metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
- f1
model-index:
- name: bert-base-phia-secondhandDescription-1000
results: []
bert-base-phia-secondhandDescription-1000
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9318
- Precision: 0.8414
- Recall: 0.8311
- Accuracy: 0.8311
- F1: 0.8306
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: 5e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- 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 | Precision | Recall | Accuracy | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 84 | 1.4608 | 0.7781 | 0.6824 | 0.6824 | 0.6766 |
| No log | 2.0 | 168 | 0.7149 | 0.8298 | 0.8176 | 0.8176 | 0.8185 |
| 1.4174 | 3.0 | 252 | 0.6704 | 0.8229 | 0.8041 | 0.8041 | 0.8036 |
| 1.4174 | 4.0 | 336 | 0.8298 | 0.8359 | 0.7973 | 0.7973 | 0.7974 |
| 0.2952 | 5.0 | 420 | 0.7800 | 0.8525 | 0.8311 | 0.8311 | 0.8305 |
| 0.2952 | 6.0 | 504 | 0.8365 | 0.8464 | 0.8311 | 0.8311 | 0.8312 |
| 0.2952 | 7.0 | 588 | 0.9032 | 0.8309 | 0.8176 | 0.8176 | 0.8184 |
| 0.0537 | 8.0 | 672 | 0.8952 | 0.8337 | 0.8243 | 0.8243 | 0.8237 |
| 0.0537 | 9.0 | 756 | 0.9206 | 0.8414 | 0.8311 | 0.8311 | 0.8306 |
| 0.0243 | 10.0 | 840 | 0.9318 | 0.8414 | 0.8311 | 0.8311 | 0.8306 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1
- Datasets 2.20.0
- Tokenizers 0.19.1