jiiyy commited on
Commit
b1e4ec3
1 Parent(s): b3796c4

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kykim/funnel-kor-base",
3
+ "activation_dropout": 0.0,
4
+ "architectures": [
5
+ "FunnelForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "attention_type": "relative_shift",
9
+ "block_repeats": [
10
+ 1,
11
+ 1,
12
+ 1
13
+ ],
14
+ "block_sizes": [
15
+ 6,
16
+ 6,
17
+ 6
18
+ ],
19
+ "d_head": 64,
20
+ "d_inner": 3072,
21
+ "d_model": 768,
22
+ "embedding_size": 768,
23
+ "hidden_act": "gelu_new",
24
+ "hidden_dropout": 0.1,
25
+ "initializer_range": 0.1,
26
+ "initializer_std": 0.02,
27
+ "layer_norm_eps": 1e-09,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "funnel",
30
+ "n_head": 12,
31
+ "num_decoder_layers": 2,
32
+ "pool_q_only": true,
33
+ "pooling_type": "mean",
34
+ "problem_type": "single_label_classification",
35
+ "rel_attn_type": "factorized",
36
+ "separate_cls": true,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.31.0",
39
+ "truncate_seq": true,
40
+ "type_vocab_size": 3,
41
+ "vocab_size": 42000
42
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c738df2702abc65648c579ceae82d3d85ea156610f12a053409dcca628492129
3
+ size 684539849
runs/Aug16_07-52-17_7b48932c89e9/events.out.tfevents.1692172343.7b48932c89e9.290.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8d0a246429b0995ab286a1c9c1932d1bd9c1f877a305f996b62f949ed78dc05
3
+ size 7358
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<cls>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "<sep>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_text": true,
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<cls>",
6
+ "do_basic_tokenize": true,
7
+ "do_lower_case": true,
8
+ "eos_token": "</s>",
9
+ "mask_token": "<mask>",
10
+ "model_max_length": 512,
11
+ "never_split": null,
12
+ "pad_token": "<pad>",
13
+ "sep_token": "<sep>",
14
+ "strip_accents": false,
15
+ "tokenize_chinese_chars": true,
16
+ "tokenizer_class": "FunnelTokenizer",
17
+ "unk_token": "<unk>",
18
+ "wordpieces_prefix": "##"
19
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e5f425d37631022076b4a41c333fbc8529b0ba63c62495765ba34fd3c9799e4
3
+ size 3963
vocab.txt ADDED
The diff for this file is too large to render. See raw diff