Hugging Face's logo

DeskDown
/
MarianMix_en-zh_to_vi-ms-hi-ja

Text2Text Generation
Transformers
PyTorch
TensorBoard
marian
Inference Endpoints
Model card Files Metrics Community
1
DeskDown commited on
Commit
1b1396c
•
1 Parent(s): 4cb77d2

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 +62 -0
  4. last-checkpoint/added_tokens.json +0 -0
  5. last-checkpoint/config.json +62 -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/Jan12_10-14-41_b9e9bdc6eb9d/1641982611.6217527/events.out.tfevents.1641982611.b9e9bdc6eb9d.34.1 +3 -0
  20. runs/Jan12_10-14-41_b9e9bdc6eb9d/events.out.tfevents.1641982611.b9e9bdc6eb9d.34.0 +3 -0
  21. runs/Jan12_10-19-43_b9e9bdc6eb9d/1641982794.959962/events.out.tfevents.1641982794.b9e9bdc6eb9d.34.3 +3 -0
  22. runs/Jan12_10-19-43_b9e9bdc6eb9d/events.out.tfevents.1641982794.b9e9bdc6eb9d.34.2 +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 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-en-zh",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "swish",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "MarianMTModel"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bad_words_ids": [
12
+ [
13
+ 65000
14
+ ]
15
+ ],
16
+ "bos_token_id": 0,
17
+ "classif_dropout": 0.0,
18
+ "classifier_dropout": 0.0,
19
+ "d_model": 512,
20
+ "decoder_attention_heads": 8,
21
+ "decoder_ffn_dim": 2048,
22
+ "decoder_layerdrop": 0.0,
23
+ "decoder_layers": 6,
24
+ "decoder_start_token_id": 65000,
25
+ "do_blenderbot_90_layernorm": false,
26
+ "dropout": 0.1,
27
+ "encoder_attention_heads": 8,
28
+ "encoder_ffn_dim": 2048,
29
+ "encoder_layerdrop": 0.0,
30
+ "encoder_layers": 6,
31
+ "eos_token_id": 0,
32
+ "extra_pos_embeddings": 0,
33
+ "force_bos_token_to_be_generated": false,
34
+ "forced_eos_token_id": 0,
35
+ "gradient_checkpointing": false,
36
+ "id2label": {
37
+ "0": "LABEL_0",
38
+ "1": "LABEL_1",
39
+ "2": "LABEL_2"
40
+ },
41
+ "init_std": 0.02,
42
+ "is_encoder_decoder": true,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1,
46
+ "LABEL_2": 2
47
+ },
48
+ "max_length": 512,
49
+ "max_position_embeddings": 512,
50
+ "model_type": "marian",
51
+ "normalize_before": false,
52
+ "normalize_embedding": false,
53
+ "num_beams": 4,
54
+ "num_hidden_layers": 6,
55
+ "pad_token_id": 65000,
56
+ "scale_embedding": true,
57
+ "static_position_embeddings": true,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.12.5",
60
+ "use_cache": true,
61
+ "vocab_size": 101452
62
+ }
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 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-en-zh",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "swish",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "MarianMTModel"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bad_words_ids": [
12
+ [
13
+ 65000
14
+ ]
15
+ ],
16
+ "bos_token_id": 0,
17
+ "classif_dropout": 0.0,
18
+ "classifier_dropout": 0.0,
19
+ "d_model": 512,
20
+ "decoder_attention_heads": 8,
21
+ "decoder_ffn_dim": 2048,
22
+ "decoder_layerdrop": 0.0,
23
+ "decoder_layers": 6,
24
+ "decoder_start_token_id": 65000,
25
+ "do_blenderbot_90_layernorm": false,
26
+ "dropout": 0.1,
27
+ "encoder_attention_heads": 8,
28
+ "encoder_ffn_dim": 2048,
29
+ "encoder_layerdrop": 0.0,
30
+ "encoder_layers": 6,
31
+ "eos_token_id": 0,
32
+ "extra_pos_embeddings": 0,
33
+ "force_bos_token_to_be_generated": false,
34
+ "forced_eos_token_id": 0,
35
+ "gradient_checkpointing": false,
36
+ "id2label": {
37
+ "0": "LABEL_0",
38
+ "1": "LABEL_1",
39
+ "2": "LABEL_2"
40
+ },
41
+ "init_std": 0.02,
42
+ "is_encoder_decoder": true,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1,
46
+ "LABEL_2": 2
47
+ },
48
+ "max_length": 512,
49
+ "max_position_embeddings": 512,
50
+ "model_type": "marian",
51
+ "normalize_before": false,
52
+ "normalize_embedding": false,
53
+ "num_beams": 4,
54
+ "num_hidden_layers": 6,
55
+ "pad_token_id": 65000,
56
+ "scale_embedding": true,
57
+ "static_position_embeddings": true,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.12.5",
60
+ "use_cache": true,
61
+ "vocab_size": 101452
62
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b82e0d8a25c4e2d10df4f17ff176a4dcab751e1e5f7da8c4ce56bf434c4a19c0
3
+ size 768802253
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f0d973f47679db77ad91a94a432ffd8d3c21e58045823622e88099f7b521793
3
+ size 384827845
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:106f38b2915671d1b908c32b3cbf76f01989ec6112a9eb279119ddf4d98c6009
3
+ size 14503
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2a4914ac33c232452b9952cfe6dce5403de9b2d4a7036f821d3c1ed1060b07a
3
+ size 559
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d466bae241df304cf88e4f0d3631f7db64bc42748c26fa5646641cbbad6810e3
3
+ size 623
last-checkpoint/source.spm ADDED
Binary file (806 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 (805 kB). View file
