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
0cdda70
·
verified ·
1 Parent(s): a204b84

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1709857711.013ec1551212.75384.21 +2 -2
  2. logs/events.out.tfevents.1709863496.013ec1551212.75384.22 +3 -0
  3. model.safetensors +1 -1
  4. run-21/checkpoint-6894/config.json +34 -0
  5. run-21/checkpoint-6894/model.safetensors +3 -0
  6. run-21/checkpoint-6894/optimizer.pt +3 -0
  7. run-21/checkpoint-6894/rng_state.pth +3 -0
  8. run-21/checkpoint-6894/scheduler.pt +3 -0
  9. run-21/checkpoint-6894/special_tokens_map.json +7 -0
  10. run-21/checkpoint-6894/tokenizer.json +0 -0
  11. run-21/checkpoint-6894/tokenizer_config.json +57 -0
  12. run-21/checkpoint-6894/trainer_state.json +197 -0
  13. run-21/checkpoint-6894/training_args.bin +3 -0
  14. run-21/checkpoint-6894/vocab.txt +0 -0
  15. run-21/checkpoint-7660/config.json +34 -0
  16. run-21/checkpoint-7660/model.safetensors +3 -0
  17. run-21/checkpoint-7660/optimizer.pt +3 -0
  18. run-21/checkpoint-7660/rng_state.pth +3 -0
  19. run-21/checkpoint-7660/scheduler.pt +3 -0
  20. run-21/checkpoint-7660/special_tokens_map.json +7 -0
  21. run-21/checkpoint-7660/tokenizer.json +0 -0
  22. run-21/checkpoint-7660/tokenizer_config.json +57 -0
  23. run-21/checkpoint-7660/trainer_state.json +216 -0
  24. run-21/checkpoint-7660/training_args.bin +3 -0
  25. run-21/checkpoint-7660/vocab.txt +0 -0
  26. run-22/checkpoint-766/config.json +34 -0
  27. run-22/checkpoint-766/model.safetensors +3 -0
  28. run-22/checkpoint-766/optimizer.pt +3 -0
  29. run-22/checkpoint-766/rng_state.pth +3 -0
  30. run-22/checkpoint-766/scheduler.pt +3 -0
  31. run-22/checkpoint-766/special_tokens_map.json +7 -0
  32. run-22/checkpoint-766/tokenizer.json +0 -0
  33. run-22/checkpoint-766/tokenizer_config.json +57 -0
  34. run-22/checkpoint-766/trainer_state.json +45 -0
  35. run-22/checkpoint-766/training_args.bin +3 -0
  36. run-22/checkpoint-766/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1709857711.013ec1551212.75384.21 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbef0bcf54a95ae35f1e51ba45b47de3374cde4ccf5a45da4ff3f52169c9bcee
3
- size 6009
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:404bfce517e659946dde70dd490069ca15d72c0f6f19c9998cb50ebc1f9795d9
3
+ size 11827
logs/events.out.tfevents.1709863496.013ec1551212.75384.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:776c2acedb6049d6e861ae9ff56676a5d83051415cce478b629311e7cbf4bc1c
3
+ size 5325
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:522f3c7b9a4b35d19baa59dc201284cef86709113f8c96db6321cf1a3d993184
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8351a2eb5001b9a26f911bf958be7b375a20f49c9f620db249c9ffc8bc4bff36
3
  size 17549312
run-21/checkpoint-6894/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-21/checkpoint-6894/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9739577d3556bf1e5040cac241a44a691b4aef07ea634139b74d2c8d0120b3bd
3
+ size 17549312
run-21/checkpoint-6894/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b14da18e5df3ea70b5c898d852164226e4fe904e99d29bab8cbf01433362dcc
3
+ size 35122746
run-21/checkpoint-6894/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ffe05c05ef484b71468374c222ba2df0f72c4f9bf269c844f741792915a14f
3
+ size 14054
run-21/checkpoint-6894/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48adef8c5a4560df72a3e63bf8ffeb5e8408aa0471e0931ba542637b88d954ec
3
+ size 1064
run-21/checkpoint-6894/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-21/checkpoint-6894/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-21/checkpoint-6894/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-21/checkpoint-6894/trainer_state.json ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8307240704500979,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-6894",
