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
b793713
·
verified ·
1 Parent(s): e01d6ee

Training in progress, epoch 1

Browse files
Files changed (44) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-102/config.json +43 -0
  3. run-0/checkpoint-102/model.safetensors +3 -0
  4. run-0/checkpoint-102/optimizer.pt +3 -0
  5. run-0/checkpoint-102/rng_state.pth +3 -0
  6. run-0/checkpoint-102/scheduler.pt +3 -0
  7. run-0/checkpoint-102/special_tokens_map.json +37 -0
  8. run-0/checkpoint-102/tokenizer_config.json +57 -0
  9. run-0/checkpoint-102/trainer_state.json +53 -0
  10. run-0/checkpoint-102/training_args.bin +3 -0
  11. run-0/checkpoint-102/vocab.txt +0 -0
  12. run-0/checkpoint-136/config.json +43 -0
  13. run-0/checkpoint-136/model.safetensors +3 -0
  14. run-0/checkpoint-136/optimizer.pt +3 -0
  15. run-0/checkpoint-136/rng_state.pth +3 -0
  16. run-0/checkpoint-136/scheduler.pt +3 -0
  17. run-0/checkpoint-136/special_tokens_map.json +37 -0
  18. run-0/checkpoint-136/tokenizer_config.json +57 -0
  19. run-0/checkpoint-136/trainer_state.json +62 -0
  20. run-0/checkpoint-136/training_args.bin +3 -0
  21. run-0/checkpoint-136/vocab.txt +0 -0
  22. run-0/checkpoint-68/config.json +43 -0
  23. run-0/checkpoint-68/model.safetensors +3 -0
  24. run-0/checkpoint-68/optimizer.pt +3 -0
  25. run-0/checkpoint-68/rng_state.pth +3 -0
  26. run-0/checkpoint-68/scheduler.pt +3 -0
  27. run-0/checkpoint-68/special_tokens_map.json +37 -0
  28. run-0/checkpoint-68/tokenizer_config.json +57 -0
  29. run-0/checkpoint-68/trainer_state.json +44 -0
  30. run-0/checkpoint-68/training_args.bin +3 -0
  31. run-0/checkpoint-68/vocab.txt +0 -0
  32. run-1/checkpoint-267/config.json +43 -0
  33. run-1/checkpoint-267/model.safetensors +3 -0
  34. run-1/checkpoint-267/optimizer.pt +3 -0
  35. run-1/checkpoint-267/rng_state.pth +3 -0
  36. run-1/checkpoint-267/scheduler.pt +3 -0
  37. run-1/checkpoint-267/special_tokens_map.json +37 -0
  38. run-1/checkpoint-267/tokenizer_config.json +57 -0
  39. run-1/checkpoint-267/trainer_state.json +35 -0
  40. run-1/checkpoint-267/training_args.bin +3 -0
  41. run-1/checkpoint-267/vocab.txt +0 -0
  42. runs/Apr18_08-35-19_da5e8340a418/events.out.tfevents.1713429321.da5e8340a418.15241.0 +2 -2
  43. runs/Apr18_08-35-19_da5e8340a418/events.out.tfevents.1713429448.da5e8340a418.15241.1 +3 -0
  44. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f41389548935b1e2cf65361b04495cf53e596adb7a9d5abde9be5c3e6ef04678
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92a6aeb9a30f73ce24a05888adf4487978b37f6c80a54204f8182c74cc1058c8
3
  size 409103316
run-0/checkpoint-102/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-0/checkpoint-102/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:879a803debfdcbf7dc69e84c7458a82c315d8ef433482b35c6cc3802280293d8
3
+ size 409103316
run-0/checkpoint-102/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c24b77bd43edcc9513371b84323d85c019232d4f501a80092a3d53dd3bd2f24
3
+ size 818327802
run-0/checkpoint-102/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4985d3d8099710e4d513bd6b5092cdc6ef06be1b7ebf7230a3442b3ea8934631
3
+ size 14244
run-0/checkpoint-102/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97141c3bea5cc02d0b388e633ea1121d4fae73ae0b3c0ea2230043a2429ab111
3
+ size 1064
run-0/checkpoint-102/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-0/checkpoint-102/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-0/checkpoint-102/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9778991937637329,
3
+ "best_model_checkpoint": "BERT-WMM/run-0/checkpoint-102",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 102,
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": 0.4572769953051643,
14
+ "eval_loss": 1.057793140411377,
15
+ "eval_runtime": 2.1526,
16
+ "eval_samples_per_second": 989.489,
17
+ "eval_steps_per_second": 62.25,
18
+ "step": 34
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.535680751173709,
23
+ "eval_loss": 0.9990364909172058,
24
+ "eval_runtime": 2.1045,
