|
--- |
|
license: creativeml-openrail-m |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: 6b-gpteacher-role-play-chatml-10epoch |
|
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. --> |
|
|
|
# 6b-gpteacher-role-play-chatml-10epoch |
|
|
|
This model is a fine-tuned version of [PygmalionAI/pygmalion-6b](https://huggingface.co/PygmalionAI/pygmalion-6b) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.9141 |
|
- Accuracy: 0.1596 |
|
- Entropy: 1.7788 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 8 |
|
- seed: 99 |
|
- distributed_type: multi-GPU |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- num_epochs: 10.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Entropy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------:| |
|
| 2.0504 | 1.0 | 238 | 2.0176 | 0.1563 | 1.9978 | |
|
| 1.8932 | 2.0 | 476 | 1.9707 | 0.1584 | 1.9182 | |
|
| 1.8611 | 3.0 | 714 | 1.9473 | 0.1602 | 1.8831 | |
|
| 1.8206 | 4.0 | 952 | 1.9307 | 0.1604 | 1.8725 | |
|
| 1.7936 | 5.0 | 1190 | 1.9238 | 0.1613 | 1.8354 | |
|
| 1.7823 | 6.0 | 1428 | 1.9189 | 0.1618 | 1.8175 | |
|
| 1.7742 | 7.0 | 1666 | 1.9150 | 0.1615 | 1.8082 | |
|
| 1.762 | 8.0 | 1904 | 1.9141 | 0.1605 | 1.8145 | |
|
| 1.7437 | 9.0 | 2142 | 1.9160 | 0.1604 | 1.7750 | |
|
| 1.7358 | 10.0 | 2380 | 1.9141 | 0.1596 | 1.7788 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.7.1 |
|
- Tokenizers 0.13.3 |
|
|
