Hugging Face's logo

xuancoblab2023
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
xuancoblab2023 commited on
Commit
16cb551
·
verified ·
1 Parent(s): 80e12d1

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1713586947.1376c752d37a.9760.0 +2 -2
  2. logs/events.out.tfevents.1713587014.1376c752d37a.9760.1 +3 -0
  3. model.safetensors +1 -1
  4. run-0/checkpoint-856/config.json +34 -0
  5. run-0/checkpoint-856/model.safetensors +3 -0
  6. run-0/checkpoint-856/optimizer.pt +3 -0
  7. run-0/checkpoint-856/rng_state.pth +3 -0
  8. run-0/checkpoint-856/scheduler.pt +3 -0
  9. run-0/checkpoint-856/special_tokens_map.json +7 -0
  10. run-0/checkpoint-856/tokenizer.json +0 -0
  11. run-0/checkpoint-856/tokenizer_config.json +57 -0
  12. run-0/checkpoint-856/trainer_state.json +106 -0
  13. run-0/checkpoint-856/training_args.bin +3 -0
  14. run-0/checkpoint-856/vocab.txt +0 -0
  15. run-1/checkpoint-214/config.json +34 -0
  16. run-1/checkpoint-214/model.safetensors +3 -0
  17. run-1/checkpoint-214/optimizer.pt +3 -0
  18. run-1/checkpoint-214/rng_state.pth +3 -0
  19. run-1/checkpoint-214/scheduler.pt +3 -0
  20. run-1/checkpoint-214/special_tokens_map.json +7 -0
  21. run-1/checkpoint-214/tokenizer.json +0 -0
  22. run-1/checkpoint-214/tokenizer_config.json +57 -0
  23. run-1/checkpoint-214/trainer_state.json +46 -0
  24. run-1/checkpoint-214/training_args.bin +3 -0
  25. run-1/checkpoint-214/vocab.txt +0 -0
  26. training_args.bin +1 -1
logs/events.out.tfevents.1713586947.1376c752d37a.9760.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be6e33f858feaae36d9336585904c208ee321151a71b362bb7e888d3608c0089
3
- size 6213
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a628f1f0478bb1fa75b24c99ed95bec2abca3ec9a298f55ccc8f08d04030521
3
+ size 8027
logs/events.out.tfevents.1713587014.1376c752d37a.9760.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:844bc9a6f01697d443f25bad995929af7bb83749b8768ce1b6a5833b96bf69d1
3
+ size 5482
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:952d6130866f4c5830ed1aac76b56f7fdb3b045a444ce21d96e28fd594997a09
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1246b75d1fe5c85a8e4a895ed2a3e1a0873d9eded181f38336b8ce37d3f5697d
3
  size 17549312
run-0/checkpoint-856/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": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-0/checkpoint-856/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb64ef04110bd0cd29348bff3a2ed6e21b47fdda4215860bcc2a052a8b78cd18
3
+ size 17549312
run-0/checkpoint-856/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2078cd2af0c951b30df62718b156cad44a07ac90a2a20e72e2ae9efc26dc4952
3
+ size 35123898
run-0/checkpoint-856/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:057111bfbb4d541cc190a3ed4fcfe228e7425a50e4a06afd33224d43272b1a59
3
+ size 14308
run-0/checkpoint-856/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08abd2f47237a0771e55ede3215ba35ba9b0badf7493e6feb84c0245305a0b8a
3
+ size 1064
run-0/checkpoint-856/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-0/checkpoint-856/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-856/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-0/checkpoint-856/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6666666666666666,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-214",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 856,
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
+ "grad_norm": 2.621731758117676,
14
+ "learning_rate": 8.86126667135369e-06,
15
+ "loss": 0.5024,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.4761257767677307,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 3.027,
27
+ "eval_samples_per_second": 563.925,
28
+ "eval_steps_per_second": 17.839,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.105258584022522,
34
+ "learning_rate": 5.907511114235794e-06,
35
+ "loss": 0.4761,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6666666666666666,
41
+ "eval_f1": 0.0,
42
+ "eval_loss": 0.4718354642391205,
43
