Hugging Face's logo

KIT-RoboInfo
/
itou_b_20250109

Safetensors
bert
Model card Files Community
itou-kousuke021 commited on
Commit
25e67aa
·
1 Parent(s): 53ebf5d

Initial commit of fine-tuned model

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-100/config.json +47 -0
  2. checkpoint-100/model.safetensors +3 -0
  3. checkpoint-100/optimizer.pt +3 -0
  4. checkpoint-100/rng_state.pth +3 -0
  5. checkpoint-100/scheduler.pt +3 -0
  6. checkpoint-100/special_tokens_map.json +7 -0
  7. checkpoint-100/tokenizer_config.json +64 -0
  8. checkpoint-100/trainer_state.json +32 -0
  9. checkpoint-100/training_args.bin +3 -0
  10. checkpoint-100/vocab.txt +0 -0
  11. checkpoint-1000/config.json +47 -0
  12. checkpoint-1000/model.safetensors +3 -0
  13. checkpoint-1000/optimizer.pt +3 -0
  14. checkpoint-1000/rng_state.pth +3 -0
  15. checkpoint-1000/scheduler.pt +3 -0
  16. checkpoint-1000/special_tokens_map.json +7 -0
  17. checkpoint-1000/tokenizer_config.json +64 -0
  18. checkpoint-1000/trainer_state.json +47 -0
  19. checkpoint-1000/training_args.bin +3 -0
  20. checkpoint-1000/vocab.txt +0 -0
  21. checkpoint-1200/config.json +47 -0
  22. checkpoint-1200/model.safetensors +3 -0
  23. checkpoint-1200/optimizer.pt +3 -0
  24. checkpoint-1200/rng_state.pth +3 -0
  25. checkpoint-1200/scheduler.pt +3 -0
  26. checkpoint-1200/special_tokens_map.json +7 -0
  27. checkpoint-1200/tokenizer_config.json +64 -0
  28. checkpoint-1200/trainer_state.json +47 -0
  29. checkpoint-1200/training_args.bin +3 -0
  30. checkpoint-1200/vocab.txt +0 -0
  31. checkpoint-500/config.json +47 -0
  32. checkpoint-500/model.safetensors +3 -0
  33. checkpoint-500/optimizer.pt +3 -0
  34. checkpoint-500/rng_state.pth +3 -0
  35. checkpoint-500/scheduler.pt +3 -0
  36. checkpoint-500/special_tokens_map.json +7 -0
  37. checkpoint-500/tokenizer_config.json +64 -0
  38. checkpoint-500/trainer_state.json +40 -0
  39. checkpoint-500/training_args.bin +3 -0
  40. checkpoint-500/vocab.txt +0 -0
  41. checkpoint-75/config.json +47 -0
  42. checkpoint-75/model.safetensors +3 -0
  43. checkpoint-75/optimizer.pt +3 -0
  44. checkpoint-75/rng_state.pth +3 -0
  45. checkpoint-75/scheduler.pt +3 -0
  46. checkpoint-75/special_tokens_map.json +7 -0
  47. checkpoint-75/tokenizer_config.json +64 -0
  48. checkpoint-75/trainer_state.json +32 -0
  49. checkpoint-75/training_args.bin +3 -0
  50. checkpoint-75/vocab.txt +0 -0
checkpoint-100/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-100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceb853309edc8d2a5034db0e99cb3b0e1d29fd5b4b6b6f31134175d0d3a64fb3
3
+ size 442517340
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6be533913e75ff7bd4e7fb6e3ad54af3038caefde8956f2b2130791e22335214
3
+ size 885154362
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff8c58827d00a64816afe1f177dde7825b67d45deb2f884be0236869094cbf4
3
+ size 14244
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beccfaf9bab963f178f24d893fd68585ea073339edab1cdcc5698c989a1dd81e
3
+ size 1064
checkpoint-100/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-100/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-100/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
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": 100,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 4,
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": 836202538598400.0,
29
+ "train_batch_size": 32,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e073bb423ca3c7a925f3b63620fc8c4cdeb162b5242b3d43a23a66e0e2ee732
3
+ size 5304
checkpoint-100/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/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-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b25847c52a4cb35f2dc3c63e151af4ea40a0593611ca8a203b467ec3fc06c80e
3
+ size 442517340
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04624bbc71e6cdd276c0864ce270174bff8a5c09d48060b30b37c55eb8f4480a
3
+ size 885154362
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f8e61c6e4521371c10c309f0301e6714e45aaf2365669ddc0f5c50abb6680c1
3
+ size 14244
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09e1d146fa1811b6149157f0b84ed5e54fe5e0faf5ad56a1bbda57354ab4f6a8
3
+ size 1064
checkpoint-1000/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-1000/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-1000/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.5,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.25,
13
+ "grad_norm": 0.5698992013931274,
14
+ "learning_rate": 1.2173913043478263e-05,
15
+ "loss": 0.2027,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 2.5,
20
+ "grad_norm": 0.8053608536720276,
21
+ "learning_rate": 3.4782608695652175e-06,
22
+ "loss": 0.0731,
23
+ "step": 1000
24
+ }
25
+ ],
26
+ "logging_steps": 500,
27
+ "max_steps": 1200,
28
+ "num_input_tokens_seen": 0,
29
+ "num_train_epochs": 3,
30
+ "save_steps": 500,
31
+ "stateful_callbacks": {
32
+ "TrainerControl": {
33
+ "args": {
34
+ "should_epoch_stop": false,
35
+ "should_evaluate": false,
36
+ "should_log": false,
37
+ "should_save": true,
38
+ "should_training_stop": false
39
+ },
40
+ "attributes": {}
41
+ }
42
+ },
43
+ "total_flos": 522626586624000.0,
