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
306cdf2
·
verified ·
1 Parent(s): d59c5d2

Training in progress, epoch 1

Browse files
Files changed (34) hide show
  1. model.safetensors +1 -1
  2. run-14/checkpoint-1066/config.json +43 -0
  3. run-14/checkpoint-1066/model.safetensors +3 -0
  4. run-14/checkpoint-1066/optimizer.pt +3 -0
  5. run-14/checkpoint-1066/rng_state.pth +3 -0
  6. run-14/checkpoint-1066/scheduler.pt +3 -0
  7. run-14/checkpoint-1066/special_tokens_map.json +37 -0
  8. run-14/checkpoint-1066/tokenizer_config.json +57 -0
  9. run-14/checkpoint-1066/trainer_state.json +55 -0
  10. run-14/checkpoint-1066/training_args.bin +3 -0
  11. run-14/checkpoint-1066/vocab.txt +0 -0
  12. run-14/checkpoint-1599/config.json +43 -0
  13. run-14/checkpoint-1599/model.safetensors +3 -0
  14. run-14/checkpoint-1599/optimizer.pt +3 -0
  15. run-14/checkpoint-1599/rng_state.pth +3 -0
  16. run-14/checkpoint-1599/scheduler.pt +3 -0
  17. run-14/checkpoint-1599/special_tokens_map.json +37 -0
  18. run-14/checkpoint-1599/tokenizer_config.json +57 -0
  19. run-14/checkpoint-1599/trainer_state.json +71 -0
  20. run-14/checkpoint-1599/training_args.bin +3 -0
  21. run-14/checkpoint-1599/vocab.txt +0 -0
  22. run-16/checkpoint-267/config.json +43 -0
  23. run-16/checkpoint-267/model.safetensors +3 -0
  24. run-16/checkpoint-267/optimizer.pt +3 -0
  25. run-16/checkpoint-267/rng_state.pth +3 -0
  26. run-16/checkpoint-267/scheduler.pt +3 -0
  27. run-16/checkpoint-267/special_tokens_map.json +37 -0
  28. run-16/checkpoint-267/tokenizer_config.json +57 -0
  29. run-16/checkpoint-267/trainer_state.json +32 -0
  30. run-16/checkpoint-267/training_args.bin +3 -0
  31. run-16/checkpoint-267/vocab.txt +0 -0
  32. runs/Apr19_07-31-51_21d31c708e60/events.out.tfevents.1713514323.21d31c708e60.946.15 +3 -0
  33. runs/Apr19_07-31-51_21d31c708e60/events.out.tfevents.1713514355.21d31c708e60.946.16 +3 -0
  34. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a945d947e49e86e546787bb669f7b65c020565b63a4511277f9d6d829957c53
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:971a3ddf817b712dc07195c844772ef5d1ec4a8fd2faa3cfc511b714130228d0
3
  size 409103316
run-14/checkpoint-1066/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-14/checkpoint-1066/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0094f0a22b4c9ecd644f33fbecfe823d15c136fde4ad9b6a65250b64860a3beb
3
+ size 409103316
run-14/checkpoint-1066/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d121830061544b84438906af551765beebb55d80e0ca284b9cf8b975d0a28db
3
+ size 818327802
run-14/checkpoint-1066/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0352b822625e2caff966cf4803bcca008efc803cc8cf64d84f0455237f54c298
3
+ size 14244
run-14/checkpoint-1066/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ebbddc18eb83142cfebf87505d82bf5563814469a45cb0c0cbb3b98be493e95
3
+ size 1064
run-14/checkpoint-1066/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-14/checkpoint-1066/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-14/checkpoint-1066/trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.603524923324585,
3
+ "best_model_checkpoint": "BERT-WMM/run-14/checkpoint-533",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1066,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.94,
13
+ "grad_norm": 11.3766508102417,
14
+ "learning_rate": 1.0605888092670128e-05,
15
+ "loss": 0.7117,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7568075117370892,
21
+ "eval_loss": 0.603524923324585,
22
+ "eval_runtime": 2.4291,
23
+ "eval_samples_per_second": 876.864,
24
+ "eval_steps_per_second": 55.164,
25
+ "step": 533
26
+ },
27
+ {
28
+ "epoch": 1.88,
29
+ "grad_norm": 19.02298927307129,
30
+ "learning_rate": 5.780643282538131e-06,
31
+ "loss": 0.4384,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.7492957746478873,
37
+ "eval_loss": 0.6247430443763733,
38
+ "eval_runtime": 2.4634,
39
+ "eval_samples_per_second": 864.644,
40
+ "eval_steps_per_second": 54.395,
41
+ "step": 1066
42
+ }
43
+ ],
44
+ "logging_steps": 500,
45
+ "max_steps": 1599,
46
+ "num_input_tokens_seen": 0,
47
+ "num_train_epochs": 3,
48
+ "save_steps": 500,
49
+ "total_flos": 338261076519408.0,
50
+ "train_batch_size": 16,
51
+ "trial_name": null,
52
+ "trial_params": {
53
+ "per_device_train_batch_size": 16
54
+ }
55
+ }
run-14/checkpoint-1066/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebedef9b751bedd4e796367e1472df25f06ffc187165c1b123fac9f3e7ae22ec
3
+ size 4856
run-14/checkpoint-1066/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-14/checkpoint-1599/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-14/checkpoint-1599/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f332c41562365ee8d7593aa41af5a06d83316e2a7a222077608ecedeaf378706
