lr_5e-05_batch_4_epoch_5_model
This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.2724
- Rouge-1: 24.1093
- Rouge-2: 8.8384
- Rouge-l: 21.5273
- Gen Len: 17.7932
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: 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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge-1 | Rouge-2 | Rouge-l | Gen Len |
|---|---|---|---|---|---|---|---|
| 4.1453 | 1.0 | 2714 | 3.5455 | 21.4499 | 7.2857 | 19.3311 | 17.0664 |
| 3.8393 | 2.0 | 5428 | 3.3963 | 22.7766 | 8.0331 | 20.3856 | 17.5091 |
| 3.7745 | 3.0 | 8142 | 3.3187 | 23.6238 | 8.5224 | 21.0729 | 17.4938 |
| 3.6659 | 4.0 | 10856 | 3.2879 | 24.164 | 8.8808 | 21.5366 | 17.5777 |
| 3.5614 | 5.0 | 13570 | 3.2724 | 24.1093 | 8.8384 | 21.5273 | 17.7932 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.1.0
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 4
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for riiwang/lr_5e-05_batch_4_epoch_5_model
Base model
google/mt5-small