classify-articles

This model is a fine-tuned version of albert/albert-base-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3819
• Accuracy: 0.9070
• F1: 0.9061
• Precision: 0.9126
• Recall: 0.9070
• Accuracy Label Economy: 0.9429
• Accuracy Label Politics: 0.9574
• Accuracy Label Science: 0.9362
• Accuracy Label Sports: 0.96
• Accuracy Label Technology: 0.6944

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Accuracy Label Economy	Accuracy Label Politics	Accuracy Label Science	Accuracy Label Sports	Accuracy Label Technology
1.3703	1.3072	100	1.3775	0.4930	0.4238	0.6100	0.4930	0.8	0.0213	0.7021	0.72	0.2222
0.4329	2.6144	200	0.4495	0.8977	0.9004	0.9134	0.8977	0.9429	0.8936	0.9149	0.96	0.75

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1
• Datasets 2.21.0
• Tokenizers 0.19.1