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
febd4dd
·
verified ·
1 Parent(s): e41e979

Training in progress, epoch 1

Browse files
Files changed (26) hide show
  1. logs/events.out.tfevents.1709700065.a2333cf40ebd.21010.12 +2 -2
  2. logs/events.out.tfevents.1709700410.a2333cf40ebd.21010.13 +3 -0
  3. model.safetensors +1 -1
  4. run-12/checkpoint-288/config.json +34 -0
  5. run-12/checkpoint-288/model.safetensors +3 -0
  6. run-12/checkpoint-288/optimizer.pt +3 -0
  7. run-12/checkpoint-288/rng_state.pth +3 -0
  8. run-12/checkpoint-288/scheduler.pt +3 -0
  9. run-12/checkpoint-288/special_tokens_map.json +7 -0
  10. run-12/checkpoint-288/tokenizer.json +0 -0
  11. run-12/checkpoint-288/tokenizer_config.json +57 -0
  12. run-12/checkpoint-288/trainer_state.json +83 -0
  13. run-12/checkpoint-288/training_args.bin +3 -0
  14. run-12/checkpoint-288/vocab.txt +0 -0
  15. run-13/checkpoint-96/config.json +34 -0
  16. run-13/checkpoint-96/model.safetensors +3 -0
  17. run-13/checkpoint-96/optimizer.pt +3 -0
  18. run-13/checkpoint-96/rng_state.pth +3 -0
  19. run-13/checkpoint-96/scheduler.pt +3 -0
  20. run-13/checkpoint-96/special_tokens_map.json +7 -0
  21. run-13/checkpoint-96/tokenizer.json +0 -0
  22. run-13/checkpoint-96/tokenizer_config.json +57 -0
  23. run-13/checkpoint-96/trainer_state.json +45 -0
  24. run-13/checkpoint-96/training_args.bin +3 -0
  25. run-13/checkpoint-96/vocab.txt +0 -0
  26. training_args.bin +1 -1
logs/events.out.tfevents.1709700065.a2333cf40ebd.21010.12 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3519921dc1241622e621787b47d602bf5c100e59abf40d7816a59663347c7c00
3
- size 5997
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72c8a2e0957c87d2769869f18eb11896b298bd1a357422cdde1e117aebd1e433
3
+ size 7034
logs/events.out.tfevents.1709700410.a2333cf40ebd.21010.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2586102e32da660f372ed36fe089f41b67836f6862a9581524e2cacf2fce8c30
3
+ size 5314
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e68ac4ddfb83acca32122d6f55c9691c945a72d15ad8d0615740b45efb4519a0
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0ce89c0de7eff53ff8e0e099dd046cfb7cdf189abf4e221e485666006f25009
3
  size 17549312
run-12/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-12/checkpoint-288/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ae8ed182a4089d2815fa7104b753343ba79d73b53edccffb2e238515bfba7fb
3
+ size 17549312
run-12/checkpoint-288/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e88db004fe5cfdfdfa97ebbc28e8ea2ca64b331bc8b9408c1902d5d38300271
3
+ size 35122746
run-12/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-12/checkpoint-288/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c62758e83996926c4789d7a83a82603be97b577f5f9389abe0c61d58f10e4333
3
+ size 1064
run-12/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-12/checkpoint-288/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-12/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-12/checkpoint-288/trainer_state.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8111545988258317,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-12/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": 1.4721163511276245,
14
+ "learning_rate": 0.0005951476674473283,
15
+ "loss": 0.4971,
16
+ "step": 96
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7671232876712328,
21
+ "eval_f1": 0.7989864864864864,
22
+ "eval_loss": 0.4431186616420746,
23
+ "eval_precision": 0.7028231797919762,
24
+ "eval_recall": 0.9256360078277887,
25
+ "eval_runtime": 28.4119,
26
+ "eval_samples_per_second": 35.971,
27
+ "eval_steps_per_second": 1.126,
28
+ "step": 96
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 1.945635199546814,
33
+ "learning_rate": 0.00029757383372366414,
34
+ "loss": 0.4421,
35
+ "step": 192
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.7915851272015656,
40
+ "eval_f1": 0.8149435273675064,
41
+ "eval_loss": 0.4262682795524597,
42
+ "eval_precision": 0.7328125,
43
+ "eval_recall": 0.9178082191780822,
44
+ "eval_runtime": 28.1497,
45
+ "eval_samples_per_second": 36.306,
46
+ "eval_steps_per_second": 1.137,
47
+ "step": 192
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 1.666189193725586,
52
+ "learning_rate": 0.0,
53
+ "loss": 0.4148,
54
+ "step": 288
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8111545988258317,
59
+ "eval_f1": 0.8146013448607108,
60
+ "eval_loss": 0.40171727538108826,
61
+ "eval_precision": 0.8,
62
+ "eval_recall": 0.8297455968688845,
63
+ "eval_runtime": 28.233,
64
+ "eval_samples_per_second": 36.199,
65
+ "eval_steps_per_second": 1.133,
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": 0.7419170223133877,
79
+ "learning_rate": 0.0008927215011709925,
80
+ "num_train_epochs": 3,
81
+ "temperature": 30
82
+ }
83
+ }
run-12/checkpoint-288/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d9494b45a46d7299cfdd740382df8282ceb4e98494c56a4025a5a8636cf28c5
3
+ size 4920
run-12/checkpoint-288/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-13/checkpoint-96/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-13/checkpoint-96/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0ce89c0de7eff53ff8e0e099dd046cfb7cdf189abf4e221e485666006f25009
3
+ size 17549312
run-13/checkpoint-96/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41742d4b6de56ded26c7e698ae79c2745648e36fbca57a5049fff8337116825b
3
+ size 35122746
run-13/checkpoint-96/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24aa86019b8aea1c551cc1adaf38c4db2fc01de75a22af312230f6b592e0fd81
3
+ size 14054
run-13/checkpoint-96/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8013fe90162f1e3a3b1efc50c8ab0c3eb1c4f58fc9b4f1b892dd31ae38182f73
3
+ size 1064
run-13/checkpoint-96/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-13/checkpoint-96/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-13/checkpoint-96/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-13/checkpoint-96/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7818003913894325,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-96",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 96,
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": 3.178528308868408,
14
+ "learning_rate": 0.00013234646126788495,
15
+ "loss": 0.5867,
16
+ "step": 96
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7818003913894325,
21
+ "eval_f1": 0.8102127659574467,
22
+ "eval_loss": 0.47177326679229736,
23
+ "eval_precision": 0.7168674698795181,
24
+ "eval_recall": 0.9315068493150684,
25
+ "eval_runtime": 29.1712,
26
+ "eval_samples_per_second": 35.035,
27
+ "eval_steps_per_second": 1.097,
28
+ "step": 96
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 192,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 2,
35
+ "save_steps": 500,
36
+ "total_flos": 235695197280.0,
37
+ "train_batch_size": 32,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.9936603556458727,
41
+ "learning_rate": 0.0002646929225357699,
42
+ "num_train_epochs": 2,
43
+ "temperature": 26
44
+ }
45
+ }
run-13/checkpoint-96/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:633c942d0b60f05ab3fa982f5bbaaa9bbdcf47198dfbdd5d1b639decdd30975e
3
+ size 4920
run-13/checkpoint-96/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:eca285e074f5751b46e77605d55ec46cae8a3b205f294ab4811aec331d54f279
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:633c942d0b60f05ab3fa982f5bbaaa9bbdcf47198dfbdd5d1b639decdd30975e
3
  size 4920