transfer_learning_gpt2_xl
Collection
21 items
•
Updated
This model is a fine-tuned version of openai-community/gpt2-xl on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Micro | Auc |
---|---|---|---|---|---|---|
0.6949 | 1.0 | 37 | 0.6277 | 0.6607 | 0.6607 | 0.7041 |
0.4825 | 2.0 | 74 | 0.6032 | 0.6838 | 0.6838 | 0.7595 |
0.3958 | 3.0 | 111 | 0.6006 | 0.6881 | 0.6881 | 0.7734 |
0.2961 | 4.0 | 148 | 0.6529 | 0.6959 | 0.6959 | 0.7822 |
0.2 | 5.0 | 185 | 0.7515 | 0.6985 | 0.6985 | 0.7788 |
0.1849 | 6.0 | 222 | 0.8221 | 0.6993 | 0.6993 | 0.7779 |
0.114 | 7.0 | 259 | 0.8569 | 0.7027 | 0.7027 | 0.7844 |
Base model
openai-community/gpt2-xl