78 lines
2.3 KiB
Markdown
78 lines
2.3 KiB
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- generated_from_trainer
|
||
|
|
model-index:
|
||
|
|
- name: candor_np_13
|
||
|
|
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. -->
|
||
|
|
|
||
|
|
# candor_np_13
|
||
|
|
|
||
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
||
|
|
It achieves the following results on the evaluation set:
|
||
|
|
- Loss: 4.4624
|
||
|
|
|
||
|
|
## 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: 0.0001
|
||
|
|
- train_batch_size: 256
|
||
|
|
- eval_batch_size: 256
|
||
|
|
- seed: 13
|
||
|
|
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||
|
|
- lr_scheduler_type: linear
|
||
|
|
- lr_scheduler_warmup_steps: 500
|
||
|
|
- num_epochs: 20
|
||
|
|
- mixed_precision_training: Native AMP
|
||
|
|
|
||
|
|
### Training results
|
||
|
|
|
||
|
|
| Training Loss | Epoch | Step | Validation Loss |
|
||
|
|
|:-------------:|:-----:|:----:|:---------------:|
|
||
|
|
| 5.762 | 1.0 | 422 | 4.7811 |
|
||
|
|
| 4.6298 | 2.0 | 844 | 4.6029 |
|
||
|
|
| 4.5095 | 3.0 | 1266 | 4.5221 |
|
||
|
|
| 4.4388 | 4.0 | 1688 | 4.4752 |
|
||
|
|
| 4.3851 | 5.0 | 2110 | 4.4421 |
|
||
|
|
| 4.3391 | 6.0 | 2532 | 4.4180 |
|
||
|
|
| 4.2975 | 7.0 | 2954 | 4.4000 |
|
||
|
|
| 4.258 | 8.0 | 3376 | 4.3873 |
|
||
|
|
| 4.2193 | 9.0 | 3798 | 4.3806 |
|
||
|
|
| 4.1807 | 10.0 | 4220 | 4.3781 |
|
||
|
|
| 4.1418 | 11.0 | 4642 | 4.3790 |
|
||
|
|
| 4.1029 | 12.0 | 5064 | 4.3839 |
|
||
|
|
| 4.0643 | 13.0 | 5486 | 4.3914 |
|
||
|
|
| 4.0259 | 14.0 | 5908 | 4.4026 |
|
||
|
|
| 3.9896 | 15.0 | 6330 | 4.4131 |
|
||
|
|
| 3.9551 | 16.0 | 6752 | 4.4276 |
|
||
|
|
| 3.9231 | 17.0 | 7174 | 4.4376 |
|
||
|
|
| 3.8953 | 18.0 | 7596 | 4.4503 |
|
||
|
|
| 3.8731 | 19.0 | 8018 | 4.4567 |
|
||
|
|
| 3.8566 | 20.0 | 8440 | 4.4624 |
|
||
|
|
|
||
|
|
|
||
|
|
### Framework versions
|
||
|
|
|
||
|
|
- Transformers 4.56.1
|
||
|
|
- Pytorch 2.8.0+cu128
|
||
|
|
- Datasets 4.0.0
|
||
|
|
- Tokenizers 0.22.0
|