Hugging Face's logo

KIT-RoboInfo
/
toshiki20250109

Safetensors
bert
Model card Files
xet
 Community
y-toshiki commited on
Commit
0f72913
·
1 Parent(s): ef8ed0e

Initial commit of fine-tuned model

Browse files
Files changed (16) hide show
  1. checkpoint-50/config.json +47 -0
  2. checkpoint-50/model.safetensors +3 -0
  3. checkpoint-50/optimizer.pt +3 -0
  4. checkpoint-50/rng_state.pth +3 -0
  5. checkpoint-50/scheduler.pt +3 -0
  6. checkpoint-50/special_tokens_map.json +7 -0
  7. checkpoint-50/tokenizer_config.json +64 -0
  8. checkpoint-50/trainer_state.json +32 -0
  9. checkpoint-50/training_args.bin +3 -0
  10. checkpoint-50/vocab.txt +0 -0
  11. config.json +47 -0
  12. model.safetensors +3 -0
  13. special_tokens_map.json +7 -0
  14. tokenizer_config.json +64 -0
  15. training_args.bin +3 -0
  16. vocab.txt +0 -0
checkpoint-50/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tohoku-nlp/bert-base-japanese-v3",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-POS",
14
+ "2": "I-POS",
15
+ "3": "B-PST",
16
+ "4": "I-PST",
17
+ "5": "B-NEG",
18
+ "6": "I-NEG",
19
+ "7": "B-NGT",
20
+ "8": "I-NGT"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "B-NEG": 5,
26
+ "B-NGT": 7,
27
+ "B-POS": 1,
28
+ "B-PST": 3,
29
+ "I-NEG": 6,
30
+ "I-NGT": 8,
31
+ "I-POS": 2,
32
+ "I-PST": 4,
33
+ "O": 0
34
+ },
35
+ "layer_norm_eps": 1e-12,
36
+ "max_position_embeddings": 512,
37
+ "model_type": "bert",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "pad_token_id": 0,
41
+ "position_embedding_type": "absolute",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.47.1",
44
+ "type_vocab_size": 2,
45
+ "use_cache": true,
46
+ "vocab_size": 32768
47
+ }
checkpoint-50/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:719800ce8928b8f08844b7ed016838ea492db731c486bc6e49f402441f7e5a7b
3
+ size 442517340
checkpoint-50/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3369b6f9b38e3d4269f081a5b7a8050cc7ebb397cb5b8c053d56f42039236575
3
+ size 885154362
checkpoint-50/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08bb6f8db28ca573a5c93ed95bff7954478c7692428f3cccc7cba36cec034b06
3
+ size 14244
checkpoint-50/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
3
+ size 1064
checkpoint-50/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-50/tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "do_subword_tokenize": true,
48
+ "do_word_tokenize": true,
49
+ "extra_special_tokens": {},
50
+ "jumanpp_kwargs": null,
51
+ "mask_token": "[MASK]",
52
+ "mecab_kwargs": {
53
+ "mecab_dic": "unidic_lite"
54
+ },
55
+ "model_max_length": 512,
56
+ "never_split": null,
57
+ "pad_token": "[PAD]",
58
+ "sep_token": "[SEP]",
59
+ "subword_tokenizer_type": "wordpiece",
60
+ "sudachi_kwargs": null,
61
+ "tokenizer_class": "BertJapaneseTokenizer",
62
+ "unk_token": "[UNK]",
63
+ "word_tokenizer_type": "mecab"
64
+ }
checkpoint-50/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 50,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 500,
12
+ "max_steps": 50,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 2,
15
+ "save_steps": 500,
16
+ "stateful_callbacks": {
17
+ "TrainerControl": {
18
+ "args": {
19
+ "should_epoch_stop": false,
20
+ "should_evaluate": false,
21
+ "should_log": false,
22
+ "should_save": true,
23
+ "should_training_stop": true
24
+ },
25
+ "attributes": {}
26
+ }
27
+ },
28
+ "total_flos": 418101269299200.0,
29
+ "train_batch_size": 32,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
checkpoint-50/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:183a16f639bac55868cf22bab9f5bebfebcd3ff5956352838cfb9a7d95fb7079
3
+ size 5304
checkpoint-50/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tohoku-nlp/bert-base-japanese-v3",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-POS",
14
+ "2": "I-POS",
15
+ "3": "B-PST",
16
+ "4": "I-PST",
17
+ "5": "B-NEG",
18
+ "6": "I-NEG",
19
+ "7": "B-NGT",
20
+ "8": "I-NGT"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "B-NEG": 5,
26
+ "B-NGT": 7,
27
+ "B-POS": 1,
28
+ "B-PST": 3,
29
+ "I-NEG": 6,
30
+ "I-NGT": 8,
31
+ "I-POS": 2,
32
+ "I-PST": 4,
33
+ "O": 0
34
+ },
35
+ "layer_norm_eps": 1e-12,
36
+ "max_position_embeddings": 512,
37
+ "model_type": "bert",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "pad_token_id": 0,
41
+ "position_embedding_type": "absolute",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.47.1",
44
+ "type_vocab_size": 2,
45
+ "use_cache": true,
46
+ "vocab_size": 32768
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:719800ce8928b8f08844b7ed016838ea492db731c486bc6e49f402441f7e5a7b
3
+ size 442517340
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "do_subword_tokenize": true,
48
+ "do_word_tokenize": true,
49
+ "extra_special_tokens": {},
50
+ "jumanpp_kwargs": null,
51
+ "mask_token": "[MASK]",
52
+ "mecab_kwargs": {
53
+ "mecab_dic": "unidic_lite"
54
+ },
55
+ "model_max_length": 512,
56
+ "never_split": null,
57
+ "pad_token": "[PAD]",
58
+ "sep_token": "[SEP]",
59
+ "subword_tokenizer_type": "wordpiece",
60
+ "sudachi_kwargs": null,
61
+ "tokenizer_class": "BertJapaneseTokenizer",
62
+ "unk_token": "[UNK]",
63
+ "word_tokenizer_type": "mecab"
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:183a16f639bac55868cf22bab9f5bebfebcd3ff5956352838cfb9a7d95fb7079
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff