juyongjiang's picture
upload model checkpoint
2e4c345 verified
metadata
library_name: peft
tags:
  - alignment-handbook
  - generated_from_trainer
datasets:
  - llama-duo/synth_summarize_dataset_dedup
base_model: google/gemma-7b
model-index:
  - name: gemma7b-summarize-gemini1_5flash-32k
    results: []

gemma7b-summarize-gemini1_5flash-32k

This model is a fine-tuned version of google/gemma-7b on the llama-duo/synth_summarize_dataset_dedup dataset. It achieves the following results on the evaluation set:

  • Loss: 2.5408

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: 4
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • total_eval_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss
7.4587 1.0 52 4.9639
1.2656 2.0 104 2.7099
1.1018 3.0 156 2.5878
1.0198 4.0 208 2.5538
0.9682 5.0 260 2.5424
0.9349 6.0 312 2.5212
0.9093 7.0 364 2.5261
0.906 8.0 416 2.5334
0.9005 9.0 468 2.5352
0.8909 10.0 520 2.5408

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.0
  • Pytorch 2.1.2+cu121
  • Datasets 2.18.0
  • Tokenizers 0.19.1