metadata
license: apache-2.0
base_model: google/mt5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mt5-small-finetuned-b8-10
results: []
mt5-small-finetuned-b8-10
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.7340
- Rouge1: 0.0359
- Rouge2: 0.0077
- Rougel: 0.0357
- Rougelsum: 0.0357
- Gen Len: 10.8384
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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 | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 12.4116 | 1.0 | 1357 | 3.3739 | 0.0033 | 0.0002 | 0.0033 | 0.0033 | 16.3309 |
| 1.7237 | 2.0 | 2714 | 1.4076 | 0.0022 | 0.0 | 0.0021 | 0.0022 | 4.5805 |
| 1.4447 | 3.0 | 4071 | 1.2431 | 0.0031 | 0.0 | 0.0031 | 0.0031 | 4.0912 |
| 1.3493 | 4.0 | 5428 | 1.2140 | 0.0247 | 0.0026 | 0.0248 | 0.0247 | 7.3331 |
| 1.2809 | 5.0 | 6785 | 3.7340 | 0.0359 | 0.0077 | 0.0357 | 0.0357 | 10.8384 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3