metadata
tags:
- simplification
- generated_from_trainer
metrics:
- rouge
model-index:
- name: marimari-r2r-mlsum-clara-med
results: []
marimari-r2r-mlsum-clara-med
This model is a fine-tuned version of IIC/marimari-r2r-mlsum on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.9276
- Rouge1: 43.1543
- Rouge2: 24.9453
- Rougel: 37.4907
- Rougelsum: 37.6959
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: 5.6e-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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 190 | 2.3405 | 42.5983 | 25.1109 | 37.6327 | 37.7257 |
| No log | 2.0 | 380 | 2.2954 | 41.9792 | 23.9766 | 36.3881 | 36.5226 |
| 1.976 | 3.0 | 570 | 2.4302 | 42.0317 | 23.9135 | 36.186 | 36.3812 |
| 1.976 | 4.0 | 760 | 2.7029 | 41.7418 | 23.7318 | 36.2048 | 36.3403 |
| 0.6481 | 5.0 | 950 | 2.9547 | 41.2054 | 22.9037 | 35.1364 | 35.3168 |
| 0.6481 | 6.0 | 1140 | 3.1709 | 41.0444 | 23.2019 | 35.7206 | 35.8829 |
| 0.6481 | 7.0 | 1330 | 3.2556 | 41.3295 | 22.6827 | 35.2777 | 35.4701 |
| 0.1485 | 8.0 | 1520 | 3.3117 | 41.068 | 22.965 | 35.5507 | 35.6491 |
| 0.1485 | 9.0 | 1710 | 3.4171 | 41.5945 | 23.6423 | 35.8899 | 36.0442 |
| 0.0725 | 10.0 | 1900 | 3.4981 | 41.1163 | 23.0651 | 35.6205 | 35.6596 |
| 0.0725 | 11.0 | 2090 | 3.5086 | 40.9784 | 22.9125 | 35.182 | 35.5205 |
| 0.0725 | 12.0 | 2280 | 3.5503 | 41.6038 | 23.3975 | 36.0071 | 36.2095 |
| 0.0425 | 13.0 | 2470 | 3.6113 | 42.0039 | 24.0294 | 36.4882 | 36.6313 |
| 0.0425 | 14.0 | 2660 | 3.6253 | 41.3012 | 23.1452 | 35.5444 | 35.761 |
| 0.0291 | 15.0 | 2850 | 3.6247 | 42.1477 | 24.3389 | 36.4346 | 36.6004 |
| 0.0291 | 16.0 | 3040 | 3.6683 | 42.6205 | 24.3544 | 36.776 | 36.9848 |
| 0.0291 | 17.0 | 3230 | 3.7544 | 41.9877 | 24.069 | 36.6296 | 36.9115 |
| 0.0166 | 18.0 | 3420 | 3.7562 | 41.8586 | 23.6088 | 36.271 | 36.4634 |
| 0.0166 | 19.0 | 3610 | 3.7687 | 43.2161 | 25.0204 | 37.5484 | 37.759 |
| 0.0088 | 20.0 | 3800 | 3.7907 | 42.8482 | 24.8476 | 37.1841 | 37.4456 |
| 0.0088 | 21.0 | 3990 | 3.8260 | 42.3613 | 24.3827 | 36.6921 | 36.8898 |
| 0.0088 | 22.0 | 4180 | 3.8367 | 42.6367 | 24.6803 | 37.0963 | 37.3301 |
| 0.0039 | 23.0 | 4370 | 3.8613 | 42.8326 | 25.0972 | 37.4584 | 37.6063 |
| 0.0039 | 24.0 | 4560 | 3.8716 | 43.043 | 24.7042 | 37.4917 | 37.6845 |
| 0.0028 | 25.0 | 4750 | 3.8881 | 42.9107 | 25.0261 | 37.3744 | 37.6019 |
| 0.0028 | 26.0 | 4940 | 3.9005 | 42.8922 | 24.8232 | 37.4217 | 37.5928 |
| 0.0028 | 27.0 | 5130 | 3.9054 | 43.1217 | 25.1892 | 37.6801 | 37.8118 |
| 0.0017 | 28.0 | 5320 | 3.9159 | 43.3466 | 25.1834 | 37.7026 | 37.9333 |
| 0.0017 | 29.0 | 5510 | 3.9240 | 43.1974 | 25.0535 | 37.6958 | 37.9008 |
| 0.0012 | 30.0 | 5700 | 3.9276 | 43.1543 | 24.9453 | 37.4907 | 37.6959 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0
- Datasets 2.8.0
- Tokenizers 0.12.1