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
fb5a5a9
·
verified ·
1 Parent(s): b74a6d3

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1713587081.1376c752d37a.9760.2 +2 -2
  2. logs/events.out.tfevents.1713587230.1376c752d37a.9760.3 +3 -0
  3. model.safetensors +1 -1
  4. run-2/checkpoint-1712/config.json +34 -0
  5. run-2/checkpoint-1712/model.safetensors +3 -0
  6. run-2/checkpoint-1712/optimizer.pt +3 -0
  7. run-2/checkpoint-1712/rng_state.pth +3 -0
  8. run-2/checkpoint-1712/scheduler.pt +3 -0
  9. run-2/checkpoint-1712/special_tokens_map.json +7 -0
  10. run-2/checkpoint-1712/tokenizer.json +0 -0
  11. run-2/checkpoint-1712/tokenizer_config.json +57 -0
  12. run-2/checkpoint-1712/trainer_state.json +186 -0
  13. run-2/checkpoint-1712/training_args.bin +3 -0
  14. run-2/checkpoint-1712/vocab.txt +0 -0
  15. run-2/checkpoint-1926/config.json +34 -0
  16. run-2/checkpoint-1926/model.safetensors +3 -0
  17. run-2/checkpoint-1926/optimizer.pt +3 -0
  18. run-2/checkpoint-1926/rng_state.pth +3 -0
  19. run-2/checkpoint-1926/scheduler.pt +3 -0
  20. run-2/checkpoint-1926/special_tokens_map.json +7 -0
  21. run-2/checkpoint-1926/tokenizer.json +0 -0
  22. run-2/checkpoint-1926/tokenizer_config.json +57 -0
  23. run-2/checkpoint-1926/trainer_state.json +206 -0
  24. run-2/checkpoint-1926/training_args.bin +3 -0
  25. run-2/checkpoint-1926/vocab.txt +0 -0
  26. run-3/checkpoint-214/config.json +34 -0
  27. run-3/checkpoint-214/model.safetensors +3 -0
  28. run-3/checkpoint-214/optimizer.pt +3 -0
  29. run-3/checkpoint-214/rng_state.pth +3 -0
  30. run-3/checkpoint-214/scheduler.pt +3 -0
  31. run-3/checkpoint-214/special_tokens_map.json +7 -0
  32. run-3/checkpoint-214/tokenizer.json +0 -0
  33. run-3/checkpoint-214/tokenizer_config.json +57 -0
  34. run-3/checkpoint-214/trainer_state.json +46 -0
  35. run-3/checkpoint-214/training_args.bin +3 -0
  36. run-3/checkpoint-214/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1713587081.1376c752d37a.9760.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:297f50f3641cdfba62fbd62fb3c236632efc18ff2bddf9ff5d73fcefa5fea6de
3
- size 6213
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5959591f547234858b38b4e6fbc4a54a3a1bf5a1f01dc21c5ff21817706d7dc1
3
+ size 11677
logs/events.out.tfevents.1713587230.1376c752d37a.9760.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd3ebce26bdd448595d289cb3abda535b64abcde29d4199a79d74996a83041a0
3
+ size 5483
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59ddfe72b81e4efbf566f050cc5593e0bfc1ad802887aa06c88ff89265121f54
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06a4d6bc70e2d5e8a2a3750ec5030e64a4a1396309fd7cd2c1e4cdda62b2f0e8
3
  size 17549312
run-2/checkpoint-1712/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-2/checkpoint-1712/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df9affa7e75fa6bff7478f2ac3b6061f4a10cca41271ce8a4831ece1de77d092
3
+ size 17549312
run-2/checkpoint-1712/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:016bb1c392fb6874823a334ec1040dc286b089bb20726bf4a2f962e439ff046d
3
+ size 35123898
run-2/checkpoint-1712/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4989482a5a75709b5c8ca6795f7ae67e4569d30e28e8e6fcdef7d2324018c9b4
3
+ size 14308
run-2/checkpoint-1712/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb256b7ac83d4ee0b5e6cd89069cc6de0665497ba1f70e614d4fd7318af7b647
3
+ size 1064
run-2/checkpoint-1712/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-2/checkpoint-1712/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-1712/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-2/checkpoint-1712/trainer_state.json ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7685998828353837,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-1070",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1712,
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": 4.634866237640381,
14
+ "learning_rate": 0.00022230485769079655,
15
+ "loss": 0.4904,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7223198594024605,
21
+ "eval_f1": 0.4261501210653753,
22
+ "eval_loss": 0.456611692905426,
23
+ "eval_mcc": 0.31390897314151045,
24
+ "eval_precision": 0.6848249027237354,
25
+ "eval_recall": 0.3093145869947276,
26
+ "eval_runtime": 3.1485,
27
+ "eval_samples_per_second": 542.168,
28