+ "eval_mcc": 0.0,
44
+ "eval_precision": 0.0,
45
+ "eval_recall": 0.0,
46
+ "eval_runtime": 3.1045,
47
+ "eval_samples_per_second": 549.843,
48
+ "eval_steps_per_second": 17.394,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.9062323570251465,
54
+ "learning_rate": 2.953755557117897e-06,
55
+ "loss": 0.4732,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.6666666666666666,
61
+ "eval_f1": 0.0,
62
+ "eval_loss": 0.46850961446762085,
63
+ "eval_mcc": 0.0,
64
+ "eval_precision": 0.0,
65
+ "eval_recall": 0.0,
66
+ "eval_runtime": 3.1679,
67
+ "eval_samples_per_second": 538.848,
68
+ "eval_steps_per_second": 17.046,
69
+ "step": 642
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.8504718542099,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.4715,
76
+ "step": 856
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6666666666666666,
81
+ "eval_f1": 0.0,
82
+ "eval_loss": 0.4676384925842285,
83
+ "eval_mcc": 0.0,
84
+ "eval_precision": 0.0,
85
+ "eval_recall": 0.0,
86
+ "eval_runtime": 3.178,
87
+ "eval_samples_per_second": 537.136,
88
+ "eval_steps_per_second": 16.992,
89
+ "step": 856
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 856,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 4,
96
+ "save_steps": 500,
97
+ "total_flos": 2099102657760.0,
98
+ "train_batch_size": 32,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.7337380456487411,
102
+ "learning_rate": 1.1815022228471587e-05,
103
+ "num_train_epochs": 4,
104
+ "temperature": 14
105
+ }
106
+ }
run-0/checkpoint-856/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1ef4ebce0580268fde2cec4cf96d669c8d482ee4f83099bbcdf4ab3eb2af99d
3
+ size 5048
run-0/checkpoint-856/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-214/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": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-1/checkpoint-214/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1246b75d1fe5c85a8e4a895ed2a3e1a0873d9eded181f38336b8ce37d3f5697d
3
+ size 17549312
run-1/checkpoint-214/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8147100ad3d60aae24343a9e3a2868211f630ea6764f30bea9b2bb39e6f268b
3
+ size 35123898
run-1/checkpoint-214/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc7e492e6768bc7c3c01ac823da5a8177cf34fc1b175dd727fa3be969661a151
3
+ size 14308
run-1/checkpoint-214/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b009a0a959b8559f4e9c7aa91ab4b6ed129e1099c0c21c0eafc1c095a7c2d8
3
+ size 1064
run-1/checkpoint-214/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-1/checkpoint-214/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-214/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-1/checkpoint-214/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6666666666666666,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-214",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 214,
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
+ "grad_norm": 3.7990000247955322,
14
+ "learning_rate": 1.1192818975380277e-05,
15
+ "loss": 0.6296,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.609692394733429,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 3.1451,
27
+ "eval_samples_per_second": 542.745,
28
+ "eval_steps_per_second": 17.169,
29
+ "step": 214
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 856,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 4,
36
+ "save_steps": 500,
37
+ "total_flos": 524775664440.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.9645989967572975,
42
+ "learning_rate": 1.492375863384037e-05,
43
+ "num_train_epochs": 4,
44
+ "temperature": 9
45
+ }
46
+ }
run-1/checkpoint-214/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa71a1dbca872ec7f309fce727a04ece03e497d7aba911b02f734944bff7047
3
+ size 5048
run-1/checkpoint-214/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:b1ef4ebce0580268fde2cec4cf96d669c8d482ee4f83099bbcdf4ab3eb2af99d
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa71a1dbca872ec7f309fce727a04ece03e497d7aba911b02f734944bff7047
3
  size 5048