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
3c5fa98
·
verified ·
1 Parent(s): 60fcc97

Training in progress, epoch 1

Browse files
Files changed (39) hide show
  1. logs/events.out.tfevents.1713438663.ec9626078864.14834.25 +2 -2
  2. logs/events.out.tfevents.1713438974.ec9626078864.14834.26 +3 -0
  3. logs/events.out.tfevents.1713439025.ec9626078864.14834.27 +3 -0
  4. logs/events.out.tfevents.1713439077.ec9626078864.14834.28 +3 -0
  5. model.safetensors +1 -1
  6. run-24/checkpoint-2580/config.json +34 -0
  7. run-24/checkpoint-2580/model.safetensors +3 -0
  8. run-24/checkpoint-2580/optimizer.pt +3 -0
  9. run-24/checkpoint-2580/rng_state.pth +3 -0
  10. run-24/checkpoint-2580/scheduler.pt +3 -0
  11. run-24/checkpoint-2580/special_tokens_map.json +7 -0
  12. run-24/checkpoint-2580/tokenizer.json +0 -0
  13. run-24/checkpoint-2580/tokenizer_config.json +57 -0
  14. run-24/checkpoint-2580/trainer_state.json +106 -0
  15. run-24/checkpoint-2580/training_args.bin +3 -0
  16. run-24/checkpoint-2580/vocab.txt +0 -0
  17. run-24/checkpoint-3225/config.json +34 -0
  18. run-24/checkpoint-3225/model.safetensors +3 -0
  19. run-24/checkpoint-3225/optimizer.pt +3 -0
  20. run-24/checkpoint-3225/rng_state.pth +3 -0
  21. run-24/checkpoint-3225/scheduler.pt +3 -0
  22. run-24/checkpoint-3225/special_tokens_map.json +7 -0
  23. run-24/checkpoint-3225/tokenizer.json +0 -0
  24. run-24/checkpoint-3225/tokenizer_config.json +57 -0
  25. run-24/checkpoint-3225/trainer_state.json +126 -0
  26. run-24/checkpoint-3225/training_args.bin +3 -0
  27. run-24/checkpoint-3225/vocab.txt +0 -0
  28. run-27/checkpoint-645/config.json +34 -0
  29. run-27/checkpoint-645/model.safetensors +3 -0
  30. run-27/checkpoint-645/optimizer.pt +3 -0
  31. run-27/checkpoint-645/rng_state.pth +3 -0
  32. run-27/checkpoint-645/scheduler.pt +3 -0
  33. run-27/checkpoint-645/special_tokens_map.json +7 -0
  34. run-27/checkpoint-645/tokenizer.json +0 -0
  35. run-27/checkpoint-645/tokenizer_config.json +57 -0
  36. run-27/checkpoint-645/trainer_state.json +46 -0
  37. run-27/checkpoint-645/training_args.bin +3 -0
  38. run-27/checkpoint-645/vocab.txt +0 -0
  39. training_args.bin +1 -1
logs/events.out.tfevents.1713438663.ec9626078864.14834.25 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd5a6ed726904a4431eef178c21b588b94e99520658775b7ee841c21749a3eb8
3
- size 6136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8393332f77186619533cb60d3ba3e181dac94114aeeb1809a54b2e918fe685d
3
+ size 9056
logs/events.out.tfevents.1713438974.ec9626078864.14834.26 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:437200fab10b9fd409647ff24944a3864bb52ce27d199461d41ee205e2fc531f
3
+ size 5406
logs/events.out.tfevents.1713439025.ec9626078864.14834.27 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85d01f6f0913a42f8af16daf5c6c9a22504a13428e9d03c72b851d522fa90172
3
+ size 5406
logs/events.out.tfevents.1713439077.ec9626078864.14834.28 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60540a3870c26a9ea545d157b12e4690ea109ebba89531ca763a91a50ac432a8
3
+ size 5406
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79324ee299446ba31cf44449c80edf4d74a27ee08f8555b5d96f48fb5a7bac75
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6570a2091c27fd7974a205c43645145a3646f0ce971633b7b03fad4b672161a4
3
  size 17549312
run-24/checkpoint-2580/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": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-24/checkpoint-2580/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94be1b9f20351267e60aafd1796a0ac4d46c65d47d02501da17b30d050114019
3
+ size 17549312
run-24/checkpoint-2580/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ed046d6b96e2e22980c74b80e8a5317708c082d7ba1334e388a76cc9bf85a1
3
+ size 35123898
run-24/checkpoint-2580/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a023a654d9d331ee734f6327c4a0681d27975c593b68916f513cbf43ea84370
3
+ size 14308
run-24/checkpoint-2580/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e01e12a0593d68151ca8209b97b8102a2d9ed24eadc9bca3d5bb9d15ba2da69e
3
+ size 1064
run-24/checkpoint-2580/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-24/checkpoint-2580/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-24/checkpoint-2580/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-24/checkpoint-2580/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8949205118262893,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-24/checkpoint-1935",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2580,
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": 1.1594387292861938,
14
+ "learning_rate": 0.0003669096859466192,
15
+ "loss": 0.3104,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8937572702597906,
21
+ "eval_f1": 0.17717717717717715,
22
+ "eval_loss": 0.29782024025917053,
23
