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
ee392a4
·
verified ·
1 Parent(s): 5c8ae47

Training in progress, epoch 1

Browse files
Files changed (38) hide show
  1. logs/events.out.tfevents.1714704854.e992b94a7c88.3982.12 +2 -2
  2. logs/events.out.tfevents.1714705699.e992b94a7c88.3982.13 +3 -0
  3. logs/events.out.tfevents.1714705821.e992b94a7c88.3982.14 +3 -0
  4. model.safetensors +1 -1
  5. run-12/checkpoint-11116/config.json +34 -0
  6. run-12/checkpoint-11116/model.safetensors +3 -0
  7. run-12/checkpoint-11116/optimizer.pt +3 -0
  8. run-12/checkpoint-11116/rng_state.pth +3 -0
  9. run-12/checkpoint-11116/scheduler.pt +3 -0
  10. run-12/checkpoint-11116/special_tokens_map.json +7 -0
  11. run-12/checkpoint-11116/tokenizer.json +0 -0
  12. run-12/checkpoint-11116/tokenizer_config.json +57 -0
  13. run-12/checkpoint-11116/trainer_state.json +166 -0
  14. run-12/checkpoint-11116/training_args.bin +3 -0
  15. run-12/checkpoint-11116/vocab.txt +0 -0
  16. run-12/checkpoint-9528/config.json +34 -0
  17. run-12/checkpoint-9528/model.safetensors +3 -0
  18. run-12/checkpoint-9528/optimizer.pt +3 -0
  19. run-12/checkpoint-9528/rng_state.pth +3 -0
  20. run-12/checkpoint-9528/scheduler.pt +3 -0
  21. run-12/checkpoint-9528/special_tokens_map.json +7 -0
  22. run-12/checkpoint-9528/tokenizer.json +0 -0
  23. run-12/checkpoint-9528/tokenizer_config.json +57 -0
  24. run-12/checkpoint-9528/trainer_state.json +146 -0
  25. run-12/checkpoint-9528/training_args.bin +3 -0
  26. run-12/checkpoint-9528/vocab.txt +0 -0
  27. run-14/checkpoint-1588/config.json +34 -0
  28. run-14/checkpoint-1588/model.safetensors +3 -0
  29. run-14/checkpoint-1588/optimizer.pt +3 -0
  30. run-14/checkpoint-1588/rng_state.pth +3 -0
  31. run-14/checkpoint-1588/scheduler.pt +3 -0
  32. run-14/checkpoint-1588/special_tokens_map.json +7 -0
  33. run-14/checkpoint-1588/tokenizer.json +0 -0
  34. run-14/checkpoint-1588/tokenizer_config.json +57 -0
  35. run-14/checkpoint-1588/trainer_state.json +46 -0
  36. run-14/checkpoint-1588/training_args.bin +3 -0
  37. run-14/checkpoint-1588/vocab.txt +0 -0
  38. training_args.bin +1 -1
logs/events.out.tfevents.1714704854.e992b94a7c88.3982.12 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:041b5d745fea6844be8c5fb8a59b5deb3043944a46483b9f9dcb5d5d073596e9
3
- size 6212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82ebdf0567ecff001a37a526c3a2743cb105ed748890699b467aab6ee37f392c
3
+ size 10216
logs/events.out.tfevents.1714705699.e992b94a7c88.3982.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8795f795982be0a83b77c328a03ba19c235d40108cf2478a3ec66950c6d30cb9
3
+ size 5483
logs/events.out.tfevents.1714705821.e992b94a7c88.3982.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a13a74a3c2b780889cd5a185d43cdcc72e9b397e80c06cf5b543a8fb0b871fa5
3
+ size 5483
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f87289a7237bfc91c1456da63559491ad4577df7eb4dd3b2472d289804896fc
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26b02848f5adedcfaf634d46eea437ba867686b89b39a70eb1e524ec61665052
3
  size 17549312
run-12/checkpoint-11116/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": "4.40.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-12/checkpoint-11116/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61b37ce33f15489fae9ab907ba8846669fa9754f149bdf7cf5335168051e9a79
3
+ size 17549312
run-12/checkpoint-11116/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab78715711002b1a5c7a7abf453865fbb9790e4f8cf03a29f3701640ac0fe002
3
+ size 35123898
run-12/checkpoint-11116/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7d11e118a9238f88e630a28a28890730884086afd4091d0e118b4e158096b9b
3
+ size 14308
run-12/checkpoint-11116/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f282115ae4486318e507fa9e91d58614b1b90003349fbe758e54ff1ef712da26
3
+ size 1064
run-12/checkpoint-11116/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-11116/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-12/checkpoint-11116/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-11116/trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6925074767826224,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-12/checkpoint-11116",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 11116,
