README.md

---
license: llama3
language:
- en
library_name: transformers
pipeline_tag: text-generation
datasets:
- cognitivecomputations/WizardLM_alpaca_evol_instruct_70k_unfiltered
tags:
- finetune
- llama
---
# WizardHermes-2-Pro-Llama-3-8b
Finetuned from Meta-Llama-3-8b, 0.55 epoches

Merged with Hermes-2-Pro-Llama-3-8b

Eval (0.0 temp) ([https://inflection.ai/assets/MMLU-Examples.pdf](https://inflection.ai/assets/MMLU-Examples.pdf), 0-shot):
```
Hermes 2 Pro LoRA (merged) (checkpoint 1): 7/12
Hermes 2 Pro LoRA (merged) (checkpoint 2): 9/12
Hermes 2 Pro Llama 3 8b: 8/12
```
TruthfulQA (0-shot):
```
Hermes 2 Pro LoRA (merged) (checkpoint 2): 9/15
Hermes 2 Pro Llama 3 8b: 7/15
```

**Trained using MonsterAPI**

LoRA training parameters:
```
{
	"deployment_name": "wizardlm-llama-3-8b",
	"pretrainedmodel_config": {
		"model_path": "meta-llama/Meta-Llama-3-8B",
		"other_model_info": null,
		"resume_checkpoint_path": "",
		"use_lora": true,
		"lora_r": 8,
		"lora_alpha": 16,
		"lora_dropout": 0,
		"lora_bias": "none",
		"use_quantization": false,
		"use_gradient_checkpointing": false,
		"parallelization": "nmp"
	},
	"data_config": {
		"data_path": "cognitivecomputations/WizardLM_alpaca_evol_instruct_70k_unfiltered",
		"data_subset": "default",
		"data_source_type": "hub_link",
		"cutoff_len": 4096,
		"data_split_config": {
			"train": 0.9,
			"validation": 0.1
		},
		"prevalidated": true,
		"concat_config": {
			"0": {
				"text": "Below is an instruction that describes a task. Write a response that appropriately completes the request. \n\n\n###Instruction:",
				"column": false
			},
			"1": {
				"text": "instruction",
				"column": true
			},
			"2": {
				"text": "\n\n\n###Response:",
				"column": false
			},
			"3": {
				"text": "output",
				"column": true
			}
		}
	},
	"training_config": {
		"early_stopping_patience": 5,
		"num_train_epochs": 5,
		"gradient_accumulation_steps": 1,
		"warmup_steps": 300,
		"learning_rate": 0.0005,
		"lr_scheduler_type": "reduce_lr_on_plateau",
		"group_by_length": false,
		"use_hugging_face": false
	},
	"logging_config": {
		"use_wandb": false,
		"wandb_username": "",
		"wandb_login_key": "",
		"wandb_project": "",
		"wandb_run_name": ""
	},
	"accessorytasks_config": {
		"run_eval_report": false,
		"run_quantize_merge": false
	}
}
```