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
f034bed
·
verified ·
1 Parent(s): 3963d38

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1713434952.ec9626078864.14834.1 +2 -2
  2. logs/events.out.tfevents.1713435480.ec9626078864.14834.2 +3 -0
  3. model.safetensors +1 -1
  4. run-0/checkpoint-5805/config.json +34 -0
  5. run-0/checkpoint-5805/model.safetensors +3 -0
  6. run-0/checkpoint-5805/optimizer.pt +3 -0
  7. run-0/checkpoint-5805/rng_state.pth +3 -0
  8. run-0/checkpoint-5805/scheduler.pt +3 -0
  9. run-0/checkpoint-5805/special_tokens_map.json +7 -0
  10. run-0/checkpoint-5805/tokenizer.json +0 -0
  11. run-0/checkpoint-5805/tokenizer_config.json +57 -0
  12. run-0/checkpoint-5805/trainer_state.json +206 -0
  13. run-0/checkpoint-5805/training_args.bin +3 -0
  14. run-0/checkpoint-5805/vocab.txt +0 -0
  15. run-0/checkpoint-6450/config.json +34 -0
  16. run-0/checkpoint-6450/model.safetensors +3 -0
  17. run-0/checkpoint-6450/optimizer.pt +3 -0
  18. run-0/checkpoint-6450/rng_state.pth +3 -0
  19. run-0/checkpoint-6450/scheduler.pt +3 -0
  20. run-0/checkpoint-6450/special_tokens_map.json +7 -0
  21. run-0/checkpoint-6450/tokenizer.json +0 -0
  22. run-0/checkpoint-6450/tokenizer_config.json +57 -0
  23. run-0/checkpoint-6450/trainer_state.json +226 -0
  24. run-0/checkpoint-6450/training_args.bin +3 -0
  25. run-0/checkpoint-6450/vocab.txt +0 -0
  26. run-1/checkpoint-645/config.json +34 -0
  27. run-1/checkpoint-645/model.safetensors +3 -0
  28. run-1/checkpoint-645/optimizer.pt +3 -0
  29. run-1/checkpoint-645/rng_state.pth +3 -0
  30. run-1/checkpoint-645/scheduler.pt +3 -0
  31. run-1/checkpoint-645/special_tokens_map.json +7 -0
  32. run-1/checkpoint-645/tokenizer.json +0 -0
  33. run-1/checkpoint-645/tokenizer_config.json +57 -0
  34. run-1/checkpoint-645/trainer_state.json +46 -0
  35. run-1/checkpoint-645/training_args.bin +3 -0
  36. run-1/checkpoint-645/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1713434952.ec9626078864.14834.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c17566112939021221ead35c829ff6eb88c11c65eed9be656860397679375e12
3
- size 6137
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e284f83da673d22157df4c14aabbb0b3e6e4b07f75c80069eed61c3f8bcf0f91
3
+ size 12331
logs/events.out.tfevents.1713435480.ec9626078864.14834.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2619f9d01adb1896bad2660bddddf61b22ca394babbf4938ac979d5c3eae82b2
3
+ size 5406
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41fdcf897dd6f19339f3c726f5fdcb514dae7efe2b0dbedf9eb0798444f4d649
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fbb044e34c50f617b22cb45890fc7e9b2adeea85c41e0c3ad762670b840335b
3
  size 17549312
run-0/checkpoint-5805/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-0/checkpoint-5805/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4cf3472e01b5876204a630ff84bdc3fac1dd537fbfd1367cc1e9ba243b3d4eb
3
+ size 17549312
run-0/checkpoint-5805/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:808b11f996798051e9f71260c3ec544248bc0010715e3c5d7f2173bcca9f9478
3
+ size 35123898
run-0/checkpoint-5805/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34380163fd6ada55752d4a94e716873dbb1f4d44fd616dbd60f210d142e9143b
3
+ size 14308
run-0/checkpoint-5805/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b22d0af446baaf8bc41619e3d6e6d0d8525fb764a066aad4c58a32e2d4b26272
3
+ size 1064
run-0/checkpoint-5805/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-0/checkpoint-5805/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-5805/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-0/checkpoint-5805/trainer_state.json ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8986041101202016,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-4515",
