metadata
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: cbt-gutenberg_fixed-notm-log-rarity-seed
results: []
cbt-gutenberg_fixed-notm-log-rarity-seed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1166
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 |
|---|---|---|---|
| 6.3486 | 0.29 | 500 | 5.3406 |
| 5.0309 | 0.58 | 1000 | 4.9285 |
| 4.7101 | 0.87 | 1500 | 4.6879 |
| 4.4621 | 1.17 | 2000 | 4.5500 |
| 4.2913 | 1.46 | 2500 | 4.4298 |
| 4.2026 | 1.75 | 3000 | 4.3310 |
| 4.0829 | 2.04 | 3500 | 4.2546 |
| 3.8956 | 2.33 | 4000 | 4.2130 |
| 3.8692 | 2.62 | 4500 | 4.1583 |
| 3.8292 | 2.91 | 5000 | 4.1132 |
| 3.6507 | 3.21 | 5500 | 4.1047 |
| 3.5891 | 3.5 | 6000 | 4.0753 |
| 3.5712 | 3.79 | 6500 | 4.0432 |
| 3.4932 | 4.08 | 7000 | 4.0421 |
| 3.3212 | 4.37 | 7500 | 4.0385 |
| 3.3167 | 4.66 | 8000 | 4.0261 |
| 3.3035 | 4.95 | 8500 | 4.0122 |
| 3.1681 | 5.24 | 9000 | 4.0240 |
| 3.1387 | 5.54 | 9500 | 4.0244 |
| 3.1401 | 5.83 | 10000 | 4.0231 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3