distilbert_base_lda

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

• Loss: 4.3123
• Accuracy: 0.5700

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 OptimizerNames.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
8.3233	4.1982	10000	8.2422	0.1515
6.1542	8.3963	20000	5.9056	0.3692
4.8606	12.5945	30000	4.7305	0.5129
4.535	16.7926	40000	4.4266	0.5557
4.3967	20.9908	50000	4.3196	0.5676

Framework versions

• Transformers 4.46.1
• Pytorch 2.2.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.1