Hugging Face's logo

jysh1023
/
tiny-bert-sst2-distilled

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
bert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Metrics Community
jysh1023 commited on
Commit
6d950bc
·
1 Parent(s): c55ff16

Training in progress, epoch 1

Browse files
Files changed (27) hide show
  1. logs/events.out.tfevents.1699951173.45c71320b2c6.349.12 +2 -2
  2. logs/events.out.tfevents.1699951512.45c71320b2c6.349.13 +3 -0
  3. logs/events.out.tfevents.1699951579.45c71320b2c6.349.14 +3 -0
  4. model.safetensors +1 -1
  5. run-11/checkpoint-2108/config.json +34 -0
  6. run-11/checkpoint-2108/model.safetensors +3 -0
  7. run-11/checkpoint-2108/optimizer.pt +3 -0
  8. run-11/checkpoint-2108/rng_state.pth +3 -0
  9. run-11/checkpoint-2108/scheduler.pt +3 -0
  10. run-11/checkpoint-2108/special_tokens_map.json +7 -0
  11. run-11/checkpoint-2108/tokenizer.json +0 -0
  12. run-11/checkpoint-2108/tokenizer_config.json +57 -0
  13. run-11/checkpoint-2108/trainer_state.json +84 -0
  14. run-11/checkpoint-2108/training_args.bin +3 -0
  15. run-11/checkpoint-2108/vocab.txt +0 -0
  16. run-13/checkpoint-527/config.json +34 -0
  17. run-13/checkpoint-527/model.safetensors +3 -0
  18. run-13/checkpoint-527/optimizer.pt +3 -0
  19. run-13/checkpoint-527/rng_state.pth +3 -0
  20. run-13/checkpoint-527/scheduler.pt +3 -0
  21. run-13/checkpoint-527/special_tokens_map.json +7 -0
  22. run-13/checkpoint-527/tokenizer.json +0 -0
  23. run-13/checkpoint-527/tokenizer_config.json +57 -0
  24. run-13/checkpoint-527/trainer_state.json +39 -0
  25. run-13/checkpoint-527/training_args.bin +3 -0
  26. run-13/checkpoint-527/vocab.txt +0 -0
  27. training_args.bin +1 -1
logs/events.out.tfevents.1699951173.45c71320b2c6.349.12 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9ba571208bec89822af6b7b5c5f8b54734f49abf253985690a4e94480f9c880
3
- size 5254
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44e770b547df861b5665eb1dfce92f00b89f4f4ce35f9d280c167dd9826a5b8
3
+ size 6694
logs/events.out.tfevents.1699951512.45c71320b2c6.349.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:925e30bd71006cf323e2f56fd3414e2be3c972aa0e61c48890aeb94540329c8e
3
+ size 4774
logs/events.out.tfevents.1699951579.45c71320b2c6.349.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea71b91e42cfbb263f4fab81508740ba45ac6cfe62fea3226fec53142638ab4d
3
+ size 4773
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3eaf451f08f8933fc09d709d01b6f8e004f2a20c719a9a21407cdb9f239cce3d
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7481977ec57a3799e410809543b16605fe362acf8c3ae761d4995cb0c22efaf
3
  size 17549312
run-11/checkpoint-2108/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-11/checkpoint-2108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56232df03996da58d9188c75193419cd404614f1d84da1904e39e0f321a95ed6
3
+ size 17549312
run-11/checkpoint-2108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52b517a4faafb2ee2b7ed8f875d5b76b60430007a73c02cef491397c712382cc
3
+ size 35123898
run-11/checkpoint-2108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5380d7490ac96d7f61709bde5d4086c1114991ed50d41459765b29873c758add
3
+ size 14308
run-11/checkpoint-2108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:262ce34d1f1944785c40f51be4abeb997e1e495516c29bb411877f6805ddf594
3
+ size 1064
run-11/checkpoint-2108/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-11/checkpoint-2108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-11/checkpoint-2108/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-11/checkpoint-2108/trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8279816513761468,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-1054",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2108,
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": 8.853375939048859e-05,
14
+ "loss": 1.4024,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8084862385321101,
20
+ "eval_loss": 1.1691620349884033,
21
+ "eval_runtime": 0.8297,
22
+ "eval_samples_per_second": 1050.926,
23
+ "eval_steps_per_second": 8.436,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 7.869874859816409e-05,
29
+ "loss": 0.7313,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8279816513761468,
35
+ "eval_loss": 1.158647060394287,
36
+ "eval_runtime": 0.8355,
37
+ "eval_samples_per_second": 1043.71,
38
+ "eval_steps_per_second": 8.378,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 6.886373780583957e-05,
44
+ "loss": 0.5514,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8268348623853211,
50
+ "eval_loss": 1.1644270420074463,
51
+ "eval_runtime": 0.8481,
52
+ "eval_samples_per_second": 1028.211,
53
+ "eval_steps_per_second": 8.254,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 5.902872701351506e-05,
59
+ "loss": 0.4642,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8211009174311926,
65
+ "eval_loss": 1.1642404794692993,
66
+ "eval_runtime": 0.8708,
67
+ "eval_samples_per_second": 1001.401,
68
+ "eval_steps_per_second": 8.039,
69
+ "step": 2108
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 5270,
74
+ "num_train_epochs": 10,
75
+ "save_steps": 500,
76
+ "total_flos": 32320254802260.0,
77
+ "trial_name": null,
78
+ "trial_params": {
79
+ "alpha": 0.5936303845454114,
80
+ "learning_rate": 9.835010792324513e-05,
81
+ "num_train_epochs": 10,
82
+ "temperature": 30
83
+ }
84
+ }
run-11/checkpoint-2108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37d4db04d994c090d24d490a7da5025521a5238995701eaf986b4a3ce60b6d24
3
+ size 4664
run-11/checkpoint-2108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-13/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-13/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7481977ec57a3799e410809543b16605fe362acf8c3ae761d4995cb0c22efaf
3
+ size 17549312
run-13/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99ea00293a0cfd15095e8793df22c24272d558a1479414125390360310c97eb
3
+ size 35123898
run-13/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-13/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0e8f7087757bba2f5d30205c5867d8bc8e961f428b7d3da7aa0b4371458baa3
3
+ size 1064
run-13/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-13/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-13/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-13/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8027522935779816,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/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": 8.290547661378887e-05,
14
+ "loss": 0.4418,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8027522935779816,
20
+ "eval_loss": 0.4441070556640625,
21
+ "eval_runtime": 0.9514,
22
+ "eval_samples_per_second": 916.522,
23
+ "eval_steps_per_second": 7.357,
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": 0.9928258166586904,
35
+ "learning_rate": 9.474911613004443e-05,
36
+ "num_train_epochs": 8,
37
+ "temperature": 26
38
+ }
39
+ }
run-13/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e22d1954fb5f2031f95ddeab15d35636742f3c5363e24071e8a4adfc8ae29403
3
+ size 4664
run-13/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 sha256:37d4db04d994c090d24d490a7da5025521a5238995701eaf986b4a3ce60b6d24
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e22d1954fb5f2031f95ddeab15d35636742f3c5363e24071e8a4adfc8ae29403
3
  size 4664