yqelz commited on
Commit
ea80113
1 Parent(s): 06b765a

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./ckpt_roberta_nre/model_ayzfwn/epoch_5",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "B-LOC",
15
+ "1": "B-ORG",
16
+ "2": "B-PER",
17
+ "3": "I-LOC",
18
+ "4": "I-ORG",
19
+ "5": "I-PER",
20
+ "6": "O"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 4096,
24
+ "label2id": {
25
+ "B-LOC": 0,
26
+ "B-ORG": 1,
27
+ "B-PER": 2,
28
+ "I-LOC": 3,
29
+ "I-ORG": 4,
30
+ "I-PER": 5,
31
+ "O": 6
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 514,
35
+ "model_type": "xlm-roberta",
36
+ "num_attention_heads": 16,
37
+ "num_hidden_layers": 24,
38
+ "output_past": true,
39
+ "pad_token_id": 1,
40
+ "position_embedding_type": "absolute",
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.14.0",
43
+ "type_vocab_size": 1,
44
+ "use_cache": true,
45
+ "vocab_size": 250002
46
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28dacce37f34d23a6d19c24870b8b8feec7ac8c104b584fb02ec86b9fa8f9a3f
3
+ size 2235555441
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "./ckpt_roberta_nre/model_ayzfwn/epoch_5", "tokenizer_class": "XLMRobertaTokenizer"}
trainer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"dataset": "tner/wikiann", "dataset_split": "train", "dataset_name": "ru", "local_dataset": null, "model": "xlm-roberta-large", "crf": false, "max_length": 128, "epoch": 10, "batch_size": 16, "lr": 1e-05, "random_seed": 42, "gradient_accumulation_steps": 4, "weight_decay": 1e-07, "lr_warmup_step_ratio": 0.1, "max_grad_norm": 10}