This model is a fine-tuned version of meta-llama/Llama-3.2-3B on the cpt_jazz_pretrain dataset. It achieves the following results on the evaluation set:

Loss: 1.8438

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: 5e-05
train_batch_size: 2
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 32
total_train_batch_size: 256
total_eval_batch_size: 4
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_ratio: 0.03
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.9893	0.1588	200	1.9929
1.9542	0.3175	400	1.9551
1.9094	0.4763	600	1.9184
1.8666	0.6350	800	1.8803
1.8491	0.7938	1000	1.8529
1.8335	0.9525	1200	1.8440

Framework versions

Transformers 4.56.2
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1

ramzanniaz331/Llama-3.2-3B-full-pretrain-2048

full_pretrain

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

ramzanniaz331/
Llama-3.2-3B-full-pretrain-2048