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
809f9a7
·
verified ·
1 Parent(s): e7b5ed8

Training in progress, epoch 1

Browse files
Files changed (39) hide show
  1. logs/events.out.tfevents.1711298612.8cc2eef2edb7.2942.28 +2 -2
  2. logs/events.out.tfevents.1711298769.8cc2eef2edb7.2942.29 +3 -0
  3. logs/events.out.tfevents.1711298789.8cc2eef2edb7.2942.30 +3 -0
  4. logs/events.out.tfevents.1711298809.8cc2eef2edb7.2942.31 +3 -0
  5. model.safetensors +1 -1
  6. run-28/checkpoint-2079/config.json +34 -0
  7. run-28/checkpoint-2079/model.safetensors +3 -0
  8. run-28/checkpoint-2079/optimizer.pt +3 -0
  9. run-28/checkpoint-2079/rng_state.pth +3 -0
  10. run-28/checkpoint-2079/scheduler.pt +3 -0
  11. run-28/checkpoint-2079/special_tokens_map.json +7 -0
  12. run-28/checkpoint-2079/tokenizer.json +0 -0
  13. run-28/checkpoint-2079/tokenizer_config.json +57 -0
  14. run-28/checkpoint-2079/trainer_state.json +166 -0
  15. run-28/checkpoint-2079/training_args.bin +3 -0
  16. run-28/checkpoint-2079/vocab.txt +0 -0
  17. run-28/checkpoint-2376/config.json +34 -0
  18. run-28/checkpoint-2376/model.safetensors +3 -0
  19. run-28/checkpoint-2376/optimizer.pt +3 -0
  20. run-28/checkpoint-2376/rng_state.pth +3 -0
  21. run-28/checkpoint-2376/scheduler.pt +3 -0
  22. run-28/checkpoint-2376/special_tokens_map.json +7 -0
  23. run-28/checkpoint-2376/tokenizer.json +0 -0
  24. run-28/checkpoint-2376/tokenizer_config.json +57 -0
  25. run-28/checkpoint-2376/trainer_state.json +186 -0
  26. run-28/checkpoint-2376/training_args.bin +3 -0
  27. run-28/checkpoint-2376/vocab.txt +0 -0
  28. run-31/checkpoint-297/config.json +34 -0
  29. run-31/checkpoint-297/model.safetensors +3 -0
  30. run-31/checkpoint-297/optimizer.pt +3 -0
  31. run-31/checkpoint-297/rng_state.pth +3 -0
  32. run-31/checkpoint-297/scheduler.pt +3 -0
  33. run-31/checkpoint-297/special_tokens_map.json +7 -0
  34. run-31/checkpoint-297/tokenizer.json +0 -0
  35. run-31/checkpoint-297/tokenizer_config.json +57 -0
  36. run-31/checkpoint-297/trainer_state.json +46 -0
  37. run-31/checkpoint-297/training_args.bin +3 -0
  38. run-31/checkpoint-297/vocab.txt +0 -0
  39. training_args.bin +2 -2
logs/events.out.tfevents.1711298612.8cc2eef2edb7.2942.28 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64417d566ba6b4b7914865c2d5b75cd0c391f80e5be951dc1957986cb91064b5
3
- size 6136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d382b04d7935fa38f4c5a9bbdf9815867f00b4824e159390d92c4c8a67ec2d69
3
+ size 10870
logs/events.out.tfevents.1711298769.8cc2eef2edb7.2942.29 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac8474c479711bc5e37aa2120587cde4b1e7952fcb95318489d1e4f2b96b5cf0
3
+ size 5406
logs/events.out.tfevents.1711298789.8cc2eef2edb7.2942.30 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6117b88a0813fad0eb155158baa78751d1b142bf20482d85e19d06b9a11c2f3
3
+ size 5405
logs/events.out.tfevents.1711298809.8cc2eef2edb7.2942.31 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:073d9430f1c3a7af3e564528d24d7f6bafaba7a0845f60f91708c1bdbc955487
3
+ size 5407
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dca4c3b1be06dfb542a7011ce28be0c2ff7b2999e48959449b5ad02505b6a3ce
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:415d3a0921bca21b9159b1590cca6ea25fafeaed2e8b692daf129d2b0219207c
3
  size 17549312
run-28/checkpoint-2079/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": "4.39.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-28/checkpoint-2079/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b9caad76fdec47ae42d81ffdbc857717bfcb1ba918c1a19cfd5d574ce8c80c0
