learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 32
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
lr_scheduler_warmup_steps: 0.03
num_epochs: 3

Training Loss	Epoch	Step	Validation Loss
10.1416	0.0543	50	9.0038
7.2975	0.1086	100	6.9577
6.6494	0.1629	150	6.4694
6.3485	0.2172	200	6.0914
6.2067	0.2714	250	5.9083
6.0546	0.3257	300	5.7273
5.7634	0.3800	350	5.5655
5.6814	0.4343	400	5.4076
5.5820	0.4886	450	5.2923
5.5560	0.5429	500	5.1935
5.4320	0.5972	550	5.1080
5.2887	0.6515	600	5.0736
5.2464	0.7058	650	4.9919
5.2768	0.7600	700	4.9644
5.1517	0.8143	750	4.9259
5.0148	0.8686	800	4.8774
5.1010	0.9229	850	4.8530
5.1226	0.9772	900	4.8073
4.9871	1.0315	950	4.7904
4.8798	1.0858	1000	4.7541
4.9009	1.1401	1050	4.7370
4.8557	1.1944	1100	4.7059
4.9027	1.2486	1150	4.7020
4.7607	1.3029	1200	4.6803
4.7571	1.3572	1250	4.6586
4.7108	1.4115	1300	4.6308
4.7526	1.4658	1350	4.6088
4.8717	1.5201	1400	4.6057
4.7538	1.5744	1450	4.5733
4.7194	1.6287	1500	4.5682
4.7925	1.6830	1550	4.5835
4.6265	1.7372	1600	4.5304
4.6995	1.7915	1650	4.5141
4.6283	1.8458	1700	4.5023
4.6318	1.9001	1750	4.5037
4.6695	1.9544	1800	4.4839
4.5459	2.0087	1850	4.4732
4.5429	2.0630	1900	4.4729
4.6058	2.1173	1950	4.4593
4.5019	2.1716	2000	4.4685
4.4840	2.2258	2050	4.4491
4.3926	2.2801	2100	4.4450
4.4211	2.3344	2150	4.4310
4.5584	2.3887	2200	4.4319
4.5634	2.4430	2250	4.4124
4.4529	2.4973	2300	4.4226
4.5400	2.5516	2350	4.4082
4.4832	2.6059	2400	4.4071
4.5666	2.6602	2450	4.3956
4.6406	2.7144	2500	4.3879
4.4164	2.7687	2550	4.3936
4.4306	2.8230	2600	4.3943
4.4838	2.8773	2650	4.3845
4.5805	2.9316	2700	4.3815
4.4251	2.9859	2750	4.3808

math-hiyoko/pegasus-samsum

pegasus-samsum