|
--- |
|
license: creativeml-openrail-m |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: 6b-jilp |
|
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-jilp |
|
|
|
This model is a fine-tuned version of [PygmalionAI/pygmalion-6b](https://huggingface.co/PygmalionAI/pygmalion-6b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.9014 |
|
- Accuracy: 0.1213 |
|
- Entropy: 1.8265 |
|
|
|
## 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: 12 |
|
- eval_batch_size: 8 |
|
- seed: 99 |
|
- distributed_type: multi-GPU |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 24 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.05 |
|
- num_epochs: 5.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Entropy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:-------:| |
|
| 2.5421 | 1.0 | 2815 | 1.9824 | 0.1183 | 2.0945 | |
|
| 2.426 | 2.0 | 5630 | 1.9443 | 0.1197 | 1.9446 | |
|
| 2.4504 | 3.0 | 8445 | 1.9248 | 0.1204 | 1.9272 | |
|
| 2.4573 | 4.0 | 11260 | 1.9102 | 0.1211 | 1.8612 | |
|
| 2.4421 | 5.0 | 14075 | 1.9014 | 0.1213 | 1.8265 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 1.13.1 |
|
- Datasets 2.7.1 |
|
- Tokenizers 0.13.3 |
|
|