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5805,
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": 0.770919680595398,
14
+ "learning_rate": 0.00045575725544182215,
15
+ "loss": 0.2361,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8898797983714618,
21
+ "eval_f1": 0.003508771929824561,
22
+ "eval_loss": 0.22947192192077637,
23
+ "eval_mcc": 0.039546160983878816,
24
+ "eval_precision": 1.0,
25
+ "eval_recall": 0.0017574692442882249,
26
+ "eval_runtime": 9.9701,
27
+ "eval_samples_per_second": 517.345,
28
+ "eval_steps_per_second": 16.249,
29
+ "step": 645
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 0.8797195553779602,
34
+ "learning_rate": 0.00040511756039273084,
35
+ "loss": 0.2287,
36
+ "step": 1290
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8896859247770453,
41
+ "eval_f1": 0.0,
42
+ "eval_loss": 0.22863532602787018,
43
+ "eval_mcc": 0.0,
44
+ "eval_precision": 0.0,
45
+ "eval_recall": 0.0,
46
+ "eval_runtime": 10.133,
47
+ "eval_samples_per_second": 509.028,
48
+ "eval_steps_per_second": 15.987,
49
+ "step": 1290
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 0.5287452340126038,
54
+ "learning_rate": 0.0003544778653436394,
55
+ "loss": 0.2263,
56
+ "step": 1935
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.8896859247770453,
61
+ "eval_f1": 0.0,
62
+ "eval_loss": 0.2284112125635147,
63
+ "eval_mcc": 0.0,
64
+ "eval_precision": 0.0,
65
+ "eval_recall": 0.0,
66
+ "eval_runtime": 9.9193,
67
+ "eval_samples_per_second": 519.998,
68
+ "eval_steps_per_second": 16.332,
69
+ "step": 1935
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.02663254737854,
74
+ "learning_rate": 0.0003038381702945481,
75
+ "loss": 0.2233,
76
+ "step": 2580
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.8966653741760372,
81
+ "eval_f1": 0.19607843137254902,
82
+ "eval_loss": 0.2262517362833023,
83
+ "eval_mcc": 0.25274955080099837,
84
+ "eval_precision": 0.6914893617021277,
85
+ "eval_recall": 0.11423550087873462,
86
+ "eval_runtime": 9.9602,
87
+ "eval_samples_per_second": 517.859,
88
+ "eval_steps_per_second": 16.265,
89
+ "step": 2580
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 0.33138540387153625,
94
+ "learning_rate": 0.00025319847524545675,
95
+ "loss": 0.2197,
96
+ "step": 3225
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.8970531213648701,
101
+ "eval_f1": 0.18683001531393567,
102
+ "eval_loss": 0.21906551718711853,
103
+ "eval_mcc": 0.25294386512776135,
104
+ "eval_precision": 0.7261904761904762,
105
+ "eval_recall": 0.10720562390158173,
106
+ "eval_runtime": 9.9303,
107
+ "eval_samples_per_second": 519.421,
108
+ "eval_steps_per_second": 16.314,
109
+ "step": 3225
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 0.3962567448616028,
114
+ "learning_rate": 0.00020255878019636542,
115
+ "loss": 0.2188,
116
+ "step": 3870
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.8968592477704537,
121
+ "eval_f1": 0.1501597444089457,
122
+ "eval_loss": 0.21888957917690277,
123
+ "eval_mcc": 0.24100417515941616,
124
+ "eval_precision": 0.8245614035087719,
125
+ "eval_recall": 0.08260105448154657,
126
+ "eval_runtime": 9.9381,
127
+ "eval_samples_per_second": 519.011,
128
+ "eval_steps_per_second": 16.301,
129
+ "step": 3870
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 0.816288948059082,
134
+ "learning_rate": 0.00015191908514727406,
135
+ "loss": 0.217,
136
+ "step": 4515
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.8986041101202016,
141
+ "eval_f1": 0.20877458396369136,
142
+ "eval_loss": 0.2174820899963379,
143
+ "eval_mcc": 0.27516569645731026,
144
+ "eval_precision": 0.75,
145
+ "eval_recall": 0.12126537785588752,
146
+ "eval_runtime": 9.926,
147
+ "eval_samples_per_second": 519.645,
148
+ "eval_steps_per_second": 16.321,
149
+ "step": 4515
