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
88c187f
·
verified ·
1 Parent(s): a9b7c7c

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1711297090.8cc2eef2edb7.2942.4 +2 -2
  2. logs/events.out.tfevents.1711297226.8cc2eef2edb7.2942.5 +3 -0
  3. model.safetensors +1 -1
  4. run-4/checkpoint-1782/config.json +34 -0
  5. run-4/checkpoint-1782/model.safetensors +3 -0
  6. run-4/checkpoint-1782/optimizer.pt +3 -0
  7. run-4/checkpoint-1782/rng_state.pth +3 -0
  8. run-4/checkpoint-1782/scheduler.pt +3 -0
  9. run-4/checkpoint-1782/special_tokens_map.json +7 -0
  10. run-4/checkpoint-1782/tokenizer.json +0 -0
  11. run-4/checkpoint-1782/tokenizer_config.json +57 -0
  12. run-4/checkpoint-1782/trainer_state.json +146 -0
  13. run-4/checkpoint-1782/training_args.bin +3 -0
  14. run-4/checkpoint-1782/vocab.txt +0 -0
  15. run-4/checkpoint-2079/config.json +34 -0
  16. run-4/checkpoint-2079/model.safetensors +3 -0
  17. run-4/checkpoint-2079/optimizer.pt +3 -0
  18. run-4/checkpoint-2079/rng_state.pth +3 -0
  19. run-4/checkpoint-2079/scheduler.pt +3 -0
  20. run-4/checkpoint-2079/special_tokens_map.json +7 -0
  21. run-4/checkpoint-2079/tokenizer.json +0 -0
  22. run-4/checkpoint-2079/tokenizer_config.json +57 -0
  23. run-4/checkpoint-2079/trainer_state.json +166 -0
  24. run-4/checkpoint-2079/training_args.bin +3 -0
  25. run-4/checkpoint-2079/vocab.txt +0 -0
  26. run-5/checkpoint-297/config.json +34 -0
  27. run-5/checkpoint-297/model.safetensors +3 -0
  28. run-5/checkpoint-297/optimizer.pt +3 -0
  29. run-5/checkpoint-297/rng_state.pth +3 -0
  30. run-5/checkpoint-297/scheduler.pt +3 -0
  31. run-5/checkpoint-297/special_tokens_map.json +7 -0
  32. run-5/checkpoint-297/tokenizer.json +0 -0
  33. run-5/checkpoint-297/tokenizer_config.json +57 -0
  34. run-5/checkpoint-297/trainer_state.json +46 -0
  35. run-5/checkpoint-297/training_args.bin +3 -0
  36. run-5/checkpoint-297/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1711297090.8cc2eef2edb7.2942.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:890180357e2c6c1e9c781ffc2dd5737c5625af93c3736ae37f5f754885bf507d
3
- size 6136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac848390792449e1bc06a66d4f34e331b7993de9eede99cb4fd90c2a50ef8de4
3
+ size 10140
logs/events.out.tfevents.1711297226.8cc2eef2edb7.2942.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a70dd7b2a7e623580a9490e8c10312a01265c6b9b108a9763e362a13bacb03eb
3
+ size 5407
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1373d9a02412908ee3ce5bab868f7cbec3faa136e3d1694a1fe4ce56b314f5d
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59d1134edb6ec2dc170e44f0970881ff4d70535fae465a230f156035d9136f6e
3
  size 17549312
run-4/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-4/checkpoint-1782/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:985bb0bc1191284be92727058bbe6e5ff815fe51b68cf6a0acd4f553a8c5942e
3
+ size 17549312
run-4/checkpoint-1782/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:974ac65d54c8e66b6e7e7ebae0da2ae238da0510449aca5a914aaab0ef6b6d73
3
+ size 35123898
run-4/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-4/checkpoint-1782/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a2b6132a9af8120f58f2ece7426666e2a85a43418d749e7fbb2f50dc1ce7416
3
+ size 1064
run-4/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-4/checkpoint-1782/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-1782/trainer_state.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6237623762376238,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/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": 1.202705979347229,
14
+ "learning_rate": 6.504485936113838e-05,
15
+ "loss": 0.5495,
16
+ "step": 297
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5069306930693069,
21
+ "eval_f1": 0.10108303249097472,
