Instructions to use iTroned/targeted_baseline_v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use iTroned/targeted_baseline_v3 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("iTroned/targeted_baseline_v3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
targeted_baseline_v3
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1076
- Accuracy Targeted: 0.6296
- F1 Macro Targeted: 0.5493
- F1 Weighted Targeted: 0.5676
- F1 Macro Total: 0.5493
- F1 Weighted Total: 0.5676
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: 6e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 1337
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy Targeted | F1 Macro Targeted | F1 Weighted Targeted | F1 Macro Total | F1 Weighted Total |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 45 | 0.6826 | 0.4519 | 0.3112 | 0.2813 | 0.3112 | 0.2813 |
| No log | 2.0 | 90 | 0.6975 | 0.5481 | 0.3541 | 0.3882 | 0.3541 | 0.3882 |
| No log | 3.0 | 135 | 0.7052 | 0.5481 | 0.3541 | 0.3882 | 0.3541 | 0.3882 |
| No log | 4.0 | 180 | 0.7244 | 0.5481 | 0.3541 | 0.3882 | 0.3541 | 0.3882 |
| No log | 5.0 | 225 | 0.7422 | 0.5481 | 0.3541 | 0.3882 | 0.3541 | 0.3882 |
| No log | 6.0 | 270 | 0.7541 | 0.5481 | 0.3541 | 0.3882 | 0.3541 | 0.3882 |
| No log | 7.0 | 315 | 0.7346 | 0.5556 | 0.3719 | 0.4046 | 0.3719 | 0.4046 |
| No log | 8.0 | 360 | 0.8135 | 0.5630 | 0.3892 | 0.4206 | 0.3892 | 0.4206 |
| No log | 9.0 | 405 | 0.8147 | 0.5926 | 0.4646 | 0.4898 | 0.4646 | 0.4898 |
| No log | 10.0 | 450 | 0.8904 | 0.5778 | 0.4225 | 0.4513 | 0.4225 | 0.4513 |
| No log | 11.0 | 495 | 0.9292 | 0.5741 | 0.4264 | 0.4544 | 0.4264 | 0.4544 |
| 0.632 | 12.0 | 540 | 0.9412 | 0.5926 | 0.4881 | 0.5103 | 0.4881 | 0.5103 |
| 0.632 | 13.0 | 585 | 0.9978 | 0.5889 | 0.4673 | 0.4918 | 0.4673 | 0.4918 |
| 0.632 | 14.0 | 630 | 1.1020 | 0.5741 | 0.4264 | 0.4544 | 0.4264 | 0.4544 |
| 0.632 | 15.0 | 675 | 1.0806 | 0.5926 | 0.4837 | 0.5065 | 0.4837 | 0.5065 |
| 0.632 | 16.0 | 720 | 1.2255 | 0.5778 | 0.4285 | 0.4566 | 0.4285 | 0.4566 |
| 0.632 | 17.0 | 765 | 1.1076 | 0.6296 | 0.5493 | 0.5676 | 0.5493 | 0.5676 |
| 0.632 | 18.0 | 810 | 1.1627 | 0.6296 | 0.5458 | 0.5646 | 0.5458 | 0.5646 |
| 0.632 | 19.0 | 855 | 1.3126 | 0.5926 | 0.4696 | 0.4942 | 0.4696 | 0.4942 |
| 0.632 | 20.0 | 900 | 1.3914 | 0.5889 | 0.4623 | 0.4874 | 0.4623 | 0.4874 |
| 0.632 | 21.0 | 945 | 1.3736 | 0.6111 | 0.5050 | 0.5271 | 0.5050 | 0.5271 |
| 0.632 | 22.0 | 990 | 1.4834 | 0.5889 | 0.4519 | 0.4782 | 0.4519 | 0.4782 |
Framework versions
- Transformers 4.50.2
- Pytorch 2.6.0+cu124
- Datasets 3.0.1
- Tokenizers 0.21.1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support