metadata
base_model: clip-mixer-big
tags:
- generated_from_trainer
model-index:
- name: clip-mixer-big
results: []
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