_train_epochs": 5,
56
+ "per_device_train_batch_size": 32,
57
+ "seed": 20
58
+ }
59
+ }
run-3/checkpoint-804/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79499fe7d2034d8df2f65fc54dbfcd286a83e4c8aaa162c7b786314e484018d
3
+ size 4792
run-3/checkpoint-804/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-10-12_067bf7a71e5c/events.out.tfevents.1703298490.067bf7a71e5c.178.5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb0db4d47370b4ec1da67edc9cebc83883adb9feb1e0bd3e070d654e3e36abf0
3
- size 5177
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa403654bf2ac2814fa4b732d50c2514e693e0ba8f4096cb5b9c2316901cc15f
3
+ size 6693