tiny_bert_km_10_v2

This model is a fine-tuned version of on the Hartunka/processed_wikitext-103-raw-v1-km-10_v2 dataset. It achieves the following results on the evaluation set:

• Loss: 6.3428
• Accuracy: 0.1565

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10000
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
6.5128	4.1982	10000	6.4675	0.1478
6.2388	8.3963	20000	6.4157	0.1521
6.1049	12.5945	30000	6.4012	0.1543
6.018	16.7926	40000	6.4879	0.1523
5.9573	20.9908	50000	6.3911	0.1529

Framework versions

• Transformers 4.40.0
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.19.1