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
551051d
·
verified ·
1 Parent(s): 7f25e7f

Training in progress, epoch 1

Browse files
Files changed (32) hide show
  1. logs/events.out.tfevents.1709747080.1dcff7455174.7719.20 +2 -2
  2. logs/events.out.tfevents.1709747783.1dcff7455174.7719.21 +3 -0
  3. logs/events.out.tfevents.1709747882.1dcff7455174.7719.22 +3 -0
  4. model.safetensors +1 -1
  5. run-20/checkpoint-480/config.json +34 -0
  6. run-20/checkpoint-480/model.safetensors +3 -0
  7. run-20/checkpoint-480/optimizer.pt +3 -0
  8. run-20/checkpoint-480/rng_state.pth +3 -0
  9. run-20/checkpoint-480/scheduler.pt +3 -0
  10. run-20/checkpoint-480/special_tokens_map.json +7 -0
  11. run-20/checkpoint-480/tokenizer.json +0 -0
  12. run-20/checkpoint-480/tokenizer_config.json +57 -0
  13. run-20/checkpoint-480/trainer_state.json +121 -0
  14. run-20/checkpoint-480/training_args.bin +3 -0
  15. run-20/checkpoint-480/vocab.txt +0 -0
  16. run-20/checkpoint-672/config.json +34 -0
  17. run-20/checkpoint-672/model.safetensors +3 -0
  18. run-20/checkpoint-672/optimizer.pt +3 -0
  19. run-20/checkpoint-672/rng_state.pth +3 -0
  20. run-20/checkpoint-672/scheduler.pt +3 -0
  21. run-20/checkpoint-672/special_tokens_map.json +7 -0
  22. run-20/checkpoint-672/tokenizer.json +0 -0
  23. run-20/checkpoint-672/tokenizer_config.json +57 -0
  24. run-20/checkpoint-672/trainer_state.json +159 -0
  25. run-20/checkpoint-672/training_args.bin +3 -0
  26. run-20/checkpoint-672/vocab.txt +0 -0
  27. run-22/checkpoint-96/model.safetensors +1 -1
  28. run-22/checkpoint-96/optimizer.pt +1 -1
  29. run-22/checkpoint-96/scheduler.pt +1 -1
  30. run-22/checkpoint-96/trainer_state.json +18 -18
  31. run-22/checkpoint-96/training_args.bin +1 -1
  32. training_args.bin +1 -1
logs/events.out.tfevents.1709747080.1dcff7455174.7719.20 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a13080da4d52ce0a01c22f2b773b3b3e3e68b56a855b241de2b058cd75bae525
3
- size 5998
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:733f917436d6f9453b5e82bd7b91b686819b0c6f5657cec42eb3a1d92cf77bf8
3
+ size 9767
logs/events.out.tfevents.1709747783.1dcff7455174.7719.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:048ba61b00dfc8413e7679a8b38ff1fa7e0f30526defb15f7af8976066aef651
3
+ size 5316
logs/events.out.tfevents.1709747882.1dcff7455174.7719.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fbfca52a61d64ec1ee8e98a5a5739af1d585d0f00bf20353db8de56622c359e
3
+ size 5315
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28dfeee6a395a8ae4a705885d49b95bccd587f566ac67e35bd52de8d4278cf7c
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6f4518941bcca867b4097c210c9da7b27937b4f2a4d160d2ad6aa36058e2c85
3
  size 17549312
run-20/checkpoint-480/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-20/checkpoint-480/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17cb235ec6888c5eb45d1e3d2fb22d69f5e696a5d0528ebec1566e3249b31f90
3
+ size 17549312
run-20/checkpoint-480/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32679a01af604fa69b270ec73fabe2a9775d102f20e0837ee1d9f5a50b3df22b
3
+ size 35122746
run-20/checkpoint-480/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d93f4cfe67413cd27374342b3b9f13806d5fb593a9dc59106a8b24dedb590a8
3
+ size 14054
run-20/checkpoint-480/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6191b6325d11d5c6f746e8d9b1998c96553209733889bc498c9d40e243608aa
3
+ size 1064
run-20/checkpoint-480/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-20/checkpoint-480/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-20/checkpoint-480/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-20/checkpoint-480/trainer_state.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8346379647749511,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-20/checkpoint-480",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 480,
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": 3.3483004570007324,
14
+ "learning_rate": 0.00013855533928571864,
