Hugging Face's logo

Ethan615
/
try

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
Ethan615 commited on
Commit
95a0c6a
·
1 Parent(s): 79965b6

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. run-4/checkpoint-1072/config.json +25 -0
  2. run-4/checkpoint-1072/model.safetensors +3 -0
  3. run-4/checkpoint-1072/optimizer.pt +3 -0
  4. run-4/checkpoint-1072/rng_state.pth +3 -0
  5. run-4/checkpoint-1072/scheduler.pt +3 -0
  6. run-4/checkpoint-1072/special_tokens_map.json +7 -0
  7. run-4/checkpoint-1072/tokenizer.json +0 -0
  8. run-4/checkpoint-1072/tokenizer_config.json +55 -0
  9. run-4/checkpoint-1072/trainer_state.json +74 -0
  10. run-4/checkpoint-1072/training_args.bin +3 -0
  11. run-4/checkpoint-1072/vocab.txt +0 -0
  12. run-4/checkpoint-536/config.json +25 -0
  13. run-4/checkpoint-536/model.safetensors +3 -0
  14. run-4/checkpoint-536/optimizer.pt +3 -0
  15. run-4/checkpoint-536/rng_state.pth +3 -0
  16. run-4/checkpoint-536/scheduler.pt +3 -0
  17. run-4/checkpoint-536/special_tokens_map.json +7 -0
  18. run-4/checkpoint-536/tokenizer.json +0 -0
  19. run-4/checkpoint-536/tokenizer_config.json +55 -0
  20. run-4/checkpoint-536/trainer_state.json +50 -0
  21. run-4/checkpoint-536/training_args.bin +3 -0
  22. run-4/checkpoint-536/vocab.txt +0 -0
  23. run-4/checkpoint-804/config.json +25 -0
  24. run-4/checkpoint-804/model.safetensors +3 -0
  25. run-4/checkpoint-804/optimizer.pt +3 -0
  26. run-4/checkpoint-804/rng_state.pth +3 -0
  27. run-4/checkpoint-804/scheduler.pt +3 -0
  28. run-4/checkpoint-804/special_tokens_map.json +7 -0
  29. run-4/checkpoint-804/tokenizer.json +0 -0
  30. run-4/checkpoint-804/tokenizer_config.json +55 -0
  31. run-4/checkpoint-804/trainer_state.json +59 -0
  32. run-4/checkpoint-804/training_args.bin +3 -0
  33. run-4/checkpoint-804/vocab.txt +0 -0
  34. run-6/checkpoint-1070/config.json +25 -0
  35. run-6/checkpoint-1070/model.safetensors +3 -0
  36. run-6/checkpoint-1070/optimizer.pt +3 -0
  37. run-6/checkpoint-1070/rng_state.pth +3 -0
  38. run-6/checkpoint-1070/scheduler.pt +3 -0
  39. run-6/checkpoint-1070/special_tokens_map.json +7 -0
  40. run-6/checkpoint-1070/tokenizer.json +0 -0
  41. run-6/checkpoint-1070/tokenizer_config.json +55 -0
  42. run-6/checkpoint-1070/trainer_state.json +56 -0
  43. run-6/checkpoint-1070/training_args.bin +3 -0
  44. run-6/checkpoint-1070/vocab.txt +0 -0
  45. run-6/checkpoint-1605/config.json +25 -0
  46. run-6/checkpoint-1605/model.safetensors +3 -0
  47. run-6/checkpoint-1605/optimizer.pt +3 -0
  48. run-6/checkpoint-1605/rng_state.pth +3 -0
  49. run-6/checkpoint-1605/scheduler.pt +3 -0
  50. run-6/checkpoint-1605/special_tokens_map.json +7 -0
run-4/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-4/checkpoint-1072/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d60ec4d7f3d80a181c0ff02d337cde63f2c59fb4666d7046e4c1c0fd2fdeaa1
3
+ size 267832560
run-4/checkpoint-1072/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac8cd24435eccd2b4ca297f38cac18ae9cd7ff2afe66e297614c82da9d1f8736
3
+ size 535727290
run-4/checkpoint-1072/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d28407ca9326fb2f3f67659f961f74d3855fbd1338de5baf96358b3df1c2e967
3
+ size 14244
run-4/checkpoint-1072/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43f27c77a90d761e5a9759b5745e48678d5c70bf903d5df17566569838b341ee
3
+ size 1064
run-4/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-4/checkpoint-1072/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-1072/trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5070207143299597,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-804",
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": 0.478412002325058,
14
+ "eval_matthews_correlation": 0.4981947529906373,
15
+ "eval_runtime": 0.7412,
16
+ "eval_samples_per_second": 1407.09,
17
+ "eval_steps_per_second": 89.039,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 8.253927295488848e-06,
23
+ "loss": 0.4708,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.45441004633903503,
29
+ "eval_matthews_correlation": 0.5010631117439056,
30
+ "eval_runtime": 0.8128,
31
+ "eval_samples_per_second": 1283.245,
32
+ "eval_steps_per_second": 81.202,
33
+ "step": 536
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_loss": 0.5127615332603455,
38
