learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
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
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5
mixed_precision_training: Native AMP
label_smoothing_factor: 0.1

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1 Macro	F1 Weighted
1.1314	0.1964	500	1.0741	0.6719	0.3589	0.4220	0.3798	0.6300
0.9202	0.3928	1000	0.8996	0.7687	0.7522	0.6339	0.6342	0.7575
0.8809	0.5892	1500	0.8679	0.7817	0.7309	0.7068	0.7138	0.7756
0.8697	0.7855	2000	0.8244	0.7974	0.7734	0.7586	0.7611	0.7970
0.8288	0.9819	2500	0.8086	0.8104	0.7888	0.7922	0.7858	0.8108
0.7415	1.1783	3000	0.8010	0.8234	0.8033	0.7977	0.7986	0.8225
0.7711	1.3747	3500	0.7849	0.8283	0.8147	0.8094	0.8113	0.8274
0.7617	1.5711	4000	0.7898	0.8235	0.8038	0.8049	0.8029	0.8236
0.727	1.7675	4500	0.7798	0.8307	0.8155	0.8093	0.8119	0.8294
0.7306	1.9639	5000	0.7776	0.8288	0.8038	0.8181	0.8085	0.8297
0.6785	2.1603	5500	0.7906	0.8221	0.8085	0.8220	0.8116	0.8227
0.6697	2.3566	6000	0.7882	0.8300	0.8177	0.8273	0.8210	0.8307
0.6489	2.5530	6500	0.7874	0.8321	0.8369	0.8138	0.8239	0.8318
0.6619	2.7494	7000	0.7915	0.8344	0.8360	0.8232	0.8288	0.8351
0.6453	2.9458	7500	0.7837	0.8383	0.8440	0.8196	0.8288	0.8381
0.5934	3.1422	8000	0.8205	0.8355	0.8441	0.8133	0.8269	0.8343
0.5917	3.3386	8500	0.8326	0.8321	0.8246	0.8289	0.8247	0.8324
0.5918	3.5350	9000	0.8306	0.8336	0.8309	0.8277	0.8282	0.8336
0.5986	3.7313	9500	0.8202	0.8311	0.8304	0.8304	0.8289	0.8319
0.5882	3.9277	10000	0.8311	0.8342	0.8277	0.8268	0.8263	0.8338
0.5636	4.1241	10500	0.8439	0.8347	0.8308	0.8262	0.8283	0.8338
0.558	4.3205	11000	0.8668	0.8333	0.8259	0.8323	0.8279	0.8335
0.5568	4.5169	11500	0.8513	0.8356	0.8299	0.8305	0.8301	0.8351
0.5481	4.7133	12000	0.8562	0.8347	0.8333	0.8318	0.8320	0.8349
0.5526	4.9097	12500	0.8585	0.8355	0.8290	0.8332	0.8309	0.8354

NaveenTNS/distilbert-cased

distilbert-cased