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
25a95f9
·
verified ·
1 Parent(s): 7b470a7

Training in progress, epoch 1

Browse files
Files changed (39) hide show
  1. logs/events.out.tfevents.1713436809.ec9626078864.14834.12 +2 -2
  2. logs/events.out.tfevents.1713437126.ec9626078864.14834.13 +3 -0
  3. logs/events.out.tfevents.1713437179.ec9626078864.14834.14 +3 -0
  4. logs/events.out.tfevents.1713437232.ec9626078864.14834.15 +3 -0
  5. model.safetensors +1 -1
  6. run-11/checkpoint-3225/config.json +34 -0
  7. run-11/checkpoint-3225/model.safetensors +3 -0
  8. run-11/checkpoint-3225/optimizer.pt +3 -0
  9. run-11/checkpoint-3225/rng_state.pth +3 -0
  10. run-11/checkpoint-3225/scheduler.pt +3 -0
  11. run-11/checkpoint-3225/special_tokens_map.json +7 -0
  12. run-11/checkpoint-3225/tokenizer.json +0 -0
  13. run-11/checkpoint-3225/tokenizer_config.json +57 -0
  14. run-11/checkpoint-3225/trainer_state.json +126 -0
  15. run-11/checkpoint-3225/training_args.bin +3 -0
  16. run-11/checkpoint-3225/vocab.txt +0 -0
  17. run-11/checkpoint-3870/config.json +34 -0
  18. run-11/checkpoint-3870/model.safetensors +3 -0
  19. run-11/checkpoint-3870/optimizer.pt +3 -0
  20. run-11/checkpoint-3870/rng_state.pth +3 -0
  21. run-11/checkpoint-3870/scheduler.pt +3 -0
  22. run-11/checkpoint-3870/special_tokens_map.json +7 -0
  23. run-11/checkpoint-3870/tokenizer.json +0 -0
  24. run-11/checkpoint-3870/tokenizer_config.json +57 -0
  25. run-11/checkpoint-3870/trainer_state.json +146 -0
  26. run-11/checkpoint-3870/training_args.bin +3 -0
  27. run-11/checkpoint-3870/vocab.txt +0 -0
  28. run-14/checkpoint-645/config.json +34 -0
  29. run-14/checkpoint-645/model.safetensors +3 -0
  30. run-14/checkpoint-645/optimizer.pt +3 -0
  31. run-14/checkpoint-645/rng_state.pth +3 -0
  32. run-14/checkpoint-645/scheduler.pt +3 -0
  33. run-14/checkpoint-645/special_tokens_map.json +7 -0
  34. run-14/checkpoint-645/tokenizer.json +0 -0
  35. run-14/checkpoint-645/tokenizer_config.json +57 -0
  36. run-14/checkpoint-645/trainer_state.json +46 -0
  37. run-14/checkpoint-645/training_args.bin +3 -0
  38. run-14/checkpoint-645/vocab.txt +0 -0
  39. training_args.bin +1 -1
logs/events.out.tfevents.1713436809.ec9626078864.14834.12 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03674f5ee4e5071ca559afa6a5b5f9c7096a642d5aecab5fa5be150578a4182e
3
- size 6137
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d0ed9d62e60cef6cdd7182665419770474fb360d8eb58d6e08a41230fadfb2f
3
+ size 9411
logs/events.out.tfevents.1713437126.ec9626078864.14834.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29bbda959f6aab69c86ba197fee560fccde6c5c31584a2a28015572ee6a89a0d
3
+ size 5407
logs/events.out.tfevents.1713437179.ec9626078864.14834.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96f0e6a8643c39c696b1569ce6c3106d5cc2e0bf65319e6e58dee4775395db36
3
+ size 5406
logs/events.out.tfevents.1713437232.ec9626078864.14834.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fd6ff3f5c0959c502361b6e153fdf9d9e0f23f8e6f05413e1f0b87cf520fdb7
3
+ size 5406
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d214427a3608b770ce53aecbd5b67838b3e18d3951bee5cfd5020247218c829
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09640bd0a4c4890df1f44b2f3010a82d69229c89425f4c3efe67921255c1d335
3
  size 17549312
run-11/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-11/checkpoint-3225/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1afcea1a5a2312f3ce94f0bb3974fd92ba6f34db99455264fc252077e4e42910
3
+ size 17549312
run-11/checkpoint-3225/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9af9e3abe3f712e47b4c706d390a529f6a1e9595424cc75670daa40fc6862b81
3
