This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Llama-8B on the belebele_npi_Deva_train dataset.
It achieves the following results on the evaluation set:
Loss: 0.0900
Accuracy: 0.9434
Mcq Accuracy: 0.25
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: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
