electra-large-discriminator_Climate_Native

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: 2.4733
• Accuracy: 0.2192
• Macro Precision: 0.1476
• Macro F1: 0.1424

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	2.5329	0.1324	0.1095	0.0514
No log	2.0	108	2.5284	0.0868	0.1289	0.0631
No log	3.0	162	2.4963	0.1096	0.0358	0.0548
No log	4.0	216	2.4749	0.1644	0.0427	0.0636
No log	5.0	270	2.4567	0.1553	0.0468	0.0679
No log	6.0	324	2.4476	0.1735	0.0947	0.1044
No log	7.0	378	2.4474	0.1918	0.1707	0.1138
No log	8.0	432	2.4225	0.1872	0.1311	0.1320
No log	9.0	486	2.4685	0.2100	0.1621	0.1345
2.0773	10.0	540	2.4740	0.2009	0.1436	0.1314
2.0773	11.0	594	2.4529	0.2192	0.1667	0.1591
2.0773	12.0	648	2.4733	0.2192	0.1476	0.1424

Framework versions

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