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
3a6237f
·
verified ·
1 Parent(s): a4cb1cb

Training in progress, epoch 1

Browse files
Files changed (38) hide show
  1. logs/events.out.tfevents.1713437920.ec9626078864.14834.21 +2 -2
  2. logs/events.out.tfevents.1713438292.ec9626078864.14834.22 +3 -0
  3. logs/events.out.tfevents.1713438345.ec9626078864.14834.23 +3 -0
  4. model.safetensors +1 -1
  5. run-20/checkpoint-3870/config.json +34 -0
  6. run-20/checkpoint-3870/model.safetensors +3 -0
  7. run-20/checkpoint-3870/optimizer.pt +3 -0
  8. run-20/checkpoint-3870/rng_state.pth +3 -0
  9. run-20/checkpoint-3870/scheduler.pt +3 -0
  10. run-20/checkpoint-3870/special_tokens_map.json +7 -0
  11. run-20/checkpoint-3870/tokenizer.json +0 -0
  12. run-20/checkpoint-3870/tokenizer_config.json +57 -0
  13. run-20/checkpoint-3870/trainer_state.json +146 -0
  14. run-20/checkpoint-3870/training_args.bin +3 -0
  15. run-20/checkpoint-3870/vocab.txt +0 -0
  16. run-20/checkpoint-4515/config.json +34 -0
  17. run-20/checkpoint-4515/model.safetensors +3 -0
  18. run-20/checkpoint-4515/optimizer.pt +3 -0
  19. run-20/checkpoint-4515/rng_state.pth +3 -0
  20. run-20/checkpoint-4515/scheduler.pt +3 -0
  21. run-20/checkpoint-4515/special_tokens_map.json +7 -0
  22. run-20/checkpoint-4515/tokenizer.json +0 -0
  23. run-20/checkpoint-4515/tokenizer_config.json +57 -0
  24. run-20/checkpoint-4515/trainer_state.json +166 -0
  25. run-20/checkpoint-4515/training_args.bin +3 -0
  26. run-20/checkpoint-4515/vocab.txt +0 -0
  27. run-22/checkpoint-645/config.json +34 -0
  28. run-22/checkpoint-645/model.safetensors +3 -0
  29. run-22/checkpoint-645/optimizer.pt +3 -0
  30. run-22/checkpoint-645/rng_state.pth +3 -0
  31. run-22/checkpoint-645/scheduler.pt +3 -0
  32. run-22/checkpoint-645/special_tokens_map.json +7 -0
  33. run-22/checkpoint-645/tokenizer.json +0 -0
  34. run-22/checkpoint-645/tokenizer_config.json +57 -0
  35. run-22/checkpoint-645/trainer_state.json +46 -0
  36. run-22/checkpoint-645/training_args.bin +3 -0
  37. run-22/checkpoint-645/vocab.txt +0 -0
  38. training_args.bin +1 -1
logs/events.out.tfevents.1713437920.ec9626078864.14834.21 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81e666284c5e5efacfe21d0dcb8550a87ea1a3d402b984a52551acdea2731002
3
- size 6136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4836c9f3b483583e74ebd034f9cd707aa1edc84315546cd455e3d95be117efb9
3
+ size 10140
logs/events.out.tfevents.1713438292.ec9626078864.14834.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef37c0b6e35d2077a8e3b4c73a48d9e2b93619a667f81a6b6226547a4675aedd
3
+ size 5407
logs/events.out.tfevents.1713438345.ec9626078864.14834.23 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cea53af2887d60843d61f7b65c8635e4bb00997b6927acbe25ced2788ccbf87
3
+ size 5407
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35c8123f3383f26fa739512a334974cbb23bcfa0a390237f5773f25a5993c260
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d0f6599d392c90e9528fe8546a8df09766fdfc9d1d7a34f944b1777ed6258f7
3
  size 17549312
run-20/checkpoint-3870/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": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-20/checkpoint-3870/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae9d2e5bf8813f80bf8470a6e2dad988ad4e2fe3d88f4bc5b323b849f6b7e972
3
+ size 17549312
run-20/checkpoint-3870/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f1afc7fbbc918d591f0ca908605bc47eb1072c181f217bf4f9b6e9cc83896c
3
+ size 35123898
run-20/checkpoint-3870/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd3594daca53cebdd7cbf0d80846211d0eafca218895f209b5494269a0d240f
3
+ size 14308
run-20/checkpoint-3870/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:014ff7a9d841c9c0896d9a779a4e4c526e1e97200a88fc647f5dea423654084a
3
+ size 1064
run-20/checkpoint-3870/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-20/checkpoint-3870/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-20/checkpoint-3870/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-20/checkpoint-3870/trainer_state.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9038386971694455,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-20/checkpoint-3870",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3870,
