learning_rate: 5e-05
train_batch_size: 4
eval_batch_size: 8
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: reduce_lr_on_plateau
lr_scheduler_warmup_ratio: 0.06
num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss
3.3707	0.7692	10	0.8298
0.33	1.5385	20	0.0024
0.0022	2.3077	30	0.0003
0.0814	3.0769	40	0.0002
0.0004	3.8462	50	0.0001
0.0003	4.6154	60	0.0001
0.0002	5.3846	70	0.0001
0.0002	6.1538	80	0.0001
0.0002	6.9231	90	0.0001
0.0002	7.6923	100	0.0001
0.0002	8.4615	110	0.0001
0.0002	9.2308	120	0.0001
0.0001	10.0	130	0.0001
0.0001	10.7692	140	0.0001
0.0001	11.5385	150	0.0001
0.0001	12.3077	160	0.0001
0.0001	13.0769	170	0.0001
0.0001	13.8462	180	0.0001
0.0001	14.6154	190	0.0000
0.0001	15.3846	200	0.0000
0.0001	16.1538	210	0.0000
0.0001	16.9231	220	0.0000
0.0001	17.6923	230	0.0000
0.0001	18.4615	240	0.0000
0.0001	19.2308	250	0.0000
0.0001	20.0	260	0.0000
0.0001	20.7692	270	0.0000
0.0001	21.5385	280	0.0000
0.0001	22.3077	290	0.0000
0.0001	23.0769	300	0.0000
0.0001	23.8462	310	0.0000
0.0001	24.6154	320	0.0000
0.0001	25.3846	330	0.0000
0.0001	26.1538	340	0.0000
0.0001	26.9231	350	0.0000
0.0001	27.6923	360	0.0000
0.0001	28.4615	370	0.0000
0.0001	29.2308	380	0.0000
0.0001	30.0	390	0.0000
0.0001	30.7692	400	0.0000
0.0001	31.5385	410	0.0000
0.0001	32.3077	420	0.0000
0.0001	33.0769	430	0.0000
0.0001	33.8462	440	0.0000
0.0001	34.6154	450	0.0000
0.0001	35.3846	460	0.0000
0.0001	36.1538	470	0.0000
0.0	36.9231	480	0.0000
0.0	37.6923	490	0.0000
0.0	38.4615	500	0.0000
0.0	39.2308	510	0.0000
0.0	40.0	520	0.0000
0.0	40.7692	530	0.0000
0.0	41.5385	540	0.0000
0.0	42.3077	550	0.0000
0.0	43.0769	560	0.0000
0.0	43.8462	570	0.0000
0.0	44.6154	580	0.0000
0.0	45.3846	590	0.0000
0.0	46.1538	600	0.0000
0.0	46.9231	610	0.0000
0.0	47.6923	620	0.0000
0.0	48.4615	630	0.0000
0.0	49.2308	640	0.0000
0.0	50.0	650	0.0000
0.0	50.7692	660	0.0000
0.0	51.5385	670	0.0000
0.0	52.3077	680	0.0000
0.0	53.0769	690	0.0000
0.0	53.8462	700	0.0000
0.0	54.6154	710	0.0000
0.0	55.3846	720	0.0000
0.0	56.1538	730	0.0000
0.0	56.9231	740	0.0000
0.0	57.6923	750	0.0000
0.0	58.4615	760	0.0000
0.0	59.2308	770	0.0000
0.0	60.0	780	0.0000
0.0	60.7692	790	0.0000
0.0	61.5385	800	0.0000
0.0	62.3077	810	0.0000
0.0	63.0769	820	0.0000
0.0	63.8462	830	0.0000
0.0	64.6154	840	0.0000
0.0	65.3846	850	0.0000
0.0	66.1538	860	0.0000
0.0	66.9231	870	0.0000
0.0	67.6923	880	0.0000
0.0	68.4615	890	0.0000
0.0	69.2308	900	0.0000
0.0	70.0	910	0.0000
0.0	70.7692	920	0.0000
0.0	71.5385	930	0.0000
0.0	72.3077	940	0.0000
0.0	73.0769	950	0.0000
0.0	73.8462	960	0.0000
0.0	74.6154	970	0.0000
0.0	75.3846	980	0.0000
0.0	76.1538	990	0.0000
0.0	76.9231	1000	0.0000
0.0	77.6923	1010	0.0000
0.0	78.4615	1020	0.0000
0.0	79.2308	1030	0.0000
0.0	80.0	1040	0.0000
0.0	80.7692	1050	0.0000
0.0	81.5385	1060	0.0000
0.0	82.3077	1070	0.0000
0.0	83.0769	1080	0.0000
0.0	83.8462	1090	0.0000
0.0	84.6154	1100	0.0000
0.0	85.3846	1110	0.0000
0.0	86.1538	1120	0.0000
0.0	86.9231	1130	0.0000
0.0	87.6923	1140	0.0000
0.0	88.4615	1150	0.0000
0.0	89.2308	1160	0.0000
0.0	90.0	1170	0.0000
0.0	90.7692	1180	0.0000
0.0	91.5385	1190	0.0000
0.0	92.3077	1200	0.0000
0.0	93.0769	1210	0.0000
0.0	93.8462	1220	0.0000
0.0	94.6154	1230	0.0000
0.0	95.3846	1240	0.0000
0.0	96.1538	1250	0.0000
0.0	96.9231	1260	0.0000
0.0	97.6923	1270	0.0000
0.0	98.4615	1280	0.0000
0.0	99.2308	1290	0.0000
0.0	100.0	1300	0.0000

Framework versions

Transformers 4.48.0
Pytorch 2.4.1.post100
Datasets 3.2.0
Tokenizers 0.21.0

AntonioTH/Layout-finetuned-fr-model-50instances20-100epochs-5e-05lr

Layout-finetuned-fr-model-50instances20-100epochs-5e-05lr

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

AntonioTH/
Layout-finetuned-fr-model-50instances20-100epochs-5e-05lr