Alexis CarriΓ³n
commited on
Commit
β’
2e8434f
1
Parent(s):
f90f53b
commit from $USER
Browse files- added_tokens.json +13 -0
- confgAjuste.txt +10 -0
- config.json +28 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"AstraZeneca": 29003,
|
3 |
+
"COVID-19": 28997,
|
4 |
+
"COVID19": 28998,
|
5 |
+
"Pfizer": 29004,
|
6 |
+
"antibiotics": 29006,
|
7 |
+
"coronavirus": 29000,
|
8 |
+
"covid-19": 28996,
|
9 |
+
"quarantine": 29005,
|
10 |
+
"risk factors": 29001,
|
11 |
+
"sars-cov-2": 28999,
|
12 |
+
"vaccines": 29002
|
13 |
+
}
|
confgAjuste.txt
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
optim = AdamW(model.parameters(), lr=3e-5) #tasa de aprendizaje
|
2 |
+
# Se inicializa el cargador de datos para los datos de entrenamiento
|
3 |
+
train_loader = DataLoader(train_dataset, batch_size=24, shuffle=True)
|
4 |
+
|
5 |
+
for epoch in range(3):
|
6 |
+
|
7 |
+
|
8 |
+
Epoch 0: 100%|ββββββββββ| 83/83 [01:14<00:00, 1.12it/s, loss=2.14]
|
9 |
+
Epoch 1: 100%|ββββββββββ| 83/83 [01:14<00:00, 1.12it/s, loss=1.04]
|
10 |
+
Epoch 2: 100%|ββββββββββ| 83/83 [01:14<00:00, 1.12it/s, loss=0.68]
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "deepset/bert-base-cased-squad2",
|
3 |
+
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"language": "english",
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"name": "Bert",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.21.2",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 29007
|
28 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bab36da67a3bff0ab5693e7adcf39c11d308c019558cbe6cdbef4605770242f6
|
3 |
+
size 430989105
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"max_len": 512,
|
7 |
+
"name_or_path": "deepset/bert-base-cased-squad2",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": "/root/.cache/huggingface/transformers/5fa07cc35cf92053100af63a5b23424ba428c75dafc83de837f7c2bd5118a8b1.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|