Downloads · 30 days
11
17% of all-time downloads
mt-pre-RLHF
crslnjoyz/mt-pre-RLHF
mt-pre-RLHF is a machine learning model from crslnjoyz. 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
64
Public
Parameters
611M
12.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.4 GB · 99%
At a glance
- Library
- transformers
- Model type
- mbart
- Access
- Public
- Created
- Feb 18, 2026
- Updated
- Feb 18, 2026
- SHA
- 10adbf98
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. -->
mt-pre-RLHF
This model is a fine-tuned version of facebook/mbart-large-50-many-to-many-mmt on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0196
- Bleu: 89.7710
- Chrf: 94.0872
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Chrf |
|---|---|---|---|---|---|
| 0.1401 | 2.1462 | 500 | 0.0612 | 87.1690 | 90.0446 |
| 0.0591 | 4.2925 | 1000 | 0.0439 | 91.5263 | 94.2053 |
| 0.0503 | 6.4387 | 1500 | 0.0233 | 92.9078 | 94.8257 |
| 0.0421 | 8.5849 | 2000 | 0.0196 | 89.7710 | 94.0872 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.9.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Library
- transformers
- Type
- mbart
- Created
- Feb 18, 2026
- Updated
- Feb 18, 2026