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
677ec28
·
1 Parent(s): 5284458

Training in progress, epoch 1

Browse files
Files changed (28) hide show
  1. logs/events.out.tfevents.1699909720.b18f42e49ba4.3021.19 +2 -2
  2. logs/events.out.tfevents.1699910189.b18f42e49ba4.3021.20 +3 -0
  3. logs/events.out.tfevents.1699910256.b18f42e49ba4.3021.21 +3 -0
  4. logs/events.out.tfevents.1699910323.b18f42e49ba4.3021.22 +3 -0
  5. model.safetensors +1 -1
  6. run-18/checkpoint-3162/config.json +34 -0
  7. run-18/checkpoint-3162/model.safetensors +3 -0
  8. run-18/checkpoint-3162/optimizer.pt +3 -0
  9. run-18/checkpoint-3162/rng_state.pth +3 -0
  10. run-18/checkpoint-3162/scheduler.pt +3 -0
  11. run-18/checkpoint-3162/special_tokens_map.json +7 -0
  12. run-18/checkpoint-3162/tokenizer.json +0 -0
  13. run-18/checkpoint-3162/tokenizer_config.json +57 -0
  14. run-18/checkpoint-3162/trainer_state.json +114 -0
  15. run-18/checkpoint-3162/training_args.bin +3 -0
  16. run-18/checkpoint-3162/vocab.txt +0 -0
  17. run-21/checkpoint-527/config.json +34 -0
  18. run-21/checkpoint-527/model.safetensors +3 -0
  19. run-21/checkpoint-527/optimizer.pt +3 -0
  20. run-21/checkpoint-527/rng_state.pth +3 -0
  21. run-21/checkpoint-527/scheduler.pt +3 -0
  22. run-21/checkpoint-527/special_tokens_map.json +7 -0
  23. run-21/checkpoint-527/tokenizer.json +0 -0
  24. run-21/checkpoint-527/tokenizer_config.json +57 -0
  25. run-21/checkpoint-527/trainer_state.json +39 -0
  26. run-21/checkpoint-527/training_args.bin +3 -0
  27. run-21/checkpoint-527/vocab.txt +0 -0
  28. training_args.bin +1 -1
logs/events.out.tfevents.1699909720.b18f42e49ba4.3021.19 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62d791afbd75d6ef3d790595f7226ee09710f7716f60845792968c16813dad05
3
- size 5253
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8ff152fbe0c14b2e751e9e9d66c2f9be29cba7e4d12607e4a0b08805ff34878
3
+ size 7653
logs/events.out.tfevents.1699910189.b18f42e49ba4.3021.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1875869a98d2c680674e9a0dbc18faa58500a329d6af0c891219534336f6fa9
3
+ size 4773
logs/events.out.tfevents.1699910256.b18f42e49ba4.3021.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a14e685d2148779c17ca20ee323ece0596ed16687e5a621b61421d92e9267554
3
+ size 4774
logs/events.out.tfevents.1699910323.b18f42e49ba4.3021.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9baa1f9a8931663d89030e696f660ba2bbf771412da79d64dc405abb9a840a7
3
+ size 4773
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f634e31fa845a12702af3d80ec5bb599ddf854bb59f7025c8b8b8125bb499a97
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e38cc5ba5e818f31af0b64ec8e8ed6691e3bb8a5ede94923612049376a9e8ef
3
  size 17549312
run-18/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-18/checkpoint-3162/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4034e7c4e4481005a3fc487af22354e67712858d66953e94b9f2d501721c844d
3
+ size 17549312
run-18/checkpoint-3162/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd0dc036fc6a78b06c865c5d69c31df5d46c31859a3e509ee5ed9c976d055dc
3
+ size 35123898
run-18/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-18/checkpoint-3162/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4991d27afc5e505352ea8a99fd5c0c5babf34b2b1e2940146269c1b697df8a7e
3
+ size 1064
run-18/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-18/checkpoint-3162/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-18/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-18/checkpoint-3162/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8291284403669725,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-18/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": 0.00021709281283020836,
14
+ "loss": 1.1483,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.819954128440367,
20
+ "eval_loss": 1.1504446268081665,
21
+ "eval_runtime": 0.9064,
22
+ "eval_samples_per_second": 962.038,
23
+ "eval_steps_per_second": 7.723,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.00018995621122643234,
