|
--- |
|
language: |
|
- mn |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: roberta-large-mnli-ner-2000 |
|
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. --> |
|
|
|
# roberta-large-mnli-ner-2000 |
|
|
|
This model is a fine-tuned version of [roberta-large-mnli](https://huggingface.co/roberta-large-mnli) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2962 |
|
- Precision: 0.5550 |
|
- Recall: 0.7002 |
|
- F1: 0.6192 |
|
- Accuracy: 0.9229 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 32 |
|
- 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 | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.5957 | 1.0 | 47 | 0.3873 | 0.3785 | 0.5503 | 0.4485 | 0.8762 | |
|
| 0.3783 | 2.0 | 94 | 0.3326 | 0.4809 | 0.6208 | 0.5420 | 0.8970 | |
|
| 0.31 | 3.0 | 141 | 0.3072 | 0.4149 | 0.5996 | 0.4904 | 0.8932 | |
|
| 0.2706 | 4.0 | 188 | 0.2973 | 0.5096 | 0.6510 | 0.5717 | 0.9096 | |
|
| 0.2486 | 5.0 | 235 | 0.3273 | 0.4987 | 0.6454 | 0.5627 | 0.9061 | |
|
| 0.2113 | 6.0 | 282 | 0.2658 | 0.5148 | 0.6611 | 0.5788 | 0.9146 | |
|
| 0.1856 | 7.0 | 329 | 0.2824 | 0.5140 | 0.6767 | 0.5843 | 0.9138 | |
|
| 0.1554 | 8.0 | 376 | 0.2944 | 0.5450 | 0.6980 | 0.6121 | 0.9181 | |
|
| 0.1362 | 9.0 | 423 | 0.2893 | 0.5475 | 0.6969 | 0.6132 | 0.9199 | |
|
| 0.1232 | 10.0 | 470 | 0.2962 | 0.5550 | 0.7002 | 0.6192 | 0.9229 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
