This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on the marsyas/gtzan dataset. It achieves the following results on the evaluation set:

Loss: 1.3441

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: 1e-05
train_batch_size: 4
eval_batch_size: 2
seed: 42
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

Training results

Training Loss	Epoch	Step	Validation Loss
1.4573	0.8333	40	1.1830
0.6112	1.6667	80	0.9472
0.3228	2.5	120	1.0455
0.2166	3.3333	160	1.2302
0.1909	4.1667	200	1.1505
0.1657	5.0	240	1.1343
0.1434	5.8333	280	1.1638
0.138	6.6667	320	1.2728
0.1304	7.5	360	1.3117
0.1223	8.3333	400	1.3209
0.1218	9.1667	440	1.3353
0.1147	10.0	480	1.3441

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0

Erioh/fine-tuned-model

Erioh/finetuned-model

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Erioh/
fine-tuned-model