zephyr-2b-gemma-dft / README.md
ale-bay's picture
Model save
75ee381 verified
|
raw
history blame
1.29 kB
metadata
tags:
  - trl
  - sft
  - generated_from_trainer
datasets:
  - generator
model-index:
  - name: zephyr-2b-gemma-dft
    results: []

Visualize in Weights & Biases

zephyr-2b-gemma-dft

This model was trained from scratch on the generator dataset.

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 0

Training results

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1