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
398e224
·
verified ·
1 Parent(s): 6cc00de

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1709553057.11df171e7ffa.529.2 +2 -2
  2. logs/events.out.tfevents.1709558881.11df171e7ffa.529.3 +3 -0
  3. model.safetensors +1 -1
  4. run-0/checkpoint-375/config.json +34 -0
  5. run-0/checkpoint-375/model.safetensors +3 -0
  6. run-0/checkpoint-375/optimizer.pt +3 -0
  7. run-0/checkpoint-375/rng_state.pth +3 -0
  8. run-0/checkpoint-375/scheduler.pt +3 -0
  9. run-0/checkpoint-375/special_tokens_map.json +7 -0
  10. run-0/checkpoint-375/tokenizer.json +0 -0
  11. run-0/checkpoint-375/tokenizer_config.json +57 -0
  12. run-0/checkpoint-375/trainer_state.json +106 -0
  13. run-0/checkpoint-375/training_args.bin +3 -0
  14. run-0/checkpoint-375/vocab.txt +0 -0
  15. run-1/checkpoint-75/config.json +34 -0
  16. run-1/checkpoint-75/model.safetensors +3 -0
  17. run-1/checkpoint-75/optimizer.pt +3 -0
  18. run-1/checkpoint-75/rng_state.pth +3 -0
  19. run-1/checkpoint-75/scheduler.pt +3 -0
  20. run-1/checkpoint-75/special_tokens_map.json +7 -0
  21. run-1/checkpoint-75/tokenizer.json +0 -0
  22. run-1/checkpoint-75/tokenizer_config.json +57 -0
  23. run-1/checkpoint-75/trainer_state.json +42 -0
  24. run-1/checkpoint-75/training_args.bin +3 -0
  25. run-1/checkpoint-75/vocab.txt +0 -0
  26. training_args.bin +1 -1
logs/events.out.tfevents.1709553057.11df171e7ffa.529.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6b37859b6cd1af402d3caca60337040d9be5a39c5d3393a383827d73b2e1399
3
- size 5705
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79ad369b4e81cfe27467bc4fc9ac91997e5d1a24b2cc9605cd1770085600c365
3
+ size 7661
logs/events.out.tfevents.1709558881.11df171e7ffa.529.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c07543418b98e3b312677474faf28fe807d4cdae025821f616a789aa0f1eb68
3
+ size 5170
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d58208b0ddc02f75930b9008c9f7cc555ee87161825ee38fa8856e14556baa14
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:520ec340aa4df8b503086dc909ace3b33eb50a219a790a0942828b07d2ee9cd7
3
  size 17549312
run-0/checkpoint-375/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-0/checkpoint-375/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd2dc489eaa3cd72c1ba76100241f35dded8b38028de976d3f9a2f6a52974a82
3
+ size 17549312
run-0/checkpoint-375/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:509a99ae3a65420088a549698dcf175e2bad812f1aed3ff46c3a634694309393
3
+ size 35122746
run-0/checkpoint-375/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c14eb8f89902058ad595279205959d8cab05770e2b1ff80058565f001236409
3
+ size 14054
run-0/checkpoint-375/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc3f8a2327766d45e5c624a96fc23be019487a2034bd7b3288112c0ca2c55c64
3
+ size 1064
run-0/checkpoint-375/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-375/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-375/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-375/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5148514851485149,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-75",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 375,
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": 0.31773510575294495,
14
+ "learning_rate": 0.00019498896290528944,
15
+ "loss": 0.0964,
16
+ "step": 75
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.5148514851485149,
21
+ "eval_loss": 0.077483631670475,
22
+ "eval_runtime": 57.3954,
23
+ "eval_samples_per_second": 8.799,
24
+ "eval_steps_per_second": 0.07,
25
+ "step": 75
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 0.29849082231521606,
30
+ "learning_rate": 0.00014624172217896707,
31
+ "loss": 0.0774,
32
+ "step": 150
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.5069306930693069,
37
+ "eval_loss": 0.07408903539180756,
38
+ "eval_runtime": 57.3815,
39
+ "eval_samples_per_second": 8.801,
40
+ "eval_steps_per_second": 0.07,
41
+ "step": 150
