metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - unsup-wc
model-index:
  - name: contrastive-unsup-wc-pixel-base-mean-64-128-1-3e-6-7600-42-eval
    results: []

contrastive-unsup-wc-pixel-base-mean-64-128-1-3e-6-7600-42-eval

This model is a fine-tuned version of Team-PIXEL/pixel-base on the UNSUP-WC dataset.

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: 3e-06
train_batch_size: 128
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 7600

Training results

Framework versions

Transformers 4.17.0
Pytorch 1.11.0
Datasets 2.14.7.dev0
Tokenizers 0.14.1