base_seed-42_1e-3

This model was trained from scratch on the data/babylm dataset. It achieves the following results on the evaluation set:

• Loss: nan
• Accuracy: 0.0

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: 0.001
• train_batch_size: 32
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 256
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 32000
• num_epochs: 20.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
41630360724688510976.0000	1.0	1824	nan	0.0
0.0	2.0	3648	nan	0.0
0.0	3.0	5472	nan	0.0
0.0	4.0	7296	nan	0.0

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0