<!-- 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. -->
all-base-miss-bnc_spoken-seed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1513
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 |
---|---|---|---|
6.3641 | 0.32 | 500 | 5.3464 |
5.0373 | 0.63 | 1000 | 4.9460 |
4.7011 | 0.95 | 1500 | 4.6952 |
4.4149 | 1.27 | 2000 | 4.5651 |
4.2888 | 1.59 | 2500 | 4.4379 |
4.1672 | 1.9 | 3000 | 4.3374 |
3.9667 | 2.22 | 3500 | 4.2840 |
3.8923 | 2.54 | 4000 | 4.2189 |
3.8426 | 2.86 | 4500 | 4.1625 |
3.6826 | 3.17 | 5000 | 4.1468 |
3.5794 | 3.49 | 5500 | 4.1185 |
3.5684 | 3.81 | 6000 | 4.0819 |
3.4457 | 4.12 | 6500 | 4.0807 |
3.3055 | 4.44 | 7000 | 4.0720 |
3.2937 | 4.76 | 7500 | 4.0584 |
3.2382 | 5.08 | 8000 | 4.0593 |
3.1108 | 5.39 | 8500 | 4.0617 |
3.1154 | 5.71 | 9000 | 4.0602 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3