metadata
license: creativeml-openrail-m
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: 6b-gpteacher-role-play-lmgym
results: []
6b-gpteacher-role-play-lmgym
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: 1.9316
- Accuracy: 0.1617
- Entropy: 1.8675
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-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 99
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Entropy |
|---|---|---|---|---|---|
| 2.0861 | 1.0 | 119 | 2.0195 | 0.1562 | 1.8990 |
| 1.9173 | 2.0 | 238 | 1.9658 | 0.1585 | 1.9174 |
| 1.871 | 3.0 | 357 | 1.9463 | 0.1595 | 1.8724 |
| 1.8566 | 4.0 | 476 | 1.9316 | 0.1617 | 1.8675 |
Framework versions
- Transformers 4.28.1
- Pytorch 1.13.1
- Datasets 2.7.1
- Tokenizers 0.13.3