Hugging Face's logo

jysh1023
/
tiny-bert-sst2-distilled_original

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
jysh1023 commited on
Commit
6a0f185
·
1 Parent(s): a445e54

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1700285285.bdba95a6283e.570.7 +2 -2
  2. logs/events.out.tfevents.1700285685.bdba95a6283e.570.8 +3 -0
  3. model.safetensors +1 -1
  4. run-4/checkpoint-1054/config.json +34 -0
  5. run-4/checkpoint-1054/model.safetensors +3 -0
  6. run-4/checkpoint-1054/optimizer.pt +3 -0
  7. run-4/checkpoint-1054/rng_state.pth +3 -0
  8. run-4/checkpoint-1054/scheduler.pt +3 -0
  9. run-4/checkpoint-1054/special_tokens_map.json +7 -0
  10. run-4/checkpoint-1054/tokenizer.json +0 -0
  11. run-4/checkpoint-1054/tokenizer_config.json +57 -0
  12. run-4/checkpoint-1054/trainer_state.json +54 -0
  13. run-4/checkpoint-1054/training_args.bin +3 -0
  14. run-4/checkpoint-1054/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.1700285285.bdba95a6283e.570.7 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5d31a16baff08f5dd59ea33391489ef84275615930962fb5fd29f836519590b
3
- size 4809
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:056721a9107ec0d97c9b058ad8de29b995591bb804da5dc75d8a613170d35ae1
3
+ size 5643
logs/events.out.tfevents.1700285685.bdba95a6283e.570.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab8d21ded6ccc0f21bcdf2f7fd9a11f9cfd55d86a0d1780bf92497fbbf84093e
3
+ size 4809
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bec741eb50ca966021fc5eb858b611d56bfab0d2542f2e7b6771c1c2678f2b30
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8412eacc2cfb1cbbf5ba2f3078f852fea92a9778c5c5b71dda10a2436f6689bf
3
  size 17549312
run-4/checkpoint-1054/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": "4.35.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-4/checkpoint-1054/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:658a31625d712751c32c83418362138cc20db694670c47a0736572f9ce8ed17c
3
+ size 17549312
run-4/checkpoint-1054/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:829c62be8820a556ae249060d4f2c6a8c3dd1d5d32472bc49cafe0b7d741e91a
3
+ size 35123898
run-4/checkpoint-1054/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:257145d19710cbf39344544002ce35377faa97e289b8c6f1104c9033e98d4161
3
+ size 14308
run-4/checkpoint-1054/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:709d96ec33b79e2862f330e84a8bce8a11836c81e3953993dcfa6510531c961d
3
+ size 1064
run-4/checkpoint-1054/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-1054/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-1054/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-1054/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8245412844036697,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled_original/run-4/checkpoint-527",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1054,
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": 0.00026263729264372335,
14
+ "loss": 0.3473,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8245412844036697,
20
+ "eval_loss": 0.4497273862361908,
21
+ "eval_runtime": 2.7322,
22
+ "eval_samples_per_second": 319.158,
23
+ "eval_steps_per_second": 2.562,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.0,
29
+ "loss": 0.1899,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8119266055045872,
35
+ "eval_loss": 0.5498592853546143,
36
+ "eval_runtime": 2.6954,
37
+ "eval_samples_per_second": 323.513,
38
+ "eval_steps_per_second": 2.597,
39
+ "step": 1054
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 1054,
44
+ "num_train_epochs": 2,
45
+ "save_steps": 500,
46
+ "total_flos": 16194449161860.0,
47
+ "trial_name": null,
48
+ "trial_params": {
49
+ "alpha": 0.9886564369229293,
50
+ "learning_rate": 0.0005252745852874467,
51
+ "num_train_epochs": 2,
52
+ "temperature": 23
53
+ }
54
+ }
run-4/checkpoint-1054/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:104618e22d255edd417a8506be527da66f3b1071557d7321cb32843026f9257f
3
+ size 4664
run-4/checkpoint-1054/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": "4.35.2",
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 sha256:8412eacc2cfb1cbbf5ba2f3078f852fea92a9778c5c5b71dda10a2436f6689bf
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:ebff4fa62945d7098687d97303cc4073a2730490541a4552b1cc524b3fc4c8df
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:df95bce5c5c16e60e49eb22753b34dbfa7966d22f239bd4ae61a5f9a0e6ccf0d
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 sha256:871cfd622b6e72840fc4cb0f334393c2a4bdc9e955ea45bcbb8f81ae6c3c421d
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": 0.8119266055045872,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled_original/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": 0.0006521893115545731,
14
+ "loss": 1.1514,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8119266055045872,
20
+ "eval_loss": 1.6072802543640137,
21
+ "eval_runtime": 2.6998,
22
+ "eval_samples_per_second": 322.982,
23
+ "eval_steps_per_second": 2.593,
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": 0.33140181919816125,
35
+ "learning_rate": 0.0007337129754988948,
36
+ "num_train_epochs": 9,
37
+ "temperature": 8
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 sha256:75a07f86b5e6b9a8e9e28b1a380cc79b873a2cbfbfffbb4b2f2beac31c3225e5
3
+ size 4664
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 sha256:104618e22d255edd417a8506be527da66f3b1071557d7321cb32843026f9257f
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a07f86b5e6b9a8e9e28b1a380cc79b873a2cbfbfffbb4b2f2beac31c3225e5
3
  size 4664