my_awesome_qa_model

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.5971

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: 2e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• 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
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	63	3.4355
No log	2.0	126	2.6230
No log	3.0	189	1.8876
No log	4.0	252	1.6358
No log	5.0	315	1.5591
No log	6.0	378	1.5578
No log	7.0	441	1.5629
1.9367	8.0	504	1.5743
1.9367	9.0	567	1.5862
1.9367	10.0	630	1.5971

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0