metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
- precision
- recall
model-index:
- name: soft-search
results: []
soft-search
This model is a fine-tuned version of distilbert-base-uncased-finetuned-sst-2-english on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7833
- F1: 0.5304
- Accuracy: 0.6780
- Precision: 0.5333
- Recall: 0.5275
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: 3e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.5776 | 1.0 | 50 | 0.6066 | 0.3803 | 0.6667 | 0.5294 | 0.2967 |
| 0.5545 | 2.0 | 100 | 0.6261 | 0.4331 | 0.6629 | 0.5152 | 0.3736 |
| 0.4599 | 3.0 | 150 | 0.7046 | 0.5472 | 0.6364 | 0.4793 | 0.6374 |
| 0.2527 | 4.0 | 200 | 0.7285 | 0.5521 | 0.6742 | 0.5248 | 0.5824 |
| 0.2423 | 5.0 | 250 | 0.7833 | 0.5304 | 0.6780 | 0.5333 | 0.5275 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu117
- Datasets 2.8.0
- Tokenizers 0.13.2