learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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: cosine
lr_scheduler_warmup_steps: 200
num_epochs: 8
mixed_precision_training: Native AMP
label_smoothing_factor: 0.1

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	Precision Macro	Recall Macro
1.8278	1.0	443	0.8410	0.6552	0.6576	0.6629	0.6555
1.5314	2.0	886	0.7458	0.7299	0.7277	0.7278	0.7303
1.4421	3.0	1329	0.7242	0.7408	0.7430	0.7470	0.7409
1.2426	4.0	1772	0.7210	0.7531	0.7518	0.7516	0.7534
1.1617	5.0	2215	0.7287	0.7493	0.7478	0.7558	0.7497
1.0077	6.0	2658	0.7423	0.7684	0.7703	0.7739	0.7685
0.9360	7.0	3101	0.7687	0.7729	0.7731	0.7737	0.7731
0.9381	8.0	3544	0.7782	0.7691	0.7692	0.7690	0.7694

sayikhushhal/results_final

results_final