Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +62 -0
- pytorch_model.bin +3 -0
- runs/Feb21_17-36-04_c6c13abd3ea7/1677000981.65731/events.out.tfevents.1677000981.c6c13abd3ea7.2267.1 +3 -0
- runs/Feb21_17-36-04_c6c13abd3ea7/events.out.tfevents.1677000981.c6c13abd3ea7.2267.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dccuchile/distilbert-base-spanish-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForTokenClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "O",
|
| 13 |
+
"1": "B-celular",
|
| 14 |
+
"2": "I-celular",
|
| 15 |
+
"3": "B-correo",
|
| 16 |
+
"4": "I-correo",
|
| 17 |
+
"5": "B-curp",
|
| 18 |
+
"6": "I-curp",
|
| 19 |
+
"7": "B-direccion",
|
| 20 |
+
"8": "I-direccion",
|
| 21 |
+
"9": "B-nombre",
|
| 22 |
+
"10": "I-nombre",
|
| 23 |
+
"11": "B-referencia",
|
| 24 |
+
"12": "I-referencia",
|
| 25 |
+
"13": "B-rfc",
|
| 26 |
+
"14": "I-rfc",
|
| 27 |
+
"15": "B-telefono_fijo",
|
| 28 |
+
"16": "I-telefono_fijo"
|
| 29 |
+
},
|
| 30 |
+
"initializer_range": 0.02,
|
| 31 |
+
"label2id": {
|
| 32 |
+
"B-celular": 1,
|
| 33 |
+
"B-correo": 3,
|
| 34 |
+
"B-curp": 5,
|
| 35 |
+
"B-direccion": 7,
|
| 36 |
+
"B-nombre": 9,
|
| 37 |
+
"B-referencia": 11,
|
| 38 |
+
"B-rfc": 13,
|
| 39 |
+
"B-telefono_fijo": 15,
|
| 40 |
+
"I-celular": 2,
|
| 41 |
+
"I-correo": 4,
|
| 42 |
+
"I-curp": 6,
|
| 43 |
+
"I-direccion": 8,
|
| 44 |
+
"I-nombre": 10,
|
| 45 |
+
"I-referencia": 12,
|
| 46 |
+
"I-rfc": 14,
|
| 47 |
+
"I-telefono_fijo": 16,
|
| 48 |
+
"O": 0
|
| 49 |
+
},
|
| 50 |
+
"max_position_embeddings": 512,
|
| 51 |
+
"model_type": "distilbert",
|
| 52 |
+
"n_heads": 12,
|
| 53 |
+
"n_layers": 6,
|
| 54 |
+
"pad_token_id": 0,
|
| 55 |
+
"qa_dropout": 0.1,
|
| 56 |
+
"seq_classif_dropout": 0.2,
|
| 57 |
+
"sinusoidal_pos_embds": true,
|
| 58 |
+
"tie_weights_": true,
|
| 59 |
+
"torch_dtype": "float32",
|
| 60 |
+
"transformers_version": "4.26.1",
|
| 61 |
+
"vocab_size": 31002
|
| 62 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3c3f8da060d6862e98edcd9deec0124c120f28e326b86f6d71741b7f41f19c3
|
| 3 |
+
size 267013221
|
runs/Feb21_17-36-04_c6c13abd3ea7/1677000981.65731/events.out.tfevents.1677000981.c6c13abd3ea7.2267.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53eedbca17a6cd9f1d06273bd5e8b818ae856020e23395c5f4d0b47789f85dcd
|
| 3 |
+
size 5649
|
runs/Feb21_17-36-04_c6c13abd3ea7/events.out.tfevents.1677000981.c6c13abd3ea7.2267.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9100e5092a3cbac50723fcd4c2d1bc94f271d7d3b8200576a9346db6daabe711
|
| 3 |
+
size 4946
|
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": true,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 512,
|
| 7 |
+
"name_or_path": "dccuchile/distilbert-base-spanish-uncased",
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"special_tokens_map_file": null,
|
| 12 |
+
"strip_accents": false,
|
| 13 |
+
"tokenize_chinese_chars": true,
|
| 14 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:206005f06ba2ab1e5dba300ad172f1ae433faac8a4254bfd3d216ac7b2a1f9a5
|
| 3 |
+
size 3515
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|