Text-to-Speech
English
German
voice-acting
qwen3
moss-audio-tokenizer-v2
audio-generation
Humaneness-Voice-Small / code /plan_caption_production_32nodes.json
ChristophSchuhmann's picture
Document architecture, prompts, code, and full run statistics
d911efa verified
Raw History Blame Contribute Delete
5.58 kB
{
"kind": "m2_continuous_large_talker_v1",
"architecture": "qwen3_0.6b_plus_fresh_sft3_width_talker",
"initialization": {
"semantic": "original_pretrained_Qwen3-0.6B",
"talker": "random_fresh"
},
"nodes": 32,
"ranks_per_node": 4,
"world_size": 128,
"samples_per_gpu": 32,
"global_batch": 4096,
"seed": 20260923,
"max_padded_tokens": 12000,
"max_examples": 16,
"lr_backbone_peak": 8e-05,
"lr_talker_peak": 0.00024,
"lr_floor_factor": 0.05,
"scheduler": "single_linear_warmup_then_cosine_no_stage_restarts",
"gradient_communication": "bfloat16",
"deterministic": false,
"checkpoint_policy": "all_stage_boundaries_plus_interval",
"checkpoint_interval_seconds": 3600,
"max_invocation_seconds": 40000,
"resume_policy": "latest_complete_same_plan_world",
"prompt_contract": "m2-multiformat-caption-v1-20260923",
"allowed_prompt_format_ids": [
"m2-cascade-timed-repair-v1-20260920",
"m2-multiformat-caption-v1-20260923"
],
"codec_contract": "MOSS-Audio-Tokenizer-v2; 12 codebooks/frame; 12.5 frames/s; 150 codebook tokens/s",
"code_sha256": {
"continuous_train.py": "58b6c82beaaf6ff8e2b65fea6312a28afd75079153c13dfdb9d432de4c42befc",
"large_talker.py": "3a1d0ed44467a6933dfac2a21a143a1c802482bafb2e992a1e6d8793e3fcdae4",
"caption_curriculum_dataset.py": "6c01a3e26e5908d01391bfd4aa89815746a6a26aedca397ba1299e5d688a2a64",
"cascade_dataset.py": "784967ce6d1a545d565a95a16c940ee2743085362576d1566c2b37aa2f40b351",
"timed_prompt.py": "4d06d0447573284f09804ba516bb2121f65d4cb26ec5a2c01c5bd8d425c8a642",
"anno_timed.py": "06df8ed3cb7f67d59d1bfca2931e26dd4489344925c01e4412836d2fcf946ec6"
},
"created_at": "2026-09-25T08:43:16.244121+02:00",
"stages": [
{
"name": "S1",
"tier": "x100",
"manifest": "/e/scratch/reformo/schuhmann1_moss/out/m2_600m_ladder/caption_curriculum_v1/manifests/S1/manifest.json",
"manifest_sha256": "447cc8c91fa507dad7e4c30fbe36e1f5510efcc13e49b2e267e4fdbc04cad56f",
"presentations": 66621417,
"measured_hours": 188353.851,
"updates": 16265
},
{
"name": "S2",
"tier": "x50",
"manifest": "/e/scratch/reformo/schuhmann1_moss/out/m2_600m_ladder/caption_curriculum_v1/manifests/S2/manifest.json",
"manifest_sha256": "1db622e32c210ad3bf258251852e4f4fd0095d521da8aa08c91431e1ac175ade",
"presentations": 41036973,
"measured_hours": 116837.568,
"updates": 10019
},
{
"name": "S3",
"tier": "tier7",
"manifest": "/e/scratch/reformo/schuhmann1_moss/out/m2_600m_ladder/caption_curriculum_v1/manifests/S3/manifest.json",
"manifest_sha256": "7625d9fb0a74709af1f6ad7698c77369c32e131271b8f88f8714d12e821eee50",
"presentations": 24789493,
"measured_hours": 72314.446,
"updates": 6053
},
{
"name": "S4",
"tier": "tier6",
"manifest": "/e/scratch/reformo/schuhmann1_moss/out/m2_600m_ladder/caption_curriculum_v1/manifests/S4/manifest.json",
"manifest_sha256": "255cb00bc50183ceadf7b1dec23b65a3fb6f575daa06002365a9c658e21a6226",
"presentations": 19842627,
"measured_hours": 57419.06,
"updates": 4845
},
{
"name": "S5",
"tier": "tier5",
"manifest": "/e/scratch/reformo/schuhmann1_moss/out/m2_600m_ladder/caption_curriculum_v1/manifests/S5/manifest.json",
"manifest_sha256": "eb3b6e0d004f6460adff2274d3041925d5b417a853010dad3c39106b30074a24",
"presentations": 10152521,
"measured_hours": 28716.381,
"updates": 2479
},
{
"name": "S6",
"tier": "tier4",
"manifest": "/e/scratch/reformo/schuhmann1_moss/out/m2_600m_ladder/caption_curriculum_v1/manifests/S6/manifest.json",
"manifest_sha256": "90094e2cb294791ff7e24df7f36acddac39e95cca25a6c2fc885bc2b9f2f5bb2",
"presentations": 5217313,
"measured_hours": 14361.366,
"updates": 1274
},
{
"name": "S7",
"tier": "tier3",
"manifest": "/e/scratch/reformo/schuhmann1_moss/out/m2_600m_ladder/caption_curriculum_v1/manifests/S7/manifest.json",
"manifest_sha256": "b3d94f4b4b10e78fc4b4a33186b86611f7d1ad69a88a84175f9d9c0a69f98df7",
"presentations": 2171373,
"measured_hours": 5749.569,
"updates": 531
},
{
"name": "S8",
"tier": "tier2",
"manifest": "/e/scratch/reformo/schuhmann1_moss/out/m2_600m_ladder/caption_curriculum_v1/manifests/S8/manifest.json",
"manifest_sha256": "0187e2809cee89f6f4431b3827d8046ce2f8d4f059c37e3086e38d42197db865",
"presentations": 1116702,
"measured_hours": 2877.426,
"updates": 273
},
{
"name": "S9",
"tier": "tier1",
"manifest": "/e/scratch/reformo/schuhmann1_moss/out/m2_600m_ladder/caption_curriculum_v1/manifests/S9/manifest.json",
"manifest_sha256": "edf6e8fff72d6d6e8128a0c2f06e7a0ee2aa1064c420d85dbc17fd7f0871372f",
"presentations": 568338,
"measured_hours": 1439.466,
"updates": 139
},
{
"name": "S10",
"tier": "tier0",
"manifest": "/e/scratch/reformo/schuhmann1_moss/out/m2_600m_ladder/caption_curriculum_v1/manifests/S10/manifest.json",
"manifest_sha256": "24d9d3f500c8132fc07168ad07470f7cafdecec4dde7c7b064d395d49909ec13",
"presentations": 234815,
"measured_hours": 577.881,
"updates": 58
}
],
"total_updates": 41936,
"warmup_steps": 2097,
"output": "/e/scratch/reformo/schuhmann1_moss/out/m2_600m_ladder/caption_curriculum_v1/training",
"purpose": "authorized continuous S1-to-S10 multi-caption production"
}