Mizuiro-sakura commited on
Commit
f40ef21
1 Parent(s): 76576c2

Upload 11 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<ent2>": 32771,
3
+ "<ent>": 32770
4
+ }
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "studio-ousia/luke-japanese-base-lite",
3
+ "architectures": [
4
+ "LukeForQuestionAnswering"
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": 4,
13
+ "eos_token_id": 2,
14
+ "hidden_act": "gelu",
15
+ "hidden_dropout_prob": 0.1,
16
+ "hidden_size": 768,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-05,
20
+ "max_position_embeddings": 514,
21
+ "model_type": "luke",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 1,
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.24.0",
28
+ "type_vocab_size": 1,
29
+ "use_cache": true,
30
+ "use_entity_aware_attention": true,
31
+ "vocab_size": 32772
32
+ }
entity_vocab.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "[MASK2]": 3,
3
+ "[MASK]": 0,
4
+ "[PAD]": 2,
5
+ "[UNK]": 1
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7edf78f024cc72a62e7a8e92036b2a845f61063f72c0b0251b24e4dd83ac9928
3
+ size 530000599
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5c301b643f5b62e64f34c00291aa9f34fe6ffb1aa2918ce8fa90ea25a517a9b
3
+ size 13547
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27617c79b467bcfab635b9ce51cc47f24cc2d3ebeb0772c41bb63e5892c6103d
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-lite",
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_lite_epoch20/tokenizer.json",
78
+ "unk_token": "<unk>"
79
+ }
trainer_state.json ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.984126984126984,
5
+ "global_step": 9400,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.16,
12
+ "learning_rate": 5e-05,
13
+ "loss": 2.3401,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.32,
18
+ "learning_rate": 4.7206703910614525e-05,
19
+ "loss": 1.3787,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.48,
24
+ "learning_rate": 4.4413407821229054e-05,
25
+ "loss": 1.297,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.63,
30
+ "learning_rate": 4.1620111731843576e-05,
31
+ "loss": 1.218,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.79,
36
+ "learning_rate": 3.8826815642458106e-05,
37
+ "loss": 1.1163,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.95,
42
+ "learning_rate": 3.603351955307263e-05,
43
+ "loss": 1.0974,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.11,
48
+ "learning_rate": 3.324022346368715e-05,
49
+ "loss": 0.9195,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.27,
54
+ "learning_rate": 3.0446927374301676e-05,
55
+ "loss": 0.8382,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.43,
60
+ "learning_rate": 2.7653631284916205e-05,
61
+ "loss": 0.8836,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.59,
66
+ "learning_rate": 2.4860335195530728e-05,
67
+ "loss": 0.8712,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.75,
72
+ "learning_rate": 2.206703910614525e-05,
73
+ "loss": 0.8452,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.9,
78
+ "learning_rate": 1.9273743016759776e-05,
79
+ "loss": 0.8412,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 2.06,
84
+ "learning_rate": 1.64804469273743e-05,
85
+ "loss": 0.7541,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 2.22,
90
+ "learning_rate": 1.3687150837988827e-05,
91
+ "loss": 0.631,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 2.38,
96
+ "learning_rate": 1.0893854748603351e-05,
97
+ "loss": 0.6282,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 2.54,
102
+ "learning_rate": 8.100558659217877e-06,
103
+ "loss": 0.6039,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 2.7,
108
+ "learning_rate": 5.307262569832402e-06,
109
+ "loss": 0.6112,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 2.86,
114
+ "learning_rate": 2.5139664804469276e-06,
115
+ "loss": 0.5946,
116
+ "step": 9000
117
+ }
118
+ ],
119
+ "max_steps": 9450,
120
+ "num_train_epochs": 3,
121
+ "total_flos": 5953096748635776.0,
122
+ "trial_name": null,
123
+ "trial_params": null
124
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2bffb9cafa2ca8d4f5328a2c6468f6778b3df24f7de50913085dc112039665a
3
+ size 3439