auto-sync wandb 2026-07-02 15:58

wandb/offline-run-20260629_191603-j2uy9df0/logs/debug-internal.log

@@ -7,3 +7,7 @@
 {"time":"2026-06-29T19:16:04.590846272+08:00","level":"INFO","msg":"sender: started"}
 {"time":"2026-06-29T19:16:04.590847669+08:00","level":"INFO","msg":"writer: started","stream_id":"j2uy9df0"}
 {"time":"2026-06-29T19:16:04.592207471+08:00","level":"WARN","msg":"runupserter: server does not expand metric globs but the x_server_side_expand_glob_metrics setting is set; ignoring"}
+{"time":"2026-06-30T16:35:06.58373947+08:00","level":"INFO","msg":"stream: closing"}
+{"time":"2026-06-30T16:35:06.631128665+08:00","level":"INFO","msg":"handler: closed"}
+{"time":"2026-06-30T16:35:06.675281225+08:00","level":"INFO","msg":"sender: closed"}
+{"time":"2026-06-30T16:35:06.675314818+08:00","level":"INFO","msg":"stream: closed"}

wandb/offline-run-20260629_191603-j2uy9df0/logs/debug.log

@@ -20,3 +20,5 @@ config: {'_wandb': {}}
 2026-06-29 19:16:10,735 INFO    MainThread:2003816 [wandb_run.py:_config_callback():1403] config_cb None None {'peft_config': {'default': {'task_type': None, 'peft_type': 'LORA', 'auto_mapping': None, 'peft_version': '0.18.1', 'base_model_name_or_path': None, 'revision': None, 'inference_mode': False, 'r': 128, 'target_modules': ['q_proj', 'k_proj', 'v_proj', 'o_proj', 'up_proj', 'down_proj', 'gate_proj'], 'exclude_modules': None, 'lora_alpha': 64, 'lora_dropout': 0.0, 'fan_in_fan_out': False, 'bias': 'none', 'use_rslora': False, 'modules_to_save': ['fork_head'], 'init_lora_weights': True, 'layers_to_transform': None, 'layers_pattern': None, 'rank_pattern': {}, 'alpha_pattern': {}, 'megatron_config': None, 'megatron_core': 'megatron.core', 'trainable_token_indices': None, 'loftq_config': {}, 'eva_config': None, 'corda_config': None, 'use_dora': False, 'alora_invocation_tokens': None, 'use_qalora': False, 'qalora_group_size': 16, 'layer_replication': None, 'runtime_config': {'ephemeral_gpu_offload': False}, 'lora_bias': False, 'target_parameters': None, 'arrow_config': None, 'ensure_weight_tying': False}}, 'vocab_size': 155136, 'max_position_embeddings': 8192, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.013975424859373685, 'rms_norm_eps': 1e-05, 'layer_norm_eps': None, 'rope_theta': 10000.0, 'rope_scaling': {'factor': 1.0, 'rope_type': 'default'}, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'resid_pdrop': 0.0, 'return_dict': True, 'output_hidden_states': False, 'torchscript': False, 'dtype': 'float32', '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, 'architectures': ['ILLaDAForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'task_specific_params': None, 'problem_type': None, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'temperature': 1.0, 'top_k': 0, '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, 'num_beam_groups': 1, 'diversity_penalty': 0.0, '_name_or_path': '/llm-align/liuchonghan/models/iLLaDA-8B-Instruct', 'transformers_version': '4.57.3', 'auto_map': {'AutoConfig': 'configuration_illada.ILLaDAConfig', 'AutoModel': 'modeling_illada.ILLaDAForCausalLM', 'AutoModelForCausalLM': 'modeling_illada.ILLaDAForCausalLM'}, 'model_type': 'illada', 'tf_legacy_loss': False, 'use_bfloat16': False, 'output_attentions': False, 'output_dir': '/llm-align/liuchonghan/lizonghui/heat/outputs/appo_math_illada/2026-06-29_19-13-52', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 16, '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': 3e-06, 'weight_decay': 0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1, 'max_steps': -1, 'lr_scheduler_type': 'constant', 'lr_scheduler_kwargs': None, 'warmup_ratio': 0.0, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/llm-align/liuchonghan/lizonghui/heat/outputs/appo_math_illada/2026-06-29_19-13-52/logs', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 0.1, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': True, '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, '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': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': None, '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}, 'parallelism_config': 