This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the belebele_hat_Latn_train dataset. It achieves the following results on the evaluation set:

Loss: 0.2357
Accuracy: 0.9565
Mcq Accuracy: 0.5778

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
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.1
num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Mcq Accuracy
0.0912	1.0	40	0.0979	0.9558	0.5778
0.0487	2.0	80	0.1067	0.9580	0.5556
0.0053	3.0	120	0.1562	0.9588	0.6
0.0192	4.0	160	0.2303	0.9579	0.5889
0.0077	5.0	200	0.2357	0.9565	0.5778

Framework versions

PEFT 0.18.1
Transformers 5.2.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

xummer/llama3-1-8b-belebele-lora-hat-latn

belebele_hat_Latn

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

xummer/
llama3-1-8b-belebele-lora-hat-latn