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 6894,
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": 1.5445048809051514,
14
+ "learning_rate": 0.0001354005618154073,
15
+ "loss": 0.4902,
16
+ "step": 766
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7710371819960861,
21
+ "eval_f1": 0.7943760984182776,
22
+ "eval_loss": 0.4425993263721466,
23
+ "eval_precision": 0.7208931419457735,
24
+ "eval_recall": 0.8845401174168297,
25
+ "eval_runtime": 133.7206,
26
+ "eval_samples_per_second": 7.643,
27
+ "eval_steps_per_second": 1.914,
28
+ "step": 766
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 6.882767677307129,
33
+ "learning_rate": 0.00012035605494702872,
34
+ "loss": 0.4409,
35
+ "step": 1532
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8111545988258317,
40
+ "eval_f1": 0.8360237892948172,
41
+ "eval_loss": 0.41539597511291504,
42
+ "eval_precision": 0.7387387387387387,
43
+ "eval_recall": 0.9628180039138943,
44
+ "eval_runtime": 133.4678,
45
+ "eval_samples_per_second": 7.657,
46
+ "eval_steps_per_second": 1.918,
47
+ "step": 1532
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 2.518984794616699,
52
+ "learning_rate": 0.00010531154807865013,
53
+ "loss": 0.4251,
54
+ "step": 2298
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8180039138943248,
59
+ "eval_f1": 0.8264925373134328,
60
+ "eval_loss": 0.42979857325553894,
61
+ "eval_precision": 0.7896613190730838,
62
+ "eval_recall": 0.8669275929549902,
63
+ "eval_runtime": 132.8888,
64
+ "eval_samples_per_second": 7.691,
65
+ "eval_steps_per_second": 1.926,
66
+ "step": 2298
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 1.3853329420089722,
71
+ "learning_rate": 9.026704121027153e-05,
72
+ "loss": 0.4192,
73
+ "step": 3064
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8189823874755382,
78
+ "eval_f1": 0.8269410664172124,
79
+ "eval_loss": 0.4213884174823761,
80
+ "eval_precision": 0.7921146953405018,
81
+ "eval_recall": 0.8649706457925636,
82
+ "eval_runtime": 133.0333,
83
+ "eval_samples_per_second": 7.682,
84
+ "eval_steps_per_second": 1.924,
85
+ "step": 3064
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 16.2620792388916,
90
+ "learning_rate": 7.522253434189295e-05,
91
+ "loss": 0.4053,
92
+ "step": 3830
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.8228962818003914,
97
+ "eval_f1": 0.8300469483568074,
98
+ "eval_loss": 0.4430813789367676,
99
+ "eval_precision": 0.7978339350180506,
100
+ "eval_recall": 0.8649706457925636,
101
+ "eval_runtime": 133.6623,
102
+ "eval_samples_per_second": 7.646,
103
+ "eval_steps_per_second": 1.915,
104
+ "step": 3830
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "grad_norm": 1.759765386581421,
109
+ "learning_rate": 6.017802747351436e-05,
110
+ "loss": 0.4021,
111
+ "step": 4596
112
+ },
113
+ {
114
+ "epoch": 6.0,
115
+ "eval_accuracy": 0.8189823874755382,
116
+ "eval_f1": 0.8316651501364878,
117
+ "eval_loss": 0.43012145161628723,
118
+ "eval_precision": 0.7772108843537415,
119
+ "eval_recall": 0.8943248532289628,
120
+ "eval_runtime": 133.3962,
121
+ "eval_samples_per_second": 7.661,
122
+ "eval_steps_per_second": 1.919,
123
+ "step": 4596
124
+ },
125
+ {
126
+ "epoch": 7.0,
127
+ "grad_norm": 1.6848570108413696,
128
+ "learning_rate": 4.5133520605135766e-05,
129
+ "loss": 0.3933,
130
+ "step": 5362
131
+ },
132
+ {
133
+ "epoch": 7.0,
134
+ "eval_accuracy": 0.8199608610567515,
135
+ "eval_f1": 0.8362989323843416,
136
+ "eval_loss": 0.4251769185066223,
137
+ "eval_precision": 0.766721044045677,
138
+ "eval_recall": 0.9197651663405088,
139
+ "eval_runtime": 133.0713,
140
+ "eval_samples_per_second": 7.68,
141
