Hugging Face's logo

HikasaHana
/
BERT-WMM

Text Classification
Transformers
TensorBoard
Safetensors
Chinese
bert
Inference Endpoints
Model card Files Metrics Community
HikasaHana commited on
Commit
df0f609
·
verified ·
1 Parent(s): 7f30550

Training in progress, epoch 1

Browse files
Files changed (32) hide show
  1. run-13/checkpoint-1068/config.json +43 -0
  2. run-13/checkpoint-1068/model.safetensors +3 -0
  3. run-13/checkpoint-1068/optimizer.pt +3 -0
  4. run-13/checkpoint-1068/rng_state.pth +3 -0
  5. run-13/checkpoint-1068/scheduler.pt +3 -0
  6. run-13/checkpoint-1068/special_tokens_map.json +37 -0
  7. run-13/checkpoint-1068/tokenizer_config.json +57 -0
  8. run-13/checkpoint-1068/trainer_state.json +73 -0
  9. run-13/checkpoint-1068/training_args.bin +3 -0
  10. run-13/checkpoint-1068/vocab.txt +0 -0
  11. run-13/checkpoint-1335/config.json +43 -0
  12. run-13/checkpoint-1335/model.safetensors +3 -0
  13. run-13/checkpoint-1335/optimizer.pt +3 -0
  14. run-13/checkpoint-1335/rng_state.pth +3 -0
  15. run-13/checkpoint-1335/scheduler.pt +3 -0
  16. run-13/checkpoint-1335/special_tokens_map.json +37 -0
  17. run-13/checkpoint-1335/tokenizer_config.json +57 -0
  18. run-13/checkpoint-1335/trainer_state.json +82 -0
  19. run-13/checkpoint-1335/training_args.bin +3 -0
  20. run-13/checkpoint-1335/vocab.txt +0 -0
  21. run-15/checkpoint-267/config.json +43 -0
  22. run-15/checkpoint-267/model.safetensors +3 -0
  23. run-15/checkpoint-267/optimizer.pt +3 -0
  24. run-15/checkpoint-267/rng_state.pth +3 -0
  25. run-15/checkpoint-267/scheduler.pt +3 -0
  26. run-15/checkpoint-267/special_tokens_map.json +37 -0
  27. run-15/checkpoint-267/tokenizer_config.json +57 -0
  28. run-15/checkpoint-267/trainer_state.json +32 -0
  29. run-15/checkpoint-267/training_args.bin +3 -0
  30. run-15/checkpoint-267/vocab.txt +0 -0
  31. runs/Apr19_08-35-52_21d31c708e60/events.out.tfevents.1713519969.21d31c708e60.946.34 +3 -0
  32. runs/Apr19_08-35-52_21d31c708e60/events.out.tfevents.1713520006.21d31c708e60.946.35 +3 -0
run-13/checkpoint-1068/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hfl/chinese-bert-wwm-ext",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "NEGATIVE",
14
+ "1": "POSITIVE",
15
+ "2": "NEUTRAL"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "NEGATIVE": 0,
21
+ "NEUTRAL": 2,
22
+ "POSITIVE": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "output_past": true,
30
+ "pad_token_id": 0,
31
+ "pooler_fc_size": 768,
32
+ "pooler_num_attention_heads": 12,
33
+ "pooler_num_fc_layers": 3,
34
+ "pooler_size_per_head": 128,
35
+ "pooler_type": "first_token_transform",
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "single_label_classification",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.38.2",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 21128
43
+ }
run-13/checkpoint-1068/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be86a3545123e440e90e40dcbfd3e25b7c607d03543cf59dbfbcfd5ab4c3b45f
3
+ size 409103316
run-13/checkpoint-1068/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26e1166e00c810b5e1aece2aa8579986f54f02a7ac182283da9312b97e3dc9e8
3
+ size 818327802
run-13/checkpoint-1068/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88efce74fbb2721dc5ac34e297a693ee9d8b613381cc20bc06917c3f551f452b
3
+ size 14244
run-13/checkpoint-1068/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99710eaca949f554ced3febb88242f5791546c4a3874f3ce0ec9086db0a0ce0b
3
+ size 1064
run-13/checkpoint-1068/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
run-13/checkpoint-1068/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": 1000000000000000019884624838656,
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-1068/trainer_state.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5776590704917908,
3
+ "best_model_checkpoint": "BERT-WMM/run-13/checkpoint-534",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1068,
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
+ "eval_accuracy": 0.7577464788732394,
14
+ "eval_loss": 0.6081846952438354,
15
+ "eval_runtime": 2.4174,
16
+ "eval_samples_per_second": 881.101,
17
+ "eval_steps_per_second": 55.431,
18
