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
d54604e
·
verified ·
1 Parent(s): 3de5ac0

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. logs/events.out.tfevents.1709839346.013ec1551212.75384.13 +2 -2
  2. logs/events.out.tfevents.1709842785.013ec1551212.75384.14 +3 -0
  3. model.safetensors +1 -1
  4. run-13/checkpoint-3830/config.json +34 -0
  5. run-13/checkpoint-3830/model.safetensors +3 -0
  6. run-13/checkpoint-3830/optimizer.pt +3 -0
  7. run-13/checkpoint-3830/rng_state.pth +3 -0
  8. run-13/checkpoint-3830/scheduler.pt +3 -0
  9. run-13/checkpoint-3830/special_tokens_map.json +7 -0
  10. run-13/checkpoint-3830/tokenizer.json +0 -0
  11. run-13/checkpoint-3830/tokenizer_config.json +57 -0
  12. run-13/checkpoint-3830/trainer_state.json +121 -0
  13. run-13/checkpoint-3830/training_args.bin +3 -0
  14. run-13/checkpoint-3830/vocab.txt +0 -0
  15. run-13/checkpoint-4596/config.json +34 -0
  16. run-13/checkpoint-4596/model.safetensors +3 -0
  17. run-13/checkpoint-4596/optimizer.pt +3 -0
  18. run-13/checkpoint-4596/rng_state.pth +3 -0
  19. run-13/checkpoint-4596/scheduler.pt +3 -0
  20. run-13/checkpoint-4596/special_tokens_map.json +7 -0
  21. run-13/checkpoint-4596/tokenizer.json +0 -0
  22. run-13/checkpoint-4596/tokenizer_config.json +57 -0
  23. run-13/checkpoint-4596/trainer_state.json +140 -0
  24. run-13/checkpoint-4596/training_args.bin +3 -0
  25. run-13/checkpoint-4596/vocab.txt +0 -0
  26. run-14/checkpoint-766/config.json +34 -0
  27. run-14/checkpoint-766/model.safetensors +3 -0
  28. run-14/checkpoint-766/optimizer.pt +3 -0
  29. run-14/checkpoint-766/rng_state.pth +3 -0
  30. run-14/checkpoint-766/scheduler.pt +3 -0
  31. run-14/checkpoint-766/special_tokens_map.json +7 -0
  32. run-14/checkpoint-766/tokenizer.json +0 -0
  33. run-14/checkpoint-766/tokenizer_config.json +57 -0
  34. run-14/checkpoint-766/trainer_state.json +45 -0
  35. run-14/checkpoint-766/training_args.bin +3 -0
  36. run-14/checkpoint-766/vocab.txt +0 -0
  37. training_args.bin +1 -1
logs/events.out.tfevents.1709839346.013ec1551212.75384.13 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4626c8fa8a939f83661fa768e0f7a5fb38ef84ece3d73e24149f6741ea926326
3
- size 6009
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e94c7fe793c798f1f6a5f342d5a3287d361070352205d44bbe2f0e75596b8871
3
+ size 9095
logs/events.out.tfevents.1709842785.013ec1551212.75384.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f39cfb6538d32c8141e7a564fbc1e36e8c13fc74c967b485b688165f952db7df
3
+ size 5325
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:559ff4be5d0a310ccb1b400436b5388f6835588fe76d88880660d07b4bdd40d8
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12937f00824ab76d4bd65d63263bef0f59f9e0957edcbbf178afb6a29bd32b21
3
  size 17549312
run-13/checkpoint-3830/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-3830/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be3394f7cd25f8bee3f024916e2c93affd2370678a19eafa48d19b646a3c33a9
3
+ size 17549312
run-13/checkpoint-3830/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dc2f75d9f5e4c05af11d0011c9bbb421f7e660773923b0804772786dcf6187f
3
+ size 35122746
run-13/checkpoint-3830/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11f0f7f8253cabe8457ea3e8be3f556fa57dd5de6a14e336e6ae5d5e2e50d1cf
3
+ size 14054
run-13/checkpoint-3830/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:764ea7d6b36cee8df331f43cc6cc15743ae6b8f27c724d597fc6e9a851ad4c3c
3
+ size 1064
