add model
Browse files- .gitignore +1 -0
- README.md +72 -0
- config.json +60 -0
- pytorch_model.bin +3 -0
- runs/Jul27_03-16-02_baadd1eee5cb/1627355776.5392456/events.out.tfevents.1627355776.baadd1eee5cb.67.1 +3 -0
- runs/Jul27_03-16-02_baadd1eee5cb/events.out.tfevents.1627355776.baadd1eee5cb.67.0 +3 -0
- source.spm +0 -0
- special_tokens_map.json +1 -0
- target.spm +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- wmt16
|
6 |
+
metrics:
|
7 |
+
- bleu
|
8 |
+
model_index:
|
9 |
+
- name: opus-mt-en-ro-finetuned-en-to-ro
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Sequence-to-sequence Language Modeling
|
13 |
+
type: text2text-generation
|
14 |
+
dataset:
|
15 |
+
name: wmt16
|
16 |
+
type: wmt16
|
17 |
+
args: ro-en
|
18 |
+
metric:
|
19 |
+
name: Bleu
|
20 |
+
type: bleu
|
21 |
+
value: 28.1641
|
22 |
+
---
|
23 |
+
|
24 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
25 |
+
should probably proofread and complete it, then remove this comment. -->
|
26 |
+
|
27 |
+
# opus-mt-en-ro-finetuned-en-to-ro
|
28 |
+
|
29 |
+
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ro](https://huggingface.co/Helsinki-NLP/opus-mt-en-ro) on the wmt16 dataset.
|
30 |
+
It achieves the following results on the evaluation set:
|
31 |
+
- Loss: 1.2886
|
32 |
+
- Bleu: 28.1641
|
33 |
+
- Gen Len: 34.1071
|
34 |
+
|
35 |
+
## Model description
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Intended uses & limitations
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training and evaluation data
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training procedure
|
48 |
+
|
49 |
+
### Training hyperparameters
|
50 |
+
|
51 |
+
The following hyperparameters were used during training:
|
52 |
+
- learning_rate: 2e-05
|
53 |
+
- train_batch_size: 16
|
54 |
+
- eval_batch_size: 16
|
55 |
+
- seed: 42
|
56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
+
- lr_scheduler_type: linear
|
58 |
+
- num_epochs: 1
|
59 |
+
|
60 |
+
### Training results
|
61 |
+
|
62 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
63 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
|
64 |
+
| 0.7436 | 1.0 | 38145 | 1.2886 | 28.1641 | 34.1071 |
|
65 |
+
|
66 |
+
|
67 |
+
### Framework versions
|
68 |
+
|
69 |
+
- Transformers 4.9.1
|
70 |
+
- Pytorch 1.9.0+cu102
|
71 |
+
- Datasets 1.10.2
|
72 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-en-ro",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "swish",
|
6 |
+
"add_bias_logits": false,
|
7 |
+
"add_final_layer_norm": false,
|
8 |
+
"architectures": [
|
9 |
+
"MarianMTModel"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bad_words_ids": [
|
13 |
+
[
|
14 |
+
59542
|
15 |
+
]
|
16 |
+
],
|
17 |
+
"bos_token_id": 0,
|
18 |
+
"classif_dropout": 0.0,
|
19 |
+
"classifier_dropout": 0.0,
|
20 |
+
"d_model": 512,
|
21 |
+
"decoder_attention_heads": 8,
|
22 |
+
"decoder_ffn_dim": 2048,
|
23 |
+
"decoder_layerdrop": 0.0,
|
24 |
+
"decoder_layers": 6,
|
25 |
+
"decoder_start_token_id": 59542,
|
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 |
+
"forced_eos_token_id": 0,
|
33 |
+
"gradient_checkpointing": false,
|
34 |
+
"id2label": {
|
35 |
+
"0": "LABEL_0",
|
36 |
+
"1": "LABEL_1",
|
37 |
+
"2": "LABEL_2"
|
38 |
+
},
|
39 |
+
"init_std": 0.02,
|
40 |
+
"is_encoder_decoder": true,
|
41 |
+
"label2id": {
|
42 |
+
"LABEL_0": 0,
|
43 |
+
"LABEL_1": 1,
|
44 |
+
"LABEL_2": 2
|
45 |
+
},
|
46 |
+
"max_length": 512,
|
47 |
+
"max_position_embeddings": 512,
|
48 |
+
"model_type": "marian",
|
49 |
+
"normalize_before": false,
|
50 |
+
"normalize_embedding": false,
|
51 |
+
"num_beams": 4,
|
52 |
+
"num_hidden_layers": 6,
|
53 |
+
"pad_token_id": 59542,
|
54 |
+
"scale_embedding": true,
|
55 |
+
"static_position_embeddings": true,
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.9.1",
|
58 |
+
"use_cache": true,
|
59 |
+
"vocab_size": 59543
|
60 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bee95f1226caf47e323fdf054cba4b6ab1d52a608ca510f09a06dfc95b3bde4
|
3 |
+
size 298820677
|
runs/Jul27_03-16-02_baadd1eee5cb/1627355776.5392456/events.out.tfevents.1627355776.baadd1eee5cb.67.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc2b8b87082d6468010a120ec6383541a776637d75329788c40b3e99c373dfd8
|
3 |
+
size 4337
|
runs/Jul27_03-16-02_baadd1eee5cb/events.out.tfevents.1627355776.baadd1eee5cb.67.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9da3fbc94682441def03397306aae574a5706a611b902fb34a934de3f0f2710e
|
3 |
+
size 16534
|
source.spm
ADDED
Binary file (789 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 (817 kB). View file
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"source_lang": "en", "target_lang": "ro", "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-ro", "tokenizer_class": "MarianTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8cbc967174535b894fca348a79e6d925f9e28b0140dc4e605ff24d178b338b9
|
3 |
+
size 2735
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|