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
34a678b
·
verified ·
1 Parent(s): f25ade1

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1714699776.e992b94a7c88.3982.1 +2 -2
  2. logs/events.out.tfevents.1714700864.e992b94a7c88.3982.2 +3 -0
  3. model.safetensors +1 -1
  4. run-1/checkpoint-12704/config.json +34 -0
  5. run-1/checkpoint-12704/model.safetensors +3 -0
  6. run-1/checkpoint-12704/optimizer.pt +3 -0
  7. run-1/checkpoint-12704/rng_state.pth +3 -0
  8. run-1/checkpoint-12704/scheduler.pt +3 -0
  9. run-1/checkpoint-12704/special_tokens_map.json +7 -0
  10. run-1/checkpoint-12704/tokenizer.json +0 -0
  11. run-1/checkpoint-12704/tokenizer_config.json +57 -0
  12. run-1/checkpoint-12704/trainer_state.json +186 -0
  13. run-1/checkpoint-12704/training_args.bin +3 -0
  14. run-1/checkpoint-12704/vocab.txt +0 -0
  15. run-1/checkpoint-14292/config.json +34 -0
  16. run-1/checkpoint-14292/model.safetensors +3 -0
  17. run-1/checkpoint-14292/optimizer.pt +3 -0
  18. run-1/checkpoint-14292/rng_state.pth +3 -0
  19. run-1/checkpoint-14292/scheduler.pt +3 -0
  20. run-1/checkpoint-14292/special_tokens_map.json +7 -0
  21. run-1/checkpoint-14292/tokenizer.json +0 -0
  22. run-1/checkpoint-14292/tokenizer_config.json +57 -0
  23. run-1/checkpoint-14292/trainer_state.json +206 -0
  24. run-1/checkpoint-14292/training_args.bin +3 -0
  25. run-1/checkpoint-14292/vocab.txt +0 -0
  26. run-2/checkpoint-1588/config.json +34 -0
  27. run-2/checkpoint-1588/model.safetensors +3 -0
  28. run-2/checkpoint-1588/optimizer.pt +3 -0
  29. run-2/checkpoint-1588/rng_state.pth +3 -0
  30. run-2/checkpoint-1588/scheduler.pt +3 -0
  31. run-2/checkpoint-1588/special_tokens_map.json +7 -0
  32. run-2/checkpoint-1588/tokenizer.json +0 -0
  33. run-2/checkpoint-1588/tokenizer_config.json +57 -0
  34. run-2/checkpoint-1588/trainer_state.json +46 -0
  35. run-2/checkpoint-1588/training_args.bin +3 -0
  36. run-2/checkpoint-1588/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1714699776.e992b94a7c88.3982.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e9fe69162d7066a3891aa6d1a38592074fb757dba22d4cfb35a77842fc3c301
3
- size 6213
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d613192359e53ae3628e6d313049135f8a4277266f3bb7351abd39b929db0f5
3
+ size 11677
logs/events.out.tfevents.1714700864.e992b94a7c88.3982.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2bf606e47b4aeeff0d05e888fe0285e07dda271a52098b247e12eb99379d851
3
+ size 5483
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3ab0c120ecc805185554f6347902d8d4a2a3d34a6348ac7df5c40f4a4708d59
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25c125813a4956316ef095cd7066585d0221614128db53d055c3f9db6535cb1d
3
  size 17549312
run-1/checkpoint-12704/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-1/checkpoint-12704/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1579798c526743b46bf805f296e0e9cc5b6b4d589d721ceb599500386e68c541
3
+ size 17549312
run-1/checkpoint-12704/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a85d82c6c418fa145f5507284e0fc5e05bd87ab069edb84ad84f334b6f9e0b2
3
+ size 35123898
run-1/checkpoint-12704/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:553811aa55e65a06f40cc78b842a2927f755bd7f2c6e1c1734fef60ab9a75575
3
+ size 14308
run-1/checkpoint-12704/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c33aac46f218a0624afd1ed315674df12f05bc9cf2f57740cc7a0719f41412f
3
+ size 1064
