See axolotl config

axolotl version: 0.13.0.dev0

base_model: KaraKaraWitch/CavesOfQwen3-8b
hub_model_id: KaraKaraWitch/lossing-it-potpourri-5

load_in_8bit: true
load_in_4bit: false


chat_template: qwen3
datasets:
  - path: train.jsonl
    type: chat_template

    field_messages: conversation
    train_on_eos: all
    message_property_mappings:
      role: from
      content: content


    roles:
      assistant:
        - gpt
        - model
        - assistant
      user:
        - human
        - user
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: lora-out

adapter: lora
lora_model_dir:

sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true


plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: false
cut_cross_entropy: true

lora_r: 64
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: azure-edge
wandb_entity:
wandb_watch:
wandb_name: lossing-it-potpourri-5
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 8
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.002

bf16: auto
tf32: false

gradient_checkpointing: true
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 100
evals_per_epoch: 1
saves_per_epoch: 4
weight_decay: 0.0
special_tokens:
  eos_token: <|im_end|>

# save_first_step: true  # uncomment this to validate checkpoint saving works with your config

lossing-it-potpourri-5

This model is a fine-tuned version of KaraKaraWitch/CavesOfQwen3-8b on the train.jsonl 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: 0.002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• total_eval_batch_size: 4
• optimizer: Use OptimizerNames.ADAMW_BNB 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
• training_steps: 5616

Training results

Training Loss	Epoch	Step	Validation Loss	Mem Active(gib)	Mem Allocated(gib)	Mem Reserved(gib)
No log	0	0	1.7247	18.3	12.95	18.5

Framework versions

• PEFT 0.17.0
• Transformers 4.55.2
• Pytorch 2.7.1+cu126
• Datasets 4.0.0
• Tokenizers 0.21.4