Horoscope Model Tiny - finetuned on weather
This model is a fine-tuned version of iulik-pisik/horoscope_model_tiny on the Vreme ProTV dataset. It achieves the following results on the evaluation set:
- Loss: 0.2868
- Wer: 13.9951
Model description
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- 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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0443 | 6.02 | 1000 | 0.1949 | 15.5569 |
| 0.0023 | 12.05 | 2000 | 0.2601 | 14.1389 |
| 0.0008 | 18.07 | 3000 | 0.2798 | 14.0362 |
| 0.0006 | 24.1 | 4000 | 0.2868 | 13.9951 |
Framework versions
- Transformers 4.39.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 8
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.