+ "step": 267
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "grad_norm": 9.532360076904297,
23
+ "learning_rate": 9.65168237740807e-06,
24
+ "loss": 0.6057,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.7657276995305164,
30
+ "eval_loss": 0.5776590704917908,
31
+ "eval_runtime": 2.4511,
32
+ "eval_samples_per_second": 868.982,
33
+ "eval_steps_per_second": 54.668,
34
+ "step": 534
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_accuracy": 0.7690140845070422,
39
+ "eval_loss": 0.6647635102272034,
40
+ "eval_runtime": 2.4588,
41
+ "eval_samples_per_second": 866.264,
42
+ "eval_steps_per_second": 54.497,
43
+ "step": 801
44
+ },
45
+ {
46
+ "epoch": 3.75,
47
+ "grad_norm": 26.327552795410156,
48
+ "learning_rate": 3.872231852014017e-06,
49
+ "loss": 0.2807,
50
+ "step": 1000
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "eval_accuracy": 0.7615023474178404,
55
+ "eval_loss": 0.758091151714325,
56
+ "eval_runtime": 2.483,
57
+ "eval_samples_per_second": 857.84,
58
+ "eval_steps_per_second": 53.967,
59
+ "step": 1068
60
+ }
61
+ ],
62
+ "logging_steps": 500,
63
+ "max_steps": 1335,
64
+ "num_input_tokens_seen": 0,
65
+ "num_train_epochs": 5,
66
+ "save_steps": 500,
67
+ "total_flos": 697511614823352.0,
68
+ "train_batch_size": 32,
69
+ "trial_name": null,
70
+ "trial_params": {
71
+ "num_train_epochs": 5
72
+ }
73
+ }
run-13/checkpoint-1068/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
3
+ size 4856
run-13/checkpoint-1068/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-13/checkpoint-1335/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hfl/chinese-bert-wwm-ext",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "NEGATIVE",
14
+ "1": "POSITIVE",
15
+ "2": "NEUTRAL"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "NEGATIVE": 0,
21
+ "NEUTRAL": 2,
22
+ "POSITIVE": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "output_past": true,
30
+ "pad_token_id": 0,
31
+ "pooler_fc_size": 768,
32
+ "pooler_num_attention_heads": 12,
33
+ "pooler_num_fc_layers": 3,
34
+ "pooler_size_per_head": 128,
35
+ "pooler_type": "first_token_transform",
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "single_label_classification",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.38.2",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 21128
43
+ }
run-13/checkpoint-1335/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87d7df15b3f66abb639f6f827a81d42cb4047051cfbde3665cb2ce2fecb82122
3
+ size 409103316
run-13/checkpoint-1335/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f151333b045123e4862a3a7fab6912fb367a75dc6421cb1df423ce26a10162f0
3
+ size 818327802
run-13/checkpoint-1335/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe610f625e919d82fdbaa3afd268f77970e25b62afd1b9f3d78dc3d12f69f50
3
+ size 14244
run-13/checkpoint-1335/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9462cebdd70bc492d7b3757b48d821084c9fd9829a619f501a3658a0972c6551
3
+ size 1064
run-13/checkpoint-1335/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
run-13/checkpoint-1335/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": 1000000000000000019884624838656,
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-1335/trainer_state.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5776590704917908,
3
+ "best_model_checkpoint": "BERT-WMM/run-13/checkpoint-534",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1335,
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
+ "eval_accuracy": 0.7577464788732394,
14
+ "eval_loss": 0.6081846952438354,
15
+ "eval_runtime": 2.4174,
16
+ "eval_samples_per_second": 881.101,
17
+ "eval_steps_per_second": 55.431,
18
+ "step": 267
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "grad_norm": 9.532360076904297,
23
+ "learning_rate": 9.65168237740807e-06,
24
+ "loss": 0.6057,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.7657276995305164,
30
+ "eval_loss": 0.5776590704917908,
31
+ "eval_runtime": 2.4511,
32
+ "eval_samples_per_second": 868.982,
33
+ "eval_steps_per_second": 54.668,
34
+ "step": 534
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_accuracy": 0.7690140845070422,
39
+ "eval_loss": 0.6647635102272034,
