metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert-ner-essays-classify_span
results: []
bert-ner-essays-classify_span
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6951
- Claim: {'precision': 0.4811320754716981, 'recall': 0.3541666666666667, 'f1-score': 0.408, 'support': 144.0}
- Majorclaim: {'precision': 0.625, 'recall': 0.4861111111111111, 'f1-score': 0.5468749999999999, 'support': 72.0}
- Premise: {'precision': 0.7718120805369127, 'recall': 0.8778625954198473, 'f1-score': 0.8214285714285714, 'support': 393.0}
- Accuracy: 0.7077
- Macro avg: {'precision': 0.6259813853362036, 'recall': 0.5727134577325418, 'f1-score': 0.5921011904761905, 'support': 609.0}
- Weighted avg: {'precision': 0.6857227693250102, 'recall': 0.7077175697865353, 'f1-score': 0.6912125263898662, 'support': 609.0}
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Claim | Majorclaim | Premise | Accuracy | Macro avg | Weighted avg |
|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 267 | 0.7245 | {'precision': 0.35714285714285715, 'recall': 0.10416666666666667, 'f1-score': 0.16129032258064516, 'support': 144.0} | {'precision': 0.5806451612903226, 'recall': 0.25, 'f1-score': 0.34951456310679613, 'support': 72.0} | {'precision': 0.6940298507462687, 'recall': 0.9465648854961832, 'f1-score': 0.8008611410118407, 'support': 393.0} | 0.6650 | {'precision': 0.5439392897264828, 'recall': 0.4335771840542833, 'f1-score': 0.4372220088997607, 'support': 609.0} | {'precision': 0.6009667559684043, 'recall': 0.6650246305418719, 'f1-score': 0.5962714013349024, 'support': 609.0} |
| 0.7275 | 2.0 | 534 | 0.6951 | {'precision': 0.4811320754716981, 'recall': 0.3541666666666667, 'f1-score': 0.408, 'support': 144.0} | {'precision': 0.625, 'recall': 0.4861111111111111, 'f1-score': 0.5468749999999999, 'support': 72.0} | {'precision': 0.7718120805369127, 'recall': 0.8778625954198473, 'f1-score': 0.8214285714285714, 'support': 393.0} | 0.7077 | {'precision': 0.6259813853362036, 'recall': 0.5727134577325418, 'f1-score': 0.5921011904761905, 'support': 609.0} | {'precision': 0.6857227693250102, 'recall': 0.7077175697865353, 'f1-score': 0.6912125263898662, 'support': 609.0} |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3