metadata
license: mit
base_model: openai-community/gpt2-medium
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: model_gpt2_medium_d_political_bias_ep_2_sqn_a_p_100_v_1
results: []
model_gpt2_medium_d_political_bias_ep_2_sqn_a_p_100_v_1
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: 0.4577
- Balanced Accuracy: 0.7785
- Accuracy: 0.7784
- F1 Micro: 0.7784
- F1 Macro: 0.7781
- Precision Micro: 0.7784
- Precision Macro: 0.7801
- Recall Micro: 0.7784
- Recall Macro: 0.7785
- Auc: 0.8765
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: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
Training Loss | Epoch | Step | Validation Loss | Balanced Accuracy | Accuracy | F1 Micro | F1 Macro | Precision Micro | Precision Macro | Recall Micro | Recall Macro | Auc |
---|---|---|---|---|---|---|---|---|---|---|---|---|
0.6433 | 1.0 | 727 | 0.4741 | 0.7665 | 0.7663 | 0.7663 | 0.7662 | 0.7663 | 0.7671 | 0.7663 | 0.7665 | 0.8560 |
0.4554 | 2.0 | 1454 | 0.4577 | 0.7785 | 0.7784 | 0.7784 | 0.7781 | 0.7784 | 0.7801 | 0.7784 | 0.7785 | 0.8765 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1