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
72a356d
·
verified ·
1 Parent(s): 6250445

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1713611625.a9446dbff3d4.7440.15 +2 -2
  2. logs/events.out.tfevents.1713611707.a9446dbff3d4.7440.16 +3 -0
  3. model.safetensors +1 -1
  4. run-13/checkpoint-1120/config.json +34 -0
  5. run-13/checkpoint-1120/model.safetensors +3 -0
  6. run-13/checkpoint-1120/optimizer.pt +3 -0
  7. run-13/checkpoint-1120/rng_state.pth +3 -0
  8. run-13/checkpoint-1120/scheduler.pt +3 -0
  9. run-13/checkpoint-1120/special_tokens_map.json +7 -0
  10. run-13/checkpoint-1120/tokenizer.json +0 -0
  11. run-13/checkpoint-1120/tokenizer_config.json +57 -0
  12. run-13/checkpoint-1120/trainer_state.json +166 -0
  13. run-13/checkpoint-1120/training_args.bin +3 -0
  14. run-13/checkpoint-1120/vocab.txt +0 -0
  15. run-13/checkpoint-1280/config.json +34 -0
  16. run-13/checkpoint-1280/model.safetensors +3 -0
  17. run-13/checkpoint-1280/optimizer.pt +3 -0
  18. run-13/checkpoint-1280/rng_state.pth +3 -0
  19. run-13/checkpoint-1280/scheduler.pt +3 -0
  20. run-13/checkpoint-1280/special_tokens_map.json +7 -0
  21. run-13/checkpoint-1280/tokenizer.json +0 -0
  22. run-13/checkpoint-1280/tokenizer_config.json +57 -0
  23. run-13/checkpoint-1280/trainer_state.json +186 -0
  24. run-13/checkpoint-1280/training_args.bin +3 -0
  25. run-13/checkpoint-1280/vocab.txt +0 -0
  26. run-14/checkpoint-160/config.json +34 -0
  27. run-14/checkpoint-160/model.safetensors +3 -0
  28. run-14/checkpoint-160/optimizer.pt +3 -0
  29. run-14/checkpoint-160/rng_state.pth +3 -0
  30. run-14/checkpoint-160/scheduler.pt +3 -0
  31. run-14/checkpoint-160/special_tokens_map.json +7 -0
  32. run-14/checkpoint-160/tokenizer.json +0 -0
  33. run-14/checkpoint-160/tokenizer_config.json +57 -0
  34. run-14/checkpoint-160/trainer_state.json +46 -0
  35. run-14/checkpoint-160/training_args.bin +3 -0
  36. run-14/checkpoint-160/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1713611625.a9446dbff3d4.7440.15 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06983d2ad03d21b35010f689a27c474f7ad7bf3dbc5783a05ba2461586a91e2e
3
- size 6211
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20fbf3cb59c706cdba8bd067419ff325edb77912e498c8b7b7bd6c1cb81c42c1
3
+ size 10945
logs/events.out.tfevents.1713611707.a9446dbff3d4.7440.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28043178bd882b340f3230feba3deb72bc4e78ca58adc105f0a62124530afefa
3
+ size 5483
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92c9f6092ec70603457429477d4808f8093c435713e779bb0e2b655287caa418
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0142724fa20ed611e1b33d0280d454e12ec1c71b9b71578e3db5fc76a38a438
3
  size 17549312
run-13/checkpoint-1120/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-13/checkpoint-1120/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85344d367eede7437ae91a7fd4dc3238311ec14e8cb04011ecdc7dbd64d5591b
3
+ size 17549312
run-13/checkpoint-1120/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c64244e69ca644d0cadd2dde3c2028a5a4b77fe79a30dce66a6148bc5f4cd1e1
3
+ size 35123898
run-13/checkpoint-1120/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dff60335fa5283437e5a2cb72f0621ff75353a3210e4a78bc955f52e428c356c
3
+ size 14308
run-13/checkpoint-1120/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a788154f87965c40ee6541d7b11959eab4d1b13ce68666f7a31632ba655b76d9
3
+ size 1064
run-13/checkpoint-1120/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-13/checkpoint-1120/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-13/checkpoint-1120/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-13/checkpoint-1120/trainer_state.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7607843137254902,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-1120",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1120,
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": 1.6348164081573486,
14
+ "learning_rate": 0.00028293467755282096,
15
+ "loss": 0.4646,
16
+ "step": 160
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.668235294117647,
21
+ "eval_f1": 0.018561484918793503,
22
+ "eval_loss": 0.43796491622924805,
23
+ "eval_mcc": 0.04862166383263152,
