babylama-gpttoken

This model is a fine-tuned version of babylm/babyllama-100m-2024 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 38.2921

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
30.4256	0.9999	5559	29.8987
38.306	1.9999	11119	37.7677
38.7146	3.0000	16679	37.7375
37.8024	4.0	22239	38.2709
37.35	4.9993	27795	38.2921

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1