|
|
--- |
|
|
license: mit |
|
|
base_model: roberta-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
- f1 |
|
|
model-index: |
|
|
- name: roberta-base-topic_classification_simple2 |
|
|
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-base-topic_classification_simple2 |
|
|
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.1250 |
|
|
- Accuracy: {'accuracy': 0.866996699669967} |
|
|
- F1: {'f1': 0.8657113367537151} |
|
|
|
|
|
## 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: 32 |
|
|
- eval_batch_size: 32 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 20 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------------------------------:|:--------------------------:| |
|
|
| No log | 1.0 | 313 | 0.5920 | {'accuracy': 0.8158415841584158} | {'f1': 0.8063426391052376} | |
|
|
| 0.7507 | 2.0 | 626 | 0.5183 | {'accuracy': 0.8419141914191419} | {'f1': 0.8450438669495921} | |
|
|
| 0.7507 | 3.0 | 939 | 0.5089 | {'accuracy': 0.8514851485148515} | {'f1': 0.8522994355907825} | |
|
|
| 0.3199 | 4.0 | 1252 | 0.6030 | {'accuracy': 0.8508250825082508} | {'f1': 0.8484331857141633} | |
|
|
| 0.1504 | 5.0 | 1565 | 0.6894 | {'accuracy': 0.8617161716171617} | {'f1': 0.8599694556754336} | |
|
|
| 0.1504 | 6.0 | 1878 | 0.8381 | {'accuracy': 0.8448844884488449} | {'f1': 0.8461993387843019} | |
|
|
| 0.0822 | 7.0 | 2191 | 0.8515 | {'accuracy': 0.8554455445544554} | {'f1': 0.8542784950089077} | |
|
|
| 0.0551 | 8.0 | 2504 | 0.9319 | {'accuracy': 0.8531353135313532} | {'f1': 0.853451943641699} | |
|
|
| 0.0551 | 9.0 | 2817 | 0.9478 | {'accuracy': 0.8577557755775578} | {'f1': 0.8565849659994866} | |
|
|
| 0.0377 | 10.0 | 3130 | 0.9998 | {'accuracy': 0.8554455445544554} | {'f1': 0.8550659197552203} | |
|
|
| 0.0377 | 11.0 | 3443 | 1.0025 | {'accuracy': 0.8554455445544554} | {'f1': 0.8550137537621838} | |
|
|
| 0.0279 | 12.0 | 3756 | 1.0728 | {'accuracy': 0.8574257425742574} | {'f1': 0.8566278925949554} | |
|
|
| 0.0132 | 13.0 | 4069 | 1.0873 | {'accuracy': 0.8623762376237624} | {'f1': 0.8610125122049608} | |
|
|
| 0.0132 | 14.0 | 4382 | 1.0989 | {'accuracy': 0.8653465346534653} | {'f1': 0.863969705278768} | |
|
|
| 0.0124 | 15.0 | 4695 | 1.1379 | {'accuracy': 0.8643564356435643} | {'f1': 0.8630599594036119} | |
|
|
| 0.0095 | 16.0 | 5008 | 1.1207 | {'accuracy': 0.8653465346534653} | {'f1': 0.8639194427774014} | |
|
|
| 0.0095 | 17.0 | 5321 | 1.1053 | {'accuracy': 0.866006600660066} | {'f1': 0.8652013668499585} | |
|
|
| 0.0074 | 18.0 | 5634 | 1.1296 | {'accuracy': 0.863036303630363} | {'f1': 0.8615189712315606} | |
|
|
| 0.0074 | 19.0 | 5947 | 1.1099 | {'accuracy': 0.8689768976897689} | {'f1': 0.867663744149239} | |
|
|
| 0.0046 | 20.0 | 6260 | 1.1250 | {'accuracy': 0.866996699669967} | {'f1': 0.8657113367537151} | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.35.2 |
|
|
- Pytorch 2.1.0+cu121 |
|
|
- Datasets 2.16.1 |
|
|
- Tokenizers 0.15.1 |
|
|
|
