clip-mixer-big

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

• Loss: 1.1063

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

Training Loss	Epoch	Step	Validation Loss
1.5067	1.0	68750	1.6837
1.1444	2.0	137500	1.3133
0.7653	3.0	206250	1.1063

Framework versions

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