distilbert-base-uncased

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.9069
• Accuracy: {'accuracy': 0.871}

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: 0.001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	1.7205	{'accuracy': 0.868}
0.1563	2.0	500	1.5937	{'accuracy': 0.865}
0.1563	3.0	750	1.6187	{'accuracy': 0.861}
0.1939	4.0	1000	1.2535	{'accuracy': 0.861}
0.1939	5.0	1250	1.5725	{'accuracy': 0.87}
0.0701	6.0	1500	1.7691	{'accuracy': 0.874}
0.0701	7.0	1750	1.8419	{'accuracy': 0.864}
0.0224	8.0	2000	1.8159	{'accuracy': 0.876}
0.0224	9.0	2250	1.9088	{'accuracy': 0.871}
0.0129	10.0	2500	1.9069	{'accuracy': 0.871}

Framework versions

• Transformers 4.35.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1