iceman2434 commited on
Commit
bcb02e4
1 Parent(s): 5594145

Upload 6 files

Browse files
xlm-roberta-base-ft-udpos213-top4lang/config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "output\\xlm-roberta-base_ft_udpos213-top4lang\\1d6ca3e8",
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
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "ADJ",
16
+ "1": "ADP",
17
+ "2": "ADV",
18
+ "3": "AUX",
19
+ "4": "CCONJ",
20
+ "5": "DET",
21
+ "6": "INTJ",
22
+ "7": "NOUN",
23
+ "8": "NUM",
24
+ "9": "PART",
25
+ "10": "PRON",
26
+ "11": "PROPN",
27
+ "12": "PUNCT",
28
+ "13": "SCONJ",
29
+ "14": "SYM",
30
+ "15": "VERB",
31
+ "16": "X"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "ADJ": 0,
37
+ "ADP": 1,
38
+ "ADV": 2,
39
+ "AUX": 3,
40
+ "CCONJ": 4,
41
+ "DET": 5,
42
+ "INTJ": 6,
43
+ "NOUN": 7,
44
+ "NUM": 8,
45
+ "PART": 9,
46
+ "PRON": 10,
47
+ "PROPN": 11,
48
+ "PUNCT": 12,
49
+ "SCONJ": 13,
50
+ "SYM": 14,
51
+ "VERB": 15,
52
+ "X": 16
53
+ },
54
+ "layer_norm_eps": 1e-05,
55
+ "max_position_embeddings": 514,
56
+ "model_type": "xlm-roberta",
57
+ "num_attention_heads": 12,
58
+ "num_hidden_layers": 12,
59
+ "output_past": true,
60
+ "pad_token_id": 1,
61
+ "position_embedding_type": "absolute",
62
+ "torch_dtype": "float32",
63
+ "transformers_version": "4.10.2",
64
+ "type_vocab_size": 1,
65
+ "use_cache": true,
66
+ "vocab_size": 250002
67
+ }
xlm-roberta-base-ft-udpos213-top4lang/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dacfba1fc40b9e7ef4e7aff699a8bbd6e491f038d6556170fa457965646b0b2
3
+ size 1109948586
xlm-roberta-base-ft-udpos213-top4lang/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}}
xlm-roberta-base-ft-udpos213-top4lang/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
xlm-roberta-base-ft-udpos213-top4lang/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, "add_prefix_space": true, "special_tokens_map_file": null, "name_or_path": "output\\xlm-roberta-base_ft_udpos213-top4lang\\1d6ca3e8", "tokenizer_class": "XLMRobertaTokenizer"}
xlm-roberta-base-ft-udpos213-top4lang/train.args ADDED
@@ -0,0 +1 @@
 
 
1
+ udpos --learning_rate=5e-5 --eval_steps=1000 --per_device_batch_size=10 --max_steps=1000 --language_source=top4lang