Hugging Face's logo

pellucid
/
my_awesome_opus100_model

Transformers
PyTorch
TensorBoard
longt5
text2text-generation
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
pellucid commited on
Commit
bb35a4f
·
1 Parent(s): 02eb769

Training in progress, step 500

Browse files
Files changed (14) hide show
  1. config.json +27 -38
  2. pytorch_model.bin +2 -2
  3. runs/Jun21_13-00-57_a1b30e893bc0/events.out.tfevents.1687352652.a1b30e893bc0.1769.0 +3 -0
  4. runs/Jun21_13-10-44_a1b30e893bc0/events.out.tfevents.1687353052.a1b30e893bc0.4132.0 +3 -0
  5. runs/Jun21_13-12-11_a1b30e893bc0/events.out.tfevents.1687353134.a1b30e893bc0.4132.1 +3 -0
  6. runs/Jun21_13-13-48_a1b30e893bc0/events.out.tfevents.1687353231.a1b30e893bc0.4132.2 +3 -0
  7. runs/Jun21_13-23-43_a1b30e893bc0/events.out.tfevents.1687353834.a1b30e893bc0.7458.0 +3 -0
  8. runs/Jun21_13-26-01_a1b30e893bc0/events.out.tfevents.1687353964.a1b30e893bc0.7458.1 +3 -0
  9. runs/Jun21_13-26-20_a1b30e893bc0/events.out.tfevents.1687353983.a1b30e893bc0.7458.2 +3 -0
  10. special_tokens_map.json +103 -0
  11. spiece.model +3 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +106 -5
  14. training_args.bin +1 -1
config.json CHANGED
@@ -1,46 +1,35 @@
1
  {
2
- "_name_or_path": "Helsinki-NLP/opus-mt-tc-big-en-ko",
3
- "activation_dropout": 0.0,
4
- "activation_function": "relu",
5
  "architectures": [
6
- "MarianMTModel"
7
  ],
8
- "attention_dropout": 0.0,
9
- "bad_words_ids": [
10
- [
11
- 32000
12
- ]
13
- ],
14
- "bos_token_id": 0,
15
- "classifier_dropout": 0.0,
16
- "d_model": 1024,
17
- "decoder_attention_heads": 16,
18
- "decoder_ffn_dim": 4096,
19
- "decoder_layerdrop": 0.0,
20
- "decoder_layers": 6,
21
- "decoder_start_token_id": 32000,
22
- "decoder_vocab_size": 32001,
23
- "dropout": 0.1,
24
- "encoder_attention_heads": 16,
25
- "encoder_ffn_dim": 4096,
26
- "encoder_layerdrop": 0.0,
27
- "encoder_layers": 6,
28
- "eos_token_id": 2,
29
- "forced_eos_token_id": 2,
30
- "init_std": 0.02,
31
  "is_encoder_decoder": true,
32
- "max_length": 512,
33
- "max_position_embeddings": 1024,
34
- "model_type": "marian",
35
- "normalize_embedding": false,
36
- "num_beams": 4,
37
- "num_hidden_layers": 6,
38
- "pad_token_id": 32000,
39
- "scale_embedding": true,
40
- "share_encoder_decoder_embeddings": true,
41
- "static_position_embeddings": true,
 
 
 
42
  "torch_dtype": "float32",
43
  "transformers_version": "4.30.2",
44
  "use_cache": true,
45
- "vocab_size": 32001
46
  }
 
1
  {
2
+ "_name_or_path": "KETI-AIR-Downstream/long-ke-t5-base-translation-aihub-en2ko",
 
 
3
  "architectures": [
4
+ "LongT5ForConditionalGeneration"
5
  ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "encoder_attention_type": "transient-global",
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "global_block_size": 16,
16
+ "initializer_factor": 1.0,
 
 
 
 
 
 
 
 
 
 
 
