meta_data/README_s42_e6.md

metadata

base_model: allenai/longformer-base-4096
tags:
  - generated_from_trainer
datasets:
  - essays_su_g
metrics:
  - accuracy
model-index:
  - name: longformer-sep_tok_full_labels
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: essays_su_g
          type: essays_su_g
          config: sep_tok_full_labels
          split: train[80%:100%]
          args: sep_tok_full_labels
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8885036189193738

longformer-sep_tok_full_labels

This model is a fine-tuned version of allenai/longformer-base-4096 on the essays_su_g dataset. It achieves the following results on the evaluation set:

• Loss: 0.2761
• B-claim: {'precision': 0.6297872340425532, 'recall': 0.5461254612546126, 'f1-score': 0.5849802371541503, 'support': 271.0}
• B-majorclaim: {'precision': 0.8091603053435115, 'recall': 0.762589928057554, 'f1-score': 0.7851851851851852, 'support': 139.0}
• B-premise: {'precision': 0.8537666174298375, 'recall': 0.9131121642969984, 'f1-score': 0.882442748091603, 'support': 633.0}
• I-claim: {'precision': 0.6177314211212517, 'recall': 0.5921019745063734, 'f1-score': 0.6046452271567125, 'support': 4001.0}
• I-majorclaim: {'precision': 0.8511749347258486, 'recall': 0.8097367113760556, 'f1-score': 0.829938900203666, 'support': 2013.0}
• I-premise: {'precision': 0.8836507799706972, 'recall': 0.9044636556104446, 'f1-score': 0.8939360913727712, 'support': 11336.0}
• O: {'precision': 1.0, 'recall': 0.9997347949080623, 'f1-score': 0.9998673798682641, 'support': 11312.0}
• Accuracy: 0.8885
• Macro avg: {'precision': 0.8064673275191, 'recall': 0.7896949557157287, 'f1-score': 0.7972851098617647, 'support': 29705.0}
• Weighted avg: {'precision': 0.8866387373492157, 'recall': 0.8885036189193738, 'f1-score': 0.8874017349734732, '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: 6

