learning_rate: 0.0003
train_batch_size: 4
eval_batch_size: 4
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
4.4421	1.0	1031	3.7025
3.6107	2.0	2062	3.2316
3.0197	3.0	3093	2.8729
2.6591	4.0	4124	2.6624
2.3048	5.0	5155	2.5423
2.0147	6.0	6186	2.4637
1.7714	7.0	7217	2.4011
1.5943	8.0	8248	2.3722
1.4302	9.0	9279	2.3561
1.2905	10.0	10310	2.3710
1.206	11.0	11341	2.3609
1.0743	12.0	12372	2.4143
1.0458	13.0	13403	2.4083
0.9801	14.0	14434	2.4436
0.9405	15.0	15465	2.4441

capadesu/mt5-finetuned-mdo-id-epoch15

mt5-finetuned-mdo-id-epoch15