slimorca-gemma2-9b / README.md
winglian's picture
Upload folder using huggingface_hub
1d0765a verified
metadata
base_model: google/gemma-2-9b
library_name: peft
license: gemma
tags:
  - generated_from_trainer
model-index:
  - name: outputs/out
    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

# huggingface repo
chat_template: gemma
datasets:
  - path: cgato/SlimOrcaDedupCleaned
    type: chat_template
    chat_template: gemma
    drop_system_message: true
val_set_size: 0.0
output_dir: ./outputs/out

adapter: lora
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_modules_to_save:
  - embed_tokens
  - lm_head


sequence_len: 2048
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

wandb_project: gemma2-exp
wandb_entity: oaaic
wandb_watch:
wandb_name:
wandb_log_model:


gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 1
optimizer: adamw_bnb_8bit
adam_beta2: 0.95
adam_eps: 0.00001
max_grad_norm: 1.0
lr_scheduler: cosine
learning_rate: 0.00003

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: 2
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:

Visualize in Weights & Biases

outputs/out

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: 3e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • total_eval_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 89
  • num_epochs: 1

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