run-1/checkpoint-12704/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-1/checkpoint-12704/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-12704/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-1/checkpoint-12704/trainer_state.json ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6979379820557217,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-12704",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 12704,
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": 1.0594383478164673,
14
+ "learning_rate": 8.902447569795288e-05,
15
+ "loss": 0.5725,
16
+ "step": 1588
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6804659216118369,
21
+ "eval_f1": 0.3575949367088608,
22
+ "eval_loss": 0.5597381591796875,
23
+ "eval_mcc": 0.19612047304332003,
24
+ "eval_precision": 0.5419664268585132,
25
+ "eval_recall": 0.2668240850059032,
26
+ "eval_runtime": 23.4624,
27
+ "eval_samples_per_second": 541.547,
28
+ "eval_steps_per_second": 16.963,
29
+ "step": 1588
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.540066123008728,
34
+ "learning_rate": 7.789641623570877e-05,
35
+ "loss": 0.5555,
36
+ "step": 3176
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6874704863843853,
41
+ "eval_f1": 0.2603836841124977,
42
+ "eval_loss": 0.5536655783653259,
43
+ "eval_mcc": 0.18799631789309962,
44
+ "eval_precision": 0.6164021164021164,
45
+ "eval_recall": 0.16505312868949232,
46
+ "eval_runtime": 23.2494,
47
+ "eval_samples_per_second": 546.509,
48
+ "eval_steps_per_second": 17.119,
49
+ "step": 3176
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.06575608253479,
54
+ "learning_rate": 6.676835677346465e-05,
55
+ "loss": 0.5493,
56
+ "step": 4764
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.6873130804344404,
61
+ "eval_f1": 0.267379679144385,
62
+ "eval_loss": 0.5435917377471924,
63
+ "eval_mcc": 0.18869269284566614,
64
+ "eval_precision": 0.6102693602693603,
65
+ "eval_recall": 0.17119244391971664,
66
+ "eval_runtime": 23.3586,
67
+ "eval_samples_per_second": 543.954,
68
+ "eval_steps_per_second": 17.039,
69
+ "step": 4764
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 2.0746259689331055,
74
+ "learning_rate": 5.564029731122055e-05,
75
+ "loss": 0.543,
76
+ "step": 6352
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6910908232331182,
81
+ "eval_f1": 0.36064505619807785,
82
+ "eval_loss": 0.5372793674468994,
83
+ "eval_mcc": 0.22096514058006989,
84
+ "eval_precision": 0.5814075630252101,
85
+ "eval_recall": 0.2613931523022432,
86
+ "eval_runtime": 23.311,
87
+ "eval_samples_per_second": 545.065,
88
+ "eval_steps_per_second": 17.073,
89
+ "step": 6352
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 2.557748794555664,
94
+ "learning_rate": 4.451223784897644e-05,
95
+ "loss": 0.5374,
96
+ "step": 7940
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.6961278136313552,
101
+ "eval_f1": 0.36839522329461794,
102
+ "eval_loss": 0.5319377183914185,
103
+ "eval_mcc": 0.23523702656150358,
104
+ "eval_precision": 0.5995740149094781,
105
+ "eval_recall": 0.26587957497048403,
106
+ "eval_runtime": 23.5602,
107
+ "eval_samples_per_second": 539.299,
108
+ "eval_steps_per_second": 16.893,
109
+ "step": 7940
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 1.728196620941162,
114
+ "learning_rate": 3.3384178386732324e-05,
115
+ "loss": 0.5341,
116
+ "step": 9528
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.6946324571068786,
121
+ "eval_f1": 0.42279083606069623,
122
+ "eval_loss": 0.5333712100982666,
123
+ "eval_mcc": 0.2491393222028609,
124
+ "eval_precision": 0.5713711298753519,
125
+ "eval_recall": 0.33553719008264465,
126
+ "eval_runtime": 23.3995,
127
+ "eval_samples_per_second": 543.002,
