[2026-03-23 06:22:22,947] [WARNING] [huggingface_hub.utils._http._warn_on_warning_headers:916] [PID:180] Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. config.json: 0%| | 0.00/675 [00:00", line 198, in _run_module_as_main File "", line 88, in _run_code File "/workspace/axolotl/src/axolotl/cli/train.py", line 121, in fire.Fire(do_cli) File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/fire/core.py", line 135, in Fire component_trace = _Fire(component, args, parsed_flag_args, context, name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/fire/core.py", line 468, in _Fire component, remaining_args = _CallAndUpdateTrace( ^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/fire/core.py", line 684, in _CallAndUpdateTrace component = fn(*varargs, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/cli/train.py", line 88, in do_cli return do_train(parsed_cfg, parsed_cli_args) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/cli/train.py", line 43, in do_train dataset_meta = load_datasets(cfg=cfg, cli_args=cli_args) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/telemetry/errors.py", line 127, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/common/datasets.py", line 61, in load_datasets train_dataset, eval_dataset, total_num_steps, prompters = prepare_datasets( ^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/utils.py", line 50, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/sft.py", line 65, in prepare_datasets return _prepare_standard_dataset(cfg, tokenizer, processor) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/sft.py", line 98, in _prepare_standard_dataset train_dataset, eval_dataset, prompters = loader.load(_load_datasets) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/lock.py", line 38, in load result = load_fn() ^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/sft.py", line 77, in _load_datasets train_dataset, eval_dataset, prompters = _load_and_prepare_datasets( ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/sft.py", line 492, in _load_and_prepare_datasets dataset, prompters = _load_tokenized_prepared_datasets( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/sft.py", line 299, in _load_tokenized_prepared_datasets dataset, prompters = _load_raw_datasets( ^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/sft.py", line 331, in _load_raw_datasets dataset_wrapper, dataset_prompter = _load_and_process_single_dataset( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/sft.py", line 380, in _load_and_process_single_dataset dataset = load_dataset_with_config( ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/shared.py", line 121, in load_dataset_with_config is_hub_dataset = _check_if_hub_dataset(dataset_config, use_auth_token) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/shared.py", line 154, in _check_if_hub_dataset snapshot_download( File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 89, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/huggingface_hub/_snapshot_download.py", line 240, in snapshot_download repo_info = api.repo_info(repo_id=repo_id, repo_type=repo_type, revision=revision) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 89, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/huggingface_hub/hf_api.py", line 3146, in repo_info return method( ^^^^^^^ File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 89, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/huggingface_hub/hf_api.py", line 2997, in dataset_info headers = self._build_hf_headers(token=token) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/huggingface_hub/hf_api.py", line 10083, in _build_hf_headers return build_hf_headers( ^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 89, in _inner_fn return fn(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/huggingface_hub/utils/_headers.py", line 110, in build_hf_headers token_to_send = get_token_to_send(token) ^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/huggingface_hub/utils/_headers.py", line 143, in get_token_to_send raise LocalTokenNotFoundError( huggingface_hub.errors.LocalTokenNotFoundError: Token is required (`token=True`), but no token found. You need to provide a token or be logged in to Hugging Face with `hf auth login` or `huggingface_hub.login`. See https://huggingface.co/settings/tokens. [2026-03-23 06:23:31,392] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:323] baseline 0.000GB (+0.000GB allocated, +0.002GB reserved) [2026-03-23 06:23:31,393] [INFO] [axolotl.cli.config.load_cfg:341] [PID:323] config: { "activation_offloading": false, "adapter": "lora", "auto_resume_from_checkpoints": true, "axolotl_config_path": "train.yml", "base_model": "PicoKittens/PicoMistral-23M", "base_model_config": "PicoKittens/PicoMistral-23M", "batch_size": 4, "bf16": false, "capabilities": { "bf16": true, "compute_capability": "sm_75", "fp8": false, "n_gpu": 1, "n_node": 1, "tf32": false }, "context_parallel_size": 1, "dataloader_num_workers": 1, "dataloader_pin_memory": true, "dataloader_prefetch_factor": 256, "dataset_num_proc": 16, "datasets": [ { "message_property_mappings": { "content": "content", "role": "role" }, "path": "psychopenguin/indian_legal_dataset_qna", "split": "train[:2%]", "trust_remote_code": false, "type": "alpaca" } ], "ddp": false, "device": "cuda:0", "dion_rank_fraction": 1.0, "dion_rank_multiple_of": 1, "eaft_alpha": 1.0, "eaft_k": 20, "early_stopping_patience": 3, "env_capabilities": { "torch_version": "2.9.1" }, "eval_batch_size": 2, "eval_causal_lm_metrics": [ "sacrebleu", "comet", "ter", "chrf" ], "eval_max_new_tokens": 128, "eval_steps": 100, "eval_strategy": "steps", "eval_table_size": 0, "experimental_skip_move_to_device": true, "fp16": true, "generate_samples": false, "generation_do_sample": true, "generation_max_new_tokens": 50, "generation_prompt_ratio": 0.5, "generation_temperature": 0.7, "gradient_accumulation_steps": 2, "gradient_checkpointing": false, "hf_use_auth_token": true, "hub_model_id": "psychopenguin/t1", "include_tkps": true, "is_falcon_derived_model": false, "is_llama_derived_model": false, "is_mistral_derived_model": true, "learning_rate": 0.0002, "lisa_layers_attribute": "model.layers", "load_best_model_at_end": true, "load_in_4bit": false, "load_in_8bit": false, "local_rank": 0, "lora_alpha": 8, "lora_dropout": 0.05, "lora_r": 4, "lora_target_linear": true, "loraplus_lr_embedding": 1e-06, "lr_scheduler": "cosine", "mean_resizing_embeddings": false, "merge_lora": true, "micro_batch_size": 2, "model_config_type": "mistral", "neftune_noise_alpha": 5.0, "num_epochs": 3.0, "num_generation_samples": 3, "optimizer": "adamw_bnb_8bit", "otel_metrics_host": "localhost", "otel_metrics_port": 8000, "output_dir": "./final_model", "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_steps": 100, "sdp_attention": true, "seed": 9, "sequence_len": 256, "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": "PicoKittens/PicoMistral-23M", "tokenizer_save_jinja_files": true, "tokenizer_type": "AutoTokenizer", "tokenizer_use_fast": true, "torch_dtype": "torch.float16", "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 }, "trust_remote_code": true, "type_of_model": "AutoModelForCausalLM", "use_otel_metrics": false, "use_ray": false, "use_wandb": true, "val_set_size": 0.3, "vllm": { "device": "auto", "dtype": "auto", "gpu_memory_utilization": 0.9, "host": "0.0.0.0", "port": 8000 }, "wandb_name": "t1", "wandb_project": "tttt", "weight_decay": 0.0, "world_size": 1 } [2026-03-23 06:23:33,247] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:299] [PID:323] EOS: 2 / [EOS] [2026-03-23 06:23:33,247] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:300] [PID:323] BOS: 1 / [BOS] [2026-03-23 06:23:33,247] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:301] [PID:323] PAD: 0 / [PAD] [2026-03-23 06:23:33,247] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:302] [PID:323] UNK: 3 / [UNK] [2026-03-23 06:23:33,247] [INFO] [axolotl.loaders.tokenizer.load_tokenizer:316] [PID:323] No Chat template selected. Consider adding a chat template for easier inference. [2026-03-23 06:23:33,248] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:480] [PID:323] Unable to find prepared dataset in last_run_prepared/d5a17e3528edff9ec955ba25ed6f7604 [2026-03-23 