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "grad_norm": 0.9780616760253906,
154
+ "learning_rate": 0.00010127939009818271,
155
+ "loss": 0.2152,
156
+ "step": 5160
157
+ },
158
+ {
159
+ "epoch": 8.0,
160
+ "eval_accuracy": 0.8972469949592865,
161
+ "eval_f1": 0.16927899686520376,
162
+ "eval_loss": 0.2163967788219452,
163
+ "eval_mcc": 0.2498815158419147,
164
+ "eval_precision": 0.782608695652174,
165
+ "eval_recall": 0.09490333919156414,
166
+ "eval_runtime": 9.9496,
167
+ "eval_samples_per_second": 518.41,
168
+ "eval_steps_per_second": 16.282,
169
+ "step": 5160
170
+ },
171
+ {
172
+ "epoch": 9.0,
173
+ "grad_norm": 0.3984989523887634,
174
+ "learning_rate": 5.0639695049091355e-05,
175
+ "loss": 0.2142,
176
+ "step": 5805
177
+ },
178
+ {
179
+ "epoch": 9.0,
180
+ "eval_accuracy": 0.8986041101202016,
181
+ "eval_f1": 0.22288261515601784,
182
+ "eval_loss": 0.21662580966949463,
183
+ "eval_mcc": 0.2797000424158355,
184
+ "eval_precision": 0.7211538461538461,
185
+ "eval_recall": 0.13181019332161686,
186
+ "eval_runtime": 9.9343,
187
+ "eval_samples_per_second": 519.211,
188
+ "eval_steps_per_second": 16.307,
189
+ "step": 5805
190
+ }
191
+ ],
192
+ "logging_steps": 500,
193
+ "max_steps": 6450,
194
+ "num_input_tokens_seen": 0,
195
+ "num_train_epochs": 10,
196
+ "save_steps": 500,
197
+ "total_flos": 14282482793400.0,
198
+ "train_batch_size": 32,
199
+ "trial_name": null,
200
+ "trial_params": {
201
+ "alpha": 0.6185480031675171,
202
+ "learning_rate": 0.0005063969504909135,
203
+ "num_train_epochs": 10,
204
+ "temperature": 26
205
+ }
206
+ }
run-0/checkpoint-5805/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e00b6308354fcc4fbffa0d77653d8e9ff2f79de3d1452d8a8cbff61d75d82cfc
3
+ size 4984
run-0/checkpoint-5805/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-6450/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-0/checkpoint-6450/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdfedc31b5a94f1c670b4d5f094a8cf5bcbd03a4e961b6c6dbca901f9d751295
3
+ size 17549312
run-0/checkpoint-6450/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1553f86de9cb74688c03e63c3066dfb1644e71b365c00577bdf59fb954ad755
3
+ size 35123898
run-0/checkpoint-6450/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:182eb50e24bf6cb5a0779e6036e35eefa649bd68162809f13135143ff5f4ac06
3
+ size 14308
run-0/checkpoint-6450/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f7fcc9234b2468805454086f301f1d84e6ffba7c9236a3e94ce985e893552d9
3
+ size 1064
run-0/checkpoint-6450/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-0/checkpoint-6450/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-6450/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-0/checkpoint-6450/trainer_state.json ADDED
@@ -0,0 +1,226 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8989918573090345,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-6450",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 6450,
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": 0.770919680595398,
14
+ "learning_rate": 0.00045575725544182215,
15
+ "loss": 0.2361,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8898797983714618,
21
+ "eval_f1": 0.003508771929824561,
22
+ "eval_loss": 0.22947192192077637,
23
+ "eval_mcc": 0.039546160983878816,
24
+ "eval_precision": 1.0,
25
+ "eval_recall": 0.0017574692442882249,
26
+ "eval_runtime": 9.9701,
27
+ "eval_samples_per_second": 517.345,
28
+ "eval_steps_per_second": 16.249,
29
+ "step": 645
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 0.8797195553779602,
34
+ "learning_rate": 0.00040511756039273084,
35
+ "loss": 0.2287,
36
+ "step": 1290
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8896859247770453,
41
+ "eval_f1": 0.0,
42
+ "eval_loss": 0.22863532602787018,
43
+ "eval_mcc": 0.0,
44
+ "eval_precision": 0.0,
45
