Initial commit from mrm8488
Browse files- config.json +42 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Jan03_20-28-55_a6b229e4fd6f/1641241860.181772/events.out.tfevents.1641241860.a6b229e4fd6f.127.1 +3 -0
- runs/Jan03_20-28-55_a6b229e4fd6f/events.out.tfevents.1641241860.a6b229e4fd6f.127.0 +3 -0
- runs/Jan03_21-01-39_a6b229e4fd6f/1641243701.7058358/events.out.tfevents.1641243701.a6b229e4fd6f.127.3 +3 -0
- runs/Jan03_21-01-39_a6b229e4fd6f/events.out.tfevents.1641243701.a6b229e4fd6f.127.2 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/drive/MyDrive/longormer-es-3/train/checkpoint-1000",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaLongForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"attention_window": [
|
8 |
+
512,
|
9 |
+
512,
|
10 |
+
512,
|
11 |
+
512,
|
12 |
+
512,
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512
|
20 |
+
],
|
21 |
+
"bos_token_id": 0,
|
22 |
+
"classifier_dropout": null,
|
23 |
+
"eos_token_id": 2,
|
24 |
+
"gradient_checkpointing": false,
|
25 |
+
"hidden_act": "gelu",
|
26 |
+
"hidden_dropout_prob": 0.1,
|
27 |
+
"hidden_size": 768,
|
28 |
+
"initializer_range": 0.02,
|
29 |
+
"intermediate_size": 3072,
|
30 |
+
"layer_norm_eps": 1e-05,
|
31 |
+
"max_position_embeddings": 4098,
|
32 |
+
"model_type": "roberta",
|
33 |
+
"num_attention_heads": 12,
|
34 |
+
"num_hidden_layers": 12,
|
35 |
+
"pad_token_id": 1,
|
36 |
+
"position_embedding_type": "absolute",
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.15.0",
|
39 |
+
"type_vocab_size": 1,
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 50265
|
42 |
+
}
|
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:b574efd034f9f24ea4275b129c0c24dab2720f86acd3114827829f63fa645489
|
3 |
+
size 594982427
|
runs/Jan03_20-28-55_a6b229e4fd6f/1641241860.181772/events.out.tfevents.1641241860.a6b229e4fd6f.127.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef8f8b5bd6c8c2bba8e9731f935a0879d41b9e4dc44bfa5ba091a22818dc7e62
|
3 |
+
size 4803
|
runs/Jan03_20-28-55_a6b229e4fd6f/events.out.tfevents.1641241860.a6b229e4fd6f.127.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46987d38767fa0ad7922821ad23cf80f57a52daf6a7b15182b2c5364fe13d343
|
3 |
+
size 3601
|
runs/Jan03_21-01-39_a6b229e4fd6f/1641243701.7058358/events.out.tfevents.1641243701.a6b229e4fd6f.127.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d5810ad7719510283ae73f4bb0da4bc625409e7e4d526a5cf9ff2331cc78112
|
3 |
+
size 4803
|
runs/Jan03_21-01-39_a6b229e4fd6f/events.out.tfevents.1641243701.a6b229e4fd6f.127.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e15d0b478ec86c0c57ab2adcf6a1ffbb6a7350f04aa00d8c9bb48a785d0ea68
|
3 |
+
size 3916
|
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.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "special_tokens_map_file": null, "name_or_path": "bertin-project/bertin-roberta-base-spanish", "tokenizer_class": "RobertaTokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|