|
--- |
|
license: apache-2.0 |
|
base_model: facebook/bart-large |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bart-finetuned-lyrlen-512-tokens |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# bart-finetuned-lyrlen-512-tokens |
|
|
|
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.8349 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 2.3484 | 0.08 | 500 | 2.0373 | |
|
| 2.0389 | 0.17 | 1000 | 1.9391 | |
|
| 2.0181 | 0.25 | 1500 | 1.9070 | |
|
| 1.9238 | 0.33 | 2000 | 1.9121 | |
|
| 1.9005 | 0.42 | 2500 | 1.8966 | |
|
| 1.8814 | 0.5 | 3000 | 1.8816 | |
|
| 1.8839 | 0.58 | 3500 | 1.8806 | |
|
| 1.8251 | 0.67 | 4000 | 1.9091 | |
|
| 1.8454 | 0.75 | 4500 | 1.8798 | |
|
| 1.8264 | 0.83 | 5000 | 1.8769 | |
|
| 1.8545 | 0.92 | 5500 | 1.8511 | |
|
| 1.8335 | 1.0 | 6000 | 1.9010 | |
|
| 1.8184 | 1.08 | 6500 | 1.8511 | |
|
| 1.7887 | 1.17 | 7000 | 1.8472 | |
|
| 1.7811 | 1.25 | 7500 | 1.8341 | |
|
| 1.7388 | 1.33 | 8000 | 1.8912 | |
|
| 1.7981 | 1.42 | 8500 | 1.8615 | |
|
| 1.7849 | 1.5 | 9000 | 1.8405 | |
|
| 1.7814 | 1.58 | 9500 | 1.8314 | |
|
| 1.7568 | 1.67 | 10000 | 1.8449 | |
|
| 1.7061 | 1.75 | 10500 | 1.8545 | |
|
| 1.7169 | 1.83 | 11000 | 1.8361 | |
|
| 1.7019 | 1.92 | 11500 | 1.8479 | |
|
| 1.727 | 2.0 | 12000 | 1.8741 | |
|
| 1.7035 | 2.08 | 12500 | 1.8518 | |
|
| 1.7134 | 2.17 | 13000 | 1.8361 | |
|
| 1.6809 | 2.25 | 13500 | 1.8279 | |
|
| 1.7093 | 2.33 | 14000 | 1.8428 | |
|
| 1.7437 | 2.42 | 14500 | 1.8424 | |
|
| 1.6968 | 2.5 | 15000 | 1.8325 | |
|
| 1.661 | 2.58 | 15500 | 1.8337 | |
|
| 1.6542 | 2.67 | 16000 | 1.8282 | |
|
| 1.6607 | 2.75 | 16500 | 1.8300 | |
|
| 1.6427 | 2.83 | 17000 | 1.8389 | |
|
| 1.6821 | 2.92 | 17500 | 1.8242 | |
|
| 1.6968 | 3.0 | 18000 | 1.8376 | |
|
| 1.6716 | 3.08 | 18500 | 1.8302 | |
|
| 1.6706 | 3.17 | 19000 | 1.8326 | |
|
| 1.622 | 3.25 | 19500 | 1.8246 | |
|
| 1.6802 | 3.33 | 20000 | 1.8345 | |
|
| 1.6321 | 3.42 | 20500 | 1.8499 | |
|
| 1.6832 | 3.5 | 21000 | 1.8394 | |
|
| 1.6223 | 3.58 | 21500 | 1.8329 | |
|
| 1.6831 | 3.67 | 22000 | 1.8408 | |
|
| 1.6455 | 3.75 | 22500 | 1.8336 | |
|
| 1.64 | 3.83 | 23000 | 1.8372 | |
|
| 1.663 | 3.92 | 23500 | 1.8340 | |
|
| 1.6 | 4.0 | 24000 | 1.8349 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
