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
62c0e11
·
verified ·
1 Parent(s): f656fa7

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1713611290.a9446dbff3d4.7440.7 +2 -2
  2. logs/events.out.tfevents.1713611332.a9446dbff3d4.7440.8 +3 -0
  3. model.safetensors +1 -1
  4. run-5/checkpoint-640/config.json +34 -0
  5. run-5/checkpoint-640/model.safetensors +3 -0
  6. run-5/checkpoint-640/optimizer.pt +3 -0
  7. run-5/checkpoint-640/rng_state.pth +3 -0
  8. run-5/checkpoint-640/scheduler.pt +3 -0
  9. run-5/checkpoint-640/special_tokens_map.json +7 -0
  10. run-5/checkpoint-640/tokenizer.json +0 -0
  11. run-5/checkpoint-640/tokenizer_config.json +57 -0
  12. run-5/checkpoint-640/trainer_state.json +106 -0
  13. run-5/checkpoint-640/training_args.bin +3 -0
  14. run-5/checkpoint-640/vocab.txt +0 -0
  15. run-6/checkpoint-160/config.json +34 -0
  16. run-6/checkpoint-160/model.safetensors +3 -0
  17. run-6/checkpoint-160/optimizer.pt +3 -0
  18. run-6/checkpoint-160/rng_state.pth +3 -0
  19. run-6/checkpoint-160/scheduler.pt +3 -0
  20. run-6/checkpoint-160/special_tokens_map.json +7 -0
  21. run-6/checkpoint-160/tokenizer.json +0 -0
  22. run-6/checkpoint-160/tokenizer_config.json +57 -0
  23. run-6/checkpoint-160/trainer_state.json +46 -0
  24. run-6/checkpoint-160/training_args.bin +3 -0
  25. run-6/checkpoint-160/vocab.txt +0 -0
  26. training_args.bin +1 -1
logs/events.out.tfevents.1713611290.a9446dbff3d4.7440.7 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a46310afb864e247633d7a7a05f1b94dd9d349ee5f408b7ecfe661c442a0fdff
3
- size 6212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3a335102ea542d12c51b41f0502658b3c2fd89f0f4787300c390b9aacc71e48
3
+ size 8026
logs/events.out.tfevents.1713611332.a9446dbff3d4.7440.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:766c620d60f21e260986a54808ee98b4492ddf72373876e48f761679a36c1e4d
3
+ size 5482
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f525e8451b4902afd8e971b39415474fef1509ada19ad59f421194a0eeaf7efe
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a9aa369fa4fe8e12c2ac8d6ca8981de3eebcba5b2a7e56b6a7417be034c719
3
  size 17549312
run-5/checkpoint-640/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-5/checkpoint-640/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8875c72079f2057d69b99aa9f33c11b77896e824f47ac88701155e0ed2aa32c6
3
+ size 17549312
run-5/checkpoint-640/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8bba1712f12b52b9421ffa19e2ddef39ad098100e95c7b6ad2f35bd1e2d64e2
3
+ size 35123898
run-5/checkpoint-640/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fae3cb80286aa140b95db910a9642553ceeaeadd75e7dc192487af85f7f7af75
3
+ size 14308
run-5/checkpoint-640/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e930f47acf49913aa7b3e01d65e76e5191a55289fc5a131e9089604e3fbeeb5
3
+ size 1064
run-5/checkpoint-640/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-640/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-640/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-640/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6674509803921569,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-5/checkpoint-320",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 640,
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": 0.9986019134521484,
14
+ "learning_rate": 6.067732661916699e-05,
15
+ "loss": 0.3474,
16
+ "step": 160
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.33498698472976685,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 1.8603,
27
+ "eval_samples_per_second": 685.372,
28
+ "eval_steps_per_second": 21.502,
29
+ "step": 160
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 0.9157262444496155,
34
+ "learning_rate": 4.045155107944466e-05,
35
+ "loss": 0.3312,
36
+ "step": 320
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.6674509803921569,
41
+ "eval_f1": 0.004694835680751173,
42
+ "eval_loss": 0.3251466453075409,
43
+ "eval_mcc": 0.03962144258751637,
44
+ "eval_precision": 1.0,
45
+ "eval_recall": 0.002352941176470588,
46
+ "eval_runtime": 1.8638,
47
+ "eval_samples_per_second": 684.076,
48