24
+ "eval_precision": 0.6666666666666666,
25
+ "eval_recall": 0.009411764705882352,
26
+ "eval_runtime": 1.8631,
27
+ "eval_samples_per_second": 684.329,
28
+ "eval_steps_per_second": 21.469,
29
+ "step": 160
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.2706644535064697,
34
+ "learning_rate": 0.000242515437902418,
35
+ "loss": 0.4357,
36
+ "step": 320
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7184313725490196,
41
+ "eval_f1": 0.37565217391304345,
42
+ "eval_loss": 0.4178254306316376,
43
+ "eval_mcc": 0.2995107121067069,
44
+ "eval_precision": 0.72,
45
+ "eval_recall": 0.2541176470588235,
46
+ "eval_runtime": 1.8716,
47
+ "eval_samples_per_second": 681.232,
48
+ "eval_steps_per_second": 21.372,
49
+ "step": 320
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.069754123687744,
54
+ "learning_rate": 0.00020209619825201498,
55
+ "loss": 0.4247,
56
+ "step": 480
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7419607843137255,
61
+ "eval_f1": 0.5548037889039241,
62
+ "eval_loss": 0.4210284948348999,
63
+ "eval_mcc": 0.38745831003992626,
64
+ "eval_precision": 0.6528662420382165,
65
+ "eval_recall": 0.4823529411764706,
66
+ "eval_runtime": 1.8687,
67
+ "eval_samples_per_second": 682.3,
68
+ "eval_steps_per_second": 21.405,
69
+ "step": 480
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 0.9811561703681946,
74
+ "learning_rate": 0.000161676958601612,
75
+ "loss": 0.4179,
76
+ "step": 640
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7349019607843137,
81
+ "eval_f1": 0.43666666666666665,
82
+ "eval_loss": 0.4131487309932709,
83
+ "eval_mcc": 0.3513388123150658,
84
+ "eval_precision": 0.7485714285714286,
85
+ "eval_recall": 0.30823529411764705,
86
+ "eval_runtime": 1.8772,
87
+ "eval_samples_per_second": 679.197,
88
+ "eval_steps_per_second": 21.308,
89
+ "step": 640
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 1.1143430471420288,
94
+ "learning_rate": 0.000121257718951209,
95
+ "loss": 0.4113,
96
+ "step": 800
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.7545098039215686,
101
+ "eval_f1": 0.5908496732026145,
102
+ "eval_loss": 0.4124383330345154,
103
+ "eval_mcc": 0.42389318898939016,
104
+ "eval_precision": 0.6647058823529411,
105
+ "eval_recall": 0.5317647058823529,
106
+ "eval_runtime": 1.8732,
107
+ "eval_samples_per_second": 680.66,
108
+ "eval_steps_per_second": 21.354,
109
+ "step": 800
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 1.0988030433654785,
114
+ "learning_rate": 8.0838479300806e-05,
115
+ "loss": 0.4058,
116
+ "step": 960
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.7529411764705882,
121
+ "eval_f1": 0.5493562231759658,
122
+ "eval_loss": 0.4068860113620758,
123
+ "eval_mcc": 0.40775530964263945,
124
+ "eval_precision": 0.7007299270072993,
125
+ "eval_recall": 0.45176470588235296,
126
+ "eval_runtime": 1.8719,
127
+ "eval_samples_per_second": 681.136,
128
+ "eval_steps_per_second": 21.369,
129
+ "step": 960
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 1.373121738433838,
134
+ "learning_rate": 4.0419239650403e-05,
135
+ "loss": 0.407,
136
+ "step": 1120
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.7607843137254902,
141
+ "eval_f1": 0.5960264900662252,
142
+ "eval_loss": 0.4111056327819824,
143
+ "eval_mcc": 0.43684887642861214,
144
+ "eval_precision": 0.6818181818181818,
145
+ "eval_recall": 0.5294117647058824,
146
+ "eval_runtime": 1.8826,
147
+ "eval_samples_per_second": 677.271,
148
+ "eval_steps_per_second": 21.248,
149
+ "step": 1120
150
+ }
151
+ ],
152
+ "logging_steps": 500,
153
+ "max_steps": 1280,
154
+ "num_input_tokens_seen": 0,
155
+ "num_train_epochs": 8,
156
+ "save_steps": 500,
157
+ "total_flos": 2042288065440.0,
158
+ "train_batch_size": 32,
159
+ "trial_name": null,
160
+ "trial_params": {
161
+ "alpha": 0.7266899336949371,
162
+ "learning_rate": 0.000323353917203224,
163
+ "num_train_epochs": 8,
164
+ "temperature": 24
165
+ }
166
+ }
run-13/checkpoint-1120/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b75d1a13345b1b7409ffa5572fa151259b0166dcbee52e95898829d69dc6b9cd
3
+ size 5048
