| 2025-03-05 23:32:46,342 INFO MainThread:163 [wandb_setup.py:_flush():67] Current SDK version is 0.19.8 | |
| 2025-03-05 23:32:46,342 INFO MainThread:163 [wandb_setup.py:_flush():67] Configure stats pid to 163 | |
| 2025-03-05 23:32:46,342 INFO MainThread:163 [wandb_setup.py:_flush():67] Loading settings from /root/.config/wandb/settings | |
| 2025-03-05 23:32:46,342 INFO MainThread:163 [wandb_setup.py:_flush():67] Loading settings from /kaggle/working/LLaMA-Factory/wandb/settings | |
| 2025-03-05 23:32:46,342 INFO MainThread:163 [wandb_setup.py:_flush():67] Loading settings from environment variables | |
| 2025-03-05 23:32:46,342 INFO MainThread:163 [wandb_init.py:setup_run_log_directory():647] Logging user logs to /kaggle/working/LLaMA-Factory/wandb/run-20250305_233246-9ct1o6yk/logs/debug.log | |
| 2025-03-05 23:32:46,342 INFO MainThread:163 [wandb_init.py:setup_run_log_directory():648] Logging internal logs to /kaggle/working/LLaMA-Factory/wandb/run-20250305_233246-9ct1o6yk/logs/debug-internal.log | |
| 2025-03-05 23:32:46,343 INFO MainThread:163 [wandb_init.py:init():761] calling init triggers | |
| 2025-03-05 23:32:46,343 INFO MainThread:163 [wandb_init.py:init():766] wandb.init called with sweep_config: {} | |
| config: {'_wandb': {}} | |
| 2025-03-05 23:32:46,343 INFO MainThread:163 [wandb_init.py:init():784] starting backend | |
| 2025-03-05 23:32:46,343 INFO MainThread:163 [wandb_init.py:init():788] sending inform_init request | |
| 2025-03-05 23:32:46,350 INFO MainThread:163 [backend.py:_multiprocessing_setup():101] multiprocessing start_methods=fork,spawn,forkserver, using: spawn | |
| 2025-03-05 23:32:46,350 INFO MainThread:163 [wandb_init.py:init():798] backend started and connected | |
| 2025-03-05 23:32:46,355 INFO MainThread:163 [wandb_init.py:init():891] updated telemetry | |
| 2025-03-05 23:32:46,361 INFO MainThread:163 [wandb_init.py:init():915] communicating run to backend with 90.0 second timeout | |
| 2025-03-05 23:32:46,782 INFO MainThread:163 [wandb_init.py:init():990] starting run threads in backend | |
| 2025-03-05 23:32:47,457 INFO MainThread:163 [wandb_run.py:_console_start():2375] atexit reg | |
| 2025-03-05 23:32:47,457 INFO MainThread:163 [wandb_run.py:_redirect():2227] redirect: wrap_raw | |
| 2025-03-05 23:32:47,457 INFO MainThread:163 [wandb_run.py:_redirect():2292] Wrapping output streams. | |
| 2025-03-05 23:32:47,457 INFO MainThread:163 [wandb_run.py:_redirect():2315] Redirects installed. | |
| 2025-03-05 23:32:47,460 INFO MainThread:163 [wandb_init.py:init():1032] run started, returning control to user process | |
| 2025-03-05 23:32:47,463 INFO MainThread:163 [wandb_run.py:_config_callback():1261] config_cb None None {'peft_config': {'default': {'peft_type': <PeftType.LORA: 'LORA'>, 'auto_mapping': None, 'base_model_name_or_path': 'Qwen/Qwen2.5-1.5B-Instruct', 'revision': None, 'task_type': <TaskType.CAUSAL_LM: 'CAUSAL_LM'>, 'inference_mode': False, 'r': 64, 'target_modules': {'q_proj', 'v_proj', 'gate_proj', 'k_proj', 'down_proj', 'o_proj', 'up_proj'}, 'lora_alpha': 128, 'lora_dropout': 0.0, 'fan_in_fan_out': False, 'bias': 'none', 'use_rslora': False, 'modules_to_save': None, 'init_lora_weights': True, 'layers_to_transform': None, 'layers_pattern': None, 'rank_pattern': {}, 'alpha_pattern': {}, 'megatron_config': None, 'megatron_core': 'megatron.core', 'loftq_config': {}, 'use_dora': False, 'layer_replication': None, 'runtime_config': {'ephemeral_gpu_offload': False}}}, 'vocab_size': 151936, 'max_position_embeddings': 32768, 'hidden_size': 1536, 'intermediate_size': 8960, 'num_hidden_layers': 28, 