Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Llama-3-8B-qlora-adapter – AI Model by zhangjie6 | AlphaNeural AI
You can deploy this model and start earning money today!
zhangjie6
/
Llama-3-8B-qlora-adapter
like
0
peft
safetensors
trl
sft
generated_from_trainer
meta-llama/Meta-Llama-3-8B
adapter
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Visualize in Weights & Biases
Llama-3-8B-qlora-adapter
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: 0.5384
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: 0.0001
train_batch_size: 6
eval_batch_size: 6
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 24
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
1.5779
0.2395
10
1.0884
0.855
0.4790
20
0.6652
0.5649
0.7186
30
0.5557
0.5273
0.9581
40
0.5384
Framework versions
PEFT 0.11.1
Transformers 4.42.3
Pytorch 2.1.2
Datasets 2.20.0
Tokenizers 0.19.1
