meta_data/README_s42_e7.md

---
license: apache-2.0
base_model: allenai/longformer-base-4096
tags:
- generated_from_trainer
datasets:
- essays_su_g
metrics:
- accuracy
model-index:
- name: longformer-sep_tok
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: essays_su_g
      type: essays_su_g
      config: sep_tok
      split: train[80%:100%]
      args: sep_tok
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8963474162598889
---

<!-- 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-sep_tok

This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the essays_su_g dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2715
- Claim: {'precision': 0.6254587155963303, 'recall': 0.6542706333973128, 'f1-score': 0.6395403377110694, 'support': 4168.0}
- Majorclaim: {'precision': 0.8875878220140515, 'recall': 0.8805762081784386, 'f1-score': 0.8840681128994634, 'support': 2152.0}
- O: {'precision': 0.9999116061168567, 'recall': 1.0, 'f1-score': 0.9999558011049724, 'support': 11312.0}
- Premise: {'precision': 0.8987139615028998, 'recall': 0.8856125238134681, 'f1-score': 0.8921151439299123, 'support': 12073.0}
- Accuracy: 0.8963
- Macro avg: {'precision': 0.8529180263075345, 'recall': 0.8551148413473049, 'f1-score': 0.8539198489113544, 'support': 29705.0}
- Weighted avg: {'precision': 0.8981038432990452, 'recall': 0.8963474162598889, 'f1-score': 0.8971595644270212, 'support': 29705.0}

