learning_rate: 0.0003
train_batch_size: 16
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Use OptimizerNames.ADAFACTOR and the args are: No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 200
num_epochs: 7

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
67.9227	1.0	124	6.5664	12.2511	1.6918	12.0381	12.0393
49.7622	2.0	248	4.2584	45.1896	24.7258	37.0393	36.9982
32.0932	3.0	372	2.4803	42.0063	22.7813	33.3049	33.2774
19.7087	4.0	496	1.4753	47.3619	29.5111	38.6752	38.5921
12.6708	5.0	620	1.0041	55.6679	39.8804	48.7806	48.7339
9.3372	6.0	744	0.8130	58.0711	41.5208	50.8048	50.7743
8.0455	7.0	868	0.7587	59.9808	43.9895	52.6426	52.6476

nguyennghia0902/t5-feedback-generator-newfinal

t5-feedback-generator-newfinal