Haimee's picture
End of training
5ad536e verified
|
raw
history blame
1.27 kB
metadata
license: mit
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: TheBloke/zephyr-7B-alpha-GPTQ
model-index:
  - name: zephyr-support-mitigation_new
    results: []

zephyr-support-mitigation_new

This model is a fine-tuned version of TheBloke/zephyr-7B-alpha-GPTQ on the None 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: 0.0002
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 5
  • total_train_batch_size: 40
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • training_steps: 500
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • PEFT 0.10.0
  • Transformers 4.39.1
  • Pytorch 2.1.0a0+29c30b1
  • Datasets 2.18.0
  • Tokenizers 0.15.2