## 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: 7

### Training results

| Training Loss | Epoch | Step | Validation Loss | Claim                                                                                                               | Majorclaim                                                                                                         | O                                                                                                                   | Premise                                                                                                             | Accuracy | Macro avg                                                                                                           | Weighted avg                                                                                                        |
|:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|:--------:|:-------------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|
| No log        | 1.0   | 41   | 0.3907          | {'precision': 0.4622047244094488, 'recall': 0.28166986564299423, 'f1-score': 0.3500298151460942, 'support': 4168.0} | {'precision': 0.6884593519044911, 'recall': 0.5627323420074349, 'f1-score': 0.6192789567885452, 'support': 2152.0} | {'precision': 0.9988159213043082, 'recall': 0.9694130127298444, 'f1-score': 0.9838948454533218, 'support': 11312.0} | {'precision': 0.8006515561100714, 'recall': 0.9567630249316657, 'f1-score': 0.8717735849056604, 'support': 12073.0} | 0.8383   | {'precision': 0.7375328884320799, 'recall': 0.6926445613279848, 'f1-score': 0.7062443005734054, 'support': 29705.0} | {'precision': 0.8204984263709232, 'recall': 0.838310048813331, 'f1-score': 0.8229710003996594, 'support': 29705.0}  |
| No log        | 2.0   | 82   | 0.2736          | {'precision': 0.6199246546672248, 'recall': 0.3553262955854127, 'f1-score': 0.45173097453103556, 'support': 4168.0} | {'precision': 0.7746005046257359, 'recall': 0.8559479553903345, 'f1-score': 0.8132450331125828, 'support': 2152.0} | {'precision': 0.9999114103472715, 'recall': 0.9977899575671852, 'f1-score': 0.9988495575221238, 'support': 11312.0} | {'precision': 0.8387545787545787, 'recall': 0.9483144206079682, 'f1-score': 0.8901761069859658, 'support': 12073.0} | 0.8773   | {'precision': 0.8082977870987028, 'recall': 0.7893446572877252, 'f1-score': 0.7885004180379269, 'support': 29705.0} | {'precision': 0.8647725349186985, 'recall': 0.87725972058576, 'f1-score': 0.8644672730999988, 'support': 29705.0}   |
| No log        | 3.0   | 123  | 0.2407          | {'precision': 0.6129186602870813, 'recall': 0.6146833013435701, 'f1-score': 0.6137997125059894, 'support': 4168.0}  | {'precision': 0.7996618765849535, 'recall': 0.879182156133829, 'f1-score': 0.8375387339530764, 'support': 2152.0}  | {'precision': 0.9999115904871364, 'recall': 0.9998231966053748, 'f1-score': 0.9998673915926268, 'support': 11312.0} | {'precision': 0.9024307900067522, 'recall': 0.8856125238134681, 'f1-score': 0.8939425609297271, 'support': 12073.0} | 0.8906   | {'precision': 0.8287307293414808, 'recall': 0.8448252944740605, 'f1-score': 0.836287099745355, 'support': 29705.0}  | {'precision': 0.8914850757054159, 'recall': 0.890624473994277, 'f1-score': 0.8908860134318254, 'support': 29705.0}  |
| No log        | 4.0   | 164  | 0.2498          | {'precision': 0.6335050149091895, 'recall': 0.560700575815739, 'f1-score': 0.5948835433371515, 'support': 4168.0}   | {'precision': 0.8946840521564694, 'recall': 0.828996282527881, 'f1-score': 0.8605885190545105, 'support': 2152.0}  | {'precision': 0.9999116061168567, 'recall': 1.0, 'f1-score': 0.9999558011049724, 'support': 11312.0}                | {'precision': 0.872137855063341, 'recall': 0.9180816698417957, 'f1-score': 0.894520216286014, 'support': 12073.0}   | 0.8927   | {'precision': 0.8500596320614642, 'recall': 0.8269446320463539, 'f1-score': 0.8374870199456621, 'support': 29705.0} | {'precision': 0.8889456116800479, 'recall': 0.8926780003366437, 'f1-score': 0.890170129437975, 'support': 29705.0}  |
| No log        | 5.0   | 205  | 0.2543          | {'precision': 0.6193029490616622, 'recall': 0.6650671785028791, 'f1-score': 0.6413697362332255, 'support': 4168.0}  | {'precision': 0.8613728129205922, 'recall': 0.8921933085501859, 'f1-score': 0.8765122118237845, 'support': 2152.0} | {'precision': 0.9999115592111082, 'recall': 0.9994695898161244, 'f1-score': 0.9996905256642645, 'support': 11312.0} | {'precision': 0.9060976652698195, 'recall': 0.8775780667605401, 'f1-score': 0.8916098628292518, 'support': 12073.0} | 0.8952   | {'precision': 0.8466712466157955, 'recall': 0.8585770359074323, 'f1-score': 0.8522955841376315, 'support': 29705.0} | {'precision': 0.8983418837129342, 'recall': 0.8952364921730348, 'f1-score': 0.8965624790680554, 'support': 29705.0} |
| No log        | 6.0   | 246  | 0.2768          | {'precision': 0.6175036567528035, 'recall': 0.607725527831094, 'f1-score': 0.6125755743651752, 'support': 4168.0}   | {'precision': 0.9085303186022611, 'recall': 0.8215613382899628, 'f1-score': 0.8628599316739872, 'support': 2152.0} | {'precision': 0.9999116061168567, 'recall': 1.0, 'f1-score': 0.9999558011049724, 'support': 11312.0}                | {'precision': 0.8816429034348672, 'recall': 0.9014329495568624, 'f1-score': 0.8914281033706025, 'support': 12073.0} | 0.8920   | {'precision': 0.8518971212266971, 'recall': 0.8326799539194798, 'f1-score': 0.8417048526286843, 'support': 29705.0} | {'precision': 0.8915666503464329, 'recall': 0.8919710486450093, 'f1-score': 0.8915603797680256, 'support': 29705.0} |
| No log        | 7.0   | 287  | 0.2715          | {'precision': 0.6254587155963303, 'recall': 0.6542706333973128, 'f1-score': 0.6395403377110694, 'support': 4168.0}  | {'precision': 0.8875878220140515, 'recall': 0.8805762081784386, 'f1-score': 0.8840681128994634, 'support': 2152.0} | {'precision': 0.9999116061168567, 'recall': 1.0, 'f1-score': 0.9999558011049724, 'support': 11312.0}                | {'precision': 0.8987139615028998, 'recall': 0.8856125238134681, 'f1-score': 0.8921151439299123, 'support': 12073.0} | 0.8963   | {'precision': 0.8529180263075345, 'recall': 0.8551148413473049, 'f1-score': 0.8539198489113544, 'support': 29705.0} | {'precision': 0.8981038432990452, 'recall': 0.8963474162598889, 'f1-score': 0.8971595644270212, 'support': 29705.0} |


### Framework versions

- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2