tiny_bert_rand_100_v2

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

• Loss: 10.8907
• Accuracy: 0.1523

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
10.6784	4.1982	10000	10.8779	0.1501
10.0232	8.3963	20000	11.1558	0.1530
9.1752	12.5945	30000	11.7162	0.1537
8.2175	16.7926	40000	12.6584	0.1513
7.4989	20.9908	50000	13.4746	0.1518

Framework versions

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