metadata
license: mit
base_model: openai-community/gpt2-medium
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: model_gpt2_medium_d_gender_bias_gender_bias_ep_1_3_a_sqn_a_b_p_100_5_v_10
results: []
model_gpt2_medium_d_gender_bias_gender_bias_ep_1_3_a_sqn_a_b_p_100_5_v_10
This model is a fine-tuned version of openai-community/gpt2-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6237
- Accuracy: 0.7784
- F1 Micro: 0.7784
- Auc: 0.8486
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Micro | Auc |
|---|---|---|---|---|---|---|
| 0.7716 | 0.2632 | 10 | 0.5949 | 0.7057 | 0.7057 | 0.7616 |
| 0.6115 | 0.5263 | 20 | 0.5305 | 0.7358 | 0.7358 | 0.8084 |
| 0.5723 | 0.7895 | 30 | 0.8684 | 0.6254 | 0.6254 | 0.8108 |
| 0.5526 | 1.0526 | 40 | 0.5311 | 0.7609 | 0.7609 | 0.8251 |
| 0.4619 | 1.3158 | 50 | 0.5312 | 0.7676 | 0.7676 | 0.8396 |
| 0.4556 | 1.5789 | 60 | 0.6235 | 0.6923 | 0.6923 | 0.8349 |
| 0.5434 | 1.8421 | 70 | 0.5453 | 0.7617 | 0.7617 | 0.8319 |
| 0.4141 | 2.1053 | 80 | 0.5142 | 0.7667 | 0.7667 | 0.8406 |
| 0.2681 | 2.3684 | 90 | 0.5732 | 0.7843 | 0.7843 | 0.8451 |
| 0.2561 | 2.6316 | 100 | 0.6299 | 0.7567 | 0.7567 | 0.8464 |
| 0.3531 | 2.8947 | 110 | 0.6237 | 0.7784 | 0.7784 | 0.8486 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1