mdeberta-v3-base-finetuned-climate-vs-environment-classification

This model is a fine-tuned version of microsoft/mdeberta-v3-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3046
• Accuracy: 0.9412
• Accuracy Balanced: 0.9408
• F1 Macro: 0.9407
• F1 Micro: 0.9412
• Precision Macro: 0.9405
• Recall Macro: 0.9408
• Precision Micro: 0.9412
• Recall Micro: 0.9412
• Precision Class 0: 0.9332
• Recall Class 0: 0.9369
• F1 Class 0: 0.9350
• Support Class 0: 745
• Precision Class 1: 0.9479
• Recall Class 1: 0.9448
• F1 Class 1: 0.9463
• Support Class 1: 905

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.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: 0.06
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Accuracy Balanced	F1 Macro	F1 Micro	Precision Macro	Recall Macro	Precision Micro	Recall Micro	Precision Class 0	Recall Class 0	F1 Class 0	Support Class 0	Precision Class 1	Recall Class 1	F1 Class 1	Support Class 1
0.5189	0.6061	500	0.5022	0.8521	0.8638	0.8519	0.8521	0.8710	0.8638	0.8521	0.8521	0.7596	0.9839	0.8573	745	0.9825	0.7436	0.8465	905
0.2674	1.2121	1000	0.3443	0.9291	0.9284	0.9284	0.9291	0.9285	0.9284	0.9291	0.9291	0.9220	0.9208	0.9214	745	0.9349	0.9359	0.9354	905
0.253	1.8182	1500	0.2558	0.9261	0.9218	0.9247	0.9261	0.9302	0.9218	0.9261	0.9261	0.9547	0.8779	0.9147	745	0.9057	0.9657	0.9348	905
0.1733	2.4242	2000	0.2983	0.94	0.9394	0.9394	0.94	0.9395	0.9394	0.94	0.94	0.9341	0.9329	0.9335	745	0.9448	0.9459	0.9453	905
0.151	3.0303	2500	0.2986	0.9394	0.9372	0.9386	0.9394	0.9406	0.9372	0.9394	0.9394	0.9498	0.9141	0.9316	745	0.9314	0.9602	0.9456	905
0.1003	3.6364	3000	0.3046	0.9412	0.9408	0.9407	0.9412	0.9405	0.9408	0.9412	0.9412	0.9332	0.9369	0.9350	745	0.9479	0.9448	0.9463	905

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 2.14.4
• Tokenizers 0.21.1