run-13/checkpoint-1120/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-13/checkpoint-1280/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-13/checkpoint-1280/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4725914f21b654da2a144be28990cf66590da4bba7e0da5df44d30bfeadb485
3
+ size 17549312
run-13/checkpoint-1280/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67db50ca76c00239e6dab82dbb4b16129282d06ffc80691cfe74e7efb90ea8cc
3
+ size 35123898
run-13/checkpoint-1280/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:242da79f0f40d17a976877b7744318ca279c3e455ed5f3332156e384fbc450c4
3
+ size 14308
run-13/checkpoint-1280/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afad99148381fbd0ea38e76b99ebe31b1c6ba2f1dbe0b792550114cd3f1482b6
3
+ size 1064
run-13/checkpoint-1280/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-13/checkpoint-1280/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-13/checkpoint-1280/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-13/checkpoint-1280/trainer_state.json ADDED
@@ -0,0 +1,186 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7607843137254902,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-1120",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1280,
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": 1.6348164081573486,
14
+ "learning_rate": 0.00028293467755282096,
15
+ "loss": 0.4646,
16
+ "step": 160
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.668235294117647,
21
+ "eval_f1": 0.018561484918793503,
22
+ "eval_loss": 0.43796491622924805,
23
+ "eval_mcc": 0.04862166383263152,
24
+ "eval_precision": 0.6666666666666666,
25
+ "eval_recall": 0.009411764705882352,
26
+ "eval_runtime": 1.8631,
27
+ "eval_samples_per_second": 684.329,
28
+ "eval_steps_per_second": 21.469,
29
+ "step": 160
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.2706644535064697,
34
+ "learning_rate": 0.000242515437902418,
35
+ "loss": 0.4357,
36
+ "step": 320
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7184313725490196,
41
+ "eval_f1": 0.37565217391304345,
42
+ "eval_loss": 0.4178254306316376,
43
+ "eval_mcc": 0.2995107121067069,
44
+ "eval_precision": 0.72,
45
+ "eval_recall": 0.2541176470588235,
46
+ "eval_runtime": 1.8716,
47
+ "eval_samples_per_second": 681.232,
48
+ "eval_steps_per_second": 21.372,
49
+ "step": 320
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.069754123687744,
54
+ "learning_rate": 0.00020209619825201498,
55
+ "loss": 0.4247,
56
+ "step": 480
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7419607843137255,
61
+ "eval_f1": 0.5548037889039241,
62
+ "eval_loss": 0.4210284948348999,
63
+ "eval_mcc": 0.38745831003992626,
64
+ "eval_precision": 0.6528662420382165,
65
+ "eval_recall": 0.4823529411764706,
66
+ "eval_runtime": 1.8687,
67
+ "eval_samples_per_second": 682.3,
68
+ "eval_steps_per_second": 21.405,
69
+ "step": 480
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 0.9811561703681946,
74
+ "learning_rate": 0.000161676958601612,
75
+ "loss": 0.4179,
76
+ "step": 640
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7349019607843137,
81
+ "eval_f1": 0.43666666666666665,
82
+ "eval_loss": 0.4131487309932709,
83
+ "eval_mcc": 0.3513388123150658,
84
+ "eval_precision": 0.7485714285714286,
85
+ "eval_recall": 0.30823529411764705,
86
+ "eval_runtime": 1.8772,
87
+ "eval_samples_per_second": 679.197,
88
+ "eval_steps_per_second": 21.308,
89
+ "step": 640
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 1.1143430471420288,
94
+ "learning_rate": 0.000121257718951209,
95
+ "loss": 0.4113,
96
+ "step": 800
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.7545098039215686,
101
+ "eval_f1": 0.5908496732026145,
102
+ "eval_loss": 0.4124383330345154,
103
+ "eval_mcc": 0.42389318898939016,
104
+ "eval_precision": 0.6647058823529411,
105
+ "eval_recall": 0.5317647058823529,
106
+ "eval_runtime": 1.8732,
107
+ "eval_samples_per_second": 680.66,
108
+ "eval_steps_per_second": 21.354,
109
+ "step": 800
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 1.0988030433654785,
114
+ "learning_rate": 8.0838479300806e-05,
115
+ "loss": 0.4058,
116
+ "step": 960
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.7529411764705882,
121
+ "eval_f1": 0.5493562231759658,
122
+ "eval_loss": 0.4068860113620758,
123
+ "eval_mcc": 0.40775530964263945,
124
+ "eval_precision": 0.7007299270072993,
