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
9ced70f
·
verified ·
1 Parent(s): 20af06a

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1713587889.1376c752d37a.9760.11 +2 -2
  2. logs/events.out.tfevents.1713588021.1376c752d37a.9760.12 +3 -0
  3. model.safetensors +1 -1
  4. run-11/checkpoint-1284/config.json +34 -0
  5. run-11/checkpoint-1284/model.safetensors +3 -0
  6. run-11/checkpoint-1284/optimizer.pt +3 -0
  7. run-11/checkpoint-1284/rng_state.pth +3 -0
  8. run-11/checkpoint-1284/scheduler.pt +3 -0
  9. run-11/checkpoint-1284/special_tokens_map.json +7 -0
  10. run-11/checkpoint-1284/tokenizer.json +0 -0
  11. run-11/checkpoint-1284/tokenizer_config.json +57 -0
  12. run-11/checkpoint-1284/trainer_state.json +146 -0
  13. run-11/checkpoint-1284/training_args.bin +3 -0
  14. run-11/checkpoint-1284/vocab.txt +0 -0
  15. run-11/checkpoint-1498/config.json +34 -0
  16. run-11/checkpoint-1498/model.safetensors +3 -0
  17. run-11/checkpoint-1498/optimizer.pt +3 -0
  18. run-11/checkpoint-1498/rng_state.pth +3 -0
  19. run-11/checkpoint-1498/scheduler.pt +3 -0
  20. run-11/checkpoint-1498/special_tokens_map.json +7 -0
  21. run-11/checkpoint-1498/tokenizer.json +0 -0
  22. run-11/checkpoint-1498/tokenizer_config.json +57 -0
  23. run-11/checkpoint-1498/trainer_state.json +166 -0
  24. run-11/checkpoint-1498/training_args.bin +3 -0
  25. run-11/checkpoint-1498/vocab.txt +0 -0
  26. run-12/checkpoint-214/config.json +34 -0
  27. run-12/checkpoint-214/model.safetensors +3 -0
  28. run-12/checkpoint-214/optimizer.pt +3 -0
  29. run-12/checkpoint-214/rng_state.pth +3 -0
  30. run-12/checkpoint-214/scheduler.pt +3 -0
  31. run-12/checkpoint-214/special_tokens_map.json +7 -0
  32. run-12/checkpoint-214/tokenizer.json +0 -0
  33. run-12/checkpoint-214/tokenizer_config.json +57 -0
  34. run-12/checkpoint-214/trainer_state.json +46 -0
  35. run-12/checkpoint-214/training_args.bin +3 -0
  36. run-12/checkpoint-214/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1713587889.1376c752d37a.9760.11 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b4f351159d55bb7acdf33bead71c5c36d5be6dabe6f2c70b5eea867de86a1b7
3
- size 6212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c6d48ebae58d6b357be7e2045994c0c4cb1cede2d46a25f3618295c6653430e
3
+ size 10592
logs/events.out.tfevents.1713588021.1376c752d37a.9760.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1509510aa366fae46a160899b5a512e06271badcc2fc48a53ba434e088a3c266
3
+ size 5482
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3b84a61c3ccfff50f3e1e582b590a88411d8954c88388b4974f57c18f97b93e
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2c243a74d5c0149360ec4a2f2cc02adf29f7df79b88595328d7c5f705bded82
3
  size 17549312
run-11/checkpoint-1284/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": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-11/checkpoint-1284/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec10911932d63788b92acdd440e90456186cae2ecf3937b79c12f2a1f45e8ffa
3
+ size 17549312
run-11/checkpoint-1284/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dd525a44cca2a4241bfd23e58da4884701ce44628b5b562f82876270d7edea4
3
+ size 35123898
run-11/checkpoint-1284/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faa74fb48b8739c352726086ee20186281632dbf682ba20839e3522db3e3b091
3
+ size 14308
run-11/checkpoint-1284/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55f20f6cebb930684e2ec77c2c77b94334fb3f70306d6344c69fa6fa2f67ee67
3
+ size 1064
run-11/checkpoint-1284/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-1284/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-11/checkpoint-1284/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-1284/trainer_state.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7557117750439367,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-1284",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1284,
