learning_rate: 0.0003
train_batch_size: 8
eval_batch_size: 8
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: cosine
num_epochs: 2

Training Loss	Epoch	Step	Validation Loss
1.1347	0.0667	250	3.5258
1.4249	0.1333	500	3.1897
2.1567	0.2	750	3.0544
2.0502	0.2667	1000	2.9841
1.9906	0.3333	1250	2.9156
1.884	0.4	1500	2.8856
1.868	0.4667	1750	2.8510
1.8392	0.5333	2000	2.8131
1.8603	0.6	2250	2.7714
1.9325	0.6667	2500	2.7086
1.9161	0.7333	2750	2.6814
1.8554	0.8	3000	2.6437
1.8801	0.8667	3250	2.5983
1.8579	0.9333	3500	2.5905
1.8245	1.0	3750	2.5566
0.8401	1.0667	4000	2.7241
0.8312	1.1333	4250	2.7352
0.8416	1.2	4500	2.7241
0.8433	1.2667	4750	2.7169
0.852	1.3333	5000	2.6969
0.8705	1.4	5250	2.6834
0.8723	1.4667	5500	2.6791
0.9135	1.5333	5750	2.6663
0.9026	1.6	6000	2.6622
0.8954	1.6667	6250	2.6524
0.9425	1.7333	6500	2.6419
0.9312	1.8	6750	2.6407
0.9258	1.8667	7000	2.6381
0.929	1.9333	7250	2.6374
0.9461	2.0	7500	2.6371

denisdrobs/business-news-generator-3rd_iteration

business-news-generator-3rd_iteration