44
+ "train_batch_size": 2,
45
+ "trial_name": null,
46
+ "trial_params": null
47
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2a4ed7e5bedd6b0e0497f3bd37c67423068705a56fe53584376220f5215e05e
3
+ size 5304
checkpoint-1000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1200/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-1200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0929aa6b57c343e3d27531d8b0b8cec4455d5901ea451dd3bd456884541a257
3
+ size 442517340
checkpoint-1200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e5adaa48dea5e747d924a18a13d2109766b113712bf10df5f9fa68fc2272a0
3
+ size 885154362
checkpoint-1200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff3b215993bb305f3da021b49a5969a508fd46447812b7c80a2cf22ad32af4d
3
+ size 14244
checkpoint-1200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dbcd8bb7627ff20a690e1dcef58b9babd947ff44c1ea4785784740fa416a427
3
+ size 1064
checkpoint-1200/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-1200/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-1200/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.25,
13
+ "grad_norm": 0.5698992013931274,
14
+ "learning_rate": 1.2173913043478263e-05,
15
+ "loss": 0.2027,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 2.5,
20
+ "grad_norm": 0.8053608536720276,
21
+ "learning_rate": 3.4782608695652175e-06,
22
+ "loss": 0.0731,
23
+ "step": 1000
24
+ }
25
+ ],
26
+ "logging_steps": 500,
27
+ "max_steps": 1200,
28
+ "num_input_tokens_seen": 0,
29
+ "num_train_epochs": 3,
30
+ "save_steps": 500,
31
+ "stateful_callbacks": {
32
+ "TrainerControl": {
33
+ "args": {
34
+ "should_epoch_stop": false,
35
+ "should_evaluate": false,
36
+ "should_log": false,
37
+ "should_save": true,
38
+ "should_training_stop": true
39
+ },
40
+ "attributes": {}
41
+ }
42
+ },
43
+ "total_flos": 627151903948800.0,
44
+ "train_batch_size": 2,
45
+ "trial_name": null,
46
+ "trial_params": null
47
+ }
checkpoint-1200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2a4ed7e5bedd6b0e0497f3bd37c67423068705a56fe53584376220f5215e05e
3
+ size 5304
checkpoint-1200/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/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-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3eea84a49bc17b78494dde70428a80ef7ebe516cd7eb79ae3d68e0c25580188
3
+ size 442517340
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d683cddd426a28fd74dc231df42d530f73233d44c756d3f0e6442e804cdb592
3
+ size 885154362
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfe7e28914cf1759ae2d075a723f32809a485ad4b118cdc1ba3bf4f411ff3492
3
+ size 14244
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96aac63cbafeabe90e455718b58c392b5a1771a750af6acf49d636d38e47e57a
3
+ size 1064
checkpoint-500/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-500/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-500/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.25,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.25,
13
+ "grad_norm": 0.5698992013931274,
14
+ "learning_rate": 1.2173913043478263e-05,
15
+ "loss": 0.2027,
16
+ "step": 500
17
+ }
18
+ ],
19
+ "logging_steps": 500,
20
+ "max_steps": 1200,
21
+ "num_input_tokens_seen": 0,
22
+ "num_train_epochs": 3,
23
+ "save_steps": 500,
24
+ "stateful_callbacks": {
25
+ "TrainerControl": {
26
+ "args": {
27
+ "should_epoch_stop": false,
28
+ "should_evaluate": false,
29
+ "should_log": false,
30
+ "should_save": true,
31
+ "should_training_stop": false
32
+ },
33
+ "attributes": {}
34
+ }
35
+ },
36
+ "total_flos": 261313293312000.0,
37
+ "train_batch_size": 2,
38
+ "trial_name": null,
39
+ "trial_params": null
40
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2a4ed7e5bedd6b0e0497f3bd37c67423068705a56fe53584376220f5215e05e
3
+ size 5304
checkpoint-500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-75/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-75/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99bec2f7f62f01913e8b1871c0ab247e83d9c8bd23ef355c2772cd820d053aee
3
+ size 442517340
checkpoint-75/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1ffeab4b02dbe1c162d2c586bc73d16b35c19be723831004461af869d37d9c3
3
+ size 885154362
checkpoint-75/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6180bc217820e01c9ec907369a5c79179f9ead5fb8e05fbaecd18bec0a9a74b
3
+ size 14244
checkpoint-75/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f6003820aa1d9b0e6aa1d70309948568223b16abb8759408bc4ed8976518161
3
+ size 1064
checkpoint-75/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-75/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-75/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 75,
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": 75,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 3,
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": 627151903948800.0,
29
+ "train_batch_size": 32,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
checkpoint-75/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:636218e449c6c1b6590a5a29c69568a90f5a537e70e0dc34506869cc17649bb2
3
+ size 5304
checkpoint-75/vocab.txt ADDED
The diff for this file is too large to render. See raw diff