iceman2434
commited on
Commit
•
39ee4fe
1
Parent(s):
340e484
Upload 8 files
Browse files- roberta-tagalog-base-ft-udpos213-top5langrandom/config.json +66 -0
- roberta-tagalog-base-ft-udpos213-top5langrandom/merges.txt +0 -0
- roberta-tagalog-base-ft-udpos213-top5langrandom/pytorch_model.bin +3 -0
- roberta-tagalog-base-ft-udpos213-top5langrandom/special_tokens_map.json +1 -0
- roberta-tagalog-base-ft-udpos213-top5langrandom/tokenizer.json +0 -0
- roberta-tagalog-base-ft-udpos213-top5langrandom/tokenizer_config.json +1 -0
- roberta-tagalog-base-ft-udpos213-top5langrandom/train.args +1 -0
- roberta-tagalog-base-ft-udpos213-top5langrandom/vocab.json +0 -0
roberta-tagalog-base-ft-udpos213-top5langrandom/config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "output\\jcblaise-roberta-tagalog-base_ft_udpos213-top5langrandom\\1d6ca3e8",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
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": "roberta",
|
57 |
+
"num_attention_heads": 12,
|
58 |
+
"num_hidden_layers": 12,
|
59 |
+
"pad_token_id": 1,
|
60 |
+
"position_embedding_type": "absolute",
|
61 |
+
"torch_dtype": "float32",
|
62 |
+
"transformers_version": "4.10.2",
|
63 |
+
"type_vocab_size": 1,
|
64 |
+
"use_cache": true,
|
65 |
+
"vocab_size": 30000
|
66 |
+
}
|
roberta-tagalog-base-ft-udpos213-top5langrandom/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
roberta-tagalog-base-ft-udpos213-top5langrandom/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd412d92b2098ccc8c846eed79dcd0a429382fc3a274ee38ea727dd02dda69fe
|
3 |
+
size 434102442
|
roberta-tagalog-base-ft-udpos213-top5langrandom/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
roberta-tagalog-base-ft-udpos213-top5langrandom/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
roberta-tagalog-base-ft-udpos213-top5langrandom/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": null, "name_or_path": "output\\jcblaise-roberta-tagalog-base_ft_udpos213-top5langrandom\\1d6ca3e8", "model_max_length": 512, "tokenizer_class": "RobertaTokenizer"}
|
roberta-tagalog-base-ft-udpos213-top5langrandom/train.args
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
udpos --learning_rate=5e-5 --eval_steps=1000 --per_device_batch_size=10 --max_steps=1000 --multi
|
roberta-tagalog-base-ft-udpos213-top5langrandom/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|