40
+ "eval_runtime": 2.4588,
41
+ "eval_samples_per_second": 866.264,
42
+ "eval_steps_per_second": 54.497,
43
+ "step": 801
44
+ },
45
+ {
46
+ "epoch": 3.75,
47
+ "grad_norm": 26.327552795410156,
48
+ "learning_rate": 3.872231852014017e-06,
49
+ "loss": 0.2807,
50
+ "step": 1000
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "eval_accuracy": 0.7615023474178404,
55
+ "eval_loss": 0.758091151714325,
56
+ "eval_runtime": 2.483,
57
+ "eval_samples_per_second": 857.84,
58
+ "eval_steps_per_second": 53.967,
59
+ "step": 1068
60
+ },
61
+ {
62
+ "epoch": 5.0,
63
+ "eval_accuracy": 0.7643192488262911,
64
+ "eval_loss": 0.8205846548080444,
65
+ "eval_runtime": 2.4655,
66
+ "eval_samples_per_second": 863.914,
67
+ "eval_steps_per_second": 54.35,
68
+ "step": 1335
69
+ }
70
+ ],
71
+ "logging_steps": 500,
72
+ "max_steps": 1335,
73
+ "num_input_tokens_seen": 0,
74
+ "num_train_epochs": 5,
75
+ "save_steps": 500,
76
+ "total_flos": 697511614823352.0,
77
+ "train_batch_size": 32,
78
+ "trial_name": null,
79
+ "trial_params": {
80
+ "num_train_epochs": 5
81
+ }
82
+ }
run-13/checkpoint-1335/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
3
+ size 4856
run-13/checkpoint-1335/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-15/checkpoint-267/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hfl/chinese-bert-wwm-ext",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "NEGATIVE",
14
+ "1": "POSITIVE",
15
+ "2": "NEUTRAL"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "NEGATIVE": 0,
21
+ "NEUTRAL": 2,
22
+ "POSITIVE": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "output_past": true,
30
+ "pad_token_id": 0,
31
+ "pooler_fc_size": 768,
32
+ "pooler_num_attention_heads": 12,
33
+ "pooler_num_fc_layers": 3,
34
+ "pooler_size_per_head": 128,
35
+ "pooler_type": "first_token_transform",
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "single_label_classification",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.38.2",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 21128
43
+ }
run-15/checkpoint-267/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:709e0174af7e7bfc36b2ca42177cb07663d435c4830e3ef2fd95156cc7684138
3
+ size 409103316
run-15/checkpoint-267/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52ef4431d2c45c5021200b1e749d9a863141163026b276944e492c1db9ee3f59
3
+ size 818327802
run-15/checkpoint-267/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0980580128ccd5e578c966c8ffb616b8165a0951ed4f83a639bfa5862c1defb0
3
+ size 14244
run-15/checkpoint-267/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44c8fc955f6ab66538b705aa40f6ebb08474ec445464a7a19ca29971b9fc42d4
3
+ size 1064
run-15/checkpoint-267/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
run-15/checkpoint-267/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": 1000000000000000019884624838656,
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-15/checkpoint-267/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6081846952438354,
3
+ "best_model_checkpoint": "BERT-WMM/run-15/checkpoint-267",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 267,
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
+ "eval_accuracy": 0.7577464788732394,
14
+ "eval_loss": 0.6081846952438354,
15
+ "eval_runtime": 2.4313,
16
+ "eval_samples_per_second": 876.086,
17
+ "eval_steps_per_second": 55.115,
18
+ "step": 267
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 1335,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 32,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "num_train_epochs": 5
31
+ }
32
+ }
run-15/checkpoint-267/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
3
+ size 4856
run-15/checkpoint-267/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr19_08-35-52_21d31c708e60/events.out.tfevents.1713519969.21d31c708e60.946.34 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45fecd47b65c1cb4d60c810d9245cf888b90badffe4d59facaab5375402137d2
3
+ size 5217
runs/Apr19_08-35-52_21d31c708e60/events.out.tfevents.1713520006.21d31c708e60.946.35 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c2f4913529a3a3a17d28b15626443b8f8f2ff9b8fae85a769c935e9258c7fa6
3
+ size 7285