interview_electra

This model is a fine-tuned version of mrm8488/electra-small-finetuned-squadv2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.6205
• Accuracy: 0.8981

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: 2
• eval_batch_size: 2
• 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	Accuracy
No log	1.0	54	2.2879	0.1481
No log	2.0	108	2.2626	0.2963
No log	3.0	162	2.2317	0.3704
No log	4.0	216	2.1939	0.3704
No log	5.0	270	2.1577	0.3796
No log	6.0	324	2.0902	0.5741
No log	7.0	378	2.0270	0.7407
No log	8.0	432	1.9740	0.7222
No log	9.0	486	1.9228	0.7685
2.1738	10.0	540	1.8774	0.7778
2.1738	11.0	594	1.8201	0.8519
2.1738	12.0	648	1.7920	0.8611
2.1738	13.0	702	1.7574	0.8333
2.1738	14.0	756	1.7125	0.8704
2.1738	15.0	810	1.6907	0.8611
2.1738	16.0	864	1.6571	0.8981
2.1738	17.0	918	1.6424	0.8981
2.1738	18.0	972	1.6284	0.8981
1.7996	19.0	1026	1.6225	0.8981
1.7996	20.0	1080	1.6205	0.8981

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1