metadata
license: apache-2.0
base_model: google/t5-v1_1-base
tags:
- generated_from_trainer
datasets:
- samsum
metrics:
- rouge
model-index:
- name: samsum_42
results:
- task:
name: Summarization
type: summarization
dataset:
name: samsum
type: samsum
metrics:
- name: Rouge1
type: rouge
value: 49.78
samsum_42
This model is a fine-tuned version of google/t5-v1_1-base on the samsum dataset. It achieves the following results on the evaluation set:
- Loss: 1.4769
- Rouge1: 49.78
- Rouge2: 25.0211
- Rougel: 41.3044
- Rougelsum: 45.928
- Gen Len: 24.1523
- Test Rougel: 41.2383
- Df Rougel: 41.8167
- Unlearn Overall Rougel: 0.2108
- Unlearn Time: 4034.7489
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: 32
- eval_batch_size: 64
- 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 | Gen Len | Overall Rougel | Unlearn Overall Rougel | Time |
|---|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 460 | 1.4973 | 48.6265 | 24.2942 | 41.7917 | 44.7761 | 22.6510 | -0.0701 | -0.0701 | -1 |
| No log | 2.0 | 920 | 1.4938 | 48.9671 | 24.4584 | 42.125 | 45.2967 | 24.3021 | -0.2166 | -0.2166 | -1 |
| 1.886 | 3.0 | 1380 | 1.4769 | 49.78 | 25.0211 | 41.8167 | 45.928 | 24.1523 | 0.2108 | 0.2108 | -1 |
| 1.886 | 4.0 | 1840 | 1.4737 | 49.4167 | 24.7497 | 41.9533 | 45.6082 | 23.8464 | 0.0736 | 0.0736 | -1 |
| 1.7917 | 5.0 | 2300 | 1.4701 | 49.5761 | 24.7762 | 42.1164 | 45.7806 | 23.8906 | 0.0526 | 0.0526 | -1 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2