MaziyarPanahi's picture
Update README.md
1964dbb verified
|
raw
history blame
4.04 kB
metadata
license: apache-2.0
library_name: transformers
tags:
  - axolotl
  - generated_from_trainer
  - gemma
  - 7b
  - alpaca
  - peft
  - lora
  - qlora
  - openhermes
base_model: google/gemma-7b
model-index:
  - name: gemma-7b-Open-Hermes-v0.1
    results: []
datasets:
  - teknium/openhermes
pipeline_tag: text-generation

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

# use google/gemma-7b if you have access
#base_model: mhenrichsen/gemma-7b
base_model: google/gemma-7b
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

hub_model_id: MaziyarPanahi/gemma-7b-Open-Hermes-v0.1
hf_use_auth_token: true

load_in_8bit: false
load_in_4bit: true
strict: false

# huggingface repo
datasets:
  - path: teknium/openhermes
    type: alpaca
val_set_size: 0.1
output_dir: ./qlora-gemma-7b-openhermes

adapter: qlora
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true


sequence_len: 4096
sample_packing: false
pad_to_sequence_len: false

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:


gradient_accumulation_steps: 3
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

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

warmup_ratio: 0.1
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

gemma-7b-Open-Hermes-v0.1

This model is a fine-tuned version of google/gemma-7b on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4456

How to use

PEFT

from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM

model_id = "MaziyarPanahi/gemma-7b-Open-Hermes-v0.1"

config = PeftConfig.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b")
model = PeftModel.from_pretrained(model, model_id)

Transformers

# Use a pipeline as a high-level helper
from transformers import pipeline

model_id = "MaziyarPanahi/gemma-7b-Open-Hermes-v0.1"

pipe = pipeline("text-generation", model=model_id)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

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: 0.0002
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 3
  • total_train_batch_size: 24
  • total_eval_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 227
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
1.3258 0.0 1 1.9697
0.63 0.25 2277 1.5227
0.642 0.5 4554 1.4835
0.7721 0.75 6831 1.4456

Framework versions

  • PEFT 0.8.2
  • Transformers 4.39.0.dev0
  • Pytorch 2.2.0+cu121
  • Datasets 2.17.0
  • Tokenizers 0.15.0