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
97548fb
·
1 Parent(s): f505479

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1699950902.45c71320b2c6.349.11 +2 -2
  2. logs/events.out.tfevents.1699951173.45c71320b2c6.349.12 +3 -0
  3. model.safetensors +1 -1
  4. run-10/checkpoint-1581/config.json +34 -0
  5. run-10/checkpoint-1581/model.safetensors +3 -0
  6. run-10/checkpoint-1581/optimizer.pt +3 -0
  7. run-10/checkpoint-1581/rng_state.pth +3 -0
  8. run-10/checkpoint-1581/scheduler.pt +3 -0
  9. run-10/checkpoint-1581/special_tokens_map.json +7 -0
  10. run-10/checkpoint-1581/tokenizer.json +0 -0
  11. run-10/checkpoint-1581/tokenizer_config.json +57 -0
  12. run-10/checkpoint-1581/trainer_state.json +69 -0
  13. run-10/checkpoint-1581/training_args.bin +3 -0
  14. run-10/checkpoint-1581/vocab.txt +0 -0
  15. run-11/checkpoint-527/config.json +34 -0
  16. run-11/checkpoint-527/model.safetensors +3 -0
  17. run-11/checkpoint-527/optimizer.pt +3 -0
  18. run-11/checkpoint-527/rng_state.pth +3 -0
  19. run-11/checkpoint-527/scheduler.pt +3 -0
  20. run-11/checkpoint-527/special_tokens_map.json +7 -0
  21. run-11/checkpoint-527/tokenizer.json +0 -0
  22. run-11/checkpoint-527/tokenizer_config.json +57 -0
  23. run-11/checkpoint-527/trainer_state.json +39 -0
  24. run-11/checkpoint-527/training_args.bin +3 -0
  25. run-11/checkpoint-527/vocab.txt +0 -0
  26. training_args.bin +1 -1
logs/events.out.tfevents.1699950902.45c71320b2c6.349.11 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d14f26098a9f85f7f800ec22c42992ffdc5d1469fcf239794ce05a37d25514ca
3
- size 5254
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54676538fe2daaef98934d58299c690b1c77aa61ef94e9b333484d9b4f81d238
3
+ size 6214
logs/events.out.tfevents.1699951173.45c71320b2c6.349.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9de9d8d7a16d0b00f679f5e9f3b6b72424030ad3a747e7eb4bc85402d322dd
3
+ size 4774
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:561f4ea6e4038a507c577b59360561e2cf4cb75aed13d0164a4dbfae6f124b3d
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d29a20baa1b804ed752cb770dafddf31466d5f2d1d8e95037775fd9ca7f9d73d
3
  size 17549312
run-10/checkpoint-1581/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-10/checkpoint-1581/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56bc32a1abc46a1d91df71a9c59db5c748c53777fac3397ee32f4d20521931b4
3
+ size 17549312
run-10/checkpoint-1581/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c210e4f591bb5d708ab545cc6fd3955d52c7303353938e91c6f657aaa66d8fc5
3
+ size 35123898
run-10/checkpoint-1581/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0145a794c4550fd779295bb332661a545e0c28f08ca5060bf05d2337c4c7b4d2
3
+ size 14308
run-10/checkpoint-1581/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69e9192c1e81322aab2cb11dd7fba5d86dcf373eec20e89d385db0c8ca135abe
3
+ size 1064
run-10/checkpoint-1581/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-10/checkpoint-1581/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-10/checkpoint-1581/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-10/checkpoint-1581/trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8222477064220184,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/checkpoint-527",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1581,
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": 0.0005718052284282855,
14
+ "loss": 0.8086,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8222477064220184,
20
+ "eval_loss": 0.9947215914726257,
21
+ "eval_runtime": 0.9316,
22
+ "eval_samples_per_second": 935.976,
23
+ "eval_steps_per_second": 7.514,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.000508271314158476,
29
+ "loss": 0.3833,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8027522935779816,
35
+ "eval_loss": 1.1898581981658936,
36
+ "eval_runtime": 0.853,
37
+ "eval_samples_per_second": 1022.311,
38
+ "eval_steps_per_second": 8.207,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 0.0004447373998886664,
44
+ "loss": 0.2601,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8084862385321101,
50
+ "eval_loss": 1.3631923198699951,
51
+ "eval_runtime": 0.8565,
52
+ "eval_samples_per_second": 1018.104,
53
+ "eval_steps_per_second": 8.173,
54
+ "step": 1581
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 5270,
59
+ "num_train_epochs": 10,
60
+ "save_steps": 500,
61
+ "total_flos": 24280106603460.0,
62
+ "trial_name": null,
63
+ "trial_params": {
64
+ "alpha": 0.6602865616625522,
65
+ "learning_rate": 0.0006353391426980949,
66
+ "num_train_epochs": 10,
67
+ "temperature": 22
68
+ }
69
+ }
run-10/checkpoint-1581/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9521568b4c35ddb8f99dab3e9093ba9e261d765428d86fec84d91d6bf0f03abe
3
+ size 4664
run-10/checkpoint-1581/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-11/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-11/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d29a20baa1b804ed752cb770dafddf31466d5f2d1d8e95037775fd9ca7f9d73d
3
+ size 17549312
run-11/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce4058cd056775c1b500bfa78fae435365fe729c5c724d20c341e01c0d14174
3
+ size 35123898
run-11/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-11/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e741afddc5e9c942ed4827591a2caee5680804c82b2b7e1b294b71c1577e958
3
+ size 1064
run-11/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-11/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-11/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-11/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8084862385321101,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/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": 8.853375939048859e-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
+ "logging_steps": 500,
28
+ "max_steps": 5270,
29
+ "num_train_epochs": 10,
30
+ "save_steps": 500,
31
+ "total_flos": 8117476690260.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.5936303845454114,
35
+ "learning_rate": 9.835010792324513e-05,
36
+ "num_train_epochs": 10,
37
+ "temperature": 30
38
+ }
39
+ }
run-11/checkpoint-527/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-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 sha256:9521568b4c35ddb8f99dab3e9093ba9e261d765428d86fec84d91d6bf0f03abe
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37d4db04d994c090d24d490a7da5025521a5238995701eaf986b4a3ce60b6d24
3
  size 4664