Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +38 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ku-nlp/deberta-v2-base-japanese",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_head_size": 64,
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"conv_act": "gelu",
|
9 |
+
"conv_kernel_size": 3,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-07,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"max_relative_positions": -1,
|
18 |
+
"model_type": "deberta-v2",
|
19 |
+
"norm_rel_ebd": "layer_norm",
|
20 |
+
"num_attention_heads": 12,
|
21 |
+
"num_hidden_layers": 12,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"pooler_dropout": 0,
|
24 |
+
"pooler_hidden_act": "gelu",
|
25 |
+
"pooler_hidden_size": 768,
|
26 |
+
"pos_att_type": [
|
27 |
+
"p2c",
|
28 |
+
"c2p"
|
29 |
+
],
|
30 |
+
"position_biased_input": false,
|
31 |
+
"position_buckets": 256,
|
32 |
+
"relative_attention": true,
|
33 |
+
"share_att_key": true,
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.25.1",
|
36 |
+
"type_vocab_size": 0,
|
37 |
+
"vocab_size": 32000
|
38 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fd9d30a35607a5be786d0c62e8b0cbce1fefe1284c30b711b9dc8d803b081d6
|
3 |
+
size 449636195
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": "[UNK]"
|
9 |
+
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c111c16e2e52366dcac46b886e40650bb843fe2938a65f5970271fc5697a127
|
3 |
+
size 805061
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": false,
|
5 |
+
"eos_token": "[SEP]",
|
6 |
+
"keep_accents": true,
|
7 |
+
"mask_token": "[MASK]",
|
8 |
+
"model_max_length": 1000000000000000019884624838656,
|
9 |
+
"name_or_path": "ku-nlp/deberta-v2-base-japanese",
|
10 |
+
"pad_token": "[PAD]",
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"sp_model_kwargs": {},
|
13 |
+
"special_tokens_map_file": null,
|
14 |
+
"split_by_punct": false,
|
15 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
16 |
+
"unk_token": "[UNK]"
|
17 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55879faa80267a1a7f66617c07403127ebc62859d4123d8de52ab087e015959e
|
3 |
+
size 3439
|