electra-large-discriminator_Climate_LRTC

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

• Loss: 2.0271
• Accuracy: 0.1963
• Macro Precision: 0.2040
• Macro F1: 0.1762

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	2.0672	0.2740	0.0910	0.0824
No log	2.0	108	2.0821	0.1370	0.0736	0.0758
No log	3.0	162	2.0626	0.1324	0.1181	0.1028
No log	4.0	216	2.0790	0.2968	0.0892	0.0785
No log	5.0	270	2.0205	0.2237	0.1812	0.1569
No log	6.0	324	2.0274	0.1735	0.1979	0.1372
No log	7.0	378	2.0375	0.2055	0.1438	0.1289
No log	8.0	432	1.9617	0.2146	0.2243	0.1742
No log	9.0	486	2.0007	0.2055	0.1859	0.1613
1.8607	10.0	540	2.0348	0.2009	0.2232	0.1777
1.8607	11.0	594	2.0087	0.1872	0.2050	0.1761
1.8607	12.0	648	2.0271	0.1963	0.2040	0.1762

Framework versions

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