Edit model card

Training Details

Training Data

Training Hyperparameters

  • model: phi3
  • config: tv2o-medium
  • max-len: 2048
  • lr: 1e-4 then 2e-5
  • weight-decay: 0.01
  • batch-size-per-gpu: 8
  • GPUs: 2 A100 80gb
  • bfloat16 precision

Loss

  • val loss: 0.2740

Files

  • model.ckpt: latest model checkpoint
Downloads last month
45
Inference API
Unable to determine this model's library. Check the docs .

Dataset used to train breadlicker45/bread-tv2o-medium

Space using breadlicker45/bread-tv2o-medium 1