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": 7.572170734405518,
14
+ "learning_rate": 0.00012123385931636098,
15
+ "loss": 0.5934,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7082601054481547,
21
+ "eval_f1": 0.435374149659864,
22
+ "eval_loss": 0.5416340827941895,
23
+ "eval_mcc": 0.28153811271695595,
24
+ "eval_precision": 0.6134185303514377,
25
+ "eval_recall": 0.3374340949033392,
26
+ "eval_runtime": 3.1348,
27
+ "eval_samples_per_second": 544.534,
28
+ "eval_steps_per_second": 17.226,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.894651412963867,
34
+ "learning_rate": 0.00010607962690181587,
35
+ "loss": 0.5286,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7311072056239016,
41
+ "eval_f1": 0.5069817400644469,
42
+ "eval_loss": 0.5141445398330688,
43
+ "eval_mcc": 0.35062725647270626,
44
+ "eval_precision": 0.6519337016574586,
45
+ "eval_recall": 0.4147627416520211,
46
+ "eval_runtime": 3.1601,
47
+ "eval_samples_per_second": 540.173,
48
+ "eval_steps_per_second": 17.088,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.0373611450195312,
54
+ "learning_rate": 9.092539448727073e-05,
55
+ "loss": 0.5038,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7439953134153485,
61
+ "eval_f1": 0.5160575858250277,
62
+ "eval_loss": 0.5071386694908142,
63
+ "eval_mcc": 0.3811266912855395,
64
+ "eval_precision": 0.6976047904191617,
65
+ "eval_recall": 0.4094903339191564,
66
+ "eval_runtime": 3.1399,
67
+ "eval_samples_per_second": 543.644,
68
+ "eval_steps_per_second": 17.198,
69
+ "step": 642
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 4.4339213371276855,
74
+ "learning_rate": 7.577116207272562e-05,
75
+ "loss": 0.4942,
76
+ "step": 856
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7475102519039251,
81
+ "eval_f1": 0.529989094874591,
82
+ "eval_loss": 0.4973749816417694,
83
+ "eval_mcc": 0.39175146343575695,
84
+ "eval_precision": 0.6982758620689655,
85
+ "eval_recall": 0.4270650263620387,
86
+ "eval_runtime": 3.1527,
87
+ "eval_samples_per_second": 541.444,
88
+ "eval_steps_per_second": 17.128,
89
+ "step": 856
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 7.901586532592773,
94
+ "learning_rate": 6.061692965818049e-05,
95
+ "loss": 0.4831,
96
+ "step": 1070
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.7492677211482133,
101
+ "eval_f1": 0.5728542914171657,
102
+ "eval_loss": 0.4928971827030182,
103
+ "eval_mcc": 0.40747419365298854,
104
+ "eval_precision": 0.6628175519630485,
105
+ "eval_recall": 0.5043936731107206,
106
+ "eval_runtime": 3.1384,
107
+ "eval_samples_per_second": 543.907,
108
+ "eval_steps_per_second": 17.206,
109
+ "step": 1070
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 4.602269649505615,
114
+ "learning_rate": 4.5462697243635366e-05,
115
+ "loss": 0.4799,
116
+ "step": 1284
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.7557117750439367,
121
+ "eval_f1": 0.5858987090367429,
122
+ "eval_loss": 0.4908605217933655,
123
+ "eval_mcc": 0.4239597808599074,
124
+ "eval_precision": 0.6735159817351598,
125
+ "eval_recall": 0.5184534270650264,
126
+ "eval_runtime": 3.1381,
127
+ "eval_samples_per_second": 543.957,
128
+ "eval_steps_per_second": 17.208,
129
+ "step": 1284
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 1926,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 9,
136
+ "save_steps": 500,
137
+ "total_flos": 3148653986640.0,
138
+ "train_batch_size": 32,
139
+ "trial_name": null,
140
+ "trial_params": {
141
+ "alpha": 0.9696180923551023,
142
+ "learning_rate": 0.0001363880917309061,
143
+ "num_train_epochs": 9,
144
+ "temperature": 20
145
+ }
146
+ }
run-11/checkpoint-1284/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf09225d27944ca78423d64d6c64a16677c929bc8b03065b895767c7cb1b599b
3
+ size 5048
