Hugging Face's logo

JeukHwang
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Model card Files
xet
Metrics Community
JeukHwang commited on
Commit
bf10b0f
·
1 Parent(s): ae1fa58

Training in progress, epoch 1

Browse files
Files changed (31) hide show
  1. logs/events.out.tfevents.1699911268.b18f42e49ba4.3021.25 +2 -2
  2. logs/events.out.tfevents.1699911680.b18f42e49ba4.3021.26 +3 -0
  3. logs/events.out.tfevents.1699911746.b18f42e49ba4.3021.27 +3 -0
  4. logs/events.out.tfevents.1699911813.b18f42e49ba4.3021.28 +3 -0
  5. logs/events.out.tfevents.1699911879.b18f42e49ba4.3021.29 +3 -0
  6. logs/events.out.tfevents.1699911947.b18f42e49ba4.3021.30 +3 -0
  7. logs/events.out.tfevents.1699912014.b18f42e49ba4.3021.31 +3 -0
  8. model.safetensors +1 -1
  9. run-24/checkpoint-3162/config.json +34 -0
  10. run-24/checkpoint-3162/model.safetensors +3 -0
  11. run-24/checkpoint-3162/optimizer.pt +3 -0
  12. run-24/checkpoint-3162/rng_state.pth +3 -0
  13. run-24/checkpoint-3162/scheduler.pt +3 -0
  14. run-24/checkpoint-3162/special_tokens_map.json +7 -0
  15. run-24/checkpoint-3162/tokenizer.json +0 -0
  16. run-24/checkpoint-3162/tokenizer_config.json +57 -0
  17. run-24/checkpoint-3162/trainer_state.json +114 -0
  18. run-24/checkpoint-3162/training_args.bin +3 -0
  19. run-24/checkpoint-3162/vocab.txt +0 -0
  20. run-30/checkpoint-527/config.json +34 -0
  21. run-30/checkpoint-527/model.safetensors +3 -0
  22. run-30/checkpoint-527/optimizer.pt +3 -0
  23. run-30/checkpoint-527/rng_state.pth +3 -0
  24. run-30/checkpoint-527/scheduler.pt +3 -0
  25. run-30/checkpoint-527/special_tokens_map.json +7 -0
  26. run-30/checkpoint-527/tokenizer.json +0 -0
  27. run-30/checkpoint-527/tokenizer_config.json +57 -0
  28. run-30/checkpoint-527/trainer_state.json +39 -0
  29. run-30/checkpoint-527/training_args.bin +3 -0
  30. run-30/checkpoint-527/vocab.txt +0 -0
  31. training_args.bin +1 -1
logs/events.out.tfevents.1699911268.b18f42e49ba4.3021.25 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54b1f177f3cb3d25dfd04fd3e83ae8c2e08e783aa247f2e3951a3614088e735d
3
- size 6214
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce6253e494f4fbe169387494a84f20a28915749371b6c4fe3d9e29ddd735147e
3
+ size 7528
logs/events.out.tfevents.1699911680.b18f42e49ba4.3021.26 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bff0b36a7f11ae15632eb320369e42400325eb6245c8daf3c9cfd7e684e88278
3
+ size 4774
logs/events.out.tfevents.1699911746.b18f42e49ba4.3021.27 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d6429c01c688866c384b95ae45977dad301358193f8bd776d202e6429deef4
3
+ size 4773
logs/events.out.tfevents.1699911813.b18f42e49ba4.3021.28 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e23f5849009a6456fbfb74cfee1f9f606021b8950bf0e0b4ca96c7e1fa6a602
3
+ size 4773
logs/events.out.tfevents.1699911879.b18f42e49ba4.3021.29 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59f7b04337b89886fab8ba8064a119b09d54d89c9a19bf8d49cbb50dbf0ef2f
3
+ size 4774
logs/events.out.tfevents.1699911947.b18f42e49ba4.3021.30 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18eb7f590a7f7d3557e78fe7aaf00bead752b33bd6c803a949b4c86b6d7b596d
3
+ size 4773
logs/events.out.tfevents.1699912014.b18f42e49ba4.3021.31 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:182d941b90e4f65ea231ded0ddfa3854aa3348dd45c24f1b73dc86e1226715ac
3
+ size 4774
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6b21520346822035eb05ba85e2b02b007e9280415e6960664cb00f38a14cbed
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e9bfd5075b3023e3b5ea04a71f472a0b3d74dd50b8c42d8b856dc263c3b63e0
3
  size 17549312
run-24/checkpoint-3162/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": "4.35.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-24/checkpoint-3162/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec9044a83c1c35430e1068c45f1b8e2d1134597af032885768d583c3f01e259
3
+ size 17549312
run-24/checkpoint-3162/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62dc21ecffbcaca7e45c7802b07fd4982739bab22c48e196e5daaf831f365427
3
+ size 35123898
run-24/checkpoint-3162/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a805f5b31aed4614530263d37ef452339ef59079ff627a6dd75bd82ccc8197
3
+ size 14308
run-24/checkpoint-3162/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59ff06dfb49211322bd05101a1c17446665423078ba1ffc1bbad3f8bd2f63396
3
+ size 1064
run-24/checkpoint-3162/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-24/checkpoint-3162/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-24/checkpoint-3162/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-24/checkpoint-3162/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8302752293577982,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-24/checkpoint-1054",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3162,
