gemma-7b-10-dim / README.md
AndersGiovanni's picture
Update README.md
72a8eca verified
|
raw
history blame
1.4 kB
metadata
license: mit
base_model: google/gemma-7b
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: gemma-7b
    results: []
library_name: peft
datasets:
  - AndersGiovanni/10-dim
language:
  - en
pipeline_tag: text-classification

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