metadata
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: flan-t5-large-extraction-cnndm_4000-all
results: []
flan-t5-large-extraction-cnndm_4000-all
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7531
- Rouge1: 35.0348
- Rouge2: 15.5615
- Rougel: 30.2628
- Rougelsum: 30.218
- Gen Len: 18.994
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: 8
- eval_batch_size: 24
- seed: 1799
- 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 | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.6013 | 0.4 | 200 | 1.7818 | 34.9655 | 15.0698 | 29.8381 | 29.7984 | 19.0 |
| 1.5864 | 0.8 | 400 | 1.7662 | 33.9055 | 14.3357 | 29.3382 | 29.3206 | 19.0 |
| 1.5214 | 1.2 | 600 | 1.7988 | 34.856 | 15.4214 | 29.9006 | 29.8346 | 19.0 |
| 1.4759 | 1.6 | 800 | 1.8195 | 33.7856 | 14.6215 | 29.2806 | 29.2144 | 19.0 |
| 1.5068 | 2.0 | 1000 | 1.7686 | 34.828 | 14.8614 | 29.761 | 29.7316 | 18.998 |
| 1.5696 | 2.4 | 1200 | 1.7531 | 35.0348 | 15.5615 | 30.2628 | 30.218 | 18.994 |
| 1.5671 | 2.8 | 1400 | 1.7651 | 34.0963 | 15.2973 | 29.8032 | 29.7499 | 19.0 |
| 1.5385 | 3.2 | 1600 | 1.7834 | 33.9286 | 14.8702 | 29.2844 | 29.2384 | 19.0 |
| 1.4972 | 3.6 | 1800 | 1.7808 | 34.6569 | 15.1071 | 29.8532 | 29.8168 | 19.0 |
| 1.4991 | 4.0 | 2000 | 1.7640 | 34.7095 | 15.0358 | 29.6992 | 29.672 | 19.0 |
| 1.4504 | 4.4 | 2200 | 1.7944 | 34.9119 | 15.3942 | 29.9696 | 29.9097 | 19.0 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1