29
+ "loss": 0.5507,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8291284403669725,
35
+ "eval_loss": 1.2976974248886108,
36
+ "eval_runtime": 0.8421,
37
+ "eval_samples_per_second": 1035.487,
38
+ "eval_steps_per_second": 8.312,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 0.00016281960962265626,
44
+ "loss": 0.3943,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8107798165137615,
50
+ "eval_loss": 1.4237004518508911,
51
+ "eval_runtime": 0.8247,
52
+ "eval_samples_per_second": 1057.317,
53
+ "eval_steps_per_second": 8.488,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 0.00013573450062154393,
59
+ "loss": 0.3114,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8211009174311926,
65
+ "eval_loss": 1.3227564096450806,
66
+ "eval_runtime": 0.9243,
67
+ "eval_samples_per_second": 943.37,
68
+ "eval_steps_per_second": 7.573,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 0.0001085978990177679,
74
+ "loss": 0.252,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.819954128440367,
80
+ "eval_loss": 1.4520753622055054,
81
+ "eval_runtime": 0.8437,
82
+ "eval_samples_per_second": 1033.517,
83
+ "eval_steps_per_second": 8.297,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 8.146129741399184e-05,
89
+ "loss": 0.2181,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8176605504587156,
95
+ "eval_loss": 1.429627537727356,
96
+ "eval_runtime": 0.8408,
97
+ "eval_samples_per_second": 1037.132,
98
+ "eval_steps_per_second": 8.326,
99
+ "step": 3162
100
+ }
101
+ ],
102
+ "logging_steps": 500,
103
+ "max_steps": 4743,
104
+ "num_train_epochs": 9,
105
+ "save_steps": 500,
106
+ "total_flos": 48509902416420.0,
107
+ "trial_name": null,
108
+ "trial_params": {
109
+ "alpha": 0.5442083101388495,
110
+ "learning_rate": 0.0002442294144339844,
111
+ "num_train_epochs": 9,
112
+ "temperature": 17
113
+ }
114
+ }
run-18/checkpoint-3162/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aff00ec57d588dd5f618f738dabce7e4690b4abea90de2440abbe40581cb27d4
3
+ size 4600
run-18/checkpoint-3162/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-21/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-21/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e38cc5ba5e818f31af0b64ec8e8ed6691e3bb8a5ede94923612049376a9e8ef
3
+ size 17549312
run-21/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04df5cc6164ae0fd3e574566399b9dd71bd351586329611cefef6f88b0bad83c
3
+ size 35123898
run-21/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-21/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a1928766e1f96a982fd8da512b2422b791a3529774e71e7575cbef74e151ef9
3
+ size 1064
run-21/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-21/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-21/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-21/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8211009174311926,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/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": 0.0007813674039938339,
14
+ "loss": 1.4569,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8211009174311926,
20
+ "eval_loss": 1.8369688987731934,
21
+ "eval_runtime": 0.957,
22
+ "eval_samples_per_second": 911.136,
23
+ "eval_steps_per_second": 7.314,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 3162,
29
+ "num_train_epochs": 6,
30
+ "save_steps": 500,
31
+ "total_flos": 8117476690260.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.12545237557795993,
35
+ "learning_rate": 0.0009372851788423759,
36
+ "num_train_epochs": 6,
37
+ "temperature": 30
38
+ }
39
+ }
run-21/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf4805dbdf09e6f5258853c790c37af35f2cbe2f2d5a284a8389b7ec93b9b40
3
+ size 4600
run-21/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:aff00ec57d588dd5f618f738dabce7e4690b4abea90de2440abbe40581cb27d4
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf4805dbdf09e6f5258853c790c37af35f2cbe2f2d5a284a8389b7ec93b9b40
3
  size 4600