run-13/checkpoint-3830/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-3830/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-13/checkpoint-3830/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-3830/trainer_state.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8317025440313112,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-3064",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3830,
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": 1.943489909172058,
14
+ "learning_rate": 9.076816597122249e-05,
15
+ "loss": 0.4823,
16
+ "step": 766
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7896281800391389,
21
+ "eval_f1": 0.8125544899738447,
22
+ "eval_loss": 0.43095502257347107,
23
+ "eval_precision": 0.7327044025157232,
24
+ "eval_recall": 0.9119373776908023,
25
+ "eval_runtime": 132.0712,
26
+ "eval_samples_per_second": 7.738,
27
+ "eval_steps_per_second": 1.938,
28
+ "step": 766
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 19.456132888793945,
33
+ "learning_rate": 7.261453277697798e-05,
34
+ "loss": 0.4312,
35
+ "step": 1532
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.824853228962818,
40
+ "eval_f1": 0.8347183748845799,
41
+ "eval_loss": 0.40763548016548157,
42
+ "eval_precision": 0.7902097902097902,
43
+ "eval_recall": 0.8845401174168297,
44
+ "eval_runtime": 132.1546,
45
+ "eval_samples_per_second": 7.733,
46
+ "eval_steps_per_second": 1.937,
47
+ "step": 1532
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 3.0639514923095703,
52
+ "learning_rate": 5.446089958273349e-05,
53
+ "loss": 0.4141,
54
+ "step": 2298
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8189823874755382,
59
+ "eval_f1": 0.821944177093359,
60
+ "eval_loss": 0.43046870827674866,
61
+ "eval_precision": 0.8087121212121212,
62
+ "eval_recall": 0.8356164383561644,
63
+ "eval_runtime": 130.1314,
64
+ "eval_samples_per_second": 7.854,
65
+ "eval_steps_per_second": 1.967,
66
+ "step": 2298
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 2.4112496376037598,
71
+ "learning_rate": 3.630726638848899e-05,
72
+ "loss": 0.4066,
73
+ "step": 3064
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8317025440313112,
78
+ "eval_f1": 0.8374291115311909,
79
+ "eval_loss": 0.4001712203025818,
80
+ "eval_precision": 0.8098720292504571,
81
+ "eval_recall": 0.8669275929549902,
82
+ "eval_runtime": 132.1937,
83
+ "eval_samples_per_second": 7.731,
84
+ "eval_steps_per_second": 1.937,
85
+ "step": 3064
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 28.75933265686035,
90
+ "learning_rate": 1.8153633194244494e-05,
91
+ "loss": 0.3942,
92
+ "step": 3830
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.824853228962818,
97
+ "eval_f1": 0.8334883720930233,
98
+ "eval_loss": 0.4072827398777008,
99
+ "eval_precision": 0.7943262411347518,
100
+ "eval_recall": 0.8767123287671232,
101
+ "eval_runtime": 133.1862,
102
+ "eval_samples_per_second": 7.673,
103
+ "eval_steps_per_second": 1.922,
104
+ "step": 3830
105
+ }
106
+ ],
107
+ "logging_steps": 500,
108
+ "max_steps": 4596,
109
+ "num_input_tokens_seen": 0,
110
+ "num_train_epochs": 6,
111
+ "save_steps": 500,
112
+ "total_flos": 1178475986400.0,
113
+ "train_batch_size": 4,
114
+ "trial_name": null,
115
+ "trial_params": {
116
+ "alpha": 0.7464330126775673,
117
+ "learning_rate": 0.00010892179916546698,
118
+ "num_train_epochs": 6,
119
+ "temperature": 11
120
+ }
121
+ }
run-13/checkpoint-3830/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1695bf5cb08464044ce84908151382d3564189a20bbd25b8781afa4cb2b436ef
3
+ size 4920
run-13/checkpoint-3830/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-13/checkpoint-4596/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-4596/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c717ee151f6f4005b7c5e503a1aeff38b3994aad2623b76c0d5a3ab59e804095
