Hugging Face's logo

monsterapi
/
zephyr_7b_WizardLMEvolInstruct70k

PEFT
meta-llama
code
instruct
WizardLM
Mistral-7B-v0.1
Model card Files Community
zephyr_7b_WizardLMEvolInstruct70k / README.md
Zangs3011's picture
Zangs3011
Update README.md
860d25c
preview code
|
raw
history blame contribute delete
1.41 kB
metadata
library_name: peft
tags:
  - meta-llama
  - code
  - instruct
  - WizardLM
  - Mistral-7B-v0.1
datasets:
  - WizardLM/WizardLM_evol_instruct_70k
base_model: HuggingFaceH4/zephyr-7b-alpha
license: apache-2.0

Finetuning Overview:

Model Used: HuggingFaceH4/zephyr-7b-alpha
Dataset: WizardLM/WizardLM_evol_instruct_70k

Dataset Insights:

The WizardLM/WizardLM_evol_instruct_70k dataset, tailored specifically for enhancing interactive capabilities, was developed using the EVOL-Instruct method. This method enhances a smaller dataset with tougher questions for the LLM to perform.

Finetuning Details:

With the utilization of MonsterAPI's LLM finetuner, this finetuning:

  • Was achieved with great cost-effectiveness.
  • Completed in a total duration of 5hrs 18mins for 1 epoch using an A6000 48GB GPU.
  • Costed $10 for the entire epoch.

Hyperparameters & Additional Details:

  • Epochs: 1
  • Cost Per Epoch: $10.5
  • Total Finetuning Cost: $10.5
  • Model Path: HuggingFaceH4/zephyr-7b-alpha
  • Learning Rate: 0.0002
  • Data Split: 90% train 10% validation
  • Gradient Accumulation Steps: 4

Prompt Structure

### INSTRUCTION:
[instruction]

### RESPONSE:
[output]

Training loss : training loss

license: apache-2.0