oolel-lit-gemma/args.json

{
  "output_dir": "/workspace/output/v0-20260216-180455",
  "overwrite_output_dir": false,
  "do_train": false,
  "do_eval": false,
  "do_predict": false,
  "eval_strategy": "no",
  "prediction_loss_only": false,
  "per_device_train_batch_size": 8,
  "per_device_eval_batch_size": 1,
  "per_gpu_train_batch_size": null,
  "per_gpu_eval_batch_size": null,
  "gradient_accumulation_steps": 16,
  "eval_accumulation_steps": null,
  "eval_delay": 0,
  "torch_empty_cache_steps": null,
  "learning_rate": 0.0001,
  "weight_decay": 0.1,
  "adam_beta1": 0.9,
  "adam_beta2": 0.95,
  "adam_epsilon": 1e-08,
  "max_grad_norm": 1.0,
  "num_train_epochs": 2.0,
  "max_steps": -1,
  "lr_scheduler_type": "cosine",
  "lr_scheduler_kwargs": null,
  "warmup_ratio": 0.05,
  "warmup_steps": 0,
  "log_level": "passive",
  "log_level_replica": "warning",
  "log_on_each_node": true,
  "logging_dir": "/workspace/output/v0-20260216-180455/runs",
  "logging_strategy": "steps",
  "logging_first_step": true,
  "logging_steps": 100,
  "logging_nan_inf_filter": true,
  "save_strategy": "steps",
  "save_steps": 1000.0,
  "save_total_limit": 3,
  "save_safetensors": true,
  "save_on_each_node": false,
  "save_only_model": false,
  "restore_callback_states_from_checkpoint": false,
  "no_cuda": false,
  "use_cpu": false,
  "use_mps_device": false,
  "seed": 42,
  "data_seed": 42,
  "jit_mode_eval": false,
  "bf16": true,
  "fp16": false,
  "fp16_opt_level": "O1",
  "half_precision_backend": "auto",
  "bf16_full_eval": false,
  "fp16_full_eval": false,
  "tf32": null,
  "local_rank": -1,
  "ddp_backend": null,
  "tpu_num_cores": null,
  "tpu_metrics_debug": false,
  "debug": null,
  "dataloader_drop_last": false,
  "eval_steps": null,
  "dataloader_num_workers": 16,
  "dataloader_prefetch_factor": null,
  "past_index": -1,
  "run_name": "/workspace/output/v0-20260216-180455",
  "disable_tqdm": null,
  "remove_unused_columns": true,
  "label_names": null,
  "load_best_model_at_end": false,
  "metric_for_best_model": "loss",
  "greater_is_better": false,
  "ignore_data_skip": false,
  "fsdp": [],
  "fsdp_min_num_params": 0,
  "fsdp_config": null,
  "fsdp_transformer_layer_cls_to_wrap": null,
  "accelerator_config": {
    "dispatch_batches": false
  },
  "parallelism_config": null,
  "deepspeed": null,
  "label_smoothing_factor": 0.0,
  "optim": "adamw_torch_fused",
  "optim_args": null,
  "adafactor": false,
  "group_by_length": false,
  "length_column_name": "length",
  "report_to": [
    "tensorboard"
  ],
  "project": "huggingface",
  "trackio_space_id": "trackio",
  "ddp_find_unused_parameters": null,
  "ddp_bucket_cap_mb": null,
  "ddp_broadcast_buffers": null,
  "dataloader_pin_memory": true,
  "dataloader_persistent_workers": false,
  "skip_memory_metrics": true,
  "use_legacy_prediction_loop": false,
  "push_to_hub": true,
  "resume_from_checkpoint": null,
  "hub_model_id": null,
  "hub_strategy": "every_save",
  "hub_token": null,
  "hub_private_repo": true,
  "hub_always_push": false,
  "hub_revision": null,
  "gradient_checkpointing": true,
  "gradient_checkpointing_kwargs": null,
  "include_inputs_for_metrics": false,
  "include_for_metrics": [],
  "eval_do_concat_batches": true,
  "fp16_backend": "auto",
  "push_to_hub_model_id": null,
  "push_to_hub_organization": null,
  "push_to_hub_token": null,
  "mp_parameters": "",
  "auto_find_batch_size": false,
  "full_determinism": false,
  "torchdynamo": null,
  "ray_scope": "last",
  "ddp_timeout": 18000000,
  "torch_compile": false,
  "torch_compile_backend": null,
  "torch_compile_mode": null,
  "include_tokens_per_second": false,
  "include_num_input_tokens_seen": false,
  "neftune_noise_alpha": null,
  "optim_target_modules": null,
  "batch_eval_metrics": false,
  "eval_on_start": false,
  "use_liger_kernel": false,
  "liger_kernel_config": null,
  "eval_use_gather_object": false,
  "average_tokens_across_devices": true,
  "sortish_sampler": false,
  "predict_with_generate": false,
  "generation_max_length": null,
  "generation_num_beams": null,
  "generation_config": null,
