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
60b7616
·
verified ·
1 Parent(s): 616d568

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1711298809.8cc2eef2edb7.2942.31 +2 -2
  2. logs/events.out.tfevents.1711298948.8cc2eef2edb7.2942.32 +3 -0
  3. model.safetensors +1 -1
  4. run-31/checkpoint-1782/config.json +34 -0
  5. run-31/checkpoint-1782/model.safetensors +3 -0
  6. run-31/checkpoint-1782/optimizer.pt +3 -0
  7. run-31/checkpoint-1782/rng_state.pth +3 -0
  8. run-31/checkpoint-1782/scheduler.pt +3 -0
  9. run-31/checkpoint-1782/special_tokens_map.json +7 -0
  10. run-31/checkpoint-1782/tokenizer.json +0 -0
  11. run-31/checkpoint-1782/tokenizer_config.json +57 -0
  12. run-31/checkpoint-1782/trainer_state.json +146 -0
  13. run-31/checkpoint-1782/training_args.bin +3 -0
  14. run-31/checkpoint-1782/vocab.txt +0 -0
  15. run-31/checkpoint-2079/config.json +34 -0
  16. run-31/checkpoint-2079/model.safetensors +3 -0
  17. run-31/checkpoint-2079/optimizer.pt +3 -0
  18. run-31/checkpoint-2079/rng_state.pth +3 -0
  19. run-31/checkpoint-2079/scheduler.pt +3 -0
  20. run-31/checkpoint-2079/special_tokens_map.json +7 -0
  21. run-31/checkpoint-2079/tokenizer.json +0 -0
  22. run-31/checkpoint-2079/tokenizer_config.json +57 -0
  23. run-31/checkpoint-2079/trainer_state.json +166 -0
  24. run-31/checkpoint-2079/training_args.bin +3 -0
  25. run-31/checkpoint-2079/vocab.txt +0 -0
  26. run-32/checkpoint-297/config.json +34 -0
  27. run-32/checkpoint-297/model.safetensors +3 -0
  28. run-32/checkpoint-297/optimizer.pt +3 -0
  29. run-32/checkpoint-297/rng_state.pth +3 -0
  30. run-32/checkpoint-297/scheduler.pt +3 -0
  31. run-32/checkpoint-297/special_tokens_map.json +7 -0
  32. run-32/checkpoint-297/tokenizer.json +0 -0
  33. run-32/checkpoint-297/tokenizer_config.json +57 -0
  34. run-32/checkpoint-297/trainer_state.json +46 -0
  35. run-32/checkpoint-297/training_args.bin +3 -0
  36. run-32/checkpoint-297/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1711298809.8cc2eef2edb7.2942.31 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac96198a01357f92af47100af2f36a15fef9535dd89da44a39d6c685d3093de9
3
- size 8327
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea3f437daf679086ff09444e759fd6ed60aa54658f6b191314363a0c8c7045dc
3
+ size 10141
logs/events.out.tfevents.1711298948.8cc2eef2edb7.2942.32 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b833876ef384697c84e8bdc83053e0c3c340cd89a23cc770245f1c8a8a8edf2
3
+ size 5406
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29cc9bc8212bbd2dddabfcabad96f67006e7065179d3e66c0ebced9d32615c5a
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69fde95b06053d9298a2983bf29cce7ca963088c56abb9abaf7f79a01f3729ee
3
  size 17549312
run-31/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-31/checkpoint-1782/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6fc89f52dd1b48b029fbe4e9c5809b9451842d42870a9b138574375e1103891
3
+ size 17549312
run-31/checkpoint-1782/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61d14d9d5263566e4ed1322be8ee19763750dd22802106bd85d43286678f1fbc
3
+ size 35123898
run-31/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-31/checkpoint-1782/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57457560817349adf6526b41cb4684e1c2d020c57aef6dc7ae53aa3a14351a93
3
+ size 1064
run-31/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-31/checkpoint-1782/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-31/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-31/checkpoint-1782/trainer_state.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6792079207920793,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-31/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": 1.7863609790802002,
14
+ "learning_rate": 0.00019509013723494322,
15
+ "loss": 0.6459,
16
+ "step": 297
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5504950495049505,
21
+ "eval_f1": 0.3605633802816901,
22
+ "eval_loss": 0.6387978196144104,
23
+ "eval_mcc": 0.12386197513513038,
24
+ "eval_precision": 0.6213592233009708,
25
+ "eval_recall": 0.25396825396825395,
26
+ "eval_runtime": 0.929,
27
+ "eval_samples_per_second": 543.623,
28
+ "eval_steps_per_second": 17.224,
29
+ "step": 297
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.8095519542694092,
34
+ "learning_rate": 0.0001625751143624527,
35
+ "loss": 0.6195,
36
+ "step": 594
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6633663366336634,
41
+ "eval_f1": 0.7007042253521126,
42
+ "eval_loss": 0.5977084636688232,
43
+ "eval_mcc": 0.33809736315331057,
44
+ "eval_precision": 0.629746835443038,
45
+ "eval_recall": 0.7896825396825397,
46
+ "eval_runtime": 0.9344,
47
+ "eval_samples_per_second": 540.431,
48
+ "eval_steps_per_second": 17.123,
49
+ "step": 594
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.1215713024139404,
54
+ "learning_rate": 0.00013006009148996216,
