48 lines
1.1 KiB
Markdown
48 lines
1.1 KiB
Markdown
---
|
|
base_model: unsloth/Meta-Llama-3.1-8B-bnb-4bit
|
|
language:
|
|
- en
|
|
tags:
|
|
- text-generation-inference
|
|
- transformers
|
|
- unsloth
|
|
- llama
|
|
- trl
|
|
- sft
|
|
- dpo
|
|
license: llama3.1
|
|
datasets:
|
|
- reciperesearch/dolphin-sft-v0.1-preference
|
|
pipeline_tag: text-generation
|
|
license_name: llama3
|
|
license_link: LICENSE
|
|
model_creator: EpistemeAI
|
|
quantized_by: EpistemeAI
|
|
---
|
|
|
|
**gguf**:
|
|
- q4_k_m
|
|
- 16-bit
|
|
|
|
|
|
This model is based on Meta Llama 3.1 8b, and is governed by the Llama 3.1 license.
|
|
|
|
Fine-tune using ORPO
|
|
|
|
## Training Details
|
|
|
|
### Training Data
|
|
|
|
- dataset: reciperesearch/dolphin-sft-v0.1-preference
|
|
|
|
### Training Procedure
|
|
ORPO techniques
|
|
|
|
|
|
#### Training Hyperparameters
|
|
|
|
- **Training regime:** {{ training_regime | default("[More Information Needed]", true)}} <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
|
|
|
|
|
|
|
TrainOutput(global_step=30, training_loss=4.25380277633667, metrics={'train_runtime': 679.3467, 'train_samples_per_second': 0.353, 'train_steps_per_second': 0.044, 'total_flos': 0.0, 'train_loss': 4.25380277633667, 'epoch': 0.015}) |