metadata
base_model: google-t5/t5-base
datasets:
- samsum
library_name: peft
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: my-t5-summarization-model
results: []
my-t5-summarization-model
This model is a fine-tuned version of google-t5/t5-base on the samsum dataset. It achieves the following results on the evaluation set:
- Loss: 0.2478
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: 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 17.2263 | 1.0 | 74 | 20.5598 |
| 10.8174 | 2.0 | 148 | 12.3219 |
| 2.9638 | 3.0 | 222 | 0.6010 |
| 1.4073 | 4.0 | 296 | 0.2598 |
| 1.1503 | 5.0 | 370 | 0.2604 |
| 1.5418 | 6.0 | 444 | 0.2595 |
| 0.6755 | 7.0 | 518 | 0.2574 |
| 0.833 | 8.0 | 592 | 0.2550 |
| 0.5194 | 9.0 | 666 | 0.2549 |
| 0.7579 | 10.0 | 740 | 0.2553 |
| 0.6712 | 11.0 | 814 | 0.2545 |
| 0.6565 | 12.0 | 888 | 0.2540 |
| 0.262 | 13.0 | 962 | 0.2529 |
| 0.3144 | 14.0 | 1036 | 0.2518 |
| 0.6226 | 15.0 | 1110 | 0.2509 |
| 0.5695 | 16.0 | 1184 | 0.2498 |
| 0.2856 | 17.0 | 1258 | 0.2490 |
| 0.2869 | 18.0 | 1332 | 0.2484 |
| 0.6049 | 19.0 | 1406 | 0.2480 |
| 0.6421 | 20.0 | 1480 | 0.2478 |
Framework versions
- PEFT 0.12.0
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1