learning_rate: 0.0003
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 500
training_steps: 10000

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time
3.1615	0.0101	500	1.4611	0.0575
3.0072	0.0202	1000	1.3972	0.0575
2.8503	0.0303	1500	1.3589	0.0575
2.8210	0.0404	2000	1.3341	0.0575
2.8089	0.0505	2500	1.3136	0.0575
2.7953	0.0606	3000	1.2988	0.0575
2.7414	0.0707	3500	1.2842	0.0575
2.6644	0.0808	4000	1.2661	0.0575
2.6363	0.0909	4500	1.2535	0.0575
2.6871	0.1010	5000	1.2412	0.0575
2.5607	0.1111	5500	1.2289	0.0575
2.6463	0.1212	6000	1.2177	0.0575
2.6042	0.1313	6500	1.2101	0.0575
2.5593	0.1414	7000	1.2027	0.0575
2.6148	0.1515	7500	1.1949	0.0575
2.5434	0.1616	8000	1.1908	0.0575
2.5353	0.1717	8500	1.1868	0.0575
2.5028	0.1818	9000	1.1856	0.0575
2.5299	0.1919	9500	1.1844	0.0575
2.4559	0.2020	10000	1.1843	0.0575

Or4kool/nllb-sa-finetuned

nllb-sa-finetuned