Hugging Face's logo

tdross
/
mistral_base_compare

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
mistral_base_compare / README.md
tdross's picture
tdross
End of training
0f86fd9
preview code
|
raw
history blame
1.52 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: mistralai/Mistral-7B-Instruct-v0.2
model-index:
  - name: mistral_base_compare
    results: []

mistral_base_compare

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3114

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: 4
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_steps: 0.03
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
0.674 0.07 22 0.5538
0.4119 1.07 44 0.3594
0.3298 2.07 66 0.3114

Framework versions

  • PEFT 0.7.1
  • Transformers 4.37.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.15.0
  • Tokenizers 0.15.0