[2025-10-05 21:06:42,900] [DEBUG] [axolotl.utils.config.resolve_dtype:66] [PID:11253] bf16 support detected, enabling for this configuration. [2025-10-05 21:06:43,084] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:11253] baseline 0.000GB () [2025-10-05 21:06:43,085] [INFO] [axolotl.cli.config.load_cfg:248] [PID:11253] config: { "activation_offloading": false, "adapter": "lora", "axolotl_config_path": "muse-marvin.yaml", "base_model": "LatitudeGames/Muse-12B", "base_model_config": "LatitudeGames/Muse-12B", "batch_size": 6, "bf16": true, "capabilities": { "bf16": true, "compute_capability": "sm_120", "fp8": false, "n_gpu": 1, "n_node": 1 }, "context_parallel_size": 1, "cut_cross_entropy": true, "dataloader_num_workers": 1, "dataloader_pin_memory": true, "dataloader_prefetch_factor": 256, "dataset_prepared_path": "last_run_prepared", "dataset_processes": 16, "datasets": [ { "chat_template": "tokenizer_default", "field_messages": "conversations", "message_property_mappings": { "content": "value", "role": "from" }, "path": "grimulkan/LimaRP-augmented", "trust_remote_code": false, "type": "chat_template" }, { "data_files": "marvin.json", "message_property_mappings": { "content": "content", "role": "role" }, "path": "ToastyPigeon/steve-and-marvin", "trust_remote_code": false, "type": "completion" }, { "message_property_mappings": { "content": "content", "role": "role" }, "path": "ToastyPigeon/kimi-stories-completion", "trust_remote_code": false, "type": "completion" } ], "ddp": false, "device": "cuda:0", "dion_rank_fraction": 1.0, "dion_rank_multiple_of": 1, "env_capabilities": { "torch_version": "2.8.0" }, "eval_batch_size": 6, "eval_causal_lm_metrics": [ "sacrebleu", "comet", "ter", "chrf" ], "eval_max_new_tokens": 128, "eval_sample_packing": true, "eval_steps": 0.1, "eval_table_size": 0, "evals_per_epoch": 10, "experimental_skip_move_to_device": true, "flash_attention": true, "fp16": false, "gc_steps": 10, "gradient_accumulation_steps": 1, "gradient_checkpointing": true, "gradient_checkpointing_kwargs": { "use_reentrant": true }, "group_by_length": false, "hub_model_id": "ToastyPigeon/muse-marvin-lora", "hub_strategy": "every_save", "include_tkps": true, "is_mistral_derived_model": true, "learning_rate": 1e-05, "liger_glu_activation": true, "liger_layer_norm": true, "liger_rms_norm": true, "liger_rope": true, "lisa_layers_attribute": "model.layers", "load_best_model_at_end": false, "load_in_4bit": false, "load_in_8bit": true, "local_rank": 0, "logging_steps": 1, "lora_alpha": 32, "lora_dropout": 0.1, "lora_r": 32, "lora_target_linear": true, "loraplus_lr_embedding": 1e-06, "lr_scheduler": "cosine", "max_grad_norm": 1.0, "mean_resizing_embeddings": false, "micro_batch_size": 6, "model_config_type": "mistral", "num_epochs": 1.0, "optimizer": "paged_adamw_8bit", "output_dir": "ckpts", "pad_to_sequence_len": true, "peft_use_rslora": false, "plugins": [ "axolotl.integrations.liger.LigerPlugin", "axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin" ], "pretrain_multipack_attn": true, "profiler_steps_start": 0, "qlora_sharded_model_loading": false, "ray_num_workers": 1, "resources_per_worker": { "GPU": 1 }, "sample_packing": true, "sample_packing_bin_size": 200, "sample_packing_group_size": 100000, "save_only_model": false, "save_safetensors": true, "save_steps": 0.1, "save_total_limit": 1, "saves_per_epoch": 10, "seed": 69, "sequence_len": 16384, "shuffle_before_merging_datasets": false, "shuffle_merged_datasets": true, "skip_prepare_dataset": false, "streaming_multipack_buffer_size": 10000, "strict": false, "tensor_parallel_size": 1, "tiled_mlp_use_original_mlp": true, "tokenizer_config": "LatitudeGames/Muse-12B", "tokenizer_save_jinja_files": true, "torch_dtype": "torch.bfloat16", "train_on_inputs": false, "trl": { "log_completions": false, "mask_truncated_completions": false, "ref_model_mixup_alpha": 0.9, "ref_model_sync_steps": 64, "scale_rewards": true, "sync_ref_model": false, "use_vllm": false, "vllm_server_host": "0.0.0.0", "vllm_server_port": 8000 }, "use_ray": false, "use_wandb": true, "val_set_size": 0.025, "vllm": { "device": "auto", "dtype": "auto", "gpu_memory_utilization": 