You can deploy this model and start earning money today!

Jofthomas/
Llama-3-8B-function_calling

Name: Llama-3-8B-function_calling
Availability: InStock

generated_from_trainer

generator

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

adapter

other

Views

No views yet

Llama-3-8B-function_calling

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the generator dataset. It achieves the following results on the evaluation set:

Loss: 3.2600

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: 0.0005
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
3.2373	0.9999	3794	3.2600

Framework versions

PEFT 0.10.0
Transformers 4.40.2
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Jofthomas/Llama-3-8B-function_calling

Llama-3-8B-function_calling

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Jofthomas/
Llama-3-8B-function_calling