eskayML's picture
eskayML/interview_classfier
a2643b5 verified
|
raw
history blame
2.56 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: 0.1049
- Accuracy: 0.9682
## 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 | 2.2043 | 0.1720 |
| No log | 2.0 | 158 | 1.8878 | 0.4331 |
| No log | 3.0 | 237 | 1.4540 | 0.6624 |
| No log | 4.0 | 316 | 1.1512 | 0.7134 |
| No log | 5.0 | 395 | 0.8028 | 0.8153 |
| No log | 6.0 | 474 | 0.5610 | 0.8854 |
| 1.5247 | 7.0 | 553 | 0.4031 | 0.9299 |
| 1.5247 | 8.0 | 632 | 0.3275 | 0.9172 |
| 1.5247 | 9.0 | 711 | 0.2420 | 0.9363 |
| 1.5247 | 10.0 | 790 | 0.1941 | 0.9490 |
| 1.5247 | 11.0 | 869 | 0.1656 | 0.9682 |
| 1.5247 | 12.0 | 948 | 0.1444 | 0.9682 |
| 0.3164 | 13.0 | 1027 | 0.1325 | 0.9682 |
| 0.3164 | 14.0 | 1106 | 0.1194 | 0.9682 |
| 0.3164 | 15.0 | 1185 | 0.1145 | 0.9682 |
| 0.3164 | 16.0 | 1264 | 0.1138 | 0.9682 |
| 0.3164 | 17.0 | 1343 | 0.1101 | 0.9682 |
| 0.3164 | 18.0 | 1422 | 0.1074 | 0.9682 |
| 0.1327 | 19.0 | 1501 | 0.1050 | 0.9682 |
| 0.1327 | 20.0 | 1580 | 0.1049 | 0.9682 |
### Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1