+ size 35123898
run-11/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-11/checkpoint-3225/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6815855aaf9225ab570db8016cdb2dd7f65ad1692a381eb1662961039bfe3f54
3
+ size 1064
run-11/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-11/checkpoint-3225/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-11/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-11/checkpoint-3225/trainer_state.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9009305932531989,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-2580",
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": 1.607855200767517,
14
+ "learning_rate": 0.0001975417814253403,
15
+ "loss": 0.323,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.89433889104304,
21
+ "eval_f1": 0.17549167927382753,
22
+ "eval_loss": 0.2909184396266937,
23
+ "eval_mcc": 0.2237338217806634,
24
+ "eval_precision": 0.6304347826086957,
25
+ "eval_recall": 0.10193321616871705,
26
+ "eval_runtime": 9.9415,
27
+ "eval_samples_per_second": 518.835,
28
+ "eval_steps_per_second": 16.295,
29
+ "step": 645
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 0.786813497543335,
34
+ "learning_rate": 0.00015803342514027224,
35
+ "loss": 0.2905,
36
+ "step": 1290
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8993796044978674,
41
+ "eval_f1": 0.2638297872340425,
42
+ "eval_loss": 0.2894259989261627,
43
+ "eval_mcc": 0.3012574927502475,
44
+ "eval_precision": 0.6838235294117647,
45
+ "eval_recall": 0.1634446397188049,
46
+ "eval_runtime": 9.9325,
47
+ "eval_samples_per_second": 519.307,
48
+ "eval_steps_per_second": 16.31,
49
+ "step": 1290
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.3571267127990723,
54
+ "learning_rate": 0.00011852506885520418,
55
+ "loss": 0.2788,
56
+ "step": 1935
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.8999612252811167,
61
+ "eval_f1": 0.27323943661971833,
62
+ "eval_loss": 0.27123183012008667,
63
+ "eval_mcc": 0.3091027090036446,
64
+ "eval_precision": 0.6879432624113475,
65
+ "eval_recall": 0.1704745166959578,
66
+ "eval_runtime": 9.9597,
67
+ "eval_samples_per_second": 517.885,
68
+ "eval_steps_per_second": 16.265,
69
+ "step": 1935
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 3.1741175651550293,
74
+ "learning_rate": 7.901671257013612e-05,
75
+ "loss": 0.2702,
76
+ "step": 2580
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.9009305932531989,
81
+ "eval_f1": 0.360450563204005,
82
+ "eval_loss": 0.27194449305534363,
83
+ "eval_mcc": 0.3556749244413605,
84
+ "eval_precision": 0.6260869565217392,
85
+ "eval_recall": 0.2530755711775044,
86
+ "eval_runtime": 9.9233,
87
+ "eval_samples_per_second": 519.788,
88
+ "eval_steps_per_second": 16.325,
89
+ "step": 2580
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 1.695178508758545,
94
+ "learning_rate": 3.950835628506806e-05,
95
+ "loss": 0.263,
96
+ "step": 3225
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.9005428460643661,
101
+ "eval_f1": 0.3736263736263736,
102
+ "eval_loss": 0.26569855213165283,
103
+ "eval_mcc": 0.3614230277235667,
104
+ "eval_precision": 0.612,
105
+ "eval_recall": 0.2688927943760984,
106
+ "eval_runtime": 9.9181,
107
+ "eval_samples_per_second": 520.059,
108
+ "eval_steps_per_second": 16.334,
109
+ "step": 3225
110
+ }
111
+ ],
112
+ "logging_steps": 500,
113
+ "max_steps": 3870,
114
+ "num_input_tokens_seen": 0,
115
+ "num_train_epochs": 6,
116
+ "save_steps": 500,
117
+ "total_flos": 7934712663000.0,
118
+ "train_batch_size": 32,
119
+ "trial_name": null,
120
+ "trial_params": {
121
+ "alpha": 0.9710090300316248,
122
+ "learning_rate": 0.00023705013771040836,
123
+ "num_train_epochs": 6,
124
