Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
pgd_mistral_8bits_lr0.0008_bs3_ep4_alpha16_rk8_do1.0e-01_wd8.0e-05 – AI Model by nelkh | AlphaNeural AI
You can deploy this model and start earning money today!
nelkh
/
pgd_mistral_8bits_lr0.0008_bs3_ep4_alpha16_rk8_do1.0e-01_wd8.0e-05
like
0
peft
safetensors
generated_from_trainer
mistralai/Mistral-7B-Instruct-v0.3
adapter
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
pgd_mistral_8bits_lr0.0008_bs3_ep4_alpha16_rk8_do1.0e-01_wd8.0e-05
This model is a fine-tuned version of
mistralai/Mistral-7B-Instruct-v0.3
on the None dataset. It achieves the following results on the evaluation set:
Loss: 0.8441
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: 0.0008
train_batch_size: 3
eval_batch_size: 3
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 12
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 20
num_epochs: 4
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
2.066
0.9778
22
1.0233
0.8429
2.0
45
0.8696
0.8258
2.9778
67
0.8511
0.7691
3.9111
88
0.8441
Framework versions
PEFT 0.12.0
Transformers 4.42.4
Pytorch 2.4.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1
