| { | |
| "model_type": "molmo-7b-d", | |
| "model_id_or_path": "allenai/Molmo-7B-D-0924", | |
| "model_revision": "main", | |
| "full_determinism": false, | |
| "sft_type": "full", | |
| "freeze_parameters": [], | |
| "freeze_vit": false, | |
| "freeze_parameters_ratio": 0.0, | |
| "additional_trainable_parameters": [], | |
| "tuner_backend": "peft", | |
| "template_type": "molmo", | |
| "output_dir": "/workspace/output/molmo-7b-d/v0-20250103-184047", | |
| "add_output_dir_suffix": true, | |
| "ddp_backend": "nccl", | |
| "ddp_find_unused_parameters": null, | |
| "ddp_broadcast_buffers": null, | |
| "ddp_timeout": 1800, | |
| "seed": 42, | |
| "resume_from_checkpoint": null, | |
| "resume_only_model": false, | |
| "ignore_data_skip": false, | |
| "dtype": "bf16", | |
| "packing": false, | |
| "train_backend": "transformers", | |
| "tp": 1, | |
| "pp": 1, | |
| "min_lr": null, | |
| "sequence_parallel": false, | |
| "model_kwargs": {}, | |
| "loss_name": null, | |
| "dataset": [ | |
| "/workspace/train.jsonl" | |
| ], | |
| "val_dataset": [ | |
| "/workspace/val.jsonl" | |
| ], | |
| "dataset_seed": 42, | |
| "dataset_test_ratio": 0.0, | |
| "use_loss_scale": false, | |
| "loss_scale_config_path": "/workspace/miniconda/lib/python3.12/site-packages/swift/llm/agent/default_loss_scale_config.json", | |
| "system": null, | |
| "tools_prompt": "react_en", | |
| "max_length": 4096, | |
| "truncation_strategy": "delete", | |
| "check_dataset_strategy": "none", | |
| "streaming": false, | |
| "streaming_val_size": 0, | |
| "streaming_buffer_size": 16384, | |
| "model_name": [ | |
| null, | |
| null | |
| ], | |
| "model_author": [ | |
| null, | |
| null | |
| ], | |
| "quant_method": null, | |
| "quantization_bit": 0, | |
| "hqq_axis": 0, | |
| "hqq_dynamic_config_path": null, | |
| "bnb_4bit_comp_dtype": "bf16", | |
| "bnb_4bit_quant_type": "nf4", | |
| "bnb_4bit_use_double_quant": true, | |
| "bnb_4bit_quant_storage": null, | |
| "rescale_image": -1, | |
| "target_modules": "^(model.transformer)(?!.*(lm_head|output|emb|wte|shared)).*", | |
| "target_regex": null, | |
| "modules_to_save": [], | |
| "lora_rank": 8, | |
| "lora_alpha": 32, | |
| "lora_dropout": 0.05, | |
| "lora_bias_trainable": "none", | |
| "lora_dtype": "AUTO", | |
| "lora_lr_ratio": null, | |
| "use_rslora": false, | |
| "use_dora": false, | |
| "init_lora_weights": "true", | |
| "fourier_n_frequency": 2000, | |
| "fourier_scaling": 300.0, | |
| "rope_scaling": null, | |
| "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, | |
| "ia3_feedforward_modules": [], | |
| "llamapro_num_new_blocks": 4, | |
| "llamapro_num_groups": null, | |
| "neftune_noise_alpha": null, | |
| "neftune_backend": "transformers", | |
| "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, | |
| "use_liger": false, | |
| "gradient_checkpointing": false, | |
| "vit_use_gc": true, | |
| "deepspeed": { | |
| "fp16": { | |
| "enabled": "auto", | |
| "loss_scale": 0, | |
| "loss_scale_window": 1000, | |
| "initial_scale_power": 16, | |
| "hysteresis": 2, | |
| "min_loss_scale": 1 | |
| }, | |
| "bf16": { | |
| "enabled": "auto" | |
| }, | |
| "optimizer": { | |
| "type": "AdamW", | |
| "params": { | |
| "lr": "auto", | |
| "betas": "auto", | |
| "eps": "auto", | |
| "weight_decay": "auto" | |
| } | |
| }, | |
| "scheduler": { | |
| "type": "WarmupCosineLR", | |
| "params": { | |
| "total_num_steps": "auto", | |
| "warmup_num_steps": "auto" | |
| } | |
| }, | |
| "zero_optimization": { | |
| "stage": 3, | |
| "offload_optimizer": { | |
| "device": "none", | |
| "pin_memory": true | |
| }, | |
| "offload_param": { | |
| "device": "none", | |
| "pin_memory": true | |
| }, | |
| "overlap_comm": true, | |
| "contiguous_gradients": true, | |
| "sub_group_size": 1000000000.0, | |
| "reduce_bucket_size": "auto", | |
| "stage3_prefetch_bucket_size": "auto", | |
| "stage3_param_persistence_threshold": "auto", | |
| "stage3_max_live_parameters": 1000000000.0, | |
| "stage3_max_reuse_distance": 1000000000.0, | |
| "stage3_gather_16bit_weights_on_model_save": true | |
| }, | |
| "gradient_accumulation_steps": "auto", | |
| "gradient_clipping": "auto", | |
| "steps_per_print": 2000, | |
| "train_batch_size": "auto", | |
| "train_micro_batch_size_per_gpu": "auto", | |
| "wall_clock_breakdown": false | |
| }, | |
| "batch_size": 1, | |
| "eval_batch_size": 1, | |
| "auto_find_batch_size": false, | |
| "num_train_epochs": 6, | |
| "max_steps": -1, | |
| "optim": "adamw_torch", | |
| "adam_beta1": 0.9, | |
| "adam_beta2": 0.95, | |
| "adam_epsilon": 1e-08, | |
| "learning_rate": 1e-05, | |
| "weight_decay": 0.1, | |
| "gradient_accumulation_steps": 2, | |
| "max_grad_norm": 1, | |
| "predict_with_generate": false, | |
| "lr_scheduler_type": "cosine", | |
| "lr_scheduler_kwargs": {}, | |
