Mizuiro-sakura commited on
Commit
7b43b48
1 Parent(s): b7d26ca

Upload 11 files

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ entity_vocab.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<ent2>": 32771,
3
+ "<ent>": 32770
4
+ }
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "studio-ousia/luke-japanese-base",
3
+ "architectures": [
4
+ "LukeForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bert_model_name": "models/luke-japanese/hf_xlm_roberta",
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": null,
10
+ "cls_entity_prediction": false,
11
+ "entity_emb_size": 256,
12
+ "entity_vocab_size": 570505,
13
+ "eos_token_id": 2,
14
+ "hidden_act": "gelu",
15
+ "hidden_dropout_prob": 0.1,
16
+ "hidden_size": 768,
17
+ "id2label": {
18
+ "0": "LABEL_0",
19
+ "1": "LABEL_1",
20
+ "2": "LABEL_2"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1,
27
+ "LABEL_2": 2
28
+ },
29
+ "layer_norm_eps": 1e-05,
30
+ "max_position_embeddings": 514,
31
+ "model_type": "luke",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "pad_token_id": 1,
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.26.0",
39
+ "type_vocab_size": 1,
40
+ "use_cache": true,
41
+ "use_entity_aware_attention": true,
42
+ "vocab_size": 32772
43
+ }
entity_vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e067714dc43f11c0d14d84f760c16b87dbfd5225e463408c0baedec0c1aafd76
3
+ size 22254903
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6619af51c9c03a94887d5a17273a299852c7620b2c541d6bf360f7b9ba09567
3
+ size 1116561961
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc4b1664b32d6a2c89a7ffbcbef4540607493c7e5cc1c6c4fffafbce0a735bc2
3
+ size 13553
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:350993ba93565f86b9cbab9f456499a8d43a72dc299df1de11f87676dfdd2b40
3
+ size 627
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b73a5e054936c920cf5b7d1ec21ce9c281977078269963beb821c6c86fbff7
3
+ size 841889
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<ent>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<ent2>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<s>",
19
+ "cls_token": "<s>",
20
+ "eos_token": "</s>",
21
+ "mask_token": {
22
+ "content": "<mask>",
23
+ "lstrip": true,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "pad_token": "<pad>",
29
+ "sep_token": "</s>",
30
+ "unk_token": "<unk>"
31
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "__type": "AddedToken",
5
+ "content": "<ent>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ {
12
+ "__type": "AddedToken",
13
+ "content": "<ent2>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ {
20
+ "__type": "AddedToken",
21
+ "content": "<ent>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ {
28
+ "__type": "AddedToken",
29
+ "content": "<ent2>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ ],
36
+ "bos_token": "<s>",
37
+ "cls_token": "<s>",
38
+ "entity_mask2_token": "[MASK2]",
39
+ "entity_mask_token": "[MASK]",
40
+ "entity_pad_token": "[PAD]",
41
+ "entity_token_1": {
42
+ "__type": "AddedToken",
43
+ "content": "<ent>",
44
+ "lstrip": false,
45
+ "normalized": true,
46
+ "rstrip": false,
47
+ "single_word": false
48
+ },
49
+ "entity_token_2": {
50
+ "__type": "AddedToken",
51
+ "content": "<ent2>",
52
+ "lstrip": false,
53
+ "normalized": true,
54
+ "rstrip": false,
55
+ "single_word": false
56
+ },
57
+ "entity_unk_token": "[UNK]",
58
+ "eos_token": "</s>",
59
+ "mask_token": {
60
+ "__type": "AddedToken",
61
+ "content": "<mask>",
62
+ "lstrip": true,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ },
67
+ "max_entity_length": 32,
68
+ "max_mention_length": 30,
69
+ "model_max_length": 512,
70
+ "name_or_path": "studio-ousia/luke-japanese-base",
71
+ "pad_token": "<pad>",
72
+ "sep_token": "</s>",
73
+ "sp_model_kwargs": {},
74
+ "special_tokens_map_file": "models/luke-japanese/hf_xlm_roberta/special_tokens_map.json",
75
+ "task": null,
76
+ "tokenizer_class": "MLukeTokenizer",
77
+ "tokenizer_file": "models/luke-japanese/hf_luke_japanese_epoch20/tokenizer.json",
78
+ "unk_token": "<unk>"
79
+ }
trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 395,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_accuracy": 0.8114215283483976,
13
+ "eval_f1": 0.818616230475624,
14
+ "eval_loss": 0.4595734179019928,
15
+ "eval_precision": 0.8389816919950399,
16
+ "eval_recall": 0.8114215283483976,
17
+ "eval_runtime": 305.353,
18
+ "eval_samples_per_second": 7.971,
19
+ "eval_steps_per_second": 0.033,
20
+ "step": 79
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.8952341824157765,
25
+ "eval_f1": 0.8954913458940253,
26
+ "eval_loss": 0.28638511896133423,
27
+ "eval_precision": 0.8961827409877436,
28
+ "eval_recall": 0.8952341824157765,
29
+ "eval_runtime": 306.1964,
30
+ "eval_samples_per_second": 7.949,
31
+ "eval_steps_per_second": 0.033,
32
+ "step": 158
33
+ },
34
+ {
35
+ "epoch": 3.0,
36
+ "eval_accuracy": 0.8878389482333607,
37
+ "eval_f1": 0.8917239250068452,
38
+ "eval_loss": 0.2966187298297882,
39
+ "eval_precision": 0.8994920866634257,
40
+ "eval_recall": 0.8878389482333607,
41
+ "eval_runtime": 309.8999,
42
+ "eval_samples_per_second": 7.854,
43
+ "eval_steps_per_second": 0.032,
44
+ "step": 237
45
+ },
46
+ {
47
+ "epoch": 4.0,
48
+ "eval_accuracy": 0.8964667214461791,
49
+ "eval_f1": 0.8983882066368747,
50
+ "eval_loss": 0.2941748797893524,
51
+ "eval_precision": 0.9015125324656873,
52
+ "eval_recall": 0.8964667214461791,
53
+ "eval_runtime": 308.8193,
54
+ "eval_samples_per_second": 7.882,
55
+ "eval_steps_per_second": 0.032,
56
+ "step": 316
57
+ },
58
+ {
59
+ "epoch": 5.0,
60
+ "eval_accuracy": 0.8976992604765818,
61
+ "eval_f1": 0.8991780621741491,
62
+ "eval_loss": 0.3037779927253723,
63
+ "eval_precision": 0.9013216300304917,
64
+ "eval_recall": 0.8976992604765818,
65
+ "eval_runtime": 306.6866,
66
+ "eval_samples_per_second": 7.936,
67
+ "eval_steps_per_second": 0.033,
68
+ "step": 395
69
+ }
70
+ ],
71
+ "max_steps": 395,
72
+ "num_train_epochs": 5,
73
+ "total_flos": 8255946278073600.0,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec995683874c1b40d267b2c8d07633352c6f18789b65f422488271b94db557fe
3
+ size 3515