README.md

---
library_name: peft
license: other
base_model: axolotl-quants/Llama-4-Scout-17B-16E-Linearized-bnb-nf4-bf16
tags:
- generated_from_trainer
datasets:
- mlabonne/FineTome-100k
model-index:
- name: outputs/out
  results: []
---

<!-- 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"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>

axolotl version: `0.8.0`
```yaml
base_model: axolotl-quants/Llama-4-Scout-17B-16E-Linearized-bnb-nf4-bf16
model_type: Llama4ForConditionalGeneration
  # Automatically upload checkpoint and final model to HF
  # hub_model_id: username/custom_model_name

strict: false

# torch_compile: true
plugins:
  - axolotl.integrations.liger.LigerPlugin

liger_glu_activation: true
liger_rms_norm: true
liger_layer_norm: true

llama4_linearized_experts: true
load_in_4bit: true
adapter: qlora
lora_r: 32
lora_alpha: 64
lora_target_modules:
  - self_attn.q_proj
  - self_attn.k_proj
  - self_attn.v_proj
  - self_attn.o_proj
  - shared_expert.gate_proj
  - shared_expert.up_proj
  - shared_expert.down_proj
    # - experts.gate_projs.[0-9]+$
    # - experts.up_projs.[0-9]+$
    # - experts.down_projs.[0-9]+$
lora_modules_to_save:
  # - lm_head
  # - embed_tokens

chat_template: llama4
datasets:
  - path: mlabonne/FineTome-100k
    type: chat_template
    split: train[:20%]
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value

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:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 3
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 1e-4

bf16: true
tf32: true

logging_steps: 1
flash_attention: true

warmup_steps: 10
evals_per_epoch: 1
saves_per_epoch: 1
weight_decay: 0.0
fsdp:
  - auto_wrap
  - full_shard
fsdp_config:
  fsdp_transformer_layer_cls_to_wrap: Llama4TextDecoderLayer
  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_state_dict_type: FULL_STATE_DICT
  fsdp_sharding_strategy: FULL_SHARD
  fsdp_activation_checkpointing: true
special_tokens:
  pad_token: <|finetune_right_pad_id|>
  eos_token: <|eot|>

```

</details><br>

# outputs/out

This model is a fine-tuned version of [axolotl-quants/Llama-4-Scout-17B-16E-Linearized-bnb-nf4-bf16](https://huggingface.co/axolotl-quants/Llama-4-Scout-17B-16E-Linearized-bnb-nf4-bf16) on the mlabonne/FineTome-100k 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: 8
- total_train_batch_size: 16
- total_eval_batch_size: 16
- 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: 10
- num_epochs: 3.0

### Training results



### Framework versions

- PEFT 0.15.1
- Transformers 4.51.1
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1