tiny_bert_rand_10_v1

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

• Loss: 8.5547
• Accuracy: 0.1530

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
8.4297	4.1982	10000	8.5470	0.1506
8.1384	8.3963	20000	8.6191	0.1527
7.8049	12.5945	30000	8.9257	0.1533
7.317	16.7926	40000	9.5911	0.1519
6.9107	20.9908	50000	10.2223	0.1510

Framework versions

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