Mizuiro-sakura
commited on
Commit
•
8f89b85
1
Parent(s):
da59f0f
Upload 11 files
Browse files- .gitattributes +1 -0
- added_tokens.json +4 -0
- config.json +70 -0
- entity_vocab.json +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +31 -0
- tokenizer_config.json +79 -0
- trainer_state.json +70 -0
- training_args.bin +3 -0
.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 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "studio-ousia/luke-japanese-base",
|
3 |
+
"architectures": [
|
4 |
+
"LukeForTokenClassification"
|
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": "O",
|
19 |
+
"1": "B-\u305d\u306e\u4ed6\u306e\u7d44\u7e54\u540d",
|
20 |
+
"2": "I-\u305d\u306e\u4ed6\u306e\u7d44\u7e54\u540d",
|
21 |
+
"3": "B-\u6cd5\u4eba\u540d",
|
22 |
+
"4": "I-\u6cd5\u4eba\u540d",
|
23 |
+
"5": "B-\u5730\u540d",
|
24 |
+
"6": "I-\u5730\u540d",
|
25 |
+
"7": "B-\u4eba\u540d",
|
26 |
+
"8": "I-\u4eba\u540d",
|
27 |
+
"9": "B-\u65bd\u8a2d\u540d",
|
28 |
+
"10": "I-\u65bd\u8a2d\u540d",
|
29 |
+
"11": "B-\u30a4\u30d9\u30f3\u30c8\u540d",
|
30 |
+
"12": "I-\u30a4\u30d9\u30f3\u30c8\u540d",
|
31 |
+
"13": "B-\u653f\u6cbb\u7684\u7d44\u7e54\u540d",
|
32 |
+
"14": "I-\u653f\u6cbb\u7684\u7d44\u7e54\u540d",
|
33 |
+
"15": "B-\u88fd\u54c1\u540d",
|
34 |
+
"16": "I-\u88fd\u54c1\u540d"
|
35 |
+
},
|
36 |
+
"initializer_range": 0.02,
|
37 |
+
"intermediate_size": 3072,
|
38 |
+
"label2id": {
|
39 |
+
"B-\u305d\u306e\u4ed6\u306e\u7d44\u7e54\u540d": 1,
|
40 |
+
"B-\u30a4\u30d9\u30f3\u30c8\u540d": 11,
|
41 |
+
"B-\u4eba\u540d": 7,
|
42 |
+
"B-\u5730\u540d": 5,
|
43 |
+
"B-\u653f\u6cbb\u7684\u7d44\u7e54\u540d": 13,
|
44 |
+
"B-\u65bd\u8a2d\u540d": 9,
|
45 |
+
"B-\u6cd5\u4eba\u540d": 3,
|
46 |
+
"B-\u88fd\u54c1\u540d": 15,
|
47 |
+
"I-\u305d\u306e\u4ed6\u306e\u7d44\u7e54\u540d": 2,
|
48 |
+
"I-\u30a4\u30d9\u30f3\u30c8\u540d": 12,
|
49 |
+
"I-\u4eba\u540d": 8,
|
50 |
+
"I-\u5730\u540d": 6,
|
51 |
+
"I-\u653f\u6cbb\u7684\u7d44\u7e54\u540d": 14,
|
52 |
+
"I-\u65bd\u8a2d\u540d": 10,
|
53 |
+
"I-\u6cd5\u4eba\u540d": 4,
|
54 |
+
"I-\u88fd\u54c1\u540d": 16,
|
55 |
+
"O": 0
|
56 |
+
},
|
57 |
+
"layer_norm_eps": 1e-05,
|
58 |
+
"max_position_embeddings": 514,
|
59 |
+
"model_type": "luke",
|
60 |
+
"num_attention_heads": 12,
|
61 |
+
"num_hidden_layers": 12,
|
62 |
+
"pad_token_id": 1,
|
63 |
+
"position_embedding_type": "absolute",
|
64 |
+
"torch_dtype": "float32",
|
65 |
+
"transformers_version": "4.24.0",
|
66 |
+
"type_vocab_size": 1,
|
67 |
+
"use_cache": true,
|
68 |
+
"use_entity_aware_attention": true,
|
69 |
+
"vocab_size": 32772
|
70 |
+
}
|
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:a9b07a4cd15015bef48face04fc7daf505b5fddad969a3984a62853f57425f00
|
3 |
+
size 1114239767
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:081c2b01a5f3bceabac08d0e4815b1f8beb8d765f013f387c075a0c4ba91585f
|
3 |
+
size 13547
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98550081a88b52162b64702eb8442daf011bee40fb84b06e8ad57b708e39b359
|
3 |
+
size 623
|
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 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.82905982905983,
|
5 |
+
"global_step": 4600,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.07,
|
12 |
+
"learning_rate": 4.95260663507109e-05,
|
13 |
+
"loss": 0.2546,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 2.14,
|
18 |
+
"learning_rate": 4.3601895734597157e-05,
|
19 |
+
"loss": 0.0295,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 3.21,
|
24 |
+
"learning_rate": 3.767772511848342e-05,
|
25 |
+
"loss": 0.017,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 4.27,
|
30 |
+
"learning_rate": 3.175355450236967e-05,
|
31 |
+
"loss": 0.0107,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 5.34,
|
36 |
+
"learning_rate": 2.5829383886255927e-05,
|
37 |
+
"loss": 0.007,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 6.41,
|
42 |
+
"learning_rate": 1.990521327014218e-05,
|
43 |
+
"loss": 0.005,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 7.48,
|
48 |
+
"learning_rate": 1.3981042654028437e-05,
|
49 |
+
"loss": 0.0033,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 8.55,
|
54 |
+
"learning_rate": 8.056872037914693e-06,
|
55 |
+
"loss": 0.0026,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 9.62,
|
60 |
+
"learning_rate": 2.1327014218009483e-06,
|
61 |
+
"loss": 0.0018,
|
62 |
+
"step": 4500
|
63 |
+
}
|
64 |
+
],
|
65 |
+
"max_steps": 4680,
|
66 |
+
"num_train_epochs": 10,
|
67 |
+
"total_flos": 6017085844864512.0,
|
68 |
+
"trial_name": null,
|
69 |
+
"trial_params": null
|
70 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97d1dba5b6b9e1eb7545ec264f3a7c4a433724c78a9450e7487bd27db7d1bad7
|
3 |
+
size 3375
|