Primera versión POS
Browse files- .gitattributes +2 -0
- config.json +63 -0
- eval_results.txt +6 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -6,3 +6,5 @@
|
|
6 |
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
8 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
6 |
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
8 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
9 |
+
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
10 |
+
optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ramonzaca/roberto",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "O",
|
15 |
+
"1": "ADJ",
|
16 |
+
"2": "ADP",
|
17 |
+
"3": "ADV",
|
18 |
+
"4": "AUX",
|
19 |
+
"5": "CCONJ",
|
20 |
+
"6": "DET",
|
21 |
+
"7": "INTJ",
|
22 |
+
"8": "NOUN",
|
23 |
+
"9": "NUM",
|
24 |
+
"10": "PART",
|
25 |
+
"11": "PRON",
|
26 |
+
"12": "PROPN",
|
27 |
+
"13": "PUNCT",
|
28 |
+
"14": "SCONJ",
|
29 |
+
"15": "SYM",
|
30 |
+
"16": "VERB"
|
31 |
+
},
|
32 |
+
"initializer_range": 0.02,
|
33 |
+
"intermediate_size": 3072,
|
34 |
+
"label2id": {
|
35 |
+
"ADJ": 1,
|
36 |
+
"ADP": 2,
|
37 |
+
"ADV": 3,
|
38 |
+
"AUX": 4,
|
39 |
+
"CCONJ": 5,
|
40 |
+
"DET": 6,
|
41 |
+
"INTJ": 7,
|
42 |
+
"NOUN": 8,
|
43 |
+
"NUM": 9,
|
44 |
+
"O": 0,
|
45 |
+
"PART": 10,
|
46 |
+
"PRON": 11,
|
47 |
+
"PROPN": 12,
|
48 |
+
"PUNCT": 13,
|
49 |
+
"SCONJ": 14,
|
50 |
+
"SYM": 15,
|
51 |
+
"VERB": 16
|
52 |
+
},
|
53 |
+
"layer_norm_eps": 1e-05,
|
54 |
+
"max_position_embeddings": 514,
|
55 |
+
"model_type": "roberta",
|
56 |
+
"num_attention_heads": 12,
|
57 |
+
"num_hidden_layers": 12,
|
58 |
+
"pad_token_id": 1,
|
59 |
+
"position_embedding_type": "absolute",
|
60 |
+
"type_vocab_size": 1,
|
61 |
+
"vocab_size": 52000,
|
62 |
+
"xla_device": true
|
63 |
+
}
|
eval_results.txt
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
eval_loss = 0.40307992696762085
|
2 |
+
eval_accuracy_score = 0.8636372275120209
|
3 |
+
eval_precision = 0.8474101534342499
|
4 |
+
eval_recall = 0.8280039442174955
|
5 |
+
eval_f1 = 0.8375946584154386
|
6 |
+
epoch = 10.0
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa15715a848bb83c4824cd78aa3e159d7c9da84f0ec38e6f4dd1708840a2c472
|
3 |
+
size 501690191
|
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_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "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": false, "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"}, "max_len": 512, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "ramonzaca/roberto", "tokenizer_file": null}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d1ead0c958ccbae3f733712df3d8910372a1b18c32052667ead94454e4fbaec
|
3 |
+
size 1839
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|