Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
WeniGPT-2.1.1-zephyr-7b-beta-BitsandBytes-LLM-Base-1.0.1-6k_Random_selection – AI Model by Weni | AlphaNeural AI
You can deploy this model and start earning money today!
Weni
/
WeniGPT-2.1.1-zephyr-7b-beta-BitsandBytes-LLM-Base-1.0.1-6k_Random_selection
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-2.1.1-zephyr-7b-beta-BitsandBytes-LLM-Base-1.0.1-6k_Random_selection
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: 0.4532
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: 16
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
training_steps: 42
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
No log
0.99
34
0.4548
No log
1.22
42
0.4532
Framework versions
PEFT 0.7.1
Transformers 4.37.0.dev0
Pytorch 2.1.0+cu118
Datasets 2.16.1
Tokenizers 0.15.0
