| --- |
| license: cc-by-nc-4.0 |
| base_model: NeverSleep/Nethena-20B |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: lora-outA |
| results: [] |
| --- |
| |
| <!-- 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. --> |
|
|
| [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
|
|
| This model is a fine-tuned version of [NeverSleep/Nethena-20B](https://huggingface.co/NeverSleep/Nethena-20B) on a private dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 1.3864 |
|
|
| ## Model description |
|
|
| athirdpath/Nethena-20b-Glued-LORA is a 128 rank LORA for RP, trained on [NeverSleep/Nethena-20B](https://huggingface.co/NeverSleep/Nethena-20B). It is unalligned and NSFW-oriented. |
|
|
| This is a test, exploring the effects of "gluing" the components of the 20b model together to reduce the iconic word replacement errors, increase lucidity, and improve recall. |
|
|
| ## Training and evaluation data |
|
|
| The private ~500k token dataset used to train the LORA was Alpaca formatted and focused on 4 primary categories: |
|
|
| - Medical texts (on psychology, reproductive organs, anatomy, and pregnancy). These are formatted so the model, in character as a doctor or therapist, answers a patient's question in short to medium form. |
| - Excerpts from short stories and novellas (erotic and romantic) centered around both realistic and fantastic situations, covering several fetishes as well. These are sliced into ~2048 token chunks, and these long-form responses are all tied to the command “Enter narrator mode.” in the instructions. |
| - A selection from PIPPA, using a wide keyword search for tokens associated with low quality human or AI data to remove those responses, then a positive search was done for words and phrases associated with a higher reading level. These are converted to Alpaca with “Enter RP mode.” in all the instruction fields. |
| - ~18k tokens of GPT-4 generated data on role-playing from various characters’ perspectives, focusing on different situations and emotions. Includes many multi-turn conversations. |
|
|
| ### Training hyperparameters |
|
|
| The following hyperparameters were used during training: |
| - learning_rate: 2e-05 |
| - train_batch_size: 4 |
| - eval_batch_size: 4 |
| - seed: 42 |
| - gradient_accumulation_steps: 5 |
| - total_train_batch_size: 20 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_steps: 10 |
| - num_epochs: 3 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:-----:|:----:|:---------------:| |
| | 1.955 | 0.38 | 25 | 1.9037 | |
| | 1.6598 | 0.75 | 50 | 1.6192 | |
| | 1.5649 | 1.13 | 75 | 1.5010 | |
| | 1.4424 | 1.5 | 100 | 1.4424 | |
| | 1.4142 | 1.88 | 125 | 1.4068 | |
| | 1.4951 | 2.25 | 150 | 1.3908 | |
| | 1.4418 | 2.63 | 175 | 1.3864 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.34.1 |
| - Pytorch 2.1.0+cu118 |
| - Datasets 2.14.6 |
| - Tokenizers 0.14.1 |
|
|
