See axolotl config

axolotl version: 0.10.0.dev0

base_model: meta-llama/Llama-3.2-1B-Instruct
# Automatically upload checkpoint and final model to HF
hub_model_id: syvai/reasoning-gen-1b

datasets:
  - path: syvai/reasoning-gen
    type: chat_template

dataset_prepared_path: last_run_prepared
val_set_size: 0.02
output_dir: ./outputs/out

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

wandb_project: reasoning-gen
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5

bf16: auto
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

warmup_steps: 100
evals_per_epoch: 2
saves_per_epoch: 1
weight_decay: 0.0
special_tokens:
  pad_token: <|end_of_text|>

reasoning-gen-1b

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on the syvai/reasoning-gen dataset. It achieves the following results on the evaluation set:

• Loss: 0.9280

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.PAGED_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: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.2977	0.0001	1	1.3637
1.0656	0.5000	5243	0.9280

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.1
• Tokenizers 0.21.1