Hugging Face's logo

JeukHwang
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
text-embeddings-inference
Model card Files
xet
Metrics Community
JeukHwang commited on
Commit
cd0fd90
·
1 Parent(s): eeda3af

Training in progress, epoch 1

Browse files
Files changed (29) hide show
  1. logs/events.out.tfevents.1699907043.b18f42e49ba4.3021.8 +2 -2
  2. logs/events.out.tfevents.1699907447.b18f42e49ba4.3021.9 +3 -0
  3. logs/events.out.tfevents.1699907514.b18f42e49ba4.3021.10 +3 -0
  4. logs/events.out.tfevents.1699907580.b18f42e49ba4.3021.11 +3 -0
  5. logs/events.out.tfevents.1699907646.b18f42e49ba4.3021.12 +3 -0
  6. model.safetensors +1 -1
  7. run-11/checkpoint-527/config.json +34 -0
  8. run-11/checkpoint-527/model.safetensors +3 -0
  9. run-11/checkpoint-527/optimizer.pt +3 -0
  10. run-11/checkpoint-527/rng_state.pth +3 -0
  11. run-11/checkpoint-527/scheduler.pt +3 -0
  12. run-11/checkpoint-527/special_tokens_map.json +7 -0
  13. run-11/checkpoint-527/tokenizer.json +0 -0
  14. run-11/checkpoint-527/tokenizer_config.json +57 -0
  15. run-11/checkpoint-527/trainer_state.json +39 -0
  16. run-11/checkpoint-527/training_args.bin +3 -0
  17. run-11/checkpoint-527/vocab.txt +0 -0
  18. run-7/checkpoint-3162/config.json +34 -0
  19. run-7/checkpoint-3162/model.safetensors +3 -0
  20. run-7/checkpoint-3162/optimizer.pt +3 -0
  21. run-7/checkpoint-3162/rng_state.pth +3 -0
  22. run-7/checkpoint-3162/scheduler.pt +3 -0
  23. run-7/checkpoint-3162/special_tokens_map.json +7 -0
  24. run-7/checkpoint-3162/tokenizer.json +0 -0
  25. run-7/checkpoint-3162/tokenizer_config.json +57 -0
  26. run-7/checkpoint-3162/trainer_state.json +114 -0
  27. run-7/checkpoint-3162/training_args.bin +3 -0
  28. run-7/checkpoint-3162/vocab.txt +0 -0
  29. training_args.bin +1 -1
logs/events.out.tfevents.1699907043.b18f42e49ba4.3021.8 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1493a0bcc94527a05ef081d6245053acbd5c5562dd46e58505f32f0613542e9
3
- size 5253
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d22e50380458e48f257d09c6a80eb66e0b1b95cc5339d07882f882adea86053
3
+ size 7527
logs/events.out.tfevents.1699907447.b18f42e49ba4.3021.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cf96c4efc6c9ad0084052a227fe4a7df04d197c69b126c3a6abec815287e963
3
+ size 4773
logs/events.out.tfevents.1699907514.b18f42e49ba4.3021.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea96859b561fec172e6f83131db5d3b504ea7a121e70426f3e3874a596f6f46b
3
+ size 4774
logs/events.out.tfevents.1699907580.b18f42e49ba4.3021.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc4bf99f7a3d7275514b0ad6a86235b1c7d6cf703f746118a503ac4b7cd7888
3
+ size 4775
logs/events.out.tfevents.1699907646.b18f42e49ba4.3021.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94c704be7aefb960ab10cd337bac4afdda214861323ab2fd2fdce957d9cfe30e
3
+ size 4774
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b7ed0c19c55fd65baba6dc45ea4decfa7fc81e4c673d6aa3750b9696bb68155
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d49e96cf869161174066080e4ddd811d079a0dc4f6894979953a693c46684002
3
  size 17549312
run-11/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": "4.35.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-11/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d49e96cf869161174066080e4ddd811d079a0dc4f6894979953a693c46684002
3
+ size 17549312
run-11/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e6e6551c7ba9624dd92df8cf859fc5c3d333de389639c318a71827f780396c7
3
+ size 35123898
run-11/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ababcbf30496eb4976cce44a5faf0cf605467f452ba655745eb60d884a0042d8
3
+ size 14308
run-11/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e2ecb7fd42dfdcdf639b00796000d39f6e7d3f74d11bac8f02468196f5cfb87
3
+ size 1064
run-11/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-11/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-11/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-11/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8107798165137615,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/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": 0.00015537272513250802,
14
+ "loss": 1.5331,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8107798165137615,
20
+ "eval_loss": 1.4093362092971802,
21
+ "eval_runtime": 0.8295,
22
+ "eval_samples_per_second": 1051.285,
