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
bc15186
·
verified ·
1 Parent(s): c17dfd4

Training in progress, epoch 1

Browse files
Files changed (28) hide show
  1. logs/events.out.tfevents.1709467127.49ae8f4e8e7b.1647.39 +2 -2
  2. logs/events.out.tfevents.1709468352.49ae8f4e8e7b.1647.40 +3 -0
  3. logs/events.out.tfevents.1709468554.49ae8f4e8e7b.1647.41 +3 -0
  4. logs/events.out.tfevents.1709468757.49ae8f4e8e7b.1647.42 +3 -0
  5. model.safetensors +1 -1
  6. run-38/checkpoint-3162/config.json +34 -0
  7. run-38/checkpoint-3162/model.safetensors +3 -0
  8. run-38/checkpoint-3162/optimizer.pt +3 -0
  9. run-38/checkpoint-3162/rng_state.pth +3 -0
  10. run-38/checkpoint-3162/scheduler.pt +3 -0
  11. run-38/checkpoint-3162/special_tokens_map.json +7 -0
  12. run-38/checkpoint-3162/tokenizer.json +0 -0
  13. run-38/checkpoint-3162/tokenizer_config.json +57 -0
  14. run-38/checkpoint-3162/trainer_state.json +122 -0
  15. run-38/checkpoint-3162/training_args.bin +3 -0
  16. run-38/checkpoint-3162/vocab.txt +0 -0
  17. run-41/checkpoint-527/config.json +34 -0
  18. run-41/checkpoint-527/model.safetensors +3 -0
  19. run-41/checkpoint-527/optimizer.pt +3 -0
  20. run-41/checkpoint-527/rng_state.pth +3 -0
  21. run-41/checkpoint-527/scheduler.pt +3 -0
  22. run-41/checkpoint-527/special_tokens_map.json +7 -0
  23. run-41/checkpoint-527/tokenizer.json +0 -0
  24. run-41/checkpoint-527/tokenizer_config.json +57 -0
  25. run-41/checkpoint-527/trainer_state.json +42 -0
  26. run-41/checkpoint-527/training_args.bin +3 -0
  27. run-41/checkpoint-527/vocab.txt +0 -0
  28. training_args.bin +1 -1
logs/events.out.tfevents.1709467127.49ae8f4e8e7b.1647.39 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8c9052a7bbe97e18c77a64ddb2a4e150206d4ab886a80dd396e8c0277145c40
3
- size 5714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1459e5f70f8dd347bd38d19bcb57ce8e5faeadb93998cd376d86dc3a8700ca9
3
+ size 8204
logs/events.out.tfevents.1709468352.49ae8f4e8e7b.1647.40 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e5b79a755d6836239ddc362947e7e71d0a2981468f9fd45e60590ec23141358
3
+ size 5179
logs/events.out.tfevents.1709468554.49ae8f4e8e7b.1647.41 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fd3dbdaa57fdaadff8ef5d73fbc1a0d98fc572af3b5a9b98415092f7232a005
3
+ size 5180
logs/events.out.tfevents.1709468757.49ae8f4e8e7b.1647.42 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:551d93821ed1a5cc65d84d5681f95aa4dab3dcbfea4df83bbdefd64c963b3910
3
+ size 5180
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf31aeba08693b3be127ceb0ca75998cb34628f790d2234fad6f7d950a5d1ea4
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3331d46e55fbbf222bfc3e4de56859f9adc2724280d5dea3f1ffaf1167aaeda3
3
  size 17549312
run-38/checkpoint-3162/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-38/checkpoint-3162/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eda3e77bc08a2ce1ac3395959050ef6b13299034158443d8bc0fdb3be9383730
3
+ size 17549312
run-38/checkpoint-3162/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be3e02a993f4f663505838a62ac53efbdaf04a763c4983d1269bbad8d417a29e
3
+ size 35123898
run-38/checkpoint-3162/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:325174c6b534997502739bbdb7dbf427d5dd29029c4826f2d9412e96c82e681b
3
+ size 14308
run-38/checkpoint-3162/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40ae1a00ec462ce2101d17aef3693473772407a339d0023591ef2f1d6cfeea57
3
+ size 1064
run-38/checkpoint-3162/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-38/checkpoint-3162/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-38/checkpoint-3162/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-38/checkpoint-3162/trainer_state.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8371559633027523,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-38/checkpoint-527",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3162,
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": 6.650190353393555,
14
+ "learning_rate": 0.0003977381702368286,
15
+ "loss": 0.8907,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8371559633027523,
21
+ "eval_loss": 1.0675474405288696,
22
+ "eval_runtime": 2.812,
23
+ "eval_samples_per_second": 310.097,
24
+ "eval_steps_per_second": 2.489,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 7.2698974609375,
30
+ "learning_rate": 0.0003181905361894629,
31
+ "loss": 0.4134,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.8084862385321101,
37
