roberta-base-kennedy2020constructing
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: FacebookAI/roberta-base
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
- precision
|
| 10 |
+
- recall
|
| 11 |
+
- f1
|
| 12 |
+
model-index:
|
| 13 |
+
- name: roberta-base-kennedy2020constructing
|
| 14 |
+
results: []
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 18 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 19 |
+
|
| 20 |
+
# roberta-base-kennedy2020constructing
|
| 21 |
+
|
| 22 |
+
This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
|
| 23 |
+
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.2110
|
| 25 |
+
- Accuracy: 0.9738
|
| 26 |
+
- Roc Auc: 0.9915
|
| 27 |
+
- Precision: 0.9680
|
| 28 |
+
- Recall: 0.9592
|
| 29 |
+
- F1: 0.9636
|
| 30 |
+
|
| 31 |
+
## Model description
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Intended uses & limitations
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training and evaluation data
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training procedure
|
| 44 |
+
|
| 45 |
+
### Training hyperparameters
|
| 46 |
+
|
| 47 |
+
The following hyperparameters were used during training:
|
| 48 |
+
- learning_rate: 2e-05
|
| 49 |
+
- train_batch_size: 96
|
| 50 |
+
- eval_batch_size: 128
|
| 51 |
+
- seed: 42
|
| 52 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 53 |
+
- lr_scheduler_type: linear
|
| 54 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 55 |
+
- num_epochs: 10
|
| 56 |
+
|
| 57 |
+
### Training results
|
| 58 |
+
|
| 59 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Roc Auc | Precision | Recall | F1 |
|
| 60 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:-------:|:---------:|:------:|:------:|
|
| 61 |
+
| 0.2481 | 1.0 | 1144 | 0.2172 | 0.9001 | 0.9676 | 0.9266 | 0.7861 | 0.8506 |
|
| 62 |
+
| 0.1822 | 2.0 | 2288 | 0.1604 | 0.9380 | 0.9836 | 0.9252 | 0.9017 | 0.9133 |
|
| 63 |
+
| 0.1085 | 3.0 | 3432 | 0.1343 | 0.9575 | 0.9893 | 0.9627 | 0.9180 | 0.9398 |
|
| 64 |
+
| 0.0674 | 4.0 | 4576 | 0.1225 | 0.9649 | 0.9918 | 0.9477 | 0.9558 | 0.9517 |
|
| 65 |
+
| 0.0502 | 5.0 | 5720 | 0.1455 | 0.9688 | 0.9919 | 0.9561 | 0.9576 | 0.9569 |
|
| 66 |
+
| 0.0365 | 6.0 | 6864 | 0.1370 | 0.9698 | 0.9921 | 0.9676 | 0.9481 | 0.9578 |
|
| 67 |
+
| 0.0258 | 7.0 | 8008 | 0.1719 | 0.9706 | 0.9925 | 0.9615 | 0.9570 | 0.9592 |
|
| 68 |
+
| 0.0184 | 8.0 | 9152 | 0.1737 | 0.9731 | 0.9922 | 0.9686 | 0.9567 | 0.9626 |
|
| 69 |
+
| 0.0141 | 9.0 | 10296 | 0.2051 | 0.9734 | 0.9916 | 0.9673 | 0.9588 | 0.9630 |
|
| 70 |
+
| 0.01 | 10.0 | 11440 | 0.2110 | 0.9738 | 0.9915 | 0.9680 | 0.9592 | 0.9636 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.49.0
|
| 76 |
+
- Pytorch 2.6.0+cu124
|
| 77 |
+
- Datasets 3.3.2
|
| 78 |
+
- Tokenizers 0.21.0
|