metadata
license: mit
base_model: openai-community/gpt2
tags:
- generated_from_trainer
model-index:
- name: time_calculation
results: []
time_calculation
This model is a fine-tuned version of openai-community/gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 9.7598
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: 8
- seed: 42
- gradient_accumulation_steps: 128
- total_train_batch_size: 2048
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
5.3211 | 1.0 | 1 | 10.9807 |
5.3184 | 2.0 | 2 | 10.2633 |
2.4486 | 3.0 | 4 | 9.9073 |
4.8026 | 4.0 | 5 | 9.8741 |
2.365 | 5.0 | 7 | 9.7946 |
4.6989 | 6.0 | 8 | 9.7726 |
2.3358 | 7.0 | 10 | 9.7598 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2