Edit model card

gemma-7b

This model is a fine-tuned version of google/gemma-7b on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4939
  • Accuracy: 0.0806
  • Precision: 0.4535
  • Recall: 0.3826
  • F1: 0.4150
  • Hamming Loss: 0.2312

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: 0.0001
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_ratio: 0.05
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • PEFT 0.5.0
  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
5
Inference Examples
Inference API (serverless) does not yet support peft models for this pipeline type.

Model tree for AndersGiovanni/gemma-7b-10-dim

Base model

google/gemma-7b
Adapter
(9012)
this model

Dataset used to train AndersGiovanni/gemma-7b-10-dim

Collection including AndersGiovanni/gemma-7b-10-dim