You can deploy this model and start earning money today!

jhkim64/
Llama-3.1-8B-Instruct-lora-finetuned-fol

Name: Llama-3.1-8B-Instruct-lora-finetuned-fol
Availability: InStock

generated_from_trainer

meta-llama/Llama-3.1-8B-Instruct

adapter

llama3.1

Views

No views yet

Llama-3.1-8B-Instruct-lora-finetuned-fol

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

Loss: 0.2384

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: 2
eval_batch_size: 8
seed: 42
optimizer: Use paged_adamw_32bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
lr_scheduler_warmup_ratio: 0.05
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
0.1628	1.0	1211	0.2254
0.1627	2.0	2422	0.2023
0.1264	3.0	3633	0.1923
0.0973	4.0	4844	0.1930
0.0934	5.0	6055	0.1903
0.0845	6.0	7266	0.1922
0.0716	7.0	8477	0.2055
0.0679	8.0	9688	0.2116
0.0714	9.0	10899	0.2072
0.062	10.0	12110	0.2181
0.0649	11.0	13321	0.2182
0.0589	12.0	14532	0.2262
0.0614	13.0	15743	0.2226
0.0645	14.0	16954	0.2239
0.0566	15.0	18165	0.2384

Framework versions

PEFT 0.10.0
Transformers 4.47.0
Pytorch 2.5.1+cu124
Datasets 2.19.0
Tokenizers 0.21.0

jhkim64/Llama-3.1-8B-Instruct-lora-finetuned-fol

Llama-3.1-8B-Instruct-lora-finetuned-fol

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jhkim64/
Llama-3.1-8B-Instruct-lora-finetuned-fol