How_to_fine-tune_a_model_for_common_downstream_tasks_V2

This model is a fine-tuned version of Tural/language-modeling-from-scratch on the squad dataset. It achieves the following results on the evaluation set:

• Loss: 3.4298

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: 24
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
3.647	1.0	3650	3.6697
3.4239	2.0	7300	3.4835
3.2087	3.0	10950	3.4298

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.0
• Datasets 2.14.5
• Tokenizers 0.14.1