ders-soru-uretici

This model is a fine-tuned version of google/mt5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2647

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• 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: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss
3.3663	0.2126	300	2.4418
2.6894	0.4252	600	2.1777
2.3458	0.6378	900	1.9197
2.2044	0.8505	1200	1.7413
1.8493	1.0631	1500	1.6080
1.7591	1.2757	1800	1.5205
1.7067	1.4883	2100	1.4153
1.5728	1.7009	2400	1.3224
1.4995	1.9135	2700	1.2258
1.2553	2.1262	3000	1.1618
1.2354	2.3388	3300	1.0915
1.1576	2.5514	3600	1.0160
1.1443	2.7640	3900	0.9424
1.1236	2.9766	4200	0.8838
0.9129	3.1892	4500	0.8344
0.9065	3.4018	4800	0.7887
0.8752	3.6145	5100	0.7340
0.8206	3.8271	5400	0.6945
0.7643	4.0397	5700	0.6396
0.6853	4.2523	6000	0.6001
0.6727	4.4649	6300	0.5610
0.6436	4.6775	6600	0.5249
0.6089	4.8901	6900	0.4907
0.5272	5.1028	7200	0.4541
0.5080	5.3154	7500	0.4338
0.5104	5.5280	7800	0.4078
0.4879	5.7406	8100	0.3836
0.4876	5.9532	8400	0.3607
0.4190	6.1658	8700	0.3432
0.4284	6.3785	9000	0.3269
0.4111	6.5911	9300	0.3130
0.3887	6.8037	9600	0.3000
0.3718	7.0163	9900	0.2863
0.3324	7.2289	10200	0.2785
0.3407	7.4415	10500	0.2731
0.3423	7.6541	10800	0.2673
0.3520	7.8668	11100	0.2655
0.3430	8.0	11288	0.2647

Framework versions

• Transformers 5.10.2
• Pytorch 2.11.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2