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
5e14204
·
verified ·
1 Parent(s): 0366c45

Training in progress, epoch 3

Browse files
Files changed (22) hide show
  1. model.safetensors +1 -1
  2. run-3/checkpoint-534/config.json +43 -0
  3. run-3/checkpoint-534/model.safetensors +3 -0
  4. run-3/checkpoint-534/optimizer.pt +3 -0
  5. run-3/checkpoint-534/rng_state.pth +3 -0
  6. run-3/checkpoint-534/scheduler.pt +3 -0
  7. run-3/checkpoint-534/special_tokens_map.json +37 -0
  8. run-3/checkpoint-534/tokenizer_config.json +57 -0
  9. run-3/checkpoint-534/trainer_state.json +51 -0
  10. run-3/checkpoint-534/training_args.bin +3 -0
  11. run-3/checkpoint-534/vocab.txt +0 -0
  12. run-3/checkpoint-801/config.json +43 -0
  13. run-3/checkpoint-801/model.safetensors +3 -0
  14. run-3/checkpoint-801/optimizer.pt +3 -0
  15. run-3/checkpoint-801/rng_state.pth +3 -0
  16. run-3/checkpoint-801/scheduler.pt +3 -0
  17. run-3/checkpoint-801/special_tokens_map.json +37 -0
  18. run-3/checkpoint-801/tokenizer_config.json +57 -0
  19. run-3/checkpoint-801/trainer_state.json +60 -0
  20. run-3/checkpoint-801/training_args.bin +3 -0
  21. run-3/checkpoint-801/vocab.txt +0 -0
  22. runs/Apr18_08-35-19_da5e8340a418/events.out.tfevents.1713429603.da5e8340a418.15241.3 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba3f272ba28850e271d835a10c87730be852ab6db516e012cbc44531b94fa555
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05281ccfdb04657dc1f21097d3ad9814c9a9b02f644351f16dffed288040b382
3
  size 409103316
run-3/checkpoint-534/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-3/checkpoint-534/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22f8b5c2a4ec7c4ba90d6aff2ea3e383335216cad48a11aad9a4c34ba98ec717
3
+ size 409103316
run-3/checkpoint-534/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15515177657ad8b28551b140b8ba13ae9ced7b249f415715555788f0ae3458f
3
+ size 818327802
run-3/checkpoint-534/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc165f31ff0ffc674ac86349e2664c1e7bec0f07f3940fd4286bacf83dbab044
3
+ size 14244
run-3/checkpoint-534/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3db5ba154f6a7f69aebf98a2b4a4ac03660b2d28daa6f2a82bd1de57dd1df6d
3
+ size 1064
run-3/checkpoint-534/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-3/checkpoint-534/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-3/checkpoint-534/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6060042381286621,
3
+ "best_model_checkpoint": "BERT-WMM/run-3/checkpoint-534",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 534,
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": 0.7262910798122065,
14
+ "eval_loss": 0.6716192960739136,
15
+ "eval_runtime": 2.087,
16
+ "eval_samples_per_second": 1020.621,
17
+ "eval_steps_per_second": 64.208,
18
+ "step": 267
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "grad_norm": 8.963554382324219,
23
+ "learning_rate": 2.063992947537006e-05,
24
+ "loss": 0.5881,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.7652582159624414,
30
+ "eval_loss": 0.6060042381286621,
31
+ "eval_runtime": 2.1035,
32
+ "eval_samples_per_second": 1012.591,
33
+ "eval_steps_per_second": 63.703,
34
+ "step": 534
35
+ }
36
+ ],
37
+ "logging_steps": 500,
38
+ "max_steps": 1068,
39
+ "num_input_tokens_seen": 0,
40
+ "num_train_epochs": 4,
41
+ "save_steps": 500,
42
+ "total_flos": 349221394826640.0,
43
+ "train_batch_size": 32,
44
+ "trial_name": null,
45
+ "trial_params": {
46
+ "learning_rate": 3.8808881478336665e-05,
47
+ "num_train_epochs": 4,
48
+ "per_device_train_batch_size": 32,
49
+ "weight_decay": 1.7684940065509674e-05
50
+ }
51
+ }
run-3/checkpoint-534/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6332b6cec121d165520e5db70de2b1562eb8b726bb5c9d5f52be871bd32d17a
3
+ size 4856
run-3/checkpoint-534/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-801/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-3/checkpoint-801/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05281ccfdb04657dc1f21097d3ad9814c9a9b02f644351f16dffed288040b382
3
+ size 409103316
run-3/checkpoint-801/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27ea57bff0992ea25dfd5bf56db87bf04d8cd5bd28a538a99a2d7764f24c4a2d
3
+ size 818327802
run-3/checkpoint-801/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb690786753304d1db2cd6b182863e5aa8196fd7b3d7323f4e394214c3dc44f0
3
+ size 14244
run-3/checkpoint-801/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd3575a4ca08ff450ace7dcb5ea12993a659670863eefbcb00aa5df4d3ebd0c5
3
+ size 1064
run-3/checkpoint-801/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-3/checkpoint-801/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-3/checkpoint-801/trainer_state.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6060042381286621,
3
+ "best_model_checkpoint": "BERT-WMM/run-3/checkpoint-534",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 801,
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": 0.7262910798122065,
14
+ "eval_loss": 0.6716192960739136,
15
+ "eval_runtime": 2.087,
16
+ "eval_samples_per_second": 1020.621,
17
+ "eval_steps_per_second": 64.208,
18
+ "step": 267
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "grad_norm": 8.963554382324219,
23
+ "learning_rate": 2.063992947537006e-05,
24
+ "loss": 0.5881,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.7652582159624414,
30
+ "eval_loss": 0.6060042381286621,
31
+ "eval_runtime": 2.1035,
32
+ "eval_samples_per_second": 1012.591,
33
+ "eval_steps_per_second": 63.703,
34
+ "step": 534
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_accuracy": 0.7680751173708921,
39
+ "eval_loss": 0.7311103343963623,
40
+ "eval_runtime": 1.9991,
41
+ "eval_samples_per_second": 1065.459,
42
+ "eval_steps_per_second": 67.029,
43
+ "step": 801
44
+ }
45
+ ],
46
+ "logging_steps": 500,
47
+ "max_steps": 1068,
48
+ "num_input_tokens_seen": 0,
49
+ "num_train_epochs": 4,
50
+ "save_steps": 500,
51
+ "total_flos": 349221394826640.0,
52
+ "train_batch_size": 32,
53
+ "trial_name": null,
54
+ "trial_params": {
55
+ "learning_rate": 3.8808881478336665e-05,
56
+ "num_train_epochs": 4,
57
+ "per_device_train_batch_size": 32,
58
+ "weight_decay": 1.7684940065509674e-05
59
+ }
60
+ }
run-3/checkpoint-801/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6332b6cec121d165520e5db70de2b1562eb8b726bb5c9d5f52be871bd32d17a
3
+ size 4856
run-3/checkpoint-801/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr18_08-35-19_da5e8340a418/events.out.tfevents.1713429603.da5e8340a418.15241.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ff45af27ef0616ed33cd09989d42c7e8ba2b0ed167dd66f6cf63bd558e74cc7
3
- size 5769
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d3d8c4c74a29d090f59b7734cbc22828fe60300d25adf9ddbd633281e149a6f
3
+ size 6980