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
d96555d
·
verified ·
1 Parent(s): 4ad32ca

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1709746083.1dcff7455174.7719.19 +2 -2
  2. logs/events.out.tfevents.1709747080.1dcff7455174.7719.20 +3 -0
  3. model.safetensors +1 -1
  4. run-19/checkpoint-864/config.json +34 -0
  5. run-19/checkpoint-864/model.safetensors +3 -0
  6. run-19/checkpoint-864/optimizer.pt +3 -0
  7. run-19/checkpoint-864/rng_state.pth +3 -0
  8. run-19/checkpoint-864/scheduler.pt +3 -0
  9. run-19/checkpoint-864/special_tokens_map.json +7 -0
  10. run-19/checkpoint-864/tokenizer.json +0 -0
  11. run-19/checkpoint-864/tokenizer_config.json +57 -0
  12. run-19/checkpoint-864/trainer_state.json +197 -0
  13. run-19/checkpoint-864/training_args.bin +3 -0
  14. run-19/checkpoint-864/vocab.txt +0 -0
  15. run-19/checkpoint-960/config.json +34 -0
  16. run-19/checkpoint-960/model.safetensors +3 -0
  17. run-19/checkpoint-960/optimizer.pt +3 -0
  18. run-19/checkpoint-960/rng_state.pth +3 -0
  19. run-19/checkpoint-960/scheduler.pt +3 -0
  20. run-19/checkpoint-960/special_tokens_map.json +7 -0
  21. run-19/checkpoint-960/tokenizer.json +0 -0
  22. run-19/checkpoint-960/tokenizer_config.json +57 -0
  23. run-19/checkpoint-960/trainer_state.json +216 -0
  24. run-19/checkpoint-960/training_args.bin +3 -0
  25. run-19/checkpoint-960/vocab.txt +0 -0
  26. run-20/checkpoint-96/config.json +34 -0
  27. run-20/checkpoint-96/model.safetensors +3 -0
  28. run-20/checkpoint-96/optimizer.pt +3 -0
  29. run-20/checkpoint-96/rng_state.pth +3 -0
  30. run-20/checkpoint-96/scheduler.pt +3 -0
  31. run-20/checkpoint-96/special_tokens_map.json +7 -0
  32. run-20/checkpoint-96/tokenizer.json +0 -0
  33. run-20/checkpoint-96/tokenizer_config.json +57 -0
  34. run-20/checkpoint-96/trainer_state.json +45 -0
  35. run-20/checkpoint-96/training_args.bin +3 -0
  36. run-20/checkpoint-96/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1709746083.1dcff7455174.7719.19 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18b3b618dffe475fc66abdca6f7fca93a96c45ba45db832e75d1659fbf3cf13c
3
- size 5999
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b5bb948900b22edbc872349d0811dc0f89b767024e955a7cddfbc93e726cca
3
+ size 11817
logs/events.out.tfevents.1709747080.1dcff7455174.7719.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f545c331a42c4d6b767ed2e2c0eb1b07daacf56a7d2ad0ed35b289c769ef350
3
+ size 5315
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1ae99479f844e3d5c0330ffce135ff0c0adcd53da25d99bf2a8b922d2f2ea41
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb816014d21e58d0c0648cca41f343b54b9f7ec0cc268405a0e9f1c3082ba859
3
  size 17549312
run-19/checkpoint-864/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-19/checkpoint-864/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:074ff971e9ef09a44740d6477bccfa6332447b1f0bd11e7256df2f8431f6137a
3
+ size 17549312
run-19/checkpoint-864/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b55c1e927ad96bf296c71f58362552ee6e47b9cb83ef513a3f6317a6877af71d
3
+ size 35122746
run-19/checkpoint-864/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97d9a51ee84ffde410aa6ee4faf7cd8373bce5e285d974fd9648694f2208055b
3
+ size 14054
run-19/checkpoint-864/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddecf1e9635cd8bedfc3c7294c339311a62fee11ac67f838c471cb1eb3503659
3
+ size 1064
run-19/checkpoint-864/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-19/checkpoint-864/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-19/checkpoint-864/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-19/checkpoint-864/trainer_state.json ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8365949119373777,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-19/checkpoint-864",