+ "eval_steps_per_second": 17.151,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.5362380743026733,
34
+ "learning_rate": 0.000194516750479447,
35
+ "loss": 0.4471,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7375512595196251,
41
+ "eval_f1": 0.4628297362110312,
42
+ "eval_loss": 0.44590938091278076,
43
+ "eval_mcc": 0.3591774667498448,
44
+ "eval_precision": 0.7283018867924528,
45
+ "eval_recall": 0.3391915641476274,
46
+ "eval_runtime": 3.1481,
47
+ "eval_samples_per_second": 542.232,
48
+ "eval_steps_per_second": 17.153,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.2486709356307983,
54
+ "learning_rate": 0.00016672864326809742,
55
+ "loss": 0.4324,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7510251903925015,
61
+ "eval_f1": 0.4860943168077388,
62
+ "eval_loss": 0.43371039628982544,
63
+ "eval_mcc": 0.3989881998382762,
64
+ "eval_precision": 0.7790697674418605,
65
+ "eval_recall": 0.3532513181019332,
66
+ "eval_runtime": 3.1303,
67
+ "eval_samples_per_second": 545.315,
68
+ "eval_steps_per_second": 17.251,
69
+ "step": 642
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 2.0944862365722656,
74
+ "learning_rate": 0.00013894053605674787,
75
+ "loss": 0.4261,
76
+ "step": 856
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7574692442882249,
81
+ "eval_f1": 0.5035971223021583,
82
+ "eval_loss": 0.4297623634338379,
83
+ "eval_mcc": 0.4175152081646285,
84
+ "eval_precision": 0.7924528301886793,
85
+ "eval_recall": 0.36906854130052724,
86
+ "eval_runtime": 3.1386,
87
+ "eval_samples_per_second": 543.865,
88
+ "eval_steps_per_second": 17.205,
89
+ "step": 856
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 4.000136852264404,
94
+ "learning_rate": 0.00011115242884539828,
95
+ "loss": 0.4173,
96
+ "step": 1070
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.7685998828353837,
101
+ "eval_f1": 0.5586592178770949,
102
+ "eval_loss": 0.42163264751434326,
103
+ "eval_mcc": 0.44683297923513404,
104
+ "eval_precision": 0.7668711656441718,
105
+ "eval_recall": 0.43936731107205623,
106
+ "eval_runtime": 3.1323,
107
+ "eval_samples_per_second": 544.972,
108
+ "eval_steps_per_second": 17.24,
109
+ "step": 1070
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 3.801867961883545,
114
+ "learning_rate": 8.336432163404871e-05,
115
+ "loss": 0.4119,
116
+ "step": 1284
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.7656707674282367,
121
+ "eval_f1": 0.5893223819301848,
122
+ "eval_loss": 0.41923508048057556,
123
+ "eval_mcc": 0.44403462928634485,
124
+ "eval_precision": 0.7086419753086419,
125
+ "eval_recall": 0.5043936731107206,
126
+ "eval_runtime": 3.1503,
127
+ "eval_samples_per_second": 541.845,
128
+ "eval_steps_per_second": 17.141,
129
+ "step": 1284
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 3.013810157775879,
134
+ "learning_rate": 5.557621442269914e-05,
135
+ "loss": 0.4058,
136
+ "step": 1498
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.7685998828353837,
141
+ "eval_f1": 0.5496009122006841,
142
+ "eval_loss": 0.418170690536499,
143
+ "eval_mcc": 0.4470425722955601,
144
+ "eval_precision": 0.7824675324675324,
145
+ "eval_recall": 0.4235500878734622,
146
+ "eval_runtime": 3.1741,
147
+ "eval_samples_per_second": 537.794,
148
+ "eval_steps_per_second": 17.013,
149
+ "step": 1498
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "grad_norm": 2.8315951824188232,
154
+ "learning_rate": 2.778810721134957e-05,
155
+ "loss": 0.3998,
156
+ "step": 1712
157
+ },
158
+ {
159
+ "epoch": 8.0,
160
+ "eval_accuracy": 0.7674282366725249,
161
+ "eval_f1": 0.576307363927428,
162
+ "eval_loss": 0.4167364537715912,
163
+ "eval_mcc": 0.4452388718633528,
164
+ "eval_precision": 0.7336956521739131,
165
+ "eval_recall": 0.47451669595782076,
166
+ "eval_runtime": 3.1403,
167
+ "eval_samples_per_second": 543.573,
168
+ "eval_steps_per_second": 17.196,
169
+ "step": 1712
170
+ }
171
+ ],
172
+ "logging_steps": 500,
173
+ "max_steps": 1926,
174
+ "num_input_tokens_seen": 0,
175
+ "num_train_epochs": 9,
176
+ "save_steps": 500,
177
+ "total_flos": 4198205315520.0,
178
+ "train_batch_size": 32,
179
+ "trial_name": null,
180
+ "trial_params": {
181
+ "alpha": 0.7932456774257669,
182
+ "learning_rate": 0.00025009296490214613,
183
+ "num_train_epochs": 9,
184
+ "temperature": 23
185
+ }
186
+ }
