metadata
license: mit
base_model: microsoft/xclip-base-patch32
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: xclip-base-patch32-finetuned-SLT-subset
results: []
xclip-base-patch32-finetuned-SLT-subset
This model is a fine-tuned version of microsoft/xclip-base-patch32 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.2063
- Accuracy: 0.05
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 80
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 5.3738 | 0.25 | 20 | 3.2214 | 0.05 |
| 4.0026 | 1.25 | 40 | 3.1167 | 0.05 |
| 3.3822 | 2.25 | 60 | 3.0319 | 0.05 |
| 3.1538 | 3.25 | 80 | 3.0141 | 0.05 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3