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 864,
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": 3.265742301940918,
14
+ "learning_rate": 0.00016552182978108178,
15
+ "loss": 0.5708,
16
+ "step": 96
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7592954990215264,
21
+ "eval_f1": 0.7980295566502462,
22
+ "eval_loss": 0.4895075857639313,
23
+ "eval_precision": 0.6874115983026874,
24
+ "eval_recall": 0.9510763209393346,
25
+ "eval_runtime": 24.8356,
26
+ "eval_samples_per_second": 41.151,
27
+ "eval_steps_per_second": 1.288,
28
+ "step": 96
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 4.506702899932861,
33
+ "learning_rate": 0.00014713051536096157,
34
+ "loss": 0.4657,
35
+ "step": 192
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.812133072407045,
40
+ "eval_f1": 0.8318739054290717,
41
+ "eval_loss": 0.42986905574798584,
42
+ "eval_precision": 0.7527733755942948,
43
+ "eval_recall": 0.9295499021526419,
44
+ "eval_runtime": 25.1401,
45
+ "eval_samples_per_second": 40.652,
46
+ "eval_steps_per_second": 1.273,
47
+ "step": 192
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 2.952416181564331,
52
+ "learning_rate": 0.00012873920094084136,
53
+ "loss": 0.4303,
54
+ "step": 288
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8209393346379648,
59
+ "eval_f1": 0.8300835654596102,
60
+ "eval_loss": 0.42889997363090515,
61
+ "eval_precision": 0.7897526501766784,
62
+ "eval_recall": 0.8747553816046967,
63
+ "eval_runtime": 25.3264,
64
+ "eval_samples_per_second": 40.353,
65
+ "eval_steps_per_second": 1.264,
66
+ "step": 288
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 7.971947193145752,
71
+ "learning_rate": 0.00011034788652072118,
72
+ "loss": 0.4148,
73
+ "step": 384
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.815068493150685,
78
+ "eval_f1": 0.8156097560975609,
79
+ "eval_loss": 0.4303808808326721,
80
+ "eval_precision": 0.8132295719844358,
81
+ "eval_recall": 0.8180039138943248,
82
+ "eval_runtime": 25.4322,
83
+ "eval_samples_per_second": 40.185,
84
+ "eval_steps_per_second": 1.258,
85
+ "step": 384
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 1.9225187301635742,
90
+ "learning_rate": 9.195657210060098e-05,
91
+ "loss": 0.4076,
92
+ "step": 480
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.8277886497064579,
97
+ "eval_f1": 0.8414414414414414,
98
+ "eval_loss": 0.40675535798072815,
99
+ "eval_precision": 0.7796327212020033,
100
+ "eval_recall": 0.913894324853229,
101
+ "eval_runtime": 25.6271,
102
+ "eval_samples_per_second": 39.88,
103
+ "eval_steps_per_second": 1.249,
104
+ "step": 480
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "grad_norm": 4.180634498596191,
109
+ "learning_rate": 7.356525768048079e-05,
110
+ "loss": 0.4009,
111
+ "step": 576
112
+ },
113
+ {
114
+ "epoch": 6.0,
115
+ "eval_accuracy": 0.8238747553816047,
116
+ "eval_f1": 0.8432055749128919,
117
+ "eval_loss": 0.4179611802101135,
118
+ "eval_precision": 0.7598116169544741,
119
+ "eval_recall": 0.9471624266144814,
120
+ "eval_runtime": 25.4907,
121
+ "eval_samples_per_second": 40.093,
122
+ "eval_steps_per_second": 1.255,
123
+ "step": 576
124
+ },
125
+ {
126
+ "epoch": 7.0,
127
+ "grad_norm": 3.1518468856811523,
128
+ "learning_rate": 5.517394326036059e-05,
129
+ "loss": 0.3956,
130
+ "step": 672
131
+ },
132
+ {
133
+ "epoch": 7.0,
134
+ "eval_accuracy": 0.8268101761252447,
135
+ "eval_f1": 0.8456843940714908,
136
+ "eval_loss": 0.412363737821579,
137
+ "eval_precision": 0.7625786163522013,
138
+ "eval_recall": 0.949119373776908,
139
+ "eval_runtime": 25.9899,
140
+ "eval_samples_per_second": 39.323,
141
+ "eval_steps_per_second": 1.231,
