Llama3-8B-lora-r-32-generic-epoch-5-labels_40.0 – AI Model by Siqi-Hu | AlphaNeural AI

You can deploy this model and start earning money today!

Siqi-Hu/
Llama3-8B-lora-r-32-generic-epoch-5-labels_40.0

like

0

generated_from_trainer

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

Views

No views yet

Llama3-8B-lora-r-32-generic-epoch-5-labels_40.0

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

Loss: 2.7063

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: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
4.9819	0.4348	20	4.8000
4.2687	0.8696	40	4.0327
3.7192	1.3043	60	3.5718
3.3579	1.7391	80	3.2549
3.0728	2.1739	100	3.0341
2.8592	2.6087	120	2.8915
2.7385	3.0435	140	2.8108
2.5793	3.4783	160	2.7529
2.5261	3.9130	180	2.7187
2.394	4.3478	200	2.7112
2.3941	4.7826	220	2.7063

Framework versions

PEFT 0.15.2
Transformers 4.45.2
Pytorch 2.5.0+cu121
Datasets 3.2.0
Tokenizers 0.20.3