tiny_bert_km_5_v1

This model is a fine-tuned version of on the data/processed_wikitext-103-raw-v1-km-5 dataset. It achieves the following results on the evaluation set:

• Loss: 6.3009
• Accuracy: 0.1550

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
6.4666	4.1982	10000	6.4894	0.1503
6.1797	8.3963	20000	6.3096	0.1525
6.059	12.5945	30000	6.3069	0.1536
5.9706	16.7926	40000	6.2870	0.1523
5.9245	20.9908	50000	6.2746	0.1522

Framework versions

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