distilbert-no-aug

This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on the pietrolesci/pubmed-20k-rct dataset. It achieves the following results on the evaluation set:

• Loss: 0.7617
• F1: 0.6681

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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	32	1.3697	0.4109
No log	2.0	64	0.9464	0.6173
No log	3.0	96	0.7975	0.6557
No log	4.0	128	0.7662	0.6566
No log	5.0	160	0.7366	0.6712
No log	6.0	192	0.7750	0.6511
No log	7.0	224	0.7260	0.6740
No log	8.0	256	0.7392	0.6729
No log	9.0	288	0.7626	0.6687
No log	10.0	320	0.7617	0.6681

Framework versions

• Transformers 4.57.1
• Pytorch 2.9.0+cu128
• Datasets 4.3.0
• Tokenizers 0.22.1