learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use adamw_torch 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: 1024
num_epochs: 15
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.4042	1.0	1828	1.7451	0.4622	0.1906	0.3370	0.3422
1.5875	2.0	3656	1.5933	0.4599	0.2060	0.3451	0.3472
1.3882	3.0	5484	1.5322	0.4606	0.2082	0.3422	0.3442
1.2415	4.0	7312	1.5130	0.4687	0.2208	0.3458	0.3476
1.1113	5.0	9140	1.5186	0.4630	0.2146	0.3398	0.3402
0.9671	6.0	10968	1.5683	0.4720	0.2290	0.3517	0.3520
0.8528	7.0	12796	1.6352	0.4704	0.2281	0.3491	0.3496
0.7555	8.0	14624	1.7122	0.4725	0.2305	0.3477	0.3481
0.6567	9.0	16452	1.7814	0.4763	0.2389	0.3537	0.3543
0.5612	10.0	18280	1.8528	0.4777	0.2410	0.3515	0.3516
0.4953	11.0	20108	1.9072	0.4799	0.2487	0.3562	0.3565
0.4445	12.0	21936	1.9503	0.4829	0.2514	0.3571	0.3574
0.3976	13.0	23764	1.9928	0.4834	0.2543	0.3569	0.3573
0.3643	14.0	25592	2.0249	0.4820	0.2520	0.3575	0.3581
0.3263	15.0	27420	2.0461	0.4850	0.2566	0.3589	0.3595

Skyler215/VIT_Captioning

VIT_Captioning