| "warmup_ratio": 0.05, | |
| "warmup_steps": 0, | |
| "eval_steps": 200, | |
| "save_steps": 200, | |
| "save_only_model": false, | |
| "save_total_limit": 5, | |
| "logging_steps": 5, | |
| "acc_steps": 1, | |
| "dataloader_num_workers": 1, | |
| "dataloader_pin_memory": true, | |
| "dataloader_drop_last": false, | |
| "push_to_hub": false, | |
| "hub_model_id": null, | |
| "hub_token": null, | |
| "hub_private_repo": false, | |
| "hub_strategy": "every_save", | |
| "test_oom_error": false, | |
| "disable_tqdm": false, | |
| "lazy_tokenize": true, | |
| "preprocess_num_proc": 1, | |
| "use_flash_attn": null, | |
| "ignore_args_error": false, | |
| "check_model_is_latest": true, | |
| "logging_dir": "/workspace/output/molmo-7b-d/v0-20250103-184047/runs", | |
| "report_to": [ | |
| "wandb" | |
| ], | |
| "acc_strategy": "token", | |
| "save_on_each_node": false, | |
| "evaluation_strategy": "epoch", | |
| "save_strategy": "epoch", | |
| "save_safetensors": true, | |
| "gpu_memory_fraction": null, | |
| "include_num_input_tokens_seen": false, | |
| "local_repo_path": null, | |
| "custom_register_path": null, | |
| "custom_dataset_info": null, | |
| "device_map_config": null, | |
| "device_max_memory": [], | |
| "max_new_tokens": 2048, | |
| "do_sample": null, | |
| "temperature": null, | |
| "top_k": null, | |
| "top_p": null, | |
| "repetition_penalty": null, | |
| "num_beams": 1, | |
| "fsdp": "", | |
| "fsdp_config": null, | |
| "sequence_parallel_size": 1, | |
| "model_layer_cls_name": null, | |
| "metric_warmup_step": 0, | |
| "fsdp_num": 1, | |
| "per_device_train_batch_size": null, | |
| "per_device_eval_batch_size": null, | |
| "eval_strategy": "epoch", | |
| "self_cognition_sample": 0, | |
| "train_dataset_mix_ratio": 0.0, | |
| "train_dataset_mix_ds": [ | |
| "ms-bench" | |
| ], | |
| "train_dataset_sample": -1, | |
| "val_dataset_sample": null, | |
| "safe_serialization": null, | |
| "only_save_model": null, | |
| "neftune_alpha": null, | |
| "deepspeed_config_path": null, | |
| "model_cache_dir": null, | |
| "lora_dropout_p": null, | |
| "lora_target_modules": [], | |
| "lora_target_regex": null, | |
| "lora_modules_to_save": [], | |
| "boft_target_modules": [], | |
| "boft_modules_to_save": [], | |
| "vera_target_modules": [], | |
| "vera_modules_to_save": [], | |
| "ia3_target_modules": [], | |
| "ia3_modules_to_save": [], | |
| "custom_train_dataset_path": [], | |
| "custom_val_dataset_path": [], | |
| "device_map_config_path": null, | |
| "push_hub_strategy": null, | |
| "use_self_cognition": false, | |
| "is_multimodal": true, | |
| "is_vision": true, | |
| "lora_use_embedding": false, | |
| "lora_use_all": false, | |
| "lora_m2s_use_embedding": false, | |
| "lora_m2s_use_ln": false, | |
| "torch_dtype": "torch.bfloat16", | |
| "fp16": false, | |
| "bf16": true, | |
| "rank": 0, | |
| "local_rank": 0, | |
| "world_size": 8, | |
| "local_world_size": 8, | |
| "bnb_4bit_compute_dtype": "torch.bfloat16", | |
| "load_in_4bit": false, | |
| "load_in_8bit": false, | |
| "train_sampler_random": true, | |
| "train_type": "sft", | |
| "training_args": "Seq2SeqTrainingArguments(output_dir='/workspace/output/molmo-7b-d/v0-20250103-184047', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.EPOCH: 'epoch'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=6, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs={}, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/workspace/output/molmo-7b-d/v0-20250103-184047/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.EPOCH: 'epoch'>, save_steps=200, save_total_limit=5, 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, use_ipex=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='nccl', tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=200, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/workspace/output/molmo-7b-d/v0-20250103-184047', 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), deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'optimizer': {'type': 'AdamW', 'params': {'lr': 'auto', 'betas': 'auto', 'eps': 'auto', 'weight_decay': 'auto'}}, 'scheduler': {'type': 'WarmupCosineLR', 'params': {'total_num_steps': 'auto', 'warmup_num_steps': 'auto'}}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': True, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['wandb'], ddp_find_unused_parameters=True, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=True, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=False, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, 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=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"eos_token_id\": 151643,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 151643\n}\n, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" | |
| } |