metadata
license: apache-2.0
base_model: google/long-t5-tglobal-base
tags:
- generated_from_trainer
metrics:
- rouge
- bleu
model-index:
- name: t5_long_tglobal_base_samsum
results: []
t5_long_tglobal_base_samsum
This model is a fine-tuned version of google/long-t5-tglobal-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3947
- Rouge1: 45.5932
- Rouge2: 21.2389
- Rougel: 38.0289
- Rougelsum: 41.6019
- Bleu: 0.0
- Meteor: 0.3517
- Gen Len: 16.8303
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: 2
- total_train_batch_size: 8
- 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 | Bleu | Meteor | Gen Len |
|---|---|---|---|---|---|---|---|---|---|---|
| 1.8835 | 0.9997 | 1841 | 1.4599 | 43.5088 | 19.377 | 36.0811 | 39.65 | 0.0 | 0.3294 | 16.3346 |
| 1.7514 | 2.0 | 3683 | 1.4235 | 44.2039 | 20.1072 | 36.6115 | 40.352 | 0.0 | 0.3385 | 16.8217 |
| 1.6756 | 2.9997 | 5524 | 1.4020 | 44.824 | 20.5361 | 37.1858 | 40.7583 | 0.0 | 0.3431 | 16.6752 |
| 1.6694 | 4.0 | 7366 | 1.3984 | 45.2781 | 21.1846 | 37.7909 | 41.3745 | 0.0 | 0.3504 | 16.7741 |
| 1.6449 | 4.9986 | 9205 | 1.3947 | 45.5932 | 21.2389 | 38.0289 | 41.6019 | 0.0 | 0.3517 | 16.8303 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1