142
+ "step": 672
143
+ },
144
+ {
145
+ "epoch": 8.0,
146
+ "grad_norm": 3.885427236557007,
147
+ "learning_rate": 3.678262884024039e-05,
148
+ "loss": 0.3914,
149
+ "step": 768
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "eval_accuracy": 0.8287671232876712,
154
+ "eval_f1": 0.8466257668711656,
155
+ "eval_loss": 0.4102531671524048,
156
+ "eval_precision": 0.7666666666666667,
157
+ "eval_recall": 0.9452054794520548,
158
+ "eval_runtime": 25.478,
159
+ "eval_samples_per_second": 40.113,
160
+ "eval_steps_per_second": 1.256,
161
+ "step": 768
162
+ },
163
+ {
164
+ "epoch": 9.0,
165
+ "grad_norm": 2.2045633792877197,
166
+ "learning_rate": 1.8391314420120196e-05,
167
+ "loss": 0.3868,
168
+ "step": 864
169
+ },
170
+ {
171
+ "epoch": 9.0,
172
+ "eval_accuracy": 0.8365949119373777,
173
+ "eval_f1": 0.8460829493087557,
174
+ "eval_loss": 0.4009145498275757,
175
+ "eval_precision": 0.7996515679442509,
176
+ "eval_recall": 0.898238747553816,
177
+ "eval_runtime": 24.6734,
178
+ "eval_samples_per_second": 41.421,
179
+ "eval_steps_per_second": 1.297,
180
+ "step": 864
181
+ }
182
+ ],
183
+ "logging_steps": 500,
184
+ "max_steps": 960,
185
+ "num_input_tokens_seen": 0,
186
+ "num_train_epochs": 10,
187
+ "save_steps": 500,
188
+ "total_flos": 2121256775520.0,
189
+ "train_batch_size": 32,
190
+ "trial_name": null,
191
+ "trial_params": {
192
+ "alpha": 0.8822091648395545,
193
+ "learning_rate": 0.00018391314420120196,
194
+ "num_train_epochs": 10,
195
+ "temperature": 8
196
+ }
197
+ }
run-19/checkpoint-864/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e3bbdb4e3659e78e11bd3dd728828bd0d60a7b872ca6afbd011a6c807e9f19d
3
+ size 4920
run-19/checkpoint-864/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-19/checkpoint-960/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-19/checkpoint-960/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11569e1900e4a92139c4aca589a288f822e6695dab6578719e90ed6717984db5
3
+ size 17549312
run-19/checkpoint-960/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b19b0b38cb0cf512d0d2cdbd4da40ec346468d578679fef8a46bc9c25cac4d5
3
+ size 35122746
run-19/checkpoint-960/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bc70fadfc325a9e3454d9d9f633805a30a7b6edb6e2dafe2e6da349874f75d0
3
+ size 14054
run-19/checkpoint-960/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fb6ef27a00444d88526f4ef9d8d6c53f951cab058afbbd5a7670d206c87a397
3
+ size 1064
run-19/checkpoint-960/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-19/checkpoint-960/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-19/checkpoint-960/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-19/checkpoint-960/trainer_state.json ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8395303326810176,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-19/checkpoint-960",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 960,
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": 3.265742301940918,
14
+ "learning_rate": 0.00016552182978108178,
15
+ "loss": 0.5708,
16
+ "step": 96
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7592954990215264,
21
+ "eval_f1": 0.7980295566502462,
22
+ "eval_loss": 0.4895075857639313,
23
+ "eval_precision": 0.6874115983026874,
24
+ "eval_recall": 0.9510763209393346,
25
+ "eval_runtime": 24.8356,
26
+ "eval_samples_per_second": 41.151,
27
+ "eval_steps_per_second": 1.288,
28
+ "step": 96
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 4.506702899932861,
33
+ "learning_rate": 0.00014713051536096157,
34
+ "loss": 0.4657,
35
+ "step": 192
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.812133072407045,
40
+ "eval_f1": 0.8318739054290717,
41
+ "eval_loss": 0.42986905574798584,
42
+ "eval_precision": 0.7527733755942948,
