metadata
library_name: transformers
license: apache-2.0
base_model: google/mt5-small
tags:
- generated_from_trainer
model-index:
- name: lr_3e-06_batch_4_epoch_5_model
results: []
lr_3e-06_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: 3.9163
- Rouge-1: 17.3664
- Rouge-2: 5.7503
- Rouge-l: 16.1687
- Gen Len: 11.7807
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: 3e-06
- 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 |
|---|---|---|---|---|---|---|---|
| 6.5716 | 1.0 | 2714 | 4.6237 | 15.8545 | 4.4526 | 14.2598 | 18.8185 |
| 5.5876 | 2.0 | 5428 | 4.1738 | 17.5525 | 5.4549 | 15.7657 | 16.4976 |
| 5.3214 | 3.0 | 8142 | 3.9089 | 17.0725 | 5.5016 | 15.8996 | 11.4751 |
| 5.2179 | 4.0 | 10856 | 3.9146 | 17.2716 | 5.7367 | 16.1091 | 11.7639 |
| 5.0379 | 5.0 | 13570 | 3.9163 | 17.3664 | 5.7503 | 16.1687 | 11.7807 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.1.0
- Datasets 2.21.0
- Tokenizers 0.19.1