learning_rate: 1e-05
train_batch_size: 32
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
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: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Bleu
2.4992	0.7042	500	1.2539	39.8924
2.5255	1.4085	1000	1.2499	40.3541
2.5365	2.1127	1500	1.2485	39.6821
2.5415	2.8169	2000	1.2442	40.2859
2.4872	3.5211	2500	1.2413	39.9425
2.4966	4.2254	3000	1.2382	40.2337
2.5133	4.9296	3500	1.2361	39.7923
2.5473	5.6338	4000	1.2352	39.8885
2.5065	6.3380	4500	1.2334	39.9683
2.5025	7.0423	5000	1.2332	40.1251
2.4967	7.7465	5500	1.2320	40.1722
2.5091	8.4507	6000	1.2320	40.0111
2.509	9.1549	6500	1.2319	40.0434
2.5453	9.8592	7000	1.2319	40.0532

carlynamazed24/marian-mt-cb-tl-lora-finetuned

marian-mt-cb-tl-lora-finetuned