| | --- |
| | license: mit |
| | base_model: gpt2 |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: star-trek-tng-script-generator |
| | results: [] |
| | datasets: |
| | - progs2002/star-trek-tng-scripts |
| | language: |
| | - en |
| | pipeline_tag: text-generation |
| | widget: |
| | - text: "PICARD: Make it so!\nRIKER: Captain! That ship is hailing us." |
| | --- |
| | |
| | <!-- 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. --> |
| | # data cleaning and training code |
| | https://github.com/progs2002/StarTrekTNG-ScriptGenerator |
| |
|
| | # star-trek-tng-script-generator |
| |
|
| | This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 2.8459 |
| |
|
| | ## 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: 0.0002 |
| | - train_batch_size: 1 |
| | - eval_batch_size: 1 |
| | - seed: 42 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: cosine |
| | - lr_scheduler_warmup_steps: 50 |
| | - num_epochs: 3 |
| | |
| | ### Training results |
| | |
| | | Training Loss | Epoch | Step | Validation Loss | |
| | |:-------------:|:-----:|:-----:|:---------------:| |
| | | 3.1502 | 0.13 | 500 | 3.0233 | |
| | | 3.0538 | 0.26 | 1000 | 2.9728 | |
| | | 2.9951 | 0.38 | 1500 | 2.9437 | |
| | | 2.9891 | 0.51 | 2000 | 2.9125 | |
| | | 2.9289 | 0.64 | 2500 | 2.9159 | |
| | | 2.9091 | 0.77 | 3000 | 2.9008 | |
| | | 2.8916 | 0.89 | 3500 | 2.8752 | |
| | | 2.8122 | 1.02 | 4000 | 2.8881 | |
| | | 2.5224 | 1.15 | 4500 | 2.8896 | |
| | | 2.5284 | 1.28 | 5000 | 2.8667 | |
| | | 2.5191 | 1.4 | 5500 | 2.8599 | |
| | | 2.5119 | 1.53 | 6000 | 2.8488 | |
| | | 2.4808 | 1.66 | 6500 | 2.8296 | |
| | | 2.4601 | 1.79 | 7000 | 2.8081 | |
| | | 2.4331 | 1.91 | 7500 | 2.7993 | |
| | | 2.3716 | 2.04 | 8000 | 2.8518 | |
| | | 2.1528 | 2.17 | 8500 | 2.8634 | |
| | | 2.1276 | 2.3 | 9000 | 2.8617 | |
| | | 2.1329 | 2.43 | 9500 | 2.8489 | |
| | | 2.1135 | 2.55 | 10000 | 2.8446 | |
| | | 2.1259 | 2.68 | 10500 | 2.8461 | |
| | | 2.1142 | 2.81 | 11000 | 2.8472 | |
| | | 2.1071 | 2.94 | 11500 | 2.8459 | |
| | |
| | |
| | ### Framework versions |
| | |
| | - Transformers 4.35.2 |
| | - Pytorch 2.1.0+cu121 |
| | - Datasets 2.16.1 |
| | - Tokenizers 0.15.0 |
