|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: ro-sequence |
|
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. --> |
|
|
|
# ro-sequence |
|
|
|
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: 815.9874 |
|
- Precision: 0.7802 |
|
- Recall: 0.8225 |
|
- F1: 0.8008 |
|
|
|
## 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: 4e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 64 |
|
- seed: 352269 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 30 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:| |
|
| 798.342 | 1.0 | 125 | 619.5866 | 0.7472 | 0.7369 | 0.7420 | |
|
| 377.8265 | 2.0 | 250 | 521.1552 | 0.7833 | 0.7998 | 0.7915 | |
|
| 288.2568 | 3.0 | 375 | 559.4092 | 0.7469 | 0.8145 | 0.7792 | |
|
| 192.2052 | 4.0 | 500 | 555.9223 | 0.8252 | 0.7889 | 0.8066 | |
|
| 128.4364 | 5.0 | 625 | 719.3274 | 0.7848 | 0.8042 | 0.7944 | |
|
| 86.742 | 6.0 | 750 | 797.8254 | 0.7391 | 0.8281 | 0.7811 | |
|
| 62.8087 | 7.0 | 875 | 815.9874 | 0.7802 | 0.8225 | 0.8008 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|
