<!-- 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-norm
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: 0.8127
- Precision: 0.8429
- Recall: 0.8701
- F1: 0.8562
- Accuracy: 0.8221
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 |
|---|---|---|---|---|---|---|---|
| 0.8008 | 1.0 | 1012 | 0.5839 | 0.8266 | 0.8637 | 0.8447 | 0.8084 |
| 0.5168 | 2.0 | 2024 | 0.5927 | 0.7940 | 0.9102 | 0.8481 | 0.8117 |
| 0.3936 | 3.0 | 3036 | 0.5651 | 0.8476 | 0.8501 | 0.8488 | 0.8143 |
| 0.2939 | 4.0 | 4048 | 0.6411 | 0.8494 | 0.8578 | 0.8536 | 0.8204 |
| 0.2165 | 5.0 | 5060 | 0.6833 | 0.8409 | 0.8822 | 0.8611 | 0.8270 |
| 0.1561 | 6.0 | 6072 | 0.7643 | 0.8404 | 0.8810 | 0.8602 | 0.8259 |
| 0.1164 | 7.0 | 7084 | 0.8127 | 0.8429 | 0.8701 | 0.8562 | 0.8221 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6