3
+ size 17549312
run-28/checkpoint-2079/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c962b048925ec09aa7a37ab0cbb7d3ae62902e9bc4e9e4200e1b57b1f376595c
3
+ size 35123898
run-28/checkpoint-2079/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cb1e97db59d008285d4798ce62e5afec1cdcb1f6d8dc6abd815daafb111f5ec
3
+ size 14308
run-28/checkpoint-2079/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85d3490a5ae963474da69a33e091af1af3997dbfafe7860b5cf6ef18be82535a
3
+ size 1064
run-28/checkpoint-2079/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-28/checkpoint-2079/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-28/checkpoint-2079/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-28/checkpoint-2079/trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7089108910891089,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-28/checkpoint-1782",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2079,
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": 1.3590941429138184,
14
+ "learning_rate": 0.00033268893750406807,
15
+ "loss": 0.6415,
16
+ "step": 297
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5861386138613861,
21
+ "eval_f1": 0.473551637279597,
22
+ "eval_loss": 0.6401379108428955,
23
+ "eval_mcc": 0.1894629867942258,
24
+ "eval_precision": 0.6482758620689655,
25
+ "eval_recall": 0.373015873015873,
26
+ "eval_runtime": 0.9371,
27
+ "eval_samples_per_second": 538.913,
28
+ "eval_steps_per_second": 17.074,
29
+ "step": 297
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.476292848587036,
34
+ "learning_rate": 0.00028516194643205835,
35
+ "loss": 0.613,
36
+ "step": 594
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6514851485148515,
41
+ "eval_f1": 0.68,
42
+ "eval_loss": 0.5918833017349243,
43
+ "eval_mcc": 0.30837572082433856,
44
+ "eval_precision": 0.62751677852349,
45
+ "eval_recall": 0.7420634920634921,
46
+ "eval_runtime": 0.9445,
47
+ "eval_samples_per_second": 534.7,
48
+ "eval_steps_per_second": 16.941,
49
+ "step": 594
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.6527726650238037,
54
+ "learning_rate": 0.0002376349553600486,
55
+ "loss": 0.5836,
56
+ "step": 891
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.6594059405940594,
61
+ "eval_f1": 0.693950177935943,
62
+ "eval_loss": 0.5902799367904663,
63
+ "eval_mcc": 0.3278781101029775,
64
+ "eval_precision": 0.6290322580645161,
65
+ "eval_recall": 0.7738095238095238,
66
+ "eval_runtime": 0.9292,
67
+ "eval_samples_per_second": 543.474,
68
+ "eval_steps_per_second": 17.219,
69
+ "step": 891
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.4662635326385498,
74
+ "learning_rate": 0.0001901079642880389,
75
+ "loss": 0.5692,
76
+ "step": 1188
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6613861386138614,
81
+ "eval_f1": 0.6994727592267135,
82
+ "eval_loss": 0.5874853730201721,
83
+ "eval_mcc": 0.33437205674458564,
84
+ "eval_precision": 0.6277602523659306,
85
+ "eval_recall": 0.7896825396825397,
86
+ "eval_runtime": 0.9276,
87
+ "eval_samples_per_second": 544.403,
88
+ "eval_steps_per_second": 17.248,
89
+ "step": 1188
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 2.2937889099121094,
94
+ "learning_rate": 0.00014258097321602918,
95
+ "loss": 0.5565,
96
+ "step": 1485
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.6712871287128713,
101
+ "eval_f1": 0.6844106463878327,
102
+ "eval_loss": 0.5748322010040283,
103
+ "eval_mcc": 0.34399282923991964,
104
+ "eval_precision": 0.656934306569343,
105
+ "eval_recall": 0.7142857142857143,
106