23
+ "eval_steps_per_second": 8.439,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 4216,
29
+ "num_train_epochs": 8,
30
+ "save_steps": 500,
31
+ "total_flos": 8117476690260.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.27442938939526085,
35
+ "learning_rate": 0.00017752070708906609,
36
+ "num_train_epochs": 8,
37
+ "temperature": 6
38
+ }
39
+ }
run-11/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8541f76d1c79fd075a297470befb23d7b1fe8c6fe221cd6971ff0ead39278fa9
3
+ size 4600
run-11/checkpoint-527/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/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": "4.35.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-7/checkpoint-3162/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba9ba70d1355beb00f9fb1f25d9de6c5786f36a5440b32c97ab29fa6631ba8eb
3
+ size 17549312
run-7/checkpoint-3162/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a57f97c9a52cd3eca69a463b41701b6ca13528088378bf0eb1585c23b713c05f
3
+ size 35123898
run-7/checkpoint-3162/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a805f5b31aed4614530263d37ef452339ef59079ff627a6dd75bd82ccc8197
3
+ size 14308
run-7/checkpoint-3162/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68d74a46b35b5096ae1d43a786d97de51c3ee23edb2da8caf573ced3b694b3f2
3
+ size 1064
run-7/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-7/checkpoint-3162/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/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-7/checkpoint-3162/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8302752293577982,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-7/checkpoint-1054",
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
+ "learning_rate": 0.0006483137812430133,
14
+ "loss": 1.4329,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8153669724770642,
20
+ "eval_loss": 1.7355903387069702,
21
+ "eval_runtime": 0.9503,
22
+ "eval_samples_per_second": 917.634,
23
+ "eval_steps_per_second": 7.366,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.0005186510249944106,
29
+ "loss": 0.6173,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8302752293577982,
35
+ "eval_loss": 2.0379607677459717,
36
+ "eval_runtime": 0.8981,
37
+ "eval_samples_per_second": 970.954,
38
+ "eval_steps_per_second": 7.794,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 0.00038923430813147896,
44
+ "loss": 0.395,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8176605504587156,
50
+ "eval_loss": 2.1129705905914307,
51
+ "eval_runtime": 0.8373,
52
+ "eval_samples_per_second": 1041.442,
53
+ "eval_steps_per_second": 8.36,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 0.0002595715518828763,
59
+ "loss": 0.2914,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.819954128440367,
65
+ "eval_loss": 1.9875473976135254,
66
+ "eval_runtime": 0.8438,
67
+ "eval_samples_per_second": 1033.427,
68
+ "eval_steps_per_second": 8.296,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 0.00012990879563427364,
74
+ "loss": 0.2152,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.8165137614678899,
80
+ "eval_loss": 2.055243730545044,
81
+ "eval_runtime": 0.8254,
82
+ "eval_samples_per_second": 1056.5,
83
+ "eval_steps_per_second": 8.481,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 2.4603938567097275e-07,
89
+ "loss": 0.1726,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8142201834862385,
95
+ "eval_loss": 2.071915864944458,
96
+ "eval_runtime": 0.8284,
97
+ "eval_samples_per_second": 1052.639,
98
+ "eval_steps_per_second": 8.45,
99
+ "step": 3162
100
+ }
101
+ ],
102
+ "logging_steps": 500,
103
+ "max_steps": 3162,
104
+ "num_train_epochs": 6,
105
+ "save_steps": 500,
106
+ "total_flos": 48509902416420.0,
107
+ "trial_name": null,
108
+ "trial_params": {
109
+ "alpha": 0.14334837282224033,
110
+ "learning_rate": 0.0007779765374916159,
111
+ "num_train_epochs": 6,
112
+ "temperature": 27
113
+ }
114
+ }
run-7/checkpoint-3162/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:806ae42596d54c22720aa3a78ba8e832b7e98ba0160c60b7c181bc0d45da910b
3
+ size 4600
run-7/checkpoint-3162/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 sha256:806ae42596d54c22720aa3a78ba8e832b7e98ba0160c60b7c181bc0d45da910b
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8541f76d1c79fd075a297470befb23d7b1fe8c6fe221cd6971ff0ead39278fa9
3
  size 4600