metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: amtibot0
results: []
amtibot0
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.7046
- Rouge1: 0.3003
- Rouge2: 0.1181
- Rougel: 0.2653
- Rougelsum: 0.2653
- Gen Len: 19.0
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: 32
- eval_batch_size: 32
- 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 | 10 | 4.1094 | 0.3037 | 0.1191 | 0.2643 | 0.2644 | 19.0 |
| No log | 2.0 | 20 | 3.8791 | 0.3019 | 0.1174 | 0.2645 | 0.2644 | 19.0 |
| No log | 3.0 | 30 | 3.7484 | 0.3031 | 0.1202 | 0.2678 | 0.268 | 19.0 |
| No log | 4.0 | 40 | 3.7046 | 0.3003 | 0.1181 | 0.2653 | 0.2653 | 19.0 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2