[2026-04-23 04:55:06,854] [DEBUG] [axolotl.utils.config.resolve_dtype:74] [PID:2005626] bf16 support detected, enabling for this configuration. [2026-04-23 04:55:06,954] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:2005626] baseline 0.000GB () [2026-04-23 04:55:06,954] [INFO] [axolotl.cli.config.load_cfg:341] [PID:2005626] config: { "activation_offloading": true, "adam_beta1": 0.9, "adam_beta2": 0.95, "axolotl_config_path": "/e/scratch/jureap59/feuer1/code/axolotl_configs/qwen3_8b_sera_v4_1000.yaml", "base_model": "Qwen/Qwen3-8B", "base_model_config": "Qwen/Qwen3-8B", "batch_size": 32, "bf16": true, "capabilities": { "bf16": true, "compute_capability": "sm_90", "fp8": true, "n_gpu": 4, "n_node": 1, "tf32": true }, "chat_template": "chatml", "context_parallel_size": 1, "dataloader_num_workers": 4, "dataloader_pin_memory": true, "dataloader_prefetch_factor": 256, "dataset_num_proc": 288, "dataset_prepared_path": "/e/data1/datasets/playground/ot-baf/axolotl_dataset_cache/sera-v4-1000", "datasets": [ { "chat_template": "tokenizer_default", "data_files": [ "sera-4.6-lite-t2_v4_1000.jsonl" ], "ds_type": "json", "field_messages": "messages", "message_field_training": "train", "message_property_mappings": { "content": "content", "role": "role" }, "path": "laion/Sera-4.6-Lite-T2-v4-1000", "trust_remote_code": false, "type": "chat_template" } ], "ddp": true, "deepspeed": { "bf16": { "enabled": true }, "gradient_accumulation_steps": "auto", "gradient_clipping": "auto", "train_batch_size": "auto", "train_micro_batch_size_per_gpu": "auto", "wall_clock_breakdown": false, "zero_optimization": { "contiguous_gradients": true, "gather_16bit_weights_on_model_save": true, "max_live_parameters": 0, "max_reuse_distance": 0, "overlap_comm": true, "reduce_bucket_size": "auto", "stage": 3, "stage3_param_persistence_threshold": "auto", "stage3_prefetch_bucket_size": "auto", "sub_group_size": 0 } }, "device": "cuda:0", "device_map": { "": 0 }, "dion_rank_fraction": 1.0, "dion_rank_multiple_of": 1, "eaft_alpha": 1.0, "eaft_k": 20, "env_capabilities": { "torch_version": "2.9.1" }, "eval_batch_size": 1, "eval_causal_lm_metrics": [ "sacrebleu", "comet", "ter", "chrf" ], "eval_max_new_tokens": 128, "eval_table_size": 0, "evals_per_epoch": 0, "experimental_skip_move_to_device": true, "flash_attention": true, "fp16": false, "generate_samples": false, "generation_do_sample": true, "generation_max_new_tokens": 50, "generation_prompt_ratio": 0.5, "generation_temperature": 0.7, "gradient_accumulation_steps": 8, "gradient_checkpointing": true, "gradient_checkpointing_kwargs": { "use_reentrant": true }, "include_tkps": true, "layer_offloading": false, "learning_rate": 1e-05, "lisa_layers_attribute": "model.layers", "load_best_model_at_end": false, "load_in_4bit": false, "load_in_8bit": false, "local_rank": 0, "logging_steps": 1, "lora_dropout": 0.0, "loraplus_lr_embedding": 1e-06, "loss_watchdog_patience": 3, "loss_watchdog_threshold": 5.0, "lr_scheduler": "cosine", "max_grad_norm": 1.0, "mean_resizing_embeddings": false, "merge_method": "memory_efficient", "micro_batch_size": 1, "model_config_type": "qwen3", "num_epochs": 3.0, "num_generation_samples": 3, "optimizer": "adamw_torch", "otel_metrics_host": "localhost", "otel_metrics_port": 8000, "output_dir": "/e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-1000-axolotl__Qwen3-8B", "pretrain_multipack_attn": true, "profiler_steps_start": 0, "qlora_sharded_model_loading": false, "quantize_moe_experts": false, "ray_num_workers": 1, "resources_per_worker": { "GPU": 1 }, "sample_packing_bin_size": 200, "sample_packing_group_size": 100000, "save_only_model": false, "save_safetensors": true, "save_strategy": "epoch", "sequence_len": 32768, "shuffle_before_merging_datasets": false, "shuffle_merged_datasets": true, "skip_prepare_dataset": false, "streaming_multipack_buffer_size": 10000, "strict": false, "tensor_parallel_size": 1, "tf32": false, "tiled_mlp_use_original_mlp": true, "tokenizer_config": "Qwen/Qwen3-8B", "tokenizer_save_jinja_files": true, "torch_dtype": "torch.bfloat16", "train_on_inputs": false, "trl": { "async_prefetch": false, "log_completions": false, "mask_truncated_completions": false, "ref_model_mixup_alpha": 0.9, "ref_model_sync_steps": 64, "replay_buffer_size": 0, "replay_recompute_logps": true, "reroll_max_groups": 1, "reroll_start_fraction": 1.0, "reward_num_workers": 1, "scale_rewards": true, "skip_zero_advantage_batches": true, "sync_ref_model": false, "use_data_producer": false, "use_vllm": false, "vllm_lora_sync": false, "vllm_server_host": "0.0.0.0", "vllm_server_port": 8000 }, "use_otel_metrics": false, "use_ray": false, "val_set_size": 0.0, "vllm": { "device": "auto", "dtype": "auto", "gpu_memory_utilization": 0.9, "host": "0.0.0.0", "port": 8000 }, "wandb_name": "sera-v4-1000-axolotl__Qwen3-8B", "warmup_ratio": 0.1875, "weight_decay": 0.01, "world_size": 4 } [2026-04-23 04:55:06,969] [INFO] [axolotl.cli.checks.check_user_token:37] [PID:2005626] Skipping HuggingFace token verification because HF_HUB_OFFLINE is set to True. Only local files will be used. [2026-04-23 04:55:07,497] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:307] [PID:2005626] EOS: 151645 / <|im_end|> [2026-04-23 04:55:07,497] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:308] [PID:2005626] BOS: None / None [2026-04-23 04:55:07,497] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:309] [PID:2005626] PAD: 151643 / <|endoftext|> [2026-04-23 04:55:07,497] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:310] [PID:2005626] UNK: None / None [2026-04-23 04:55:07,655] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:475] [PID:2005626] Loading