Hugging Face's logo

pigeon01
/
sungju-finetuned-ko-to-en_ver2

Translation
Transformers
PyTorch
TensorBoard
m2m_100
text2text-generation
Generated from Trainer
Model card Files Metrics Community
1
pigeon01 commited on
Commit
7a40ce8
·
1 Parent(s): 7cedf03

Training in progress, epoch 1

Browse files
Files changed (22) hide show
  1. .gitignore +1 -0
  2. config.json +35 -0
  3. pytorch_model.bin +3 -0
  4. runs/Jun03_07-02-48_bd31fece64bd/1685776171.3980927/events.out.tfevents.1685776171.bd31fece64bd.168.1 +3 -0
  5. runs/Jun03_07-02-48_bd31fece64bd/events.out.tfevents.1685776162.bd31fece64bd.168.0 +3 -0
  6. runs/Jun03_07-10-44_bd31fece64bd/1685776250.5779/events.out.tfevents.1685776250.bd31fece64bd.168.3 +3 -0
  7. runs/Jun03_07-10-44_bd31fece64bd/1685776332.75175/events.out.tfevents.1685776332.bd31fece64bd.168.5 +3 -0
  8. runs/Jun03_07-10-44_bd31fece64bd/1685776406.9812376/events.out.tfevents.1685776406.bd31fece64bd.168.7 +3 -0
  9. runs/Jun03_07-10-44_bd31fece64bd/events.out.tfevents.1685776250.bd31fece64bd.168.2 +3 -0
  10. runs/Jun03_07-10-44_bd31fece64bd/events.out.tfevents.1685776332.bd31fece64bd.168.4 +3 -0
  11. runs/Jun03_07-10-44_bd31fece64bd/events.out.tfevents.1685776406.bd31fece64bd.168.6 +3 -0
  12. runs/Jun03_07-14-05_bd31fece64bd/1685776451.1795483/events.out.tfevents.1685776451.bd31fece64bd.168.9 +3 -0
  13. runs/Jun03_07-14-05_bd31fece64bd/events.out.tfevents.1685776451.bd31fece64bd.168.8 +3 -0
  14. runs/Jun03_07-19-26_bd31fece64bd/1685776773.1338637/events.out.tfevents.1685776773.bd31fece64bd.168.11 +3 -0
  15. runs/Jun03_07-19-26_bd31fece64bd/events.out.tfevents.1685776773.bd31fece64bd.168.10 +3 -0
  16. runs/Jun03_07-53-11_bd31fece64bd/1685781045.8641338/events.out.tfevents.1685781045.bd31fece64bd.168.13 +3 -0
  17. runs/Jun03_07-53-11_bd31fece64bd/events.out.tfevents.1685781033.bd31fece64bd.168.12 +3 -0
  18. sentencepiece.bpe.model +3 -0
  19. special_tokens_map.json +109 -0
  20. tokenizer_config.json +119 -0
  21. training_args.bin +3 -0
  22. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "alirezamsh/small100",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "M2M100ForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 0,
10
+ "d_model": 1024,
11
+ "decoder_attention_heads": 16,
12
+ "decoder_ffn_dim": 4096,
13
+ "decoder_layerdrop": 0.0,
14
+ "decoder_layers": 3,
15
+ "decoder_start_token_id": 2,
16
+ "dropout": 0.1,
17
+ "encoder_attention_heads": 16,
18
+ "encoder_ffn_dim": 4096,
19
+ "encoder_layerdrop": 0.0,
20
+ "encoder_layers": 12,
21
+ "eos_token_id": 2,
22
+ "init_std": 0.02,
23
+ "is_encoder_decoder": true,
24
+ "max_length": 256,
25
+ "max_position_embeddings": 1024,
26
+ "model_type": "m2m_100",
27
+ "num_beams": 5,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 1,
30
+ "scale_embedding": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.29.2",
33
+ "use_cache": true,
34
+ "vocab_size": 128112
35
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20c9d5f14af212b4b729a75d60c15b01757fb62b64620bd718f68c74e1e9e790
3
+ size 1339441057
runs/Jun03_07-02-48_bd31fece64bd/1685776171.3980927/events.out.tfevents.1685776171.bd31fece64bd.168.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa46f8034deec10191397cd70c57640659acc42fa29f628cd132f667af3822d8
3
+ size 6237
runs/Jun03_07-02-48_bd31fece64bd/events.out.tfevents.1685776162.bd31fece64bd.168.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9efc0199d98776ba708343d4c5c0071582566e75a2181d391e68d67faf7db748
