Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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
num_epochs: 50
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
1.6886	1.5231	50	1.4529	0.3885	0.4649	0.3885	0.3044
1.3569	3.0308	100	0.9348	0.7962	0.8157	0.7962	0.7900
0.7753	4.5538	150	0.3586	0.8962	0.9000	0.8962	0.8944
0.3148	6.0615	200	0.1407	0.9538	0.9539	0.9538	0.9536
0.147	7.5846	250	0.1306	0.9654	0.9659	0.9654	0.9649
0.0831	9.0923	300	0.1335	0.9654	0.9658	0.9654	0.9650
0.0426	10.6154	350	0.1359	0.9654	0.9654	0.9654	0.9651
0.0227	12.1231	400	0.1296	0.9692	0.9692	0.9692	0.9690
0.0272	13.6462	450	0.1280	0.9731	0.9730	0.9731	0.9728
0.0094	15.1538	500	0.1333	0.9731	0.9730	0.9731	0.9728
0.0272	16.6769	550	0.1403	0.9731	0.9730	0.9731	0.9728
0.0146	18.1846	600	0.1471	0.9731	0.9730	0.9731	0.9728
0.015	19.7077	650	0.1571	0.9654	0.9655	0.9654	0.9652
0.022	21.2154	700	0.1532	0.9731	0.9730	0.9731	0.9728
0.0302	22.7385	750	0.1601	0.9692	0.9694	0.9692	0.9690
0.0293	24.2462	800	0.1659	0.9731	0.9730	0.9731	0.9728
0.0318	25.7692	850	0.1655	0.9692	0.9693	0.9692	0.9691
0.0479	27.2769	900	0.1613	0.9692	0.9693	0.9692	0.9691
0.0307	28.8	950	0.1552	0.9692	0.9693	0.9692	0.9691
0.0323	30.3077	1000	0.1522	0.9654	0.9655	0.9654	0.9653
0.0214	31.8308	1050	0.1528	0.9692	0.9693	0.9692	0.9691
0.0132	33.3385	1100	0.1610	0.9692	0.9693	0.9692	0.9691
0.0174	34.8615	1150	0.1585	0.9731	0.9730	0.9731	0.9728
0.0212	36.3692	1200	0.1556	0.9731	0.9730	0.9731	0.9728
0.0189	37.8923	1250	0.1537	0.9769	0.9771	0.9769	0.9767
0.0165	39.4	1300	0.1550	0.9769	0.9771	0.9769	0.9767
0.0286	40.9231	1350	0.1514	0.9731	0.9731	0.9731	0.9729
0.0161	42.4308	1400	0.1530	0.9769	0.9771	0.9769	0.9767
0.018	43.9538	1450	0.1535	0.9769	0.9771	0.9769	0.9767
0.0088	45.4615	1500	0.1542	0.9769	0.9771	0.9769	0.9767
0.0073	46.9846	1550	0.1551	0.9769	0.9771	0.9769	0.9767
0.0119	48.4923	1600	0.1545	0.9769	0.9771	0.9769	0.9767

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1

KittiphopKhankaew/Aina-emotion-classification-WangChanBERTa

Aina-emotion-classification-WangChanBERTa

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

KittiphopKhankaew/
Aina-emotion-classification-WangChanBERTa