This model is a fine-tuned version of google/flan-t5-small on the None 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 | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 3.043 | 1.0 | 1348 | 2.7636 | 34.4245 | 20.9962 | 34.386 | 34.3876 | 15.1150 |
| 2.8078 | 2.0 | 2696 | 2.6540 | 32.5342 | 19.3983 | 32.4966 | 32.4947 | 16.7662 |
| 2.7166 | 3.0 | 4044 | 2.6103 | 32.4564 | 19.3597 | 32.4255 | 32.4355 | 16.6037 |
| 2.6876 | 4.0 | 5392 | 2.5985 | 32.7607 | 19.5507 | 32.7312 | 32.7306 | 16.4212 |
checkpoint-4044/optimizer.pt 616 MBcheckpoint-5392/optimizer.pt 616 MBcheckpoint-4044/pytorch_model.bin 308 MBcheckpoint-5392/pytorch_model.bin 308 MBpytorch_model.bin 308 MBcheckpoint-4044/rng_state.pth 14.6 kBcheckpoint-5392/rng_state.pth 14.6 kBcheckpoint-4044/training_args.bin 4.1 kBcheckpoint-5392/training_args.bin 4.1 kBtraining_args.bin 4.1 kBcheckpoint-4044/scheduler.pt 0.6 kBcheckpoint-5392/scheduler.pt 0.6 kB