Edit model card

gemma2b-summarize-gemini1_5flash-4k

This model is a fine-tuned version of google/gemma-2b on the llama-duo/synth_summarize_dataset_dedup dataset. It achieves the following results on the evaluation set:

  • Loss: 2.5520

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
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • total_eval_batch_size: 32
  • 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
2.9598 1.0 7 3.0819
2.584 2.0 14 2.7799
1.8743 3.0 21 2.6390
1.6598 4.0 28 2.6231
1.4458 5.0 35 2.5861
1.3889 6.0 42 2.5646
1.3527 7.0 49 2.5569
1.2936 8.0 56 2.5532
1.2855 9.0 63 2.5514
1.2802 10.0 70 2.5520

Framework versions

  • PEFT 0.11.1
  • Transformers 4.40.1
  • Pytorch 2.2.0+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1
Downloads last month
1
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for llama-duo/gemma2b-summarize-gemini1_5flash-4k

Base model

google/gemma-2b
Adapter
(23172)
this model

Dataset used to train llama-duo/gemma2b-summarize-gemini1_5flash-4k

Collection including llama-duo/gemma2b-summarize-gemini1_5flash-4k