3
+ size 4714
runs/Jun03_07-10-44_bd31fece64bd/1685776250.5779/events.out.tfevents.1685776250.bd31fece64bd.168.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8542b1cbbe28f3bdefeea37b5b52fb746551953f4594af7afc800e461e052362
3
+ size 6237
runs/Jun03_07-10-44_bd31fece64bd/1685776332.75175/events.out.tfevents.1685776332.bd31fece64bd.168.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0acb7a85922766874b33b3b2424f762c1063fd3112bac1651b551c3e6ac017d5
3
+ size 6237
runs/Jun03_07-10-44_bd31fece64bd/1685776406.9812376/events.out.tfevents.1685776406.bd31fece64bd.168.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:367590fa945532b7ceefd372b6594fb6b80c155b747a14dcd2c786ebdfcf422c
3
+ size 6237
runs/Jun03_07-10-44_bd31fece64bd/events.out.tfevents.1685776250.bd31fece64bd.168.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:163b7faa6fba31337ba54a2c391263ba9eb81796c03852bc1c8d76d6eb8fc0d6
3
+ size 4460
runs/Jun03_07-10-44_bd31fece64bd/events.out.tfevents.1685776332.bd31fece64bd.168.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821aafba9ad442daaeb3dbc566d92fa802a8685b17562d79b60d895c7508638d
3
+ size 4460
runs/Jun03_07-10-44_bd31fece64bd/events.out.tfevents.1685776406.bd31fece64bd.168.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c8de8fc09e331e6a865437c5b1b95dc733f0c243d3e9548b69bb8c4676cc1c1
3
+ size 4460
runs/Jun03_07-14-05_bd31fece64bd/1685776451.1795483/events.out.tfevents.1685776451.bd31fece64bd.168.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc709562a2cfe2af8d07ebc41d05a4171211b72df30841cdf1909e9278ce0c79
3
+ size 6237
runs/Jun03_07-14-05_bd31fece64bd/events.out.tfevents.1685776451.bd31fece64bd.168.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3c875b4ed2e07c2cabd9b21af49af5aa566780e4c55a88e2e9f31d5da68d098
3
+ size 4459
runs/Jun03_07-19-26_bd31fece64bd/1685776773.1338637/events.out.tfevents.1685776773.bd31fece64bd.168.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f6c631af59e6973085d43a61a48d59fcee801eeb8b9b38b9f1e20186395a554
3
+ size 6237
runs/Jun03_07-19-26_bd31fece64bd/events.out.tfevents.1685776773.bd31fece64bd.168.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1da7941155ae604baacd3c41bebb8aa4e8621be1b5263f7b05d1bebe6e638835
3
+ size 4458
runs/Jun03_07-53-11_bd31fece64bd/1685781045.8641338/events.out.tfevents.1685781045.bd31fece64bd.168.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d67720185cae00d6465154585702b7ecd77e603888fb48d1b4c9fb288cc819d
3
+ size 6237
runs/Jun03_07-53-11_bd31fece64bd/events.out.tfevents.1685781033.bd31fece64bd.168.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:624504b56e1ece538071cb8c90588a64c926811ed3f6ef63de3b0587ed846a4f
3
+ size 7510
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f7c76ed2a5e0822be39f0a4f95a55eb19c78f4593ce609e2edbc2aea4d380a
3
+ size 2423393
special_tokens_map.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "__af__",
4
+ "__am__",
5
+ "__ar__",
6
+ "__ast__",
7
+ "__az__",
8
+ "__ba__",
9
+ "__be__",
10
+ "__bg__",
11
+ "__bn__",
12
+ "__br__",
13
+ "__bs__",
14
+ "__ca__",
15
+ "__ceb__",
16
+ "__cs__",
17
+ "__cy__",
18
+ "__da__",
19
+ "__de__",
20
+ "__el__",
21
+ "__en__",
22
+ "__es__",
23
+ "__et__",
24
+ "__fa__",
25
+ "__ff__",
26
+ "__fi__",
27
+ "__fr__",
28
+ "__fy__",
29
+ "__ga__",
30
+ "__gd__",
31
+ "__gl__",
32
+ "__gu__",
33
+ "__ha__",
