<!-- 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-open_subtitles-seed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.2914
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 |
---|---|---|---|
6.6315 | 0.44 | 500 | 5.3853 |
5.2354 | 0.88 | 1000 | 4.9560 |
4.8007 | 1.32 | 1500 | 4.7428 |
4.5677 | 1.76 | 2000 | 4.5749 |
4.3152 | 2.2 | 2500 | 4.4831 |
4.1412 | 2.64 | 3000 | 4.3900 |
4.02 | 3.08 | 3500 | 4.3240 |
3.7856 | 3.52 | 4000 | 4.2916 |
3.755 | 3.96 | 4500 | 4.2318 |
3.487 | 4.4 | 5000 | 4.2370 |
3.4453 | 4.84 | 5500 | 4.2119 |
3.3098 | 5.28 | 6000 | 4.2182 |
3.231 | 5.72 | 6500 | 4.2157 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3