run-2/checkpoint-1712/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89992d1c1b0b499ec7dee4b5a730ed684159d7afeb30eaab398451703cc62b58
3
+ size 5048
run-2/checkpoint-1712/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-1926/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-2/checkpoint-1926/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ccd0ff971edd1c27031d01c1eb333f1f0e68709e1099293418415da536b7e7c
3
+ size 17549312
run-2/checkpoint-1926/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d25bf07f31e1222a9380d317f3d3d62ed4d3c8d8ee67c1d1c52406b29f12aed
3
+ size 35123898
run-2/checkpoint-1926/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2411fdfdbcf5b48d15f394158baa93e72fe1dc9a2034dc7fa2b11b876e3bf2a
3
+ size 14308
run-2/checkpoint-1926/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:078c8566406ec98261ccdff3cc113314ef89e0241246efc286d08990a9113899
3
+ size 1064
run-2/checkpoint-1926/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-2/checkpoint-1926/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-1926/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-2/checkpoint-1926/trainer_state.json ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7697715289982425,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-1926",
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1926,
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": 4.634866237640381,
14
+ "learning_rate": 0.00022230485769079655,
15
+ "loss": 0.4904,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7223198594024605,
21
+ "eval_f1": 0.4261501210653753,
22
+ "eval_loss": 0.456611692905426,
23
+ "eval_mcc": 0.31390897314151045,
24
+ "eval_precision": 0.6848249027237354,
25
+ "eval_recall": 0.3093145869947276,
26
+ "eval_runtime": 3.1485,
27
+ "eval_samples_per_second": 542.168,
28
+ "eval_steps_per_second": 17.151,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.5362380743026733,
34
+ "learning_rate": 0.000194516750479447,
35
+ "loss": 0.4471,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7375512595196251,
41
+ "eval_f1": 0.4628297362110312,
42
+ "eval_loss": 0.44590938091278076,
43
+ "eval_mcc": 0.3591774667498448,
44
+ "eval_precision": 0.7283018867924528,
45
+ "eval_recall": 0.3391915641476274,
46
+ "eval_runtime": 3.1481,
47
+ "eval_samples_per_second": 542.232,
48
+ "eval_steps_per_second": 17.153,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.2486709356307983,
54
+ "learning_rate": 0.00016672864326809742,
55
+ "loss": 0.4324,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7510251903925015,
61
+ "eval_f1": 0.4860943168077388,
62
+ "eval_loss": 0.43371039628982544,
63
+ "eval_mcc": 0.3989881998382762,
64
+ "eval_precision": 0.7790697674418605,
65
+ "eval_recall": 0.3532513181019332,
66
+ "eval_runtime": 3.1303,
67
+ "eval_samples_per_second": 545.315,
68
+ "eval_steps_per_second": 17.251,
69
+ "step": 642
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 2.0944862365722656,
74
+ "learning_rate": 0.00013894053605674787,
75
+ "loss": 0.4261,
76
+ "step": 856
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7574692442882249,
81
+ "eval_f1": 0.5035971223021583,
82
+ "eval_loss": 0.4297623634338379,
83
+ "eval_mcc": 0.4175152081646285,
84
+ "eval_precision": 0.7924528301886793,
85
+ "eval_recall": 0.36906854130052724,
86
+ "eval_runtime": 3.1386,
87
+ "eval_samples_per_second": 543.865,
88
+ "eval_steps_per_second": 17.205,
89
+ "step": 856
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 4.000136852264404,
94
+ "learning_rate": 0.00011115242884539828,
95
+ "loss": 0.4173,
96
+ "step": 1070
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.7685998828353837,
101
+ "eval_f1": 0.5586592178770949,
102
+ "eval_loss": 0.42163264751434326,
103
+ "eval_mcc": 0.44683297923513404,
104
+ "eval_precision": 0.7668711656441718,
105
+ "eval_recall": 0.43936731107205623,
106
+ "eval_runtime": 3.1323,
107
+ "eval_samples_per_second": 544.972,
108
+ "eval_steps_per_second": 17.24,
109
+ "step": 1070
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 3.801867961883545,
114
+ "learning_rate": 8.336432163404871e-05,
115
+ "loss": 0.4119,
116
+ "step": 1284
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.7656707674282367,
121
+ "eval_f1": 0.5893223819301848,
122
+ "eval_loss": 0.41923508048057556,
123
+ "eval_mcc": 0.44403462928634485,
124
+ "eval_precision": 0.7086419753086419,
125
