Hugging Face's logo

GuilhermeNaturaUmana
/
Nature-Reason-1.2-healed-censored-lora

PEFT
Safetensors
qwen2
Generated from Trainer
Model card Files Community
Nature-Reason-1.2-healed-censored-lora / README.md
GuilhermeNaturaUmana's picture
GuilhermeNaturaUmana
Upload folder using huggingface_hub
8209029 verified
preview code
|
raw
history blame contribute delete
3.17 kB
metadata
library_name: peft
tags:
  - generated_from_trainer
datasets:
  - GuilhermeNaturaUmana/Reasoning-deepseek
base_model: GuilhermeNaturaUmana/mini-test
model-index:
  - name: outputs/out
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.8.0.dev0

base_model: /root/mini-test
# optionally might have model_type or tokenizer_type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
# Automatically upload checkpoint and final model to HF
#hub_model_id: GuilhermeNaturaUmana/Nature-Reason-1-small

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: GuilhermeNaturaUmana/Reasoning-deepseek
    type: chat_template
    chat_template: qwen_25
    field_messages: messages
    message_field_role: role
    message_field_content: content
    roles:
      system:
        - system
      user:
        - user
      assistant:
        - assistant
dataset_prepared_path: last_run_prepared
val_set_size: 0.0
output_dir: ./outputs/out

sequence_len: 4096
sample_packing: false
pad_to_sequence_len: false

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
auto_resume_from_checkpoints: true
logging_steps: 1
xformers_attention:
flash_attention: false
flash_attn_cross_entropy: false
flash_attn_rms_norm: false
flash_attn_fuse_qkv: false
flash_attn_fuse_mlp: false

warmup_steps: 100
evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 4
debug:
deepspeed: deepspeed_configs/zero3_bf16_cpuoffload_all.json
weight_decay: 0.1

outputs/out

This model was trained from scratch on the GuilhermeNaturaUmana/Reasoning-deepseek 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: 0.0002
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 3
  • total_train_batch_size: 3
  • total_eval_batch_size: 3
  • optimizer: Use OptimizerNames.ADAMW_TORCH 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: 1.0

Training results

Framework versions

  • PEFT 0.14.0
  • Transformers 4.49.0
  • Pytorch 2.6.0+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0