'num_attention_heads': 12, 'use_sliding_window': False, 'sliding_window': None, 'max_window_layers': 21, 'num_key_value_heads': 2, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-06, 'use_cache': False, 'rope_theta': 1000000.0, 'rope_scaling': None, 'attention_dropout': 0.0, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'bfloat16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['Qwen2ForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 151643, 'pad_token_id': None, 'eos_token_id': 151645, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'Qwen/Qwen2.5-1.5B-Instruct', '_attn_implementation_autoset': True, 'transformers_version': '4.48.3', 'model_type': 'qwen2', 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': True, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', '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': 4, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 0.0001, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.1, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/Mar05_23-32-16_7cf3bf98fc84', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 10, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': None, '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': None, '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': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 100, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'newsx-finetune-llamafactory', 'disable_tqdm': False, 'remove_unused_columns': False, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, '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': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], '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': 'checkpoint', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': True, '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': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 180000000, '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': 2048, 'generation_num_beams': None, 'generation_config': None, 'ray_run_name': None, 'ray_storage_path': './saves', 'ray_num_workers': 1, 'resources_per_worker': {'GPU': 1}, 'placement_strategy': 'PACK'} | |
| 2025-03-05 23:32:47,471 INFO MainThread:163 [wandb_config.py:__setitem__():154] config set model/num_parameters = 1617573376 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x78ceca0a02b0>> | |
| 2025-03-05 23:32:47,471 INFO MainThread:163 [wandb_run.py:_config_callback():1261] config_cb model/num_parameters 1617573376 None | |
| 2025-03-05 23:32:47,473 INFO MainThread:163 [wandb_run.py:_config_callback():1261] config_cb None None {'model_args': {'vllm_maxlen': 4096, 'vllm_gpu_util': 0.9, 'vllm_enforce_eager': False, 'vllm_max_lora_rank': 32, 'vllm_config': None, 'export_dir': None, 'export_size': 5, 'export_device': 'cpu', 'export_quantization_bit': None, 'export_quantization_dataset': None, 'export_quantization_nsamples': 128, 'export_quantization_maxlen': 1024, 'export_legacy_format': False, 'export_hub_model_id': 'OsamaMo/Arabic_Text-To-SQL', 'image_max_pixels': 589824, 'image_min_pixels': 1024, 'video_max_pixels': 65536, 'video_min_pixels': 256, 'video_fps': 2.0, 'video_maxlen': 128, 'quantization_method': 'bitsandbytes', 'quantization_bit': None, 'quantization_type': 'nf4', 'double_quantization': True, 'quantization_device_map': None, 'model_name_or_path': 'Qwen/Qwen2.5-1.5B-Instruct', 'adapter_name_or_path': None, 'adapter_folder': None, 'cache_dir': None, 'use_fast_tokenizer': True, 'resize_vocab': False, 'split_special_tokens': False, 'new_special_tokens': None, 'model_revision': 'main', 