Hugging Face's logo

KIT-RoboInfo
/
2025-1-9

Safetensors
bert
Model card Files Community
Kojihaji commited on
Commit
fd73bf6
·
1 Parent(s): 3109a9e

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-120/config.json +47 -0
  12. checkpoint-120/model.safetensors +3 -0
  13. checkpoint-120/optimizer.pt +3 -0
  14. checkpoint-120/rng_state.pth +3 -0
  15. checkpoint-120/scheduler.pt +3 -0
  16. checkpoint-120/special_tokens_map.json +7 -0
  17. checkpoint-120/tokenizer_config.json +64 -0
  18. checkpoint-120/trainer_state.json +32 -0
  19. checkpoint-120/training_args.bin +3 -0
  20. checkpoint-120/vocab.txt +0 -0
  21. checkpoint-125/config.json +47 -0
  22. checkpoint-125/model.safetensors +3 -0
  23. checkpoint-125/optimizer.pt +3 -0
  24. checkpoint-125/rng_state.pth +3 -0
  25. checkpoint-125/scheduler.pt +3 -0
  26. checkpoint-125/special_tokens_map.json +7 -0
  27. checkpoint-125/tokenizer_config.json +64 -0
  28. checkpoint-125/trainer_state.json +32 -0
  29. checkpoint-125/training_args.bin +3 -0
  30. checkpoint-125/vocab.txt +0 -0
  31. checkpoint-150/config.json +47 -0
  32. checkpoint-150/model.safetensors +3 -0
  33. checkpoint-150/optimizer.pt +3 -0
  34. checkpoint-150/rng_state.pth +3 -0
  35. checkpoint-150/scheduler.pt +3 -0
  36. checkpoint-150/special_tokens_map.json +7 -0
  37. checkpoint-150/tokenizer_config.json +64 -0
  38. checkpoint-150/trainer_state.json +32 -0
  39. checkpoint-150/training_args.bin +3 -0
  40. checkpoint-150/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 sha256:129761083ddffffb6f54eb6c4fd32cecdf6135fa26df2de081aa4526bd763773
3
+ size 442517340
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e37c9466537726cbe97ba4ed83d0e80edabe515e8fdd4fc367ff2491720e7f9b
3
+ size 885154362
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d4fbae5728b236ead9efa777ac02f0cd5f9a482fbd7af877f16e21edee0af1c
3
+ size 14244
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dba5b1eceb58ed8e1d6e1125a30f45797ddcd98d1f22ce2c95178f34f64b52bf
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": 2.0,
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": 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": 16,
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:bc7b80aa4b6f2e8c5881fec65111e845dabaa4fc86f574fabc9e66b3844dbce0
3
+ size 5304
checkpoint-100/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-120/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-120/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db2dfbe00e6c833cea1c10e0f7c75c079df45f460608894b01ef7b29a16fbb4e
3
+ size 442517340
checkpoint-120/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a08fb0cd44838d8641686c1b6a521c75b0c9db2eb0fc3a37b49aa22052afe2f5
3
+ size 885154362
checkpoint-120/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9d8d36327877d1eeac1ba93c90091bb349231e444b1c6aedd915c1e0f247ca1
3
+ size 14244
checkpoint-120/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb11af3877a0b59a1c464201367ff885985a923815135df4e6ba9d60ad76251d
3
+ size 1064
checkpoint-120/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-120/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-120/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": 120,
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": 120,
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": 20,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
checkpoint-120/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd5af878e1aa9d1169dc567681c624725cd687a91884fe4a3f18c03f4caefe32
3
+ size 5304
checkpoint-120/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-125/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-125/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e4397b747879eb0735068688c6e590ad72bb9918cad643bdf6080abd80a3beb
3
+ size 442517340
checkpoint-125/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca5e4ead95137e58a4055ed3a6b91ef8e8e6d691ccafb8e48c41bdc730c157cf
3
+ size 885154362
checkpoint-125/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad162d6d3e88d3dde26779c526a81063a9845822df7bb3b4e083f32a33337e5
3
+ size 14244
checkpoint-125/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ad9db9086b13fa50ddb2493d487fa336135a6f7b0c46652bbb1ee1fa3931100
3
+ size 1064
checkpoint-125/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-125/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-125/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.5,
5
+ "eval_steps": 500,
6
+ "global_step": 125,
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": 125,
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": 522626586624000.0,
29
+ "train_batch_size": 16,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
checkpoint-125/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df9258bb37d60f88aae04cfd79693ced93c9121e0e7f2ece1f83c888c8053add
3
+ size 5304
checkpoint-125/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-150/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-150/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b24203259c5b864cf2f81cfcb3e83609dcbcd5ff8ddd9d39e705ed7535897812
3
+ size 442517340
checkpoint-150/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de7bdd241de5db0ec3c392c06770af717b14675ec49de2bb0c9d7a81c2efdd96
3
+ size 885154362
checkpoint-150/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8548694265ee5e939a5b2ca785bc04d6e726bc2d91f97380fde67703ed170e4
3
+ size 14244
checkpoint-150/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3b70ad0cd9144ba90ee64e944e2b60fd1ed7029d14b16795ae00ff3af0741cb
3
+ size 1064
checkpoint-150/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-150/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-150/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": 150,
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": 150,
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": 16,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
checkpoint-150/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cea3d3e3f7bddf59f0aa159172a5cab739ef5d8236c3531ebacde95f717a880a
3
+ size 5304
checkpoint-150/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:f2bdca57b44c3877e88a7e3f4dce78cd4246d9e5f0decfedb3d52460d6b0279b
3
+ size 442517340
checkpoint-75/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc1f1f60ede90233454f89753f9af10b120addd97586db91885b0ed2aa7d3c87
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:fafb9cb00ee266e132ca3b850775e86ed087b1dc9d488657147b40387dc5427f
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:d3d4469a315b70ecafd4256c29a7a03eab91318a29b74f4724e0143e669b65a7
3
+ size 5304
checkpoint-75/vocab.txt ADDED
The diff for this file is too large to render. See raw diff