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": 1.6259269714355469,
14
+ "learning_rate": 0.0003431069228198171,
15
+ "loss": 0.3055,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8889104303993796,
21
+ "eval_f1": 0.19409282700421943,
22
+ "eval_loss": 0.2940736413002014,
23
+ "eval_mcc": 0.20172457395808635,
24
+ "eval_precision": 0.4859154929577465,
25
+ "eval_recall": 0.12126537785588752,
26
+ "eval_runtime": 9.9362,
27
+ "eval_samples_per_second": 519.111,
28
+ "eval_steps_per_second": 16.304,
29
+ "step": 645
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 0.638690710067749,
34
+ "learning_rate": 0.00028592243568318097,
35
+ "loss": 0.2894,
36
+ "step": 1290
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8964715005816207,
41
+ "eval_f1": 0.18844984802431614,
42
+ "eval_loss": 0.2831971049308777,
43
+ "eval_mcc": 0.24798827118495087,
44
+ "eval_precision": 0.6966292134831461,
45
+ "eval_recall": 0.10896309314586995,
46
+ "eval_runtime": 9.9132,
47
+ "eval_samples_per_second": 520.316,
48
+ "eval_steps_per_second": 16.342,
49
+ "step": 1290
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 0.7561137080192566,
54
+ "learning_rate": 0.00022873794854654474,
55
+ "loss": 0.2795,
56
+ "step": 1935
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.8964715005816207,
61
+ "eval_f1": 0.165625,
62
+ "eval_loss": 0.2780698239803314,
63
+ "eval_mcc": 0.2399021362225046,
64
+ "eval_precision": 0.7464788732394366,
65
+ "eval_recall": 0.09314586994727592,
66
+ "eval_runtime": 10.0176,
67
+ "eval_samples_per_second": 514.893,
68
+ "eval_steps_per_second": 16.172,
69
+ "step": 1935
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.1933393478393555,
74
+ "learning_rate": 0.00017155346140990856,
75
+ "loss": 0.2738,
76
+ "step": 2580
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.8986041101202016,
81
+ "eval_f1": 0.309114927344782,
82
+ "eval_loss": 0.28069812059402466,
83
+ "eval_mcc": 0.3178770819197392,
84
+ "eval_precision": 0.6223404255319149,
85
+ "eval_recall": 0.2056239015817223,
86
+ "eval_runtime": 10.0583,
87
+ "eval_samples_per_second": 512.809,
88
+ "eval_steps_per_second": 16.106,
89
+ "step": 2580
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 0.9380802512168884,
94
+ "learning_rate": 0.00011436897427327237,
95
+ "loss": 0.27,
96
+ "step": 3225
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.9011244668476154,
101
+ "eval_f1": 0.32180851063829785,
102
+ "eval_loss": 0.2702881097793579,
103
+ "eval_mcc": 0.3372551401109897,
104
+ "eval_precision": 0.6612021857923497,
105
+ "eval_recall": 0.2126537785588752,
106
+ "eval_runtime": 10.0143,
107
+ "eval_samples_per_second": 515.061,
108
+ "eval_steps_per_second": 16.177,
109
+ "step": 3225
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 1.2645069360733032,
114
+ "learning_rate": 5.7184487136636185e-05,
115
+ "loss": 0.2641,
116
+ "step": 3870
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.9038386971694455,
121
+ "eval_f1": 0.35078534031413616,
122
+ "eval_loss": 0.26536738872528076,
123
+ "eval_mcc": 0.36499409965660234,
124
+ "eval_precision": 0.6871794871794872,
125
+ "eval_recall": 0.23550087873462214,
126
+ "eval_runtime": 10.0214,
127
+ "eval_samples_per_second": 514.7,
128
+ "eval_steps_per_second": 16.165,
129
+ "step": 3870
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 4515,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 7,
136
+ "save_steps": 500,
137
+ "total_flos": 9521655195600.0,
138
+ "train_batch_size": 32,
139
+ "trial_name": null,
140
+ "trial_params": {
141
+ "alpha": 0.8743805278290786,
142
+ "learning_rate": 0.0004002914099564533,
143
+ "num_train_epochs": 7,
144
+ "temperature": 27
145
+ }
146
+ }
run-20/checkpoint-3870/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbe36ec58db211b259b67da56dd68bab1173e0379eb4df2b16394348319aa391
3
+ size 4984