55
+ "loss": 0.5905,
56
+ "step": 891
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.6554455445544555,
61
+ "eval_f1": 0.712871287128713,
62
+ "eval_loss": 0.602749228477478,
63
+ "eval_mcc": 0.34040109061689877,
64
+ "eval_precision": 0.6101694915254238,
65
+ "eval_recall": 0.8571428571428571,
66
+ "eval_runtime": 0.9266,
67
+ "eval_samples_per_second": 545.023,
68
+ "eval_steps_per_second": 17.268,
69
+ "step": 891
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 2.1008222103118896,
74
+ "learning_rate": 9.754506861747161e-05,
75
+ "loss": 0.5654,
76
+ "step": 1188
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6712871287128713,
81
+ "eval_f1": 0.7224080267558528,
82
+ "eval_loss": 0.59177166223526,
83
+ "eval_mcc": 0.36958040539129916,
84
+ "eval_precision": 0.6242774566473989,
85
+ "eval_recall": 0.8571428571428571,
86
+ "eval_runtime": 0.9407,
87
+ "eval_samples_per_second": 536.843,
88
+ "eval_steps_per_second": 17.009,
89
+ "step": 1188
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 3.422161817550659,
94
+ "learning_rate": 6.503004574498108e-05,
95
+ "loss": 0.5459,
96
+ "step": 1485
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.6752475247524753,
101
+ "eval_f1": 0.7018181818181819,
102
+ "eval_loss": 0.5669044852256775,
103
+ "eval_mcc": 0.356691478314268,
104
+ "eval_precision": 0.6476510067114094,
105
+ "eval_recall": 0.7658730158730159,
106
+ "eval_runtime": 0.9343,
107
+ "eval_samples_per_second": 540.495,
108
+ "eval_steps_per_second": 17.125,
109
+ "step": 1485
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 3.3977699279785156,
114
+ "learning_rate": 3.251502287249054e-05,
115
+ "loss": 0.5351,
116
+ "step": 1782
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.6792079207920793,
121
+ "eval_f1": 0.7011070110701108,
122
+ "eval_loss": 0.5643479824066162,
123
+ "eval_mcc": 0.3627332814413178,
124
+ "eval_precision": 0.6551724137931034,
125
+ "eval_recall": 0.753968253968254,
126
+ "eval_runtime": 0.9387,
127
+ "eval_samples_per_second": 537.967,
128
+ "eval_steps_per_second": 17.045,
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": 0.9148462770396972,
142
+ "learning_rate": 0.00022760516010743377,
143
+ "num_train_epochs": 7,
144
+ "temperature": 11
145
+ }
146
+ }
run-31/checkpoint-1782/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8131558b780b77bdf48e590f1c8267970dee97d61ef55d4d3c8bc00b44e025a2
3
+ size 4920
run-31/checkpoint-1782/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-31/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-31/checkpoint-2079/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9503879cf4d9c1c1d48e60755de6aaea459c462423ab2f19d002180918f3d78
3
+ size 17549312
run-31/checkpoint-2079/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:591d693b5a58bf611167e12eca53b5a0aecc65818d6392c37c4bebe974ab4636
3
+ size 35123898
run-31/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-31/checkpoint-2079/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94956d9c7e05bc2e33931b2990eae075824ef33803cc23b2e5602fe785e93769
3
+ size 1064
run-31/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-31/checkpoint-2079/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-31/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-31/checkpoint-2079/trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6792079207920793,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-31/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": 1.7863609790802002,
14
+ "learning_rate": 0.00019509013723494322,
15
+ "loss": 0.6459,
16
+ "step": 297
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5504950495049505,
21
+ "eval_f1": 0.3605633802816901,
22
+ "eval_loss": 0.6387978196144104,
23
+ "eval_mcc": 0.12386197513513038,
24
+ "eval_precision": 0.6213592233009708,
25
+ "eval_recall": 0.25396825396825395,
26
+ "eval_runtime": 0.929,
27
+ "eval_samples_per_second": 543.623,
28
+ "eval_steps_per_second": 17.224,
29
+ "step": 297
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.8095519542694092,
34
+ "learning_rate": 0.0001625751143624527,
35
+ "loss": 0.6195,
36
+ "step": 594
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6633663366336634,
41
+ "eval_f1": 0.7007042253521126,
42
+ "eval_loss": 0.5977084636688232,
43
+ "eval_mcc": 0.33809736315331057,
44
+ "eval_precision": 0.629746835443038,
45
+ "eval_recall": 0.7896825396825397,
46
+ "eval_runtime": 0.9344,
47
+ "eval_samples_per_second": 540.431,
48
+ "eval_steps_per_second": 17.123,
49
+ "step": 594
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.1215713024139404,
54
+ "learning_rate": 0.00013006009148996216,
55
+ "loss": 0.5905,
56
+ "step": 891
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.6554455445544555,
61
+ "eval_f1": 0.712871287128713,
62
+ "eval_loss": 0.602749228477478,
63
+ "eval_mcc": 0.34040109061689877,