128
+ "eval_steps_per_second": 17.009,
129
+ "step": 9528
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 2.6901352405548096,
134
+ "learning_rate": 2.225611892448822e-05,
135
+ "loss": 0.5312,
136
+ "step": 11116
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.6938454273571542,
141
+ "eval_f1": 0.4832624867162594,
142
+ "eval_loss": 0.5355043411254883,
143
+ "eval_mcc": 0.27487985905109846,
144
+ "eval_precision": 0.552383844518676,
145
+ "eval_recall": 0.4295159386068477,
146
+ "eval_runtime": 23.5503,
147
+ "eval_samples_per_second": 539.525,
148
+ "eval_steps_per_second": 16.9,
149
+ "step": 11116
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "grad_norm": 1.672201156616211,
154
+ "learning_rate": 1.112805946224411e-05,
155
+ "loss": 0.5288,
156
+ "step": 12704
157
+ },
158
+ {
159
+ "epoch": 8.0,
160
+ "eval_accuracy": 0.6979379820557217,
161
+ "eval_f1": 0.42613636363636365,
162
+ "eval_loss": 0.5302781462669373,
163
+ "eval_mcc": 0.2569293292783036,
164
+ "eval_precision": 0.5809213208316347,
165
+ "eval_recall": 0.3364817001180638,
166
+ "eval_runtime": 23.502,
167
+ "eval_samples_per_second": 540.634,
168
+ "eval_steps_per_second": 16.935,
169
+ "step": 12704
170
+ }
171
+ ],
172
+ "logging_steps": 500,
173
+ "max_steps": 14292,
174
+ "num_input_tokens_seen": 0,
175
+ "num_train_epochs": 9,
176
+ "save_steps": 500,
177
+ "total_flos": 31271152610400.0,
178
+ "train_batch_size": 32,
179
+ "trial_name": null,
180
+ "trial_params": {
181
+ "alpha": 0.9165014388792823,
182
+ "learning_rate": 0.00010015253516019699,
183
+ "num_train_epochs": 9,
184
+ "temperature": 13
185
+ }
186
+ }
run-1/checkpoint-12704/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad73700bc97770fed9d7ff7b9185fb4b6eb7aab5e5ee65d46e74c56c44c8da3
3
+ size 4984
run-1/checkpoint-12704/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-14292/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-1/checkpoint-14292/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091ecbf9c4201a1168bbf274dc5dc1bb1de741761fb469fcc216bee3b9a1004c
3
+ size 17549312
run-1/checkpoint-14292/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e656e59376af830243a2603f98a60766e1f04eb993f69a5735d30f61981aa28
3
+ size 35123898
run-1/checkpoint-14292/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e79de612232dae3769006bb79b70294246e1bd144345ab616cac2895e3951a60
3
+ size 14308
run-1/checkpoint-14292/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82d82a371fd0ee306213922ff140338e382edc4a54deabea44a065d8eb5bf721
3
+ size 1064
run-1/checkpoint-14292/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-1/checkpoint-14292/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-14292/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-1/checkpoint-14292/trainer_state.json ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6988037147804187,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-14292",
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 14292,
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": 1.0594383478164673,
14
+ "learning_rate": 8.902447569795288e-05,
15
+ "loss": 0.5725,
16
+ "step": 1588
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6804659216118369,
21
+ "eval_f1": 0.3575949367088608,
22
+ "eval_loss": 0.5597381591796875,
23
+ "eval_mcc": 0.19612047304332003,
24
+ "eval_precision": 0.5419664268585132,
25
+ "eval_recall": 0.2668240850059032,
26
+ "eval_runtime": 23.4624,
27
+ "eval_samples_per_second": 541.547,
28
+ "eval_steps_per_second": 16.963,
29
+ "step": 1588
