distilbert_km_100_v2

This model is a fine-tuned version of on the Hartunka/processed_wikitext-103-raw-v1-km-100_v2 dataset. It achieves the following results on the evaluation set:

• Loss: 7.0274
• Accuracy: 0.1543

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: 96
• eval_batch_size: 96
• seed: 10
• optimizer: Use 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: 10000
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
7.039	4.1982	10000	7.2284	0.1497
6.5358	8.3963	20000	7.0446	0.1528
6.2663	12.5945	30000	7.2460	0.1541
6.1164	16.7926	40000	7.4136	0.1521
6.0315	20.9908	50000	7.3543	0.1515

Framework versions

• Transformers 4.50.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.21.1