metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- sem_eval2010_task8
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned-sem
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: sem_eval2010_task8
type: sem_eval2010_task8
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8314317261685683
distilbert-base-uncased-finetuned-sem
This model is a fine-tuned version of distilbert-base-uncased on the sem_eval2010_task8 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6704
- Accuracy: 0.8314
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: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9556 | 1.0 | 800 | 0.7859 | 0.7814 |
| 0.6136 | 2.0 | 1600 | 0.6069 | 0.8193 |
| 0.4314 | 3.0 | 2400 | 0.6179 | 0.8211 |
| 0.2315 | 4.0 | 3200 | 0.6617 | 0.8281 |
| 0.1655 | 5.0 | 4000 | 0.6704 | 0.8314 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 1.18.4
- Tokenizers 0.11.6