+ "temperature": 29
125
+ }
126
+ }
run-11/checkpoint-3225/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1de49bd0f41aa5672da08260ef6b27988cb8c8a163c452ae19b99e8326f3fb04
3
+ size 4984
run-11/checkpoint-3225/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-11/checkpoint-3870/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-11/checkpoint-3870/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e67979a3c24ce85dda3c2abc8f0655ccbb05faf7e4b55b33cbb224fc91e86344
3
+ size 17549312
run-11/checkpoint-3870/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2b3f363adc7989284a656f1fabffada94b4c78511265ea50890c4dc6d3ab97d
3
+ size 35123898
run-11/checkpoint-3870/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd3594daca53cebdd7cbf0d80846211d0eafca218895f209b5494269a0d240f
3
+ size 14308
run-11/checkpoint-3870/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4440edf2fd4512d52abbfdb11023be4f1f7db264c2dd48cbd6c0cf9c73a0e5f1
3
+ size 1064
run-11/checkpoint-3870/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-11/checkpoint-3870/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-11/checkpoint-3870/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-11/checkpoint-3870/trainer_state.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9030632027917798,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-3870",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3870,
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": 1.607855200767517,
14
+ "learning_rate": 0.0001975417814253403,
15
+ "loss": 0.323,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.89433889104304,
21
+ "eval_f1": 0.17549167927382753,
22
+ "eval_loss": 0.2909184396266937,
23
+ "eval_mcc": 0.2237338217806634,
24
+ "eval_precision": 0.6304347826086957,
25
+ "eval_recall": 0.10193321616871705,
26
+ "eval_runtime": 9.9415,
27
+ "eval_samples_per_second": 518.835,
28
+ "eval_steps_per_second": 16.295,
29
+ "step": 645
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 0.786813497543335,
34
+ "learning_rate": 0.00015803342514027224,
35
+ "loss": 0.2905,
36
+ "step": 1290
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.8993796044978674,
41
+ "eval_f1": 0.2638297872340425,
42
+ "eval_loss": 0.2894259989261627,
43
+ "eval_mcc": 0.3012574927502475,
44
+ "eval_precision": 0.6838235294117647,
45
+ "eval_recall": 0.1634446397188049,
46
+ "eval_runtime": 9.9325,
47
+ "eval_samples_per_second": 519.307,
48
+ "eval_steps_per_second": 16.31,
49
+ "step": 1290
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 1.3571267127990723,
54
+ "learning_rate": 0.00011852506885520418,
55
+ "loss": 0.2788,
56
+ "step": 1935
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.8999612252811167,
61
+ "eval_f1": 0.27323943661971833,
62
+ "eval_loss": 0.27123183012008667,
63
+ "eval_mcc": 0.3091027090036446,
64
+ "eval_precision": 0.6879432624113475,
65
+ "eval_recall": 0.1704745166959578,
66
+ "eval_runtime": 9.9597,
67
+ "eval_samples_per_second": 517.885,
68
+ "eval_steps_per_second": 16.265,
69
+ "step": 1935
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 3.1741175651550293,
74
+ "learning_rate": 7.901671257013612e-05,
75
+ "loss": 0.2702,
76
+ "step": 2580
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.9009305932531989,
81
+ "eval_f1": 0.360450563204005,
82
+ "eval_loss": 0.27194449305534363,
83
+ "eval_mcc": 0.3556749244413605,
84
+ "eval_precision": 0.6260869565217392,
85
+ "eval_recall": 0.2530755711775044,
86
+ "eval_runtime": 9.9233,
87
+ "eval_samples_per_second": 519.788,
88
+ "eval_steps_per_second": 16.325,
89
+ "step": 2580
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 1.695178508758545,
94
+ "learning_rate": 3.950835628506806e-05,
