learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
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: linear
num_epochs: 3

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8181	0.0393	100	0.2443	0.9050
0.4998	0.0785	200	0.2800	0.8754
0.4488	0.1178	300	0.5770	0.8710
0.3996	0.1570	400	0.1956	0.9139
0.298	0.1963	500	0.3754	0.9307
0.2918	0.2356	600	0.7744	0.8905
0.2906	0.2748	700	0.2349	0.9214
0.2113	0.3141	800	0.2182	0.9443
0.2552	0.3534	900	0.1959	0.9501
0.227	0.3926	1000	0.1768	0.9496
0.2203	0.4319	1100	0.1711	0.9439
0.2212	0.4711	1200	0.1652	0.9585
0.2153	0.5104	1300	0.1695	0.9567
0.1975	0.5497	1400	0.1776	0.9536
0.1866	0.5889	1500	0.1516	0.9602
0.2209	0.6282	1600	0.1139	0.9691
0.1788	0.6675	1700	0.1995	0.9563
0.1808	0.7067	1800	0.1857	0.9554
0.2401	0.7460	1900	0.1397	0.9686
0.1602	0.7852	2000	0.1974	0.9620
0.2206	0.8245	2100	0.1392	0.9633
0.1609	0.8638	2200	0.1904	0.9620
0.2108	0.9030	2300	0.1774	0.9611
0.1408	0.9423	2400	0.1598	0.9669
0.1696	0.9815	2500	0.1694	0.9660
0.1231	1.0208	2600	0.1451	0.9682

EndLessTime/fine_tuned_tldr_callback10

fine_tuned_tldr_callback10