metadata
tags:
- generated_from_trainer
model-index:
- name: baseline
results: []
baseline
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4307
- Exact Match: 0.0
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: 0.001
- train_batch_size: 100
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 400
- optimizer: Adam with betas=(0.98,0.999) and epsilon=1e-08
- lr_scheduler_type: inverse_sqrt
- lr_scheduler_warmup_steps: 4000
- num_epochs: 20
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Exact Match |
|---|---|---|---|---|
| 6.3427 | 1.0 | 25 | 5.7961 | 0.0 |
| 5.7757 | 2.0 | 50 | 4.8370 | 0.0 |
| 5.0702 | 3.0 | 75 | 4.3284 | 0.0 |
| 4.6064 | 4.0 | 100 | 4.0447 | 0.0 |
| 4.3415 | 5.0 | 125 | 3.8892 | 0.0 |
| 4.1863 | 6.0 | 150 | 3.7803 | 0.0 |
| 4.0684 | 7.0 | 175 | 3.6724 | 0.0 |
| 3.9449 | 8.0 | 200 | 3.5356 | 0.0 |
| 3.7922 | 9.0 | 225 | 3.3716 | 0.0 |
| 3.6343 | 10.0 | 250 | 3.2232 | 0.0 |
| 3.4833 | 11.0 | 275 | 3.0938 | 0.0 |
| 3.3374 | 12.0 | 300 | 2.9880 | 0.0 |
| 3.2006 | 13.0 | 325 | 2.8960 | 0.0 |
| 3.0796 | 14.0 | 350 | 2.8199 | 0.0 |
| 2.9739 | 15.0 | 375 | 2.7270 | 0.0 |
| 2.8824 | 16.0 | 400 | 2.6369 | 0.0 |
| 2.8 | 17.0 | 425 | 2.5811 | 0.0 |
| 2.7323 | 18.0 | 450 | 2.5184 | 0.0 |
| 2.6596 | 19.0 | 475 | 2.4946 | 0.0 |
| 2.5931 | 20.0 | 500 | 2.4307 | 0.0 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0