Hugging Face's logo

xuancoblab2023
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
xuancoblab2023 commited on
Commit
5993472
·
verified ·
1 Parent(s): 4ba0e2b

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1711297556.8cc2eef2edb7.2942.10 +2 -2
  2. logs/events.out.tfevents.1711297672.8cc2eef2edb7.2942.11 +3 -0
  3. model.safetensors +1 -1
  4. run-10/checkpoint-1485/config.json +34 -0
  5. run-10/checkpoint-1485/model.safetensors +3 -0
  6. run-10/checkpoint-1485/optimizer.pt +3 -0
  7. run-10/checkpoint-1485/rng_state.pth +3 -0
  8. run-10/checkpoint-1485/scheduler.pt +3 -0
  9. run-10/checkpoint-1485/special_tokens_map.json +7 -0
  10. run-10/checkpoint-1485/tokenizer.json +0 -0
  11. run-10/checkpoint-1485/tokenizer_config.json +57 -0
  12. run-10/checkpoint-1485/trainer_state.json +126 -0
  13. run-10/checkpoint-1485/training_args.bin +3 -0
  14. run-10/checkpoint-1485/vocab.txt +0 -0
  15. run-10/checkpoint-1782/config.json +34 -0
  16. run-10/checkpoint-1782/model.safetensors +3 -0
  17. run-10/checkpoint-1782/optimizer.pt +3 -0
  18. run-10/checkpoint-1782/rng_state.pth +3 -0
  19. run-10/checkpoint-1782/scheduler.pt +3 -0
  20. run-10/checkpoint-1782/special_tokens_map.json +7 -0
  21. run-10/checkpoint-1782/tokenizer.json +0 -0
  22. run-10/checkpoint-1782/tokenizer_config.json +57 -0
  23. run-10/checkpoint-1782/trainer_state.json +146 -0
  24. run-10/checkpoint-1782/training_args.bin +3 -0
  25. run-10/checkpoint-1782/vocab.txt +0 -0
  26. run-11/checkpoint-297/config.json +34 -0
  27. run-11/checkpoint-297/model.safetensors +3 -0
  28. run-11/checkpoint-297/optimizer.pt +3 -0
  29. run-11/checkpoint-297/rng_state.pth +3 -0
  30. run-11/checkpoint-297/scheduler.pt +3 -0
  31. run-11/checkpoint-297/special_tokens_map.json +7 -0
  32. run-11/checkpoint-297/tokenizer.json +0 -0
  33. run-11/checkpoint-297/tokenizer_config.json +57 -0
  34. run-11/checkpoint-297/trainer_state.json +46 -0
  35. run-11/checkpoint-297/training_args.bin +3 -0
  36. run-11/checkpoint-297/vocab.txt +0 -0
  37. training_args.bin +2 -2
logs/events.out.tfevents.1711297556.8cc2eef2edb7.2942.10 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6adc87ff7eee0ce47303d7d36afd1f8f189366e534271b06ed92957f5693016e
3
- size 6137
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f268f3ba50235960b9469426820d384dc42af99cb29b1118b07efc6868b6802
3
+ size 9411
logs/events.out.tfevents.1711297672.8cc2eef2edb7.2942.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e47f7c5fb03a345021671d2f09e19f453c5934fb37de0308a180be5cc027f03c
3
+ size 5406
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0357fb092c644e21a7a496383ce1471a9bb139c8cf8b29278061531e65ee0497
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1d78ba7bedd6c730ac672a0cc4b3d275d973b5be969fd8e11171dbb4478edd2
3
  size 17549312
run-10/checkpoint-1485/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.39.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-10/checkpoint-1485/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df1331983778cc0d1d336a9eade3e6658e75d352f1a4b9cd41668f7b6515050b
3
+ size 17549312
run-10/checkpoint-1485/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b26b7e5ce199cdc75b5c94addd8c5399fac83288e1b2f3c394ed86b1cfa594d8
3
+ size 35123898
run-10/checkpoint-1485/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60c532b5f010242990de7c2dd8b4cd2d14624b3c168e0dbeb7940a12d466a7dc
3
+ size 14308
run-10/checkpoint-1485/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:331dbc3040669dde15a191184be3807b8b0421da16e770fb579f7bc137ea9974
3
+ size 1064