22
+ "eval_loss": 0.5468167662620544,
23
+ "eval_mcc": 0.027838098756040194,
24
+ "eval_precision": 0.56,
25
+ "eval_recall": 0.05555555555555555,
26
+ "eval_runtime": 0.9316,
27
+ "eval_samples_per_second": 542.063,
28
+ "eval_steps_per_second": 17.174,
29
+ "step": 297
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 0.8953370451927185,
34
+ "learning_rate": 5.4204049467615325e-05,
35
+ "loss": 0.54,
36
+ "step": 594
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.594059405940594,
41
+ "eval_f1": 0.5858585858585857,
42
+ "eval_loss": 0.5394836068153381,
43
+ "eval_mcc": 0.18817791261380143,
44
+ "eval_precision": 0.5967078189300411,
45
+ "eval_recall": 0.5753968253968254,
46
+ "eval_runtime": 0.9335,
47
+ "eval_samples_per_second": 540.967,
48
+ "eval_steps_per_second": 17.14,
49
+ "step": 594
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.554856777191162,
54
+ "learning_rate": 4.336323957409226e-05,
55
+ "loss": 0.5316,
56
+ "step": 891
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.5861386138613861,
61
+ "eval_f1": 0.6365217391304347,
62
+ "eval_loss": 0.5389003157615662,
63
+ "eval_mcc": 0.17998847484487682,
64
+ "eval_precision": 0.56656346749226,
65
+ "eval_recall": 0.7261904761904762,
66
+ "eval_runtime": 0.9343,
67
+ "eval_samples_per_second": 540.483,
68
+ "eval_steps_per_second": 17.124,
69
+ "step": 891
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.0591225624084473,
74
+ "learning_rate": 3.252242968056919e-05,
75
+ "loss": 0.527,
76
+ "step": 1188
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6118811881188119,
81
+ "eval_f1": 0.6287878787878789,
82
+ "eval_loss": 0.5312101244926453,
83
+ "eval_mcc": 0.22492336097439145,
84
+ "eval_precision": 0.6014492753623188,
85
+ "eval_recall": 0.6587301587301587,
86
+ "eval_runtime": 0.9347,
87
+ "eval_samples_per_second": 540.304,
88
+ "eval_steps_per_second": 17.119,
89
+ "step": 1188
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 1.7271960973739624,
94
+ "learning_rate": 2.168161978704613e-05,
95
+ "loss": 0.5226,
96
+ "step": 1485
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.6138613861386139,
101
+ "eval_f1": 0.6183953033268101,
102
+ "eval_loss": 0.5254874229431152,
103
+ "eval_mcc": 0.22784970249121222,
104
+ "eval_precision": 0.61003861003861,
105
+ "eval_recall": 0.626984126984127,
106
+ "eval_runtime": 0.9248,
107
+ "eval_samples_per_second": 546.078,
108
+ "eval_steps_per_second": 17.301,
109
+ "step": 1485
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 1.6252127885818481,
114
+ "learning_rate": 1.0840809893523065e-05,
115
+ "loss": 0.5188,
116
+ "step": 1782
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.6237623762376238,
121
+ "eval_f1": 0.6468401486988847,
122
+ "eval_loss": 0.5257902145385742,
123
+ "eval_mcc": 0.24999798285978939,
124
+ "eval_precision": 0.6083916083916084,
125
+ "eval_recall": 0.6904761904761905,
126
+ "eval_runtime": 0.9286,
127
+ "eval_samples_per_second": 543.832,
128
+ "eval_steps_per_second": 17.23,
129
+ "step": 1782
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 2079,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 7,
136
+ "save_steps": 500,
137
+ "total_flos": 4384207595880.0,
138
+ "train_batch_size": 32,
139
+ "trial_name": null,
140
+ "trial_params": {
141
+ "alpha": 0.7404813991868276,
142
+ "learning_rate": 7.588566925466145e-05,
143
+ "num_train_epochs": 7,
144
+ "temperature": 47
145
+ }
146
+ }
run-4/checkpoint-1782/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b89f4b12e9eb0ed1644da45c1653800b9447c89374868af92258b08fc1b6045
3
+ size 4920
run-4/checkpoint-1782/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-2079/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-4/checkpoint-2079/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fcd3cb08850cbaf42bbdebef3456ee2dad3821c8096b1bde985e0c779423fd2