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": 0.9882927536964417,
14
+ "learning_rate": 7.410798334450794e-05,
15
+ "loss": 0.6034,
16
+ "step": 1588
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6725956241145915,
21
+ "eval_f1": 0.37966000596480765,
22
+ "eval_loss": 0.5911920070648193,
23
+ "eval_mcc": 0.1895683346876405,
24
+ "eval_precision": 0.5151760420882234,
25
+ "eval_recall": 0.30059031877213693,
26
+ "eval_runtime": 23.3666,
27
+ "eval_samples_per_second": 543.767,
28
+ "eval_steps_per_second": 17.033,
29
+ "step": 1588
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.495981216430664,
34
+ "learning_rate": 6.175665278708995e-05,
35
+ "loss": 0.5856,
36
+ "step": 3176
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6833779316858177,
41
+ "eval_f1": 0.22768285659435594,
42
+ "eval_loss": 0.5804989337921143,
43
+ "eval_mcc": 0.1684089921769426,
44
+ "eval_precision": 0.608829568788501,
45
+ "eval_recall": 0.14002361275088548,
46
+ "eval_runtime": 23.4973,
47
+ "eval_samples_per_second": 540.742,
48
+ "eval_steps_per_second": 16.938,
49
+ "step": 3176
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.520817756652832,
54
+ "learning_rate": 4.940532222967196e-05,
55
+ "loss": 0.5777,
56
+ "step": 4764
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.6877852982842751,
61
+ "eval_f1": 0.3104467234486355,
62
+ "eval_loss": 0.5734280943870544,
63
+ "eval_mcc": 0.19923165442419385,
64
+ "eval_precision": 0.5882740447957839,
65
+ "eval_recall": 0.21086186540731996,
66
+ "eval_runtime": 23.309,
67
+ "eval_samples_per_second": 545.111,
68
+ "eval_steps_per_second": 17.075,
69
+ "step": 4764
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 2.345150947570801,
74
+ "learning_rate": 3.705399167225397e-05,
75
+ "loss": 0.569,
76
+ "step": 6352
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6864473477097435,
81
+ "eval_f1": 0.38575393154486587,
82
+ "eval_loss": 0.5657527446746826,
83
+ "eval_mcc": 0.21896007670125264,
84
+ "eval_precision": 0.555752998667259,
85
+ "eval_recall": 0.29539551357733174,
86
+ "eval_runtime": 23.5253,
87
+ "eval_samples_per_second": 540.099,
88
+ "eval_steps_per_second": 16.918,
89
+ "step": 6352
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 2.713883876800537,
94
+ "learning_rate": 2.470266111483598e-05,
95
+ "loss": 0.5648,
96
+ "step": 7940
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.6918778529828428,
101
+ "eval_f1": 0.3187750130502871,
102
+ "eval_loss": 0.5613014101982117,
103
+ "eval_mcc": 0.2124639653359162,
104
+ "eval_precision": 0.6058201058201058,
105
+ "eval_recall": 0.21629279811097993,
106
+ "eval_runtime": 23.3312,
107
+ "eval_samples_per_second": 544.592,
108
+ "eval_steps_per_second": 17.059,
109
+ "step": 7940
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 2.391467809677124,
114
+ "learning_rate": 1.235133055741799e-05,
115
+ "loss": 0.5606,
116
+ "step": 9528
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.6891232488588068,
121
+ "eval_f1": 0.4268717353453279,
122
+ "eval_loss": 0.5606938004493713,
123
+ "eval_mcc": 0.24033253885885295,
124
+ "eval_precision": 0.5536319156943922,
125
+ "eval_recall": 0.3473435655253837,
126
+ "eval_runtime": 23.3051,
127
+ "eval_samples_per_second": 545.204,
128
+ "eval_steps_per_second": 17.078,
129
+ "step": 9528
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 2.2255425453186035,
134
+ "learning_rate": 0.0,
135
+ "loss": 0.558,
136
+ "step": 11116
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.6925074767826224,
141
+ "eval_f1": 0.39473276529821844,
142
+ "eval_loss": 0.5578871369361877,
143
+ "eval_mcc": 0.23481293082897708,
144
+ "eval_precision": 0.5738738738738739,
145
+ "eval_recall": 0.30082644628099175,
146
+ "eval_runtime": 23.5018,
147
+ "eval_samples_per_second": 540.639,
148
+ "eval_steps_per_second": 16.935,
149
+ "step": 11116
150
+ }
151
+ ],
152
+ "logging_steps": 500,
153
+ "max_steps": 11116,
154