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'], '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': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'hub_revision': None, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': "{'use_reentrant': False}", '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': '<PUSH_TO_HUB_TOKEN>', '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, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': 'no', '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': True, 'model_init_kwargs': None, 'disable_dropout': False, 'cast_lm_head_to_fp32': False, 'num_generations': 8, 'num_generations_eval': None, 'max_completion_length': 256, 'ds3_gather_for_generation': True, 'shuffle_dataset': True, 'pad_to_multiple_of': None, 'generation_batch_size': 32, 'steps_per_generation': 2, 'min_p': None, 'generation_kwargs': None, 'chat_template_kwargs': None, 'use_transformers_paged': False, 'cache_implementation': None, 'use_vllm': False, 'vllm_mode': 'colocate', 'vllm_model_impl': 'vllm', 'vllm_enable_sleep_mode': False, 'vllm_structured_outputs_regex': None, 'vllm_server_base_url': None, 'vllm_server_host': '0.0.0.0', 'vllm_server_port': 8000, 'vllm_server_timeout': 240.0, 'vllm_group_port': 51216, 'vllm_gpu_memory_utilization': 0.3, 'vllm_max_model_length': None, 'vllm_tensor_parallel_size': 1, 'beta': 0.0, 'num_iterations': 4, 'epsilon': 0.2, 'delta': None, 'epsilon_high': 0.28, 'sapo_temperature_neg': 1.05, 'sapo_temperature_pos': 1.0, 'vespo_k_pos': 2.0, 'vespo_lambda_pos': 3.0, 'vespo_k_neg': 3.0, 'vespo_lambda_neg': 2.0, 'importance_sampling_level': 'token', 'reward_weights': [1.0, 0.5], 'multi_objective_aggregation': 'sum_then_normalize', 'scale_rewards': 'none', 'loss_type': 'dapo', 'mask_truncated_completions': False, 'sync_ref_model': False, 'ref_model_mixup_alpha': 0.6, 'ref_model_sync_steps': 128, 'top_entropy_quantile': 1.0, 'max_tool_calling_iterations': None, 'vllm_importance_sampling_correction': True, 'vllm_importance_sampling_mode': 'sequence_mask', 'vllm_importance_sampling_cap': 3.0, 'off_policy_mask_threshold': None, 'use_bias_correction_kl': False, 'log_completions': True, 'num_completions_to_print': 0, 'log_unique_prompts': False, 'log_completions_hub_repo': None, 'decay_ratio': None, 'lora': True, 'lora_config': {'task_type': None, 'peft_type': 'LORA', 'auto_mapping': None, 'peft_version': '0.18.1', 'base_model_name_or_path': None, 'revision': None, 'inference_mode': False, 'r': 128, 'target_modules': ['q_proj', 'k_proj', 'v_proj', 'o_proj', 'up_proj', 'down_proj', 'gate_proj'], 'exclude_modules': None, 'lora_alpha': 64, 'lora_dropout': 0.0, 'fan_in_fan_out': False, 'bias': 'none', 'use_rslora': False, 'modules_to_save': ['fork_head'], 'init_lora_weights': True, 'layers_to_transform': None, 'layers_pattern': None, 'rank_pattern': {}, 'alpha_pattern': {}, 'megatron_config': None, 'megatron_core': 'megatron.core', 'trainable_token_indices': None, 'loftq_config': {}, 'eva_config': None, 'corda_config': None, 'use_dora': False, 'alora_invocation_tokens': None, 'use_qalora': False, 'qalora_group_size': 16, 'layer_replication': None, 'runtime_config': {'ephemeral_gpu_offload': False}, 'lora_bias': False, 'target_parameters': None, 'arrow_config': None, 'ensure_weight_tying': False}, 'simpson_threshold': 3, 'rl_args': {'fork_head_lr': 1e-05, 'fork_selection_strategy': 'fork_head', 'fork_selection_kwargs': "{'fork_head': None}", 'fork_head_reward_mode': 'coverage'}, 'gen_strategy': 'tree_dec', 'kl_estimator': 'k2'}
 2026-06-29 19:16:10,746 INFO    MainThread:2003816 [wandb_config.py:__setitem__():155] [no run ID] config set model/num_parameters = 7950569472 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7ff7a6416c50>>
 2026-06-29 19:16:10,746 INFO    MainThread:2003816 [wandb_run.py:_config_callback():1403] config_cb model/num_parameters 7950569472 None
+2026-06-30 16:35:06,583 INFO    wandb-AsyncioManager-main:2003816 [service_client.py:_forward_responses():134] Reached EOF.
+2026-06-30 16:35:06,585 INFO    wandb-AsyncioManager-main:2003816 [mailbox.py:close():155] Closing mailbox, abandoning 0 handles.

wandb/offline-run-20260629_191603-j2uy9df0/run-j2uy9df0.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5b4dc70949f92cfb8080659faba33d3d9b3b1b392a59ac97a7305d586cd5630
-size 37126144
+oid sha256:b8a76e5f10e1e03917265f0600a986cc17d087cc6f0c5cd1a25289f5e3119333
+size 39242679