finiteautomata
commited on
Commit
•
874e833
1
Parent(s):
7bd3b26
New model
Browse files- added_tokens.json +1 -0
- config.json +27 -0
- eval_results.json +9 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.json +9 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"emoji": 31005, "hashtag": 31004, "url": 31003, "@usuario": 31002}
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"output_past": true,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.10.0.dev0",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 31006
|
27 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.24,
|
3 |
+
"eval_loss": 0.8874114155769348,
|
4 |
+
"eval_runtime": 382.8478,
|
5 |
+
"eval_samples": 200000,
|
6 |
+
"eval_samples_per_second": 522.401,
|
7 |
+
"eval_steps_per_second": 4.083,
|
8 |
+
"perplexity": 2.428834264192218
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9936087dc2e9bde1731951c97cebfd3b483d018b1212c5a34ddc0774318f9dc
|
3 |
+
size 534989479
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "name_or_path": "/content/drive/MyDrive/models/beto-cased-ft", "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": "/home/jmperez/.cache/huggingface/transformers/9848a00af462c42dfb4ec88ef438fbab5256330f7f6f50badc48d277f9367d49.f982506b52498d4adb4bd491f593dc92b2ef6be61bfdbe9d30f53f963f9f5b66", "tokenizer_class": "BertTokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.24,
|
3 |
+
"total_flos": 3.370512610512077e+17,
|
4 |
+
"train_loss": 0.09681204452514648,
|
5 |
+
"train_runtime": 5680.8564,
|
6 |
+
"train_samples": 8369648,
|
7 |
+
"train_samples_per_second": 3605.09,
|
8 |
+
"train_steps_per_second": 1.76
|
9 |
+
}
|
vocab.txt
ADDED
File without changes
|