---
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-3B
tags:
- axolotl
- generated_from_trainer
datasets:
- axolotl-ai-co/numina-cot-logprobs-859k-8b-sft
model-index:
- name: numina-3b-ep3-lr3e-5-kd
  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: `0.6.0`
```yaml
base_model: meta-llama/Llama-3.2-3B
# Automatically upload checkpoint and final model to HF
hub_model_id: axolotl-ai-co/numina-3b-ep3-lr3e-5-kd

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

kd_trainer: true
kd_ce_alpha: 0.4
kd_alpha: 1.0
kd_temperature: 2.0

dataloader_prefetch_factor: 512
dataloader_num_workers: 8
dataloader_pin_memory: true

datasets:
- field_messages: messages
  message_field_content: content
  message_field_role: role
  logprobs_field: llm_logprobs_logprobs
  path: axolotl-ai-co/numina-cot-logprobs-859k-8b-sft
  type: axolotl.integrations.kd.chat_template
  split: train
  temperature: 1.0
    # preprocess_shards: 10

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|>
  

```

</details><br>

# numina-3b-ep3-lr3e-5-kd

This model is a fine-tuned version of [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) on the axolotl-ai-co/numina-cot-logprobs-859k-8b-sft 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