25
+ "eval_samples_per_second": 1012.106,
26
+ "eval_steps_per_second": 63.672,
27
+ "step": 68
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.5384976525821596,
32
+ "eval_loss": 0.9778991937637329,
33
+ "eval_runtime": 2.072,
34
+ "eval_samples_per_second": 1028.013,
35
+ "eval_steps_per_second": 64.673,
36
+ "step": 102
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 136,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 4,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 256,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 1.3245164890212277e-06,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 256,
51
+ "weight_decay": 3.536833872428622e-05
52
+ }
53
+ }
run-0/checkpoint-102/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0608c1059d788e034d271975d72fd13e4c51749f92b6a8bac6127d68ca536f7f
3
+ size 4856
run-0/checkpoint-102/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-136/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-0/checkpoint-136/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4747919908ab82191b631a370f17ff7c66abe89c5685a56cfb1dcf0f4ee1e4f
3
+ size 409103316
run-0/checkpoint-136/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d1a6fd2f2151b53b514785886fc30dc2ae03627cc1ab509c558dd4915c9be07
3
+ size 818327802
run-0/checkpoint-136/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b3d344575888f9e5f2710d22393a16b4dea21022f75f02ece60e1a22ca2b3a3
3
+ size 14244
run-0/checkpoint-136/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6b3173f9718496fb28ff7e71dce68223792260db6e190258ab8c5b8713a15ce
3
+ size 1064
run-0/checkpoint-136/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-0/checkpoint-136/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-0/checkpoint-136/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9739134907722473,
3
+ "best_model_checkpoint": "BERT-WMM/run-0/checkpoint-136",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 136,
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": 0.4572769953051643,
14
+ "eval_loss": 1.057793140411377,
15
+ "eval_runtime": 2.1526,
16
+ "eval_samples_per_second": 989.489,
17
+ "eval_steps_per_second": 62.25,
18
+ "step": 34
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.535680751173709,
23
+ "eval_loss": 0.9990364909172058,
24
+ "eval_runtime": 2.1045,
25
+ "eval_samples_per_second": 1012.106,
26
+ "eval_steps_per_second": 63.672,
27
+ "step": 68
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.5384976525821596,
32
+ "eval_loss": 0.9778991937637329,
33
+ "eval_runtime": 2.072,
34
+ "eval_samples_per_second": 1028.013,
35
+ "eval_steps_per_second": 64.673,
36
+ "step": 102
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_accuracy": 0.5413145539906103,
41
+ "eval_loss": 0.9739134907722473,
42
+ "eval_runtime": 2.9432,
43
+ "eval_samples_per_second": 723.71,
44
+ "eval_steps_per_second": 45.529,
45
+ "step": 136
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 136,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 4,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 256,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 1.3245164890212277e-06,
58
+ "num_train_epochs": 4,
59
+ "per_device_train_batch_size": 256,
60
+ "weight_decay": 3.536833872428622e-05
61
+ }
62
+ }
run-0/checkpoint-136/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0608c1059d788e034d271975d72fd13e4c51749f92b6a8bac6127d68ca536f7f
3
+ size 4856
run-0/checkpoint-136/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-68/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-0/checkpoint-68/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adc897bdd03421570d2d7acae2cf41dd44de2afd4f5c7b8aff7df5ec1a203fe0
3
+ size 409103316
run-0/checkpoint-68/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b958a030e1e891922eb3612f046e3a611de07866bb84728821077fca636db2f
3
+ size 818327802
run-0/checkpoint-68/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9eceba03aec53c56e4e84551a3c4df5d382d62d120b30345074d8d435cf85c5
3
+ size 14244
