Mizuiro-sakura
commited on
Commit
•
5c07e02
1
Parent(s):
4f6dc72
Upload 10 files
Browse files- config.json +38 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +9 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- trainer_state.json +52 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ku-nlp/deberta-v2-base-japanese",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForMultipleChoice"
|
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": "4.24.0",
|
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:a9ab27b7995e8c83e72ef1b7f805e08850e639f7b955f4ee49c5832f4deccd8f
|
3 |
+
size 449630179
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:488b1ff0ce7300ebc232215fc1bec5d036940b119b0362387b0e5718eee4b268
|
3 |
+
size 13547
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eac87a4f2092caa77b0f78d1f505d6896579ea2218b5fcbbc566c4882a5104fd
|
3 |
+
size 623
|
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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"name_or_path": "ku-nlp/deberta-v2-base-japanese",
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"sp_model_kwargs": {},
|
12 |
+
"special_tokens_map_file": null,
|
13 |
+
"split_by_punct": false,
|
14 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.9964221824686943,
|
5 |
+
"global_step": 3350,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.45,
|
12 |
+
"learning_rate": 4.2546213476446036e-05,
|
13 |
+
"loss": 1.0003,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.89,
|
18 |
+
"learning_rate": 3.509242695289207e-05,
|
19 |
+
"loss": 0.8309,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.34,
|
24 |
+
"learning_rate": 2.7638640429338103e-05,
|
25 |
+
"loss": 0.4982,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 1.79,
|
30 |
+
"learning_rate": 2.018485390578414e-05,
|
31 |
+
"loss": 0.4074,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.24,
|
36 |
+
"learning_rate": 1.2731067382230174e-05,
|
37 |
+
"loss": 0.2627,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 2.68,
|
42 |
+
"learning_rate": 5.277280858676208e-06,
|
43 |
+
"loss": 0.169,
|
44 |
+
"step": 3000
|
45 |
+
}
|
46 |
+
],
|
47 |
+
"max_steps": 3354,
|
48 |
+
"num_train_epochs": 3,
|
49 |
+
"total_flos": 4496639672966400.0,
|
50 |
+
"trial_name": null,
|
51 |
+
"trial_params": null
|
52 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b72526e6f5f042c5b1f6d2e8ce7abe8ff724f67d924f53d6402ac194b7ec89bf
|
3 |
+
size 3439
|