metadata
library_name: transformers
license: apache-2.0
base_model: allenai/longformer-base-4096
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: results
results: []
results
This model is a fine-tuned version of allenai/longformer-base-4096 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9265
- Accuracy: 0.881
- Precision: 0.8604
- Recall: 0.9788
- F1: 0.9158
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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.3194 | 1.0 | 157 | 0.4800 | 0.81 | 0.7827 | 0.9864 | 0.8728 |
| 0.2475 | 2.0 | 314 | 0.3097 | 0.88 | 0.8670 | 0.9667 | 0.9142 |
| 0.1697 | 3.0 | 471 | 0.5044 | 0.859 | 0.8291 | 0.9909 | 0.9028 |
| 0.0833 | 4.0 | 628 | 0.3149 | 0.911 | 0.9243 | 0.9425 | 0.9333 |
| 0.0582 | 5.0 | 785 | 0.5629 | 0.885 | 0.8709 | 0.9697 | 0.9177 |
| 0.029 | 6.0 | 942 | 0.7728 | 0.873 | 0.8541 | 0.9743 | 0.9102 |
| 0.0186 | 7.0 | 1099 | 1.0292 | 0.865 | 0.8355 | 0.9909 | 0.9066 |
| 0.0007 | 8.0 | 1256 | 0.9823 | 0.875 | 0.8508 | 0.9834 | 0.9123 |
| 0.0211 | 9.0 | 1413 | 0.8580 | 0.89 | 0.8708 | 0.9788 | 0.9217 |
| 0.0086 | 10.0 | 1570 | 0.9265 | 0.881 | 0.8604 | 0.9788 | 0.9158 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1