DuplicatiDistillBertCitations

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.5474
• eval_Accuracy: 0.8571
• eval_F1_macro: 0.8668
• eval_F1_class_0: 0.7476
• eval_F1_class_1: 0.8627
• eval_F1_class_2: 0.8975
• eval_F1_class_3: 0.9362
• eval_F1_class_4: 0.9415
• eval_F1_class_5: 0.9176
• eval_F1_class_6: 0.8864
• eval_F1_class_7: 0.9548
• eval_F1_class_8: 0.9196
• eval_F1_class_9: 0.9424
• eval_F1_class_10: 0.6921
• eval_F1_class_11: 0.3927
• eval_F1_class_12: 0.8407
• eval_F1_class_13: 0.9495
• eval_F1_class_14: 0.8884
• eval_F1_class_15: 0.8514
• eval_F1_class_16: 0.8750
• eval_F1_class_17: 0.9115
• eval_F1_class_18: 0.9647
• eval_F1_class_19: 0.9630
• eval_runtime: 30.4778
• eval_samples_per_second: 166.646
• eval_steps_per_second: 20.835
• epoch: 1.33
• step: 7681

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: 5e-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: 10

Framework versions

• Transformers 4.32.0
• Pytorch 2.0.1+cu117
• Datasets 2.14.4
• Tokenizers 0.13.3