Llama2-7B-lora-r-32-finetuned-epoch-4 – AI Model by Siqi-Hu | AlphaNeural AI

You can deploy this model and start earning money today!

Siqi-Hu/
Llama2-7B-lora-r-32-finetuned-epoch-4

like

0

generated_from_trainer

meta-llama/Llama-2-7b-hf

Views

No views yet

Llama2-7B-lora-r-32-finetuned-epoch-4

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.9852

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: 4
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.9752	0.3846	20	2.9097
2.7504	0.7692	40	2.4334
2.4683	1.1538	60	2.1800
2.3015	1.5385	80	2.0686
2.2178	1.9231	100	2.0257
2.1013	2.3077	120	1.9999
2.0749	2.6923	140	1.9843
1.9921	3.0769	160	1.9750
1.9127	3.4615	180	1.9839
1.9211	3.8462	200	1.9852

Framework versions

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