liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
31 lines
2.0 KiB
JSON
31 lines
2.0 KiB
JSON
{
|
||
"experiment": "8-6",
|
||
"status": "resolved_without_reducing_campaign",
|
||
"failures": [
|
||
{
|
||
"stage": "dataset_load",
|
||
"component": "datasets 3.6.0 / Hugging Face Hub",
|
||
"attempted_source": "MrDragonFox/Elise",
|
||
"exception_type": "FileNotFoundError",
|
||
"message": "The dataset repository exists but Hugging Face marks it disabled, so load_dataset could not resolve its data files.",
|
||
"resolution": "Pinned the public non-disabled maxbsoft/mrdragonfox-elise mirror at revision 2cc657c3f94a83df18fcd968b7531ca1a19c7f88. Both training manifests record the substitution."
|
||
},
|
||
{
|
||
"stage": "sesame_model_load",
|
||
"component": "Unsloth 2026.8.2",
|
||
"exception_type": "RuntimeError",
|
||
"message": "Unsloth: Could not find a valid pad token for unsloth/csm-1b - please inspect the tokenizer. A temporary '<｜PAD▁TOKEN｜>' was added.",
|
||
"root_cause": "The upstream tokenizer aliases pad to EOS while CSM config declares existing token 128004 (<|finetune_right_pad_id|>) as padding; the 2026.8 safety guard also interprets CSM's audio-codebook vocab_size during validation.",
|
||
"resolution": "Used standard Transformers + PEFT LoRA for Sesame, with a temporary tokenizer metadata snapshot pointing pad_token to the existing model-configured token 128004. No vocabulary item or model weight was added."
|
||
},
|
||
{
|
||
"stage": "sesame_pre_training_evaluation",
|
||
"component": "Transformers 4.57.6 CsmForConditionalGeneration",
|
||
"exception_type": "RuntimeError",
|
||
"message": "Index put requires the source and destination dtypes match, got BFloat16 for the destination and Float for the source.",
|
||
"root_cause": "CSM's audio codec returned float32 audio embeddings while bf16 autocast produced bf16 text embedding slots in _merge_input_ids_with_input_values.",
|
||
"resolution": "Ran the 1B Sesame model and its LoRA campaign in float32 (bf16 disabled). The final campaign retained the same 168 training examples, 24 held-out examples, 60 optimizer steps, and 24 base/adapted comparison WAVs."
|
||
}
|
||
]
|
||
}
|