learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use 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_steps: 500
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	F1	Precision	Recall
0.6843	1.0	689	0.6832	0.5398	0.5543	0.5445
0.6747	2.0	1378	0.6709	0.5912	0.6007	0.6062
0.6445	3.0	2067	0.6643	0.6173	0.6206	0.6274
0.5504	4.0	2756	0.6598	0.6019	0.6493	0.6442
0.3982	5.0	3445	0.7515	0.6860	0.6867	0.6855
0.5623	6.0	4134	0.8920	0.7259	0.7235	0.7312
0.4428	7.0	4823	1.0463	0.7367	0.7367	0.7367
0.2107	8.0	5512	1.1534	0.7239	0.7219	0.7319
0.1596	9.0	6201	1.3643	0.7339	0.7321	0.7363
0.0869	10.0	6890	1.3752	0.7353	0.7343	0.7365

usyk/indicbert1_sharetask-finetuned_on_codemixed

indicbert1_sharetask-finetuned_on_codemixed