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

Loss: 0.8017
Memory/max Mem Active(gib): 30.13
Memory/max Mem Allocated(gib): 30.13
Memory/device Mem Reserved(gib): 38.36

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use 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: 6
training_steps: 139

Training results

Training Loss	Epoch	Step	Validation Loss	Mem Active(gib)	Mem Allocated(gib)	Mem Reserved(gib)
No log	0	0	1.9778	25.3	25.3	27.25
0.8397	0.3597	50	0.8147	30.13	30.13	37.97
0.7795	0.7194	100	0.8017	30.13	30.13	38.36

Framework versions

PEFT 0.17.0
Transformers 4.55.2
Pytorch 2.6.0+cu124
Datasets 4.0.0
Tokenizers 0.21.4

mawiie/llama31-8b-sft-nigeria-wvs-lora

Llama-3.1-8B-Instruct Fine-tuned

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

mawiie/
llama31-8b-sft-nigeria-wvs-lora