+ "eval_steps_per_second": 21.461,
49
+ "step": 320
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.6788557767868042,
54
+ "learning_rate": 2.022577553972233e-05,
55
+ "loss": 0.3247,
56
+ "step": 480
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.6666666666666666,
61
+ "eval_f1": 0.049217002237136466,
62
+ "eval_loss": 0.32314401865005493,
63
+ "eval_mcc": 0.046847973719895464,
64
+ "eval_precision": 0.5,
65
+ "eval_recall": 0.02588235294117647,
66
+ "eval_runtime": 1.8829,
67
+ "eval_samples_per_second": 677.158,
68
+ "eval_steps_per_second": 21.244,
69
+ "step": 480
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 0.6379467844963074,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.3227,
76
+ "step": 640
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.6666666666666666,
81
+ "eval_f1": 0.018475750577367205,
82
+ "eval_loss": 0.3209414780139923,
83
+ "eval_mcc": 0.028093878027715367,
84
+ "eval_precision": 0.5,
85
+ "eval_recall": 0.009411764705882352,
86
+ "eval_runtime": 1.8827,
87
+ "eval_samples_per_second": 677.207,
88
+ "eval_steps_per_second": 21.246,
89
+ "step": 640
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 640,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 4,
96
+ "save_steps": 500,
97
+ "total_flos": 1167021751680.0,
98
+ "train_batch_size": 32,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.5122281577891578,
102
+ "learning_rate": 8.090310215888932e-05,
103
+ "num_train_epochs": 4,
104
+ "temperature": 14
105
+ }
106
+ }
run-5/checkpoint-640/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ffdc018305c7641913fb33119db0342b974e7cbd16a23cd7b923a830af0c23d
3
+ size 5048
run-5/checkpoint-640/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-160/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-6/checkpoint-160/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a9aa369fa4fe8e12c2ac8d6ca8981de3eebcba5b2a7e56b6a7417be034c719
3
+ size 17549312
run-6/checkpoint-160/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5bc697643b513962a784b5cb3a6cde7fa5309c547c5b0fa691c8178b9e7fdf5
3
+ size 35123898
run-6/checkpoint-160/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0792eaff268dd73c8e104b5060a487f4ef56535ad3b58888006338b8bc298137
3
+ size 14308
run-6/checkpoint-160/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1297ea273aa9c8ab10d13a3075573818c096ced4a00d66b13402cfcad10574e7
3
+ size 1064
run-6/checkpoint-160/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-6/checkpoint-160/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-160/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-6/checkpoint-160/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6666666666666666,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-6/checkpoint-160",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 160,
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": 0.8079733848571777,
14
+ "learning_rate": 5.379067903396322e-05,
15
+ "loss": 0.0738,
16
+ "step": 160
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6666666666666666,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.05636660009622574,
23
+ "eval_mcc": 0.0,
24
+ "eval_precision": 0.0,
25
+ "eval_recall": 0.0,
26
+ "eval_runtime": 1.8691,
27
+ "eval_samples_per_second": 682.132,
28
+ "eval_steps_per_second": 21.4,
29
+ "step": 160
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 960,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 6,
36
+ "save_steps": 500,
37
+ "total_flos": 291755437920.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.062310076275025716,
42
+ "learning_rate": 6.454881484075586e-05,
43
+ "num_train_epochs": 6,
44
+ "temperature": 27
45
+ }
46
+ }
run-6/checkpoint-160/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:874377bb5cc66029b2e8d2a1579f2feeb10b9a486f35c6379123c12f1d35621c
3
+ size 5048
run-6/checkpoint-160/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 sha256:1ffdc018305c7641913fb33119db0342b974e7cbd16a23cd7b923a830af0c23d
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:874377bb5cc66029b2e8d2a1579f2feeb10b9a486f35c6379123c12f1d35621c
3
  size 5048