madlad400-finetuned-new-npi
This model is a fine-tuned version of jbochi/madlad400-3b-mt on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2096
- Chrf: 57.7516
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: 0.0005
- train_batch_size: 4
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Chrf |
|---|---|---|---|---|
| 0.793 | 1.6626 | 1600 | 0.7295 | 31.1036 |
| 0.5771 | 3.3251 | 3200 | 0.4762 | 44.6002 |
| 0.5073 | 4.9877 | 4800 | 0.3704 | 48.9356 |
| 0.4017 | 6.6502 | 6400 | 0.2929 | 52.5807 |
| 0.3408 | 8.3128 | 8000 | 0.2341 | 55.8969 |
| 0.2914 | 9.9753 | 9600 | 0.2096 | 57.7629 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu124
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 31
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for sil-ai/madlad400-finetuned-new-npi
Base model
jbochi/madlad400-3b-mt