Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
WeniGPT-2.0.1-Zephyr-7B-bits_and_bytes-dataset-llm-base-1.0.1 – AI Model by Weni | AlphaNeural AI
You can deploy this model and start earning money today!
Weni
/
WeniGPT-2.0.1-Zephyr-7B-bits_and_bytes-dataset-llm-base-1.0.1
like
0
peft
safetensors
mistral
trl
sft
generated_from_trainer
generator
HuggingFaceH4/zephyr-7b-beta
adapter
mit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
WeniGPT-2.0.1-Zephyr-7B-bits_and_bytes-llm-base
This model is a fine-tuned version of
HuggingFaceH4/zephyr-7b-beta
on the generator dataset. It achieves the following results on the evaluation set:
Loss: 0.3610
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: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 5
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
0.4038
1.53
500
0.3728
0.3482
3.07
1000
0.3628
0.3266
4.6
1500
0.3610
Framework versions
PEFT 0.7.1
Transformers 4.36.2
Pytorch 2.0.1+cu118
Datasets 2.16.0
Tokenizers 0.15.0
