bert-base-uncased_Climate_Native

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

• Loss: 2.5023
• Accuracy: 0.1918
• Macro Precision: 0.1684
• Macro F1: 0.1506

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	2.5385	0.0776	0.0186	0.0203
No log	2.0	108	2.5546	0.1461	0.1123	0.0748
No log	3.0	162	2.5084	0.1324	0.0984	0.0825
No log	4.0	216	2.4910	0.1461	0.1522	0.1045
No log	5.0	270	2.5041	0.1461	0.1123	0.1115
No log	6.0	324	2.4740	0.1735	0.1679	0.1266
No log	7.0	378	2.4794	0.1735	0.1498	0.1278
No log	8.0	432	2.5280	0.1826	0.1629	0.1392
No log	9.0	486	2.5101	0.1826	0.1670	0.1482
2.0352	10.0	540	2.5178	0.1735	0.1505	0.1365
2.0352	11.0	594	2.5215	0.1872	0.1628	0.1458
2.0352	12.0	648	2.5023	0.1918	0.1684	0.1506

Framework versions

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