learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 3407
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
num_epochs: 100

Training Loss	Epoch	Step	Validation Loss	F1
0.4874	0.1567	50	0.5096	0.4521
0.4504	0.3135	100	0.4247	0.4333
0.4445	0.4702	150	0.3944	0.4560
0.3876	0.6270	200	0.3705	0.5248
0.3644	0.7837	250	0.4093	0.4787
0.3671	0.9404	300	0.3695	0.5158
0.3474	1.0972	350	0.3388	0.6583
0.292	1.2539	400	0.3661	0.6393
0.3209	1.4107	450	0.3504	0.6519
0.3007	1.5674	500	0.3370	0.6747
0.3298	1.7241	550	0.3278	0.6855
0.3181	1.8809	600	0.3452	0.6432
0.2428	2.0376	650	0.3531	0.6776
0.2089	2.1944	700	0.4433	0.6621
0.2568	2.3511	750	0.3727	0.6406
0.2415	2.5078	800	0.4443	0.6267

JosephYAA/arabert-base-argmin-argdet-sent

arabert-base-argmin-argdet-sent