Hugging Face's logo

rhaymison
/
opus-en-to-pt-translator

Translation
Transformers
TensorBoard
Safetensors
Portuguese
English
marian
text2text-generation
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
rhaymison commited on
Commit
2c94fc9
•
1 Parent(s): e83bda9

End of training

Browse files
Files changed (14) hide show
  1. README.md +97 -0
  2. config.json +46 -0
  3. generation_config.json +16 -0
  4. model.safetensors +3 -0
  5. runs/Mar05_17-44-32_9218e5c44178/events.out.tfevents.1709661448.9218e5c44178.10562.0 +3 -0
  6. runs/Mar05_18-24-35_9218e5c44178/events.out.tfevents.1709663076.9218e5c44178.20563.0 +3 -0
  7. runs/Mar05_19-07-44_9218e5c44178/events.out.tfevents.1709665669.9218e5c44178.20563.1 +3 -0
  8. runs/Mar05_19-08-52_9218e5c44178/events.out.tfevents.1709665742.9218e5c44178.20563.2 +3 -0
  9. source.spm +0 -0
  10. special_tokens_map.json +5 -0
  11. target.spm +0 -0
  12. tokenizer_config.json +38 -0
  13. training_args.bin +3 -0
  14. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-4.0
3
+ base_model: Helsinki-NLP/opus-mt-tc-big-en-pt
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - kde4
8
+ model-index:
9
+ - name: opus-en-to-pt-translate
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # opus-en-to-pt-translate
17
+
18
+ This model is a fine-tuned version of [Helsinki-NLP/opus-mt-tc-big-en-pt](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-en-pt) on the kde4 dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.5618
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 2e-05
40
+ - train_batch_size: 32
41
+ - eval_batch_size: 16
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 3
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:-----:|:---------------:|
52
+ | 0.4982 | 0.08 | 500 | 0.6398 |
53
+ | 0.5475 | 0.15 | 1000 | 0.6370 |
54
+ | 0.5397 | 0.23 | 1500 | 0.6333 |
55
+ | 0.5267 | 0.31 | 2000 | 0.6272 |
56
+ | 0.5212 | 0.39 | 2500 | 0.6240 |
57
+ | 0.522 | 0.46 | 3000 | 0.6179 |
58
+ | 0.5213 | 0.54 | 3500 | 0.6124 |
59
+ | 0.5155 | 0.62 | 4000 | 0.6114 |
60
+ | 0.5143 | 0.7 | 4500 | 0.6053 |
61
+ | 0.5037 | 0.77 | 5000 | 0.6058 |
62
+ | 0.5093 | 0.85 | 5500 | 0.6002 |
63
+ | 0.5253 | 0.93 | 6000 | 0.5945 |
64
+ | 0.5138 | 1.01 | 6500 | 0.5892 |
65
+ | 0.4864 | 1.08 | 7000 | 0.5906 |
66
+ | 0.491 | 1.16 | 7500 | 0.5889 |
67
+ | 0.4993 | 1.24 | 8000 | 0.5849 |
68
+ | 0.4749 | 1.32 | 8500 | 0.5849 |
69
+ | 0.4911 | 1.39 | 9000 | 0.5812 |
70
+ | 0.487 | 1.47 | 9500 | 0.5796 |
71
+ | 0.4846 | 1.55 | 10000 | 0.5758 |
72
+ | 0.4863 | 1.63 | 10500 | 0.5739 |
73
+ | 0.4792 | 1.7 | 11000 | 0.5725 |
74
+ | 0.4816 | 1.78 | 11500 | 0.5704 |
75
+ | 0.4811 | 1.86 | 12000 | 0.5684 |
76
+ | 0.4773 | 1.94 | 12500 | 0.5676 |
77
+ | 0.4657 | 2.01 | 13000 | 0.5691 |
78
+ | 0.4246 | 2.09 | 13500 | 0.5683 |
79
+ | 0.4285 | 2.17 | 14000 | 0.5693 |
80
+ | 0.4241 | 2.25 | 14500 | 0.5676 |
81
+ | 0.422 | 2.32 | 15000 | 0.5669 |
82
+ | 0.4199 | 2.4 | 15500 | 0.5656 |
83
+ | 0.4273 | 2.48 | 16000 | 0.5650 |
84
+ | 0.4161 | 2.56 | 16500 | 0.5651 |
85
+ | 0.4243 | 2.63 | 17000 | 0.5635 |
86
+ | 0.4202 | 2.71 | 17500 | 0.5628 |
87
+ | 0.4152 | 2.79 | 18000 | 0.5627 |
88
+ | 0.4179 | 2.87 | 18500 | 0.5619 |
89
+ | 0.4241 | 2.94 | 19000 | 0.5618 |
90
+
91
+
92
+ ### Framework versions
93
+
94
+ - Transformers 4.38.1
95
+ - Pytorch 2.1.0+cu121
96
+ - Datasets 2.18.0
97
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-tc-big-en-pt",
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
+ 54775
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": 54775,
22
+ "decoder_vocab_size": 54776,
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": 44670,
29
+ "forced_eos_token_id": 44670,
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": 54775,
39
+ "scale_embedding": true,
40
+ "share_encoder_decoder_embeddings": true,
41
+ "static_position_embeddings": true,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.38.1",
44
+ "use_cache": true,
45
+ "vocab_size": 54776
46
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 54775
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 54775,
9
+ "eos_token_id": 44670,
10
+ "forced_eos_token_id": 44670,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 54775,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.38.1"
16
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12eb02ff294dfe0ec1d372312b871e589cc5971f3510f9450ffbc6eca686a668
3
+ size 930040720
runs/Mar05_17-44-32_9218e5c44178/events.out.tfevents.1709661448.9218e5c44178.10562.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:459a78cb119e4691d079ab9828e81c65c6d2ca0c9e43a867673ec7957f9846d0
3
+ size 9861
runs/Mar05_18-24-35_9218e5c44178/events.out.tfevents.1709663076.9218e5c44178.20563.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:684686875176131a8c9661a6bc348192355a05dae412590bf8448e503b1d3e2b
3
+ size 7751
runs/Mar05_19-07-44_9218e5c44178/events.out.tfevents.1709665669.9218e5c44178.20563.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e66df28e5f40d6d9dc20fe3b89975b8218afea4ea1981b89a4b4d625c2183469
3
+ size 5217
runs/Mar05_19-08-52_9218e5c44178/events.out.tfevents.1709665742.9218e5c44178.20563.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe6cae7ffb45c0c6f9e49ad91af19c8a84888c56f064f513218b8631e3cc3925
3
+ size 23948
source.spm ADDED
Binary file (803 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 (825 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "44670": {
4
+ "content": "</s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "52024": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "54775": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "eos_token": "</s>",
30
+ "model_max_length": 512,
31
+ "pad_token": "<pad>",
32
+ "separate_vocabs": false,
33
+ "source_lang": "en",
34
+ "sp_model_kwargs": {},
35
+ "target_lang": "pt",
36
+ "tokenizer_class": "MarianTokenizer",
37
+ "unk_token": "<unk>"
38
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7a0e6aa3d0d2805114c60bccda7335dab21261dfa1ef5b6c067e1417fe78c9c
3
+ size 5048
vocab.json ADDED
The diff for this file is too large to render. See raw diff