+ "eval_runtime": 0.9341,
107
+ "eval_samples_per_second": 540.619,
108
+ "eval_steps_per_second": 17.129,
109
+ "step": 1485
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 2.6975440979003906,
114
+ "learning_rate": 9.505398214401945e-05,
115
+ "loss": 0.5445,
116
+ "step": 1782
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.7089108910891089,
121
+ "eval_f1": 0.7379679144385027,
122
+ "eval_loss": 0.5586543083190918,
123
+ "eval_mcc": 0.4291472704190268,
124
+ "eval_precision": 0.6699029126213593,
125
+ "eval_recall": 0.8214285714285714,
126
+ "eval_runtime": 0.932,
127
+ "eval_samples_per_second": 541.831,
128
+ "eval_steps_per_second": 17.167,
129
+ "step": 1782
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 3.01635479927063,
134
+ "learning_rate": 4.752699107200972e-05,
135
+ "loss": 0.5314,
136
+ "step": 2079
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.7069306930693069,
141
+ "eval_f1": 0.7279411764705882,
142
+ "eval_loss": 0.5484515428543091,
143
+ "eval_mcc": 0.419334756687555,
144
+ "eval_precision": 0.678082191780822,
145
+ "eval_recall": 0.7857142857142857,
146
+ "eval_runtime": 0.937,
147
+ "eval_samples_per_second": 538.933,
148
+ "eval_steps_per_second": 17.075,
149
+ "step": 2079
150
+ }
151
+ ],
152
+ "logging_steps": 500,
153
+ "max_steps": 2376,
154
+ "num_input_tokens_seen": 0,
155
+ "num_train_epochs": 8,
156
+ "save_steps": 500,
157
+ "total_flos": 5114908861860.0,
158
+ "train_batch_size": 32,
159
+ "trial_name": null,
160
+ "trial_params": {
161
+ "alpha": 0.9092941270097592,
162
+ "learning_rate": 0.0003802159285760778,
163
+ "num_train_epochs": 8,
164
+ "temperature": 11
165
+ }
166
+ }
run-28/checkpoint-2079/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71bb8fa8d66b34ebd7e14a9356f6426aa55d1b931f391a77c3b0cb47e80b8b88
3
+ size 4920
run-28/checkpoint-2079/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-28/checkpoint-2376/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": "4.39.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-28/checkpoint-2376/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d503c228d7104d4da203ee6b738561f3b13b362b20c7d9c9bab8d7ca327dde7
3
+ size 17549312
run-28/checkpoint-2376/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bcab42162b998b8c836e8b797245d136f06af3128c1ebec3e25f0e51c3250ca
3
+ size 35123898
run-28/checkpoint-2376/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa24acea97d7bc1969494356993a0576de0ba4f75fb8231b3db6717fbe926473
3
+ size 14308
run-28/checkpoint-2376/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae83cddfbc6f1d33e406db6ea026a7b1e88f2a3cc666c8479bfdc7db7f7bab47
3
+ size 1064
run-28/checkpoint-2376/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-28/checkpoint-2376/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-28/checkpoint-2376/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-28/checkpoint-2376/trainer_state.json ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7108910891089109,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-28/checkpoint-2376",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2376,
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": 1.3590941429138184,
14
+ "learning_rate": 0.00033268893750406807,
15
+ "loss": 0.6415,
16
+ "step": 297
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5861386138613861,
21
+ "eval_f1": 0.473551637279597,
22
+ "eval_loss": 0.6401379108428955,
23
+ "eval_mcc": 0.1894629867942258,
24
+ "eval_precision": 0.6482758620689655,
25
+ "eval_recall": 0.373015873015873,
26
+ "eval_runtime": 0.9371,
27