+ "eval_recall": 0.0,
46
+ "eval_runtime": 10.133,
47
+ "eval_samples_per_second": 509.028,
48
+ "eval_steps_per_second": 15.987,
49
+ "step": 1290
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 0.5287452340126038,
54
+ "learning_rate": 0.0003544778653436394,
55
+ "loss": 0.2263,
56
+ "step": 1935
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.8896859247770453,
61
+ "eval_f1": 0.0,
62
+ "eval_loss": 0.2284112125635147,
63
+ "eval_mcc": 0.0,
64
+ "eval_precision": 0.0,
65
+ "eval_recall": 0.0,
66
+ "eval_runtime": 9.9193,
67
+ "eval_samples_per_second": 519.998,
68
+ "eval_steps_per_second": 16.332,
69
+ "step": 1935
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.02663254737854,
74
+ "learning_rate": 0.0003038381702945481,
75
+ "loss": 0.2233,
76
+ "step": 2580
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.8966653741760372,
81
+ "eval_f1": 0.19607843137254902,
82
+ "eval_loss": 0.2262517362833023,
83
+ "eval_mcc": 0.25274955080099837,
84
+ "eval_precision": 0.6914893617021277,
85
+ "eval_recall": 0.11423550087873462,
86
+ "eval_runtime": 9.9602,
87
+ "eval_samples_per_second": 517.859,
88
+ "eval_steps_per_second": 16.265,
89
+ "step": 2580
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 0.33138540387153625,
94
+ "learning_rate": 0.00025319847524545675,
95
+ "loss": 0.2197,
96
+ "step": 3225
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.8970531213648701,
101
+ "eval_f1": 0.18683001531393567,
102
+ "eval_loss": 0.21906551718711853,
103
+ "eval_mcc": 0.25294386512776135,
104
+ "eval_precision": 0.7261904761904762,
105
+ "eval_recall": 0.10720562390158173,
106
+ "eval_runtime": 9.9303,
107
+ "eval_samples_per_second": 519.421,
108
+ "eval_steps_per_second": 16.314,
109
+ "step": 3225
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 0.3962567448616028,
114
+ "learning_rate": 0.00020255878019636542,
115
+ "loss": 0.2188,
116
+ "step": 3870
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.8968592477704537,
121
+ "eval_f1": 0.1501597444089457,
122
+ "eval_loss": 0.21888957917690277,
123
+ "eval_mcc": 0.24100417515941616,
124
+ "eval_precision": 0.8245614035087719,
125
+ "eval_recall": 0.08260105448154657,
126
+ "eval_runtime": 9.9381,
127
+ "eval_samples_per_second": 519.011,
128
+ "eval_steps_per_second": 16.301,
129
+ "step": 3870
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 0.816288948059082,
134
+ "learning_rate": 0.00015191908514727406,
135
+ "loss": 0.217,
136
+ "step": 4515
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.8986041101202016,
141
+ "eval_f1": 0.20877458396369136,
142
+ "eval_loss": 0.2174820899963379,
143
+ "eval_mcc": 0.27516569645731026,
144
+ "eval_precision": 0.75,
145
+ "eval_recall": 0.12126537785588752,
146
+ "eval_runtime": 9.926,
147
+ "eval_samples_per_second": 519.645,
148
+ "eval_steps_per_second": 16.321,
149
+ "step": 4515
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "grad_norm": 0.9780616760253906,
154
+ "learning_rate": 0.00010127939009818271,
155
+ "loss": 0.2152,
156
+ "step": 5160
157
+ },
158
+ {
159
+ "epoch": 8.0,
160
+ "eval_accuracy": 0.8972469949592865,
161
+ "eval_f1": 0.16927899686520376,
162
+ "eval_loss": 0.2163967788219452,
163
+ "eval_mcc": 0.2498815158419147,
164
+ "eval_precision": 0.782608695652174,
165
+ "eval_recall": 0.09490333919156414,
166
+ "eval_runtime": 9.9496,
167
+ "eval_samples_per_second": 518.41,
168
+ "eval_steps_per_second": 16.282,
169
+ "step": 5160
170
+ },
171
+ {
172
+ "epoch": 9.0,
173
+ "grad_norm": 0.3984989523887634,
174
+ "learning_rate": 5.0639695049091355e-05,
175
+ "loss": 0.2142,
176
+ "step": 5805
177
+ },
178
+ {
179
+ "epoch": 9.0,
180
+ "eval_accuracy": 0.8986041101202016,
181
+ "eval_f1": 0.22288261515601784,
182
+ "eval_loss": 0.21662580966949463,
183
+ "eval_mcc": 0.2797000424158355,
