metadata
license: apache-2.0
base_model: allenai/longformer-base-4096
tags:
- generated_from_trainer
datasets:
- fancy_dataset
metrics:
- accuracy
model-index:
- name: longformer-sep_tok
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: fancy_dataset
type: fancy_dataset
config: simple
split: test
args: simple
metrics:
- name: Accuracy
type: accuracy
value: 0.8209896449174101
longformer-sep_tok
This model is a fine-tuned version of allenai/longformer-base-4096 on the fancy_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.4200
- Claim: {'precision': 0.8410830848577645, 'recall': 0.7810956443646161, 'f1-score': 0.8099802103139188, 'support': 13362.0}
- Majorclaim: {'precision': 0.6330965315503552, 'recall': 0.6943171402383135, 'f1-score': 0.6622950819672131, 'support': 2182.0}
- Premise: {'precision': 0.8362706950484474, 'recall': 0.8864536999595632, 'f1-score': 0.8606312814070352, 'support': 12365.0}
- Accuracy: 0.8210
- Macro avg: {'precision': 0.7701501038188557, 'recall': 0.7872888281874976, 'f1-score': 0.7776355245627223, 'support': 27909.0}
- Weighted avg: {'precision': 0.8226900267292406, 'recall': 0.8209896449174101, 'f1-score': 0.8208746007977725, 'support': 27909.0}
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 | Premise | Accuracy | Macro avg | Weighted avg |
|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 41 | 0.5303 | {'precision': 0.7396921017402945, 'recall': 0.8270468492740608, 'f1-score': 0.780934209596495, 'support': 13362.0} | {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 2182.0} | {'precision': 0.8185673529184979, 'recall': 0.8585523655479175, 'f1-score': 0.8380832083366226, 'support': 12365.0} | 0.7763 | {'precision': 0.5194198182195975, 'recall': 0.5618664049406594, 'f1-score': 0.5396724726443726, 'support': 27909.0} | {'precision': 0.716806448897884, 'recall': 0.7763445483535777, 'f1-score': 0.7451983868899174, 'support': 27909.0} |
| No log | 2.0 | 82 | 0.4493 | {'precision': 0.8127147766323024, 'recall': 0.7787756323903607, 'f1-score': 0.7953833218680731, 'support': 13362.0} | {'precision': 0.7305801376597837, 'recall': 0.34051329055912005, 'f1-score': 0.4645201625507971, 'support': 2182.0} | {'precision': 0.8051533219761499, 'recall': 0.9173473513950667, 'f1-score': 0.8575964918912788, 'support': 12365.0} | 0.8059 | {'precision': 0.7828160787560786, 'recall': 0.6788787581148492, 'f1-score': 0.7058333254367164, 'support': 27909.0} | {'precision': 0.8029431915141912, 'recall': 0.8059049052277043, 'f1-score': 0.797078919478401, 'support': 27909.0} |
| No log | 3.0 | 123 | 0.4200 | {'precision': 0.8410830848577645, 'recall': 0.7810956443646161, 'f1-score': 0.8099802103139188, 'support': 13362.0} | {'precision': 0.6330965315503552, 'recall': 0.6943171402383135, 'f1-score': 0.6622950819672131, 'support': 2182.0} | {'precision': 0.8362706950484474, 'recall': 0.8864536999595632, 'f1-score': 0.8606312814070352, 'support': 12365.0} | 0.8210 | {'precision': 0.7701501038188557, 'recall': 0.7872888281874976, 'f1-score': 0.7776355245627223, 'support': 27909.0} | {'precision': 0.8226900267292406, 'recall': 0.8209896449174101, 'f1-score': 0.8208746007977725, 'support': 27909.0} |
Framework versions
- Transformers 4.37.1
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1