metadata
license: apache-2.0
base_model: emilstabil/mt5-base_V25775_V44105
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mt5-base_V25775_V44105_V65464
results: []
mt5-base_V25775_V44105_V65464
This model is a fine-tuned version of emilstabil/mt5-base_V25775_V44105 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.2155
- Rouge1: 31.936
- Rouge2: 11.6826
- Rougel: 21.8491
- Rougelsum: 26.1962
- Gen Len: 86.4335
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: 5e-05
- train_batch_size: 3
- eval_batch_size: 3
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.794 | 0.81 | 500 | 2.1891 | 29.9862 | 11.266 | 20.9904 | 24.6444 | 83.9571 |
| 1.7476 | 1.61 | 1000 | 2.1461 | 29.9736 | 10.782 | 20.6739 | 24.663 | 80.7039 |
| 1.7381 | 2.42 | 1500 | 2.1835 | 30.4805 | 11.0774 | 21.0063 | 24.9859 | 85.1545 |
| 1.6956 | 3.23 | 2000 | 2.1836 | 30.0028 | 10.9574 | 20.721 | 24.5095 | 79.6266 |
| 1.6593 | 4.03 | 2500 | 2.1878 | 29.7076 | 10.7504 | 20.4333 | 24.3183 | 77.3948 |
| 1.6416 | 4.84 | 3000 | 2.1937 | 30.4163 | 11.0254 | 20.9501 | 24.8448 | 82.9185 |
| 1.613 | 5.65 | 3500 | 2.2060 | 30.518 | 11.1385 | 21.0192 | 24.9011 | 80.5408 |
| 1.6199 | 6.45 | 4000 | 2.2267 | 30.7458 | 11.2048 | 21.3743 | 25.2027 | 82.6524 |
| 1.5769 | 7.26 | 4500 | 2.2113 | 31.6325 | 11.4758 | 21.3606 | 25.8015 | 88.4292 |
| 1.5765 | 8.06 | 5000 | 2.2101 | 31.3878 | 11.2897 | 21.3136 | 25.729 | 86.4936 |
| 1.5706 | 8.87 | 5500 | 2.2115 | 32.2878 | 11.5704 | 21.9421 | 26.3874 | 91.7768 |
| 1.5625 | 9.68 | 6000 | 2.2145 | 31.5711 | 11.4538 | 21.3608 | 25.8527 | 88.7167 |
| 1.5278 | 10.48 | 6500 | 2.2219 | 30.6581 | 11.2777 | 21.1534 | 25.0079 | 80.9785 |
| 1.5295 | 11.29 | 7000 | 2.2340 | 30.6276 | 11.0522 | 21.1302 | 25.0254 | 82.7854 |
| 1.5286 | 12.1 | 7500 | 2.2155 | 30.614 | 11.4733 | 21.3702 | 25.0853 | 78.309 |
| 1.5138 | 12.9 | 8000 | 2.2298 | 30.6334 | 11.3644 | 21.1625 | 25.0588 | 81.133 |
| 1.4935 | 13.71 | 8500 | 2.2163 | 31.0745 | 11.1841 | 21.1997 | 25.3718 | 84.8412 |
| 1.5309 | 14.52 | 9000 | 2.2133 | 31.0237 | 11.5053 | 21.5787 | 25.6145 | 80.7725 |
| 1.4852 | 15.32 | 9500 | 2.2239 | 31.9443 | 11.5394 | 21.5817 | 26.0822 | 88.2532 |
| 1.5247 | 16.13 | 10000 | 2.2258 | 31.6514 | 11.6206 | 21.5841 | 25.8946 | 85.6052 |
| 1.4931 | 16.94 | 10500 | 2.2205 | 31.522 | 11.5251 | 21.1916 | 25.587 | 87.8069 |
| 1.5085 | 17.74 | 11000 | 2.2110 | 31.4641 | 11.3441 | 21.3223 | 25.7801 | 85.7983 |
| 1.5014 | 18.55 | 11500 | 2.2162 | 31.5727 | 11.6335 | 21.6467 | 25.949 | 84.2918 |
| 1.5057 | 19.35 | 12000 | 2.2155 | 31.936 | 11.6826 | 21.8491 | 26.1962 | 86.4335 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0
- Datasets 2.12.0
- Tokenizers 0.13.3