gpt2_small_expandedbabyLM_25M_44

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

• Loss: 2.9738

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: 44
• 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
4.649	1.0	1272	4.0041
4.0422	2.0	2544	3.5217
3.7182	3.0	3816	3.3105
3.545	4.0	5088	3.1834
3.434	5.0	6360	3.1132
3.3436	6.0	7632	3.0681
3.2745	7.0	8904	3.0341
3.2176	8.0	10176	3.0149
3.151	9.0	11448	3.0002
3.1086	10.0	12720	2.9875
3.0671	11.0	13992	2.9798
3.0259	12.0	15264	2.9761
2.9978	13.0	16536	2.9738
2.9599	14.0	17808	2.9743
2.9231	15.0	19080	2.9753
2.8929	16.0	20352	2.9779

Framework versions

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