run-10/checkpoint-1485/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-10/checkpoint-1485/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-10/checkpoint-1485/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-10/checkpoint-1485/trainer_state.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6792079207920793,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/checkpoint-1485",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1485,
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
+ "grad_norm": 2.256939649581909,
14
+ "learning_rate": 0.00020003476406791257,
15
+ "loss": 0.6792,
16
+ "step": 297
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5623762376237624,
21
+ "eval_f1": 0.4199475065616798,
22
+ "eval_loss": 0.6835970878601074,
23
+ "eval_mcc": 0.14191809339823447,
24
+ "eval_precision": 0.6201550387596899,
25
+ "eval_recall": 0.31746031746031744,
26
+ "eval_runtime": 0.9302,
27
+ "eval_samples_per_second": 542.921,
28
+ "eval_steps_per_second": 17.201,
29
+ "step": 297
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.075068712234497,
34
+ "learning_rate": 0.00016002781125433002,
35
+ "loss": 0.6413,
36
+ "step": 594
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6475247524752475,
41
+ "eval_f1": 0.6920415224913495,
42
+ "eval_loss": 0.6267873644828796,
43
+ "eval_mcc": 0.3090077890032306,
44
+ "eval_precision": 0.6134969325153374,
45
+ "eval_recall": 0.7936507936507936,
46
+ "eval_runtime": 0.9329,
47
+ "eval_samples_per_second": 541.318,
48
+ "eval_steps_per_second": 17.151,
49
+ "step": 594
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.5431761741638184,
54
+ "learning_rate": 0.00012002085844074753,
55
+ "loss": 0.6128,
56
+ "step": 891
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.6376237623762376,
61
+ "eval_f1": 0.7127158555729984,
62
+ "eval_loss": 0.6455628275871277,
63
+ "eval_mcc": 0.3245645841843151,
64
+ "eval_precision": 0.5896103896103896,
65
+ "eval_recall": 0.9007936507936508,
66
+ "eval_runtime": 0.9321,
67
+ "eval_samples_per_second": 541.772,
68
+ "eval_steps_per_second": 17.165,
69
+ "step": 891
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.826803207397461,
74
+ "learning_rate": 8.001390562716501e-05,
75
+ "loss": 0.5934,
76
+ "step": 1188
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6554455445544555,
81
+ "eval_f1": 0.7156862745098039,
82
+ "eval_loss": 0.6337190866470337,
83
+ "eval_mcc": 0.3445175537543676,
84
+ "eval_precision": 0.6083333333333333,
85
+ "eval_recall": 0.8690476190476191,
86
+ "eval_runtime": 0.9303,
87
+ "eval_samples_per_second": 542.814,
88
+ "eval_steps_per_second": 17.198,
89
+ "step": 1188
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 3.4030377864837646,
94
+ "learning_rate": 4.0006952813582505e-05,
95
+ "loss": 0.5801,
96
+ "step": 1485
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.6792079207920793,
101
+ "eval_f1": 0.7054545454545453,
102
+ "eval_loss": 0.6095411777496338,
103
+ "eval_mcc": 0.3647441045625896,
104
+ "eval_precision": 0.6510067114093959,
105
+ "eval_recall": 0.7698412698412699,
106
+ "eval_runtime": 0.9333,
107
+ "eval_samples_per_second": 541.076,
108
+ "eval_steps_per_second": 17.143,
109
+ "step": 1485
110
+ }
111
+ ],
112
+ "logging_steps": 500,
113
+ "max_steps": 1782,
114
+ "num_input_tokens_seen": 0,
115
+ "num_train_epochs": 6,
116
+ "save_steps": 500,
117
+ "total_flos": 3653506329900.0,
118
+ "train_batch_size": 32,
119
+ "trial_name": null,
120
+ "trial_params": {
121
+ "alpha": 0.9802546625572438,
122
+ "learning_rate": 0.00024004171688149506,
123
+ "num_train_epochs": 6,
124
+ "temperature": 49
125
+ }
126
+ }
run-10/checkpoint-1485/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2f00f9e41c59dd180c45edf27f2b5cce7facf08fcb4e44e2c4108d00dc05a63
3
+ size 4920
run-10/checkpoint-1485/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-10/checkpoint-1782/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.39.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-10/checkpoint-1782/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1ffbb9a320b88b62c4cedb0931589ad43261ac61ee4d66dd139c1c3a37493ea