43
+ "eval_recall": 0.9295499021526419,
44
+ "eval_runtime": 25.1401,
45
+ "eval_samples_per_second": 40.652,
46
+ "eval_steps_per_second": 1.273,
47
+ "step": 192
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 2.952416181564331,
52
+ "learning_rate": 0.00012873920094084136,
53
+ "loss": 0.4303,
54
+ "step": 288
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8209393346379648,
59
+ "eval_f1": 0.8300835654596102,
60
+ "eval_loss": 0.42889997363090515,
61
+ "eval_precision": 0.7897526501766784,
62
+ "eval_recall": 0.8747553816046967,
63
+ "eval_runtime": 25.3264,
64
+ "eval_samples_per_second": 40.353,
65
+ "eval_steps_per_second": 1.264,
66
+ "step": 288
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 7.971947193145752,
71
+ "learning_rate": 0.00011034788652072118,
72
+ "loss": 0.4148,
73
+ "step": 384
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.815068493150685,
78
+ "eval_f1": 0.8156097560975609,
79
+ "eval_loss": 0.4303808808326721,
80
+ "eval_precision": 0.8132295719844358,
81
+ "eval_recall": 0.8180039138943248,
82
+ "eval_runtime": 25.4322,
83
+ "eval_samples_per_second": 40.185,
84
+ "eval_steps_per_second": 1.258,
85
+ "step": 384
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 1.9225187301635742,
90
+ "learning_rate": 9.195657210060098e-05,
91
+ "loss": 0.4076,
92
+ "step": 480
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.8277886497064579,
97
+ "eval_f1": 0.8414414414414414,
98
+ "eval_loss": 0.40675535798072815,
99
+ "eval_precision": 0.7796327212020033,
100
+ "eval_recall": 0.913894324853229,
101
+ "eval_runtime": 25.6271,
102
+ "eval_samples_per_second": 39.88,
103
+ "eval_steps_per_second": 1.249,
104
+ "step": 480
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "grad_norm": 4.180634498596191,
109
+ "learning_rate": 7.356525768048079e-05,
110
+ "loss": 0.4009,
111
+ "step": 576
112
+ },
113
+ {
114
+ "epoch": 6.0,
115
+ "eval_accuracy": 0.8238747553816047,
116
+ "eval_f1": 0.8432055749128919,
117
+ "eval_loss": 0.4179611802101135,
118
+ "eval_precision": 0.7598116169544741,
119
+ "eval_recall": 0.9471624266144814,
120
+ "eval_runtime": 25.4907,
121
+ "eval_samples_per_second": 40.093,
122
+ "eval_steps_per_second": 1.255,
123
+ "step": 576
124
+ },
125
+ {
126
+ "epoch": 7.0,
127
+ "grad_norm": 3.1518468856811523,
128
+ "learning_rate": 5.517394326036059e-05,
129
+ "loss": 0.3956,
130
+ "step": 672
131
+ },
132
+ {
133
+ "epoch": 7.0,
134
+ "eval_accuracy": 0.8268101761252447,
135
+ "eval_f1": 0.8456843940714908,
136
+ "eval_loss": 0.412363737821579,
137
+ "eval_precision": 0.7625786163522013,
138
+ "eval_recall": 0.949119373776908,
139
+ "eval_runtime": 25.9899,
140
+ "eval_samples_per_second": 39.323,
141
+ "eval_steps_per_second": 1.231,
142
+ "step": 672
143
+ },
144
+ {
145
+ "epoch": 8.0,
146
+ "grad_norm": 3.885427236557007,
147
+ "learning_rate": 3.678262884024039e-05,
148
+ "loss": 0.3914,
149
+ "step": 768
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "eval_accuracy": 0.8287671232876712,
154
+ "eval_f1": 0.8466257668711656,
155
+ "eval_loss": 0.4102531671524048,
156
+ "eval_precision": 0.7666666666666667,
157
+ "eval_recall": 0.9452054794520548,
158
+ "eval_runtime": 25.478,
159
+ "eval_samples_per_second": 40.113,
160
+ "eval_steps_per_second": 1.256,
161
+ "step": 768
162
+ },
163
+ {
164
+ "epoch": 9.0,
165
+ "grad_norm": 2.2045633792877197,
166
+ "learning_rate": 1.8391314420120196e-05,
167
+ "loss": 0.3868,
168
+ "step": 864
169
+ },
170
+ {
171
+ "epoch": 9.0,
172
+ "eval_accuracy": 0.8365949119373777,
173
+ "eval_f1": 0.8460829493087557,
174
+ "eval_loss": 0.4009145498275757,
175
+ "eval_precision": 0.7996515679442509,
176
+ "eval_recall": 0.898238747553816,
177