run-11/checkpoint-1284/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-11/checkpoint-1498/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": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-11/checkpoint-1498/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e444c5324e217ddddd4d6f69ff0f08f37fdfe138f00c818c2243d7553a00a201
3
+ size 17549312
run-11/checkpoint-1498/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:871373e983ffc33b2d18e334d4f638ac97b857e229fac9c3d8c79a9bd99bc47e
3
+ size 35123898
run-11/checkpoint-1498/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec7baa77763623ab6f5c0a3afb24b20f15950a2841a41419e9c31b1269a80a7
3
+ size 14308
run-11/checkpoint-1498/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7deade238fe5594660c87a12d9f536bb35dae59ff1048fe884f28c199f87c908
3
+ size 1064
run-11/checkpoint-1498/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-1498/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-11/checkpoint-1498/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-1498/trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7557117750439367,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-1284",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1498,
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": 7.572170734405518,
14
+ "learning_rate": 0.00012123385931636098,
15
+ "loss": 0.5934,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7082601054481547,
21
+ "eval_f1": 0.435374149659864,
22
+ "eval_loss": 0.5416340827941895,
23
+ "eval_mcc": 0.28153811271695595,
24
+ "eval_precision": 0.6134185303514377,
25
+ "eval_recall": 0.3374340949033392,
26
+ "eval_runtime": 3.1348,
27
+ "eval_samples_per_second": 544.534,
28
+ "eval_steps_per_second": 17.226,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.894651412963867,
34
+ "learning_rate": 0.00010607962690181587,
35
+ "loss": 0.5286,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7311072056239016,
41
+ "eval_f1": 0.5069817400644469,
42
+ "eval_loss": 0.5141445398330688,
43
+ "eval_mcc": 0.35062725647270626,
44
+ "eval_precision": 0.6519337016574586,
45
+ "eval_recall": 0.4147627416520211,
46
+ "eval_runtime": 3.1601,
47
+ "eval_samples_per_second": 540.173,
48
+ "eval_steps_per_second": 17.088,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.0373611450195312,
54
+ "learning_rate": 9.092539448727073e-05,
55
+ "loss": 0.5038,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7439953134153485,
61
+ "eval_f1": 0.5160575858250277,
62
+ "eval_loss": 0.5071386694908142,
63
+ "eval_mcc": 0.3811266912855395,
64
+ "eval_precision": 0.6976047904191617,
65
+ "eval_recall": 0.4094903339191564,
66
+ "eval_runtime": 3.1399,
67
+ "eval_samples_per_second": 543.644,
68
+ "eval_steps_per_second": 17.198,
69
+ "step": 642
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 4.4339213371276855,
74
+ "learning_rate": 7.577116207272562e-05,
75
+ "loss": 0.4942,
76
+ "step": 856
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7475102519039251,
81
+ "eval_f1": 0.529989094874591,
82
+ "eval_loss": 0.4973749816417694,
83
+ "eval_mcc": 0.39175146343575695,
84
+ "eval_precision": 0.6982758620689655,
85
+ "eval_recall": 0.4270650263620387,
86
+ "eval_runtime": 3.1527,
87
+ "eval_samples_per_second": 541.444,
88
+ "eval_steps_per_second": 17.128,
89
+ "step": 856
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 7.901586532592773,
94
+ "learning_rate": 6.061692965818049e-05,
95
+ "loss": 0.4831,
96
+ "step": 1070
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.7492677211482133,
101
+ "eval_f1": 0.5728542914171657,
102
+ "eval_loss": 0.4928971827030182,
103
+ "eval_mcc": 0.40747419365298854,
104
+ "eval_precision": 0.6628175519630485,
105
+ "eval_recall": 0.5043936731107206,
106
+ "eval_runtime": 3.1384,
107
+ "eval_samples_per_second": 543.907,
108
+ "eval_steps_per_second": 17.206,
109
+ "step": 1070
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 4.602269649505615,
114
+ "learning_rate": 4.5462697243635366e-05,
115
+ "loss": 0.4799,
116
+ "step": 1284