+ "eval_steps_per_second": 1.924,
142
+ "step": 5362
143
+ },
144
+ {
145
+ "epoch": 8.0,
146
+ "grad_norm": 2.3459274768829346,
147
+ "learning_rate": 3.008901373675718e-05,
148
+ "loss": 0.3864,
149
+ "step": 6128
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "eval_accuracy": 0.8199608610567515,
154
+ "eval_f1": 0.8351254480286738,
155
+ "eval_loss": 0.42666804790496826,
156
+ "eval_precision": 0.7702479338842976,
157
+ "eval_recall": 0.9119373776908023,
158
+ "eval_runtime": 131.53,
159
+ "eval_samples_per_second": 7.77,
160
+ "eval_steps_per_second": 1.946,
161
+ "step": 6128
162
+ },
163
+ {
164
+ "epoch": 9.0,
165
+ "grad_norm": 0.43761202692985535,
166
+ "learning_rate": 1.504450686837859e-05,
167
+ "loss": 0.3865,
168
+ "step": 6894
169
+ },
170
+ {
171
+ "epoch": 9.0,
172
+ "eval_accuracy": 0.8307240704500979,
173
+ "eval_f1": 0.840258541089566,
174
+ "eval_loss": 0.4156372845172882,
175
+ "eval_precision": 0.7954545454545454,
176
+ "eval_recall": 0.8904109589041096,
177
+ "eval_runtime": 131.4696,
178
+ "eval_samples_per_second": 7.774,
179
+ "eval_steps_per_second": 1.947,
180
+ "step": 6894
181
+ }
182
+ ],
183
+ "logging_steps": 500,
184
+ "max_steps": 7660,
185
+ "num_input_tokens_seen": 0,
186
+ "num_train_epochs": 10,
187
+ "save_steps": 500,
188
+ "total_flos": 2121256775520.0,
189
+ "train_batch_size": 4,
190
+ "trial_name": null,
191
+ "trial_params": {
192
+ "alpha": 0.7711149722361785,
193
+ "learning_rate": 0.0001504450686837859,
194
+ "num_train_epochs": 10,
195
+ "temperature": 20
196
+ }
197
+ }
run-21/checkpoint-6894/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeb7ed96b316155249bd80b74449e21f10852ace4b6c7dccc86652bad341ee55
3
+ size 4920
run-21/checkpoint-6894/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-21/checkpoint-7660/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-21/checkpoint-7660/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f716ebcdac815d34ff2ccf3dabb73812631b01002af4fe3d207429602c91c93b
3
+ size 17549312
run-21/checkpoint-7660/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6edde8f5bec281a72f511d616e632d69d2c99be41af311e6261e47cf171603df
3
+ size 35122746
run-21/checkpoint-7660/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33bd51131cbcff81fcd782305efd634ea9a60355b70aea2e02c54e73d400a785
3
+ size 14054
run-21/checkpoint-7660/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce9b674a87e9d7532b3ed0be01f43b46a1765601157a06ad0484373d36c4e931
3
+ size 1064
run-21/checkpoint-7660/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-21/checkpoint-7660/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-21/checkpoint-7660/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-21/checkpoint-7660/trainer_state.json ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8307240704500979,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-6894",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 7660,
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": 1.5445048809051514,
14
+ "learning_rate": 0.0001354005618154073,
15
+ "loss": 0.4902,
16
+ "step": 766
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7710371819960861,
21
+ "eval_f1": 0.7943760984182776,
22
+ "eval_loss": 0.4425993263721466,
23
+ "eval_precision": 0.7208931419457735,
24
+ "eval_recall": 0.8845401174168297,
25
+ "eval_runtime": 133.7206,
26
+ "eval_samples_per_second": 7.643,
27
+ "eval_steps_per_second": 1.914,
28
+ "step": 766
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 6.882767677307129,
33
+ "learning_rate": 0.00012035605494702872,
34
+ "loss": 0.4409,
35
+ "step": 1532
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8111545988258317,
40
+ "eval_f1": 0.8360237892948172,
41
+ "eval_loss": 0.41539597511291504,
42