3
+ size 409103316
run-14/checkpoint-1599/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c638e45453b2c280162964664b342bc92e1b627b7e528f06ffd0b9c8a69223f4
3
+ size 818327802
run-14/checkpoint-1599/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34c76749a5fca84e55dbd3027c6581d6a92ad331fccc0be7f9471b493c5f7556
3
+ size 14244
run-14/checkpoint-1599/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:094c8913743a33aabeabf57f90c4c18b7fac579cf3f31e2e70ee92e326470923
3
+ size 1064
run-14/checkpoint-1599/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-14/checkpoint-1599/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-14/checkpoint-1599/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.603524923324585,
3
+ "best_model_checkpoint": "BERT-WMM/run-14/checkpoint-533",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1599,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.94,
13
+ "grad_norm": 11.3766508102417,
14
+ "learning_rate": 1.0605888092670128e-05,
15
+ "loss": 0.7117,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7568075117370892,
21
+ "eval_loss": 0.603524923324585,
22
+ "eval_runtime": 2.4291,
23
+ "eval_samples_per_second": 876.864,
24
+ "eval_steps_per_second": 55.164,
25
+ "step": 533
26
+ },
27
+ {
28
+ "epoch": 1.88,
29
+ "grad_norm": 19.02298927307129,
30
+ "learning_rate": 5.780643282538131e-06,
31
+ "loss": 0.4384,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.7492957746478873,
37
+ "eval_loss": 0.6247430443763733,
38
+ "eval_runtime": 2.4634,
39
+ "eval_samples_per_second": 864.644,
40
+ "eval_steps_per_second": 54.395,
41
+ "step": 1066
42
+ },
43
+ {
44
+ "epoch": 2.81,
45
+ "grad_norm": 25.672210693359375,
46
+ "learning_rate": 9.553984724061353e-07,
47
+ "loss": 0.2896,
48
+ "step": 1500
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.7507042253521127,
53
+ "eval_loss": 0.7414140701293945,
54
+ "eval_runtime": 2.4641,
55
+ "eval_samples_per_second": 864.423,
56
+ "eval_steps_per_second": 54.382,
57
+ "step": 1599
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 1599,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 3,
64
+ "save_steps": 500,
65
+ "total_flos": 507646505902536.0,
66
+ "train_batch_size": 16,
67
+ "trial_name": null,
68
+ "trial_params": {
69
+ "per_device_train_batch_size": 16
70
+ }
71
+ }
run-14/checkpoint-1599/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebedef9b751bedd4e796367e1472df25f06ffc187165c1b123fac9f3e7ae22ec
3
+ size 4856
run-14/checkpoint-1599/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-16/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-16/checkpoint-267/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:971a3ddf817b712dc07195c844772ef5d1ec4a8fd2faa3cfc511b714130228d0
3
+ size 409103316
run-16/checkpoint-267/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc8b54fc5e8c9423b8eb78032472c72dce9ff03db39846d1622f31a3d6911c46
3
+ size 818327802
run-16/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-16/checkpoint-267/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d605219d0cdfe1356d19dfc261c4f045664dbc44ddf04517d0b2ebd1dab264c7
3
+ size 1064
run-16/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-16/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-16/checkpoint-267/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6019130349159241,
3
+ "best_model_checkpoint": "BERT-WMM/run-16/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": 0.7563380281690141,
14
+ "eval_loss": 0.6019130349159241,
15
+ "eval_runtime": 2.4518,
16
+ "eval_samples_per_second": 868.753,
17
+ "eval_steps_per_second": 54.654,
18
+ "step": 267
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 801,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 32,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "per_device_train_batch_size": 32
31
+ }
32
+ }
run-16/checkpoint-267/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
3
+ size 4856
run-16/checkpoint-267/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr19_07-31-51_21d31c708e60/events.out.tfevents.1713514323.21d31c708e60.946.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df3cd6e15de1b9b0570d2f75c595affb07ba3df85b38edb13c592854622ac692
3
+ size 5217
runs/Apr19_07-31-51_21d31c708e60/events.out.tfevents.1713514355.21d31c708e60.946.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1404239bacde950f2e19dc6dac53545d80abf0afd95887873034aac6e2143955
3
+ size 6428
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebedef9b751bedd4e796367e1472df25f06ffc187165c1b123fac9f3e7ae22ec
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
3
  size 4856