test4_balanced

This model is a fine-tuned version of ibaucells/RoBERTa-ca-CaWikiTC on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.7547

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: 5e-05
• train_batch_size: 10
• eval_batch_size: 10
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
2.8374	1.0	63	2.8602
2.8391	2.0	126	2.8558
2.8386	3.0	189	2.8525
2.8184	4.0	252	2.7896
2.6383	5.0	315	2.7301
2.5916	6.0	378	2.6223
2.2213	7.0	441	2.3985
2.0637	8.0	504	2.4005
1.4994	9.0	567	1.9991
1.2747	10.0	630	1.8684
0.8926	11.0	693	1.7539
0.6952	12.0	756	1.9212
0.5747	13.0	819	1.8101
0.5083	14.0	882	1.7709
0.4356	15.0	945	1.7547

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2