+ "eval_mcc": 0.22004174832122259,
24
+ "eval_precision": 0.6082474226804123,
25
+ "eval_recall": 0.10369068541300527,
26
+ "eval_runtime": 9.922,
27
+ "eval_samples_per_second": 519.854,
28
+ "eval_steps_per_second": 16.327,
29
+ "step": 645
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.089403510093689,
34
+ "learning_rate": 0.0003210459752032918,
35
+ "loss": 0.2989,
36
+ "step": 1290
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8937572702597906,
41
+ "eval_f1": 0.1217948717948718,
42
+ "eval_loss": 0.29260244965553284,
43
+ "eval_mcc": 0.19240131656369383,
44
+ "eval_precision": 0.6909090909090909,
45
+ "eval_recall": 0.06678383128295255,
46
+ "eval_runtime": 9.8986,
47
+ "eval_samples_per_second": 521.085,
48
+ "eval_steps_per_second": 16.366,
49
+ "step": 1290
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 0.7798711657524109,
54
+ "learning_rate": 0.00027518226445996435,
55
+ "loss": 0.2922,
56
+ "step": 1935
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.8949205118262893,
61
+ "eval_f1": 0.09666666666666668,
62
+ "eval_loss": 0.2949424088001251,
63
+ "eval_mcc": 0.20481355074293853,
64
+ "eval_precision": 0.9354838709677419,
65
+ "eval_recall": 0.050966608084358524,
66
+ "eval_runtime": 9.9157,
67
+ "eval_samples_per_second": 520.185,
68
+ "eval_steps_per_second": 16.338,
69
+ "step": 1935
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.8487693071365356,
74
+ "learning_rate": 0.000229318553716637,
75
+ "loss": 0.2851,
76
+ "step": 2580
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.8937572702597906,
81
+ "eval_f1": 0.3251231527093596,
82
+ "eval_loss": 0.2875448167324066,
83
+ "eval_mcc": 0.3072493162328444,
84
+ "eval_precision": 0.5432098765432098,
85
+ "eval_recall": 0.23198594024604569,
86
+ "eval_runtime": 9.9077,
87
+ "eval_samples_per_second": 520.607,
88
+ "eval_steps_per_second": 16.351,
89
+ "step": 2580
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 5805,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 9,
96
+ "save_steps": 500,
97
+ "total_flos": 6347770130400.0,
98
+ "train_batch_size": 32,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.8984215980104533,
102
+ "learning_rate": 0.0004127733966899466,
103
+ "num_train_epochs": 9,
104
+ "temperature": 29
105
+ }
106
+ }
run-24/checkpoint-2580/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:456127f7769e7956edafc511b28db8949081a7bcc64e2dae6a89559f359d58a4
3
+ size 4984
run-24/checkpoint-2580/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-24/checkpoint-3225/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": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-24/checkpoint-3225/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d43649e66a920e0421939ccf30bbd2d3819572a179e24c1e4d7c9d865b4a7da8
3
+ size 17549312
run-24/checkpoint-3225/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c901e0eedcb0e23df0170e38200e9d06889dc186cecd102b1f6adb6e4cd77060
3
+ size 35123898
run-24/checkpoint-3225/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6303d047155f3543a5a16a3524b9e783dc242e14523f52e867381087cb66480
3
+ size 14308
run-24/checkpoint-3225/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74db6d9fdd589e1035b58ddce05e5719129fa906a3d5d1e5141c094421d500e2
3
+ size 1064
run-24/checkpoint-3225/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-24/checkpoint-3225/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-24/checkpoint-3225/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-24/checkpoint-3225/trainer_state.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8980224893369523,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-24/checkpoint-3225",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3225,
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": 1.1594387292861938,
14
+ "learning_rate": 0.0003669096859466192,
15
+ "loss": 0.3104,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8937572702597906,
21
+ "eval_f1": 0.17717717717717715,
22
+ "eval_loss": 0.29782024025917053,
23
+ "eval_mcc": 0.22004174832122259,
24
+ "eval_precision": 0.6082474226804123,
25
+ "eval_recall": 0.10369068541300527,
26
+ "eval_runtime": 9.922,
27
+ "eval_samples_per_second": 519.854,
28
+ "eval_steps_per_second": 16.327,
29
+ "step": 645
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 1.089403510093689,
34
+ "learning_rate": 0.0003210459752032918,
35
+ "loss": 0.2989,
36
+ "step": 1290
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8937572702597906,
41
+ "eval_f1": 0.1217948717948718,
42
+ "eval_loss": 0.29260244965553284,
43
+ "eval_mcc": 0.19240131656369383,
44
+ "eval_precision": 0.6909090909090909,
45
+ "eval_recall": 0.06678383128295255,
46
+ "eval_runtime": 9.8986,
47
+ "eval_samples_per_second": 521.085,
48
+ "eval_steps_per_second": 16.366,
49
+ "step": 1290
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 0.7798711657524109,