 
17
  "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "local_radius": 127,
21
+ "model_type": "longt5",
22
+ "n_positions": 4096,
23
+ "num_decoder_layers": 12,
24
+ "num_heads": 12,
25
+ "num_layers": 12,
26
+ "output_past": true,
27
+ "pad_token_id": 0,
28
+ "relative_attention_max_distance": 128,
29
+ "relative_attention_num_buckets": 32,
30
+ "tie_word_embeddings": false,
31
  "torch_dtype": "float32",
32
  "transformers_version": "4.30.2",
33
  "use_cache": true,
34
+ "vocab_size": 64100
35
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75ca911a5a86529a625e2096efa4619d801ef9b351a201da34594c138cba1c69
3
- size 836720133
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45bf7850572db8b6d30f67ef166ae4a161ef7e68957644f857ee14efcbca564e
3
+ size 1186888873
runs/Jun21_13-00-57_a1b30e893bc0/events.out.tfevents.1687352652.a1b30e893bc0.1769.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:defab7851a1989a1bfd608a0339444047786aa9363832e2fb8aa908929de62f0
3
+ size 4184
runs/Jun21_13-10-44_a1b30e893bc0/events.out.tfevents.1687353052.a1b30e893bc0.4132.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be9db7aedd97fb6fad5132f4d7bbb8fe9d34b49874cf6203bb347230725c834e
3
+ size 4476
runs/Jun21_13-12-11_a1b30e893bc0/events.out.tfevents.1687353134.a1b30e893bc0.4132.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4da74cf1d921a91eaf7772415df426ff0cfc107bc86da5e7221696bcb2692b46
3
+ size 4476
runs/Jun21_13-13-48_a1b30e893bc0/events.out.tfevents.1687353231.a1b30e893bc0.4132.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3db7b8f9cef5b706ac7fd31101d0964130207da42b76da931bd4ced277b146b3
3
+ size 4476
runs/Jun21_13-23-43_a1b30e893bc0/events.out.tfevents.1687353834.a1b30e893bc0.7458.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffa04b36d762c9c28169efb2bc6cad68be8ffd0cbbaba2d7b21e26c59d2d4256
3
+ size 4476
runs/Jun21_13-26-01_a1b30e893bc0/events.out.tfevents.1687353964.a1b30e893bc0.7458.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa68442ba17b9269e1f871c66a15f4418f60f8eeeef9c2f68f115c7323226a4
3
+ size 4476
runs/Jun21_13-26-20_a1b30e893bc0/events.out.tfevents.1687353983.a1b30e893bc0.7458.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:510b11b22c9e827d27d776f7b9365b0c698df0b6701b74c8be9f8e95672690b6
3
+ size 4631
special_tokens_map.json CHANGED
@@ -1,4 +1,107 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "eos_token": "</s>",
3
  "pad_token": "<pad>",
4
  "unk_token": "<unk>"
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "bos_token": "<s>",
105
  "eos_token": "</s>",
106
  "pad_token": "<pad>",
107
  "unk_token": "<unk>"
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8084f94443e97fa1305bf48cf532a7ced0631070f2f570c156bfa1b3c72913dd
3
+ size 1592561
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,12 +1,113 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "clean_up_tokenization_spaces": true,
3
  "eos_token": "</s>",
4
- "model_max_length": 512,
 
5
  "pad_token": "<pad>",
6
- "separate_vocabs": false,
7
- "source_lang": "en",
8
  "sp_model_kwargs": {},
9
- "target_lang": "ko",
10
- "tokenizer_class": "MarianTokenizer",
11
  "unk_token": "<unk>"
12
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "bos_token": "<s>",
105
  "clean_up_tokenization_spaces": true,
106
  "eos_token": "</s>",
107
+ "extra_ids": 100,
108
+ "model_max_length": 1000000000000000019884624838656,
109
  "pad_token": "<pad>",
 
 
110
  "sp_model_kwargs": {},
111
+ "tokenizer_class": "T5Tokenizer",
 
112
  "unk_token": "<unk>"
113
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62d7402a7fe5f41fe029ca3c2d0129d551a961f00e33f1578d3ad3336ee166b5
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76e9fe3e34c33aec178581ff3da83fd16cfa235ac9811aa46425c74027adafe0
3
  size 4091