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
+ "learning_rate": 9.264654582488016e-05,
14
+ "loss": 1.9014,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8107798165137615,
20
+ "eval_loss": 1.552759051322937,
21
+ "eval_runtime": 0.8371,
22
+ "eval_samples_per_second": 1041.732,
23
+ "eval_steps_per_second": 8.363,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 7.412426598811543e-05,
29
+ "loss": 0.9481,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8302752293577982,
35
+ "eval_loss": 1.4989248514175415,
36
+ "eval_runtime": 0.8428,
37
+ "eval_samples_per_second": 1034.644,
38
+ "eval_steps_per_second": 8.306,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 5.5601986151350695e-05,
44
+ "loss": 0.716,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8256880733944955,
50
+ "eval_loss": 1.504542350769043,
51
+ "eval_runtime": 0.9321,
52
+ "eval_samples_per_second": 935.536,
53
+ "eval_steps_per_second": 7.51,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 3.7079706314585956e-05,
59
+ "loss": 0.6102,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8188073394495413,
65
+ "eval_loss": 1.5119519233703613,
66
+ "eval_runtime": 0.8521,
67
+ "eval_samples_per_second": 1023.392,
68
+ "eval_steps_per_second": 8.215,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 1.8557426477821217e-05,
74
+ "loss": 0.5393,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8279816513761468,
80
+ "eval_loss": 1.5598211288452148,
81
+ "eval_runtime": 0.8933,
82
+ "eval_samples_per_second": 976.176,
83
+ "eval_steps_per_second": 7.836,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 3.514664105647958e-08,
89
+ "loss": 0.5053,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8279816513761468,
95
+ "eval_loss": 1.5646741390228271,
96
+ "eval_runtime": 0.8367,
97
+ "eval_samples_per_second": 1042.231,
98
+ "eval_steps_per_second": 8.367,
99
+ "step": 3162
100
+ }
101
+ ],
102
+ "logging_steps": 500,
103
+ "max_steps": 3162,
104
+ "num_train_epochs": 6,
105
+ "save_steps": 500,
106
+ "total_flos": 48509902416420.0,
107
+ "trial_name": null,
108
+ "trial_params": {
109
+ "alpha": 0.32712078965773406,
110
+ "learning_rate": 0.00011113367902058842,
111
+ "num_train_epochs": 6,
112
+ "temperature": 24
113
+ }
114
+ }
run-24/checkpoint-3162/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71a8249c53933e918f28c304299ffcb113fd2a092e048e706c58ab31b2064ca9
3
+ size 4600
run-24/checkpoint-3162/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-30/checkpoint-527/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": "4.35.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-30/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e9bfd5075b3023e3b5ea04a71f472a0b3d74dd50b8c42d8b856dc263c3b63e0
3
+ size 17549312
run-30/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67e41dc00190e4961bda8d60e25e81760b80f4c4ee7b74f2977ad2b5e1b16d7c
3
+ size 35123898
run-30/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ababcbf30496eb4976cce44a5faf0cf605467f452ba655745eb60d884a0042d8
3
+ size 14308
run-30/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba6606dba004de60d8711ea019e0a4a54271723be1fa710e12b4a4e0616065a2
3
+ size 1064
run-30/checkpoint-527/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-30/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-30/checkpoint-527/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-30/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8107798165137615,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-30/checkpoint-527",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 527,
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
+ "learning_rate": 0.00012672332329282998,
14
+ "loss": 1.5289,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8107798165137615,
20
+ "eval_loss": 1.3494598865509033,
21
+ "eval_runtime": 0.837,
22
+ "eval_samples_per_second": 1041.754,
23
+ "eval_steps_per_second": 8.363,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 4743,
29
+ "num_train_epochs": 9,
30
+ "save_steps": 500,
31
+ "total_flos": 8117476690260.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.44199314752934615,
35
+ "learning_rate": 0.00014252993179461525,
36
+ "num_train_epochs": 9,
37
+ "temperature": 19
38
+ }
39
+ }
run-30/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d67ba77b95e8ae0f8074c50b63c9f0ecd721c6f94b6ab155bf1c6a999bea86e3
3
+ size 4600
run-30/checkpoint-527/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 sha256:71a8249c53933e918f28c304299ffcb113fd2a092e048e706c58ab31b2064ca9
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d67ba77b95e8ae0f8074c50b63c9f0ecd721c6f94b6ab155bf1c6a999bea86e3
3
  size 4600