learning_rate: 3e-05
train_batch_size: 64
eval_batch_size: 128
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 500
num_epochs: 2
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	Keep F1	Drop F1	Macro F1	Predicted Drop Rate	Gold Drop Rate
0.2646	0.3918	500	0.2424	0.9115	0.9362	0.8557	0.8959	0.2843	0.3288
0.2006	0.7837	1000	0.1701	0.9367	0.9531	0.9030	0.9280	0.3234	0.3288
0.1862	1.1755	1500	0.1626	0.9384	0.9542	0.9061	0.9302	0.3269	0.3288
0.1741	1.5674	2000	0.1593	0.9382	0.9538	0.9065	0.9302	0.3321	0.3288
0.1772	1.9592	2500	0.1586	0.9391	0.9546	0.9074	0.9310	0.3288	0.3288
0.1772	2.0	2552	0.1586	0.9389	0.9545	0.9072	0.9309	0.3293	0.3288

aayushbist/saccade-v2-4m

saccade-v2-4m