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
aa8a723
·
verified ·
1 Parent(s): dfecd20

Training in progress, epoch 1

Browse files
Files changed (16) hide show
  1. logs/events.out.tfevents.1709704692.a2333cf40ebd.21010.31 +2 -2
  2. logs/events.out.tfevents.1709705053.a2333cf40ebd.21010.32 +3 -0
  3. logs/events.out.tfevents.1709705169.a2333cf40ebd.21010.33 +3 -0
  4. model.safetensors +1 -1
  5. run-31/checkpoint-288/config.json +34 -0
  6. run-31/checkpoint-288/model.safetensors +3 -0
  7. run-31/checkpoint-288/optimizer.pt +3 -0
  8. run-31/checkpoint-288/rng_state.pth +3 -0
  9. run-31/checkpoint-288/scheduler.pt +3 -0
  10. run-31/checkpoint-288/special_tokens_map.json +7 -0
  11. run-31/checkpoint-288/tokenizer.json +0 -0
  12. run-31/checkpoint-288/tokenizer_config.json +57 -0
  13. run-31/checkpoint-288/trainer_state.json +83 -0
  14. run-31/checkpoint-288/training_args.bin +3 -0
  15. run-31/checkpoint-288/vocab.txt +0 -0
  16. training_args.bin +1 -1
logs/events.out.tfevents.1709704692.a2333cf40ebd.21010.31 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88f51dd38bea7cf59eb0384a56cf371f862d4da220ef7b4f1a223f63c9aa8631
3
- size 5998
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:372dd0e0b92b2cfdf4b165ad0f1862a88fda239e481240cbfcdd9384006ae416
3
+ size 7035
logs/events.out.tfevents.1709705053.a2333cf40ebd.21010.32 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:484cdd12d5af6044078ed31006a2a6a76b94972876d0fd4181cf45e114acbad9
3
+ size 5314
logs/events.out.tfevents.1709705169.a2333cf40ebd.21010.33 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:097d182d9a0bfb6106fdc1970afda3981041871452fbbef3b16d2402b2229b0c
3
+ size 5314
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34e761f88e86eb40aecd0e93d0bb9d5868089263786e6798b638e9378f881726
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a275ea9c56064014c3200667f628919c6c1a6ec0f497dd7c3fe607995a7d1a84
3
  size 17549312
run-31/checkpoint-288/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-31/checkpoint-288/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6632e8cb67396ab4f3804faee3bb4411f70f9f7f98220a303f923d2f4923085
3
+ size 17549312
run-31/checkpoint-288/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1ca04a979927f27aa2521b2c7f175d66c66c779a877da6c368aa0f849c45129
3
+ size 35122746
run-31/checkpoint-288/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba3c2bb1d96a39a28ae1b66f234e351e3c13c700fc97347efd6308798b151790
3
+ size 14054
run-31/checkpoint-288/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e5b340767acfcdc265c84f6058d413a0ada20f4b88f7f5633b103baea10ec0
3
+ size 1064
run-31/checkpoint-288/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-31/checkpoint-288/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-31/checkpoint-288/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-31/checkpoint-288/trainer_state.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.815068493150685,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-31/checkpoint-288",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 288,
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": 2.5316264629364014,
14
+ "learning_rate": 0.00014420233670578463,
15
+ "loss": 0.5643,
16
+ "step": 96
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7847358121330724,
21
+ "eval_f1": 0.8103448275862069,
22
+ "eval_loss": 0.46410736441612244,
23
+ "eval_precision": 0.724191063174114,
24
+ "eval_recall": 0.9197651663405088,
25
+ "eval_runtime": 29.4668,
26
+ "eval_samples_per_second": 34.683,
27
+ "eval_steps_per_second": 1.086,
28
+ "step": 96
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 5.006242275238037,
33
+ "learning_rate": 7.210116835289232e-05,
34
+ "loss": 0.4708,
35
+ "step": 192
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8072407045009785,
40
+ "eval_f1": 0.8248888888888889,
41
+ "eval_loss": 0.43305960297584534,
42
+ "eval_precision": 0.755700325732899,
43
+ "eval_recall": 0.9080234833659491,
44
+ "eval_runtime": 28.4097,
45
+ "eval_samples_per_second": 35.974,
46
+ "eval_steps_per_second": 1.126,
47
+ "step": 192
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 3.3985838890075684,
52
+ "learning_rate": 0.0,
53
+ "loss": 0.4453,
54
+ "step": 288
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.815068493150685,
59
+ "eval_f1": 0.8331862312444835,
60
+ "eval_loss": 0.42596298456192017,
61
+ "eval_precision": 0.7588424437299035,
62
+ "eval_recall": 0.923679060665362,
63
+ "eval_runtime": 28.3781,
64
+ "eval_samples_per_second": 36.014,
65
+ "eval_steps_per_second": 1.128,
66
+ "step": 288
67
+ }
68
+ ],
69
+ "logging_steps": 500,
70
+ "max_steps": 288,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 3,
73
+ "save_steps": 500,
74
+ "total_flos": 707085591840.0,
75
+ "train_batch_size": 32,
76
+ "trial_name": null,
77
+ "trial_params": {
78
+ "alpha": 0.9045625031297628,
79
+ "learning_rate": 0.00021630350505867697,
80
+ "num_train_epochs": 3,
81
+ "temperature": 19
82
+ }
83
+ }
run-31/checkpoint-288/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4989429ea64137d63ac1d990bdf7ffc1b241303b977185f9a5365a53b904b3a2
3
+ size 4920
run-31/checkpoint-288/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 sha256:4989429ea64137d63ac1d990bdf7ffc1b241303b977185f9a5365a53b904b3a2
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f290a192e0ea1abfff73633e45672101eb50bd64dcaf8d02a78a7004edc1f72b
3
  size 4920