adarshxs's picture
Update README.md
54c40b3
metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1

Tensoic - Mistral-7B-v0.1-alpaca-2k-test

Our first fine tune of the Mistral 7B on the Alpaca-2k-test dataset. Feel free to play around!

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0002
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • total_eval_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 3

Framework versions

  • Transformers 4.34.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.14.0