base_model: meta-llama/Llama-3.2-1B
# Automatically upload checkpoint and final model to HF
hub_model_id: axolotl-ai-co/numina-3b-ep3-lr3e-5-sft

plugins:
  # - axolotl.integrations.kd.KDPlugin
  - axolotl.integrations.liger.LigerPlugin

liger_rms_norm: true
liger_glu_activation: true

torch_compile: true

strict: false

chat_template: llama3

dataloader_prefetch_factor: 512
dataloader_num_workers: 8
dataloader_pin_memory: true

datasets:
- field_messages: messages
  message_field_content: content
  message_field_role: role
  path: AI-MO/NuminaMath-CoT
  type: chat_template
  split: train

dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./outputs/out

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

wandb_project: numina-kd-experiment
wandb_entity: axolotl-ai
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 4
num_epochs: 3
optimizer: adamw_8bit
lr_scheduler: cosine
learning_rate: 3e-5
save_safetensors: true

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

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 100
evals_per_epoch: 2
eval_table_size:
saves_per_epoch: 1
debug:
  # deepspeed: deepspeed_configs/zero1.json
weight_decay: 0.0
_fsdp:
  - full_shard
  - auto_wrap
_fsdp_config:
  fsdp_limit_all_gathers: true
  fsdp_sync_module_states: true
  fsdp_offload_params: true
  fsdp_use_orig_params: false
  fsdp_cpu_ram_efficient_loading: true
  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
  fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer
  fsdp_state_dict_type: FULL_STATE_DICT
  fsdp_sharding_strategy: FULL_SHARD
  fsdp_backward_prefetch: BACKWARD_PRE
special_tokens:
  pad_token: <|finetune_right_pad_id|>
  eos_token: <|eot_id|>
  

numina-3b-ep3-lr3e-5-sft

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the AI-MO/NuminaMath-CoT 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: 8
total_train_batch_size: 32
total_eval_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 3

Training results

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0

axolotl-ai-co/numina-1b-ep3-lr3e-5-sft

numina-3b-ep3-lr3e-5-sft

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

axolotl-ai-co/
numina-1b-ep3-lr3e-5-sft