3
+ size 17549312
run-13/checkpoint-4596/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ff4e2c91e1c76442b67db36d00b808086dc8d99765648d1f95d2e19fd36c72a
3
+ size 35122746
run-13/checkpoint-4596/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f06e3ed5d19cc4b4c47d9aedbd704375564c004c94232d74f9d579078573040d
3
+ size 14054
run-13/checkpoint-4596/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fac1fa2d793adbe1cc44ef8e2c5baffc49f83f1a4359b2de4c4730548fbbc11
3
+ size 1064
run-13/checkpoint-4596/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-4596/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-13/checkpoint-4596/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-4596/trainer_state.json ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8356164383561644,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-4596",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4596,
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": 1.943489909172058,
14
+ "learning_rate": 9.076816597122249e-05,
15
+ "loss": 0.4823,
16
+ "step": 766
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7896281800391389,
21
+ "eval_f1": 0.8125544899738447,
22
+ "eval_loss": 0.43095502257347107,
23
+ "eval_precision": 0.7327044025157232,
24
+ "eval_recall": 0.9119373776908023,
25
+ "eval_runtime": 132.0712,
26
+ "eval_samples_per_second": 7.738,
27
+ "eval_steps_per_second": 1.938,
28
+ "step": 766
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 19.456132888793945,
33
+ "learning_rate": 7.261453277697798e-05,
34
+ "loss": 0.4312,
35
+ "step": 1532
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.824853228962818,
40
+ "eval_f1": 0.8347183748845799,
41
+ "eval_loss": 0.40763548016548157,
42
+ "eval_precision": 0.7902097902097902,
43
+ "eval_recall": 0.8845401174168297,
44
+ "eval_runtime": 132.1546,
45
+ "eval_samples_per_second": 7.733,
46
+ "eval_steps_per_second": 1.937,
47
+ "step": 1532
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 3.0639514923095703,
52
+ "learning_rate": 5.446089958273349e-05,
53
+ "loss": 0.4141,
54
+ "step": 2298
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8189823874755382,
59
+ "eval_f1": 0.821944177093359,
60
+ "eval_loss": 0.43046870827674866,
61
+ "eval_precision": 0.8087121212121212,
62
+ "eval_recall": 0.8356164383561644,
63
+ "eval_runtime": 130.1314,
64
+ "eval_samples_per_second": 7.854,
65
+ "eval_steps_per_second": 1.967,
66
+ "step": 2298
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 2.4112496376037598,
71
+ "learning_rate": 3.630726638848899e-05,
72
+ "loss": 0.4066,
73
+ "step": 3064
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8317025440313112,
78
+ "eval_f1": 0.8374291115311909,
79
+ "eval_loss": 0.4001712203025818,
80
+ "eval_precision": 0.8098720292504571,
81
+ "eval_recall": 0.8669275929549902,
82
+ "eval_runtime": 132.1937,
83
+ "eval_samples_per_second": 7.731,
84
+ "eval_steps_per_second": 1.937,
85
+ "step": 3064
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 28.75933265686035,
90
+ "learning_rate": 1.8153633194244494e-05,
91
+ "loss": 0.3942,
92
+ "step": 3830
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.824853228962818,
97
+ "eval_f1": 0.8334883720930233,
98
+ "eval_loss": 0.4072827398777008,
99
+ "eval_precision": 0.7943262411347518,
100
+ "eval_recall": 0.8767123287671232,
101
+ "eval_runtime": 133.1862,
102
+ "eval_samples_per_second": 7.673,
103
+ "eval_steps_per_second": 1.922,
104
+ "step": 3830
