clip-br-100k / README.md
bilbo991's picture
update model card README.md
a63df14
---
base_model: clip-br-100k
tags:
- generated_from_trainer
model-index:
- name: clip-br-100k
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# clip-br-100k
This model is a fine-tuned version of [clip-br-100k](https://huggingface.co/clip-br-100k) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.8675
## 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.7977 | 1.0 | 3125 | 3.0236 |
| 2.2202 | 2.0 | 6250 | 2.8675 |
| 1.4086 | 3.0 | 9375 | 3.1403 |
### Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.1
- Tokenizers 0.13.3