cropwiz_qa_model

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

• Loss: 2.9531

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 27

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	6	5.5539
No log	2.0	12	4.8899
No log	3.0	18	4.0865
No log	4.0	24	3.6266
No log	5.0	30	3.3544
No log	6.0	36	3.1559
No log	7.0	42	2.9612
No log	8.0	48	2.9628
No log	9.0	54	2.9661
No log	10.0	60	2.9657
No log	11.0	66	2.9469
No log	12.0	72	2.9327
No log	13.0	78	2.9189
No log	14.0	84	2.9100
No log	15.0	90	2.9095
No log	16.0	96	2.9215
No log	17.0	102	2.9453
No log	18.0	108	2.9371
No log	19.0	114	2.9247
No log	20.0	120	2.9409
No log	21.0	126	2.9985
No log	22.0	132	2.9990
No log	23.0	138	2.9988
No log	24.0	144	2.9857
No log	25.0	150	2.9716
No log	26.0	156	2.9567
No log	27.0	162	2.9531

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1