t5-base-finetuned-ner_docred_30
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1900
- Rouge1: 6.698
- Rouge2: 5.261
- Rougel: 6.6835
- Rougelsum: 6.6818
- Gen Len: 20.0
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 125 | 0.5156 | 6.5406 | 4.9855 | 6.4905 | 6.494 | 20.0 |
No log | 2.0 | 250 | 0.3949 | 6.5113 | 4.9122 | 6.4534 | 6.4453 | 20.0 |
No log | 3.0 | 375 | 0.3280 | 6.5165 | 4.9088 | 6.4537 | 6.451 | 20.0 |
0.7311 | 4.0 | 500 | 0.2949 | 6.424 | 4.7298 | 6.3672 | 6.3627 | 20.0 |
0.7311 | 5.0 | 625 | 0.2764 | 6.6189 | 5.1219 | 6.5651 | 6.5672 | 20.0 |
0.7311 | 6.0 | 750 | 0.2633 | 6.628 | 5.1335 | 6.5664 | 6.5721 | 20.0 |
0.7311 | 7.0 | 875 | 0.2547 | 6.5591 | 4.9979 | 6.5075 | 6.5057 | 20.0 |
0.3331 | 8.0 | 1000 | 0.2482 | 6.6612 | 5.1918 | 6.5987 | 6.6068 | 20.0 |
0.3331 | 9.0 | 1125 | 0.2413 | 6.6093 | 5.0954 | 6.5515 | 6.5553 | 20.0 |
0.3331 | 10.0 | 1250 | 0.2357 | 6.6264 | 5.1201 | 6.5681 | 6.5723 | 20.0 |
0.3331 | 11.0 | 1375 | 0.2300 | 6.6487 | 5.1525 | 6.6176 | 6.6177 | 20.0 |
0.2788 | 12.0 | 1500 | 0.2226 | 6.6858 | 5.2325 | 6.6745 | 6.6762 | 20.0 |
0.2788 | 13.0 | 1625 | 0.2166 | 6.6495 | 5.1531 | 6.6378 | 6.6377 | 20.0 |
0.2788 | 14.0 | 1750 | 0.2108 | 6.6807 | 5.2212 | 6.6653 | 6.6664 | 20.0 |
0.2788 | 15.0 | 1875 | 0.2068 | 6.6811 | 5.2248 | 6.6699 | 6.6697 | 20.0 |
0.2435 | 16.0 | 2000 | 0.2030 | 6.6701 | 5.2077 | 6.652 | 6.6492 | 20.0 |
0.2435 | 17.0 | 2125 | 0.1997 | 6.6845 | 5.2334 | 6.6647 | 6.6624 | 20.0 |
0.2435 | 18.0 | 2250 | 0.1978 | 6.6762 | 5.2202 | 6.6571 | 6.6559 | 20.0 |
0.2435 | 19.0 | 2375 | 0.1964 | 6.684 | 5.2358 | 6.6695 | 6.6683 | 20.0 |
0.2188 | 20.0 | 2500 | 0.1957 | 6.6882 | 5.2426 | 6.675 | 6.6735 | 20.0 |
0.2188 | 21.0 | 2625 | 0.1942 | 6.6882 | 5.2426 | 6.675 | 6.6735 | 20.0 |
0.2188 | 22.0 | 2750 | 0.1932 | 6.6935 | 5.2513 | 6.6784 | 6.6762 | 20.0 |
0.2188 | 23.0 | 2875 | 0.1924 | 6.6935 | 5.2513 | 6.6784 | 6.6762 | 20.0 |
0.2052 | 24.0 | 3000 | 0.1918 | 6.6882 | 5.2426 | 6.675 | 6.6735 | 20.0 |
0.2052 | 25.0 | 3125 | 0.1915 | 6.6935 | 5.2513 | 6.6784 | 6.6762 | 20.0 |
0.2052 | 26.0 | 3250 | 0.1908 | 6.698 | 5.261 | 6.6835 | 6.6818 | 20.0 |
0.2052 | 27.0 | 3375 | 0.1905 | 6.698 | 5.261 | 6.6835 | 6.6818 | 20.0 |
0.1977 | 28.0 | 3500 | 0.1901 | 6.698 | 5.261 | 6.6835 | 6.6818 | 20.0 |
0.1977 | 29.0 | 3625 | 0.1900 | 6.698 | 5.261 | 6.6835 | 6.6818 | 20.0 |
0.1977 | 30.0 | 3750 | 0.1900 | 6.698 | 5.261 | 6.6835 | 6.6818 | 20.0 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.1.0.dev20230611+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.