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "grad_norm": 8.708053588867188,
109
+ "learning_rate": 0.0,
110
+ "loss": 0.3933,
111
+ "step": 4596
112
+ },
113
+ {
114
+ "epoch": 6.0,
115
+ "eval_accuracy": 0.8356164383561644,
116
+ "eval_f1": 0.8444444444444444,
117
+ "eval_loss": 0.40063977241516113,
118
+ "eval_precision": 0.8014059753954306,
119
+ "eval_recall": 0.8923679060665362,
120
+ "eval_runtime": 131.5339,
121
+ "eval_samples_per_second": 7.77,
122
+ "eval_steps_per_second": 1.946,
123
+ "step": 4596
124
+ }
125
+ ],
126
+ "logging_steps": 500,
127
+ "max_steps": 4596,
128
+ "num_input_tokens_seen": 0,
129
+ "num_train_epochs": 6,
130
+ "save_steps": 500,
131
+ "total_flos": 1414171183680.0,
132
+ "train_batch_size": 4,
133
+ "trial_name": null,
134
+ "trial_params": {
135
+ "alpha": 0.7464330126775673,
136
+ "learning_rate": 0.00010892179916546698,
137
+ "num_train_epochs": 6,
138
+ "temperature": 11
139
+ }
140
+ }
run-13/checkpoint-4596/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1695bf5cb08464044ce84908151382d3564189a20bbd25b8781afa4cb2b436ef
3
+ size 4920
run-13/checkpoint-4596/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-766/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-14/checkpoint-766/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12937f00824ab76d4bd65d63263bef0f59f9e0957edcbbf178afb6a29bd32b21
3
+ size 17549312
run-14/checkpoint-766/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eda804860d0aa5cd1ca04256c6f85be256b347254c966bca9dc2aa4c0e472e8f
3
+ size 35122746
run-14/checkpoint-766/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a29b5a9fab412f426bae759e459d7d9236aab6602ae439ea13f5bd437e1b98a4
3
+ size 14054
run-14/checkpoint-766/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f63ec0f84bd2063014357e7cb5ad8c41c07ccbf2b60ed5b37b097d9074f8d56
3
+ size 1064
run-14/checkpoint-766/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-766/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-766/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-766/trainer_state.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7847358121330724,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-766",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 766,
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": 2.48061203956604,
14
+ "learning_rate": 4.112696231809907e-05,
15
+ "loss": 0.4707,
16
+ "step": 766
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7847358121330724,
21
+ "eval_f1": 0.8018018018018018,
22
+ "eval_loss": 0.4169985055923462,
23
+ "eval_precision": 0.7429048414023373,
24
+ "eval_recall": 0.8708414872798435,
25
+ "eval_runtime": 130.438,
26
+ "eval_samples_per_second": 7.835,
27
+ "eval_steps_per_second": 1.963,
28
+ "step": 766
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 4596,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 6,
35
+ "save_steps": 500,
36
+ "total_flos": 235695197280.0,
37
+ "train_batch_size": 4,
38
+ "trial_name": null,
39
+ "trial_params": {
40
+ "alpha": 0.694449127189597,
41
+ "learning_rate": 4.935235478171889e-05,
42
+ "num_train_epochs": 6,
43
+ "temperature": 10
44
+ }
45
+ }
run-14/checkpoint-766/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f36d839ec5cecb49cd674c806780abc56bc8622bf37106f9a8505659e2e1be34
3
+ size 4920
run-14/checkpoint-766/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 sha256:1695bf5cb08464044ce84908151382d3564189a20bbd25b8781afa4cb2b436ef
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f36d839ec5cecb49cd674c806780abc56bc8622bf37106f9a8505659e2e1be34
3
  size 4920