Qwen2-7B-Instruct / README.md
sanjay920's picture
Upload folder using huggingface_hub
bed0be1 verified
|
raw
history blame
809 Bytes


run1_short_20000

This model is a fine-tuned version of Qwen/Qwen2-7B-Instruct on the rubra_train_v1_qwen_short dataset.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 1
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 20
  • total_train_batch_size: 20
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 1.0

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.1+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1