kykim0's picture
Upload folder using huggingface_hub
a74ed97 verified
metadata
base_model: meta-llama/Llama-2-7b-hf
tags:
  - alignment-handbook
  - generated_from_trainer
datasets:
  - HuggingFaceH4/ultrachat_200k
model-index:
  - name: Llama-2-7b-hf-sft-full-3e
    results: []

Llama-2-7b-hf-sft-full-3e

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9247

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: 16
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 512
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
0.931 0.7 285 0.9350
0.8672 1.7 570 0.9245
0.8189 2.7 855 0.9248

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.1.2
  • Datasets 2.14.6
  • Tokenizers 0.15.0