54
+ "learning_rate": 0.00027518226445996435,
55
+ "loss": 0.2922,
56
+ "step": 1935
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.8949205118262893,
61
+ "eval_f1": 0.09666666666666668,
62
+ "eval_loss": 0.2949424088001251,
63
+ "eval_mcc": 0.20481355074293853,
64
+ "eval_precision": 0.9354838709677419,
65
+ "eval_recall": 0.050966608084358524,
66
+ "eval_runtime": 9.9157,
67
+ "eval_samples_per_second": 520.185,
68
+ "eval_steps_per_second": 16.338,
69
+ "step": 1935
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 1.8487693071365356,
74
+ "learning_rate": 0.000229318553716637,
75
+ "loss": 0.2851,
76
+ "step": 2580
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.8937572702597906,
81
+ "eval_f1": 0.3251231527093596,
82
+ "eval_loss": 0.2875448167324066,
83
+ "eval_mcc": 0.3072493162328444,
84
+ "eval_precision": 0.5432098765432098,
85
+ "eval_recall": 0.23198594024604569,
86
+ "eval_runtime": 9.9077,
87
+ "eval_samples_per_second": 520.607,
88
+ "eval_steps_per_second": 16.351,
89
+ "step": 2580
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 1.9229811429977417,
94
+ "learning_rate": 0.0001834548429733096,
95
+ "loss": 0.2806,
96
+ "step": 3225
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.8980224893369523,
101
+ "eval_f1": 0.31510416666666663,
102
+ "eval_loss": 0.28026217222213745,
103
+ "eval_mcc": 0.3182629598429773,
104
+ "eval_precision": 0.6080402010050251,
105
+ "eval_recall": 0.2126537785588752,
106
+ "eval_runtime": 9.9166,
107
+ "eval_samples_per_second": 520.138,
108
+ "eval_steps_per_second": 16.336,
109
+ "step": 3225
110
+ }
111
+ ],
112
+ "logging_steps": 500,
113
+ "max_steps": 5805,
114
+ "num_input_tokens_seen": 0,
115
+ "num_train_epochs": 9,
116
+ "save_steps": 500,
117
+ "total_flos": 7934712663000.0,
118
+ "train_batch_size": 32,
119
+ "trial_name": null,
120
+ "trial_params": {
121
+ "alpha": 0.8984215980104533,
122
+ "learning_rate": 0.0004127733966899466,
123
+ "num_train_epochs": 9,
124
+ "temperature": 29
125
+ }
126
+ }
run-24/checkpoint-3225/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:456127f7769e7956edafc511b28db8949081a7bcc64e2dae6a89559f359d58a4
3
+ size 4984
run-24/checkpoint-3225/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-27/checkpoint-645/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": "4.39.3",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-27/checkpoint-645/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6570a2091c27fd7974a205c43645145a3646f0ce971633b7b03fad4b672161a4
3
+ size 17549312
run-27/checkpoint-645/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5134fa2f8b9fbc9942e067eb051b169e2edd3be3b2eec9ffebf2d4d318d9f643
3
+ size 35123898
run-27/checkpoint-645/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f64cda8af0c2d214cf65bdf171fde38f18025a5a08f9a451c61fdf726867d7c2
3
+ size 14308
run-27/checkpoint-645/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fee58321269521bf47d753dd28e665e0c386f2508dbd60fbd09ffce596e04d21
3
+ size 1064
run-27/checkpoint-645/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-27/checkpoint-645/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-27/checkpoint-645/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-27/checkpoint-645/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8912369135323769,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-27/checkpoint-645",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 645,
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": 2.374743938446045,
14
+ "learning_rate": 8.115439310915276e-05,
15
+ "loss": 0.333,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8912369135323769,
21
+ "eval_f1": 0.16888888888888887,
22
+ "eval_loss": 0.30435287952423096,
23
+ "eval_mcc": 0.19762599967287012,
24
+ "eval_precision": 0.5377358490566038,
25
+ "eval_recall": 0.10017574692442882,
26
+ "eval_runtime": 9.9164,
27
+ "eval_samples_per_second": 520.146,
28
+ "eval_steps_per_second": 16.337,
29
+ "step": 645
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 5160,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 8,
36
+ "save_steps": 500,
37
+ "total_flos": 1586942532600.0,
38
+ "train_batch_size": 32,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "alpha": 0.9885260340274179,
42
+ "learning_rate": 9.274787783903173e-05,
43
+ "num_train_epochs": 8,
44
+ "temperature": 24
45
+ }
46
+ }
run-27/checkpoint-645/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7809ad499bcbed21ac8f793f429b52c03cdf6367722047c9b6b05e2444c635a9
3
+ size 4984
run-27/checkpoint-645/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 sha256:456127f7769e7956edafc511b28db8949081a7bcc64e2dae6a89559f359d58a4
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7809ad499bcbed21ac8f793f429b52c03cdf6367722047c9b6b05e2444c635a9
3
  size 4984