clip-homer / README.md
bilbo991's picture
update model card README.md
59e6617
|
raw
history blame
1.09 kB
metadata
base_model: clip-homer
tags:
  - generated_from_trainer
model-index:
  - name: clip-homer
    results: []

clip-homer

This model is a fine-tuned version of clip-homer on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4658

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: 5e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.1
  • Tokenizers 0.13.3