See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: unsloth/Meta-Llama-3.1-8B
bf16: true
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:
  - MATH-K-100-train_train_data.json
  ds_type: json
  path: /workspace/input_data/MATH-K-100-train_train_data.json
  type:
    field_input: problem
    field_instruction: prompt
    field_output: solution
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map:
  ? ''
  : cuda:0
do_eval: false
early_stopping_patience: null
eval_batch_size: 2
eval_sample_packing: false
eval_steps: 0
evaluation_strategy: 'no'
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 32
gradient_checkpointing: true
group_by_length: true
hub_model_id: cwaud/6df34bb6-ff27-4664-9ce6-90f7e5840ada
hub_repo: cwaud
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lora_target_modules:
- q_proj
- v_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 76GiB
max_steps: 520
micro_batch_size: 2
mlflow_experiment_name: /tmp/MATH-K-100-train_train_data.json
model_type: UnknownForCausalLM
num_epochs: 4
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_strategy: epoch
sequence_len: 2048
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_compile: false
train_on_inputs: false
val_set_size: 50
wandb_entity: rayonlabs-rayon-labs
wandb_mode: online
wandb_project: Public_TuningSN
wandb_run: miner_id_24
wandb_runid: 6df34bb6-ff27-4664-9ce6-90f7e5840ada
warmup_raio: 0.03
warmup_ratio: 0.05
weight_decay: 0.01
xformers_attention: null

6df34bb6-ff27-4664-9ce6-90f7e5840ada

This model is a fine-tuned version of unsloth/Meta-Llama-3.1-8B 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: 0.0001
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 32
• total_train_batch_size: 256
• 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: 26
• training_steps: 520

Training results

Framework versions

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