metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: polynomial_2000_1e-3_16b_w0.075
results: []
polynomial_2000_1e-3_16b_w0.075
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.8163
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: 0.001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: polynomial
- lr_scheduler_warmup_steps: 250
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.2211 | 0.9116 | 250 | 4.7231 |
| 4.0225 | 1.8232 | 500 | 3.4634 |
| 3.2171 | 2.7347 | 750 | 3.1355 |
| 2.8923 | 3.6463 | 1000 | 2.9862 |
| 2.6796 | 4.5579 | 1250 | 2.9034 |
| 2.4887 | 5.4695 | 1500 | 2.8586 |
| 2.3317 | 6.3810 | 1750 | 2.8339 |
| 2.193 | 7.2926 | 2000 | 2.8163 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1