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 0.17056742310523987,
46
+ "learning_rate": 9.749448145264472e-05,
47
+ "loss": 0.0761,
48
+ "step": 225
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.5089108910891089,
53
+ "eval_loss": 0.07352373003959656,
54
+ "eval_runtime": 56.7092,
55
+ "eval_samples_per_second": 8.905,
56
+ "eval_steps_per_second": 0.071,
57
+ "step": 225
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 0.1569105088710785,
62
+ "learning_rate": 4.874724072632236e-05,
63
+ "loss": 0.0757,
64
+ "step": 300
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.5089108910891089,
69
+ "eval_loss": 0.07332208752632141,
70
+ "eval_runtime": 56.6672,
71
+ "eval_samples_per_second": 8.912,
72
+ "eval_steps_per_second": 0.071,
73
+ "step": 300
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 0.2125726044178009,
78
+ "learning_rate": 0.0,
79
+ "loss": 0.0752,
80
+ "step": 375
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.5089108910891089,
85
+ "eval_loss": 0.07323028892278671,
86
+ "eval_runtime": 56.4903,
87
+ "eval_samples_per_second": 8.94,
88
+ "eval_steps_per_second": 0.071,
89
+ "step": 375
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 375,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 5,
96
+ "save_steps": 500,
97
+ "total_flos": 3889216415700.0,
98
+ "train_batch_size": 128,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.08009223161090917,
102
+ "learning_rate": 0.00024373620363161177,
103
+ "num_train_epochs": 5,
104
+ "temperature": 24
105
+ }
106
+ }
run-0/checkpoint-375/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c07c5338ce9724729e2f99d42abdb57887932f817eb41546efc9c3b2ccad442
3
+ size 4984
run-0/checkpoint-375/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-75/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-1/checkpoint-75/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:520ec340aa4df8b503086dc909ace3b33eb50a219a790a0942828b07d2ee9cd7
3
+ size 17549312
run-1/checkpoint-75/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddca34829f48bfb278cc070912aff3f9180aeb8402448abadd867486f2477fe7
3
+ size 35122746
run-1/checkpoint-75/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ac8d6c67447a15b9d51f14179a6a091394591d74ba40110b627bf9167b78171
3
+ size 14054
run-1/checkpoint-75/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ee717f5c672f33c031226422f5b7a2e084949fea8bf7a985da1c71963fd8f60
3
+ size 1064
run-1/checkpoint-75/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-75/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-75/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-75/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.500990099009901,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-75",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 75,
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": 0.6191820502281189,
14
+ "learning_rate": 5.7462097344528874e-05,
15
+ "loss": 0.3664,
16
+ "step": 75
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.500990099009901,
21
+ "eval_loss": 0.35016587376594543,
22
+ "eval_runtime": 57.4035,
23
+ "eval_samples_per_second": 8.797,
24
+ "eval_steps_per_second": 0.07,
25
+ "step": 75
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 750,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 10,
32
+ "save_steps": 500,
33
+ "total_flos": 777843283140.0,
34
+ "train_batch_size": 128,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "alpha": 0.43390314470052016,
38
+ "learning_rate": 6.38467748272543e-05,
39
+ "num_train_epochs": 10,
40
+ "temperature": 19
41
+ }
42
+ }
run-1/checkpoint-75/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ff426f4757a4f504cf77c7e8084960f1d507afe91f1f5a1d1874fd6fdbd5812
3
+ size 4984
run-1/checkpoint-75/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 sha256:3c07c5338ce9724729e2f99d42abdb57887932f817eb41546efc9c3b2ccad442
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ff426f4757a4f504cf77c7e8084960f1d507afe91f1f5a1d1874fd6fdbd5812
3
  size 4984