lilt-ruroberta / README.md
Tatiana239's picture
End of training
f157d36
|
raw
history blame
7.41 kB
---
license: mit
tags:
- generated_from_trainer
model-index:
- name: lilt-ruroberta
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. -->
# lilt-ruroberta
This model is a fine-tuned version of [SCUT-DLVCLab/lilt-roberta-en-base](https://huggingface.co/SCUT-DLVCLab/lilt-roberta-en-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2043
- Comment: {'precision': 1.0, 'recall': 0.9444444444444444, 'f1': 0.9714285714285714, 'number': 18}
- Date: {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8}
- Labname: {'precision': 0.6666666666666666, 'recall': 0.8, 'f1': 0.7272727272727272, 'number': 5}
- Laboratory: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2}
- Measure: {'precision': 1.0, 'recall': 0.9230769230769231, 'f1': 0.9600000000000001, 'number': 13}
- Ref Value: {'precision': 0.875, 'recall': 1.0, 'f1': 0.9333333333333333, 'number': 14}
- Result: {'precision': 1.0, 'recall': 0.9285714285714286, 'f1': 0.962962962962963, 'number': 14}
- Overall Precision: 0.9296
- Overall Recall: 0.8919
- Overall F1: 0.9103
- Overall Accuracy: 0.9563
## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 25
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Comment | Date | Labname | Laboratory | Measure | Ref Value | Result | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------:|:---------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
| 1.2584 | 5.0 | 5 | 0.9810 | {'precision': 1.0, 'recall': 0.05555555555555555, 'f1': 0.10526315789473684, 'number': 18} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.6666666666666666, 'recall': 0.3076923076923077, 'f1': 0.42105263157894735, 'number': 13} | {'precision': 0.5714285714285714, 'recall': 0.2857142857142857, 'f1': 0.38095238095238093, 'number': 14} | {'precision': 0.4482758620689655, 'recall': 0.9285714285714286, 'f1': 0.6046511627906977, 'number': 14} | 0.44 | 0.2973 | 0.3548 | 0.7125 |
| 0.6614 | 10.0 | 10 | 0.5382 | {'precision': 0.8947368421052632, 'recall': 0.9444444444444444, 'f1': 0.918918918918919, 'number': 18} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.6666666666666666, 'recall': 0.8, 'f1': 0.7272727272727272, 'number': 5} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.8333333333333334, 'recall': 0.38461538461538464, 'f1': 0.5263157894736842, 'number': 13} | {'precision': 0.8125, 'recall': 0.9285714285714286, 'f1': 0.8666666666666666, 'number': 14} | {'precision': 1.0, 'recall': 0.7857142857142857, 'f1': 0.88, 'number': 14} | 0.8475 | 0.6757 | 0.7519 | 0.9 |
| 0.3955 | 15.0 | 15 | 0.3360 | {'precision': 0.8947368421052632, 'recall': 0.9444444444444444, 'f1': 0.918918918918919, 'number': 18} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.6666666666666666, 'recall': 0.8, 'f1': 0.7272727272727272, 'number': 5} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.8333333333333334, 'recall': 0.38461538461538464, 'f1': 0.5263157894736842, 'number': 13} | {'precision': 0.8125, 'recall': 0.9285714285714286, 'f1': 0.8666666666666666, 'number': 14} | {'precision': 1.0, 'recall': 0.7857142857142857, 'f1': 0.88, 'number': 14} | 0.8475 | 0.6757 | 0.7519 | 0.9 |
| 0.2654 | 20.0 | 20 | 0.2405 | {'precision': 1.0, 'recall': 0.8888888888888888, 'f1': 0.9411764705882353, 'number': 18} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.6666666666666666, 'recall': 0.8, 'f1': 0.7272727272727272, 'number': 5} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 1.0, 'recall': 0.9230769230769231, 'f1': 0.9600000000000001, 'number': 13} | {'precision': 0.875, 'recall': 1.0, 'f1': 0.9333333333333333, 'number': 14} | {'precision': 0.9285714285714286, 'recall': 0.9285714285714286, 'f1': 0.9285714285714286, 'number': 14} | 0.9155 | 0.8784 | 0.8966 | 0.95 |
| 0.2125 | 25.0 | 25 | 0.2043 | {'precision': 1.0, 'recall': 0.9444444444444444, 'f1': 0.9714285714285714, 'number': 18} | {'precision': 0.8571428571428571, 'recall': 0.75, 'f1': 0.7999999999999999, 'number': 8} | {'precision': 0.6666666666666666, 'recall': 0.8, 'f1': 0.7272727272727272, 'number': 5} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 1.0, 'recall': 0.9230769230769231, 'f1': 0.9600000000000001, 'number': 13} | {'precision': 0.875, 'recall': 1.0, 'f1': 0.9333333333333333, 'number': 14} | {'precision': 1.0, 'recall': 0.9285714285714286, 'f1': 0.962962962962963, 'number': 14} | 0.9296 | 0.8919 | 0.9103 | 0.9563 |
### Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.8.0
- Tokenizers 0.13.2