0.9, "host": "0.0.0.0", "port": 8000 }, "wandb_project": "MuseMarvin", "warmup_ratio": 0.025, "weight_decay": 0.01, "world_size": 1 } [2025-10-05 21:06:43,842] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:278] [PID:11253] EOS: 131072 / <|im_end|> [2025-10-05 21:06:43,842] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:279] [PID:11253] BOS: 1 / [2025-10-05 21:06:43,842] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:280] [PID:11253] PAD: 10 / [2025-10-05 21:06:43,842] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:281] [PID:11253] UNK: 0 / [2025-10-05 21:06:43,843] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:470] [PID:11253] Loading prepared dataset from disk at last_run_prepared/31b44b9f810943b30f3af91fc7580ba1... [2025-10-05 21:06:43,855] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:404] [PID:11253] total_num_tokens: 758_181 [2025-10-05 21:06:43,856] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:422] [PID:11253] `total_supervised_tokens: 716_387` [2025-10-05 21:06:45,008] [DEBUG] [axolotl.utils.samplers.multipack.__len__:458] [PID:11253] generate_batches time: 0.5532689094543457 [2025-10-05 21:06:45,597] [DEBUG] [axolotl.utils.samplers.multipack.__len__:458] [PID:11253] generate_batches time: 0.5894393920898438 [2025-10-05 21:06:46,174] [DEBUG] [axolotl.utils.samplers.multipack.__len__:458] [PID:11253] generate_batches time: 0.5761475563049316 [2025-10-05 21:06:46,747] [DEBUG] [axolotl.utils.samplers.multipack.__len__:458] [PID:11253] generate_batches time: 0.5732052326202393 [2025-10-05 21:06:46,767] [INFO] [axolotl.utils.samplers.multipack.calc_min_len:434] [PID:11253] gather_len_batches: [8] [2025-10-05 21:06:46,768] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:481] [PID:11253] data_loader_len: 8 [2025-10-05 21:06:46,768] [INFO] [axolotl.utils.trainer.calc_sample_packing_eff_est:497] [PID:11253] sample_packing_eff_est across ranks: [0.9640769958496094] [2025-10-05 21:06:46,768] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:509] [PID:11253] sample_packing_eff_est: None [2025-10-05 21:06:46,768] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:520] [PID:11253] total_num_steps: 8 [2025-10-05 21:06:46,820] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:404] [PID:11253] total_num_tokens: 30_240_821 [2025-10-05 21:06:46,871] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:422] [PID:11253] `total_supervised_tokens: 28_482_459` [2025-10-05 21:06:48,072] [DEBUG] [axolotl.utils.samplers.multipack.__len__:458] [PID:11253] generate_batches time: 0.5889458656311035 [2025-10-05 21:06:48,661] [DEBUG] [axolotl.utils.samplers.multipack.__len__:458] [PID:11253] generate_batches time: 0.5885024070739746 [2025-10-05 21:06:49,238] [DEBUG] [axolotl.utils.samplers.multipack.__len__:458] [PID:11253] generate_batches time: 0.5770845413208008 [2025-10-05 21:06:49,849] [DEBUG] [axolotl.utils.samplers.multipack.__len__:458] [PID:11253] generate_batches time: 0.6107258796691895 [2025-10-05 21:06:49,849] [INFO] [axolotl.utils.samplers.multipack.calc_min_len:434] [PID:11253] gather_len_batches: [309] [2025-10-05 21:06:49,850] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:481] [PID:11253] data_loader_len: 309 [2025-10-05 21:06:49,850] [INFO] [axolotl.utils.trainer.calc_sample_packing_eff_est:497] [PID:11253] sample_packing_eff_est across ranks: [0.9955519066144991] [2025-10-05 21:06:49,850] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:509] [PID:11253] sample_packing_eff_est: 1.0 [2025-10-05 21:06:49,850] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:520] [PID:11253] total_num_steps: 309 [2025-10-05 21:06:49,850] [INFO] [axolotl.utils.data.sft._prepare_standard_dataset:121] [PID:11253] Maximum number of steps set at 309 [2025-10-05 21:06:49,874] [DEBUG] [axolotl.train.setup_model_and_tokenizer:70] [PID:11253] Loading tokenizer... LatitudeGames/Muse-12B [2025-10-05 21:06:50,498] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:278] [PID:11253] EOS: 131072 / <|im_end|> [2025-10-05 21:06:50,498] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:279] [PID:11253] BOS: 1 / [2025-10-05 