+ "eval_recall": 0.5043936731107206,
126
+ "eval_runtime": 3.1503,
127
+ "eval_samples_per_second": 541.845,
128
+ "eval_steps_per_second": 17.141,
129
+ "step": 1284
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 3.013810157775879,
134
+ "learning_rate": 5.557621442269914e-05,
135
+ "loss": 0.4058,
136
+ "step": 1498
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.7685998828353837,
141
+ "eval_f1": 0.5496009122006841,
142
+ "eval_loss": 0.418170690536499,
143
+ "eval_mcc": 0.4470425722955601,
144
+ "eval_precision": 0.7824675324675324,
145
+ "eval_recall": 0.4235500878734622,
146
+ "eval_runtime": 3.1741,
147
+ "eval_samples_per_second": 537.794,
148
+ "eval_steps_per_second": 17.013,
149
+ "step": 1498
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "grad_norm": 2.8315951824188232,
154
+ "learning_rate": 2.778810721134957e-05,
155
+ "loss": 0.3998,
156
+ "step": 1712
157
+ },
158
+ {
159
+ "epoch": 8.0,
160
+ "eval_accuracy": 0.7674282366725249,
161
+ "eval_f1": 0.576307363927428,
162
+ "eval_loss": 0.4167364537715912,
163
+ "eval_mcc": 0.4452388718633528,
164
+ "eval_precision": 0.7336956521739131,
165
+ "eval_recall": 0.47451669595782076,
166
+ "eval_runtime": 3.1403,
167
+ "eval_samples_per_second": 543.573,
168
+ "eval_steps_per_second": 17.196,
169
+ "step": 1712
170
+ },
171
+ {
172
+ "epoch": 9.0,
173
+ "grad_norm": 2.7433109283447266,
174
+ "learning_rate": 0.0,
175
+ "loss": 0.3989,
176
+ "step": 1926
177
+ },
178
+ {
179
+ "epoch": 9.0,
180
+ "eval_accuracy": 0.7697715289982425,
181
+ "eval_f1": 0.5901981230448384,
182
+ "eval_loss": 0.4155946969985962,
183
+ "eval_mcc": 0.4528688994135847,
184
+ "eval_precision": 0.7256410256410256,
185
+ "eval_recall": 0.4973637961335677,
186
+ "eval_runtime": 3.1443,
187
+ "eval_samples_per_second": 542.891,
188
+ "eval_steps_per_second": 17.174,
189
+ "step": 1926
190
+ }
191
+ ],
192
+ "logging_steps": 500,
193
+ "max_steps": 1926,
194
+ "num_input_tokens_seen": 0,
195
+ "num_train_epochs": 9,
196
+ "save_steps": 500,
197
+ "total_flos": 4722980979960.0,
198
+ "train_batch_size": 32,
199
+ "trial_name": null,
200
+ "trial_params": {
201
+ "alpha": 0.7932456774257669,
202
+ "learning_rate": 0.00025009296490214613,
203
+ "num_train_epochs": 9,
204
+ "temperature": 23
205
+ }
206
+ }
run-2/checkpoint-1926/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89992d1c1b0b499ec7dee4b5a730ed684159d7afeb30eaab398451703cc62b58
3
+ size 5048
run-2/checkpoint-1926/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-214/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06a4d6bc70e2d5e8a2a3750ec5030e64a4a1396309fd7cd2c1e4cdda62b2f0e8
3
+ size 17549312
run-3/checkpoint-214/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65560c37a015d2f1bd16e59b8e7908b24ad628feebd46427c18a6cc54c5cbe0d
3
+ size 35123898
run-3/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-3/checkpoint-214/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:621fabe3af1b7babf77acd5943b5bf3a0e4ad80bd636e511bd3fa3c04c3d8b9f
3
+ size 1064
run-3/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-3/checkpoint-214/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/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-3/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": 2.1204113960266113,
14
+ "learning_rate": 1.1932465475413847e-05,
15
+ "loss": 0.4261,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.4023595452308655,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 3.137,
27
+ "eval_samples_per_second": 544.145,
28
+ "eval_steps_per_second": 17.214,
29
+ "step": 214
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 1070,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 5,
36
+ "save_steps": 500,
37
+ "total_flos": 524775664440.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.6118639206182097,
42
+ "learning_rate": 1.4915581844267308e-05,
43
+ "num_train_epochs": 5,
44
+ "temperature": 15
45
+ }
46
+ }
run-3/checkpoint-214/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:621c87997eb03e02a37c6a3e61f45ff57c6fdae7e493961bdadb2e1be324da40
3
+ size 5048
run-3/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 sha256:89992d1c1b0b499ec7dee4b5a730ed684159d7afeb30eaab398451703cc62b58
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:621c87997eb03e02a37c6a3e61f45ff57c6fdae7e493961bdadb2e1be324da40
3
  size 5048