  "tuner_backend": "peft",
  "vit_gradient_checkpointing": null,
  "router_aux_loss_coef": 0.0,
  "enable_dft_loss": false,
  "enable_channel_loss": false,
  "check_model": true,
  "acc_strategy": "token",
  "train_dataloader_shuffle": true,
  "max_epochs": null,
  "aligner_lr": null,
  "vit_lr": null,
  "use_logits_to_keep": null,
  "ds3_gather_for_generation": true,
  "resume_only_model": false,
  "optimizer": null,
  "loss_type": null,
  "metric": null,
  "eval_use_evalscope": false,
  "eval_dataset": [],
  "eval_dataset_args": null,
  "eval_limit": null,
  "eval_generation_config": null,
  "extra_eval_args": null,
  "use_flash_ckpt": false,
  "use_ray": false,
  "ray_exp_name": null,
  "device_groups": null,
  "model": "google/gemma-3-270m-it",
  "model_type": "gemma3_text",
  "model_revision": null,
  "task_type": "causal_lm",
  "torch_dtype": "bfloat16",
  "attn_impl": "flash_attn",
  "new_special_tokens": [],
  "num_labels": null,
  "problem_type": null,
  "rope_scaling": null,
  "device_map": null,
  "max_memory": {},
  "max_model_len": null,
  "local_repo_path": null,
  "init_strategy": null,
  "template": "gemma3_text",
  "system": null,
  "max_length": 4096,
  "truncation_strategy": "delete",
  "max_pixels": null,
  "agent_template": null,
  "norm_bbox": null,
  "use_chat_template": true,
  "padding_side": "right",
  "padding_free": false,
  "loss_scale": "default",
  "sequence_parallel_size": 1,
  "template_backend": "swift",
  "response_prefix": null,
  "enable_thinking": null,
  "add_non_thinking_prefix": true,
  "dataset": [
    "soynade-research/wo-dioula"
  ],
  "val_dataset": [],
  "cached_dataset": [],
  "cached_val_dataset": [],
  "split_dataset_ratio": 0.0,
  "dataset_num_proc": 1,
  "load_from_cache_file": false,
  "dataset_shuffle": true,
  "val_dataset_shuffle": false,
  "streaming": false,
  "interleave_prob": null,
  "stopping_strategy": "first_exhausted",
  "shuffle_buffer_size": 1000,
  "download_mode": "reuse_dataset_if_exists",
  "columns": {},
  "strict": false,
  "model_name": [
    "oolel-lit-gemma"
  ],
  "model_author": [
    "soynade-research"
  ],
  "custom_dataset_info": [],
  "quant_method": null,
  "quant_bits": null,
  "hqq_axis": null,
  "bnb_4bit_compute_dtype": "bfloat16",
  "bnb_4bit_quant_type": "nf4",
  "bnb_4bit_use_double_quant": true,
  "bnb_4bit_quant_storage": null,
  "max_new_tokens": 64,
  "temperature": 0.0,
  "top_k": null,
  "top_p": null,
  "repetition_penalty": null,
  "num_beams": 1,
  "stream": false,
  "stop_words": [],
  "logprobs": false,
  "top_logprobs": null,
  "structured_outputs_regex": null,
  "ckpt_dir": null,
  "lora_modules": [],
  "train_type": "full",
  "adapters": [],
  "external_plugins": [],
  "model_kwargs": {},
  "load_args": false,
  "load_data_args": false,
  "packing": false,
  "packing_length": null,
  "packing_num_proc": 1,
  "lazy_tokenize": false,
  "custom_register_path": [],
  "use_hf": true,
  "ignore_args_error": false,
  "use_swift_lora": false,
  "freeze_parameters": [],
  "freeze_parameters_regex": null,
  "freeze_parameters_ratio": 0.0,
  "trainable_parameters": [],
  "trainable_parameters_regex": null,
  "freeze_llm": false,
  "freeze_vit": true,
  "freeze_aligner": true,
  "target_modules": [
    "all-linear"
  ],
  "target_regex": null,
  "target_parameters": null,
  "modules_to_save": [],
  "lora_rank": 8,
  "lora_alpha": 32,
  "lora_dropout": 0.05,
  "lora_bias": "none",
  "lora_dtype": null,
  "lorap_lr_ratio": null,
  "use_rslora": false,
  "use_dora": false,
  "lora_ga_batch_size": 2,
  "lora_ga_iters": 2,
  "lora_ga_max_length": 1024,
  "lora_ga_direction": "ArB2r",
  "lora_ga_scale": "stable",
  "lora_ga_stable_gamma": 16,
  "init_weights": true,
  "fourier_n_frequency": 2000,
  "fourier_scaling": 300.0,
  "boft_block_size": 4,
  "boft_block_num": 0,
  "boft_n_butterfly_factor": 1,
  "boft_dropout": 0.0,
  "vera_rank": 256,
  "vera_projection_prng_key": 0,
  "vera_dropout": 0.0,
  "vera_d_initial": 0.1,
  "adapter_act": "gelu",
  "adapter_length": 128,
  "use_galore": false,
  "galore_target_modules": null,
