bratao/Qwen3OIE-4B

See axolotl config

axolotl version: 0.9.2

base_model: Qwen/Qwen3-4B
# Automatically upload checkpoint and final model to HF
# hub_model_id: username/custom_model_name

load_in_8bit: false
load_in_4bit: false
strict: false

plugins:
  - axolotl.integrations.liger.LigerPlugin

liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_layer_norm: true
liger_fused_linear_cross_entropy: true

datasets:
  - path: "train_dataset_updated.jsonl"
    type: chat_template

    field_messages: conversations
    message_property_mappings:
      role: from
      content: value

output_dir: ./outputs/out-4b/

sequence_len: 2048
sample_packing: true
flex_attention: true
pad_to_sequence_len: true

flex_attn_compile_kwargs:
  dynamic: false
  mode: max-autotune-no-cudagraphs



wandb_project: openie-qwen3
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 8
num_epochs: 3
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 2e-5

bf16: true
tf32: true

resume_from_checkpoint:
logging_steps: 1

evals_per_epoch: 1
saves_per_epoch: 1

warmup_steps: 10
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

outputs/out-4b/

This model is a fine-tuned version of Qwen/Qwen3-4B on the train_dataset_updated.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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use 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: 10
• num_epochs: 3.0

Training results

Framework versions

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