184
+ "eval_precision": 0.7211538461538461,
185
+ "eval_recall": 0.13181019332161686,
186
+ "eval_runtime": 9.9343,
187
+ "eval_samples_per_second": 519.211,
188
+ "eval_steps_per_second": 16.307,
189
+ "step": 5805
190
+ },
191
+ {
192
+ "epoch": 10.0,
193
+ "grad_norm": 0.5117802023887634,
194
+ "learning_rate": 0.0,
195
+ "loss": 0.2133,
196
+ "step": 6450
197
+ },
198
+ {
199
+ "epoch": 10.0,
200
+ "eval_accuracy": 0.8989918573090345,
201
+ "eval_f1": 0.21654135338345867,
202
+ "eval_loss": 0.21611623466014862,
203
+ "eval_mcc": 0.2811949499154691,
204
+ "eval_precision": 0.75,
205
+ "eval_recall": 0.1265377855887522,
206
+ "eval_runtime": 9.9337,
207
+ "eval_samples_per_second": 519.243,
208
+ "eval_steps_per_second": 16.308,
209
+ "step": 6450
210
+ }
211
+ ],
212
+ "logging_steps": 500,
213
+ "max_steps": 6450,
214
+ "num_input_tokens_seen": 0,
215
+ "num_train_epochs": 10,
216
+ "save_steps": 500,
217
+ "total_flos": 15869425326000.0,
218
+ "train_batch_size": 32,
219
+ "trial_name": null,
220
+ "trial_params": {
221
+ "alpha": 0.6185480031675171,
222
+ "learning_rate": 0.0005063969504909135,
223
+ "num_train_epochs": 10,
224
+ "temperature": 26
225
+ }
226
+ }
run-0/checkpoint-6450/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e00b6308354fcc4fbffa0d77653d8e9ff2f79de3d1452d8a8cbff61d75d82cfc
3
+ size 4984
run-0/checkpoint-6450/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-645/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-1/checkpoint-645/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fbb044e34c50f617b22cb45890fc7e9b2adeea85c41e0c3ad762670b840335b
3
+ size 17549312
run-1/checkpoint-645/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:138ce24c5ee125c85b6912d99b880d524e4ed3ad1ec0a96e5657ee4c0e59211e
3
+ size 35123898
run-1/checkpoint-645/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f64cda8af0c2d214cf65bdf171fde38f18025a5a08f9a451c61fdf726867d7c2
3
+ size 14308
run-1/checkpoint-645/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbf8cfa1dd6917e7fe24c75f029b833ab0c37660f9cb68b212fd1b929fe1abe5
3
+ size 1064
run-1/checkpoint-645/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-645/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-645/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-645/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8892981775882125,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-645",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 645,
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": 0.8288795948028564,
14
+ "learning_rate": 0.0001908740631878717,
15
+ "loss": 0.3032,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8892981775882125,
21
+ "eval_f1": 0.12557427258805512,
22
+ "eval_loss": 0.29040220379829407,
23
+ "eval_mcc": 0.15515682588139135,
24
+ "eval_precision": 0.4880952380952381,
25
+ "eval_recall": 0.07205623901581722,
26
+ "eval_runtime": 9.95,
27
+ "eval_samples_per_second": 518.391,
28
+ "eval_steps_per_second": 16.281,
29
+ "step": 645
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 1935,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 3,
36
+ "save_steps": 500,
37
+ "total_flos": 1586942532600.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.8638056037769629,
42
+ "learning_rate": 0.0002863110947818076,
43
+ "num_train_epochs": 3,
44
+ "temperature": 11
45
+ }
46
+ }
run-1/checkpoint-645/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce98fa442c340f2adff4e1c65554f6839e9ff8c67f1a36d5cc21a06f170066fc
3
+ size 4984
run-1/checkpoint-645/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:e00b6308354fcc4fbffa0d77653d8e9ff2f79de3d1452d8a8cbff61d75d82cfc
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce98fa442c340f2adff4e1c65554f6839e9ff8c67f1a36d5cc21a06f170066fc
3
  size 4984