prepared dataset from disk at /e/data1/datasets/playground/ot-baf/axolotl_dataset_cache/sera-v4-1000/76673564c8e541b3c5479d2bc430da04... [2026-04-23 04:55:07,784] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:420] [PID:2005626] total_num_tokens: 13_352_339 [2026-04-23 04:55:07,940] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:438] [PID:2005626] `total_supervised_tokens: 4_727_034` [2026-04-23 04:55:07,940] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:521] [PID:2005626] total_num_steps: 54 [2026-04-23 04:55:07,940] [INFO] [axolotl.utils.data.sft._prepare_standard_dataset:121] [PID:2005626] Maximum number of steps set at 54 [2026-04-23 04:55:07,977] [DEBUG] [axolotl.train.setup_model_and_tokenizer:70] [PID:2005626] loading tokenizer... Qwen/Qwen3-8B [2026-04-23 04:55:08,231] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:307] [PID:2005626] EOS: 151645 / <|im_end|> [2026-04-23 04:55:08,232] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:308] [PID:2005626] BOS: None / None [2026-04-23 04:55:08,232] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:309] [PID:2005626] PAD: 151643 / <|endoftext|> [2026-04-23 04:55:08,232] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:310] [PID:2005626] UNK: None / None [2026-04-23 04:55:08,232] [DEBUG] [axolotl.train.setup_model_and_tokenizer:81] [PID:2005626] Loading model [2026-04-23 04:55:08,302] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:94] [PID:2005626] Patched Trainer.evaluation_loop with nanmean loss calculation [2026-04-23 04:55:08,303] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:148] [PID:2005626] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation [2026-04-23 04:55:09,008] [INFO] [axolotl.monkeypatch.attention.flash_attn_4.patch_flash_attn_4:52] [PID:2005626] Flash Attention 4 is available for your GPU and offers faster training speeds. To enable: pip install flash-attn-4 [2026-04-23 04:55:09,009] [INFO] [axolotl.monkeypatch.deepspeed_utils.patch_checkpoint_wrapper_setattr:52] [PID:2005626] CheckpointWrapper patched to forward DeepSpeed attributes [2026-04-23 04:55:47,184] [INFO] [axolotl.loaders.model._configure_embedding_dtypes:361] [PID:2005626] Converting modules to torch.bfloat16 [2026-04-23 04:55:47,187] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:2005626] Memory usage after model load 4.973GB (+4.973GB allocated, +5.080GB reserved) [2026-04-23 04:55:53,788] [INFO] [axolotl.train.save_initial_configs:421] [PID:2005626] Pre-saving tokenizer to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-1000-axolotl__Qwen3-8B... [2026-04-23 04:55:53,869] [INFO] [axolotl.train.save_initial_configs:426] [PID:2005626] Pre-saving model config to /e/data1/datasets/playground/ot-baf/checkpoints/sera-v4-1000-axolotl__Qwen3-8B... [2026-04-23 04:55:53,872] [INFO] [axolotl.train.execute_training:222] [PID:2005626] Starting trainer... [2026-04-23 04:55:54,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,484] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,485] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,486] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,487] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,488] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,489] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_external_parameters to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,492] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,493] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,495] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,496] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,497] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,498] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,499] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,501] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,502] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,503] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,504] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,505] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,506] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,508] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,509] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,510] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,511] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,512] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,514] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,515] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,516] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,517] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,518] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,519] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,520] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,522] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,523] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,524] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,525] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,526] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,527] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,528] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,529] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,531] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,532] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer [2026-04-23 04:55:54,533] [DEBUG] [axolotl.monkeypatch.deepspeed_utils.new_setattr:43] [PID:2005626] Forwarded ds_id to wrapped module Qwen3DecoderLayer 0%| | 0/54 [00:00