125
+ "eval_recall": 0.45176470588235296,
126
+ "eval_runtime": 1.8719,
127
+ "eval_samples_per_second": 681.136,
128
+ "eval_steps_per_second": 21.369,
129
+ "step": 960
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "grad_norm": 1.373121738433838,
134
+ "learning_rate": 4.0419239650403e-05,
135
+ "loss": 0.407,
136
+ "step": 1120
137
+ },
138
+ {
139
+ "epoch": 7.0,
140
+ "eval_accuracy": 0.7607843137254902,
141
+ "eval_f1": 0.5960264900662252,
142
+ "eval_loss": 0.4111056327819824,
143
+ "eval_mcc": 0.43684887642861214,
144
+ "eval_precision": 0.6818181818181818,
145
+ "eval_recall": 0.5294117647058824,
146
+ "eval_runtime": 1.8826,
147
+ "eval_samples_per_second": 677.271,
148
+ "eval_steps_per_second": 21.248,
149
+ "step": 1120
150
+ },
151
+ {
152
+ "epoch": 8.0,
153
+ "grad_norm": 1.2871596813201904,
154
+ "learning_rate": 0.0,
155
+ "loss": 0.401,
156
+ "step": 1280
157
+ },
158
+ {
159
+ "epoch": 8.0,
160
+ "eval_accuracy": 0.7521568627450981,
161
+ "eval_f1": 0.5524079320113314,
162
+ "eval_loss": 0.4067133963108063,
163
+ "eval_mcc": 0.40673564442456084,
164
+ "eval_precision": 0.693950177935943,
165
+ "eval_recall": 0.4588235294117647,
166
+ "eval_runtime": 1.8786,
167
+ "eval_samples_per_second": 678.7,
168
+ "eval_steps_per_second": 21.293,
169
+ "step": 1280
170
+ }
171
+ ],
172
+ "logging_steps": 500,
173
+ "max_steps": 1280,
174
+ "num_input_tokens_seen": 0,
175
+ "num_train_epochs": 8,
176
+ "save_steps": 500,
177
+ "total_flos": 2334043503360.0,
178
+ "train_batch_size": 32,
179
+ "trial_name": null,
180
+ "trial_params": {
181
+ "alpha": 0.7266899336949371,
182
+ "learning_rate": 0.000323353917203224,
183
+ "num_train_epochs": 8,
184
+ "temperature": 24
185
+ }
186
+ }
run-13/checkpoint-1280/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b75d1a13345b1b7409ffa5572fa151259b0166dcbee52e95898829d69dc6b9cd
3
+ size 5048
run-13/checkpoint-1280/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-160/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-14/checkpoint-160/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0142724fa20ed611e1b33d0280d454e12ec1c71b9b71578e3db5fc76a38a438
3
+ size 17549312
run-14/checkpoint-160/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06fc69a3c1845172b3302d6428a37b38d3099ba161328d68a4b57da6d70ede95
3
+ size 35123898
run-14/checkpoint-160/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0792eaff268dd73c8e104b5060a487f4ef56535ad3b58888006338b8bc298137
3
+ size 14308
run-14/checkpoint-160/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df2f8590bbef83e155ed5b7585f819605e89c7ca41b5c1d2dd02f39a439c8a6d
3
+ size 1064
run-14/checkpoint-160/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-14/checkpoint-160/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-160/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-14/checkpoint-160/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6666666666666666,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-160",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 160,
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": 1.9069746732711792,
14
+ "learning_rate": 0.0001514416935217273,
15
+ "loss": 0.5085,
16
+ "step": 160
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.4942961037158966,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 1.8701,
27
+ "eval_samples_per_second": 681.789,
28
+ "eval_steps_per_second": 21.389,
29
+ "step": 160
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 1280,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 8,
36
+ "save_steps": 500,
37
+ "total_flos": 291755437920.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.7926575748257565,
42
+ "learning_rate": 0.00017307622116768837,
43
+ "num_train_epochs": 8,
44
+ "temperature": 11
45
+ }
46
+ }
run-14/checkpoint-160/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b6b19052d4c806997afdfae7afcfc25427cf0da55d0d521079b159e1e5e6a52
3
+ size 5048
run-14/checkpoint-160/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:b75d1a13345b1b7409ffa5572fa151259b0166dcbee52e95898829d69dc6b9cd
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b6b19052d4c806997afdfae7afcfc25427cf0da55d0d521079b159e1e5e6a52
3
  size 5048