3
+ size 17549312
run-10/checkpoint-1782/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c82c7d773bafba52ec0ad55ed93d563780cbd0b4a1503ac2ffc18fca1800ce
3
+ size 35123898
run-10/checkpoint-1782/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a02d6fe58f222754d8b6c88c72e65619363bb5593417cc44e98640fe115ffbc
3
+ size 14308
run-10/checkpoint-1782/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35fa6d2198c1bb970ba637749b33d105fbaf514e567489c39fffa43deab06728
3
+ size 1064
run-10/checkpoint-1782/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-10/checkpoint-1782/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-10/checkpoint-1782/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-10/checkpoint-1782/trainer_state.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6831683168316832,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/checkpoint-1782",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1782,
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
+ "grad_norm": 2.256939649581909,
14
+ "learning_rate": 0.00020003476406791257,
15
+ "loss": 0.6792,
16
+ "step": 297
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5623762376237624,
21
+ "eval_f1": 0.4199475065616798,
22
+ "eval_loss": 0.6835970878601074,
23
+ "eval_mcc": 0.14191809339823447,
24
+ "eval_precision": 0.6201550387596899,
25
+ "eval_recall": 0.31746031746031744,
26
+ "eval_runtime": 0.9302,
27
+ "eval_samples_per_second": 542.921,
28
+ "eval_steps_per_second": 17.201,
29
+ "step": 297
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.075068712234497,
34
+ "learning_rate": 0.00016002781125433002,
35
+ "loss": 0.6413,
36
+ "step": 594
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6475247524752475,
41
+ "eval_f1": 0.6920415224913495,
42
+ "eval_loss": 0.6267873644828796,
43
+ "eval_mcc": 0.3090077890032306,
44
+ "eval_precision": 0.6134969325153374,
45
+ "eval_recall": 0.7936507936507936,
46
+ "eval_runtime": 0.9329,
47
+ "eval_samples_per_second": 541.318,
48
+ "eval_steps_per_second": 17.151,
49
+ "step": 594
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.5431761741638184,
54
+ "learning_rate": 0.00012002085844074753,
55
+ "loss": 0.6128,
56
+ "step": 891
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.6376237623762376,
61
+ "eval_f1": 0.7127158555729984,
62
+ "eval_loss": 0.6455628275871277,
63
+ "eval_mcc": 0.3245645841843151,
64
+ "eval_precision": 0.5896103896103896,
65
+ "eval_recall": 0.9007936507936508,
66
+ "eval_runtime": 0.9321,
67
+ "eval_samples_per_second": 541.772,
68
+ "eval_steps_per_second": 17.165,
69
+ "step": 891
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.826803207397461,
74
+ "learning_rate": 8.001390562716501e-05,
75
+ "loss": 0.5934,
76
+ "step": 1188
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6554455445544555,
81
+ "eval_f1": 0.7156862745098039,
82
+ "eval_loss": 0.6337190866470337,
83
+ "eval_mcc": 0.3445175537543676,
84
+ "eval_precision": 0.6083333333333333,
85
+ "eval_recall": 0.8690476190476191,
86
+ "eval_runtime": 0.9303,
87
+ "eval_samples_per_second": 542.814,
88
+ "eval_steps_per_second": 17.198,
89
+ "step": 1188
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 3.4030377864837646,
94
+ "learning_rate": 4.0006952813582505e-05,
95
+ "loss": 0.5801,
96
+ "step": 1485
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.6792079207920793,
101
+ "eval_f1": 0.7054545454545453,
102
+ "eval_loss": 0.6095411777496338,
103
+ "eval_mcc": 0.3647441045625896,
104
+ "eval_precision": 0.6510067114093959,
105
+ "eval_recall": 0.7698412698412699,
106
+ "eval_runtime": 0.9333,
107
