distilbert-base-uncased-finetuned-pfe

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: 1.9517

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	6	2.8673
No log	2.0	12	2.7271
No log	3.0	18	2.5814
No log	4.0	24	2.5083
No log	5.0	30	2.3478
No log	6.0	36	2.3432
No log	7.0	42	2.2518
No log	8.0	48	2.2160
No log	9.0	54	2.1958
No log	10.0	60	2.1662
No log	11.0	66	2.1043
No log	12.0	72	2.0557
No log	13.0	78	2.0443
No log	14.0	84	1.9886
No log	15.0	90	1.9999
No log	16.0	96	1.9629
No log	17.0	102	1.9503
No log	18.0	108	1.9439
No log	19.0	114	1.9504
No log	20.0	120	1.9517

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2