Hugging Face's logo

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

Text Generation
Transformers
Safetensors
llama
axolotl
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
numina-1b-ep3-lr3e-5-sft / README.md
winglian's picture
winglian
Training in progress, step 1666
b6f9954 verified
preview code
|
raw
history blame
3.87 kB
metadata
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: []

Built with Axolotl

See axolotl config

axolotl version: 0.6.0

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|>

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

This model is a fine-tuned version of 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