+ "eval_samples_per_second": 541.076,
108
+ "eval_steps_per_second": 17.143,
109
+ "step": 1485
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 3.6899707317352295,
114
+ "learning_rate": 0.0,
115
+ "loss": 0.5709,
116
+ "step": 1782
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.6831683168316832,
121
+ "eval_f1": 0.7090909090909091,
122
+ "eval_loss": 0.6130138039588928,
123
+ "eval_mcc": 0.3727967308109112,
124
+ "eval_precision": 0.6543624161073825,
125
+ "eval_recall": 0.7738095238095238,
126
+ "eval_runtime": 0.9378,
127
+ "eval_samples_per_second": 538.498,
128
+ "eval_steps_per_second": 17.061,
129
+ "step": 1782
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 1782,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 6,
136
+ "save_steps": 500,
137
+ "total_flos": 4384207595880.0,
138
+ "train_batch_size": 32,
139
+ "trial_name": null,
140
+ "trial_params": {
141
+ "alpha": 0.9802546625572438,
142
+ "learning_rate": 0.00024004171688149506,
143
+ "num_train_epochs": 6,
144
+ "temperature": 49
145
+ }
146
+ }
run-10/checkpoint-1782/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2f00f9e41c59dd180c45edf27f2b5cce7facf08fcb4e44e2c4108d00dc05a63
3
+ size 4920
run-10/checkpoint-1782/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-11/checkpoint-297/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.39.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-11/checkpoint-297/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1d78ba7bedd6c730ac672a0cc4b3d275d973b5be969fd8e11171dbb4478edd2
3
+ size 17549312
run-11/checkpoint-297/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9744948f029d704417919636217644e003e100c4c314496bbde3767667adce02
3
+ size 35123898
run-11/checkpoint-297/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f5e396c574b9b2ecc40d3f9e87d628a8f4be69caef81905a47fcf8895067e6
3
+ size 14308
run-11/checkpoint-297/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a6348a8869d62ebaf5e6a8549a6157b53881a2f63c016076dbbd529d2581834
3
+ size 1064
run-11/checkpoint-297/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-11/checkpoint-297/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-11/checkpoint-297/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-11/checkpoint-297/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5623762376237624,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-297",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 297,
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
+ "grad_norm": 2.1475601196289062,
14
+ "learning_rate": 0.00023316325483820226,
15
+ "loss": 0.6759,
16
+ "step": 297
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5623762376237624,
21
+ "eval_f1": 0.3402985074626866,
22
+ "eval_loss": 0.672980785369873,
23
+ "eval_mcc": 0.1665189802603812,
24
+ "eval_precision": 0.6867469879518072,
25
+ "eval_recall": 0.2261904761904762,
26
+ "eval_runtime": 0.9357,
27
+ "eval_samples_per_second": 539.729,
28
+ "eval_steps_per_second": 17.1,
29
+ "step": 297
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 1782,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 6,
36
+ "save_steps": 500,
37
+ "total_flos": 730701265980.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.9735237137483809,
42
+ "learning_rate": 0.0002797959058058427,
43
+ "num_train_epochs": 6,
44
+ "temperature": 49
45
+ }
46
+ }
run-11/checkpoint-297/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124ecb31d14b93653c0465f644e05b3427871c8d7678267355c896850165721c
3
+ size 4920
run-11/checkpoint-297/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f91d80d8fa16254fc8cafbdb71abffe2e808a53378473794805afa08c4e2bbeb
3
- size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124ecb31d14b93653c0465f644e05b3427871c8d7678267355c896850165721c
3
+ size 4920