Hugging Face's logo

DanielHellebust
/
cyclingo

Translation
Transformers
PyTorch
English
Norwegian
Norwegian Bokmål
marian
text2text-generation
bicycleterminology
bicycle
cycling
Model card Files
xet
 Community
2
DanielHellebust commited on
Commit
8039eae
·
1 Parent(s): 5138014

Upload 12 files

Browse files
Files changed (12) hide show
  1. config.json +46 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. source.spm +0 -0
  7. special_tokens_map.json +5 -0
  8. target.spm +0 -0
  9. tokenizer_config.json +13 -0
  10. trainer_state.json +154 -0
  11. training_args.bin +3 -0
  12. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-tc-big-en-gmq",
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
+ 54666
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": 54666,
22
+ "decoder_vocab_size": 54667,
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": 41839,
29
+ "forced_eos_token_id": 41839,
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": 54666,
39
+ "scale_embedding": true,
40
+ "share_encoder_decoder_embeddings": true,
41
+ "static_position_embeddings": true,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.25.1",
44
+ "use_cache": true,
45
+ "vocab_size": 54667
46
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec6ebd4e3834191476bbae5e6a657d36a1bf398a7bf5b1bba9c76dc041d058aa
3
+ size 1858837965
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:780645fbf064497871dfc436d34b257f6702407dc4fc87e615c4788ed76d0407
3
+ size 929648645
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46b440875e92c8701b0244b8f1defaf4a55f39130272d2d8182a45c2bf736e14
3
+ size 14439
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d77a8263d2c9ab2d2fd99749ca0bd684b2d23ea39ae6b5deffc35ec07d427d80
3
+ size 623
source.spm ADDED
Binary file (794 kB). View file
 
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
target.spm ADDED
Binary file (800 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "model_max_length": 512,
4
+ "name_or_path": "Helsinki-NLP/opus-mt-tc-big-en-gmq",
5
+ "pad_token": "<pad>",
6
+ "separate_vocabs": false,
7
+ "source_lang": "en",
8
+ "sp_model_kwargs": {},
9
+ "special_tokens_map_file": null,
10
+ "target_lang": "gmq",
11
+ "tokenizer_class": "MarianTokenizer",
12
+ "unk_token": "<unk>"
13
+ }
trainer_state.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 4000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_bleu": 58.9649,
13
+ "eval_gen_len": 19.44,
14
+ "eval_loss": 0.6476399302482605,
15
+ "eval_runtime": 7.9533,
16
+ "eval_samples_per_second": 12.573,
17
+ "eval_steps_per_second": 6.287,
18
+ "step": 400
19
+ },
20
+ {
21
+ "epoch": 1.25,
22
+ "learning_rate": 1.7500000000000002e-05,
23
+ "loss": 0.6755,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_bleu": 59.7239,
29
+ "eval_gen_len": 19.21,
30
+ "eval_loss": 0.6683109998703003,
31
+ "eval_runtime": 7.5813,
32
+ "eval_samples_per_second": 13.19,
33
+ "eval_steps_per_second": 6.595,
34
+ "step": 800
35
+ },
36
+ {
37
+ "epoch": 2.5,
38
+ "learning_rate": 1.5000000000000002e-05,
39
+ "loss": 0.2568,
40
+ "step": 1000
41
+ },
42
+ {
43
+ "epoch": 3.0,
44
+ "eval_bleu": 59.3781,
45
+ "eval_gen_len": 19.22,
46
+ "eval_loss": 0.7284716963768005,
47
+ "eval_runtime": 7.5691,
48
+ "eval_samples_per_second": 13.212,
49
+ "eval_steps_per_second": 6.606,
50
+ "step": 1200
51
+ },
52
+ {
53
+ "epoch": 3.75,
54
+ "learning_rate": 1.25e-05,
55
+ "loss": 0.1116,
56
+ "step": 1500
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_bleu": 60.1615,
61
+ "eval_gen_len": 19.14,
62
+ "eval_loss": 0.8120526075363159,
63
+ "eval_runtime": 7.4229,
64
+ "eval_samples_per_second": 13.472,
65
+ "eval_steps_per_second": 6.736,
66
+ "step": 1600
67
+ },
68
+ {
69
+ "epoch": 5.0,
70
+ "learning_rate": 1e-05,
71
+ "loss": 0.048,
72
+ "step": 2000
73
+ },
74
+ {
75
+ "epoch": 5.0,
76
+ "eval_bleu": 58.8865,
77
+ "eval_gen_len": 19.34,
78
+ "eval_loss": 0.8653954267501831,
79
+ "eval_runtime": 8.7147,
80
+ "eval_samples_per_second": 11.475,
81
+ "eval_steps_per_second": 5.737,
82
+ "step": 2000
83
+ },
84
+ {
85
+ "epoch": 6.0,
86
+ "eval_bleu": 58.2232,
87
+ "eval_gen_len": 19.07,
88
+ "eval_loss": 0.8903241157531738,
89
+ "eval_runtime": 8.0705,
90
+ "eval_samples_per_second": 12.391,
91
+ "eval_steps_per_second": 6.195,
92
+ "step": 2400
93
+ },
94
+ {
95
+ "epoch": 6.25,
96
+ "learning_rate": 7.500000000000001e-06,
97
+ "loss": 0.0178,
98
+ "step": 2500
99
+ },
100
+ {
101
+ "epoch": 7.0,
102
+ "eval_bleu": 58.0224,
103
+ "eval_gen_len": 19.22,
104
+ "eval_loss": 0.9194047451019287,
105
+ "eval_runtime": 8.0477,
106
+ "eval_samples_per_second": 12.426,
107
+ "eval_steps_per_second": 6.213,
108
+ "step": 2800
109
+ },
110
+ {
111
+ "epoch": 7.5,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.0087,
114
+ "step": 3000
115
+ },
116
+ {
117
+ "epoch": 8.0,
118
+ "eval_bleu": 58.8822,
119
+ "eval_gen_len": 19.29,
120
+ "eval_loss": 0.930671751499176,
121
+ "eval_runtime": 7.9933,
122
+ "eval_samples_per_second": 12.51,
123
+ "eval_steps_per_second": 6.255,
124
+ "step": 3200
125
+ },
126
+ {
127
+ "epoch": 8.75,
128
+ "learning_rate": 2.5e-06,
129
+ "loss": 0.0039,
130
+ "step": 3500
131
+ },
132
+ {
133
+ "epoch": 9.0,
134
+ "eval_bleu": 59.1049,
135
+ "eval_gen_len": 19.18,
136
+ "eval_loss": 0.9447950124740601,
137
+ "eval_runtime": 7.8845,
138
+ "eval_samples_per_second": 12.683,
139
+ "eval_steps_per_second": 6.342,
140
+ "step": 3600
141
+ },
142
+ {
143
+ "epoch": 10.0,
144
+ "learning_rate": 0.0,
145
+ "loss": 0.0027,
146
+ "step": 4000
147
+ }
148
+ ],
149
+ "max_steps": 4000,
150
+ "num_train_epochs": 10,
151
+ "total_flos": 199212586500096.0,
152
+ "trial_name": null,
153
+ "trial_params": null
154
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c339b48e431102c24b1b77c27ac88c9ccab9d3f286d0e028efdd6f0d754a8eb
3
+ size 3567
vocab.json ADDED
The diff for this file is too large to render. See raw diff