bact_roberta_large_essentiality_Network

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

• Loss: 0.4262
• Accuracy: 0.8194
• Precision: 0.8348
• Recall: 0.7964
• F1: 0.8151

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: 1e-05
• train_batch_size: 60
• eval_batch_size: 60
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 240
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	72	0.5375	0.7480	0.7056	0.8512	0.7716
No log	2.0	144	0.4962	0.7762	0.8253	0.7006	0.7579
No log	3.0	216	0.5092	0.7620	0.7192	0.8596	0.7831
No log	4.0	288	0.4782	0.7915	0.7696	0.8322	0.7996
No log	5.0	360	0.4404	0.8073	0.8097	0.8033	0.8065
No log	6.0	432	0.4548	0.8050	0.8801	0.7062	0.7836
1.8472	7.0	504	0.4341	0.8154	0.8418	0.7768	0.8080
1.8472	8.0	576	0.4251	0.8166	0.8429	0.7782	0.8093
1.8472	9.0	648	0.4290	0.8192	0.8434	0.7838	0.8125
1.8472	10.0	720	0.4262	0.8194	0.8348	0.7964	0.8151

Framework versions

• Transformers 5.0.0
• Pytorch 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2