metadata
tags:
- generated_from_trainer
model-index:
- name: plbart-base-finetuned-ut-generator
results: []
plbart-base-finetuned-ut-generator
This model is a fine-tuned version of uclanlp/plbart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3141
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-06
- 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: 2
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.3625 | 0.09 | 100 | 0.4305 |
0.4651 | 0.18 | 200 | 0.3991 |
0.4273 | 0.27 | 300 | 0.3831 |
0.4021 | 0.36 | 400 | 0.3722 |
0.4101 | 0.44 | 500 | 0.3628 |
0.4004 | 0.53 | 600 | 0.3550 |
0.3877 | 0.62 | 700 | 0.3483 |
0.3835 | 0.71 | 800 | 0.3431 |
0.4012 | 0.8 | 900 | 0.3379 |
0.3537 | 0.89 | 1000 | 0.3343 |
0.3696 | 0.98 | 1100 | 0.3308 |
0.3574 | 1.07 | 1200 | 0.3278 |
0.3474 | 1.16 | 1300 | 0.3255 |
0.3564 | 1.24 | 1400 | 0.3228 |
0.3353 | 1.33 | 1500 | 0.3210 |
0.3233 | 1.42 | 1600 | 0.3191 |
0.3799 | 1.51 | 1700 | 0.3174 |
0.3565 | 1.6 | 1800 | 0.3164 |
0.3281 | 1.69 | 1900 | 0.3156 |
0.3272 | 1.78 | 2000 | 0.3150 |
0.3559 | 1.87 | 2100 | 0.3143 |
0.3486 | 1.96 | 2200 | 0.3141 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2