Hugging Face's logo

bbytxt
/
ad074d8b-d829-465b-ab6c-9c65e255bc33

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files Community
ad074d8b-d829-465b-ab6c-9c65e255bc33 / README.md
bbytxt's picture
bbytxt
End of training
ce356c3 verified
preview code
|
raw
history blame contribute delete
4.24 kB
metadata
library_name: peft
license: gemma
base_model: unsloth/gemma-2-9b-it
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: ad074d8b-d829-465b-ab6c-9c65e255bc33
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/gemma-2-9b-it
bf16: auto
chat_template: llama3
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
  - 23cf20a0dca9d311_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/23cf20a0dca9d311_train_data.json
  type:
    field_input: context
    field_instruction: question
    field_output: answers
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 1
eval_batch_size: 8
eval_max_new_tokens: 128
eval_steps: 25
eval_table_size: null
evals_per_epoch: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: bbytxt/ad074d8b-d829-465b-ab6c-9c65e255bc33
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0003
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 70GB
max_steps: 200
micro_batch_size: 8
mlflow_experiment_name: /tmp/23cf20a0dca9d311_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 50
saves_per_epoch: null
sequence_len: 1028
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 50
wandb_entity: null
wandb_mode: online
wandb_name: ad074d8b-d829-465b-ab6c-9c65e255bc33
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: ad074d8b-d829-465b-ab6c-9c65e255bc33
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

ad074d8b-d829-465b-ab6c-9c65e255bc33

This model is a fine-tuned version of unsloth/gemma-2-9b-it on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2769

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: 0.0003
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • training_steps: 200

Training results

Training Loss Epoch Step Validation Loss
4.0382 0.0004 1 5.3398
0.4101 0.0102 25 0.3910
0.276 0.0205 50 0.3750
0.4641 0.0307 75 0.3461
0.2448 0.0410 100 0.3171
0.2275 0.0512 125 0.2754
0.3047 0.0614 150 0.2740
0.212 0.0717 175 0.2769

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.0
  • Pytorch 2.5.0+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1