Ritvik19's picture
Update README.md
4d2c720 verified
metadata
license: mit
library_name: peft
tags:
  - alignment-handbook
  - generated_from_trainer
base_model: microsoft/phi-1_5
datasets:
  - HuggingFaceH4/ultrachat_200k
model-index:
  - name: zephyr-phi-1_5-sft-qlora
    results: []

Note: This model card has been generated automatically according to the information the Trainer had access to. Visit the model card to see the full description.

zephyr-phi-1_5-sft-qlora

This model is a fine-tuned version of microsoft/phi-1_5 on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:

  • Loss: 1.3434

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
  • gradient_accumulation_steps: 128
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
1.3423 0.9998 999 1.3434

Framework versions

  • PEFT 0.7.1
  • Transformers 4.40.1
  • Pytorch 2.1.2+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1