Upload 7 files
Browse files- config.json +26 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +19 -0
- train_results.txt +3 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "result/my-unsup-simcse-mixup-temp0.05-lambda0.2-bert-large_seed42_stsb",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
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": 1024,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 4096,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 16,
|
17 |
+
"num_hidden_layers": 24,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"tokenizer_class": "BertJapaneseTokenizer",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.21.1",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 32768
|
26 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d199395d5ef092556c226bb2bd22af4e2b66e01d51cf6f2a3853d205a277609
|
3 |
+
size 1349895025
|
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_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"do_subword_tokenize": true,
|
5 |
+
"do_word_tokenize": true,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"mecab_kwargs": {
|
8 |
+
"mecab_dic": "unidic_lite"
|
9 |
+
},
|
10 |
+
"name_or_path": "cl-tohoku/bert-large-japanese",
|
11 |
+
"never_split": null,
|
12 |
+
"pad_token": "[PAD]",
|
13 |
+
"sep_token": "[SEP]",
|
14 |
+
"special_tokens_map_file": null,
|
15 |
+
"subword_tokenizer_type": "wordpiece",
|
16 |
+
"tokenizer_class": "BertJapaneseTokenizer",
|
17 |
+
"unk_token": "[UNK]",
|
18 |
+
"word_tokenizer_type": "mecab"
|
19 |
+
}
|
train_results.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
epoch = 1.0
|
2 |
+
train_runtime = 12654.7534
|
3 |
+
train_samples_per_second = 0.412
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec03b8f59527de828342033544d19cc7d04a5e993ba06f0da48f293841a51e54
|
3 |
+
size 3439
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|