metadata
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: all-base-log-rarity
results: []
all-base-log-rarity
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 5.4679
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: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.488 | 0.31 | 500 | 5.6024 |
| 5.1781 | 0.62 | 1000 | 5.3432 |
| 4.832 | 0.94 | 1500 | 5.1744 |
| 4.5773 | 1.25 | 2000 | 5.1710 |
| 4.4585 | 1.56 | 2500 | 5.1043 |
| 4.3631 | 1.87 | 3000 | 5.0802 |
| 4.1959 | 2.19 | 3500 | 5.0614 |
| 4.1063 | 2.5 | 4000 | 5.1289 |
| 4.0747 | 2.81 | 4500 | 5.0496 |
| 3.9482 | 3.12 | 5000 | 5.1552 |
| 3.8193 | 3.44 | 5500 | 5.1364 |
| 3.804 | 3.75 | 6000 | 5.1111 |
| 3.7357 | 4.06 | 6500 | 5.2502 |
| 3.5478 | 4.37 | 7000 | 5.2565 |
| 3.5409 | 4.68 | 7500 | 5.3273 |
| 3.5276 | 5.0 | 8000 | 5.3765 |
| 3.3651 | 5.31 | 8500 | 5.4361 |
| 3.359 | 5.62 | 9000 | 5.4664 |
| 3.3559 | 5.93 | 9500 | 5.4678 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3