|
--- |
|
base_model: GeneZC/MiniChat-1.5-3B |
|
datasets: |
|
- generator |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: Rogue-MiniChat-1.5-3B |
|
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. --> |
|
|
|
# Rogue-MiniChat-1.5-3B |
|
|
|
This model is a fine-tuned version of [GeneZC/MiniChat-1.5-3B](https://huggingface.co/GeneZC/MiniChat-1.5-3B) on the generator dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9729 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 12 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 24 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.2186 | 1.0 | 109 | 1.0841 | |
|
| 1.0611 | 2.0 | 218 | 1.0355 | |
|
| 0.9969 | 3.0 | 327 | 1.0105 | |
|
| 0.9458 | 4.0 | 436 | 0.9904 | |
|
| 0.8941 | 5.0 | 545 | 0.9729 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.2.dev0 |
|
- Transformers 4.36.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.2 |