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.540066123008728,
34
+ "learning_rate": 7.789641623570877e-05,
35
+ "loss": 0.5555,
36
+ "step": 3176
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6874704863843853,
41
+ "eval_f1": 0.2603836841124977,
42
+ "eval_loss": 0.5536655783653259,
43
+ "eval_mcc": 0.18799631789309962,
44
+ "eval_precision": 0.6164021164021164,
45
+ "eval_recall": 0.16505312868949232,
46
+ "eval_runtime": 23.2494,
47
+ "eval_samples_per_second": 546.509,
48
+ "eval_steps_per_second": 17.119,
49
+ "step": 3176
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.06575608253479,
54
+ "learning_rate": 6.676835677346465e-05,
55
+ "loss": 0.5493,
56
+ "step": 4764
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.6873130804344404,
61
+ "eval_f1": 0.267379679144385,
62
+ "eval_loss": 0.5435917377471924,
63
+ "eval_mcc": 0.18869269284566614,
64
+ "eval_precision": 0.6102693602693603,
65
+ "eval_recall": 0.17119244391971664,
66
+ "eval_runtime": 23.3586,
67
+ "eval_samples_per_second": 543.954,
68
+ "eval_steps_per_second": 17.039,
69
+ "step": 4764
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 2.0746259689331055,
74
+ "learning_rate": 5.564029731122055e-05,
75
+ "loss": 0.543,
76
+ "step": 6352
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6910908232331182,
81
+ "eval_f1": 0.36064505619807785,
82
+ "eval_loss": 0.5372793674468994,
83
+ "eval_mcc": 0.22096514058006989,
84
+ "eval_precision": 0.5814075630252101,
85
+ "eval_recall": 0.2613931523022432,
86
+ "eval_runtime": 23.311,
87
+ "eval_samples_per_second": 545.065,
88
+ "eval_steps_per_second": 17.073,
89
+ "step": 6352
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 2.557748794555664,
94
+ "learning_rate": 4.451223784897644e-05,
95
+ "loss": 0.5374,
96
+ "step": 7940
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.6961278136313552,
101
+ "eval_f1": 0.36839522329461794,
102
+ "eval_loss": 0.5319377183914185,
103
+ "eval_mcc": 0.23523702656150358,
104
+ "eval_precision": 0.5995740149094781,
105
+ "eval_recall": 0.26587957497048403,
106
+ "eval_runtime": 23.5602,
107
+ "eval_samples_per_second": 539.299,
108
+ "eval_steps_per_second": 16.893,
109
+ "step": 7940
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 1.728196620941162,
114
+ "learning_rate": 3.3384178386732324e-05,
115
+ "loss": 0.5341,
116
+ "step": 9528
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.6946324571068786,
121
+ "eval_f1": 0.42279083606069623,
122
+ "eval_loss": 0.5333712100982666,
123
+ "eval_mcc": 0.2491393222028609,
124
+ "eval_precision": 0.5713711298753519,
125
+ "eval_recall": 0.33553719008264465,
126
+ "eval_runtime": 23.3995,
127
+ "eval_samples_per_second": 543.002,
128
+ "eval_steps_per_second": 17.009,
129
+ "step": 9528
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 2.6901352405548096,
134
+ "learning_rate": 2.225611892448822e-05,
135
+ "loss": 0.5312,
136
+ "step": 11116
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.6938454273571542,
141
+ "eval_f1": 0.4832624867162594,
142
+ "eval_loss": 0.5355043411254883,
143
+ "eval_mcc": 0.27487985905109846,
144
+ "eval_precision": 0.552383844518676,
145
+ "eval_recall": 0.4295159386068477,
146
+ "eval_runtime": 23.5503,
147
+ "eval_samples_per_second": 539.525,
148
+ "eval_steps_per_second": 16.9,
149
+ "step": 11116
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "grad_norm": 1.672201156616211,
154
+ "learning_rate": 1.112805946224411e-05,
155
+ "loss": 0.5288,
156
+ "step": 12704
157
+ },
158
+ {
159
+ "epoch": 8.0,
160
