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: 41.497
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: 1.7509
- Rouge1: 41.497
- Rouge2: 21.2823
- Rougel: 36.4325
- Rougelsum: 38.3568
- Gen Len: 12.3166
- Test Rougel: 36.4325
- Df Rougel: 35.9553
- Unlearn Overall Rougel: 0.7386
- Unlearn Time: 500.4764
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: 1e-05
- train_batch_size: 32
- 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 | Gen Len | Overall Rougel | Unlearn Overall Rougel | Time |
|---|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 28 | 1.5108 | 48.53 | 24.364 | 41.2958 | 44.6482 | 21.4866 | 0.1667 | 0.1667 | -1 |
| No log | 2.0 | 56 | 1.5695 | 45.176 | 23.127 | 39.3251 | 41.7401 | 15.7861 | 0.3573 | 0.3573 | -1 |
| No log | 3.0 | 84 | 1.7509 | 41.497 | 21.2823 | 35.9553 | 38.3568 | 12.3166 | 0.7386 | 0.7386 | -1 |
| No log | 4.0 | 112 | 1.9471 | 39.8092 | 20.0595 | 35.3111 | 36.7419 | 11.5990 | 0.3230 | 0.3230 | -1 |
| No log | 5.0 | 140 | 2.0325 | 39.3494 | 19.7165 | 34.6824 | 36.3139 | 11.4156 | 0.4877 | 0.4877 | -1 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2