gpt2_small_expandedbabyLM_100M_43

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

• Loss: 2.7602

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: 43
• 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
3.5647	1.0	5083	3.1769
3.2987	2.0	10166	2.9774
3.1831	3.0	15249	2.9004
3.1133	4.0	20332	2.8601
3.0712	5.0	25415	2.8346
3.0273	6.0	30498	2.8154
2.9986	7.0	35581	2.8037
2.9722	8.0	40664	2.7926
2.9433	9.0	45747	2.7850
2.9198	10.0	50830	2.7810
2.9051	11.0	55913	2.7749
2.8808	12.0	60996	2.7715
2.8653	13.0	66079	2.7689
2.8439	14.0	71162	2.7663
2.8355	15.0	76245	2.7656
2.8167	16.0	81328	2.7631
2.7977	17.0	86411	2.7611
2.7798	18.0	91494	2.7608
2.7644	19.0	96577	2.7602
2.7498	20.0	101660	2.7604

Framework versions

• Transformers 4.30.2
• Pytorch 2.11.0+cu130
• Datasets 4.1.1
• Tokenizers 0.13.3