metadata
license: creativeml-openrail-m
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: 6b-gpteacher-role-play-chatml
results: []
6b-gpteacher-role-play-chatml
This model is a fine-tuned version of PygmalionAI/pygmalion-6b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2441
- Accuracy: 0.1505
- Entropy: 1.8521
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: 1e-06
- train_batch_size: 2
- eval_batch_size: 8
- seed: 99
- distributed_type: multi-GPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 4.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Entropy |
|---|---|---|---|---|---|
| 2.2397 | 0.99 | 59 | 2.2793 | 0.1499 | 1.8243 |
| 2.2192 | 2.0 | 119 | 2.2695 | 0.1499 | 1.8324 |
| 2.2175 | 2.99 | 178 | 2.2578 | 0.1499 | 1.8420 |
| 2.1434 | 3.97 | 236 | 2.2441 | 0.1505 | 1.8521 |
Framework versions
- Transformers 4.28.1
- Pytorch 1.13.1
- Datasets 2.7.1
- Tokenizers 0.13.3