Hugging Face's logo

DeskDown
/
MarianMix_en-ja-10

Text2Text Generation
Transformers
PyTorch
TensorBoard
marian
Inference Endpoints
Model card Files Metrics Community
1
DeskDown commited on
Commit
a452dce
•
1 Parent(s): 604657d

Training in progress, step 10000

Browse files
Files changed (28) hide show
  1. .gitignore +1 -0
  2. added_tokens.json +0 -0
  3. config.json +44 -0
  4. last-checkpoint/added_tokens.json +0 -0
  5. last-checkpoint/config.json +44 -0
  6. last-checkpoint/optimizer.pt +3 -0
  7. last-checkpoint/pytorch_model.bin +3 -0
  8. last-checkpoint/rng_state.pth +3 -0
  9. last-checkpoint/scaler.pt +3 -0
  10. last-checkpoint/scheduler.pt +3 -0
  11. last-checkpoint/source.spm +0 -0
  12. last-checkpoint/special_tokens_map.json +1 -0
  13. last-checkpoint/target.spm +0 -0
  14. last-checkpoint/tokenizer_config.json +1 -0
  15. last-checkpoint/trainer_state.json +146 -0
  16. last-checkpoint/training_args.bin +3 -0
  17. last-checkpoint/vocab.json +0 -0
  18. pytorch_model.bin +3 -0
  19. runs/Feb08_18-48-19_fadcca9c27d0/1644346113.367593/events.out.tfevents.1644346113.fadcca9c27d0.35.1 +3 -0
  20. runs/Feb08_18-48-19_fadcca9c27d0/events.out.tfevents.1644346113.fadcca9c27d0.35.0 +3 -0
  21. runs/Feb08_19-24-11_fadcca9c27d0/1644348258.4993296/events.out.tfevents.1644348258.fadcca9c27d0.35.3 +3 -0
  22. runs/Feb08_19-24-11_fadcca9c27d0/events.out.tfevents.1644348258.fadcca9c27d0.35.2 +3 -0
  23. source.spm +0 -0
  24. special_tokens_map.json +1 -0
  25. target.spm +0 -0
  26. tokenizer_config.json +1 -0
  27. training_args.bin +3 -0
  28. vocab.json +0 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-tatoeba-en-ja",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "swish",
5
+ "architectures": [
6
+ "MarianMTModel"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bad_words_ids": [
10
+ [
11
+ 65000
12
+ ]
13
+ ],
14
+ "bos_token_id": 0,
15
+ "classifier_dropout": 0.0,
16
+ "d_model": 512,
17
+ "decoder_attention_heads": 8,
18
+ "decoder_ffn_dim": 2048,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 6,
21
+ "decoder_start_token_id": 65000,
22
+ "dropout": 0.1,
23
+ "encoder_attention_heads": 8,
24
+ "encoder_ffn_dim": 2048,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 6,
27
+ "eos_token_id": 0,
28
+ "forced_eos_token_id": 0,
29
+ "init_std": 0.02,
30
+ "is_encoder_decoder": true,
31
+ "max_length": 512,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "marian",
34
+ "normalize_embedding": false,
35
+ "num_beams": 6,
36
+ "num_hidden_layers": 6,
37
+ "pad_token_id": 65000,
38
+ "scale_embedding": true,
39
+ "static_position_embeddings": true,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.12.5",
42
+ "use_cache": true,
43
+ "vocab_size": 97154
44
+ }
last-checkpoint/added_tokens.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-tatoeba-en-ja",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "swish",
5
+ "architectures": [
6
+ "MarianMTModel"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bad_words_ids": [
10
+ [
11
+ 65000
12
+ ]
13
+ ],
14
+ "bos_token_id": 0,
15
+ "classifier_dropout": 0.0,
16
+ "d_model": 512,
17
+ "decoder_attention_heads": 8,
18
+ "decoder_ffn_dim": 2048,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 6,
21
+ "decoder_start_token_id": 65000,
22
+ "dropout": 0.1,
23
+ "encoder_attention_heads": 8,
24
+ "encoder_ffn_dim": 2048,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 6,
27
+ "eos_token_id": 0,
28
+ "forced_eos_token_id": 0,
29
+ "init_std": 0.02,
30
+ "is_encoder_decoder": true,
31
+ "max_length": 512,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "marian",
34
+ "normalize_embedding": false,
35
+ "num_beams": 6,
36
+ "num_hidden_layers": 6,
37
+ "pad_token_id": 65000,
38
+ "scale_embedding": true,
39
+ "static_position_embeddings": true,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.12.5",
42
+ "use_cache": true,
43
+ "vocab_size": 97154
44
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc449c3c9aa977e62e8a253fc1964181c661fbd908462f8287ca14c67fa221d5
3
+ size 751197645
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c647d2e5ab98d23af56502a4839e2d950f16e5f58d356abdc346b70f550298af
3
+ size 376008389
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392a70bbd171fc077436dd500b1dfc29564709bf147ae66f4482dfc8047b6daf
3
+ size 14503
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5afed70c6b44287fbb97642baae95caed1fca70c0d2879628f6644dcd1c87ebf
3
+ size 559
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49ac74872413f57561e77e286f80f4be64cce2d235c693168b3f7d99462940fd
3
+ size 623
last-checkpoint/source.spm ADDED
Binary file (808 kB). View file
 
