age_random

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.4612

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: 0.0001
• 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: reduce_lr_on_plateau
• lr_scheduler_warmup_steps: 500
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
4.8574	0.0106	2000	4.1984
4.145	0.0212	4000	3.9833
3.9948	0.0317	6000	3.8724
3.9047	0.0423	8000	3.8042
3.8428	0.0529	10000	3.7519
3.7955	0.0635	12000	3.7141
3.7557	0.0741	14000	3.6856
3.725	0.0847	16000	3.6586
3.6947	0.0952	18000	3.6385
3.6726	0.1058	20000	3.6223
3.6556	0.1164	22000	3.6024
3.6309	0.1270	24000	3.5923
3.619	0.1376	26000	3.5809
3.6045	0.1482	28000	3.5688
3.5854	0.1587	30000	3.5668
3.5793	0.1693	32000	3.5575
3.5685	0.1799	34000	3.5453
3.556	0.1905	36000	3.5405
3.5475	0.2011	38000	3.5332
3.5358	0.2117	40000	3.5293
3.5305	0.2222	42000	3.5237
3.5257	0.2328	44000	3.5184
3.5122	0.2434	46000	3.5163
3.5099	0.2540	48000	3.5092
3.503	0.2646	50000	3.5097
3.494	0.2752	52000	3.5058
3.4923	0.2857	54000	3.5029
3.4839	0.2963	56000	3.4993
3.4794	0.3069	58000	3.4979
3.4784	0.3175	60000	3.4935
3.4688	0.3281	62000	3.4919
3.4672	0.3387	64000	3.4888
3.4651	0.3492	66000	3.4864
3.454	0.3598	68000	3.4848
3.4579	0.3704	70000	3.4826
3.4525	0.3810	72000	3.4789
3.4448	0.3916	74000	3.4794
3.4483	0.4022	76000	3.4779
3.4422	0.4127	78000	3.4766
3.4365	0.4233	80000	3.4745
3.4383	0.4339	82000	3.4725
3.4311	0.4445	84000	3.4713
3.4304	0.4551	86000	3.4709
3.4293	0.4657	88000	3.4679
3.4218	0.4762	90000	3.4673
3.4226	0.4868	92000	3.4682
3.4231	0.4974	94000	3.4639
3.4182	0.5080	96000	3.4659
3.4165	0.5186	98000	3.4674
3.4137	0.5292	100000	3.4611
3.4101	0.5397	102000	3.4653
3.4136	0.5503	104000	3.4648
3.4059	0.5609	106000	3.4612

Framework versions

• Transformers 4.45.2
• Pytorch 2.4.1
• Datasets 3.0.1
• Tokenizers 0.20.1