<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
pretrain_Law_model_vit5_version3
This model is a fine-tuned version of KingLTD/pretrain_Law_model_vit5_version2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1136
- Rouge1: 0.4973
- Rouge2: 0.4075
- Rougel: 0.4532
- Rougelsum: 0.4674
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 245 | 0.1060 | 0.4960 | 0.4069 | 0.4502 | 0.4664 |
| No log | 2.0 | 490 | 0.1070 | 0.4946 | 0.4053 | 0.4484 | 0.4644 |
| 0.146 | 3.0 | 735 | 0.1079 | 0.4908 | 0.3988 | 0.4456 | 0.4601 |
| 0.146 | 4.0 | 980 | 0.1107 | 0.4994 | 0.4094 | 0.4508 | 0.4665 |
| 0.1149 | 5.0 | 1225 | 0.1107 | 0.4944 | 0.4024 | 0.4483 | 0.4635 |
| 0.1149 | 6.0 | 1470 | 0.1126 | 0.4931 | 0.4028 | 0.4478 | 0.4626 |
| 0.0956 | 7.0 | 1715 | 0.1124 | 0.4991 | 0.4108 | 0.4556 | 0.4701 |
| 0.0956 | 8.0 | 1960 | 0.1122 | 0.4944 | 0.4082 | 0.4515 | 0.4655 |
| 0.0822 | 9.0 | 2205 | 0.1133 | 0.4996 | 0.4111 | 0.4557 | 0.4699 |
| 0.0822 | 10.0 | 2450 | 0.1136 | 0.4973 | 0.4075 | 0.4532 | 0.4674 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
