021_train_3-2_1B_full_pt_001

This model is a fine-tuned version of gulaschnascher4000/modell-mit-erweitertem-tokenizer-50000_4096_2 on the pretraining_wiki_de_1000000_4096 dataset. It achieves the following results on the evaluation set:

• Loss: 2.1967
• Num Input Tokens Seen: 97766767

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: 1e-05
• train_batch_size: 6
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 48
• optimizer: Use OptimizerNames.ADAFACTOR and the args are: No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1.0

Training results

Framework versions

• Transformers 4.52.4
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1