+ "eval_samples_per_second": 538.913,
28
+ "eval_steps_per_second": 17.074,
29
+ "step": 297
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.476292848587036,
34
+ "learning_rate": 0.00028516194643205835,
35
+ "loss": 0.613,
36
+ "step": 594
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6514851485148515,
41
+ "eval_f1": 0.68,
42
+ "eval_loss": 0.5918833017349243,
43
+ "eval_mcc": 0.30837572082433856,
44
+ "eval_precision": 0.62751677852349,
45
+ "eval_recall": 0.7420634920634921,
46
+ "eval_runtime": 0.9445,
47
+ "eval_samples_per_second": 534.7,
48
+ "eval_steps_per_second": 16.941,
49
+ "step": 594
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.6527726650238037,
54
+ "learning_rate": 0.0002376349553600486,
55
+ "loss": 0.5836,
56
+ "step": 891
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.6594059405940594,
61
+ "eval_f1": 0.693950177935943,
62
+ "eval_loss": 0.5902799367904663,
63
+ "eval_mcc": 0.3278781101029775,
64
+ "eval_precision": 0.6290322580645161,
65
+ "eval_recall": 0.7738095238095238,
66
+ "eval_runtime": 0.9292,
67
+ "eval_samples_per_second": 543.474,
68
+ "eval_steps_per_second": 17.219,
69
+ "step": 891
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.4662635326385498,
74
+ "learning_rate": 0.0001901079642880389,
75
+ "loss": 0.5692,
76
+ "step": 1188
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6613861386138614,
81
+ "eval_f1": 0.6994727592267135,
82
+ "eval_loss": 0.5874853730201721,
83
+ "eval_mcc": 0.33437205674458564,
84
+ "eval_precision": 0.6277602523659306,
85
+ "eval_recall": 0.7896825396825397,
86
+ "eval_runtime": 0.9276,
87
+ "eval_samples_per_second": 544.403,
88
+ "eval_steps_per_second": 17.248,
89
+ "step": 1188
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 2.2937889099121094,
94
+ "learning_rate": 0.00014258097321602918,
95
+ "loss": 0.5565,
96
+ "step": 1485
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.6712871287128713,
101
+ "eval_f1": 0.6844106463878327,
102
+ "eval_loss": 0.5748322010040283,
103
+ "eval_mcc": 0.34399282923991964,
104
+ "eval_precision": 0.656934306569343,
105
+ "eval_recall": 0.7142857142857143,
106
+ "eval_runtime": 0.9341,
107
+ "eval_samples_per_second": 540.619,
108
+ "eval_steps_per_second": 17.129,
109
+ "step": 1485
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 2.6975440979003906,
114
+ "learning_rate": 9.505398214401945e-05,
115
+ "loss": 0.5445,
116
+ "step": 1782
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.7089108910891089,
121
+ "eval_f1": 0.7379679144385027,
122
+ "eval_loss": 0.5586543083190918,
123
+ "eval_mcc": 0.4291472704190268,
124
+ "eval_precision": 0.6699029126213593,
125
+ "eval_recall": 0.8214285714285714,
126
+ "eval_runtime": 0.932,
127
+ "eval_samples_per_second": 541.831,
128
+ "eval_steps_per_second": 17.167,
129
+ "step": 1782
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 3.01635479927063,
134
+ "learning_rate": 4.752699107200972e-05,
135
+ "loss": 0.5314,
136
+ "step": 2079
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.7069306930693069,
141
+ "eval_f1": 0.7279411764705882,
142
+ "eval_loss": 0.5484515428543091,
143
+ "eval_mcc": 0.419334756687555,
144
+ "eval_precision": 0.678082191780822,
145
+ "eval_recall": 0.7857142857142857,
146
+ "eval_runtime": 0.937,
147
+ "eval_samples_per_second": 538.933,
148
+ "eval_steps_per_second": 17.075,
149
+ "step": 2079
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "grad_norm": 2.718597650527954,
154
+ "learning_rate": 0.0,
155
+ "loss": 0.5189,
156
+ "step": 2376
157
+ },
158
+ {
159
+ "epoch": 8.0,