+ "eval_precision": 0.7387387387387387,
43
+ "eval_recall": 0.9628180039138943,
44
+ "eval_runtime": 133.4678,
45
+ "eval_samples_per_second": 7.657,
46
+ "eval_steps_per_second": 1.918,
47
+ "step": 1532
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 2.518984794616699,
52
+ "learning_rate": 0.00010531154807865013,
53
+ "loss": 0.4251,
54
+ "step": 2298
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8180039138943248,
59
+ "eval_f1": 0.8264925373134328,
60
+ "eval_loss": 0.42979857325553894,
61
+ "eval_precision": 0.7896613190730838,
62
+ "eval_recall": 0.8669275929549902,
63
+ "eval_runtime": 132.8888,
64
+ "eval_samples_per_second": 7.691,
65
+ "eval_steps_per_second": 1.926,
66
+ "step": 2298
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 1.3853329420089722,
71
+ "learning_rate": 9.026704121027153e-05,
72
+ "loss": 0.4192,
73
+ "step": 3064
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8189823874755382,
78
+ "eval_f1": 0.8269410664172124,
79
+ "eval_loss": 0.4213884174823761,
80
+ "eval_precision": 0.7921146953405018,
81
+ "eval_recall": 0.8649706457925636,
82
+ "eval_runtime": 133.0333,
83
+ "eval_samples_per_second": 7.682,
84
+ "eval_steps_per_second": 1.924,
85
+ "step": 3064
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 16.2620792388916,
90
+ "learning_rate": 7.522253434189295e-05,
91
+ "loss": 0.4053,
92
+ "step": 3830
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.8228962818003914,
97
+ "eval_f1": 0.8300469483568074,
98
+ "eval_loss": 0.4430813789367676,
99
+ "eval_precision": 0.7978339350180506,
100
+ "eval_recall": 0.8649706457925636,
101
+ "eval_runtime": 133.6623,
102
+ "eval_samples_per_second": 7.646,
103
+ "eval_steps_per_second": 1.915,
104
+ "step": 3830
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "grad_norm": 1.759765386581421,
109
+ "learning_rate": 6.017802747351436e-05,
110
+ "loss": 0.4021,
111
+ "step": 4596
112
+ },
113
+ {
114
+ "epoch": 6.0,
115
+ "eval_accuracy": 0.8189823874755382,
116
+ "eval_f1": 0.8316651501364878,
117
+ "eval_loss": 0.43012145161628723,
118
+ "eval_precision": 0.7772108843537415,
119
+ "eval_recall": 0.8943248532289628,
120
+ "eval_runtime": 133.3962,
121
+ "eval_samples_per_second": 7.661,
122
+ "eval_steps_per_second": 1.919,
123
+ "step": 4596
124
+ },
125
+ {
126
+ "epoch": 7.0,
127
+ "grad_norm": 1.6848570108413696,
128
+ "learning_rate": 4.5133520605135766e-05,
129
+ "loss": 0.3933,
130
+ "step": 5362
131
+ },
132
+ {
133
+ "epoch": 7.0,
134
+ "eval_accuracy": 0.8199608610567515,
135
+ "eval_f1": 0.8362989323843416,
136
+ "eval_loss": 0.4251769185066223,
137
+ "eval_precision": 0.766721044045677,
138
+ "eval_recall": 0.9197651663405088,
139
+ "eval_runtime": 133.0713,
140
+ "eval_samples_per_second": 7.68,
141
+ "eval_steps_per_second": 1.924,
142
+ "step": 5362
143
+ },
144
+ {
145
+ "epoch": 8.0,
146
+ "grad_norm": 2.3459274768829346,
147
+ "learning_rate": 3.008901373675718e-05,
148
+ "loss": 0.3864,
149
+ "step": 6128
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "eval_accuracy": 0.8199608610567515,
154
+ "eval_f1": 0.8351254480286738,
155
+ "eval_loss": 0.42666804790496826,
156
+ "eval_precision": 0.7702479338842976,
157
+ "eval_recall": 0.9119373776908023,
158
+ "eval_runtime": 131.53,
159
+ "eval_samples_per_second": 7.77,
160
+ "eval_steps_per_second": 1.946,
161
+ "step": 6128
162
+ },
163
+ {
164
+ "epoch": 9.0,
165
+ "grad_norm": 0.43761202692985535,
166
+ "learning_rate": 1.504450686837859e-05,
167
+ "loss": 0.3865,
168
+ "step": 6894
169
+ },
170
+ {
171
+ "epoch": 9.0,
172
+ "eval_accuracy": 0.8307240704500979,
173
+ "eval_f1": 0.840258541089566,
174
+ "eval_loss": 0.4156372845172882,
175
+ "eval_precision": 0.7954545454545454,
176
+ "eval_recall": 0.8904109589041096,
