learning_rate: 5e-05
train_batch_size: 24
eval_batch_size: 24
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: 15

Training Loss	Epoch	Step	Validation Loss	F1
0.5554	1.0	191	0.3139	0.7825
0.274	2.0	382	0.2869	0.7980
0.2058	3.0	573	0.3234	0.8251
0.1615	4.0	764	0.3041	0.8203
0.1201	5.0	955	0.3673	0.8226
0.0874	6.0	1146	0.3682	0.8423
0.0691	7.0	1337	0.4328	0.8372
0.0488	8.0	1528	0.4418	0.8472
0.0353	9.0	1719	0.4692	0.8518
0.0236	10.0	1910	0.4463	0.8448
0.0174	11.0	2101	0.5193	0.8484
0.0158	12.0	2292	0.5367	0.8497
0.0083	13.0	2483	0.5489	0.8476
0.0055	14.0	2674	0.5695	0.8501
0.0056	15.0	2865	0.5681	0.8502

firedfrog23/xlm-roberta-base-finetuned-panx-fr

xlm-roberta-base-finetuned-panx-fr