Hugging Face's logo

cwaud
/
07c6aa8e-c0a0-43f1-841c-581e1b16a3d1

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
07c6aa8e-c0a0-43f1-841c-581e1b16a3d1 / README.md
cwaud's picture
cwaud
End of training
217c92b verified
preview code
|
raw
history blame contribute delete
4.21 kB
metadata
library_name: peft
license: llama3.2
base_model: unsloth/Llama-3.2-3B-Instruct
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: 07c6aa8e-c0a0-43f1-841c-581e1b16a3d1
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/Llama-3.2-3B-Instruct
bf16: auto
bnb_config_kwargs:
  bnb_4bit_quant_type: nf4
  bnb_4bit_use_double_quant: true
chat_template: llama3
cosine_min_lr_ratio: 0.1
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
  - f6bd9ab418599bba_train_data.json
  ds_type: json
  path: /workspace/input_data/f6bd9ab418599bba_train_data.json
  type:
    field_input: type
    field_instruction: problem
    field_output: solution
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: '{'''':torch.cuda.current_device()}'
do_eval: true
early_stopping_patience: 1
eval_batch_size: 2
eval_sample_packing: false
eval_steps: 25
evaluation_strategy: steps
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 16
gradient_checkpointing: true
group_by_length: true
hub_model_id: cwaud/07c6aa8e-c0a0-43f1-841c-581e1b16a3d1
hub_repo: cwaud
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
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
lora_target_modules:
- q_proj
- v_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 70GiB
  1: 70GiB
  2: 70GiB
  3: 70GiB
max_steps: 222
micro_batch_size: 2
mlflow_experiment_name: /tmp/f6bd9ab418599bba_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
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
save_strategy: steps
sequence_len: 2048
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_compile: false
train_on_inputs: false
trust_remote_code: true
val_set_size: 50
wandb_entity: rayonlabs-rayon-labs
wandb_mode: online
wandb_name: 07c6aa8e-c0a0-43f1-841c-581e1b16a3d1
wandb_project: Public_TuningSN
wandb_run: miner_id_24
wandb_runid: 07c6aa8e-c0a0-43f1-841c-581e1b16a3d1
warmup_raio: 0.03
warmup_ratio: 0.04
weight_decay: 0.01
xformers_attention: null

07c6aa8e-c0a0-43f1-841c-581e1b16a3d1

This model is a fine-tuned version of unsloth/Llama-3.2-3B-Instruct on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6734

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: 16
  • total_train_batch_size: 128
  • 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: 3
  • training_steps: 82

Training results

Training Loss Epoch Step Validation Loss
0.734 0.0368 1 0.8856
0.7633 0.9195 25 0.6957
0.5943 1.8391 50 0.6792
0.6301 2.7586 75 0.6734

Framework versions

  • PEFT 0.13.2
  • Transformers 4.45.2
  • Pytorch 2.4.1+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1