34
+ "__he__",
35
+ "__hi__",
36
+ "__hr__",
37
+ "__ht__",
38
+ "__hu__",
39
+ "__hy__",
40
+ "__id__",
41
+ "__ig__",
42
+ "__ilo__",
43
+ "__is__",
44
+ "__it__",
45
+ "__ja__",
46
+ "__jv__",
47
+ "__ka__",
48
+ "__kk__",
49
+ "__km__",
50
+ "__kn__",
51
+ "__ko__",
52
+ "__lb__",
53
+ "__lg__",
54
+ "__ln__",
55
+ "__lo__",
56
+ "__lt__",
57
+ "__lv__",
58
+ "__mg__",
59
+ "__mk__",
60
+ "__ml__",
61
+ "__mn__",
62
+ "__mr__",
63
+ "__ms__",
64
+ "__my__",
65
+ "__ne__",
66
+ "__nl__",
67
+ "__no__",
68
+ "__ns__",
69
+ "__oc__",
70
+ "__or__",
71
+ "__pa__",
72
+ "__pl__",
73
+ "__ps__",
74
+ "__pt__",
75
+ "__ro__",
76
+ "__ru__",
77
+ "__sd__",
78
+ "__si__",
79
+ "__sk__",
80
+ "__sl__",
81
+ "__so__",
82
+ "__sq__",
83
+ "__sr__",
84
+ "__ss__",
85
+ "__su__",
86
+ "__sv__",
87
+ "__sw__",
88
+ "__ta__",
89
+ "__th__",
90
+ "__tl__",
91
+ "__tn__",
92
+ "__tr__",
93
+ "__uk__",
94
+ "__ur__",
95
+ "__uz__",
96
+ "__vi__",
97
+ "__wo__",
98
+ "__xh__",
99
+ "__yi__",
100
+ "__yo__",
101
+ "__zh__",
102
+ "__zu__"
103
+ ],
104
+ "bos_token": "<s>",
105
+ "eos_token": "</s>",
106
+ "pad_token": "<pad>",
107
+ "sep_token": "</s>",
108
+ "unk_token": "<unk>"
109
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "__af__",
4
+ "__am__",
5
+ "__ar__",
6
+ "__ast__",
7
+ "__az__",
8
+ "__ba__",
9
+ "__be__",
10
+ "__bg__",
11
+ "__bn__",
12
+ "__br__",
13
+ "__bs__",
14
+ "__ca__",
15
+ "__ceb__",
16
+ "__cs__",
17
+ "__cy__",
18
+ "__da__",
19
+ "__de__",
20
+ "__el__",
21
+ "__en__",
22
+ "__es__",
23
+ "__et__",
24
+ "__fa__",
25
+ "__ff__",
26
+ "__fi__",
27
+ "__fr__",
28
+ "__fy__",
29
+ "__ga__",
30
+ "__gd__",
31
+ "__gl__",
32
+ "__gu__",
33
+ "__ha__",
34
+ "__he__",
35
+ "__hi__",
36
+ "__hr__",
37
+ "__ht__",
38
+ "__hu__",
39
+ "__hy__",
40
+ "__id__",
41
+ "__ig__",
42
+ "__ilo__",
43
+ "__is__",
44
+ "__it__",
45
+ "__ja__",
46
+ "__jv__",
47
+ "__ka__",
48
+ "__kk__",
49
+ "__km__",
50
+ "__kn__",
51
+ "__ko__",
52
+ "__lb__",
53
+ "__lg__",
54
+ "__ln__",
55
+ "__lo__",
56
+ "__lt__",
57
+ "__lv__",
58
+ "__mg__",
59
+ "__mk__",
60
+ "__ml__",
61
+ "__mn__",
62
+ "__mr__",
63
+ "__ms__",
64
+ "__my__",
65
+ "__ne__",
66
+ "__nl__",
67
+ "__no__",
68
+ "__ns__",
69
+ "__oc__",
70
+ "__or__",
71
+ "__pa__",
72
+ "__pl__",
73
+ "__ps__",
74
+ "__pt__",
75
+ "__ro__",
76
+ "__ru__",
77
+ "__sd__",
78
+ "__si__",
79
+ "__sk__",
80
+ "__sl__",
81
+ "__so__",
82
+ "__sq__",
83
+ "__sr__",
84
+ "__ss__",
85
+ "__su__",
86
+ "__sv__",
87
+ "__sw__",
88
+ "__ta__",
89
+ "__th__",
90
+ "__tl__",
91
+ "__tn__",
92
+ "__tr__",
93
+ "__uk__",
94
+ "__ur__",
95
+ "__uz__",
96
+ "__vi__",
97
+ "__wo__",
98
+ "__xh__",
99
+ "__yi__",
100
+ "__yo__",
101
+ "__zh__",
102
+ "__zu__"
103
+ ],
104
+ "bos_token": "<s>",
105
+ "clean_up_tokenization_spaces": true,
106
+ "eos_token": "</s>",
107
+ "language_codes": "m2m100",
108
+ "model_max_length": 1024,
109
+ "num_madeup_words": 8,
110
+ "pad_token": "<pad>",
111
+ "return_tensors": "pt",
112
+ "sep_token": "</s>",
113
+ "sp_model_kwargs": {},
114
+ "src_lang": "ko",
115
+ "tgt_lang": "en",
116
+ "tokenizer_class": "M2M100Tokenizer",
117
+ "tokenizer_file": null,
118
+ "unk_token": "<unk>"
119
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd8f3b16d4f001a35e5e469cfc96e401e3a1dca61999dbfbe9752dccbc0bd362
3
+ size 4091
vocab.json ADDED
The diff for this file is too large to render. See raw diff