+ "eval_loss": 1.2476831674575806,
38
+ "eval_runtime": 2.8048,
39
+ "eval_samples_per_second": 310.9,
40
+ "eval_steps_per_second": 2.496,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 14.755233764648438,
46
+ "learning_rate": 0.00023864290214209717,
47
+ "loss": 0.2802,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8119266055045872,
53
+ "eval_loss": 1.312410831451416,
54
+ "eval_runtime": 2.8236,
55
+ "eval_samples_per_second": 308.82,
56
+ "eval_steps_per_second": 2.479,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 4.266346454620361,
62
+ "learning_rate": 0.00015909526809473144,
63
+ "loss": 0.208,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.8130733944954128,
69
+ "eval_loss": 1.2842535972595215,
70
+ "eval_runtime": 2.8057,
71
+ "eval_samples_per_second": 310.791,
72
+ "eval_steps_per_second": 2.495,
73
+ "step": 2108
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 4.0564045906066895,
78
+ "learning_rate": 7.969857832449545e-05,
79
+ "loss": 0.1663,
80
+ "step": 2635
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.823394495412844,
85
+ "eval_loss": 1.2945654392242432,
86
+ "eval_runtime": 2.8126,
87
+ "eval_samples_per_second": 310.037,
88
+ "eval_steps_per_second": 2.489,
89
+ "step": 2635
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "grad_norm": 8.322790145874023,
94
+ "learning_rate": 1.5094427712972622e-07,
95
+ "loss": 0.1392,
96
+ "step": 3162
97
+ },
98
+ {
99
+ "epoch": 6.0,
100
+ "eval_accuracy": 0.8176605504587156,
101
+ "eval_loss": 1.3337725400924683,
102
+ "eval_runtime": 2.8133,
103
+ "eval_samples_per_second": 309.956,
104
+ "eval_steps_per_second": 2.488,
105
+ "step": 3162
106
+ }
107
+ ],
108
+ "logging_steps": 500,
109
+ "max_steps": 3162,
110
+ "num_input_tokens_seen": 0,
111
+ "num_train_epochs": 6,
112
+ "save_steps": 500,
113
+ "total_flos": 48527917525620.0,
114
+ "train_batch_size": 128,
115
+ "trial_name": null,
116
+ "trial_params": {
117
+ "alpha": 0.63744345806538,
118
+ "learning_rate": 0.00047728580428419435,
119
+ "num_train_epochs": 6,
120
+ "temperature": 29
121
+ }
122
+ }
run-38/checkpoint-3162/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:581646305b00ffbfb4f29f1a1f4488e755bc99291408fa58ac2f91d116c96ba1
3
+ size 4984
run-38/checkpoint-3162/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-41/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": "4.38.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-41/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3331d46e55fbbf222bfc3e4de56859f9adc2724280d5dea3f1ffaf1167aaeda3
3
+ size 17549312
run-41/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2312a7dc9a046641c4bcbe113cdc0cffa39dafd5bc3132dbca2bba9ebc533f2
3
+ size 35123898
run-41/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a32291cb0c1329fbb9596dcc47c5d9b0d1f71ecc09dad1791e0b193314659e4
3
+ size 14308
run-41/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:768e815fab4521369534cf86654459722c4a930b4bf717d9f4adb32f42fe2ac2
3
+ size 1064
run-41/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-41/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-41/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-41/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8314220183486238,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-41/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
+ "grad_norm": 13.133516311645508,
14
+ "learning_rate": 0.00019951632086846584,
15
+ "loss": 0.9141,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8314220183486238,
21
+ "eval_loss": 0.9435493350028992,
22
+ "eval_runtime": 2.8138,
23
+ "eval_samples_per_second": 309.897,
24
+ "eval_steps_per_second": 2.488,
25
+ "step": 527
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 2108,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 4,
32
+ "save_steps": 500,
33
+ "total_flos": 8057768762220.0,
34
+ "train_batch_size": 128,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "alpha": 0.6708040997397258,
38
+ "learning_rate": 0.00026602176115795445,
39
+ "num_train_epochs": 4,
40
+ "temperature": 9
41
+ }
42
+ }
run-41/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2adff437ca68eed683765ea8c06e84c2925a22031efd61ee00828959779464a
3
+ size 4984
run-41/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 sha256:581646305b00ffbfb4f29f1a1f4488e755bc99291408fa58ac2f91d116c96ba1
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2adff437ca68eed683765ea8c06e84c2925a22031efd61ee00828959779464a
3
  size 4984