roberta-base_Climate_Native

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

• Loss: 2.4963
• Accuracy: 0.2237
• Macro Precision: 0.1864
• Macro F1: 0.1782

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
• 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: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Macro Precision	Macro F1
No log	1.0	54	2.5363	0.2009	0.0522	0.0673
No log	2.0	108	2.4069	0.2055	0.0897	0.1130
No log	3.0	162	2.3152	0.1963	0.1934	0.1428
No log	4.0	216	2.3128	0.2055	0.1677	0.1483
No log	5.0	270	2.3046	0.1963	0.2270	0.1593
No log	6.0	324	2.3584	0.1735	0.2232	0.1464
No log	7.0	378	2.3716	0.2055	0.2044	0.1734
No log	8.0	432	2.3831	0.2100	0.2004	0.1828
No log	9.0	486	2.4299	0.1963	0.1999	0.1720
1.7557	10.0	540	2.4529	0.2100	0.1972	0.1666
1.7557	11.0	594	2.4833	0.2192	0.1914	0.1764
1.7557	12.0	648	2.4963	0.2237	0.1864	0.1782

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2