electra-case-16

This model is a fine-tuned version of amr8ta/electra-case-16 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3250
• Accuracy: 0.9

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: 1.5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 224
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	44	0.3311	0.8733
No log	2.0	88	0.3448	0.8667
No log	3.0	132	0.3250	0.9
No log	4.0	176	0.3456	0.9
No log	5.0	220	0.3695	0.9067
No log	6.0	264	0.4012	0.8933
No log	7.0	308	0.3983	0.8933
No log	8.0	352	0.4132	0.8933
No log	9.0	396	0.4336	0.9067
No log	10.0	440	0.4263	0.8933
No log	11.0	484	0.4124	0.9
0.0318	12.0	528	0.4278	0.8933
0.0318	13.0	572	0.4593	0.8933
0.0318	14.0	616	0.4477	0.8933
0.0318	15.0	660	0.4505	0.8933
0.0318	16.0	704	0.4525	0.8933

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0