06:23:33,248] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:323] Loading raw datasets... [2026-03-23 06:23:33,248] [WARNING] [axolotl.utils.data.sft._load_raw_datasets:322] [PID:323] Processing datasets during training can lead to VRAM instability. Please pre-process your dataset using `axolotl preprocess path/to/config.yml`. Downloading (incomplete total...): 0.00B [00:00, ?B/s] Fetching 0 files: 0it [00:00, ?it/s] Fetching 0 files: 0it [00:00, ?it/s] Download complete: : 0.00B [00:00, ?B/s] Download complete: : 0.00B [00:01, ?B/s] train.json: 0%| | 0.00/16.9M [00:00256) (num_proc=16): 0%| | 0/741 [00:00256) (num_proc=16): 6%| | 47/741 [00:00<00:02, 286.9 Dropping Invalid Sequences (256) (num_proc=16): 100%|█| 741/741 [00:00<00:00, 2738 [2026-03-23 06:23:39,577] [INFO] [axolotl.utils.data.utils._drop_outside_range:306] [PID:323] Dropped 13 sequences outside valid range ([None, 256]) Saving the dataset (0/2 shards): 0%| | 0/728 [00:00.teardown_atexit at 0x7724f5a9bce0> Traceback (most recent call last): File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/wandb/sdk/lib/service/service_connection.py", line 73, in teardown_atexit [2026-03-23 06:34:33,895] [WARNING] [asyncio.write:1054] [PID:323] socket.send() raised exception. conn.teardown(hooks.exit_code) File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/wandb/sdk/lib/service/service_connection.py", line 346, in teardown return self._proc.join() [2026-03-23 06:34:33,897] [WARNING] [asyncio.write:1054] [PID:323] socket.send() raised exception. ^^^^^^^^^^^^^^^^^ [2026-03-23 06:34:33,898] [WARNING] [asyncio.write:1054] [PID:323] socket.send() raised exception. File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/wandb/sdk/lib/service/service_process.py", line 57, in join [2026-03-23 06:34:33,899] [WARNING] [asyncio.write:1054] [PID:323] socket.send() raised exception. [2026-03-23 06:34:33,900] [WARNING] [asyncio.write:1054] [PID:323] socket.send() raised exception. [2026-03-23 06:34:33,900] [WARNING] [asyncio.write:1054] [PID:323] socket.send() raised exception. [2026-03-23 06:34:33,900] [WARNING] [asyncio.write:1054] [PID:323] socket.send() raised exception. [2026-03-23 06:34:33,900] [WARNING] [asyncio.write:1054] [PID:323] socket.send() raised exception. return self._process.wait() ^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py3.11/lib/python3.11/subprocess.py", line 1264, in wait return self._wait(timeout=timeout) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py3.11/lib/python3.11/subprocess.py", line 2053, in _wait (pid, sts) = self._try_wait(0) ^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py3.11/lib/python3.11/subprocess.py", line 2011, in _try_wait (pid, sts) = os.waitpid(self.pid, wait_flags) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/train.py", line 171, in lambda signum, frame: terminate_handler(signum, frame, _model_weakref), ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/train.py", line 166, in terminate_handler sys.exit(0) File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/wandb/sdk/lib/exit_hooks.py", line 38, in exit self._orig_exit(orig_code) # type: ignore ^^^^^^^^^^^^^^^^^^^^^^^^^^ SystemExit: 0 [2026-03-23 06:35:21,063] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:774] baseline 0.000GB (+0.000GB allocated, +0.002GB reserved) [2026-03-23 06:35:21,064] [INFO] [axolotl.cli.config.load_cfg:341] [PID:774] config: { "activation_offloading": false, "adapter": "lora", "auto_resume_from_checkpoints": true, "axolotl_config_path": "train.yml", "base_model": "PicoKittens/PicoMistral-23M", "base_model_config": "PicoKittens/PicoMistral-23M", "batch_size": 4, "bf16": false, "capabilities": { "bf16": true, "compute_capability": "sm_75", "fp8": false, "n_gpu": 1, "n_node": 1, "tf32": false }, "context_parallel_size": 1, "dataloader_num_workers": 1, "dataloader_pin_memory": true, "dataloader_prefetch_factor": 256, "dataset_num_proc": 16, "datasets": [ { "message_property_mappings": { "content": "content", "role": "role" }, "path": "psychopenguin/indian_legal_dataset_qna", "split": "train[:2%]", "trust_remote_code": false, "type": "alpaca" } ], "ddp": false, "device": "cuda:0", "dion_rank_fraction": 