Edit model card

Built with Axolotl

qlora-out

This model is a fine-tuned version of microsoft/Orca-2-13b on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.5966

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: 0.0001
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 50
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss
1.645 0.23 100 1.6467
1.6459 0.45 200 1.6197
1.5916 0.68 300 1.6115
1.3587 0.9 400 1.6088
1.5232 1.12 500 1.6029
1.7568 1.34 600 1.6010
1.6536 1.57 700 1.5978
1.7821 1.8 800 1.5966

Framework versions

  • Transformers 4.35.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.7
  • Tokenizers 0.14.1
Downloads last month
9
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Quantized from