update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- precision
|
| 7 |
+
- recall
|
| 8 |
+
- f1
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: aces-roberta-base-13
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# aces-roberta-base-13
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.5171
|
| 23 |
+
- Precision: 0.8348
|
| 24 |
+
- Recall: 0.8531
|
| 25 |
+
- F1: 0.8399
|
| 26 |
+
- Accuracy: 0.8531
|
| 27 |
+
- F1 Who: 0.9134
|
| 28 |
+
- F1 What: 0.8505
|
| 29 |
+
- F1 Where: 0.8444
|
| 30 |
+
- F1 How: 0.9391
|
| 31 |
+
|
| 32 |
+
## Model description
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Intended uses & limitations
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training and evaluation data
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Training procedure
|
| 45 |
+
|
| 46 |
+
### Training hyperparameters
|
| 47 |
+
|
| 48 |
+
The following hyperparameters were used during training:
|
| 49 |
+
- learning_rate: 1e-05
|
| 50 |
+
- train_batch_size: 8
|
| 51 |
+
- eval_batch_size: 8
|
| 52 |
+
- seed: 42
|
| 53 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 54 |
+
- lr_scheduler_type: linear
|
| 55 |
+
- num_epochs: 10
|
| 56 |
+
|
| 57 |
+
### Training results
|
| 58 |
+
|
| 59 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | F1 Who | F1 What | F1 Where | F1 How |
|
| 60 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:------:|:-------:|:--------:|:------:|
|
| 61 |
+
| 1.2251 | 1.0 | 50 | 1.1108 | 0.6219 | 0.6941 | 0.6168 | 0.6941 | 0.0625 | 0.6856 | 0.5926 | 0.8138 |
|
| 62 |
+
| 0.6932 | 2.0 | 100 | 0.7015 | 0.7448 | 0.8031 | 0.7639 | 0.8031 | 0.8730 | 0.7932 | 0.8054 | 0.9293 |
|
| 63 |
+
| 0.5636 | 3.0 | 150 | 0.6059 | 0.8028 | 0.8289 | 0.8032 | 0.8289 | 0.8819 | 0.8095 | 0.8186 | 0.9346 |
|
| 64 |
+
| 0.4894 | 4.0 | 200 | 0.5492 | 0.8251 | 0.8499 | 0.8314 | 0.8499 | 0.9077 | 0.8402 | 0.8340 | 0.9393 |
|
| 65 |
+
| 0.4381 | 5.0 | 250 | 0.5289 | 0.8237 | 0.8523 | 0.8353 | 0.8523 | 0.9219 | 0.8497 | 0.8559 | 0.9438 |
|
| 66 |
+
| 0.4611 | 6.0 | 300 | 0.5233 | 0.8217 | 0.8507 | 0.8345 | 0.8507 | 0.9219 | 0.8346 | 0.8267 | 0.9436 |
|
| 67 |
+
| 0.3671 | 7.0 | 350 | 0.5268 | 0.8383 | 0.8507 | 0.8360 | 0.8507 | 0.9206 | 0.8485 | 0.8393 | 0.9395 |
|
| 68 |
+
| 0.3278 | 8.0 | 400 | 0.5278 | 0.8370 | 0.8507 | 0.8369 | 0.8507 | 0.9147 | 0.8448 | 0.8444 | 0.9348 |
|
| 69 |
+
| 0.3727 | 9.0 | 450 | 0.5170 | 0.8339 | 0.8547 | 0.8405 | 0.8547 | 0.9134 | 0.8549 | 0.8407 | 0.9423 |
|
| 70 |
+
| 0.372 | 10.0 | 500 | 0.5171 | 0.8348 | 0.8531 | 0.8399 | 0.8531 | 0.9134 | 0.8505 | 0.8444 | 0.9391 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.30.2
|
| 76 |
+
- Pytorch 1.13.1+cu117
|
| 77 |
+
- Datasets 2.15.0
|
| 78 |
+
- Tokenizers 0.13.3
|