my_qa_model_1

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: 2.4752

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.96	3	5.6227
No log	1.96	6	5.1169
No log	2.96	9	4.5577
No log	3.96	12	3.9969
No log	4.96	15	3.5279
No log	5.96	18	3.1371
No log	6.96	21	2.8468
No log	7.96	24	2.6456
No log	8.96	27	2.5241
No log	9.96	30	2.4752

Framework versions

• Transformers 4.11.3
• Pytorch 1.13.0
• Datasets 1.16.1
• Tokenizers 0.10.3