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
f7a9f7f
·
1 Parent(s): b24718a

Training in progress, epoch 1

Browse files
Files changed (29) hide show
  1. logs/events.out.tfevents.1699909051.b18f42e49ba4.3021.15 +2 -2
  2. logs/events.out.tfevents.1699909520.b18f42e49ba4.3021.16 +3 -0
  3. logs/events.out.tfevents.1699909587.b18f42e49ba4.3021.17 +3 -0
  4. logs/events.out.tfevents.1699909653.b18f42e49ba4.3021.18 +3 -0
  5. logs/events.out.tfevents.1699909720.b18f42e49ba4.3021.19 +3 -0
  6. model.safetensors +1 -1
  7. run-14/checkpoint-3162/config.json +34 -0
  8. run-14/checkpoint-3162/model.safetensors +3 -0
  9. run-14/checkpoint-3162/optimizer.pt +3 -0
  10. run-14/checkpoint-3162/rng_state.pth +3 -0
  11. run-14/checkpoint-3162/scheduler.pt +3 -0
  12. run-14/checkpoint-3162/special_tokens_map.json +7 -0
  13. run-14/checkpoint-3162/tokenizer.json +0 -0
  14. run-14/checkpoint-3162/tokenizer_config.json +57 -0
  15. run-14/checkpoint-3162/trainer_state.json +114 -0
  16. run-14/checkpoint-3162/training_args.bin +3 -0
  17. run-14/checkpoint-3162/vocab.txt +0 -0
  18. run-18/checkpoint-527/config.json +34 -0
  19. run-18/checkpoint-527/model.safetensors +3 -0
  20. run-18/checkpoint-527/optimizer.pt +3 -0
  21. run-18/checkpoint-527/rng_state.pth +3 -0
  22. run-18/checkpoint-527/scheduler.pt +3 -0
  23. run-18/checkpoint-527/special_tokens_map.json +7 -0
  24. run-18/checkpoint-527/tokenizer.json +0 -0
  25. run-18/checkpoint-527/tokenizer_config.json +57 -0
  26. run-18/checkpoint-527/trainer_state.json +39 -0
  27. run-18/checkpoint-527/training_args.bin +3 -0
  28. run-18/checkpoint-527/vocab.txt +0 -0
  29. training_args.bin +1 -1
logs/events.out.tfevents.1699909051.b18f42e49ba4.3021.15 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c10d999d6678ececd7ab2584887958b1c20d48e7030982472c3fcc3ddc9700b
3
- size 5254
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dabbd909ee1fbe071606edf7e5d5aed9c034ac387a2f1f32bbc2442fe9d3be2e
3
+ size 7654
logs/events.out.tfevents.1699909520.b18f42e49ba4.3021.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53f77db1f506efdf24ded6d68261a8193e7dfb0250a1fb289253df8506d31bee
3
+ size 4773
logs/events.out.tfevents.1699909587.b18f42e49ba4.3021.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:133b7f2c2f998864cd6ddc3dce0703bc4346534beb02789d6cf5843dc2988257
3
+ size 4774
logs/events.out.tfevents.1699909653.b18f42e49ba4.3021.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e60641fdb76a77a9de0e6f69e6849a74126ac41a6bb0c2b69c59be8f2558966
3
+ size 4773
logs/events.out.tfevents.1699909720.b18f42e49ba4.3021.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8862efddb1aec1771261d2f81e829c289fa17be4e9fbac4e08d4d4fb76f0813
3
+ size 4773
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfd6530f6a4e987f34989e99ac9e5373823b262e9efb7d81eceec495ba492031
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dd3db190afe2794968d1474a6d4fa5c9ac72c4805f0cc9b829ebd3aac849723
3
  size 17549312
run-14/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-14/checkpoint-3162/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e760fde1f8fb0ab5b907e1b72da1204dd125ed50a144362ac3c4014e8cf7d505
3
+ size 17549312
run-14/checkpoint-3162/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f559b59263aca2df18d1c61a02e4b874b191bba028bb644ed4cae912006e28d5
3
+ size 35123898
run-14/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-14/checkpoint-3162/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6636274f784d055781d46f18e7befb932abeb11169c8b301c11c1b7a849910aa
3
+ size 1064
run-14/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-14/checkpoint-3162/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-14/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-14/checkpoint-3162/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8314220183486238,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/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": 0.00010317356130055849,