3
+ size 17549312
run-4/checkpoint-2079/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20e69c68865506576db96a3de930a904da5ae216bbc5b9991b8d9e465b593680
3
+ size 35123898
run-4/checkpoint-2079/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cb1e97db59d008285d4798ce62e5afec1cdcb1f6d8dc6abd815daafb111f5ec
3
+ size 14308
run-4/checkpoint-2079/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee88a6430de282d012a526349a4feb03f1226d45bd5e5f59a50eb41dbd5c9be5
3
+ size 1064
run-4/checkpoint-2079/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-2079/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-2079/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-4/checkpoint-2079/trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6237623762376238,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-1782",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2079,
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": 1.202705979347229,
14
+ "learning_rate": 6.504485936113838e-05,
15
+ "loss": 0.5495,
16
+ "step": 297
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5069306930693069,
21
+ "eval_f1": 0.10108303249097472,
22
+ "eval_loss": 0.5468167662620544,
23
+ "eval_mcc": 0.027838098756040194,
24
+ "eval_precision": 0.56,
25
+ "eval_recall": 0.05555555555555555,
26
+ "eval_runtime": 0.9316,
27
+ "eval_samples_per_second": 542.063,
28
+ "eval_steps_per_second": 17.174,
29
+ "step": 297
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 0.8953370451927185,
34
+ "learning_rate": 5.4204049467615325e-05,
35
+ "loss": 0.54,
36
+ "step": 594
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.594059405940594,
41
+ "eval_f1": 0.5858585858585857,
42
+ "eval_loss": 0.5394836068153381,
43
+ "eval_mcc": 0.18817791261380143,
44
+ "eval_precision": 0.5967078189300411,
45
+ "eval_recall": 0.5753968253968254,
46
+ "eval_runtime": 0.9335,
47
+ "eval_samples_per_second": 540.967,
48
+ "eval_steps_per_second": 17.14,
49
+ "step": 594
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.554856777191162,
54
+ "learning_rate": 4.336323957409226e-05,
55
+ "loss": 0.5316,
56
+ "step": 891
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.5861386138613861,
61
+ "eval_f1": 0.6365217391304347,
62
+ "eval_loss": 0.5389003157615662,
63
+ "eval_mcc": 0.17998847484487682,
64
+ "eval_precision": 0.56656346749226,
65
+ "eval_recall": 0.7261904761904762,
66
+ "eval_runtime": 0.9343,
67
+ "eval_samples_per_second": 540.483,
68
+ "eval_steps_per_second": 17.124,
69
+ "step": 891
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.0591225624084473,
74
+ "learning_rate": 3.252242968056919e-05,
75
+ "loss": 0.527,
76
+ "step": 1188
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6118811881188119,
81
+ "eval_f1": 0.6287878787878789,
82
+ "eval_loss": 0.5312101244926453,
83
+ "eval_mcc": 0.22492336097439145,
84
+ "eval_precision": 0.6014492753623188,
85
+ "eval_recall": 0.6587301587301587,
86
+ "eval_runtime": 0.9347,
87
+ "eval_samples_per_second": 540.304,
88
+ "eval_steps_per_second": 17.119,
89
+ "step": 1188
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 1.7271960973739624,
94
+ "learning_rate": 2.168161978704613e-05,
95
+ "loss": 0.5226,
96
+ "step": 1485
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.6138613861386139,
101
+ "eval_f1": 0.6183953033268101,
102
+ "eval_loss": 0.5254874229431152,
103
+ "eval_mcc": 0.22784970249121222,
104
+ "eval_precision": 0.61003861003861,
105
+ "eval_recall": 0.626984126984127,
106
+ "eval_runtime": 0.9248,
107
+ "eval_samples_per_second": 546.078,
108
+ "eval_steps_per_second": 17.301,
109
+ "step": 1485
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 1.6252127885818481,
114
+ "learning_rate": 1.0840809893523065e-05,
115
+ "loss": 0.5188,
