Downloads · 30 days
8
15% of all-time downloads
mbart-mmt_7.4p_en-ko
yesj1234/mbart-mmt_7.4p_en-ko
mbart-mmt_7.4p_en-ko is a machine learning model from yesj1234. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
53
Public
Repo size
24.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt14.7 GB · 60%
At a glance
- Library
- transformers
- Model type
- mbart
- Access
- Public
- Created
- Oct 13, 2023
- Updated
- Oct 13, 2023
- SHA
- 20854cdc
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
tst-translation-output
This model is a fine-tuned version of facebook/mbart-large-50-many-to-many-mmt on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5319
- Bleu: 11.2991
- Gen Len: 16.268
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 16
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 40
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.4354 | 1.12 | 1500 | 1.5319 | 11.2991 | 16.268 |
| 0.9158 | 2.24 | 3000 | 1.5989 | 11.9085 | 16.3331 |
| 0.4823 | 3.37 | 4500 | 1.7407 | 11.2452 | 15.771 |
| 0.3005 | 4.49 | 6000 | 1.8923 | 11.0872 | 16.3668 |
| 0.1969 | 5.61 | 7500 | 2.0164 | 11.449 | 15.8694 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1
- Library
- transformers
- Type
- mbart
- Languages
- en, ko
- Created
- Oct 13, 2023
- Updated
- Oct 13, 2023