Hugging Face's logo

Ritvik19
/
zephyr-danube-sft-qlora

PEFT
Safetensors
mistral
alignment-handbook
Generated from Trainer
Model card Files Community
zephyr-danube-sft-qlora / README.md
Ritvik19's picture
Ritvik19
Update README.md
ff3defd verified
preview code
|
raw
history blame
1.41 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - alignment-handbook
  - generated_from_trainer
base_model: h2oai/h2o-danube-1.8b-base
datasets:
  - HuggingFaceH4/ultrachat_200k
model-index:
  - name: zephyr-danube-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-danube-sft-qlora

This model is a fine-tuned version of h2oai/h2o-danube-1.8b-base on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0893

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
1.0883 0.9998 1140 1.0893

Framework versions

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