gmra_model_gpt2_11082023T144604

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

• Loss: 0.8224
• Accuracy: 0.8972

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: 0.002
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• 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	0.4753	0.8946
No log	1.99	142	0.5597	0.8937
No log	2.99	213	0.6239	0.9060
No log	4.0	285	0.6510	0.9007
No log	5.0	356	0.7054	0.8998
No log	5.99	427	0.8432	0.8972
No log	6.99	498	0.8831	0.8972
0.0359	8.0	570	0.8322	0.8963
0.0359	9.0	641	0.8125	0.8954
0.0359	9.96	710	0.8224	0.8972

Framework versions

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