base_model: timarni/qwen3-0.6B-mmlu-alpaca
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

plugins:
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
strict: false

chat_template: qwen3
datasets:
  - path: timarni/sciq_alpaca
    type: alpaca
    split: train

val_set_size: 0.15
output_dir: ./outputs/qwen3_mmlu_sciq_alpaca
dataset_prepared_path: last_run_prepared

sequence_len: 4096 #2048
sample_packing: true
eval_sample_packing: true
pad_to_sequence_len: true

# To be sure that no LORA is done
adapter: null
lora: false
merge_lora: false

wandb_project: mnlp_project
wandb_entity: tim-arni
wandb_watch:
wandb_name: qwen3-0.6B-mmlu-sciq
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 0.00005 # 0.0002

bf16: auto
tf32: true

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

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
weight_decay: 0.0
special_tokens:

outputs/qwen3_mmlu_sciq_alpaca

This model is a fine-tuned version of timarni/qwen3-0.6B-mmlu-alpaca on the timarni/sciq_alpaca dataset. It achieves the following results on the evaluation set:

Loss: 0.0583

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: 5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 2
optimizer: Use 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: 10
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.149	0.0127	1	0.0983
0.0755	0.2532	20	0.0744
0.0678	0.5063	40	0.0625
0.0564	0.7595	60	0.0583

Framework versions

Transformers 4.51.3
Pytorch 2.5.1+cu121
Datasets 3.5.1
Tokenizers 0.21.1

timarni/qwen3_mmlu_sciq_alpaca

outputs/qwen3_mmlu_sciq_alpaca

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

timarni/
qwen3_mmlu_sciq_alpaca