Hugging Face's logo

yuvraj17
/
EvolCodeLlama-3.1-8B-Instruct

Safetensors
llama
Model card Files Community
EvolCodeLlama-3.1-8B-Instruct / README.md
yuvraj17's picture
yuvraj17
Update README.md
84e06d9 verified
preview code
|
raw
history blame
3.15 kB
metadata
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
library_name: peft
license: llama3.1
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: EvolCodeLlama-3.1-8B-Instruct
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
is_llama_derived_model: true
hub_model_id: EvolCodeLlama-3.1-8B-Instruct

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: mlabonne/Evol-Instruct-Python-1k
    type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.02
output_dir: ./qlora-out

adapter: qlora
lora_model_dir:

sequence_len: 2048
sample_packing: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: axolotl
wandb_entity:
wandb_watch:
wandb_run_id:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 3
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 100
eval_steps: 0.01
save_strategy: epoch
save_steps:
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<|end_of_text|>"

EvolCodeLlama-3.1-8B-Instruct

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct using QLoRA (4-bit precision) on the mlabonne/Evol-Instruct-Python-1k dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4057

Training:

It was trained on an A40 for more than 1 hour with the above mentioned Axolotl yaml configurations.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0002
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 3

The lose curves are as:

image/png

image/png

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.0
  • Pytorch 2.4.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1