metadata
license: apache-2.0
base_model: mrm8488/electra-small-finetuned-squadv2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: interview_electra
results: []
interview_electra
This model is a fine-tuned version of mrm8488/electra-small-finetuned-squadv2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3918
- Accuracy: 0.7261
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: 2
- eval_batch_size: 2
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 79 | 2.2793 | 0.1720 |
| No log | 2.0 | 158 | 2.2569 | 0.2102 |
| No log | 3.0 | 237 | 2.2141 | 0.2866 |
| No log | 4.0 | 316 | 2.1554 | 0.3121 |
| No log | 5.0 | 395 | 2.0661 | 0.5096 |
| No log | 6.0 | 474 | 1.9949 | 0.5669 |
| 2.2016 | 7.0 | 553 | 1.9088 | 0.5987 |
| 2.2016 | 8.0 | 632 | 1.8361 | 0.5605 |
| 2.2016 | 9.0 | 711 | 1.7648 | 0.6306 |
| 2.2016 | 10.0 | 790 | 1.7013 | 0.6561 |
| 2.2016 | 11.0 | 869 | 1.6548 | 0.6115 |
| 2.2016 | 12.0 | 948 | 1.5916 | 0.6943 |
| 1.812 | 13.0 | 1027 | 1.5425 | 0.6943 |
| 1.812 | 14.0 | 1106 | 1.5137 | 0.7006 |
| 1.812 | 15.0 | 1185 | 1.4722 | 0.7261 |
| 1.812 | 16.0 | 1264 | 1.4426 | 0.7197 |
| 1.812 | 17.0 | 1343 | 1.4216 | 0.7197 |
| 1.812 | 18.0 | 1422 | 1.4061 | 0.7325 |
| 1.5304 | 19.0 | 1501 | 1.3961 | 0.7325 |
| 1.5304 | 20.0 | 1580 | 1.3918 | 0.7261 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1