metadata
library_name: transformers
license: apache-2.0
base_model: alex-miller/ODABert
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: cva-flow-weighted-classifier2
results: []
cva-flow-weighted-classifier2
This model is a fine-tuned version of alex-miller/ODABert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3914
- Accuracy: 0.9236
- F1: 0.9453
- Precision: 0.9694
- Recall: 0.9223
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: 4e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.5521 | 1.0 | 18 | 0.3662 | 0.7986 | 0.8432 | 0.9512 | 0.7573 |
| 0.3114 | 2.0 | 36 | 0.4227 | 0.8125 | 0.8508 | 0.9872 | 0.7476 |
| 0.1924 | 3.0 | 54 | 0.2520 | 0.9167 | 0.9394 | 0.9789 | 0.9029 |
| 0.0878 | 4.0 | 72 | 0.3462 | 0.9097 | 0.9340 | 0.9787 | 0.8932 |
| 0.0506 | 5.0 | 90 | 0.3421 | 0.9028 | 0.93 | 0.9588 | 0.9029 |
| 0.0467 | 6.0 | 108 | 0.3557 | 0.9097 | 0.9347 | 0.9688 | 0.9029 |
| 0.0157 | 7.0 | 126 | 0.3753 | 0.9306 | 0.9505 | 0.9697 | 0.9320 |
| 0.0189 | 8.0 | 144 | 0.3314 | 0.9306 | 0.9495 | 0.9895 | 0.9126 |
| 0.0054 | 9.0 | 162 | 0.3842 | 0.9236 | 0.9453 | 0.9694 | 0.9223 |
| 0.0065 | 10.0 | 180 | 0.3914 | 0.9236 | 0.9453 | 0.9694 | 0.9223 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0