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.7557117750439367,
121
+ "eval_f1": 0.5858987090367429,
122
+ "eval_loss": 0.4908605217933655,
123
+ "eval_mcc": 0.4239597808599074,
124
+ "eval_precision": 0.6735159817351598,
125
+ "eval_recall": 0.5184534270650264,
126
+ "eval_runtime": 3.1381,
127
+ "eval_samples_per_second": 543.957,
128
+ "eval_steps_per_second": 17.208,
129
+ "step": 1284
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 6.050445079803467,
134
+ "learning_rate": 3.0308464829090246e-05,
135
+ "loss": 0.4717,
136
+ "step": 1498
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.7545401288810779,
141
+ "eval_f1": 0.5667011375387797,
142
+ "eval_loss": 0.49123701453208923,
143
+ "eval_mcc": 0.41537418240248886,
144
+ "eval_precision": 0.6884422110552764,
145
+ "eval_recall": 0.48154657293497366,
146
+ "eval_runtime": 3.1459,
147
+ "eval_samples_per_second": 542.61,
148
+ "eval_steps_per_second": 17.165,
149
+ "step": 1498
150
+ }
151
+ ],
152
+ "logging_steps": 500,
153
+ "max_steps": 1926,
154
+ "num_input_tokens_seen": 0,
155
+ "num_train_epochs": 9,
156
+ "save_steps": 500,
157
+ "total_flos": 3673429651080.0,
158
+ "train_batch_size": 32,
159
+ "trial_name": null,
160
+ "trial_params": {
161
+ "alpha": 0.9696180923551023,
162
+ "learning_rate": 0.0001363880917309061,
163
+ "num_train_epochs": 9,
164
+ "temperature": 20
165
+ }
166
+ }
run-11/checkpoint-1498/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf09225d27944ca78423d64d6c64a16677c929bc8b03065b895767c7cb1b599b
3
+ size 5048
run-11/checkpoint-1498/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-12/checkpoint-214/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": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-12/checkpoint-214/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2c243a74d5c0149360ec4a2f2cc02adf29f7df79b88595328d7c5f705bded82
3
+ size 17549312
run-12/checkpoint-214/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03b59fce6af9623a72039d403c82e82c7bea6f9e798897eaf88fad826e8b06e6
3
+ size 35123898
run-12/checkpoint-214/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc7e492e6768bc7c3c01ac823da5a8177cf34fc1b175dd727fa3be969661a151
3
+ size 14308
run-12/checkpoint-214/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27b2fd90dd5ab896f3a9799e1526c4f963696c434051b20aeab56abd909573d7
3
+ size 1064
run-12/checkpoint-214/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-12/checkpoint-214/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-12/checkpoint-214/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-12/checkpoint-214/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6666666666666666,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-12/checkpoint-214",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 214,
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": 1.3038450479507446,
14
+ "learning_rate": 8.466711582234029e-05,
15
+ "loss": 0.1784,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.16210851073265076,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 3.1313,
27
+ "eval_samples_per_second": 545.14,
28
+ "eval_steps_per_second": 17.245,
29
+ "step": 214
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 1712,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 8,
36
+ "save_steps": 500,
37
+ "total_flos": 524775664440.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.24525395176272902,
42
+ "learning_rate": 9.676241808267462e-05,
43
+ "num_train_epochs": 8,
44
+ "temperature": 20
45
+ }
46
+ }
run-12/checkpoint-214/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42e93f6e195073c040c166ef71d5874061759e34f11a01eb6df50a9c3093c4ed
3
+ size 5048
run-12/checkpoint-214/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:bf09225d27944ca78423d64d6c64a16677c929bc8b03065b895767c7cb1b599b
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42e93f6e195073c040c166ef71d5874061759e34f11a01eb6df50a9c3093c4ed
3
  size 5048