15
+ "loss": 0.5685,
16
+ "step": 96
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7671232876712328,
21
+ "eval_f1": 0.8019966722129783,
22
+ "eval_loss": 0.477300226688385,
23
+ "eval_precision": 0.6975397973950795,
24
+ "eval_recall": 0.9432485322896281,
25
+ "eval_runtime": 25.843,
26
+ "eval_samples_per_second": 39.546,
27
+ "eval_steps_per_second": 1.238,
28
+ "step": 96
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 2.558192729949951,
33
+ "learning_rate": 0.00011546278273809888,
34
+ "loss": 0.4736,
35
+ "step": 192
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8072407045009785,
40
+ "eval_f1": 0.8255093002657219,
41
+ "eval_loss": 0.43477192521095276,
42
+ "eval_precision": 0.7540453074433657,
43
+ "eval_recall": 0.9119373776908023,
44
+ "eval_runtime": 25.942,
45
+ "eval_samples_per_second": 39.396,
46
+ "eval_steps_per_second": 1.234,
47
+ "step": 192
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 3.4191761016845703,
52
+ "learning_rate": 9.237022619047909e-05,
53
+ "loss": 0.4377,
54
+ "step": 288
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8258317025440313,
59
+ "eval_f1": 0.8381818181818183,
60
+ "eval_loss": 0.4183538258075714,
61
+ "eval_precision": 0.7826825127334465,
62
+ "eval_recall": 0.9021526418786693,
63
+ "eval_runtime": 25.665,
64
+ "eval_samples_per_second": 39.821,
65
+ "eval_steps_per_second": 1.247,
66
+ "step": 288
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 7.199775218963623,
71
+ "learning_rate": 6.927766964285932e-05,
72
+ "loss": 0.4231,
73
+ "step": 384
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8199608610567515,
78
+ "eval_f1": 0.8257575757575758,
79
+ "eval_loss": 0.4184337258338928,
80
+ "eval_precision": 0.8,
81
+ "eval_recall": 0.8532289628180039,
82
+ "eval_runtime": 25.0602,
83
+ "eval_samples_per_second": 40.782,
84
+ "eval_steps_per_second": 1.277,
85
+ "step": 384
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 2.4152629375457764,
90
+ "learning_rate": 4.6185113095239546e-05,
91
+ "loss": 0.4131,
92
+ "step": 480
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.8346379647749511,
97
+ "eval_f1": 0.8467815049864007,
98
+ "eval_loss": 0.4067833125591278,
99
+ "eval_precision": 0.7888513513513513,
100
+ "eval_recall": 0.913894324853229,
101
+ "eval_runtime": 24.9745,
102
+ "eval_samples_per_second": 40.922,
103
+ "eval_steps_per_second": 1.281,
104
+ "step": 480
105
+ }
106
+ ],
107
+ "logging_steps": 500,
108
+ "max_steps": 672,
109
+ "num_input_tokens_seen": 0,
110
+ "num_train_epochs": 7,
111
+ "save_steps": 500,
112
+ "total_flos": 1178475986400.0,
113
+ "train_batch_size": 32,
114
+ "trial_name": null,
115
+ "trial_params": {
116
+ "alpha": 0.8907547983808969,
117
+ "learning_rate": 0.00016164789583333842,
118
+ "num_train_epochs": 7,
119
+ "temperature": 2
120
+ }
121
+ }
run-20/checkpoint-480/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46842c009f41275debcdf9292fb95a9ae38904afa21579baac9749258a827744
3
+ size 4920
run-20/checkpoint-480/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-20/checkpoint-672/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-20/checkpoint-672/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:863c5501abe5b8aa9376fc8348054c6c6d30850ad4d4cae053e761897ce1ed66
3
+ size 17549312
run-20/checkpoint-672/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5b661e891e6195e0c82af243742bf2e745ce262e4e1f78e1be07ecb37324112
3
+ size 35122746
run-20/checkpoint-672/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a39c6918f3fd24e7a04a4220bba5fcc478d9db2386daee293756dba26ecf21ac
3
+ size 14054
run-20/checkpoint-672/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6373ef32a8fae450a2ae5cb8763fcd5f5ea13031101f23ad10af666d3be24bca
3
+ size 1064
run-20/checkpoint-672/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-20/checkpoint-672/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-20/checkpoint-672/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-20/checkpoint-672/trainer_state.json ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8346379647749511,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-20/checkpoint-480",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 672,
