<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
gpt2-concat-all-text-processign-rarity-all-iorder-est-5p5k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3687
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 |
|---|---|---|---|
| 6.7435 | 0.32 | 500 | 5.6693 |
| 5.3983 | 0.63 | 1000 | 5.2259 |
| 5.0552 | 0.95 | 1500 | 4.9848 |
| 4.7718 | 1.27 | 2000 | 4.8394 |
| 4.6329 | 1.58 | 2500 | 4.7145 |
| 4.5322 | 1.9 | 3000 | 4.6174 |
| 4.3187 | 2.22 | 3500 | 4.5659 |
| 4.2361 | 2.53 | 4000 | 4.4971 |
| 4.1996 | 2.85 | 4500 | 4.4287 |
| 4.0309 | 3.17 | 5000 | 4.4140 |
| 3.9128 | 3.48 | 5500 | 4.3761 |
| 3.8993 | 3.8 | 6000 | 4.3344 |
| 3.7784 | 4.12 | 6500 | 4.3363 |
| 3.619 | 4.43 | 7000 | 4.3222 |
| 3.6107 | 4.75 | 7500 | 4.3063 |
| 3.5596 | 5.07 | 8000 | 4.3030 |
| 3.4209 | 5.38 | 8500 | 4.3070 |
| 3.4095 | 5.7 | 9000 | 4.3053 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
