2025-11-20 11:58:58.679 | DEBUG    | llmcompressor.core.lifecycle:reset:59 - Resetting compression lifecycle
2025-11-20 11:58:58.681 | INFO     | llmcompressor.core.lifecycle:reset:71 - Compression lifecycle reset
2025-11-20 11:58:58.681 | DEBUG    | llmcompressor.core.state:update:182 - Updating state with provided parameters: {'model': ApertusForCausalLM(
  (model): ApertusModel(
    (embed_tokens): Embedding(131072, 4096, padding_idx=3)
    (layers): ModuleList(
      (0-31): 32 x ApertusDecoderLayer(
        (self_attn): ApertusAttention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (k_proj): Linear(in_features=4096, out_features=1024, bias=False)
          (v_proj): Linear(in_features=4096, out_features=1024, bias=False)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
          (q_norm): ApertusRMSNorm((128,), eps=1e-05)
          (k_norm): ApertusRMSNorm((128,), eps=1e-05)
        )
        (mlp): ApertusMLP(
          (up_proj): Linear(in_features=4096, out_features=21504, bias=False)
          (down_proj): Linear(in_features=21504, out_features=4096, bias=False)
          (act_fn): XIELUActivation()
        )
        (attention_layernorm): ApertusRMSNorm((4096,), eps=1e-05)
        (feedforward_layernorm): ApertusRMSNorm((4096,), eps=1e-05)
      )
    )
    (norm): ApertusRMSNorm((4096,), eps=1e-05)
    (rotary_emb): ApertusRotaryEmbedding()
  )
  (lm_head): Linear(in_features=4096, out_features=131072, bias=False)
), 'teacher_model': None, 'optimizer': None, 'attach_optim_callbacks': True, 'train_data': None, 'val_data': None, 'test_data': None, 'calib_data': None, 'copy_data': True, 'start': -1, 'steps_per_epoch': None, 'batches_per_step': None, 'loggers': None, 'model_log_cadence': None, 'kwargs': {}}
2025-11-20 11:58:58.686 | INFO     | llmcompressor.metrics.logger:_create_default_logger:357 - Logging all LLM Compressor modifier-level logs to sparse_logs/20-11-2025_11.58.58.log
2025-11-20 11:58:58.688 | DEBUG    | llmcompressor.core.lifecycle:initialize:92 - Initializing compression lifecycle
2025-11-20 11:58:58.688 | INFO     | llmcompressor.recipe.recipe:from_modifiers:68 - Creating recipe from modifiers
2025-11-20 11:58:58.720 | DEBUG    | llmcompressor.core.lifecycle:initialize:105 - Initialized modifier: config_groups=None targets=['Linear'] ignore=['lm_head'] scheme='FP8_dynamic' kv_cache_scheme=None index=None group=None start=None end=None update=None initialized_=True finalized_=False started_=False ended_=False
2025-11-20 11:58:58.721 | INFO     | llmcompressor.core.lifecycle:initialize:110 - Compression lifecycle initialized for 1 modifiers
2025-11-20 11:58:58.721 | INFO     | llmcompressor.pipelines.independent.pipeline:IndependentPipeline:43 - Inferred `DataFreePipeline` for `QuantizationModifier`
2025-11-20 11:58:58.769 | DEBUG    | llmcompressor.core.lifecycle:event:195 - Handling event: EventType.CALIBRATION_EPOCH_START
2025-11-20 11:59:04.629 | DEBUG    | llmcompressor.core.lifecycle:event:205 - Updated event with modifier: config_groups=None targets=['Linear'] ignore=['lm_head'] scheme='FP8_dynamic' kv_cache_scheme=None index=None group=None start=None end=None update=None initialized_=True finalized_=False started_=True ended_=False
2025-11-20 11:59:04.631 | DEBUG    | llmcompressor.core.lifecycle:event:195 - Handling event: EventType.CALIBRATION_EPOCH_END
2025-11-20 11:59:04.636 | DEBUG    | llmcompressor.core.lifecycle:event:205 - Updated event with modifier: config_groups=None targets=['Linear'] ignore=['lm_head'] scheme='FP8_dynamic' kv_cache_scheme=None index=None group=None start=None end=None update=None initialized_=True finalized_=False started_=True ended_=True
2025-11-20 11:59:04.637 | DEBUG    | llmcompressor.core.lifecycle:finalize:134 - Finalizing compression lifecycle
2025-11-20 11:59:04.637 | DEBUG    | llmcompressor.core.lifecycle:finalize:138 - Finalized modifier: config_groups=None targets=['Linear'] ignore=['lm_head'] scheme='FP8_dynamic' kv_cache_scheme=None index=None group=None start=None end=None update=None initialized_=True finalized_=None started_=True ended_=True
2025-11-20 11:59:04.637 | INFO     | llmcompressor.core.lifecycle:finalize:144 - Compression lifecycle finalized for 1 modifiers
2025-11-20 11:59:04.642 | INFO     | llmcompressor.transformers.compression.compressed_tensors_utils:get_model_compressor:193 - skip_sparsity_compression_stats set to True. Skipping sparsity compression statistic calculations. No sparsity compressor will be applied.
2025-11-20 11:59:18.061 | DEBUG    | llmcompressor.transformers.utils.helpers:recipe_from_huggingface_model_id:146 - Unable to find recipe recipe.yaml for model ID: swiss-ai/Apertus-8B-Instruct-2509: 404 Client Error. (Request ID: Root=1-691ef485-4d55a9d36133e4333da2de98;feb77bfc-93ef-4155-9cd7-e2af43da3a52)

Entry Not Found for url: https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509/resolve/main/recipe.yaml..Skipping recipe resolution.
2025-11-20 11:59:18.063 | DEBUG    | llmcompressor.transformers.utils.helpers:infer_recipe_from_model_path:112 - Failed to infer the recipe from the model_path