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": 3.3483004570007324,
14
+ "learning_rate": 0.00013855533928571864,
15
+ "loss": 0.5685,
16
+ "step": 96
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7671232876712328,
21
+ "eval_f1": 0.8019966722129783,
22
+ "eval_loss": 0.477300226688385,
23
+ "eval_precision": 0.6975397973950795,
24
+ "eval_recall": 0.9432485322896281,
25
+ "eval_runtime": 25.843,
26
+ "eval_samples_per_second": 39.546,
27
+ "eval_steps_per_second": 1.238,
28
+ "step": 96
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 2.558192729949951,
33
+ "learning_rate": 0.00011546278273809888,
34
+ "loss": 0.4736,
35
+ "step": 192
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8072407045009785,
40
+ "eval_f1": 0.8255093002657219,
41
+ "eval_loss": 0.43477192521095276,
42
+ "eval_precision": 0.7540453074433657,
43
+ "eval_recall": 0.9119373776908023,
44
+ "eval_runtime": 25.942,
45
+ "eval_samples_per_second": 39.396,
46
+ "eval_steps_per_second": 1.234,
47
+ "step": 192
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 3.4191761016845703,
52
+ "learning_rate": 9.237022619047909e-05,
53
+ "loss": 0.4377,
54
+ "step": 288
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8258317025440313,
59
+ "eval_f1": 0.8381818181818183,
60
+ "eval_loss": 0.4183538258075714,
61
+ "eval_precision": 0.7826825127334465,
62
+ "eval_recall": 0.9021526418786693,
63
+ "eval_runtime": 25.665,
64
+ "eval_samples_per_second": 39.821,
65
+ "eval_steps_per_second": 1.247,
66
+ "step": 288
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 7.199775218963623,
71
+ "learning_rate": 6.927766964285932e-05,
72
+ "loss": 0.4231,
73
+ "step": 384
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8199608610567515,
78
+ "eval_f1": 0.8257575757575758,
79
+ "eval_loss": 0.4184337258338928,
80
+ "eval_precision": 0.8,
81
+ "eval_recall": 0.8532289628180039,
82
+ "eval_runtime": 25.0602,
83
+ "eval_samples_per_second": 40.782,
84
+ "eval_steps_per_second": 1.277,
85
+ "step": 384
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 2.4152629375457764,
90
+ "learning_rate": 4.6185113095239546e-05,
91
+ "loss": 0.4131,
92
+ "step": 480
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.8346379647749511,
97
+ "eval_f1": 0.8467815049864007,
98
+ "eval_loss": 0.4067833125591278,
99
+ "eval_precision": 0.7888513513513513,
100
+ "eval_recall": 0.913894324853229,
101
+ "eval_runtime": 24.9745,
102
+ "eval_samples_per_second": 40.922,
103
+ "eval_steps_per_second": 1.281,
104
+ "step": 480
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "grad_norm": 3.8709616661071777,
109
+ "learning_rate": 2.3092556547619773e-05,
110
+ "loss": 0.4025,
111
+ "step": 576
112
+ },
113
+ {
114
+ "epoch": 6.0,
115
+ "eval_accuracy": 0.8307240704500979,
116
+ "eval_f1": 0.8442844284428443,
117
+ "eval_loss": 0.4088129699230194,
118
+ "eval_precision": 0.7816666666666666,
119
+ "eval_recall": 0.9178082191780822,
120
+ "eval_runtime": 25.2849,
121
+ "eval_samples_per_second": 40.419,
122
+ "eval_steps_per_second": 1.266,
123
+ "step": 576
124
+ },
125
+ {
126
+ "epoch": 7.0,
127
+ "grad_norm": 3.1289896965026855,
128
+ "learning_rate": 0.0,
129
+ "loss": 0.398,
130
+ "step": 672
131
+ },
132
+ {
133
+ "epoch": 7.0,
134
+ "eval_accuracy": 0.8287671232876712,
135
+ "eval_f1": 0.839596700274977,
136
+ "eval_loss": 0.40621256828308105,
137
+ "eval_precision": 0.7896551724137931,
138
+ "eval_recall": 0.8962818003913894,
139
+ "eval_runtime": 25.662,
140
+ "eval_samples_per_second": 39.825,
141
+ "eval_steps_per_second": 1.247,
142
+ "step": 672
143
+ }
144
+ ],
145
+ "logging_steps": 500,
146
+ "max_steps": 672,
147
+ "num_input_tokens_seen": 0,
148
+ "num_train_epochs": 7,
149
+ "save_steps": 500,
150
+ "total_flos": 1649866380960.0,
151
+ "train_batch_size": 32,
