eskayML's picture
eskayML/interview_classifier
41335aa verified
|
raw
history blame
2.55 kB
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: interview_classifier
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. -->
# interview_classifier
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0333
- Accuracy: 1.0
## 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 | 54 | 2.2119 | 0.1852 |
| No log | 2.0 | 108 | 2.0620 | 0.3704 |
| No log | 3.0 | 162 | 1.7627 | 0.7037 |
| No log | 4.0 | 216 | 1.4448 | 0.7685 |
| No log | 5.0 | 270 | 1.1397 | 0.8889 |
| No log | 6.0 | 324 | 0.8434 | 0.9167 |
| No log | 7.0 | 378 | 0.6044 | 0.9444 |
| No log | 8.0 | 432 | 0.4223 | 0.9907 |
| No log | 9.0 | 486 | 0.2967 | 0.9907 |
| 1.3767 | 10.0 | 540 | 0.2077 | 0.9907 |
| 1.3767 | 11.0 | 594 | 0.1528 | 1.0 |
| 1.3767 | 12.0 | 648 | 0.1135 | 1.0 |
| 1.3767 | 13.0 | 702 | 0.0851 | 1.0 |
| 1.3767 | 14.0 | 756 | 0.0661 | 1.0 |
| 1.3767 | 15.0 | 810 | 0.0548 | 1.0 |
| 1.3767 | 16.0 | 864 | 0.0449 | 1.0 |
| 1.3767 | 17.0 | 918 | 0.0399 | 1.0 |
| 1.3767 | 18.0 | 972 | 0.0358 | 1.0 |
| 0.1191 | 19.0 | 1026 | 0.0339 | 1.0 |
| 0.1191 | 20.0 | 1080 | 0.0333 | 1.0 |
### Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1