learning_rate: 1e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
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
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Bertscore F1	Gen Len
No log	1.0	3	6.9216	86.1528	103.6
No log	2.0	6	6.5049	86.1528	103.6
No log	3.0	9	6.1069	86.1528	103.6
No log	4.0	12	5.7672	86.1528	103.6
No log	5.0	15	5.4876	86.3019	103.6
No log	6.0	18	5.1384	86.3019	103.6
No log	7.0	21	4.8817	86.3019	103.6
No log	8.0	24	4.6638	86.3019	103.6
No log	9.0	27	4.5313	86.3019	103.6
No log	10.0	30	4.4612	86.2519	103.6

leon6523/t5-small-finetuned-opinosis

t5-small-finetuned-opinosis