GPT_nyala

This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000

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: 3e-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
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	63	0.0981
No log	2.0	126	0.0007
No log	3.0	189	0.0002
No log	4.0	252	0.0006
No log	5.0	315	0.0169
No log	6.0	378	0.0002
No log	7.0	441	0.0001
0.3539	8.0	504	0.0002
0.3539	9.0	567	0.0001
0.3539	10.0	630	0.0001
0.3539	11.0	693	0.0001
0.3539	12.0	756	0.0001
0.3539	13.0	819	0.0001
0.3539	14.0	882	0.0001
0.3539	15.0	945	0.0001
0.0012	16.0	1008	0.0000
0.0012	17.0	1071	0.0001
0.0012	18.0	1134	0.0000
0.0012	19.0	1197	0.0000
0.0012	20.0	1260	0.0000

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Tokenizers 0.21.0