116
+ "step": 1782
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.6237623762376238,
121
+ "eval_f1": 0.6468401486988847,
122
+ "eval_loss": 0.5257902145385742,
123
+ "eval_mcc": 0.24999798285978939,
124
+ "eval_precision": 0.6083916083916084,
125
+ "eval_recall": 0.6904761904761905,
126
+ "eval_runtime": 0.9286,
127
+ "eval_samples_per_second": 543.832,
128
+ "eval_steps_per_second": 17.23,
129
+ "step": 1782
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 1.1970489025115967,
134
+ "learning_rate": 0.0,
135
+ "loss": 0.5139,
136
+ "step": 2079
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.6237623762376238,
141
+ "eval_f1": 0.62,
142
+ "eval_loss": 0.5197257399559021,
143
+ "eval_mcc": 0.24752925978340254,
144
+ "eval_precision": 0.625,
145
+ "eval_recall": 0.6150793650793651,
146
+ "eval_runtime": 0.934,
147
+ "eval_samples_per_second": 540.665,
148
+ "eval_steps_per_second": 17.13,
149
+ "step": 2079
150
+ }
151
+ ],
152
+ "logging_steps": 500,
153
+ "max_steps": 2079,
154
+ "num_input_tokens_seen": 0,
155
+ "num_train_epochs": 7,
156
+ "save_steps": 500,
157
+ "total_flos": 5114908861860.0,
158
+ "train_batch_size": 32,
159
+ "trial_name": null,
160
+ "trial_params": {
161
+ "alpha": 0.7404813991868276,
162
+ "learning_rate": 7.588566925466145e-05,
163
+ "num_train_epochs": 7,
164
+ "temperature": 47
165
+ }
166
+ }
run-4/checkpoint-2079/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b89f4b12e9eb0ed1644da45c1653800b9447c89374868af92258b08fc1b6045
3
+ size 4920
run-4/checkpoint-2079/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/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-5/checkpoint-297/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59d1134edb6ec2dc170e44f0970881ff4d70535fae465a230f156035d9136f6e
3
+ size 17549312
run-5/checkpoint-297/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3438f0529a8ee27210596a59759c3ef5ef8be94249386c56c0616c8c7f3965
3
+ size 35123898
run-5/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-5/checkpoint-297/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d72bc992d041fc66fc0a17113111f0de95b19021ae644fc58665b69d32cfbc47
3
+ size 1064
run-5/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-5/checkpoint-297/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/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-5/checkpoint-297/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5089108910891089,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-5/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": 0.14799009263515472,
14
+ "learning_rate": 3.564708186391241e-05,
15
+ "loss": 0.0771,
16
+ "step": 297
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5089108910891089,
21
+ "eval_f1": 0.1205673758865248,
22
+ "eval_loss": 0.058570001274347305,
23
+ "eval_mcc": 0.03400602754322123,
24
+ "eval_precision": 0.5666666666666667,
25
+ "eval_recall": 0.06746031746031746,
26
+ "eval_runtime": 0.9363,
27
+ "eval_samples_per_second": 539.332,
28
+ "eval_steps_per_second": 17.088,
29
+ "step": 297
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 891,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 3,
36
+ "save_steps": 500,
37
+ "total_flos": 730701265980.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.06013810150880572,
42
+ "learning_rate": 5.3470622795868616e-05,
43
+ "num_train_epochs": 3,
44
+ "temperature": 28
45
+ }
46
+ }
run-5/checkpoint-297/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acf48c3cfa4dae7e52899a817b599fd5585b4790698eef8cedca0db0b44fb0a8
3
+ size 4920
run-5/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 sha256:0b89f4b12e9eb0ed1644da45c1653800b9447c89374868af92258b08fc1b6045
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acf48c3cfa4dae7e52899a817b599fd5585b4790698eef8cedca0db0b44fb0a8
3
  size 4920