run-20/checkpoint-3870/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-20/checkpoint-4515/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": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-20/checkpoint-4515/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08f12787699e84b75bbb3fda8a297c483bd788daf02f010479875c9a56e6dfb1
3
+ size 17549312
run-20/checkpoint-4515/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf05ec2906e22c7c9d34e4de9bf7d31b6af97d0a49c96a9aa324a257cddcc022
3
+ size 35123898
run-20/checkpoint-4515/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a96e86d3d3d0591475970004e3cc12c4fa77897439ac6269f6ad54a0b10cb2f
3
+ size 14308
run-20/checkpoint-4515/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb610878d225393f278acf29d8a4712e01ba750413aa9cbf9a7722c481e2a5fe
3
+ size 1064
run-20/checkpoint-4515/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-20/checkpoint-4515/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-20/checkpoint-4515/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-20/checkpoint-4515/trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9038386971694455,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-20/checkpoint-3870",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4515,
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": 1.6259269714355469,
14
+ "learning_rate": 0.0003431069228198171,
15
+ "loss": 0.3055,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8889104303993796,
21
+ "eval_f1": 0.19409282700421943,
22
+ "eval_loss": 0.2940736413002014,
23
+ "eval_mcc": 0.20172457395808635,
24
+ "eval_precision": 0.4859154929577465,
25
+ "eval_recall": 0.12126537785588752,
26
+ "eval_runtime": 9.9362,
27
+ "eval_samples_per_second": 519.111,
28
+ "eval_steps_per_second": 16.304,
29
+ "step": 645
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 0.638690710067749,
34
+ "learning_rate": 0.00028592243568318097,
35
+ "loss": 0.2894,
36
+ "step": 1290
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8964715005816207,
41
+ "eval_f1": 0.18844984802431614,
42
+ "eval_loss": 0.2831971049308777,
43
+ "eval_mcc": 0.24798827118495087,
44
+ "eval_precision": 0.6966292134831461,
45
+ "eval_recall": 0.10896309314586995,
46
+ "eval_runtime": 9.9132,
47
+ "eval_samples_per_second": 520.316,
48
+ "eval_steps_per_second": 16.342,
49
+ "step": 1290
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 0.7561137080192566,
54
+ "learning_rate": 0.00022873794854654474,
55
+ "loss": 0.2795,
56
+ "step": 1935
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.8964715005816207,
61
+ "eval_f1": 0.165625,
62
+ "eval_loss": 0.2780698239803314,
63
+ "eval_mcc": 0.2399021362225046,
64
+ "eval_precision": 0.7464788732394366,
65
+ "eval_recall": 0.09314586994727592,
66
+ "eval_runtime": 10.0176,
67
+ "eval_samples_per_second": 514.893,
68
+ "eval_steps_per_second": 16.172,
69
+ "step": 1935
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.1933393478393555,
74
+ "learning_rate": 0.00017155346140990856,
75
+ "loss": 0.2738,
76
+ "step": 2580
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.8986041101202016,
81
+ "eval_f1": 0.309114927344782,
82
+ "eval_loss": 0.28069812059402466,
83
+ "eval_mcc": 0.3178770819197392,
84
+ "eval_precision": 0.6223404255319149,
85
+ "eval_recall": 0.2056239015817223,
86
+ "eval_runtime": 10.0583,
87
+ "eval_samples_per_second": 512.809,
88
+ "eval_steps_per_second": 16.106,
89
+ "step": 2580
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 0.9380802512168884,
94
+ "learning_rate": 0.00011436897427327237,
95
+ "loss": 0.27,
96
+ "step": 3225
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.9011244668476154,
101
+ "eval_f1": 0.32180851063829785,
102
+ "eval_loss": 0.2702881097793579,
103
+ "eval_mcc": 0.3372551401109897,
104
+ "eval_precision": 0.6612021857923497,
105
+ "eval_recall": 0.2126537785588752,
106
+ "eval_runtime": 10.0143,
107
+ "eval_samples_per_second": 515.061,
108
+ "eval_steps_per_second": 16.177,
109
+ "step": 3225
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 1.2645069360733032,
114
+ "learning_rate": 5.7184487136636185e-05,
115
+ "loss": 0.2641,
116
+ "step": 3870
