climate-dual-percentage-regression

This model is a fine-tuned version of alex-miller/ODABert on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0272

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-06
• train_batch_size: 24
• eval_batch_size: 24
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
0.0614	1.0	75	0.0637
0.053	2.0	150	0.0520
0.0409	3.0	225	0.0377
0.0319	4.0	300	0.0333
0.028	5.0	375	0.0313
0.0261	6.0	450	0.0303
0.0243	7.0	525	0.0296
0.0231	8.0	600	0.0293
0.0217	9.0	675	0.0288
0.0214	10.0	750	0.0282
0.0205	11.0	825	0.0280
0.02	12.0	900	0.0279
0.019	13.0	975	0.0277
0.0185	14.0	1050	0.0276
0.0182	15.0	1125	0.0276
0.0179	16.0	1200	0.0274
0.0176	17.0	1275	0.0274
0.0175	18.0	1350	0.0273
0.0174	19.0	1425	0.0272
0.0172	20.0	1500	0.0272

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1