BEE-spoke-data/roberta-base-description2genre

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

• Loss: 0.2130
• F1: 0.6717

Model description

This classifies one or more genre labels in a multi-label setting for a given book description.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 4e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-10
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.04
• num_epochs: 6.0

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.3118	1.0	62	0.2885	0.3362
0.2676	2.0	124	0.2511	0.4882
0.2325	3.0	186	0.2272	0.6093
0.2127	4.0	248	0.2181	0.6591
0.1978	5.0	310	0.2140	0.6686
0.1817	6.0	372	0.2130	0.6717

Framework versions

• Transformers 4.33.3
• Pytorch 2.2.0.dev20231001+cu121
• Datasets 2.14.5
• Tokenizers 0.13.3