'low_cpu_mem_usage': True, 'rope_scaling': None, 'flash_attn': 'auto', 'shift_attn': False, 'mixture_of_depths': None, 'use_unsloth': False, 'use_unsloth_gc': False, 'enable_liger_kernel': False, 'moe_aux_loss_coef': None, 'disable_gradient_checkpointing': False, 'use_reentrant_gc': True, 'upcast_layernorm': False, 'upcast_lmhead_output': False, 'train_from_scratch': False, 'infer_backend': 'huggingface', 'offload_folder': 'offload', 'use_cache': True, 'infer_dtype': 'auto', 'hf_hub_token': '<HF_HUB_TOKEN>', 'ms_hub_token': '<MS_HUB_TOKEN>', 'om_hub_token': '<OM_HUB_TOKEN>', 'print_param_status': False, 'trust_remote_code': True, 'compute_dtype': 'torch.bfloat16', 'device_map': {'': 'cuda:0'}, 'model_max_length': 2048, 'block_diag_attn': False}, 'data_args': {'template': 'qwen', 'dataset': ['news_finetune_train'], 'eval_dataset': ['news_finetune_val'], 'dataset_dir': 'data', 'media_dir': 'data', 'cutoff_len': 2048, 'train_on_prompt': False, 'mask_history': False, 'streaming': False, 'buffer_size': 16384, 'mix_strategy': 'concat', 'interleave_probs': None, 'overwrite_cache': True, 'preprocessing_batch_size': 1000, 'preprocessing_num_workers': 16, 'max_samples': None, 'eval_num_beams': None, 'ignore_pad_token_for_loss': True, 'val_size': 0.0, 'packing': False, 'neat_packing': False, 'tool_format': None, 'tokenized_path': None}, 'finetuning_args': {'use_swanlab': False, 'swanlab_project': 'llamafactory', 'swanlab_workspace': None, 'swanlab_run_name': None, 'swanlab_mode': 'cloud', 'swanlab_api_key': '<SWANLAB_API_KEY>', 'use_badam': False, 'badam_mode': 'layer', 'badam_start_block': None, 'badam_switch_mode': 'ascending', 'badam_switch_interval': 50, 'badam_update_ratio': 0.05, 'badam_mask_mode': 'adjacent', 'badam_verbose': 0, 'use_apollo': False, 'apollo_target': ['all'], 'apollo_rank': 16, 'apollo_update_interval': 200, 'apollo_scale': 32.0, 'apollo_proj': 'random', 'apollo_proj_type': 'std', 'apollo_scale_type': 'channel', 'apollo_layerwise': False, 'apollo_scale_front': False, 'use_galore': False, 'galore_target': ['all'], 'galore_rank': 16, 'galore_update_interval': 200, 'galore_scale': 2.0, 'galore_proj_type': 'std', 'galore_layerwise': False, 'pref_beta': 0.1, 'pref_ftx': 0.0, 'pref_loss': 'sigmoid', 'dpo_label_smoothing': 0.0, 'kto_chosen_weight': 1.0, 'kto_rejected_weight': 1.0, 'simpo_gamma': 0.5, 'ppo_buffer_size': 1, 'ppo_epochs': 4, 'ppo_score_norm': False, 'ppo_target': 6.0, 'ppo_whiten_rewards': False, 'ref_model': None, 'ref_model_adapters': None, 'ref_model_quantization_bit': None, 'reward_model': None, 'reward_model_adapters': None, 'reward_model_quantization_bit': None, 'reward_model_type': 'lora', 'additional_target': None, 'lora_alpha': 128, 'lora_dropout': 0.0, 'lora_rank': 64, 'lora_target': ['all'], 'loraplus_lr_ratio': None, 'loraplus_lr_embedding': 1e-06, 'use_rslora': False, 'use_dora': False, 'pissa_init': False, 'pissa_iter': 16, 'pissa_convert': False, 'create_new_adapter': False, 'freeze_trainable_layers': 2, 'freeze_trainable_modules': ['all'], 'freeze_extra_modules': None, 'pure_bf16': False, 'stage': 'sft', 'finetuning_type': 'lora', 'use_llama_pro': False, 'use_adam_mini': False, 'freeze_vision_tower': True, 'freeze_multi_modal_projector': True, 'train_mm_proj_only': False, 'compute_accuracy': False, 'disable_shuffling': False, 'plot_loss': True, 'include_effective_tokens_per_second': False}, 'generating_args': {'do_sample': True, 'temperature': 0.95, 'top_p': 0.7, 'top_k': 50, 'num_beams': 1, 'max_new_tokens': 1024, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'default_system': None, 'skip_special_tokens': True}} | |