<!-- 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. -->
Xensword-MT5-Base-Summarizer
This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Rouge1: 0.0159
- Rouge2: 0.0046
- Rougel: 0.0149
- Rougelsum: 0.015
- Gen Len: 9.6688
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 314 | nan | 0.0159 | 0.0046 | 0.0149 | 0.015 | 9.6688 |
| 0.0 | 2.0 | 628 | nan | 0.0159 | 0.0046 | 0.0149 | 0.015 | 9.6688 |
| 0.0 | 3.0 | 942 | nan | 0.0159 | 0.0046 | 0.0149 | 0.015 | 9.6688 |
| 0.0 | 4.0 | 1256 | nan | 0.0159 | 0.0046 | 0.0149 | 0.015 | 9.6688 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
