gmra_model_gpt2_11082023T140034

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

• Loss: 0.3032
• Accuracy: 0.8937

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
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• 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	Accuracy
No log	1.0	71	0.7347	0.7487
No log	1.99	142	0.4817	0.8251
No log	2.99	213	0.4200	0.8533
No log	4.0	285	0.4045	0.8524
No log	5.0	356	0.3576	0.8761
No log	5.99	427	0.3160	0.8875
No log	6.99	498	0.2928	0.8998
0.734	8.0	570	0.3118	0.8910
0.734	9.0	641	0.3101	0.8893
0.734	9.96	710	0.3032	0.8937

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3