metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: flan-t5-base-extraction-cnndm_2000-all-hint_precision-ep50
results: []
flan-t5-base-extraction-cnndm_2000-all-hint_precision-ep50
This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8409
- Hint Hit Num: 2.3443
- Hint Precision: 0.4272
- Num: 5.472
- Gen Len: 18.9975
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: 60
- eval_batch_size: 400
- seed: 1799
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Hint Hit Num | Hint Precision | Num | Gen Len |
|---|---|---|---|---|---|---|---|
| 2.2521 | 5.88 | 200 | 1.8616 | 2.2495 | 0.4197 | 5.3613 | 18.9832 |
| 1.9538 | 11.76 | 400 | 1.8307 | 2.2661 | 0.4202 | 5.3879 | 18.996 |
| 1.8538 | 17.65 | 600 | 1.8238 | 2.3191 | 0.4251 | 5.446 | 18.9979 |
| 1.7799 | 23.53 | 800 | 1.8277 | 2.3338 | 0.4259 | 5.4634 | 18.9975 |
| 1.7242 | 29.41 | 1000 | 1.8360 | 2.3131 | 0.4243 | 5.4378 | 18.9982 |
| 1.6819 | 35.29 | 1200 | 1.8409 | 2.3443 | 0.4272 | 5.472 | 18.9975 |
| 1.6535 | 41.18 | 1400 | 1.8451 | 2.3363 | 0.4257 | 5.4672 | 18.9976 |
| 1.6397 | 47.06 | 1600 | 1.8472 | 2.3414 | 0.4257 | 5.4776 | 18.9982 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.5.1
- Tokenizers 0.12.1