You can deploy this model and start earning money today!

TripleH/
Meta-Llama-3-8B-Instruct-qlora-modular

Name: Meta-Llama-3-8B-Instruct-qlora-modular
Availability: InStock

meta-llama/Meta-Llama-3-8B-Instruct

llama3

Views

No views yet

Meta-Llama-3-8B-Instruct-qlora-modular

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.8659

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: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
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
lr_scheduler_warmup_steps: 100
num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss
4.6094	1.0	12	3.7667
2.7371	2.0	24	1.5328
1.1169	3.0	36	1.0226
0.7548	4.0	48	0.9537
0.4412	5.0	60	0.9135
0.2324	6.0	72	0.8659

Framework versions

PEFT 0.16.0
Transformers 4.53.1
Pytorch 2.6.0+cu124
Datasets 2.14.4
Tokenizers 0.21.2

TripleH/Meta-Llama-3-8B-Instruct-qlora-modular

Meta-Llama-3-8B-Instruct-qlora-modular

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

TripleH/
Meta-Llama-3-8B-Instruct-qlora-modular