ncduy0303
commited on
Commit
•
262baea
1
Parent(s):
2ce7d3c
add model
Browse files- .gitignore +1 -0
- README.md +63 -0
- config.json +60 -0
- pytorch_model.bin +3 -0
- runs/Aug06_15-37-22_639f04c0b4ba/1628264264.9620378/events.out.tfevents.1628264264.639f04c0b4ba.168.1 +3 -0
- runs/Aug06_15-37-22_639f04c0b4ba/1628264361.4105704/events.out.tfevents.1628264361.639f04c0b4ba.168.3 +3 -0
- runs/Aug06_15-37-22_639f04c0b4ba/1628264532.6876898/events.out.tfevents.1628264532.639f04c0b4ba.168.5 +3 -0
- runs/Aug06_15-37-22_639f04c0b4ba/events.out.tfevents.1628264264.639f04c0b4ba.168.0 +3 -0
- runs/Aug06_15-37-22_639f04c0b4ba/events.out.tfevents.1628264361.639f04c0b4ba.168.2 +3 -0
- runs/Aug06_15-37-22_639f04c0b4ba/events.out.tfevents.1628264532.639f04c0b4ba.168.4 +3 -0
- runs/Aug06_15-42-12_639f04c0b4ba/1628264545.5258875/events.out.tfevents.1628264545.639f04c0b4ba.168.7 +3 -0
- runs/Aug06_15-42-12_639f04c0b4ba/1628264555.2278373/events.out.tfevents.1628264555.639f04c0b4ba.168.9 +3 -0
- runs/Aug06_15-42-12_639f04c0b4ba/events.out.tfevents.1628264545.639f04c0b4ba.168.6 +3 -0
- runs/Aug06_15-42-12_639f04c0b4ba/events.out.tfevents.1628264555.639f04c0b4ba.168.8 +3 -0
- runs/Aug06_15-44-36_639f04c0b4ba/1628264693.4917042/events.out.tfevents.1628264693.639f04c0b4ba.168.11 +3 -0
- runs/Aug06_15-44-36_639f04c0b4ba/events.out.tfevents.1628264693.639f04c0b4ba.168.10 +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 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- wmt16
|
6 |
+
model_index:
|
7 |
+
- name: opus-mt-en-ro-finetuned-en-to-ro
|
8 |
+
results:
|
9 |
+
- task:
|
10 |
+
name: Sequence-to-sequence Language Modeling
|
11 |
+
type: text2text-generation
|
12 |
+
dataset:
|
13 |
+
name: wmt16
|
14 |
+
type: wmt16
|
15 |
+
args: ro-en
|
16 |
+
---
|
17 |
+
|
18 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
19 |
+
should probably proofread and complete it, then remove this comment. -->
|
20 |
+
|
21 |
+
# opus-mt-en-ro-finetuned-en-to-ro
|
22 |
+
|
23 |
+
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.
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 2e-05
|
43 |
+
- train_batch_size: 16
|
44 |
+
- eval_batch_size: 16
|
45 |
+
- seed: 42
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 1
|
49 |
+
- mixed_precision_training: Native AMP
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
|
55 |
+
| No log | 1.0 | 382 | 1.4067 | 27.6209 | 33.5648 |
|
56 |
+
|
57 |
+
|
58 |
+
### Framework versions
|
59 |
+
|
60 |
+
- Transformers 4.9.1
|
61 |
+
- Pytorch 1.9.0+cu102
|
62 |
+
- Datasets 1.11.0
|
63 |
+
- 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 sha256:41ec1796d8016481a5711cf4dd6ffe80bd094142c8aef1ba6015f38b30caf882
|
3 |
+
size 298820677
|
runs/Aug06_15-37-22_639f04c0b4ba/1628264264.9620378/events.out.tfevents.1628264264.639f04c0b4ba.168.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0ab1aa390ffbd1d7b042ff886df8ae82737864ae3428f0b0b37122d75670418
|
3 |
+
size 4334
|
runs/Aug06_15-37-22_639f04c0b4ba/1628264361.4105704/events.out.tfevents.1628264361.639f04c0b4ba.168.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8c312a0db5ddb90a42b21cedb9bf855cc80cd2d6a459a084b9c3d26e9de28ed
|
3 |
+
size 4334
|
runs/Aug06_15-37-22_639f04c0b4ba/1628264532.6876898/events.out.tfevents.1628264532.639f04c0b4ba.168.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1625ebd8d0d34e57bfaa25a7dd5a5ddfdf7a3e4c6aa36f3018b783b85430d387
|
3 |
+
size 4334
|
runs/Aug06_15-37-22_639f04c0b4ba/events.out.tfevents.1628264264.639f04c0b4ba.168.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcd9acc341cd03795a4d07513b3b033d0eadd223275db66d72233f95a22c9031
|
3 |
+
size 3729
|
runs/Aug06_15-37-22_639f04c0b4ba/events.out.tfevents.1628264361.639f04c0b4ba.168.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bc5488ec45225d8221f19bcb9ca89be4994849fe29ce6c6e3f514a367c02332
|
3 |
+
size 3729
|
runs/Aug06_15-37-22_639f04c0b4ba/events.out.tfevents.1628264532.639f04c0b4ba.168.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb6f67c158974adadac01cf5ab1a2a142f247ddfee4aa37b2b1ec7fad118ffef
|
3 |
+
size 3729
|
runs/Aug06_15-42-12_639f04c0b4ba/1628264545.5258875/events.out.tfevents.1628264545.639f04c0b4ba.168.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a5843cfb243115f96346057201863603f2a311bc72c3fb95517b5d281d00528
|
3 |
+
size 4334
|
runs/Aug06_15-42-12_639f04c0b4ba/1628264555.2278373/events.out.tfevents.1628264555.639f04c0b4ba.168.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80a78c3ce1c5a88f9c0314c375c4763b883b72c3a9c3112c2ab036c94735b10c
|
3 |
+
size 4334
|
runs/Aug06_15-42-12_639f04c0b4ba/events.out.tfevents.1628264545.639f04c0b4ba.168.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd40ca9338ef2e28d06a61d1a6b4290f986d34716ea15ddb854c650ccc777341
|
3 |
+
size 3729
|
runs/Aug06_15-42-12_639f04c0b4ba/events.out.tfevents.1628264555.639f04c0b4ba.168.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f946e557a4f875c5d68b59c3009423a85768d33003d94bbb17f15e2d78a934fe
|
3 |
+
size 3729
|
runs/Aug06_15-44-36_639f04c0b4ba/1628264693.4917042/events.out.tfevents.1628264693.639f04c0b4ba.168.11
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a519e4bf02962daead192ebedd3d06203d24a958341ee367046d33cfb75b6c20
|
3 |
+
size 4334
|
runs/Aug06_15-44-36_639f04c0b4ba/events.out.tfevents.1628264693.639f04c0b4ba.168.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f77704f89f32174680d35dba37ff62e9afb84972b27afbb337243791b85fe6d0
|
3 |
+
size 4453
|
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 sha256:7664bebe80270d3116139dcd046cc11fac5d5d75ed716e0ea9a2e2aa2ed70fed
|
3 |
+
size 2735
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|