metadata
license: apache-2.0
base_model: facebook/bart-large
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: LLM_Teached_Bart
results: []
LLM_Teached_Bart
This model is a fine-tuned version of facebook/bart-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6728
- Rouge1: 0.3966
- Rouge2: 0.1905
- Rougel: 0.3321
- Rougelsum: 0.3322
- Gen Len: 19.9855
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 1.851 | 1.0 | 1250 | 1.6235 | 0.3808 | 0.1775 | 0.3177 | 0.318 | 19.9855 |
| 1.5876 | 2.0 | 2500 | 1.5937 | 0.389 | 0.1866 | 0.3271 | 0.3274 | 19.9782 |
| 1.3922 | 3.0 | 3750 | 1.5800 | 0.3899 | 0.182 | 0.3244 | 0.3246 | 19.9918 |
| 1.2551 | 4.0 | 5000 | 1.6044 | 0.3852 | 0.1854 | 0.3223 | 0.3227 | 19.9982 |
| 1.1329 | 5.0 | 6250 | 1.6191 | 0.3978 | 0.1923 | 0.3342 | 0.3344 | 19.9855 |
| 1.042 | 6.0 | 7500 | 1.6453 | 0.3956 | 0.192 | 0.3333 | 0.3335 | 19.9864 |
| 0.9665 | 7.0 | 8750 | 1.6554 | 0.3945 | 0.1898 | 0.331 | 0.3312 | 19.9909 |
| 0.9206 | 8.0 | 10000 | 1.6728 | 0.3966 | 0.1905 | 0.3321 | 0.3322 | 19.9855 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.15.0