64
+ "eval_precision": 0.6101694915254238,
65
+ "eval_recall": 0.8571428571428571,
66
+ "eval_runtime": 0.9266,
67
+ "eval_samples_per_second": 545.023,
68
+ "eval_steps_per_second": 17.268,
69
+ "step": 891
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 2.1008222103118896,
74
+ "learning_rate": 9.754506861747161e-05,
75
+ "loss": 0.5654,
76
+ "step": 1188
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6712871287128713,
81
+ "eval_f1": 0.7224080267558528,
82
+ "eval_loss": 0.59177166223526,
83
+ "eval_mcc": 0.36958040539129916,
84
+ "eval_precision": 0.6242774566473989,
85
+ "eval_recall": 0.8571428571428571,
86
+ "eval_runtime": 0.9407,
87
+ "eval_samples_per_second": 536.843,
88
+ "eval_steps_per_second": 17.009,
89
+ "step": 1188
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 3.422161817550659,
94
+ "learning_rate": 6.503004574498108e-05,
95
+ "loss": 0.5459,
96
+ "step": 1485
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.6752475247524753,
101
+ "eval_f1": 0.7018181818181819,
102
+ "eval_loss": 0.5669044852256775,
103
+ "eval_mcc": 0.356691478314268,
104
+ "eval_precision": 0.6476510067114094,
105
+ "eval_recall": 0.7658730158730159,
106
+ "eval_runtime": 0.9343,
107
+ "eval_samples_per_second": 540.495,
108
+ "eval_steps_per_second": 17.125,
109
+ "step": 1485
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 3.3977699279785156,
114
+ "learning_rate": 3.251502287249054e-05,
115
+ "loss": 0.5351,
116
+ "step": 1782
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.6792079207920793,
121
+ "eval_f1": 0.7011070110701108,
122
+ "eval_loss": 0.5643479824066162,
123
+ "eval_mcc": 0.3627332814413178,
124
+ "eval_precision": 0.6551724137931034,
125
+ "eval_recall": 0.753968253968254,
126
+ "eval_runtime": 0.9387,
127
+ "eval_samples_per_second": 537.967,
128
+ "eval_steps_per_second": 17.045,
129
+ "step": 1782
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 2.3606247901916504,
134
+ "learning_rate": 0.0,
135
+ "loss": 0.5289,
136
+ "step": 2079
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.6772277227722773,
141
+ "eval_f1": 0.6998158379373849,
142
+ "eval_loss": 0.5652695298194885,
143
+ "eval_mcc": 0.35895523179711203,
144
+ "eval_precision": 0.6529209621993127,
145
+ "eval_recall": 0.753968253968254,
146
+ "eval_runtime": 0.9278,
147
+ "eval_samples_per_second": 544.298,
148
+ "eval_steps_per_second": 17.245,
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": 0.9148462770396972,
162
+ "learning_rate": 0.00022760516010743377,
163
+ "num_train_epochs": 7,
164
+ "temperature": 11
165
+ }
166
+ }
run-31/checkpoint-2079/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8131558b780b77bdf48e590f1c8267970dee97d61ef55d4d3c8bc00b44e025a2
3
+ size 4920
run-31/checkpoint-2079/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-32/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-32/checkpoint-297/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69fde95b06053d9298a2983bf29cce7ca963088c56abb9abaf7f79a01f3729ee
3
+ size 17549312
run-32/checkpoint-297/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15eb92c0a9adc1553aa2f7091452647ab843da2dbcca43dbfdc4a43a098d0954
3
+ size 35123898
run-32/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-32/checkpoint-297/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36484c389f19270da291c362a962cc24d687cb60a3947cee5c2714f6e6a05e61
3
+ size 1064
run-32/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-32/checkpoint-297/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-32/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-32/checkpoint-297/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5366336633663367,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-32/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": 2.0489678382873535,
14
+ "learning_rate": 0.00030782109688346106,
15
+ "loss": 0.6591,
16
+ "step": 297
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5366336633663367,
21
+ "eval_f1": 0.20945945945945946,
22
+ "eval_loss": 0.6587525606155396,
23
+ "eval_mcc": 0.12699706368366073,
24
+ "eval_precision": 0.7045454545454546,
25
+ "eval_recall": 0.12301587301587301,
26
+ "eval_runtime": 0.9347,
27
+ "eval_samples_per_second": 540.253,
28
+ "eval_steps_per_second": 17.117,
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": 0.9361124407975862,
42
+ "learning_rate": 0.0003693853162601533,
43
+ "num_train_epochs": 6,
44
+ "temperature": 21
45
+ }
46
+ }
run-32/checkpoint-297/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b8392c48e77ef3e277bb806e38539adfe405c083ee9826264540c767c93e40b
3
+ size 4920
run-32/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 sha256:8131558b780b77bdf48e590f1c8267970dee97d61ef55d4d3c8bc00b44e025a2
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b8392c48e77ef3e277bb806e38539adfe405c083ee9826264540c767c93e40b
3
  size 4920