metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: job-listing-relevance-model
results: []
job-listing-relevance-model
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0555
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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 |
---|---|---|---|
0.6791 | 0.43 | 50 | 0.4885 |
0.2491 | 0.87 | 100 | 0.1554 |
0.1067 | 1.3 | 150 | 0.1085 |
0.1382 | 1.74 | 200 | 0.1509 |
0.0575 | 2.17 | 250 | 0.1194 |
0.0386 | 2.61 | 300 | 0.0973 |
0.1782 | 3.04 | 350 | 0.1145 |
0.0458 | 3.48 | 400 | 0.0852 |
0.0043 | 3.91 | 450 | 0.0878 |
0.0374 | 4.35 | 500 | 0.0673 |
0.09 | 4.78 | 550 | 0.0483 |
0.0017 | 5.22 | 600 | 0.0978 |
0.0025 | 5.65 | 650 | 0.0792 |
0.0138 | 6.09 | 700 | 0.0358 |
0.0716 | 6.52 | 750 | 0.0463 |
0.0391 | 6.95 | 800 | 0.1162 |
0.0164 | 7.39 | 850 | 0.0509 |
0.0359 | 7.82 | 900 | 0.0757 |
0.0012 | 8.26 | 950 | 0.0337 |
0.0008 | 8.69 | 1000 | 0.0585 |
0.0007 | 9.13 | 1050 | 0.0655 |
0.0609 | 9.56 | 1100 | 0.0481 |
0.0007 | 10.0 | 1150 | 0.0555 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.11.0+cu113
- Datasets 2.0.0
- Tokenizers 0.11.6