Hugging Face's logo

watsonchua
/
hansard-gemma-2-9b-lora

PEFT
Safetensors
gemma2
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
hansard-gemma-2-9b-lora / README.md
watsonchua's picture
watsonchua
Upload folder using huggingface_hub
046fdc8 verified
preview code
|
raw
history blame contribute delete
2.85 kB
metadata
base_model: google/gemma-2-9b
library_name: peft
license: gemma
tags:
  - generated_from_trainer
model-index:
  - name: root/data/finetuned_models/gemma2-9b-hansard-llama-format
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

base_model: google/gemma-2-9b
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer


load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: /root/data/input_data/hansard/reply_by_hyd_llama3_formatted_train.jsonl
    type: completion
    field: input

# dataset_prepared_path: /root/data/prepared_datasets/hansard_gemma2_alpaca
# val_set_size: 0.1
output_dir: /root/data/finetuned_models/gemma2-9b-hansard-llama-format

sequence_len: 2500
sample_packing: false
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true

eval_sample_packing: false
pad_to_sequence_len: true

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:


gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

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:
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

root/data/finetuned_models/gemma2-9b-hansard-llama-format

This model is a fine-tuned version of google/gemma-2-9b on the None dataset.

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: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 178
  • num_epochs: 4

Training results

Framework versions

  • PEFT 0.11.1
  • Transformers 4.42.3
  • Pytorch 2.1.2+cu118
  • Datasets 2.19.1
  • Tokenizers 0.19.1