+ "eval_runtime": 24.6734,
178
+ "eval_samples_per_second": 41.421,
179
+ "eval_steps_per_second": 1.297,
180
+ "step": 864
181
+ },
182
+ {
183
+ "epoch": 10.0,
184
+ "grad_norm": 4.398197650909424,
185
+ "learning_rate": 0.0,
186
+ "loss": 0.3889,
187
+ "step": 960
188
+ },
189
+ {
190
+ "epoch": 10.0,
191
+ "eval_accuracy": 0.8395303326810176,
192
+ "eval_f1": 0.8509090909090908,
193
+ "eval_loss": 0.3997047245502472,
194
+ "eval_precision": 0.7945670628183361,
195
+ "eval_recall": 0.9158512720156555,
196
+ "eval_runtime": 25.0131,
197
+ "eval_samples_per_second": 40.859,
198
+ "eval_steps_per_second": 1.279,
199
+ "step": 960
200
+ }
201
+ ],
202
+ "logging_steps": 500,
203
+ "max_steps": 960,
204
+ "num_input_tokens_seen": 0,
205
+ "num_train_epochs": 10,
206
+ "save_steps": 500,
207
+ "total_flos": 2356951972800.0,
208
+ "train_batch_size": 32,
209
+ "trial_name": null,
210
+ "trial_params": {
211
+ "alpha": 0.8822091648395545,
212
+ "learning_rate": 0.00018391314420120196,
213
+ "num_train_epochs": 10,
214
+ "temperature": 8
215
+ }
216
+ }
run-19/checkpoint-960/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e3bbdb4e3659e78e11bd3dd728828bd0d60a7b872ca6afbd011a6c807e9f19d
3
+ size 4920
run-19/checkpoint-960/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-20/checkpoint-96/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-20/checkpoint-96/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb816014d21e58d0c0648cca41f343b54b9f7ec0cc268405a0e9f1c3082ba859
3
+ size 17549312
run-20/checkpoint-96/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85fb8853d04893a02287bb2049446fe855e7b4878bace3073529fcb2396dc26
3
+ size 35122746
run-20/checkpoint-96/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24aa86019b8aea1c551cc1adaf38c4db2fc01de75a22af312230f6b592e0fd81
3
+ size 14054
run-20/checkpoint-96/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c7235ac6a7a285a991139c952e4af8c06f528a6ccf0ba06997dab75875dc302
3
+ size 1064
run-20/checkpoint-96/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-20/checkpoint-96/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-20/checkpoint-96/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-20/checkpoint-96/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7671232876712328,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-20/checkpoint-96",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 96,
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": 3.3483004570007324,
14
+ "learning_rate": 0.00013855533928571864,
15
+ "loss": 0.5685,
16
+ "step": 96
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7671232876712328,
21
+ "eval_f1": 0.8019966722129783,
22
+ "eval_loss": 0.477300226688385,
23
+ "eval_precision": 0.6975397973950795,
24
+ "eval_recall": 0.9432485322896281,
25
+ "eval_runtime": 25.843,
26
+ "eval_samples_per_second": 39.546,
27
+ "eval_steps_per_second": 1.238,
28
+ "step": 96
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 672,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 7,
35
+ "save_steps": 500,
36
+ "total_flos": 235695197280.0,
37
+ "train_batch_size": 32,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.8907547983808969,
41
+ "learning_rate": 0.00016164789583333842,
42
+ "num_train_epochs": 7,
43
+ "temperature": 2
44
+ }
45
+ }
run-20/checkpoint-96/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46842c009f41275debcdf9292fb95a9ae38904afa21579baac9749258a827744
3
+ size 4920
run-20/checkpoint-96/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 sha256:853b9bd91d8e7500b2e68ab85992695ef180b9f0e29125c26ec58713c7d0700a
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46842c009f41275debcdf9292fb95a9ae38904afa21579baac9749258a827744
3
  size 4920