llama_2_alpaca_helpful – AI Model by CharlesLi | AlphaNeural AI

You can deploy this model and start earning money today!

CharlesLi/
llama_2_alpaca_helpful

like

0

alignment-handbook

generated_from_trainer

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

Views

No views yet

llama_2_alpaca_helpful

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

Loss: 0.7725

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: 4
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 2
total_train_batch_size: 16
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
training_steps: 50

Training results

Training Loss	Epoch	Step	Validation Loss
2.0822	0.7692	5	2.1225
1.2508	1.5385	10	1.1862
0.9991	2.3077	15	0.9066
0.9464	3.0769	20	0.8430
0.8294	3.8462	25	0.7977
0.7715	4.6154	30	0.7767
0.7379	5.3846	35	0.7684
0.6983	6.1538	40	0.7742
0.7095	6.9231	45	0.7737
0.6622	7.6923	50	0.7725

Framework versions

PEFT 0.12.0
Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.19.1