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
last-checkpoint/target.spm ADDED
Binary file (834 kB). View file
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"source_lang": "eng", "target_lang": "jpn", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "Helsinki-NLP/opus-tatoeba-en-ja", "tokenizer_class": "MarianTokenizer"}
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.7863522686673812,
5
+ "global_step": 10000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.09,
12
+ "learning_rate": 9.825589706933525e-05,
13
+ "loss": 2.1183,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.18,
18
+ "learning_rate": 9.646890636168693e-05,
19
+ "loss": 1.8604,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.27,
24
+ "learning_rate": 9.46819156540386e-05,
25
+ "loss": 1.7038,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.36,
30
+ "learning_rate": 9.289492494639028e-05,
31
+ "loss": 1.5787,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.45,
36
+ "learning_rate": 9.110793423874197e-05,
37
+ "loss": 1.4618,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.54,
42
+ "learning_rate": 8.932094353109363e-05,
43
+ "loss": 1.3833,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.63,
48
+ "learning_rate": 8.753395282344532e-05,
49
+ "loss": 1.3247,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.71,
54
+ "learning_rate": 8.5746962115797e-05,
55
+ "loss": 1.2699,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.8,
60
+ "learning_rate": 8.395997140814869e-05,
61
+ "loss": 1.2196,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.89,
66
+ "learning_rate": 8.217298070050035e-05,
67
+ "loss": 1.1743,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.98,
72
+ "learning_rate": 8.038598999285204e-05,
73
+ "loss": 1.1334,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.07,
78
+ "learning_rate": 7.859899928520372e-05,
79
+ "loss": 1.0688,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.16,
84
+ "learning_rate": 7.681200857755541e-05,
85
+ "loss": 1.0209,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.25,
90
+ "learning_rate": 7.502501786990707e-05,
91
+ "loss": 1.0123,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.34,
96
+ "learning_rate": 7.323802716225876e-05,
97
+ "loss": 0.9964,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.43,
102
+ "learning_rate": 7.145461043602574e-05,
103
+ "loss": 0.9671,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.52,
108
+ "learning_rate": 6.966761972837742e-05,
109
+ "loss": 0.9496,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.61,
114
+ "learning_rate": 6.788062902072909e-05,
115
+ "loss": 0.9354,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.7,
120
+ "learning_rate": 6.609363831308077e-05,
121
+ "loss": 0.9291,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.79,
126
+ "learning_rate": 6.430664760543246e-05,
127
+ "loss": 0.9039,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.79,
132
+ "eval_bleu": 4.2041,
133
+ "eval_gen_len": 43.7816,
134
+ "eval_loss": 0.9678672552108765,
135
+ "eval_runtime": 1428.8589,
136
+ "eval_samples_per_second": 6.25,
137
+ "eval_steps_per_second": 0.196,
138
+ "step": 10000
139
+ }
140
+ ],
141
+ "max_steps": 27990,
142
+ "num_train_epochs": 5,
143
+ "total_flos": 2.16932586356736e+16,
144
+ "trial_name": null,
145
+ "trial_params": null
146
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:788f94a24f9e0e59617584da9ecf7e726c3cbc0e93e03fa9a8b7ffebbb2ba793
3
+ size 2991
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c647d2e5ab98d23af56502a4839e2d950f16e5f58d356abdc346b70f550298af
3
+ size 376008389
runs/Feb08_18-48-19_fadcca9c27d0/1644346113.367593/events.out.tfevents.1644346113.fadcca9c27d0.35.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf9f14dcd24b9ee8df91b65a81d3f26f7d5d9075887d06c0dfd9dd1cbaa11664
3
+ size 4774
runs/Feb08_18-48-19_fadcca9c27d0/events.out.tfevents.1644346113.fadcca9c27d0.35.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a597dccc6f3715d001247946702bb39eef529586ea5d315e3d36b1aa9cbb49c
3
+ size 3708
runs/Feb08_19-24-11_fadcca9c27d0/1644348258.4993296/events.out.tfevents.1644348258.fadcca9c27d0.35.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ed6ebedcab88a55afcd700c0f19249b5caa25dee5a606313a8781c3a4101d3f
3
+ size 4774
runs/Feb08_19-24-11_fadcca9c27d0/events.out.tfevents.1644348258.fadcca9c27d0.35.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fb419f0fea41195134665abb1056ce1fcc92f38e8ba7eff4ff72a2e64885d36
3
+ size 7218
source.spm ADDED
Binary file (808 kB). View file
 
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
target.spm ADDED
Binary file (834 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"source_lang": "eng", "target_lang": "jpn", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "Helsinki-NLP/opus-tatoeba-en-ja", "tokenizer_class": "MarianTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:788f94a24f9e0e59617584da9ecf7e726c3cbc0e93e03fa9a8b7ffebbb2ba793
3
+ size 2991
vocab.json ADDED
The diff for this file is too large to render. See raw diff