timarni/qwen3-0.6B-mmlu-alpaca

See axolotl config

axolotl version: 0.9.2

base_model: Qwen/Qwen3-0.6B-Base
# 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/MNLP_dataset_mmlu_train
    type: alpaca
    split: train

val_set_size: 0.15
output_dir: ./outputs/qwen3_mmlu_alpaca_lr_5e-5
dataset_prepared_path: last_run_prepared

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

wandb_project: mnlp_project
wandb_entity: tim-arni
wandb_watch:
wandb_name: qwen3-0.6B-mmlu_alpaca_style_lr_5e-5
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
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_alpaca_lr_5e-5

This model is a fine-tuned version of Qwen/Qwen3-0.6B-Base on the timarni/MNLP_dataset_mmlu_train dataset. It achieves the following results on the evaluation set:

• Loss: 0.0741

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
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• total_eval_batch_size: 4
• 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: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.2846	0.0009	1	0.4087
0.0757	0.2502	275	0.0757
0.0592	0.5005	550	0.0678
0.0657	0.7507	825	0.0639
0.0435	1.0009	1100	0.0605
0.01	1.2511	1375	0.0704
0.0035	1.5014	1650	0.0756
0.0081	1.7516	1925	0.0741

Framework versions

• Transformers 4.51.3
• Pytorch 2.5.1+cu121
• Datasets 3.5.1
• Tokenizers 0.21.1