1.0, "dion_rank_multiple_of": 1, "eaft_alpha": 1.0, "eaft_k": 20, "early_stopping_patience": 3, "env_capabilities": { "torch_version": "2.9.1" }, "eval_batch_size": 2, "eval_causal_lm_metrics": [ "sacrebleu", "comet", "ter", "chrf" ], "eval_max_new_tokens": 128, "eval_steps": 100, "eval_strategy": "steps", "eval_table_size": 0, "experimental_skip_move_to_device": true, "fp16": true, "generate_samples": false, "generation_do_sample": true, "generation_max_new_tokens": 50, "generation_prompt_ratio": 0.5, "generation_temperature": 0.7, "gradient_accumulation_steps": 2, "gradient_checkpointing": false, "hf_use_auth_token": true, "hub_model_id": "psychopenguin/t1", "include_tkps": true, "is_falcon_derived_model": false, "is_llama_derived_model": false, "is_mistral_derived_model": true, "learning_rate": 0.0002, "lisa_layers_attribute": "model.layers", "load_best_model_at_end": true, "load_in_4bit": false, "load_in_8bit": false, "local_rank": 0, "lora_alpha": 8, "lora_dropout": 0.05, "lora_r": 4, "lora_target_linear": true, "loraplus_lr_embedding": 1e-06, "lr_scheduler": "cosine", "mean_resizing_embeddings": false, "merge_lora": true, "micro_batch_size": 2, "model_config_type": "mistral", "neftune_noise_alpha": 5.0, "num_epochs": 3.0, "num_generation_samples": 3, "optimizer": "adamw_bnb_8bit", "otel_metrics_host": "localhost", "otel_metrics_port": 8000, "output_dir": "./final_model", "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_steps": 100, "sdp_attention": true, "seed": 9, "sequence_len": 256, "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": "PicoKittens/PicoMistral-23M", "tokenizer_save_jinja_files": true, "tokenizer_type": "AutoTokenizer", "tokenizer_use_fast": true, "torch_dtype": "torch.float16", "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 }, "trust_remote_code": true, "type_of_model": "AutoModelForCausalLM", "use_otel_metrics": false, "use_ray": false, "use_wandb": true, "val_set_size": 0.3, "vllm": { "device": "auto", "dtype": "auto", "gpu_memory_utilization": 0.9, "host": "0.0.0.0", "port": 8000 }, "wandb_name": "t1", "wandb_project": "tttt", "weight_decay": 0.0, "world_size": 1 } [2026-03-23 06:35:22,707] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:299] [PID:774] EOS: 2 / [EOS] [2026-03-23 06:35:22,707] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:300] [PID:774] BOS: 1 / [BOS] [2026-03-23 06:35:22,707] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:301] [PID:774] PAD: 0 / [PAD] [2026-03-23 06:35:22,707] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:302] [PID:774] UNK: 3 / [UNK] [2026-03-23 06:35:22,707] [INFO] [axolotl.loaders.tokenizer.load_tokenizer:316] [PID:774] No Chat template selected. Consider adding a chat template for easier inference. [2026-03-23 06:35:22,707] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:480] [PID:774] Unable to find prepared dataset in last_run_prepared/d5a17e3528edff9ec955ba25ed6f7604 [2026-03-23 06:35:22,708] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:774] Loading raw datasets... [2026-03-23 06:35:22,708] [WARNING] [axolotl.utils.data.sft._load_raw_datasets:322] [PID:774] Processing datasets during training can lead to VRAM instability. Please pre-process your dataset using `axolotl preprocess path/to/config.yml`. Downloading (incomplete total...): 0.00B [00:00, ?B/s] Fetching 0 files: 0it [00:00, ?it/s] Fetching 0 files: 0it [00:00, ?it/s] Download complete: : 0.00B [00:00, ?B/s] Download complete: : 0.00B [00:01, ?B/s] [2026-03-23 06:35:26,131] [INFO] [axolotl.utils.data.wrappers.get_dataset_wrapper:87] [PID:774] Loading dataset: psychopenguin/indian_legal_dataset_qna with base_type: alpaca and prompt_style: None [2026-03-23 06:35:26,161] [INFO] [axolotl.utils.data.utils._log_dataset_stats:212] [PID:774] min_input_len: 46 [2026-03-23 06:35:26,161] [INFO] [axolotl.utils.data.utils._log_dataset_stats:213] [PID:774] max_input_len: 333 [2026-03-23 06:35:26,182] [INFO] [axolotl.utils.data.utils._drop_outside_range:306] [PID:774] Dropped 13 sequences outside valid range ([None, 256]) Saving the dataset (0/2 shards): 0%| | 0/728 [00:00