gpt2_small_expandedbabyLM_25M_42

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

• Loss: 2.9741
• Accuracy: 0.4568

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: 256
• eval_batch_size: 256
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 4000
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
4.6449	1.0	1272	4.0085	0.3801
4.0272	2.0	2544	3.5140	0.4116
3.7172	3.0	3816	3.3074	0.4253
3.5442	4.0	5088	3.1836	0.4342
3.4316	5.0	6360	3.1111	0.4416
3.3438	6.0	7632	3.0669	0.4453
3.2775	7.0	8904	3.0341	0.4485
3.2134	8.0	10176	3.0115	0.4511
3.16	9.0	11448	2.9964	0.4528
3.111	10.0	12720	2.9854	0.4542
3.0673	11.0	13992	2.9790	0.4555
3.0274	12.0	15264	2.9757	0.4558
2.9901	13.0	16536	2.9742	0.4567
2.9555	14.0	17808	2.9741	0.4568
2.9291	15.0	19080	2.9744	0.4570
2.8978	16.0	20352	2.9771	0.4571

Framework versions

• Transformers 4.30.2
• Pytorch 2.10.0+cu128
• Datasets 4.1.1
• Tokenizers 0.13.3