+ "eval_accuracy": 0.6979379820557217,
161
+ "eval_f1": 0.42613636363636365,
162
+ "eval_loss": 0.5302781462669373,
163
+ "eval_mcc": 0.2569293292783036,
164
+ "eval_precision": 0.5809213208316347,
165
+ "eval_recall": 0.3364817001180638,
166
+ "eval_runtime": 23.502,
167
+ "eval_samples_per_second": 540.634,
168
+ "eval_steps_per_second": 16.935,
169
+ "step": 12704
170
+ },
171
+ {
172
+ "epoch": 9.0,
173
+ "grad_norm": 1.6605579853057861,
174
+ "learning_rate": 0.0,
175
+ "loss": 0.5269,
176
+ "step": 14292
177
+ },
178
+ {
179
+ "epoch": 9.0,
180
+ "eval_accuracy": 0.6988037147804187,
181
+ "eval_f1": 0.4386093589555523,
182
+ "eval_loss": 0.5291692018508911,
183
+ "eval_mcc": 0.2632234170463615,
184
+ "eval_precision": 0.5790085205267235,
185
+ "eval_recall": 0.3530106257378985,
186
+ "eval_runtime": 23.2847,
187
+ "eval_samples_per_second": 545.68,
188
+ "eval_steps_per_second": 17.093,
189
+ "step": 14292
190
+ }
191
+ ],
192
+ "logging_steps": 500,
193
+ "max_steps": 14292,
194
+ "num_input_tokens_seen": 0,
195
+ "num_train_epochs": 9,
196
+ "save_steps": 500,
197
+ "total_flos": 35180046686700.0,
198
+ "train_batch_size": 32,
199
+ "trial_name": null,
200
+ "trial_params": {
201
+ "alpha": 0.9165014388792823,
202
+ "learning_rate": 0.00010015253516019699,
203
+ "num_train_epochs": 9,
204
+ "temperature": 13
205
+ }
206
+ }
run-1/checkpoint-14292/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad73700bc97770fed9d7ff7b9185fb4b6eb7aab5e5ee65d46e74c56c44c8da3
3
+ size 4984
run-1/checkpoint-14292/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-1588/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25c125813a4956316ef095cd7066585d0221614128db53d055c3f9db6535cb1d
3
+ size 17549312
run-2/checkpoint-1588/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5bdca5be982793ee7e8047332e94bec07591788a433668b49bcdd64501ce81e
3
+ size 35123898
run-2/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-2/checkpoint-1588/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b7130c5cfe47003c612214906d906c44aeeaeb3d3e7f7646322fe644d505ff1
3
+ size 1064
run-2/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-2/checkpoint-1588/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-1588/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6666929009916575,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/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": 0.5482791066169739,
14
+ "learning_rate": 9.642076934385773e-06,
15
+ "loss": 0.5031,
16
+ "step": 1588
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666929009916575,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.49551922082901,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 23.2895,
27
+ "eval_samples_per_second": 545.567,
28
+ "eval_steps_per_second": 17.089,
29
+ "step": 1588
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 14292,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 9,
36
+ "save_steps": 500,
37
+ "total_flos": 3908894076300.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.7681424055105933,
42
+ "learning_rate": 1.0847336551183995e-05,
43
+ "num_train_epochs": 9,
44
+ "temperature": 16
45
+ }
46
+ }
run-2/checkpoint-1588/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af62eff3e380aae108292c73f008f9877e2ad7abffa7d67edf7a00b8980fb10b
3
+ size 4984
run-2/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:cad73700bc97770fed9d7ff7b9185fb4b6eb7aab5e5ee65d46e74c56c44c8da3
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af62eff3e380aae108292c73f008f9877e2ad7abffa7d67edf7a00b8980fb10b
3
  size 4984