lab9_model

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9260

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	50	2.7295
No log	2.0	100	1.9478
No log	3.0	150	1.5205
No log	4.0	200	1.3049
No log	5.0	250	1.1897
No log	6.0	300	0.9814
No log	7.0	350	0.9855
No log	8.0	400	0.9473
No log	9.0	450	0.9239
1.3271	10.0	500	0.9260

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2