|
--- |
|
license: apache-2.0 |
|
base_model: anandNakat/bart_math_solver |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bart_math_solver |
|
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_math_solver |
|
|
|
This model is a fine-tuned version of [anandNakat/bart_math_solver](https://huggingface.co/anandNakat/bart_math_solver) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7365 |
|
|
|
## 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: 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| No log | 1.0 | 221 | 0.6829 | |
|
| No log | 2.0 | 442 | 0.4829 | |
|
| 0.2857 | 3.0 | 663 | 1.2298 | |
|
| 0.2857 | 4.0 | 884 | 0.4878 | |
|
| 0.2399 | 5.0 | 1105 | 1.1191 | |
|
| 0.2399 | 6.0 | 1326 | 0.6093 | |
|
| 0.1495 | 7.0 | 1547 | 0.5928 | |
|
| 0.1495 | 8.0 | 1768 | 0.5647 | |
|
| 0.1495 | 9.0 | 1989 | 0.6989 | |
|
| 0.0935 | 10.0 | 2210 | 0.7365 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