+ "num_input_tokens_seen": 0,
155
+ "num_train_epochs": 7,
156
+ "save_steps": 500,
157
+ "total_flos": 27362258534100.0,
158
+ "train_batch_size": 32,
159
+ "trial_name": null,
160
+ "trial_params": {
161
+ "alpha": 0.971233252957219,
162
+ "learning_rate": 8.645931390192593e-05,
163
+ "num_train_epochs": 7,
164
+ "temperature": 16
165
+ }
166
+ }
run-12/checkpoint-11116/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee1795c6c064e30b93b61f7db5815153fa9a2685024f5a88af44cf5291be307
3
+ size 4984
run-12/checkpoint-11116/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-12/checkpoint-9528/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": "4.40.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-12/checkpoint-9528/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36a8623f5c2503144f5312aba6a526b81cb34e8bb697cf5828084979aa14e90e
3
+ size 17549312
run-12/checkpoint-9528/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c90aab09f5469c085ce64f43cbaefd713065cf34a93934bb638d31b4e68534c3
3
+ size 35123898
run-12/checkpoint-9528/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e33d2e8b149bac8cac32da7101c4c42cadaa056452d54f4838ec1fec07908607
3
+ size 14308
run-12/checkpoint-9528/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9d668f33fecfd6f5017bc3062ceffb8528bf989543a536482087be48baf214d
3
+ size 1064
run-12/checkpoint-9528/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-9528/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-12/checkpoint-9528/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-9528/trainer_state.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6918778529828428,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-12/checkpoint-7940",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 9528,
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": 0.9882927536964417,
14
+ "learning_rate": 7.410798334450794e-05,
15
+ "loss": 0.6034,
16
+ "step": 1588
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6725956241145915,
21
+ "eval_f1": 0.37966000596480765,
22
+ "eval_loss": 0.5911920070648193,
23
+ "eval_mcc": 0.1895683346876405,
24
+ "eval_precision": 0.5151760420882234,
25
+ "eval_recall": 0.30059031877213693,
26
+ "eval_runtime": 23.3666,
27
+ "eval_samples_per_second": 543.767,
28
+ "eval_steps_per_second": 17.033,
29
+ "step": 1588
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.495981216430664,
34
+ "learning_rate": 6.175665278708995e-05,
35
+ "loss": 0.5856,
36
+ "step": 3176
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6833779316858177,
41
+ "eval_f1": 0.22768285659435594,
42
+ "eval_loss": 0.5804989337921143,
43
+ "eval_mcc": 0.1684089921769426,
44
+ "eval_precision": 0.608829568788501,
45
+ "eval_recall": 0.14002361275088548,
46
+ "eval_runtime": 23.4973,
47
+ "eval_samples_per_second": 540.742,
48
+ "eval_steps_per_second": 16.938,
49
+ "step": 3176
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.520817756652832,
54
+ "learning_rate": 4.940532222967196e-05,
55
+ "loss": 0.5777,
56
+ "step": 4764
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.6877852982842751,
61
+ "eval_f1": 0.3104467234486355,
62
+ "eval_loss": 0.5734280943870544,
63
+ "eval_mcc": 0.19923165442419385,
64
+ "eval_precision": 0.5882740447957839,
65
+ "eval_recall": 0.21086186540731996,
66
+ "eval_runtime": 23.309,
67
+ "eval_samples_per_second": 545.111,
68
+ "eval_steps_per_second": 17.075,
69
+ "step": 4764
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 2.345150947570801,
74
+ "learning_rate": 3.705399167225397e-05,
75
+ "loss": 0.569,
76
+ "step": 6352
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6864473477097435,
81
+ "eval_f1": 0.38575393154486587,
82
+ "eval_loss": 0.5657527446746826,
83
+ "eval_mcc": 0.21896007670125264,
84
+ "eval_precision": 0.555752998667259,
85
+ "eval_recall": 0.29539551357733174,
86
+ "eval_runtime": 23.5253,
87
+ "eval_samples_per_second": 540.099,
88
+ "eval_steps_per_second": 16.918,
89
+ "step": 6352
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 2.713883876800537,
94
+ "learning_rate": 2.470266111483598e-05,
95
+ "loss": 0.5648,
96
+ "step": 7940