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.9038386971694455,
121
+ "eval_f1": 0.35078534031413616,
122
+ "eval_loss": 0.26536738872528076,
123
+ "eval_mcc": 0.36499409965660234,
124
+ "eval_precision": 0.6871794871794872,
125
+ "eval_recall": 0.23550087873462214,
126
+ "eval_runtime": 10.0214,
127
+ "eval_samples_per_second": 514.7,
128
+ "eval_steps_per_second": 16.165,
129
+ "step": 3870
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 0.633353054523468,
134
+ "learning_rate": 0.0,
135
+ "loss": 0.2619,
136
+ "step": 4515
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.9026754556029469,
141
+ "eval_f1": 0.335978835978836,
142
+ "eval_loss": 0.2652672529220581,
143
+ "eval_mcc": 0.35216632630481853,
144
+ "eval_precision": 0.679144385026738,
145
+ "eval_recall": 0.22319859402460457,
146
+ "eval_runtime": 9.9714,
147
+ "eval_samples_per_second": 517.279,
148
+ "eval_steps_per_second": 16.246,
149
+ "step": 4515
150
+ }
151
+ ],
152
+ "logging_steps": 500,
153
+ "max_steps": 4515,
154
+ "num_input_tokens_seen": 0,
155
+ "num_train_epochs": 7,
156
+ "save_steps": 500,
157
+ "total_flos": 11108597728200.0,
158
+ "train_batch_size": 32,
159
+ "trial_name": null,
160
+ "trial_params": {
161
+ "alpha": 0.8743805278290786,
162
+ "learning_rate": 0.0004002914099564533,
163
+ "num_train_epochs": 7,
164
+ "temperature": 27
165
+ }
166
+ }
run-20/checkpoint-4515/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbe36ec58db211b259b67da56dd68bab1173e0379eb4df2b16394348319aa391
3
+ size 4984
run-20/checkpoint-4515/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-22/checkpoint-645/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": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-22/checkpoint-645/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d0f6599d392c90e9528fe8546a8df09766fdfc9d1d7a34f944b1777ed6258f7
3
+ size 17549312
run-22/checkpoint-645/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a93bc57f233250629b5e281fe44fc98ca87d42cfc7958d16afdfd5b84e3b0caa
3
+ size 35123898
run-22/checkpoint-645/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f64cda8af0c2d214cf65bdf171fde38f18025a5a08f9a451c61fdf726867d7c2
3
+ size 14308
run-22/checkpoint-645/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c2cc55af8ea300fac7724b9b4c79b334613a45790eb94f0fd66a406c3852aa5
3
+ size 1064
run-22/checkpoint-645/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-22/checkpoint-645/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-22/checkpoint-645/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-22/checkpoint-645/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8945327646374563,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-22/checkpoint-645",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 645,
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": 2.1603200435638428,
14
+ "learning_rate": 0.00015804016249699036,
15
+ "loss": 0.3253,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8945327646374563,
21
+ "eval_f1": 0.19047619047619047,
22
+ "eval_loss": 0.29357558488845825,
23
+ "eval_mcc": 0.23285387927696083,
24
+ "eval_precision": 0.6213592233009708,
25
+ "eval_recall": 0.11247803163444639,
26
+ "eval_runtime": 9.9704,
27
+ "eval_samples_per_second": 517.33,
28
+ "eval_steps_per_second": 16.248,
29
+ "step": 645
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 3225,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 5,
36
+ "save_steps": 500,
37
+ "total_flos": 1586942532600.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.9879592289455201,
42
+ "learning_rate": 0.00019755020312123793,
43
+ "num_train_epochs": 5,
44
+ "temperature": 26
45
+ }
46
+ }
run-22/checkpoint-645/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:463d23df8f476e3af460c3bc4425d71e9123ebed51ff3120d6a6683ba8684432
3
+ size 4984
run-22/checkpoint-645/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:fbe36ec58db211b259b67da56dd68bab1173e0379eb4df2b16394348319aa391
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:463d23df8f476e3af460c3bc4425d71e9123ebed51ff3120d6a6683ba8684432
3
  size 4984