learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
num_epochs: 50

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro	Rouge1	Rougel	Rougelsum
No log	0	0	12.5337	0	97.5575	0.3740	0.2807	0.3740	0.3740	0.3742
4.4062	1	11370	3.8879	0.0078	123.8071	0.6417	0.4672	0.6415	0.6417	0.6416
2.4745	2	22740	2.5586	0.0156	150.9046	0.7012	0.6452	0.7011	0.7010	0.7010
2.2957	3	34110	2.3952	0.0312	204.3855	0.6959	0.6037	0.6958	0.6958	0.6956
2.1827	4	45480	2.4881	0.0625	301.6521	0.6734	0.6719	0.6735	0.6734	0.6734
1.9945	5	56850	2.0471	0.125	502.3815	0.7452	0.7321	0.7451	0.7453	0.7451
1.7042	6	68220	1.7885	0.25	894.4348	0.7860	0.7711	0.7860	0.7859	0.7859
1.6192	7	79590	1.6304	0.5	1689.8291	0.8058	0.7958	0.8058	0.8058	0.8058
1.3484	8.0	90960	1.4467	1.0	3272.1442	0.8381	0.8252	0.8380	0.8381	0.8381
0.9428	9.0	102330	1.5240	1.0	3262.2948	0.8394	0.8309	0.8394	0.8394	0.8394
0.6673	10.0	113700	1.7234	1.0	3284.5675	0.8391	0.8285	0.8390	0.8392	0.8391
0.5009	11.0	125070	2.1515	1.0	3279.5725	0.8374	0.8273	0.8374	0.8375	0.8375
0.4964	12.0	136440	2.7772	1.0	3256.0133	0.8394	0.8260	0.8394	0.8395	0.8393

contemmcm/3b5ad0ad59c36a81ce72dbfc3904edb7

3b5ad0ad59c36a81ce72dbfc3904edb7