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"source_lang": "eng", "target_lang": "zho", "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-mt-en-zh", "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": 3.5587188612099645,
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": 0.18,
12
+ "learning_rate": 9.650997150997152e-05,
13
+ "loss": 1.5302,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.36,
18
+ "learning_rate": 9.295584045584046e-05,
19
+ "loss": 1.3916,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.53,
24
+ "learning_rate": 8.939458689458689e-05,
25
+ "loss": 1.2024,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.71,
30
+ "learning_rate": 8.583333333333334e-05,
31
+ "loss": 1.0846,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.89,
36
+ "learning_rate": 8.227207977207978e-05,
37
+ "loss": 1.0088,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.07,
42
+ "learning_rate": 7.871082621082622e-05,
43
+ "loss": 0.9088,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.25,
48
+ "learning_rate": 7.514957264957265e-05,
49
+ "loss": 0.8388,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.42,
54
+ "learning_rate": 7.158831908831909e-05,
55
+ "loss": 0.7937,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.6,
60
+ "learning_rate": 6.802706552706552e-05,
61
+ "loss": 0.7683,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.78,
66
+ "learning_rate": 6.446581196581197e-05,
67
+ "loss": 0.734,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.96,
72
+ "learning_rate": 6.090455840455841e-05,
73
+ "loss": 0.7031,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 2.14,
78
+ "learning_rate": 5.7343304843304845e-05,
79
+ "loss": 0.6465,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 2.31,
84
+ "learning_rate": 5.378205128205128e-05,
85
+ "loss": 0.6236,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 2.49,
90
+ "learning_rate": 5.022079772079772e-05,
91
+ "loss": 0.6151,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 2.67,
96
+ "learning_rate": 4.665954415954416e-05,
97
+ "loss": 0.5924,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 2.85,
102
+ "learning_rate": 4.30982905982906e-05,
103
+ "loss": 0.5918,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 3.02,
108
+ "learning_rate": 3.9537037037037036e-05,
109
+ "loss": 0.5756,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 3.2,
114
+ "learning_rate": 3.597578347578348e-05,
115
+ "loss": 0.5302,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 3.38,
120
+ "learning_rate": 3.241452991452992e-05,
121
+ "loss": 0.5245,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 3.56,
126
+ "learning_rate": 2.8853276353276353e-05,
127
+ "loss": 0.5219,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 3.56,
132
+ "eval_bleu": 9.2289,
133
+ "eval_gen_len": 36.3363,
134
+ "eval_loss": 0.7101184129714966,
135
+ "eval_runtime": 335.0095,
136
+ "eval_samples_per_second": 11.892,
137
+ "eval_steps_per_second": 0.373,
138
+ "step": 10000
139
+ }
140
+ ],
141
+ "max_steps": 14050,
142
+ "num_train_epochs": 5,
143
+ "total_flos": 2.169210609126605e+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 sha256:8a36939be1771359f3b477e541ab1d6ae1de57d2c29ccbf158d1775562e8e679
3
+ size 3055
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 sha256:0f0d973f47679db77ad91a94a432ffd8d3c21e58045823622e88099f7b521793
3
+ size 384827845
runs/Jan12_10-14-41_b9e9bdc6eb9d/1641982611.6217527/events.out.tfevents.1641982611.b9e9bdc6eb9d.34.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:776fa9e49e5332ca9b699169d2e175e869af486285b7ced60b6ca43c9517a55d
3
+ size 4783
runs/Jan12_10-14-41_b9e9bdc6eb9d/events.out.tfevents.1641982611.b9e9bdc6eb9d.34.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a45051cfeb9d3f161924cecaea417d0a4563aec0243f2db20b435edb4414eec9
3
+ size 4103
runs/Jan12_10-19-43_b9e9bdc6eb9d/1641982794.959962/events.out.tfevents.1641982794.b9e9bdc6eb9d.34.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f989ac58fdee6cb0725fc266999bedc8b079a8481270a12e889f7ea34a8a5f72
3
+ size 4783
runs/Jan12_10-19-43_b9e9bdc6eb9d/events.out.tfevents.1641982794.b9e9bdc6eb9d.34.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f51a7a3bdf6998ae2da30f3c398b721caa626cbff8e1e2f7e75879173d8ef841
3
+ size 7612
source.spm ADDED
Binary file (806 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 (805 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"source_lang": "eng", "target_lang": "zho", "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-mt-en-zh", "tokenizer_class": "MarianTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a36939be1771359f3b477e541ab1d6ae1de57d2c29ccbf158d1775562e8e679
3
+ size 3055
vocab.json ADDED
The diff for this file is too large to render. See raw diff