run-0/checkpoint-68/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972d7b7d908b2d5cb5c9b5b4417638f6c5acc4dd482194948d652c83d406e805
3
+ size 1064
run-0/checkpoint-68/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-0/checkpoint-68/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-0/checkpoint-68/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9990364909172058,
3
+ "best_model_checkpoint": "BERT-WMM/run-0/checkpoint-68",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 68,
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": 0.4572769953051643,
14
+ "eval_loss": 1.057793140411377,
15
+ "eval_runtime": 2.1526,
16
+ "eval_samples_per_second": 989.489,
17
+ "eval_steps_per_second": 62.25,
18
+ "step": 34
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.535680751173709,
23
+ "eval_loss": 0.9990364909172058,
24
+ "eval_runtime": 2.1045,
25
+ "eval_samples_per_second": 1012.106,
26
+ "eval_steps_per_second": 63.672,
27
+ "step": 68
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 136,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 256,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 1.3245164890212277e-06,
40
+ "num_train_epochs": 4,
41
+ "per_device_train_batch_size": 256,
42
+ "weight_decay": 3.536833872428622e-05
43
+ }
44
+ }
run-0/checkpoint-68/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0608c1059d788e034d271975d72fd13e4c51749f92b6a8bac6127d68ca536f7f
3
+ size 4856
run-0/checkpoint-68/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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-1/checkpoint-267/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92a6aeb9a30f73ce24a05888adf4487978b37f6c80a54204f8182c74cc1058c8
3
+ size 409103316
run-1/checkpoint-267/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afad6cb08ab18686a7d95a9d44eddc76a676fea1e828bcf79ac259f7d48b67d0
3
+ size 818327802
run-1/checkpoint-267/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:123e89548a83b33069b1dc6f7e79d621eac970b4e99c56bc48c19b6733a7f692
3
+ size 14244
run-1/checkpoint-267/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5af2257da28264dc49f53431d24fa6ff424d40aefe39a89c65cfa19983234f82
3
+ size 1064
run-1/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-1/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-1/checkpoint-267/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6613610982894897,
3
+ "best_model_checkpoint": "BERT-WMM/run-1/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": 0.7253521126760564,
14
+ "eval_loss": 0.6613610982894897,
15
+ "eval_runtime": 2.0934,
16
+ "eval_samples_per_second": 1017.498,
17
+ "eval_steps_per_second": 64.012,
18
+ "step": 267
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 267,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 1,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 32,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 8.498240026043864e-05,
31
+ "num_train_epochs": 1,
32
+ "per_device_train_batch_size": 32,
33
+ "weight_decay": 0.0005460680272968455
34
+ }
35
+ }
run-1/checkpoint-267/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9784c45e6719f61497978d8d02dce0ab8813a80db941f3be399c65fceda6292
3
+ size 4856
run-1/checkpoint-267/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.1713429321.da5e8340a418.15241.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16826b4f58f182242bdfb00cc438c2fc0e66916c7ce89638f183d8c4cd9f0b5b
3
- size 5229
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9809ca9cbd60e6076ec368702c523ca70c8129099a6ac4ce555ea5492a8c1300
3
+ size 6540
runs/Apr18_08-35-19_da5e8340a418/events.out.tfevents.1713429448.da5e8340a418.15241.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1d3d5150f317a923672454d84409a82c0f0b4ed0c580b1cf3f9817ffc331a6e
3
+ size 5587
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0608c1059d788e034d271975d72fd13e4c51749f92b6a8bac6127d68ca536f7f
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9784c45e6719f61497978d8d02dce0ab8813a80db941f3be399c65fceda6292
3
  size 4856