llama3.2-3b-base-data-nemotron

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

<details><summary>See axolotl config</summary>

axolotl version: 0.13.0.dev0

# ===== Modelo =====
base_model: meta-llama/Llama-3.2-3B
tokenizer_type: AutoTokenizer
trust_remote_code: true

# Llama 3.1 é derivado de Llama, isso ajuda Axolotl a aplicar otmizações corretas
is_llama_derived_model: true

# Template de conversa
chat_template: chatml

plugins:
  - axolotl.integrations.liger.LigerPlugin

special_tokens:
  pad_token: "<|eot_id|>"

# ===== Dataset (Nemotron Post-Training SFT) =====
datasets:
  - path: nvidia/Llama-Nemotron-Post-Training-Dataset
    name: SFT           # subset da HF
    split: chat         # você pode duplicar este bloco para math_v1.1, science, etc.
    type: chat_template
    field_messages: input            # coluna com a lista de {role, content}
    # Se os campos já forem "role" e "content", não precisa do mapping abaixo.
    message_property_mappings:
      role: role
      content: content
    # A coluna "output" é a resposta; o Axolotl converte input+output em conversa interna.
    field_output: output

# Não treinar nos tokens do usuário/system
train_on_inputs: false

# ===== Comprimento de contexto =====
sequence_len: 8192
eval_sequence_len: 8192
pad_to_sequence_len: true
sample_packing: true
sample_packing_group_size: 100000
sample_packing_bin_size: 200
group_by_length: true

# ===== Batch / epochs – hiperparâmetros do paper =====
micro_batch_size: 1               # per-device batch size
gradient_accumulation_steps: 8    # 4 GPUs -> effective batch = 32
num_epochs: 2

# (opcional) se quiser deixar explícito que você tem 4 GPUs para DP
# dp_shard_size: 4

# ===== Otimizador / LR =====
learning_rate: 2.0e-5
optimizer: adamw_torch_fused
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1.0e-8

lr_scheduler: cosine
warmup_steps: 100
weight_decay: 0.0   # paper não especifica, então deixei 0.0 (padrão)

# ===== Precisão / memória =====
bf16: true          # ou "auto" se preferir
tf32: true
gradient_checkpointing: true
activation_offloading: false

# ===== Eval / logging / checkpoints =====
val_set_size: 0.01          # 1% do dataset para validação (ajuste se quiser)
eval_strategy: steps
eval_steps: 100

save_strategy: steps
save_steps: 100
save_total_limit: 3
save_only_model: false
save_safetensors: true
load_best_model_at_end: true
metric_for_best_model: eval_loss
greater_is_better: false

logging_steps: 10

# ===== Saída / reproducibilidade / tracking =====
output_dir: ./outputs/llama31_3b_nemotron_full_sft
seed: 42

use_wandb: true
wandb_project: "llama32_nemotron_sft"
wandb_name: "llama32-3b-base-full-sft-chatml"

</details><br>

outputs/llama31_3b_nemotron_full_sft

This model is a fine-tuned version of meta-llama/Llama-3.2-3B on the nvidia/Llama-Nemotron-Post-Training-Dataset dataset. It achieves the following results on the evaluation set:

• Loss: 1.2638
• Memory/max Active (gib): 30.79
• Memory/max Allocated (gib): 30.79
• Memory/device Reserved (gib): 45.32

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: 2e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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
• training_steps: 570

Training results

Framework versions

• Transformers 4.57.1
• Pytorch 2.9.0+cu130
• Datasets 4.3.0
• Tokenizers 0.22.1