bart-large-cnn-finetuned-quran

This model is a fine-tuned version of facebook/bart-large-cnn on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0519

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
0.7497	1.0	99	0.2608
0.1367	2.0	198	0.0607
0.0658	3.0	297	0.0529
0.0563	4.0	396	0.0521
0.0575	5.0	495	0.0522
0.0489	6.0	594	0.0518
0.0503	7.0	693	0.0511
0.0494	8.0	792	0.0532
0.0496	9.0	891	0.0512
0.0494	10.0	990	0.0515
0.051	11.0	1089	0.0517
0.0508	12.0	1188	0.0509
0.0543	13.0	1287	0.0516
0.0471	14.0	1386	0.0520
0.0483	15.0	1485	0.0519
0.0469	16.0	1584	0.0516
0.0478	17.0	1683	0.0514
0.0477	18.0	1782	0.0513
0.0479	19.0	1881	0.0511
0.0473	20.0	1980	0.0512
0.046	21.0	2079	0.0522
0.0481	22.0	2178	0.0514
0.0477	23.0	2277	0.0513
0.0476	24.0	2376	0.0514
0.047	25.0	2475	0.0517
0.0477	26.0	2574	0.0515
0.0461	27.0	2673	0.0515
0.0458	28.0	2772	0.0516
0.0463	29.0	2871	0.0518
0.0471	30.0	2970	0.0514
0.0452	31.0	3069	0.0518
0.0441	32.0	3168	0.0515
0.0477	33.0	3267	0.0519
0.0467	34.0	3366	0.0518
0.0464	35.0	3465	0.0515
0.045	36.0	3564	0.0517
0.0445	37.0	3663	0.0517
0.0449	38.0	3762	0.0515
0.0449	39.0	3861	0.0518
0.0454	40.0	3960	0.0518
0.0452	41.0	4059	0.0518
0.0448	42.0	4158	0.0518
0.0446	43.0	4257	0.0519
0.0448	44.0	4356	0.0519
0.0443	45.0	4455	0.0519
0.0452	46.0	4554	0.0519
0.0429	47.0	4653	0.0519
0.0455	48.0	4752	0.0519
0.0452	49.0	4851	0.0519
0.0441	50.0	4950	0.0519

Framework versions

• Transformers 4.30.2
• Pytorch 2.1.2+cu121
• Datasets 2.18.0
• Tokenizers 0.13.3