<!-- 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. -->
Megagon_step3_tsmtz
This model is a fine-tuned version of tsmatz/mt5_summarize_japanese on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6120
- Rouge1: 0.1897
- Rouge2: 0.0766
- Rougel: 0.1897
- Rougelsum: 0.1916
- Gen Len: 9.5631
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 79 | 1.8495 | 0.1928 | 0.0738 | 0.1918 | 0.1949 | 9.536 |
| No log | 2.0 | 158 | 1.7032 | 0.1975 | 0.0758 | 0.1978 | 0.2004 | 9.5586 |
| No log | 3.0 | 237 | 1.6334 | 0.1883 | 0.0751 | 0.1882 | 0.1901 | 9.5315 |
| No log | 4.0 | 316 | 1.6120 | 0.1897 | 0.0766 | 0.1897 | 0.1916 | 9.5631 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
