Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Fine-tuned-Zephyr7B – AI Model by HugThang | AlphaNeural AI
You can deploy this model and start earning money today!
HugThang
/
Fine-tuned-Zephyr7B
like
0
peft
tensorboard
safetensors
trl
sft
generated_from_trainer
TheBloke/zephyr-7B-beta-GPTQ
adapter
mit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Fine-tuned-Zephyr7B
This model is a fine-tuned version of
TheBloke/zephyr-7B-beta-GPTQ
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.7121
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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
training_steps: 100
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
0.9911
0.0186
50
0.7504
0.7259
0.0372
100
0.7121
Framework versions
PEFT 0.10.0
Transformers 4.40.1
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.19.1
