---
license: apache-2.0
base_model: allenai/longformer-base-4096
tags:
- generated_from_trainer
datasets:
- fancy_dataset
metrics:
- accuracy
model-index:
- name: longformer-one-step
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: fancy_dataset
      type: fancy_dataset
      config: sep_tok
      split: test
      args: sep_tok
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8691844007060312
---

<!-- 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-one-step

This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the fancy_dataset dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3013
- Claim: {'precision': 0.5698178664353859, 'recall': 0.4524793388429752, 'f1-score': 0.5044145873320538, 'support': 4356.0}
- Majorclaim: {'precision': 0.7584043030031377, 'recall': 0.775435380384968, 'f1-score': 0.7668252889191027, 'support': 2182.0}
- O: {'precision': 0.9997360084477297, 'recall': 0.9971912577898709, 'f1-score': 0.9984620116887112, 'support': 11393.0}
- Premise: {'precision': 0.8536961381330456, 'recall': 0.9155919312169312, 'f1-score': 0.8835613706170967, 'support': 12096.0}
- Accuracy: 0.8692
- Macro avg: {'precision': 0.7954135790048247, 'recall': 0.7851744770586864, 'f1-score': 0.7883158146392412, 'support': 30027.0}
- Weighted avg: {'precision': 0.8610006209893659, 'recall': 0.8691844007060312, 'f1-score': 0.8636719872446065, 'support': 30027.0}

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Claim                                                                                                               | Majorclaim                                                                                                         | O                                                                                                                   | Premise                                                                                                             | Accuracy | Macro avg                                                                                                           | Weighted avg                                                                                                        |
|:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|:--------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|
| No log        | 1.0   | 41   | 0.4523          | {'precision': 0.4538361508452536, 'recall': 0.16023875114784206, 'f1-score': 0.2368510349507974, 'support': 4356.0} | {'precision': 0.6438781852082038, 'recall': 0.4747937671860678, 'f1-score': 0.5465576365075178, 'support': 2182.0} | {'precision': 0.961874840791373, 'recall': 0.9942947423856754, 'f1-score': 0.9778161415623651, 'support': 11393.0}  | {'precision': 0.7773290074819572, 'recall': 0.970568783068783, 'f1-score': 0.8632670318761719, 'support': 12096.0}  | 0.8260   | {'precision': 0.7092295460816969, 'recall': 0.6499740109470921, 'f1-score': 0.656122961224213, 'support': 30027.0}  | {'precision': 0.7907238221881672, 'recall': 0.8259899423851866, 'f1-score': 0.7928414157091711, 'support': 30027.0} |
| No log        | 2.0   | 82   | 0.3203          | {'precision': 0.5346471710108074, 'recall': 0.38613406795224975, 'f1-score': 0.4484137563316448, 'support': 4356.0} | {'precision': 0.8060538116591929, 'recall': 0.6590284142988084, 'f1-score': 0.7251638930912757, 'support': 2182.0} | {'precision': 0.9997357759379955, 'recall': 0.9963135258492056, 'f1-score': 0.9980217171495142, 'support': 11393.0} | {'precision': 0.8241286473113585, 'recall': 0.9363425925925926, 'f1-score': 0.8766593134409226, 'support': 12096.0} | 0.8591   | {'precision': 0.7911413514798384, 'recall': 0.7444546501732141, 'f1-score': 0.7620646700033393, 'support': 30027.0} | {'precision': 0.8474500385354251, 'recall': 0.8591267858926965, 'f1-score': 0.8495730647807515, 'support': 30027.0} |
| No log        | 3.0   | 123  | 0.3013          | {'precision': 0.5698178664353859, 'recall': 0.4524793388429752, 'f1-score': 0.5044145873320538, 'support': 4356.0}  | {'precision': 0.7584043030031377, 'recall': 0.775435380384968, 'f1-score': 0.7668252889191027, 'support': 2182.0}  | {'precision': 0.9997360084477297, 'recall': 0.9971912577898709, 'f1-score': 0.9984620116887112, 'support': 11393.0} | {'precision': 0.8536961381330456, 'recall': 0.9155919312169312, 'f1-score': 0.8835613706170967, 'support': 12096.0} | 0.8692   | {'precision': 0.7954135790048247, 'recall': 0.7851744770586864, 'f1-score': 0.7883158146392412, 'support': 30027.0} | {'precision': 0.8610006209893659, 'recall': 0.8691844007060312, 'f1-score': 0.8636719872446065, 'support': 30027.0} |


### Framework versions

- Transformers 4.37.1
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1