<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
Longformer-finetuned-comp5
This model is a fine-tuned version of allenai/longformer-base-4096 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8180
- Precision: 0.5680
- Recall: 0.7490
- F1: 0.6430
- Accuracy: 0.6430
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
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.8296 | 1.0 | 1012 | 0.5801 | 0.4806 | 0.6633 | 0.5448 | 0.5448 |
| 0.5367 | 2.0 | 2024 | 0.5386 | 0.5617 | 0.7042 | 0.6172 | 0.6172 |
| 0.4109 | 3.0 | 3036 | 0.5755 | 0.5590 | 0.7261 | 0.6248 | 0.6248 |
| 0.3088 | 4.0 | 4048 | 0.6167 | 0.5775 | 0.7394 | 0.6435 | 0.6435 |
| 0.2234 | 5.0 | 5060 | 0.7098 | 0.5626 | 0.7477 | 0.6370 | 0.6370 |
| 0.1637 | 6.0 | 6072 | 0.7399 | 0.5742 | 0.7413 | 0.6438 | 0.6438 |
| 0.1236 | 7.0 | 7084 | 0.8180 | 0.5680 | 0.7490 | 0.6430 | 0.6430 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6
