Hugging Face's logo

mjobe105
/
qlora-dolphindataset

PEFT
Safetensors
llama
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
qlora-dolphindataset / README.md
mjobe105's picture
mjobe105
Upload folder using huggingface_hub
c15d061 verified
preview code
|
raw
history blame
3.74 kB
metadata
license: llama3
library_name: peft
tags:
  - generated_from_trainer
base_model: meta-llama/Meta-Llama-3-70B-Instruct
model-index:
  - name: workspace/data/out/qlora
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

base_model: meta-llama/Meta-Llama-3-70B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer  # PreTrainedTokenizerFast

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: /workspace/data/dataset/hex_phi_dolphin_responses.jsonl
    ds_type: json
    type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: /workspace/data/out/qlora

adapter: qlora
lora_model_dir:

sequence_len: 512
sample_packing: false
eval_sample_packing: false
pad_to_sequence_len: 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:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00001

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

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

warmup_steps: 100
evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|end_of_text|>

workspace/data/out/qlora

This model is a fine-tuned version of meta-llama/Meta-Llama-3-70B-Instruct on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.0876

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 10
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 80
  • total_eval_batch_size: 20
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss
1.7723 0.2667 1 2.0884
1.8176 0.5333 2 2.0872
1.8499 0.8 3 2.0874
1.7963 1.0667 4 2.0865
1.8762 1.3333 5 2.0866
1.7795 1.6 6 2.0875
1.8179 1.8667 7 2.0880
1.8353 2.1333 8 2.0874
1.8009 2.4 9 2.0864
1.7625 2.6667 10 2.0869
1.8273 2.9333 11 2.0874
1.8198 3.2 12 2.0876

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.2
  • Pytorch 2.1.2+cu118
  • Datasets 2.19.1
  • Tokenizers 0.19.1