roberta-base-continual-kennedy2020constructing-S0T0

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

• Loss: 2.0370
• Accuracy: 0.5467
• Roc Auc: 0.7213
• Micro Precision: 0.5467
• Macro Precision: 0.5594
• Weighted Precision: 0.5594
• Micro Recall: 0.5467
• Macro Recall: 0.5467
• Weighted Recall: 0.5467
• Micro F1: 0.5467
• Macro F1: 0.5357
• Weighted F1: 0.5357

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: 32
• eval_batch_size: 64
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Roc Auc	Micro Precision	Macro Precision	Weighted Precision	Micro Recall	Macro Recall	Weighted Recall	Micro F1	Macro F1	Weighted F1
No log	1.0	67	1.2564	0.3333	0.6979	0.3333	0.1111	0.1111	0.3333	0.3333	0.3333	0.3333	0.1667	0.1667
No log	2.0	134	1.0816	0.5	0.7139	0.5	0.3326	0.3326	0.5	0.5	0.5	0.5	0.3992	0.3992
No log	3.0	201	1.3762	0.4667	0.7282	0.4667	0.4991	0.4991	0.4667	0.4667	0.4667	0.4667	0.4301	0.4301
No log	4.0	268	1.2988	0.4933	0.7387	0.4933	0.4845	0.4845	0.4933	0.4933	0.4933	0.4933	0.4633	0.4633
No log	5.0	335	1.6177	0.5067	0.7195	0.5067	0.5205	0.5205	0.5067	0.5067	0.5067	0.5067	0.4792	0.4792
No log	6.0	402	1.8167	0.5067	0.7207	0.5067	0.5282	0.5282	0.5067	0.5067	0.5067	0.5067	0.4867	0.4867
No log	7.0	469	1.9179	0.5533	0.723	0.5533	0.5811	0.5811	0.5533	0.5533	0.5533	0.5533	0.5352	0.5352
0.429	8.0	536	1.8665	0.5267	0.7226	0.5267	0.5286	0.5286	0.5267	0.5267	0.5267	0.5267	0.5174	0.5174
0.429	9.0	603	2.0073	0.5333	0.7238	0.5333	0.5487	0.5487	0.5333	0.5333	0.5333	0.5333	0.5207	0.5207
0.429	10.0	670	2.0370	0.5467	0.7213	0.5467	0.5594	0.5594	0.5467	0.5467	0.5467	0.5467	0.5357	0.5357

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0