You can deploy this model and start earning money today!

hurtmongoose/
llama3.2-adalora-rank8-single

Name: llama3.2-adalora-rank8-single
Availability: InStock

meta-llama/Llama-3.2-3B-Instruct

llama3.2

Views

No views yet

llama3.2-adalora-rank8-single

This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.4219
Accuracy: 0.8983
Mcc: 0.7990
Recall: 0.86
Fpr: 0.0633
Auc: 0.9535

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: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
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: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Mcc	Recall	Fpr	Auc
1.1176	1.0	313	0.3560	0.8933	0.7873	0.8733	0.0867	0.9550
1.0387	2.0	626	0.3078	0.905	0.8104	0.89	0.08	0.9663
0.6005	3.0	939	0.4986	0.9083	0.8229	0.8467	0.03	0.9690
0.4207	4.0	1252	0.7503	0.8883	0.7881	0.8033	0.0267	0.9686
0.1613	5.0	1565	0.6694	0.895	0.7982	0.8233	0.0333	0.9706

Framework versions

PEFT 0.18.0
Transformers 4.57.3
Pytorch 2.9.1+cu128
Datasets 2.15.0
Tokenizers 0.22.1

hurtmongoose/llama3.2-adalora-rank8-single

llama3.2-adalora-rank8-single

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

hurtmongoose/
llama3.2-adalora-rank8-single