Training results

Training Loss	Epoch	Step	Validation Loss	B-claim	B-majorclaim	B-premise	I-claim	I-majorclaim	I-premise	O	Accuracy	Macro avg	Weighted avg
No log	1.0	41	0.3999	{'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 271.0}	{'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 139.0}	{'precision': 0.6303219106957425, 'recall': 0.9589257503949447, 'f1-score': 0.7606516290726817, 'support': 633.0}	{'precision': 0.4507791714177119, 'recall': 0.29642589352661836, 'f1-score': 0.3576598311218336, 'support': 4001.0}	{'precision': 0.7615720524017467, 'recall': 0.43318430203676106, 'f1-score': 0.552248258391387, 'support': 2013.0}	{'precision': 0.7975903614457831, 'recall': 0.9635673959068455, 'f1-score': 0.8727577803523631, 'support': 11336.0}	{'precision': 0.9987578741904002, 'recall': 0.9951379066478077, 'f1-score': 0.9969446043484037, 'support': 11312.0}	0.8364	{'precision': 0.5198601957359121, 'recall': 0.5210344640732825, 'f1-score': 0.5057517290409528, 'support': 29705.0}	{'precision': 0.8104709370809154, 'recall': 0.8363911799360377, 'f1-score': 0.8145155620981941, 'support': 29705.0}
No log	2.0	82	0.2924	{'precision': 0.3881578947368421, 'recall': 0.2177121771217712, 'f1-score': 0.2789598108747045, 'support': 271.0}	{'precision': 0.7941176470588235, 'recall': 0.19424460431654678, 'f1-score': 0.3121387283236995, 'support': 139.0}	{'precision': 0.7440191387559809, 'recall': 0.9826224328593997, 'f1-score': 0.8468345813478556, 'support': 633.0}	{'precision': 0.5826734979040522, 'recall': 0.3126718320419895, 'f1-score': 0.4069616135328562, 'support': 4001.0}	{'precision': 0.7138250705360741, 'recall': 0.8797814207650273, 'f1-score': 0.7881619937694704, 'support': 2013.0}	{'precision': 0.8334770678165425, 'recall': 0.9378087508821453, 'f1-score': 0.88257025445187, 'support': 11336.0}	{'precision': 0.9999115044247787, 'recall': 0.9988507779349364, 'f1-score': 0.9993808597205024, 'support': 11312.0}	0.8638	{'precision': 0.7223116887475848, 'recall': 0.6462417137031166, 'f1-score': 0.6450011202887085, 'support': 29705.0}	{'precision': 0.8488146361949856, 'recall': 0.8638276384447062, 'f1-score': 0.8476575620536897, 'support': 29705.0}
No log	3.0	123	0.2738	{'precision': 0.5565217391304348, 'recall': 0.47232472324723246, 'f1-score': 0.5109780439121756, 'support': 271.0}	{'precision': 0.7876106194690266, 'recall': 0.6402877697841727, 'f1-score': 0.7063492063492063, 'support': 139.0}	{'precision': 0.829512893982808, 'recall': 0.9146919431279621, 'f1-score': 0.870022539444027, 'support': 633.0}	{'precision': 0.6028012684989429, 'recall': 0.5701074731317171, 'f1-score': 0.5859987154784841, 'support': 4001.0}	{'precision': 0.7227219397731717, 'recall': 0.9180327868852459, 'f1-score': 0.8087527352297593, 'support': 2013.0}	{'precision': 0.9032961046036503, 'recall': 0.8775582215949188, 'f1-score': 0.8902411741017495, 'support': 11336.0}	{'precision': 1.0, 'recall': 0.9998231966053748, 'f1-score': 0.9999115904871364, 'support': 11312.0}	0.8814	{'precision': 0.7717806522082906, 'recall': 0.770403730625232, 'f1-score': 0.7674648578575054, 'support': 29705.0}	{'precision': 0.8821339407882951, 'recall': 0.8814341020030297, 'f1-score': 0.8807525950144975, 'support': 29705.0}
No log	4.0	164	0.2622	{'precision': 0.6040816326530613, 'recall': 0.5461254612546126, 'f1-score': 0.5736434108527132, 'support': 271.0}	{'precision': 0.7846153846153846, 'recall': 0.7338129496402878, 'f1-score': 0.758364312267658, 'support': 139.0}	{'precision': 0.8562874251497006, 'recall': 0.9036334913112164, 'f1-score': 0.8793235972328977, 'support': 633.0}	{'precision': 0.619699409554482, 'recall': 0.5771057235691077, 'f1-score': 0.5976446227513912, 'support': 4001.0}	{'precision': 0.8258227848101266, 'recall': 0.8102334823646299, 'f1-score': 0.8179538615847542, 'support': 2013.0}	{'precision': 0.8841960683320457, 'recall': 0.9086097388849682, 'f1-score': 0.8962366760931041, 'support': 11336.0}	{'precision': 1.0, 'recall': 1.0, 'f1-score': 1.0, 'support': 11312.0}	0.8879	{'precision': 0.7963861007306858, 'recall': 0.7827886924321176, 'f1-score': 0.7890237829689312, 'support': 29705.0}	{'precision': 0.8850982270692683, 'recall': 0.8878639959602761, 'f1-score': 0.8862796855742996, 'support': 29705.0}
No log	5.0	205	0.2694	{'precision': 0.6382978723404256, 'recall': 0.5535055350553506, 'f1-score': 0.5928853754940712, 'support': 271.0}	{'precision': 0.7837837837837838, 'recall': 0.8345323741007195, 'f1-score': 0.808362369337979, 'support': 139.0}	{'precision': 0.8636363636363636, 'recall': 0.9004739336492891, 'f1-score': 0.8816705336426915, 'support': 633.0}	{'precision': 0.6288815955566776, 'recall': 0.6225943514121469, 'f1-score': 0.6257221803566944, 'support': 4001.0}	{'precision': 0.8174868609651218, 'recall': 0.8499751614505713, 'f1-score': 0.8334145153433998, 'support': 2013.0}	{'precision': 0.899646017699115, 'recall': 0.8967889908256881, 'f1-score': 0.8982152323732108, 'support': 11336.0}	{'precision': 1.0, 'recall': 0.9996463932107497, 'f1-score': 0.9998231653404068, 'support': 11312.0}	0.8925	{'precision': 0.8045332134259268, 'recall': 0.808216677100645, 'f1-score': 0.8057276245554933, 'support': 29705.0}	{'precision': 0.8921309563748273, 'recall': 0.8925096785053022, 'f1-score': 0.8922564261033327, 'support': 29705.0}
No log	6.0	246	0.2761	{'precision': 0.6297872340425532, 'recall': 0.5461254612546126, 'f1-score': 0.5849802371541503, 'support': 271.0}	{'precision': 0.8091603053435115, 'recall': 0.762589928057554, 'f1-score': 0.7851851851851852, 'support': 139.0}	{'precision': 0.8537666174298375, 'recall': 0.9131121642969984, 'f1-score': 0.882442748091603, 'support': 633.0}	{'precision': 0.6177314211212517, 'recall': 0.5921019745063734, 'f1-score': 0.6046452271567125, 'support': 4001.0}	{'precision': 0.8511749347258486, 'recall': 0.8097367113760556, 'f1-score': 0.829938900203666, 'support': 2013.0}	{'precision': 0.8836507799706972, 'recall': 0.9044636556104446, 'f1-score': 0.8939360913727712, 'support': 11336.0}	{'precision': 1.0, 'recall': 0.9997347949080623, 'f1-score': 0.9998673798682641, 'support': 11312.0}	0.8885	{'precision': 0.8064673275191, 'recall': 0.7896949557157287, 'f1-score': 0.7972851098617647, 'support': 29705.0}	{'precision': 0.8866387373492157, 'recall': 0.8885036189193738, 'f1-score': 0.8874017349734732, 'support': 29705.0}

Framework versions

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