95
+ "loss": 0.263,
96
+ "step": 3225
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.9005428460643661,
101
+ "eval_f1": 0.3736263736263736,
102
+ "eval_loss": 0.26569855213165283,
103
+ "eval_mcc": 0.3614230277235667,
104
+ "eval_precision": 0.612,
105
+ "eval_recall": 0.2688927943760984,
106
+ "eval_runtime": 9.9181,
107
+ "eval_samples_per_second": 520.059,
108
+ "eval_steps_per_second": 16.334,
109
+ "step": 3225
110
+ },
111
+ {
112
+ "epoch": 6.0,
113
+ "grad_norm": 1.3037900924682617,
114
+ "learning_rate": 0.0,
115
+ "loss": 0.2585,
116
+ "step": 3870
117
+ },
118
+ {
119
+ "epoch": 6.0,
120
+ "eval_accuracy": 0.9030632027917798,
121
+ "eval_f1": 0.3765586034912718,
122
+ "eval_loss": 0.26524817943573,
123
+ "eval_mcc": 0.3733577307997014,
124
+ "eval_precision": 0.648068669527897,
125
+ "eval_recall": 0.26537785588752194,
126
+ "eval_runtime": 9.9309,
127
+ "eval_samples_per_second": 519.389,
128
+ "eval_steps_per_second": 16.313,
129
+ "step": 3870
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 3870,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 6,
136
+ "save_steps": 500,
137
+ "total_flos": 9521655195600.0,
138
+ "train_batch_size": 32,
139
+ "trial_name": null,
140
+ "trial_params": {
141
+ "alpha": 0.9710090300316248,
142
+ "learning_rate": 0.00023705013771040836,
143
+ "num_train_epochs": 6,
144
+ "temperature": 29
145
+ }
146
+ }
run-11/checkpoint-3870/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1de49bd0f41aa5672da08260ef6b27988cb8c8a163c452ae19b99e8326f3fb04
3
+ size 4984
run-11/checkpoint-3870/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-14/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-14/checkpoint-645/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09640bd0a4c4890df1f44b2f3010a82d69229c89425f4c3efe67921255c1d335
3
+ size 17549312
run-14/checkpoint-645/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96d17060799fa04810c0da2ea5a7158609f2d2f23649b7bf3e0939bd2f9cda4e
3
+ size 35123898
run-14/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-14/checkpoint-645/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84237a3cb8f2e6593db455e59f5eb7fd54005ec2f77dd9cb797598f700f414e7
3
+ size 1064
run-14/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-14/checkpoint-645/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-14/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-14/checkpoint-645/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8887165568049632,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/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": 1.9803465604782104,
14
+ "learning_rate": 0.00027230837357094026,
15
+ "loss": 0.327,
16
+ "step": 645
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8887165568049632,
21
+ "eval_f1": 0.19154929577464788,
22
+ "eval_loss": 0.3063199520111084,
23
+ "eval_mcc": 0.1990419339488759,
24
+ "eval_precision": 0.48226950354609927,
25
+ "eval_recall": 0.1195079086115993,
26
+ "eval_runtime": 9.9261,
27
+ "eval_samples_per_second": 519.642,
28
+ "eval_steps_per_second": 16.321,
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": 0.9932188265495786,
42
+ "learning_rate": 0.0003112095697953603,
43
+ "num_train_epochs": 8,
44
+ "temperature": 21
45
+ }
46
+ }
run-14/checkpoint-645/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:477fc5e0a8a4f66ce89d996de5d48a66ce5157517c69b38a9deeba1e7b63e8ee
3
+ size 4984
run-14/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 sha256:1de49bd0f41aa5672da08260ef6b27988cb8c8a163c452ae19b99e8326f3fb04
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:477fc5e0a8a4f66ce89d996de5d48a66ce5157517c69b38a9deeba1e7b63e8ee
3
  size 4984