177
+ "eval_runtime": 131.4696,
178
+ "eval_samples_per_second": 7.774,
179
+ "eval_steps_per_second": 1.947,
180
+ "step": 6894
181
+ },
182
+ {
183
+ "epoch": 10.0,
184
+ "grad_norm": 0.9364714622497559,
185
+ "learning_rate": 0.0,
186
+ "loss": 0.3784,
187
+ "step": 7660
188
+ },
189
+ {
190
+ "epoch": 10.0,
191
+ "eval_accuracy": 0.8277886497064579,
192
+ "eval_f1": 0.8391224862888481,
193
+ "eval_loss": 0.4185905158519745,
194
+ "eval_precision": 0.7873070325900514,
195
+ "eval_recall": 0.898238747553816,
196
+ "eval_runtime": 131.6081,
197
+ "eval_samples_per_second": 7.765,
198
+ "eval_steps_per_second": 1.945,
199
+ "step": 7660
200
+ }
201
+ ],
202
+ "logging_steps": 500,
203
+ "max_steps": 7660,
204
+ "num_input_tokens_seen": 0,
205
+ "num_train_epochs": 10,
206
+ "save_steps": 500,
207
+ "total_flos": 2356951972800.0,
208
+ "train_batch_size": 4,
209
+ "trial_name": null,
210
+ "trial_params": {
211
+ "alpha": 0.7711149722361785,
212
+ "learning_rate": 0.0001504450686837859,
213
+ "num_train_epochs": 10,
214
+ "temperature": 20
215
+ }
216
+ }
run-21/checkpoint-7660/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeb7ed96b316155249bd80b74449e21f10852ace4b6c7dccc86652bad341ee55
3
+ size 4920
run-21/checkpoint-7660/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-22/checkpoint-766/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-22/checkpoint-766/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8351a2eb5001b9a26f911bf958be7b375a20f49c9f620db249c9ffc8bc4bff36
3
+ size 17549312
run-22/checkpoint-766/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74d72026cbb1ca08cfb07a1767a7f29d67cdf67503786b04a7f4bdecb7b58e7b
3
+ size 35122746
run-22/checkpoint-766/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a29b5a9fab412f426bae759e459d7d9236aab6602ae439ea13f5bd437e1b98a4
3
+ size 14054
run-22/checkpoint-766/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd9f6b405659c4f4d1b73ff2abca324a6af1778d9b0fee02ad26d630f37d6826
3
+ size 1064
run-22/checkpoint-766/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-22/checkpoint-766/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-22/checkpoint-766/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-22/checkpoint-766/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7690802348336595,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-22/checkpoint-766",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 766,
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": 3.696702480316162,
14
+ "learning_rate": 5.5657923048038e-05,
15
+ "loss": 0.5322,
16
+ "step": 766
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7690802348336595,
21
+ "eval_f1": 0.7962003454231433,
22
+ "eval_loss": 0.4672633707523346,
23
+ "eval_precision": 0.7125193199381762,
24
+ "eval_recall": 0.9021526418786693,
25
+ "eval_runtime": 130.6713,
26
+ "eval_samples_per_second": 7.821,
27
+ "eval_steps_per_second": 1.959,
28
+ "step": 766
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 6128,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 8,
35
+ "save_steps": 500,
36
+ "total_flos": 235695197280.0,
37
+ "train_batch_size": 4,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.838703892208557,
41
+ "learning_rate": 6.360905491204343e-05,
42
+ "num_train_epochs": 8,
43
+ "temperature": 22
44
+ }
45
+ }
run-22/checkpoint-766/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cf0be8ae28c43b5c83910e19925f31be35d90d8d2b7695122214bc45f7e5646
3
+ size 4920
run-22/checkpoint-766/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:eeb7ed96b316155249bd80b74449e21f10852ace4b6c7dccc86652bad341ee55
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cf0be8ae28c43b5c83910e19925f31be35d90d8d2b7695122214bc45f7e5646
3
  size 4920