gpt2-case-12

This model is a fine-tuned version of amr8ta/gpt2-case-25 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4168
• Accuracy: 0.8867

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: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	44	0.4447	0.86
No log	2.0	88	0.4168	0.8867
No log	3.0	132	0.4203	0.88
No log	4.0	176	0.4302	0.88
No log	5.0	220	0.4739	0.8733
No log	6.0	264	0.4493	0.8867
No log	7.0	308	0.4630	0.9
No log	8.0	352	0.4853	0.8867
No log	9.0	396	0.5138	0.8867
No log	10.0	440	0.4921	0.8867
No log	11.0	484	0.4986	0.8867
0.1288	12.0	528	0.4993	0.8867

Framework versions

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