learning_rate: 0.0005
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
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: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss
3.0528	0.2133	100	2.7539
2.5956	0.4267	200	2.6524
2.5519	0.64	300	2.5826
2.454	0.8533	400	2.5007
2.2554	1.0661	500	2.4537
1.9405	1.2795	600	2.4237
1.9406	1.4928	700	2.3943
1.924	1.7061	800	2.3455
1.9371	1.9195	900	2.3112
1.5472	2.1323	1000	2.4458
1.3414	2.3456	1100	2.4200
1.3884	2.5589	1200	2.3994

lcaragiov/business-news-generator-v5

business-news-generator-v5