Model description

More information needed

Intended uses & limitations

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 3e-06
train_batch_size: 16
eval_batch_size: 8
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: linear
num_epochs: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	F1 Weighted
1.0829	1.0	178	0.8684	0.5980
0.8123	2.0	356	0.5814	0.6966
0.6025	3.0	534	0.4584	0.7583
0.4907	4.0	712	0.3871	0.7954
0.422	5.0	890	0.3562	0.8068
0.3762	6.0	1068	0.3218	0.8299
0.3347	7.0	1246	0.3066	0.8399
0.3032	8.0	1424	0.2843	0.8505
0.2782	9.0	1602	0.2726	0.8592
0.2527	10.0	1780	0.2639	0.8653
0.2352	11.0	1958	0.2632	0.8648
0.2211	12.0	2136	0.2549	0.8717
0.2076	13.0	2314	0.2557	0.8746
0.1963	14.0	2492	0.2467	0.8816
0.1865	15.0	2670	0.2471	0.8808
0.1808	16.0	2848	0.2471	0.8829
0.1755	17.0	3026	0.2391	0.8873
0.1723	18.0	3204	0.2404	0.8853
0.1665	19.0	3382	0.2434	0.8848
0.1643	20.0	3560	0.2425	0.8843