metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: jpmodel_remote-work_distilbert-base-uncased_0517
results: []
jpmodel_remote-work_distilbert-base-uncased_0517
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4293
- Accuracy: {'accuracy': 0.9476614699331849}
- F1: {'f1': 0.9316670582946814}
- Precision: {'precision': 0.9211843955719234}
- Recall: {'recall': 0.9476614699331849}
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: 16
- 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 | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 449 | 0.2487 | {'accuracy': 0.9532293986636972} | {'f1': 0.9304040652863451} | {'precision': 0.9086462864767536} | {'recall': 0.9532293986636972} |
| 0.2176 | 2.0 | 898 | 0.2366 | {'accuracy': 0.9532293986636972} | {'f1': 0.9304040652863451} | {'precision': 0.9086462864767536} | {'recall': 0.9532293986636972} |
| 0.1796 | 3.0 | 1347 | 0.2228 | {'accuracy': 0.9526726057906458} | {'f1': 0.9320734514025724} | {'precision': 0.9182722571033837} | {'recall': 0.9526726057906458} |
| 0.1469 | 4.0 | 1796 | 0.2856 | {'accuracy': 0.9437639198218263} | {'f1': 0.9282364670603435} | {'precision': 0.9135405361560103} | {'recall': 0.9437639198218263} |
| 0.1045 | 5.0 | 2245 | 0.3386 | {'accuracy': 0.9437639198218263} | {'f1': 0.9280406899884679} | {'precision': 0.9132963430863958} | {'recall': 0.9437639198218263} |
| 0.0742 | 6.0 | 2694 | 0.3708 | {'accuracy': 0.9437639198218263} | {'f1': 0.928813770000516} | {'precision': 0.9155656638103506} | {'recall': 0.9437639198218263} |
| 0.0401 | 7.0 | 3143 | 0.3897 | {'accuracy': 0.9437639198218263} | {'f1': 0.9291849652492169} | {'precision': 0.9199457677450203} | {'recall': 0.9437639198218263} |
| 0.0263 | 8.0 | 3592 | 0.4163 | {'accuracy': 0.9471046770601337} | {'f1': 0.9322848244083336} | {'precision': 0.9235426032908877} | {'recall': 0.9471046770601337} |
| 0.0149 | 9.0 | 4041 | 0.4249 | {'accuracy': 0.9471046770601337} | {'f1': 0.9313864813181381} | {'precision': 0.9211608097664751} | {'recall': 0.9471046770601337} |
| 0.0149 | 10.0 | 4490 | 0.4293 | {'accuracy': 0.9476614699331849} | {'f1': 0.9316670582946814} | {'precision': 0.9211843955719234} | {'recall': 0.9476614699331849} |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1