100 lines
2.2 KiB
Markdown
100 lines
2.2 KiB
Markdown
---
|
|
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
|
|
}
|
|
}
|
|
``` |