metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: distilbert-base-uncased-finetuned
results: []
distilbert-base-uncased-finetuned
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9967
- Accuracy: 0.9032
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: 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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3072 | 1.0 | 5250 | 0.2747 | 0.8940 |
| 0.2381 | 2.0 | 10500 | 0.2871 | 0.8986 |
| 0.1858 | 3.0 | 15750 | 0.3444 | 0.8996 |
| 0.1385 | 4.0 | 21000 | 0.4799 | 0.8937 |
| 0.1057 | 5.0 | 26250 | 0.5324 | 0.8961 |
| 0.0779 | 6.0 | 31500 | 0.6222 | 0.8969 |
| 0.0654 | 7.0 | 36750 | 0.6665 | 0.8968 |
| 0.046 | 8.0 | 42000 | 0.7111 | 0.8989 |
| 0.0384 | 9.0 | 47250 | 0.7815 | 0.8987 |
| 0.0348 | 10.0 | 52500 | 0.8023 | 0.9029 |
| 0.0224 | 11.0 | 57750 | 0.8676 | 0.9011 |
| 0.0172 | 12.0 | 63000 | 0.8881 | 0.8999 |
| 0.0068 | 13.0 | 68250 | 0.9122 | 0.9025 |
| 0.0032 | 14.0 | 73500 | 0.9938 | 0.9005 |
| 0.0071 | 15.0 | 78750 | 0.9967 | 0.9032 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3