21:06:50,498] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:280] [PID:11253] PAD: 10 / [2025-10-05 21:06:50,498] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:281] [PID:11253] UNK: 0 / [2025-10-05 21:06:50,498] [DEBUG] [axolotl.train.setup_model_and_tokenizer:79] [PID:11253] Loading model [2025-10-05 21:06:50,604] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:87] [PID:11253] Patched Trainer.evaluation_loop with nanmean loss calculation [2025-10-05 21:06:50,605] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:138] [PID:11253] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation [2025-10-05 21:06:50,605] [INFO] [axolotl.loaders.patch_manager._apply_multipack_patches:301] [PID:11253] Applying multipack dataloader patch for sample packing... [2025-10-05 21:06:50,615] [INFO] [axolotl.integrations.liger.plugin.pre_model_load:71] [PID:11253] Applying LIGER to mistral with kwargs: {'rope': True, 'cross_entropy': None, 'fused_linear_cross_entropy': None, 'rms_norm': True, 'swiglu': True} [2025-10-05 21:06:50,774] [INFO] [axolotl.integrations.cut_cross_entropy.pre_model_load:94] [PID:11253] Applying Cut Cross Entropy to model type: mistral Loading checkpoint shards: 0%| | 0/5 [00:00", line 198, in _run_module_as_main File "", line 88, in _run_code File "/workspace/.venv/lib/python3.12/site-packages/axolotl/cli/train.py", line 121, in fire.Fire(do_cli) File "/workspace/.venv/lib/python3.12/site-packages/fire/core.py", line 135, in Fire component_trace = _Fire(component, args, parsed_flag_args, context, name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/.venv/lib/python3.12/site-packages/fire/core.py", line 468, in _Fire component, remaining_args = _CallAndUpdateTrace( ^^^^^^^^^^^^^^^^^^^^ File "/workspace/.venv/lib/python3.12/site-packages/fire/core.py", line 684, in _CallAndUpdateTrace component = fn(*varargs, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/.venv/lib/python3.12/site-packages/axolotl/cli/train.py", line 88, in do_cli return do_train(parsed_cfg, parsed_cli_args) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/.venv/lib/python3.12/site-packages/axolotl/cli/train.py", line 45, in do_train model, tokenizer, trainer = train(cfg=cfg, dataset_meta=dataset_meta) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/.venv/lib/python3.12/site-packages/axolotl/train.py", line 594, in train create_model_card(cfg, trainer) File "/workspace/.venv/lib/python3.12/site-packages/axolotl/train.py", line 382, in create_model_card trainer.push_to_hub() File "/workspace/.venv/lib/python3.12/site-packages/axolotl/core/trainers/base.py", line 551, in push_to_hub return super().push_to_hub(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/.venv/lib/python3.12/site-packages/transformers/trainer.py", line 5164, in push_to_hub return upload_folder( ^^^^^^^^^^^^^^ File "/workspace/.venv/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/workspace/.venv/lib/python3.12/site-packages/huggingface_hub/hf_api.py", line 1669, in _inner return fn(self, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/.venv/lib/python3.12/site-packages/huggingface_hub/hf_api.py", line 4993, in upload_folder commit_info = self.create_commit( ^^^^^^^^^^^^^^^^^^^ File "/workspace/.venv/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/workspace/.venv/lib/python3.12/site-packages/huggingface_hub/hf_api.py", line 1669, in _inner return fn(self, *args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/.venv/lib/python3.12/site-packages/huggingface_hub/hf_api.py", line 4342, in create_commit hf_raise_for_status(commit_resp, endpoint_name="commit") File "/workspace/.venv/lib/python3.12/site-packages/huggingface_hub/utils/_http.py", line 471, in hf_raise_for_status raise _format(HfHubHTTPError, message, response) from e huggingface_hub.errors.HfHubHTTPError: (Request ID: Root=1-68e30fa7-793d8ae8160b7f2176cf50e4;ec3ddf31-6b11-4509-95d3-948e1a100918) 403 Forbidden: Private repository storage limit reached, please upgrade your plan to increase your private storage limit. Cannot access content at: https://huggingface.co/api/models/ToastyPigeon/muse-marvin-lora/commit/main. Make sure your token has the correct permissions.