dylanmengzhou commited on
Commit
9dd6c82
1 Parent(s): a97c84c

Training in progress, epoch 1

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "circulus/kobart-trans-en-ko-v2",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "author": "Heewon Jeon(madjakarta@gmail.com)",
12
+ "bos_token_id": 1,
13
+ "classif_dropout": 0.1,
14
+ "classifier_dropout": 0.1,
15
+ "d_model": 768,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 3072,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 6,
20
+ "decoder_start_token_id": 1,
21
+ "do_blenderbot_90_layernorm": false,
22
+ "dropout": 0.1,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 6,
27
+ "eos_token_id": 1,
28
+ "extra_pos_embeddings": 2,
29
+ "force_bos_token_to_be_generated": false,
30
+ "forced_eos_token_id": 1,
31
+ "gradient_checkpointing": false,
32
+ "id2label": {
33
+ "0": "NEGATIVE",
34
+ "1": "POSITIVE"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "kobart_version": 2.0,
39
+ "label2id": {
40
+ "NEGATIVE": 0,
41
+ "POSITIVE": 1
42
+ },
43
+ "max_position_embeddings": 1026,
44
+ "model_type": "bart",
45
+ "normalize_before": false,
46
+ "normalize_embedding": true,
47
+ "num_hidden_layers": 6,
48
+ "pad_token_id": 3,
49
+ "scale_embedding": false,
50
+ "static_position_embeddings": false,
51
+ "tokenizer_class": "PreTrainedTokenizerFast",
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.28.1",
54
+ "use_cache": true,
55
+ "vocab_size": 30000
56
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c59a321dea579443cde137e01505df0de46f662e986a8ac17f2e3551a9c0b1
3
+ size 495644701
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "</s>",
3
+ "eos_token": "</s>",
4
+ "mask_token": "<mask>",
5
+ "pad_token": "<pad>",
6
+ "unk_token": "<unk>"
7
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fbd99725ee0a3b95c01bd0713e56c65c9ed7bcdd10d8f658314f9d62533e9e7
3
+ size 1049462
tokenizer_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "model_max_length": 1000000000000000019884624838656,
4
+ "tokenizer_class": "PreTrainedTokenizerFast"
5
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:636bbb3d532f29c007cd5586ccc58760548419cec0b5690af53021c03f7ed56a
3
+ size 3771