Built with Axolotl

See axolotl config

axolotl version: 0.6.0

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
Downloads last month
1
Safetensors
Model size
1.24B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

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

Finetuned
(229)
this model

Dataset used to train axolotl-ai-co/numina-1b-ep3-lr3e-5-sft