learning_rate: 9.638903028324055e-07
train_batch_size: 16
eval_batch_size: 16
seed: 42
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_ratio: 0.1
num_epochs: 50
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
1.1602	1.0	24	1.1641	0.2439	0.0610	0.2439	0.0976
1.129	2.0	48	1.1631	0.2439	0.0595	0.2439	0.0956
1.0808	3.0	72	1.1699	0.2683	0.4268	0.2683	0.1433
1.0639	4.0	96	1.1825	0.2927	0.2488	0.2927	0.1808
1.0523	5.0	120	1.1802	0.2683	0.2073	0.2683	0.1686
1.0519	6.0	144	1.1623	0.2683	0.3017	0.2683	0.1728
1.0314	7.0	168	1.1333	0.2927	0.2421	0.2927	0.2180
1.0147	8.0	192	1.1085	0.3902	0.2948	0.3902	0.3118
0.989	9.0	216	1.0818	0.4634	0.3433	0.4634	0.3767
0.9571	10.0	240	1.0650	0.4146	0.3230	0.4146	0.3379
0.9545	11.0	264	1.0206	0.4634	0.3455	0.4634	0.3837
0.9242	12.0	288	0.9929	0.5366	0.6484	0.5366	0.5105
0.9029	13.0	312	0.9604	0.5610	0.6577	0.5610	0.5414
0.857	14.0	336	0.9288	0.5610	0.6577	0.5610	0.5414
0.8467	15.0	360	0.8948	0.6341	0.7033	0.6341	0.6330
0.82	16.0	384	0.8697	0.6341	0.7033	0.6341	0.6330
0.7915	17.0	408	0.8411	0.6829	0.7290	0.6829	0.6783
0.7592	18.0	432	0.8155	0.7317	0.7572	0.7317	0.7281
0.7443	19.0	456	0.8008	0.7317	0.7572	0.7317	0.7281
0.731	20.0	480	0.7860	0.7317	0.7572	0.7317	0.7281
0.7107	21.0	504	0.7690	0.7317	0.7613	0.7317	0.7325
0.7096	22.0	528	0.7513	0.7561	0.7796	0.7561	0.7530
0.6829	23.0	552	0.7270	0.7561	0.7796	0.7561	0.7530
0.6723	24.0	576	0.7300	0.7561	0.7796	0.7561	0.7530
0.6447	25.0	600	0.7303	0.7561	0.7796	0.7561	0.7530
0.6615	26.0	624	0.7096	0.7561	0.7796	0.7561	0.7530
0.6587	27.0	648	0.7022	0.7561	0.7796	0.7561	0.7530
0.6351	28.0	672	0.7226	0.7561	0.7796	0.7561	0.7530
0.6216	29.0	696	0.6917	0.7561	0.7796	0.7561	0.7530
0.6264	30.0	720	0.7024	0.7561	0.7796	0.7561	0.7530
0.6152	31.0	744	0.7011	0.7561	0.7796	0.7561	0.7530
0.6094	32.0	768	0.6815	0.7317	0.7411	0.7317	0.7264
0.6028	33.0	792	0.6816	0.7317	0.7411	0.7317	0.7264
0.5997	34.0	816	0.6850	0.7317	0.7411	0.7317	0.7264
0.5932	35.0	840	0.6916	0.7317	0.7411	0.7317	0.7264
0.5882	36.0	864	0.6960	0.7561	0.7796	0.7561	0.7530
0.5839	37.0	888	0.6859	0.7317	0.7411	0.7317	0.7264

Framework versions

Transformers 4.57.6
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.2

Noctuaru/tone-berita-v2

results

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Noctuaru/
tone-berita-v2