160
+ "eval_accuracy": 0.7108910891089109,
161
+ "eval_f1": 0.7326007326007326,
162
+ "eval_loss": 0.5490905046463013,
163
+ "eval_mcc": 0.42792784855482224,
164
+ "eval_precision": 0.6802721088435374,
165
+ "eval_recall": 0.7936507936507936,
166
+ "eval_runtime": 0.9303,
167
+ "eval_samples_per_second": 542.853,
168
+ "eval_steps_per_second": 17.199,
169
+ "step": 2376
170
+ }
171
+ ],
172
+ "logging_steps": 500,
173
+ "max_steps": 2376,
174
+ "num_input_tokens_seen": 0,
175
+ "num_train_epochs": 8,
176
+ "save_steps": 500,
177
+ "total_flos": 5845610127840.0,
178
+ "train_batch_size": 32,
179
+ "trial_name": null,
180
+ "trial_params": {
181
+ "alpha": 0.9092941270097592,
182
+ "learning_rate": 0.0003802159285760778,
183
+ "num_train_epochs": 8,
184
+ "temperature": 11
185
+ }
186
+ }
run-28/checkpoint-2376/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71bb8fa8d66b34ebd7e14a9356f6426aa55d1b931f391a77c3b0cb47e80b8b88
3
+ size 4920
run-28/checkpoint-2376/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-31/checkpoint-297/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": "4.39.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-31/checkpoint-297/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:415d3a0921bca21b9159b1590cca6ea25fafeaed2e8b692daf129d2b0219207c
3
+ size 17549312
run-31/checkpoint-297/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:331356c3b5f22c0194161355e30e7bf0ee7fab9e50ab9a916ec74dd0ed29bc2a
3
+ size 35123898
run-31/checkpoint-297/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f5e396c574b9b2ecc40d3f9e87d628a8f4be69caef81905a47fcf8895067e6
3
+ size 14308
run-31/checkpoint-297/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f79f297614db797f220adae59dee61f79e8cc9e36da1a1bf2f3d31987d5c03d7
3
+ size 1064
run-31/checkpoint-297/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-31/checkpoint-297/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-31/checkpoint-297/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-31/checkpoint-297/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5504950495049505,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-31/checkpoint-297",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 297,
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": 1.7863609790802002,
14
+ "learning_rate": 0.00019509013723494322,
15
+ "loss": 0.6459,
16
+ "step": 297
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5504950495049505,
21
+ "eval_f1": 0.3605633802816901,
22
+ "eval_loss": 0.6387978196144104,
23
+ "eval_mcc": 0.12386197513513038,
24
+ "eval_precision": 0.6213592233009708,
25
+ "eval_recall": 0.25396825396825395,
26
+ "eval_runtime": 0.929,
27
+ "eval_samples_per_second": 543.623,
28
+ "eval_steps_per_second": 17.224,
29
+ "step": 297
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 2079,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 7,
36
+ "save_steps": 500,
37
+ "total_flos": 730701265980.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.9148462770396972,
42
+ "learning_rate": 0.00022760516010743377,
43
+ "num_train_epochs": 7,
44
+ "temperature": 11
45
+ }
46
+ }
run-31/checkpoint-297/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8131558b780b77bdf48e590f1c8267970dee97d61ef55d4d3c8bc00b44e025a2
3
+ size 4920
run-31/checkpoint-297/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 sha256:082ccacbf20ed2e5f12a8657057e2759074f79e8de35cb8d580c36b197471a5a
3
- size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8131558b780b77bdf48e590f1c8267970dee97d61ef55d4d3c8bc00b44e025a2
3
+ size 4920