metadata
license: apache-2.0
base_model: google/flan-t5-large
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: flan-t5-large-mawpnli-calcx-nli-pt
results: []
flan-t5-large-mawpnli-calcx-nli-pt
This model is a fine-tuned version of google/flan-t5-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1217
- Rouge1: 95.7098
- Rouge2: 89.9271
- Rougel: 95.5836
- Rougelsum: 95.5842
- Gen Len: 10.9151
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: 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.2279 | 1.0 | 819 | 0.1290 | 95.075 | 87.8764 | 94.7902 | 94.8057 | 10.7978 |
| 0.0612 | 2.0 | 1638 | 0.1012 | 95.6219 | 89.6809 | 95.4399 | 95.4521 | 10.9029 |
| 0.0418 | 3.0 | 2457 | 0.0972 | 95.7709 | 90.1703 | 95.613 | 95.637 | 10.9328 |
| 0.0272 | 4.0 | 3276 | 0.1174 | 95.7478 | 90.1332 | 95.5931 | 95.6069 | 10.9395 |
| 0.0215 | 5.0 | 4095 | 0.1217 | 95.7098 | 89.9271 | 95.5836 | 95.5842 | 10.9151 |
Framework versions
- Transformers 4.35.2
- Pytorch 1.12.1+cu113
- Datasets 2.15.0
- Tokenizers 0.15.0