+ "eval_matthews_correlation": 0.5070207143299597,
39
+ "eval_runtime": 0.7719,
40
+ "eval_samples_per_second": 1351.188,
41
+ "eval_steps_per_second": 85.502,
42
+ "step": 804
43
+ },
44
+ {
45
+ "epoch": 3.73,
46
+ "learning_rate": 1.0389558833482465e-06,
47
+ "loss": 0.2823,
48
+ "step": 1000
49
+ },
50
+ {
51
+ "epoch": 4.0,
52
+ "eval_loss": 0.5544026494026184,
53
+ "eval_matthews_correlation": 0.5009143907959095,
54
+ "eval_runtime": 0.7703,
55
+ "eval_samples_per_second": 1353.94,
56
+ "eval_steps_per_second": 85.676,
57
+ "step": 1072
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 1072,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 4,
64
+ "save_steps": 500,
65
+ "total_flos": 191834008735704.0,
66
+ "train_batch_size": 32,
67
+ "trial_name": null,
68
+ "trial_params": {
69
+ "learning_rate": 1.546889870762945e-05,
70
+ "num_train_epochs": 4,
71
+ "per_device_train_batch_size": 32,
72
+ "seed": 6
73
+ }
74
+ }
run-4/checkpoint-1072/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e659d03ffe6756d57c4e0e598cf990e7f41d01544dda0051abdb26300ef89e7f
3
+ size 4792
run-4/checkpoint-1072/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748a6f895e3f0b08bedcc855b1f82847f050fcd2a8353edff53f0f7cab9570a1
3
+ size 267832560
run-4/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb97f59fe49564dd2fdf3a56689a25e5bad95a44988bd227cc83c4e2c59430eb
3
+ size 535727290
run-4/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988bfdc2a1ab004ff55df4947fd2755654adae7dd44b6617a6c27b44c5205ed5
3
+ size 14244
run-4/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:744bc505fa61932d5d3d8a8fb68a9e144c59fafb5674f6c1b011d16614d05ec8
3
+ size 1064
run-4/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-4/checkpoint-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-536/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5010631117439056,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/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": 0.478412002325058,
14
+ "eval_matthews_correlation": 0.4981947529906373,
15
+ "eval_runtime": 0.7412,
16
+ "eval_samples_per_second": 1407.09,
17
+ "eval_steps_per_second": 89.039,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 8.253927295488848e-06,
23
+ "loss": 0.4708,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.45441004633903503,
29
+ "eval_matthews_correlation": 0.5010631117439056,
30
+ "eval_runtime": 0.8128,
31
+ "eval_samples_per_second": 1283.245,
32
+ "eval_steps_per_second": 81.202,
33
+ "step": 536
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 1072,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 4,
40
+ "save_steps": 500,
41
+ "total_flos": 95450522493288.0,
42
+ "train_batch_size": 32,
43
+ "trial_name": null,
44
+ "trial_params": {
45
+ "learning_rate": 1.546889870762945e-05,
46
+ "num_train_epochs": 4,
47
+ "per_device_train_batch_size": 32,
48
+ "seed": 6
49
+ }
50
+ }
run-4/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e659d03ffe6756d57c4e0e598cf990e7f41d01544dda0051abdb26300ef89e7f
3
+ size 4792
run-4/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-804/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d5c9dcbc1532d98a0abe41b3daecfdc5c404d0fe4e084e3e5fbc14cb188fbed
3
+ size 267832560
run-4/checkpoint-804/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b803593355a07b8d7756d9ebcb9cbf39e517bc7aa81a9b269d61d9805a6cbde
3
+ size 535727290
run-4/checkpoint-804/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2de754c6ffdd99498f69e21ad636090d78405e54e5fddbf05afb8569ac15a358
3
+ size 14244
run-4/checkpoint-804/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c47da02b5e58332106a6645e14397ab32170e900baca7032c258977d43f66b7a
3
+ size 1064
run-4/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-4/checkpoint-804/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-804/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5070207143299597,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/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": 0.478412002325058,
14
+ "eval_matthews_correlation": 0.4981947529906373,
15
+ "eval_runtime": 0.7412,
16
+ "eval_samples_per_second": 1407.09,
17
+ "eval_steps_per_second": 89.039,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 8.253927295488848e-06,
23