152
+ "trial_name": null,
153
+ "trial_params": {
154
+ "alpha": 0.8907547983808969,
155
+ "learning_rate": 0.00016164789583333842,
156
+ "num_train_epochs": 7,
157
+ "temperature": 2
158
+ }
159
+ }
run-20/checkpoint-672/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46842c009f41275debcdf9292fb95a9ae38904afa21579baac9749258a827744
3
+ size 4920
run-20/checkpoint-672/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-22/checkpoint-96/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53debfa8fff7eaac5c8a752a46f88af3240966d13e2032f508c74638e0aed3df
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6f4518941bcca867b4097c210c9da7b27937b4f2a4d160d2ad6aa36058e2c85
3
  size 17549312
run-22/checkpoint-96/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:464f6a057451f83e13031f3480674b67812e8c5efdf72fd228a7b18720663d12
3
  size 35122746
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78bc300d2ca2ff0207c7b2bf296fc7d5b707da746ac53dc0b887f90a66a35b5e
3
  size 35122746
run-22/checkpoint-96/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42e3d5f21a4bb94288b5c0bed505051f2f9adbc3b3119c8803fb75c431de6fce
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe0130d07a6b0565036c3ff656cfc34f73698e07298c3d765cba0cf202b09e7
3
  size 1064
run-22/checkpoint-96/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.773972602739726,
3
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-22/checkpoint-96",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -10,36 +10,36 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "grad_norm": 1.634097933769226,
14
- "learning_rate": 0.0001003330154271938,
15
- "loss": 0.5664,
16
  "step": 96
17
  },
18
  {
19
  "epoch": 1.0,
20
- "eval_accuracy": 0.773972602739726,
21
- "eval_f1": 0.8027327070879591,
22
- "eval_loss": 0.48113834857940674,
23
- "eval_precision": 0.7121212121212122,
24
- "eval_recall": 0.9197651663405088,
25
- "eval_runtime": 28.856,
26
- "eval_samples_per_second": 35.417,
27
- "eval_steps_per_second": 1.109,
28
  "step": 96
29
  }
30
  ],
31
  "logging_steps": 500,
32
- "max_steps": 288,
33
  "num_input_tokens_seen": 0,
34
- "num_train_epochs": 3,
35
  "save_steps": 500,
36
  "total_flos": 235695197280.0,
37
  "train_batch_size": 32,
38
  "trial_name": null,
39
  "trial_params": {
40
- "alpha": 0.8605867890458055,
41
- "learning_rate": 0.0001504995231407907,
42
- "num_train_epochs": 3,
43
- "temperature": 22
44
  }
45
  }
 
1
  {
2
+ "best_metric": 0.7788649706457925,
3
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-22/checkpoint-96",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "grad_norm": 2.464465618133545,
14
+ "learning_rate": 0.0001794635836369996,
15
+ "loss": 0.565,
16
  "step": 96
17
  },
18
  {
19
  "epoch": 1.0,
20
+ "eval_accuracy": 0.7788649706457925,
21
+ "eval_f1": 0.8078231292517007,
22
+ "eval_loss": 0.4691426157951355,
23
+ "eval_precision": 0.7142857142857143,
24
+ "eval_recall": 0.9295499021526419,
25
+ "eval_runtime": 25.0337,
26
+ "eval_samples_per_second": 40.825,
27
+ "eval_steps_per_second": 1.278,
28
  "step": 96
29
  }
30
  ],
31
  "logging_steps": 500,
32
+ "max_steps": 864,
33
  "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 9,
35
  "save_steps": 500,
36
  "total_flos": 235695197280.0,
37
  "train_batch_size": 32,
38
  "trial_name": null,
39
  "trial_params": {
40
+ "alpha": 0.8956145079239534,
41
+ "learning_rate": 0.00020189653159162458,
42
+ "num_train_epochs": 9,
43
+ "temperature": 8
44
  }
45
  }
run-22/checkpoint-96/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cd17833af62a2bdf35925c6807f6c91df68db0111517d291ec7cc64940e5ee3
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a59435df03122e4e47861365c1b2756f99313581e8b38e82a031f16aa354557d
3
  size 4920
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b133c48486b4ca0f2783f5e1eaa0825a6f32235c8367d680f8abffab8cb5f911
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a59435df03122e4e47861365c1b2756f99313581e8b38e82a031f16aa354557d
3
  size 4920