|
--- |
|
license: apache-2.0 |
|
base_model: Deci/DeciLM-7B |
|
datasets: |
|
- HuggingFaceH4/ultrachat_200k |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bbdeci7b-sft-lora |
|
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. --> |
|
|
|
# bbdeci7b-sft-lora |
|
|
|
This model is a fine-tuned version of [Deci/DeciLM-7B](https://huggingface.co/Deci/DeciLM-7B) on [HuggingFaceH4/ultrachat_200k](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0110 |
|
|
|
## Model description |
|
more information to come soon |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- gradient_accumulation_steps: 128 |
|
- total_train_batch_size: 1024 |
|
- total_eval_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.0062 | 1.00 | 136 | 1.0110 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
