euk_roberta_base_essentiality

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

• Loss: 0.3886
• Accuracy: 0.8418
• Precision: 0.8379
• Recall: 0.8474
• F1: 0.8427

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: 50
• eval_batch_size: 50
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 200
• 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: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	68	0.4700	0.7911	0.7674	0.8355	0.8
No log	2.0	136	0.4625	0.8010	0.8440	0.7384	0.7877
No log	3.0	204	0.4453	0.8173	0.8571	0.7616	0.8066
No log	4.0	272	0.4034	0.8337	0.8104	0.8713	0.8397
No log	5.0	340	0.3929	0.8325	0.8402	0.8212	0.8306
No log	6.0	408	0.3894	0.8352	0.8571	0.8045	0.8300
No log	7.0	476	0.4159	0.8343	0.8638	0.7938	0.8273
1.6691	8.0	544	0.3870	0.8379	0.8487	0.8224	0.8354
1.6691	9.0	612	0.3872	0.8421	0.8433	0.8403	0.8418
1.6691	10.0	680	0.3763	0.8367	0.8218	0.8600	0.8404
1.6691	11.0	748	0.3865	0.8355	0.8243	0.8528	0.8383
1.6691	12.0	816	0.3823	0.8403	0.8289	0.8576	0.8430
1.6691	13.0	884	0.3915	0.8412	0.8354	0.8498	0.8425
1.6691	14.0	952	0.3886	0.8424	0.8389	0.8474	0.8432
1.2977	15.0	1020	0.3866	0.8352	0.8220	0.8558	0.8385

Framework versions

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