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
e186e92
·
verified ·
1 Parent(s): c036441

Training in progress, epoch 3

Browse files
Files changed (22) hide show
  1. model.safetensors +1 -1
  2. run-1/checkpoint-1066/config.json +43 -0
  3. run-1/checkpoint-1066/model.safetensors +3 -0
  4. run-1/checkpoint-1066/optimizer.pt +3 -0
  5. run-1/checkpoint-1066/rng_state.pth +3 -0
  6. run-1/checkpoint-1066/scheduler.pt +3 -0
  7. run-1/checkpoint-1066/special_tokens_map.json +37 -0
  8. run-1/checkpoint-1066/tokenizer_config.json +57 -0
  9. run-1/checkpoint-1066/trainer_state.json +55 -0
  10. run-1/checkpoint-1066/training_args.bin +3 -0
  11. run-1/checkpoint-1066/vocab.txt +0 -0
  12. run-1/checkpoint-1599/config.json +43 -0
  13. run-1/checkpoint-1599/model.safetensors +3 -0
  14. run-1/checkpoint-1599/optimizer.pt +3 -0
  15. run-1/checkpoint-1599/rng_state.pth +3 -0
  16. run-1/checkpoint-1599/scheduler.pt +3 -0
  17. run-1/checkpoint-1599/special_tokens_map.json +37 -0
  18. run-1/checkpoint-1599/tokenizer_config.json +57 -0
  19. run-1/checkpoint-1599/trainer_state.json +71 -0
  20. run-1/checkpoint-1599/training_args.bin +3 -0
  21. run-1/checkpoint-1599/vocab.txt +0 -0
  22. runs/Apr18_16-31-07_544fc269209b/events.out.tfevents.1713458029.544fc269209b.792.1 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d2ab9aa929add29843ba7a7b6daa14d441e741d52aac7ba2526c9b16ab2ae54
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e30af18b4b712a2743d94beaab28c03b2fda61bc9f9ba12362e144acb8dfd1e
3
  size 409103316
run-1/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-1/checkpoint-1066/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95402ab1ab2f0424ef5249bdf433211d442515db94c5e11f32ddba31f53be6d2
3
+ size 409103316
run-1/checkpoint-1066/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:930f022c2bcc533b71280180e69085e7cea10af3a5a1a6fd0beeacc2aca33fd6
3
+ size 818327802
run-1/checkpoint-1066/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e93670da55318d823f1e4c03808b51663a5b6c2853342674abb539144107925
3
+ size 14244
run-1/checkpoint-1066/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c06c195baf48e433db10c52687d4a4fb3fd1f70bf11af72abc605f447b5cf733
3
+ size 1064
run-1/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-1/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-1/checkpoint-1066/trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6096339821815491,
3
+ "best_model_checkpoint": "BERT-WMM/run-1/checkpoint-1066",
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": 13.094008445739746,
14
+ "learning_rate": 6.009687524192743e-06,
15
+ "loss": 0.7652,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7244131455399061,
21
+ "eval_loss": 0.6637173295021057,
22
+ "eval_runtime": 2.0459,
23
+ "eval_samples_per_second": 1041.116,
24
+ "eval_steps_per_second": 65.497,
25
+ "step": 533
26
+ },
27
+ {
28
+ "epoch": 1.88,
29
+ "grad_norm": 24.103755950927734,
30
+ "learning_rate": 3.27552577524245e-06,
31
+ "loss": 0.543,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.7615023474178404,
37
+ "eval_loss": 0.6096339821815491,
38
+ "eval_runtime": 2.2188,
39
+ "eval_samples_per_second": 959.966,
40
+ "eval_steps_per_second": 60.392,
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
+ "learning_rate": 8.743849273143035e-06
54
+ }
55
+ }
run-1/checkpoint-1066/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96acc0d6a278deedc1ad94c23c932749f68e8e22ce3768b8816b072f56729d43
3
+ size 4856
run-1/checkpoint-1066/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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-1/checkpoint-1599/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e30af18b4b712a2743d94beaab28c03b2fda61bc9f9ba12362e144acb8dfd1e
3
+ size 409103316
run-1/checkpoint-1599/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fcf6ad24b627f11c03774fe274a77e2d6b9a4110b392202322769b0db56db3d
3
+ size 818327802
run-1/checkpoint-1599/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a0297d8a44379421fcc37b5cd89b37859cf20f999ea1e0c6d33126202fb0483
3
+ size 14244
run-1/checkpoint-1599/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de9dce2cc2b6fc5378e32f56c70a091729f33d97ff52a9ca0eb310d1fc825f63
3
+ size 1064
run-1/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-1/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-1/checkpoint-1599/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6096339821815491,
3
+ "best_model_checkpoint": "BERT-WMM/run-1/checkpoint-1066",
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": 13.094008445739746,
14
+ "learning_rate": 6.009687524192743e-06,
15
+ "loss": 0.7652,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7244131455399061,
21
+ "eval_loss": 0.6637173295021057,
22
+ "eval_runtime": 2.0459,
23
+ "eval_samples_per_second": 1041.116,
24
+ "eval_steps_per_second": 65.497,
25
+ "step": 533
26
+ },
27
+ {
28
+ "epoch": 1.88,
29
+ "grad_norm": 24.103755950927734,
30
+ "learning_rate": 3.27552577524245e-06,
31
+ "loss": 0.543,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.7615023474178404,
37
+ "eval_loss": 0.6096339821815491,
38
+ "eval_runtime": 2.2188,
39
+ "eval_samples_per_second": 959.966,
40
+ "eval_steps_per_second": 60.392,
41
+ "step": 1066
42
+ },
43
+ {
44
+ "epoch": 2.81,
45
+ "grad_norm": 58.51288986206055,
46
+ "learning_rate": 5.413640262921578e-07,
47
+ "loss": 0.4444,
48
+ "step": 1500
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.7596244131455399,
53
+ "eval_loss": 0.6346573233604431,
54
+ "eval_runtime": 2.0157,
55
+ "eval_samples_per_second": 1056.709,
56
+ "eval_steps_per_second": 66.478,
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
+ "learning_rate": 8.743849273143035e-06
70
+ }
71
+ }
run-1/checkpoint-1599/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96acc0d6a278deedc1ad94c23c932749f68e8e22ce3768b8816b072f56729d43
3
+ size 4856
run-1/checkpoint-1599/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr18_16-31-07_544fc269209b/events.out.tfevents.1713458029.544fc269209b.792.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:990cd9437f35c91a731315d2cbc35e217cc206323e1a99c00d8ed757b11af8d9
3
- size 5427
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c865bf2f689f9dc7837d8cb1d8e7ca6c04705eb95590ff94fb4f779d69a76117
3
+ size 6849