metadata
library_name: transformers
license: apache-2.0
base_model: google/mt5-base
tags:
- generated_from_trainer
metrics:
- rouge
- bleu
model-index:
- name: mt5-base-qaqg-finetuned-SQuAD-id-ir
results: []
mt5-base-qaqg-finetuned-SQuAD-id-ir
This model is a fine-tuned version of google/mt5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2951
- Rouge1: 0.4537
- Rouge2: 0.2692
- Rougel: 0.4120
- Rougelsum: 0.4144
- Bleu: 0.2295
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: 0.0001
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu |
|---|---|---|---|---|---|---|---|---|
| 1.5663 | 1.0 | 2000 | 1.4508 | 0.4214 | 0.2349 | 0.3787 | 0.3812 | 0.2152 |
| 1.3135 | 2.0 | 4000 | 1.3187 | 0.4432 | 0.2562 | 0.4011 | 0.4033 | 0.2262 |
| 1.1748 | 3.0 | 6000 | 1.2928 | 0.4482 | 0.2641 | 0.4070 | 0.4097 | 0.2255 |
| 1.1115 | 4.0 | 8000 | 1.2927 | 0.4543 | 0.2714 | 0.4128 | 0.4150 | 0.2293 |
| 1.0387 | 5.0 | 10000 | 1.2951 | 0.4537 | 0.2692 | 0.4120 | 0.4144 | 0.2295 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0a0+f70bd71a48.nv24.06
- Datasets 2.21.0
- Tokenizers 0.19.1