|
|
--- |
|
|
library_name: transformers |
|
|
license: mit |
|
|
base_model: FacebookAI/roberta-large |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
model-index: |
|
|
- name: roberta-Reflections-goodareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current |
|
|
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-Reflections-goodareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current |
|
|
|
|
|
This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.2525 |
|
|
- Accuracy: 0.8947 |
|
|
- Precision: 0.5424 |
|
|
- Recall: 0.3678 |
|
|
- F1: 0.4384 |
|
|
|
|
|
## 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: 3.322508414488167e-05 |
|
|
- train_batch_size: 32 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 20 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
|
| 0.32 | 1.0 | 61 | 0.1403 | 0.8883 | 0.0 | 0.0 | 0.0 | |
|
|
| 0.2689 | 2.0 | 122 | 0.1174 | 0.8883 | 0.0 | 0.0 | 0.0 | |
|
|
| 0.2466 | 3.0 | 183 | 0.1255 | 0.8883 | 0.0 | 0.0 | 0.0 | |
|
|
| 0.2297 | 4.0 | 244 | 0.0992 | 0.8883 | 0.0 | 0.0 | 0.0 | |
|
|
| 0.2138 | 5.0 | 305 | 0.1326 | 0.8986 | 0.5690 | 0.3793 | 0.4552 | |
|
|
| 0.1877 | 6.0 | 366 | 0.1163 | 0.8909 | 0.5179 | 0.3333 | 0.4056 | |
|
|
| 0.1558 | 7.0 | 427 | 0.1209 | 0.8947 | 0.5397 | 0.3908 | 0.4533 | |
|
|
| 0.135 | 8.0 | 488 | 0.1446 | 0.8896 | 0.5056 | 0.5172 | 0.5114 | |
|
|
| 0.1208 | 9.0 | 549 | 0.1435 | 0.8986 | 0.5455 | 0.5517 | 0.5486 | |
|
|
| 0.1212 | 10.0 | 610 | 0.2261 | 0.8665 | 0.4309 | 0.6092 | 0.5048 | |
|
|
| 0.1011 | 11.0 | 671 | 0.1425 | 0.8973 | 0.5714 | 0.3218 | 0.4118 | |
|
|
| 0.0918 | 12.0 | 732 | 0.2365 | 0.8832 | 0.4811 | 0.5862 | 0.5285 | |
|
|
| 0.0892 | 13.0 | 793 | 0.1622 | 0.8935 | 0.525 | 0.4828 | 0.5030 | |
|
|
| 0.0593 | 14.0 | 854 | 0.1927 | 0.8922 | 0.5273 | 0.3333 | 0.4085 | |
|
|
| 0.0552 | 15.0 | 915 | 0.3540 | 0.8819 | 0.4762 | 0.5747 | 0.5208 | |
|
|
| 0.0523 | 16.0 | 976 | 0.2782 | 0.8909 | 0.5119 | 0.4943 | 0.5029 | |
|
|
| 0.0481 | 17.0 | 1037 | 0.2596 | 0.8922 | 0.5195 | 0.4598 | 0.4878 | |
|
|
| 0.0435 | 18.0 | 1098 | 0.2729 | 0.8947 | 0.5333 | 0.4598 | 0.4938 | |
|
|
| 0.0326 | 19.0 | 1159 | 0.2382 | 0.8935 | 0.5385 | 0.3218 | 0.4029 | |
|
|
| 0.0418 | 20.0 | 1220 | 0.2525 | 0.8947 | 0.5424 | 0.3678 | 0.4384 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.48.3 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 2.21.0 |
|
|
- Tokenizers 0.21.0 |
|
|
|
