learning_rate: 2e-05
train_batch_size: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
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: 0.1
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	Macro F1	Weighted F1
4.7533	1.0	333	2.3427	0.2797	0.0414	0.1751
4.6166	2.0	666	2.2027	0.3173	0.0861	0.2329
4.4714	3.0	999	2.1763	0.3504	0.1236	0.2978
3.8243	4.0	1332	2.1699	0.3564	0.1285	0.3080
3.7490	5.0	1665	2.1986	0.3489	0.1256	0.3025
3.3961	6.0	1998	2.2100	0.3639	0.1535	0.3168
3.0140	7.0	2331	2.2518	0.3624	0.1581	0.3286
2.7022	8.0	2664	2.3148	0.3714	0.1638	0.3358
2.3658	9.0	2997	2.3779	0.3684	0.1623	0.3352
2.4651	10.0	3330	2.4045	0.3639	0.1590	0.3318

akunskripsiapillv1/artifacts

artifacts