Hugging Face's logo

JeukHwang
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
text-embeddings-inference
Model card Files
xet
Metrics Community
JeukHwang commited on
Commit
8ca8e00
·
1 Parent(s): 435a6c4

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1699906034.b18f42e49ba4.3021.5 +2 -2
  2. logs/events.out.tfevents.1699906437.b18f42e49ba4.3021.6 +3 -0
  3. model.safetensors +1 -1
  4. run-4/checkpoint-3162/config.json +34 -0
  5. run-4/checkpoint-3162/model.safetensors +3 -0
  6. run-4/checkpoint-3162/optimizer.pt +3 -0
  7. run-4/checkpoint-3162/rng_state.pth +3 -0
  8. run-4/checkpoint-3162/scheduler.pt +3 -0
  9. run-4/checkpoint-3162/special_tokens_map.json +7 -0
  10. run-4/checkpoint-3162/tokenizer.json +0 -0
  11. run-4/checkpoint-3162/tokenizer_config.json +57 -0
  12. run-4/checkpoint-3162/trainer_state.json +114 -0
  13. run-4/checkpoint-3162/training_args.bin +3 -0
  14. run-4/checkpoint-3162/vocab.txt +0 -0
  15. run-5/checkpoint-527/config.json +34 -0
  16. run-5/checkpoint-527/model.safetensors +3 -0
  17. run-5/checkpoint-527/optimizer.pt +3 -0
  18. run-5/checkpoint-527/rng_state.pth +3 -0
  19. run-5/checkpoint-527/scheduler.pt +3 -0
  20. run-5/checkpoint-527/special_tokens_map.json +7 -0
  21. run-5/checkpoint-527/tokenizer.json +0 -0
  22. run-5/checkpoint-527/tokenizer_config.json +57 -0
  23. run-5/checkpoint-527/trainer_state.json +39 -0
  24. run-5/checkpoint-527/training_args.bin +3 -0
  25. run-5/checkpoint-527/vocab.txt +0 -0
  26. training_args.bin +1 -1
logs/events.out.tfevents.1699906034.b18f42e49ba4.3021.5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed074b6f1488de3b352a61c494012e0cbbef4391fd5fbfa888841818b369320a
3
- size 5253
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:785825df6090c4b022e21d703ab59abdaa22fef5687ca64591efd5b371b08f88
3
+ size 7527
logs/events.out.tfevents.1699906437.b18f42e49ba4.3021.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0331af381a6f2d18f70e022bc4b8bba51106850701e1a53e0ac5b196809c1111
3
+ size 4774
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab5e6c5c1b173993187fa092d72f6830f6c451d9862a2e0c030d62e60d28e1d3
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd2ddf19765e685364794c6680907306d67781bc5803be99e453c18f132d4c30
3
  size 17549312
run-4/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-4/checkpoint-3162/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d8cfbc3f2ac8186da18a7bd7ef9a85ec1989babd870f37c1b1bf475ad915bc4
3
+ size 17549312
run-4/checkpoint-3162/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46b5e246bfb089ad283c98cd30bed861417fcd5e5bf4ef36031ccc7c6d45d52c
3
+ size 35123898
run-4/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-4/checkpoint-3162/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d83a490d1083b568e2c1afdcfbb909ea21ea38a2fbb49791f2a472e836ed3bf5
3
+ size 1064
run-4/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-4/checkpoint-3162/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-3162/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8188073394495413,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/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": 0.00040021870017567724,
14
+ "loss": 1.2163,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8142201834862385,
20
+ "eval_loss": 1.4123148918151855,
21
+ "eval_runtime": 0.9262,
22
+ "eval_samples_per_second": 941.52,
23
+ "eval_steps_per_second": 7.558,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.0003201749601405418,
29
+ "loss": 0.5495,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8188073394495413,
35
+ "eval_loss": 1.6448004245758057,
36
+ "eval_runtime": 0.9196,
37
+ "eval_samples_per_second": 948.263,
38
+ "eval_steps_per_second": 7.612,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 0.00024013122010540635,
44
+ "loss": 0.3613,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8130733944954128,
50
+ "eval_loss": 1.7091050148010254,
51
+ "eval_runtime": 0.9201,
52
+ "eval_samples_per_second": 947.704,
53
+ "eval_steps_per_second": 7.608,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 0.0001600874800702709,
59
+ "loss": 0.2633,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8061926605504587,
65
+ "eval_loss": 1.7558174133300781,
66
+ "eval_runtime": 0.9207,
67
+ "eval_samples_per_second": 947.104,
68
+ "eval_steps_per_second": 7.603,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 8.019562568985109e-05,
74
+ "loss": 0.2098,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8119266055045872,
80
+ "eval_loss": 1.7234684228897095,
81
+ "eval_runtime": 0.9327,
82
+ "eval_samples_per_second": 934.936,
83
+ "eval_steps_per_second": 7.505,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 1.5188565471562704e-07,
89
+ "loss": 0.1772,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8073394495412844,
95
+ "eval_loss": 1.7331962585449219,
96
+ "eval_runtime": 0.9164,
97
+ "eval_samples_per_second": 951.555,
98
+ "eval_steps_per_second": 7.639,
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": 0.3872215527509325,
110
+ "learning_rate": 0.0004802624402108127,
111
+ "num_train_epochs": 6,
112
+ "temperature": 26
113
+ }
114
+ }
run-4/checkpoint-3162/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8b08743d46499d2923be786e050cfb5462874efdc395fd5a374a78ef5a78d32
3
+ size 4600
run-4/checkpoint-3162/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/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-5/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd2ddf19765e685364794c6680907306d67781bc5803be99e453c18f132d4c30
3
+ size 17549312
run-5/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f7aa1eb152a775ace0909929b60fd6063359d8b317731fd89ccc6973cd399dd
3
+ size 35123898
run-5/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-5/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a521d4b38a4c93d2e6ccf553c2b2a8bd9a3220c57f2bd5a5eaf4cd3cb31b533
3
+ size 1064
run-5/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-5/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/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-5/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8073394495412844,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-5/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": 0.0001244210714352971,
14
+ "loss": 2.1634,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8073394495412844,
20
+ "eval_loss": 1.7978096008300781,
21
+ "eval_runtime": 0.92,
22
+ "eval_samples_per_second": 947.846,
23
+ "eval_steps_per_second": 7.609,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 4216,
29
+ "num_train_epochs": 8,
30
+ "save_steps": 500,
31
+ "total_flos": 8117476690260.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.10702478077127464,
35
+ "learning_rate": 0.00014215697484314704,
36
+ "num_train_epochs": 8,
37
+ "temperature": 30
38
+ }
39
+ }
run-5/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:296db979eca092ce7396cd9509850c8dd40fdce13dfed2ce7efeefca33233a59
3
+ size 4600
run-5/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:e8b08743d46499d2923be786e050cfb5462874efdc395fd5a374a78ef5a78d32
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:296db979eca092ce7396cd9509850c8dd40fdce13dfed2ce7efeefca33233a59
3
  size 4600