14
+ "loss": 2.0283,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8107798165137615,
20
+ "eval_loss": 1.6509921550750732,
21
+ "eval_runtime": 0.8261,
22
+ "eval_samples_per_second": 1055.546,
23
+ "eval_steps_per_second": 8.473,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 9.027992440101039e-05,
29
+ "loss": 0.9916,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.8314220183486238,
35
+ "eval_loss": 1.661346435546875,
36
+ "eval_runtime": 0.8315,
37
+ "eval_samples_per_second": 1048.709,
38
+ "eval_steps_per_second": 8.419,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 7.73862875014623e-05,
44
+ "loss": 0.735,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8256880733944955,
50
+ "eval_loss": 1.6645842790603638,
51
+ "eval_runtime": 0.8342,
52
+ "eval_samples_per_second": 1045.253,
53
+ "eval_steps_per_second": 8.391,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 6.44926506019142e-05,
59
+ "loss": 0.613,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8211009174311926,
65
+ "eval_loss": 1.671504020690918,
66
+ "eval_runtime": 0.8454,
67
+ "eval_samples_per_second": 1031.462,
68
+ "eval_steps_per_second": 8.28,
69
+ "step": 2108
70
+ },
71
+ {
72
+ "epoch": 5.0,
73
+ "learning_rate": 5.15990137023661e-05,
74
+ "loss": 0.5223,
75
+ "step": 2635
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "eval_accuracy": 0.823394495412844,
80
+ "eval_loss": 1.77200186252594,
81
+ "eval_runtime": 0.8235,
82
+ "eval_samples_per_second": 1058.878,
83
+ "eval_steps_per_second": 8.5,
84
+ "step": 2635
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "learning_rate": 3.8705376802818e-05,
89
+ "loss": 0.467,
90
+ "step": 3162
91
+ },
92
+ {
93
+ "epoch": 6.0,
94
+ "eval_accuracy": 0.8291284403669725,
95
+ "eval_loss": 1.7289667129516602,
96
+ "eval_runtime": 0.8962,
97
+ "eval_samples_per_second": 972.994,
98
+ "eval_steps_per_second": 7.811,
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": 0.14932769169050555,
110
+ "learning_rate": 0.00011604273209593286,
111
+ "num_train_epochs": 9,
112
+ "temperature": 7
113
+ }
114
+ }
run-14/checkpoint-3162/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a549b24996639a9d6d22a725e933f19e20d6ce242486e15b2b9ab359427b8d2f
3
+ size 4600
run-14/checkpoint-3162/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-18/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-18/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dd3db190afe2794968d1474a6d4fa5c9ac72c4805f0cc9b829ebd3aac849723
3
+ size 17549312
run-18/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8488b4a19e9c7e058e95f3a508f8a9f549d2fa369ca4dd726bda8d3a64697bc2
3
+ size 35123898
run-18/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-18/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce22c0764503e81070c385aadc4012a807b8ce566bc289a29ae5777d0d1387ca
3
+ size 1064
run-18/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-18/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-18/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-18/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.819954128440367,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-18/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": 0.00021709281283020836,
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
+ "logging_steps": 500,
28
+ "max_steps": 4743,
29
+ "num_train_epochs": 9,
30
+ "save_steps": 500,
31
+ "total_flos": 8117476690260.0,
32
+ "trial_name": null,
33
+ "trial_params": {
34
+ "alpha": 0.5442083101388495,
35
+ "learning_rate": 0.0002442294144339844,
36
+ "num_train_epochs": 9,
37
+ "temperature": 17
38
+ }
39
+ }
run-18/checkpoint-527/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-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:a549b24996639a9d6d22a725e933f19e20d6ce242486e15b2b9ab359427b8d2f
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aff00ec57d588dd5f618f738dabce7e4690b4abea90de2440abbe40581cb27d4
3
  size 4600