  "galore_rank": 128,
  "galore_update_proj_gap": 50,
  "galore_scale": 1.0,
  "galore_proj_type": "std",
  "galore_optim_per_parameter": false,
  "galore_with_embedding": false,
  "galore_quantization": false,
  "galore_proj_quant": false,
  "galore_proj_bits": 4,
  "galore_proj_group_size": 256,
  "galore_cos_threshold": 0.4,
  "galore_gamma_proj": 2,
  "galore_queue_size": 5,
  "adalora_target_r": 8,
  "adalora_init_r": 12,
  "adalora_tinit": 0,
  "adalora_tfinal": 0,
  "adalora_deltaT": 1,
  "adalora_beta1": 0.85,
  "adalora_beta2": 0.85,
  "adalora_orth_reg_weight": 0.5,
  "llamapro_num_new_blocks": 4,
  "llamapro_num_groups": null,
  "lisa_activated_layers": 0,
  "lisa_step_interval": 20,
  "reft_layer_key": null,
  "reft_layers": null,
  "reft_rank": 4,
  "reft_intervention_type": "LoreftIntervention",
  "reft_args": null,
  "swanlab_token": null,
  "swanlab_project": "ms-swift",
  "swanlab_workspace": null,
  "swanlab_exp_name": null,
  "swanlab_notification_method": null,
  "swanlab_webhook_url": null,
  "swanlab_secret": null,
  "swanlab_sender_email": null,
  "swanlab_receiver_email": null,
  "swanlab_smtp_server": null,
  "swanlab_smtp_port": null,
  "swanlab_email_language": "zh",
  "swanlab_mode": "cloud",
  "add_version": true,
  "create_checkpoint_symlink": false,
  "zero_hpz_partition_size": null,
  "deepspeed_autotp_size": null,
  "early_stop_interval": null,
  "rank": -1,
  "global_world_size": 1,
  "local_world_size": 1,
  "model_suffix": "gemma-3-270m-it",
  "model_info": "ModelInfo(model_type='gemma3_text', model_dir='/workspace/hf_artifacts/hub/models--google--gemma-3-270m-it/snapshots/ac82b4e820549b854eebf28ce6dedaf9fdfa17b3', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=False, config=None, task_type='causal_lm', num_labels=None)",
  "model_meta": "ModelMeta(model_type='gemma3_text', model_groups=[ModelGroup(models=[Model(ms_model_id='LLM-Research/gemma-3-1b-pt', hf_model_id='google/gemma-3-1b-pt', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='LLM-Research/gemma-3-1b-it', hf_model_id='google/gemma-3-1b-it', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='google/gemma-3-270m', hf_model_id='google/gemma-3-270m', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='google/gemma-3-270m-it', hf_model_id='google/gemma-3-270m-it', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='google/medgemma-27b-text-it', hf_model_id='google/medgemma-27b-text-it', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='gemma3_text', get_function=<function get_model_tokenizer_gemma3_text at 0x70064a6a37e0>, model_arch=ModelKeys(arch_name='llama', embedding='model.embed_tokens', module_list='model.layers', lm_head='lm_head', q_proj='model.layers.{}.self_attn.q_proj', k_proj='model.layers.{}.self_attn.k_proj', v_proj='model.layers.{}.self_attn.v_proj', o_proj='model.layers.{}.self_attn.o_proj', attention='model.layers.{}.self_attn', mlp='model.layers.{}.mlp', down_proj='model.layers.{}.mlp.down_proj', qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None), architectures=['Gemma3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49'], tags=[])",
  "model_dir": "/workspace/hf_artifacts/hub/models--google--gemma-3-270m-it/snapshots/ac82b4e820549b854eebf28ce6dedaf9fdfa17b3",
  "_val_dataset_exists": [],
  "hub": "<class 'swift.hub.hub.HFHub'>",
  "evaluation_strategy": "no",
  "training_args": "Seq2SeqTrainingArguments(output_dir='/workspace/output/v0-20260216-180455', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=8, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/workspace/output/v0-20260216-180455/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=100, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=1000, save_total_limit=3, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=None, dataloader_num_workers=16, dataloader_prefetch_factor=2, past_index=-1, run_name='/workspace/output/v0-20260216-180455', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=True, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=True, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_
}