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.6918778529828428,
101
+ "eval_f1": 0.3187750130502871,
102
+ "eval_loss": 0.5613014101982117,
103
+ "eval_mcc": 0.2124639653359162,
104
+ "eval_precision": 0.6058201058201058,
105
+ "eval_recall": 0.21629279811097993,
106
+ "eval_runtime": 23.3312,
107
+ "eval_samples_per_second": 544.592,
108
+ "eval_steps_per_second": 17.059,
109
+ "step": 7940
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 2.391467809677124,
114
+ "learning_rate": 1.235133055741799e-05,
115
+ "loss": 0.5606,
116
+ "step": 9528
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.6891232488588068,
121
+ "eval_f1": 0.4268717353453279,
122
+ "eval_loss": 0.5606938004493713,
123
+ "eval_mcc": 0.24033253885885295,
124
+ "eval_precision": 0.5536319156943922,
125
+ "eval_recall": 0.3473435655253837,
126
+ "eval_runtime": 23.3051,
127
+ "eval_samples_per_second": 545.204,
128
+ "eval_steps_per_second": 17.078,
129
+ "step": 9528
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 11116,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 7,
136
+ "save_steps": 500,
137
+ "total_flos": 23453364457800.0,
138
+ "train_batch_size": 32,
139
+ "trial_name": null,
140
+ "trial_params": {
141
+ "alpha": 0.971233252957219,
142
+ "learning_rate": 8.645931390192593e-05,
143
+ "num_train_epochs": 7,
144
+ "temperature": 16
145
+ }
146
+ }
run-12/checkpoint-9528/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee1795c6c064e30b93b61f7db5815153fa9a2685024f5a88af44cf5291be307
3
+ size 4984
run-12/checkpoint-9528/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-1588/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": "4.40.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-14/checkpoint-1588/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26b02848f5adedcfaf634d46eea437ba867686b89b39a70eb1e524ec61665052
3
+ size 17549312
run-14/checkpoint-1588/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58319300b16cb92d7ff18aa7259e1167552f4fe930da1d3d1b810867a3fe3418
3
+ size 35123898
run-14/checkpoint-1588/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:937f4e47675de5e7170e218630c85dd36f459549fb8994b62c13ea83fc7a261c
3
+ size 14308
run-14/checkpoint-1588/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b7a8985fe2e0aef5578fd3c091209b25a41cb8dd0316ec0ecb475a1b286546f
3
+ size 1064
run-14/checkpoint-1588/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-14/checkpoint-1588/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-1588/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-14/checkpoint-1588/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6728317330395089,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-1588",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1588,
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": 1.0097990036010742,
14
+ "learning_rate": 0.00014225432321746245,
15
+ "loss": 0.6009,
16
+ "step": 1588
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6728317330395089,
21
+ "eval_f1": 0.4162336750456397,
22
+ "eval_loss": 0.5847160816192627,
23
+ "eval_mcc": 0.20724185361309674,
24
+ "eval_precision": 0.5135135135135135,
25
+ "eval_recall": 0.3499409681227863,
26
+ "eval_runtime": 23.7837,
27
+ "eval_samples_per_second": 534.232,
28
+ "eval_steps_per_second": 16.734,
29
+ "step": 1588
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 11116,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 7,
36
+ "save_steps": 500,
37
+ "total_flos": 3908894076300.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.9737159843938835,
42
+ "learning_rate": 0.00016596337708703953,
43
+ "num_train_epochs": 7,
44
+ "temperature": 10
45
+ }
46
+ }
run-14/checkpoint-1588/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19165ff4e84f2f2a45207bd5833120ec4416946a98fdd3c0fde9e7a5315b9e2a
3
+ size 4984
run-14/checkpoint-1588/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 sha256:8ee1795c6c064e30b93b61f7db5815153fa9a2685024f5a88af44cf5291be307
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19165ff4e84f2f2a45207bd5833120ec4416946a98fdd3c0fde9e7a5315b9e2a
3
  size 4984