+ "loss": 0.4708,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.45441004633903503,
29
+ "eval_matthews_correlation": 0.5010631117439056,
30
+ "eval_runtime": 0.8128,
31
+ "eval_samples_per_second": 1283.245,
32
+ "eval_steps_per_second": 81.202,
33
+ "step": 536
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_loss": 0.5127615332603455,
38
+ "eval_matthews_correlation": 0.5070207143299597,
39
+ "eval_runtime": 0.7719,
40
+ "eval_samples_per_second": 1351.188,
41
+ "eval_steps_per_second": 85.502,
42
+ "step": 804
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 1072,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 4,
49
+ "save_steps": 500,
50
+ "total_flos": 95450522493288.0,
51
+ "train_batch_size": 32,
52
+ "trial_name": null,
53
+ "trial_params": {
54
+ "learning_rate": 1.546889870762945e-05,
55
+ "num_train_epochs": 4,
56
+ "per_device_train_batch_size": 32,
57
+ "seed": 6
58
+ }
59
+ }
run-4/checkpoint-804/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e659d03ffe6756d57c4e0e598cf990e7f41d01544dda0051abdb26300ef89e7f
3
+ size 4792
run-4/checkpoint-804/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-1070/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-6/checkpoint-1070/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa2fae8c0cd112bbf18a9c59c05c0a9d568db5a3401a6f617cd1781a8e116a1c
3
+ size 267832560
run-6/checkpoint-1070/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:624b284c1b3b3559200094e9b6f24f2a3a6724cba39c01ff199b273925edb9ee
3
+ size 535727290
run-6/checkpoint-1070/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4814f9c305ef9b1a52ae5f6e0fc8f4e772be1346df886cdb0fc74fe4979a8614
3
+ size 14308
run-6/checkpoint-1070/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:075ac007a397547ede9d1d51de0da9e21c36d55a276f562b11fffccea345af07
3
+ size 1064
run-6/checkpoint-1070/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-6/checkpoint-1070/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-1070/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-6/checkpoint-1070/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3132088164238629,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-1070",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1070,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "learning_rate": 1.5070736020231148e-06,
14
+ "loss": 0.5992,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.5636755228042603,
20
+ "eval_matthews_correlation": 0.0463559874942472,
21
+ "eval_runtime": 0.7247,
22
+ "eval_samples_per_second": 1439.132,
23
+ "eval_steps_per_second": 91.067,
24
+ "step": 535
25
+ },
26
+ {
27
+ "epoch": 1.87,
28
+ "learning_rate": 1.047599942869726e-06,
29
+ "loss": 0.5321,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_loss": 0.5432226061820984,
35
+ "eval_matthews_correlation": 0.3132088164238629,
36
+ "eval_runtime": 0.8222,
37
+ "eval_samples_per_second": 1268.565,
38
+ "eval_steps_per_second": 80.274,
39
+ "step": 1070
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 2140,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 4,
46
+ "save_steps": 500,
47
+ "total_flos": 87574921682568.0,
48
+ "train_batch_size": 16,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 1.9665472611765034e-06,
52
+ "num_train_epochs": 4,
53
+ "per_device_train_batch_size": 16,
54
+ "seed": 17
55
+ }
56
+ }
run-6/checkpoint-1070/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc141d7f4a0953bf5b1d96f762463ca1354802bc561e391209bc59c826f96ea9
3
+ size 4792
run-6/checkpoint-1070/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-1605/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-6/checkpoint-1605/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a562e1c07536a1101e236c9834a7822ced9b7009fcbad354a66fd250d83508b3
3
+ size 267832560
run-6/checkpoint-1605/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02b5be57d33a8d00073cb9280be20ad270b6b4f387e66d95d6bcbcfd85db684
3
+ size 535727290
run-6/checkpoint-1605/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5b483317cc198d88826dc7fa7cc001a768b155508213fdb2b79446bef149bdb
3
+ size 14308
run-6/checkpoint-1605/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b90440ec1ef750954cd312d5f7dd4211e9d739fcab9dc81696ecb2b766a27ed
3
+ size 1064
run-6/checkpoint-1605/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
+ }