Downloads · 30 days
13
3% of all-time downloads
catla-nllb-en2bn
shanjivkr/catla-nllb-en2bn
catla-nllb-en2bn is a machine learning model from shanjivkr. 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 peft. The card lists the license as cc-by-nc-4.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
468
Public
Repo size
2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors34.7 MB · 52%
At a glance
- Library
- peft
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- Aug 5, 2026
- Updated
- Sep 6, 2026
- SHA
- 639f509f
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. -->
catla-nllb-en2bn
This model is a fine-tuned version of facebook/nllb-200-distilled-600M on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9267
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 1.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 11.5100 | 0.0280 | 500 | 2.5831 |
| 10.3122 | 0.0560 | 1000 | 2.3685 |
| 10.3199 | 0.0840 | 1500 | 2.2951 |
| 9.9178 | 0.1120 | 2000 | 2.2435 |
| 9.9873 | 0.1400 | 2500 | 2.2024 |
| 9.6865 | 0.1680 | 3000 | 2.1741 |
| 9.6152 | 0.1960 | 3500 | 2.1389 |
| 9.4381 | 0.2240 | 4000 | 2.1200 |
| 9.3266 | 0.2520 | 4500 | 2.0949 |
| 9.3635 | 0.2800 | 5000 | 2.0772 |
| 9.1342 | 0.3080 | 5500 | 2.0656 |
| 9.0540 | 0.3360 | 6000 | 2.0529 |
| 9.2147 | 0.3640 | 6500 | 2.0381 |
| 9.1070 | 0.3920 | 7000 | 2.0310 |
| 9.0736 | 0.4200 | 7500 | 2.0172 |
| 8.9068 | 0.4480 | 8000 | 2.0097 |
| 9.1283 | 0.4760 | 8500 | 2.0037 |
| 8.9724 | 0.5039 | 9000 | 1.9944 |
| 8.8401 | 0.5319 | 9500 | 1.9865 |
| 9.0307 | 0.5599 | 10000 | 1.9837 |
| 9.0398 | 0.5879 | 10500 | 1.9790 |
| 8.9052 | 0.6159 | 11000 | 1.9704 |
| 8.7513 | 0.6439 | 11500 | 1.9640 |
| 8.9286 | 0.6719 | 12000 | 1.9615 |
| 8.7243 | 0.6999 | 12500 | 1.9550 |
| 8.8446 | 0.7279 | 13000 | 1.9496 |
| 8.6795 | 0.7559 | 13500 | 1.9447 |
| 8.7174 | 0.7839 | 14000 | 1.9405 |
| 8.7698 | 0.8119 | 14500 | 1.9399 |
| 8.6614 | 0.8399 | 15000 | 1.9359 |
| 8.5888 | 0.8679 | 15500 | 1.9298 |
| 8.6753 | 0.8959 | 16000 | 1.9350 |
| 8.5696 | 0.9239 | 16500 | 1.9289 |
| 8.6053 | 0.9519 | 17000 | 1.9296 |
| 8.8083 | 0.9799 | 17500 | 1.9267 |
Framework versions
- PEFT 0.19.1
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2
- Library
- peft
- License
- cc-by-nc-4.0
- Created
- Aug 5, 2026
- Updated
- Sep 6, 2026