gpt2_small_babyLM_100_bigbatch

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

• Loss: 3.1462
• Accuracy: 0.4419

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: 128
• eval_batch_size: 128
• 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.9337	1.0	1606	3.9849	0.3807
3.4681	2.0	3212	3.5638	0.4060
3.255	3.0	4818	3.3811	0.4190
3.1262	4.0	6424	3.2809	0.4278
3.0298	5.0	8030	3.2220	0.4326
2.9616	6.0	9636	3.1861	0.4366
2.8886	7.0	11242	3.1659	0.4390
2.8312	8.0	12848	3.1516	0.4407
2.7643	9.0	14454	3.1457	0.4416
2.7283	10.0	16060	3.1462	0.4419

Framework versions

• Transformers 4.30.2
• Pytorch 2.9.1+cu128
• Datasets 4.1.1
• Tokenizers 0.13.3