age_sentence

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

• Loss: 3.4127

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
4.7516	0.0425	2000	4.0094
3.8831	0.0849	4000	3.7839
3.7148	0.1274	6000	3.6747
3.6187	0.1698	8000	3.6089
3.5503	0.2123	10000	3.5638
3.5022	0.2547	12000	3.5323
3.4622	0.2972	14000	3.5102
3.4268	0.3397	16000	3.4906
3.4003	0.3821	18000	3.4741
3.3742	0.4246	20000	3.4613
3.3535	0.4670	22000	3.4514
3.3294	0.5095	24000	3.4427
3.3122	0.5519	26000	3.4370
3.2964	0.5944	28000	3.4273
3.2791	0.6368	30000	3.4252
3.2623	0.6793	32000	3.4226
3.252	0.7218	34000	3.4194
3.2376	0.7642	36000	3.4121
3.2248	0.8067	38000	3.4103
3.2126	0.8491	40000	3.4097
3.2021	0.8916	42000	3.4161
3.1945	0.9340	44000	3.4127

Framework versions

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