See axolotl config
axolotl version: 0.11.0
base_model: Qwen/Qwen3-1.7B
load_in_8bit: false
load_in_4bit: false
datasets:
- path: train_ot3_ko_sampled.jsonl
type: chat_template
dataset_prepared_path: preprocess_ko
val_set_size: 0.01
output_dir: ./outputs_ko
dataloader_num_workers: 20
adapter:
lora_model_dir:
sequence_len: 16384
sample_packing: false
eval_sample_packing: false
pad_to_sequence_len: false
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
hub_model_id:
gradient_accumulation_steps: 64
micro_batch_size: 1
num_epochs: 5
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 4e-5
bf16: auto
tf32: false
gradient_checkpointing:
resume_from_checkpoint: ./outputs_ko/checkpoint-3540
logging_steps: 1
flash_attention: true
warmup_ratio: 0.05
weight_decay: 0.01
evals_per_epoch: 0
saves_per_epoch: 1
fsdp:
- full_shard
- auto_wrap
fsdp_config:
fsdp_state_dict_type: FULL_STATE_DICT
fsdp_transformer_layer_cls_to_wrap: Qwen3DecoderLayer
fsdp_activation_checkpointing: true
outputs_ko
This model is a fine-tuned version of Qwen/Qwen3-1.7B on the train_ot3_ko_sampled.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: 4e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 64
- total_train_batch_size: 128
- total_eval_batch_size: 2
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 221
- training_steps: 4423
Training results
Framework versions
- Transformers 4.53.1
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2
- Downloads last month
- 17