<!-- 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-longer-top3-aochildes-cbt-guten
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 3.1961
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 |
|---|---|---|---|
| 6.7253 | 0.3 | 500 | 5.6413 |
| 5.3666 | 0.6 | 1000 | 5.2023 |
| 5.0141 | 0.91 | 1500 | 4.9461 |
| 4.7385 | 1.21 | 2000 | 4.8082 |
| 4.5903 | 1.51 | 2500 | 4.6877 |
| 4.483 | 1.81 | 3000 | 4.5759 |
| 4.314 | 2.12 | 3500 | 4.5164 |
| 4.168 | 2.42 | 4000 | 4.4640 |
| 4.1319 | 2.72 | 4500 | 4.4091 |
| 4.0719 | 3.02 | 5000 | 4.3683 |
| 3.8391 | 3.33 | 5500 | 4.3567 |
| 3.8393 | 3.63 | 6000 | 4.3232 |
| 3.8102 | 3.93 | 6500 | 4.2943 |
| 3.5985 | 4.23 | 7000 | 4.3109 |
| 3.5515 | 4.53 | 7500 | 4.2990 |
| 3.5377 | 4.84 | 8000 | 4.2872 |
| 3.4488 | 5.14 | 8500 | 4.2986 |
| 3.3497 | 5.44 | 9000 | 4.3006 |
| 3.3502 | 5.74 | 9500 | 4.2999 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
