PyTorch
Diffusers
audio
music
minimax-music-3
rvq
reference-audio
comfyui
open-rvq-encoder-minimax-music3 / evaluation /condition-replay-aggregate.json
bghira's picture
Add v1-v4 RVQ encoder collection and reference-audio integrations
1203bba verified
Raw
History Blame Contribute Delete
7.33 kB
{
"dataset": {
"exact_alignment_records": 130,
"repo_id": "bghira/minimax-music3-rvq-reverse-distillation",
"revision": "5029b1e7f1bbfbf028b76b38564fecccda94a111",
"split": "holdout"
},
"format": "simpletuner-minimaxmusic-replay-comparison-v1",
"metric": "per-record mean stitched condition-embedding cosine",
"models": [
{
"checkpoint": {
"checkpoint_bytes": 163955786,
"checkpoint_sha256": "fd7bfefb197cb7b65a6b6d9b1373c1772a15979f1a4b67d820764d610f0fb9a5",
"checkpoint_url": "https://www.serveurperso.com/ia/ssd/workspace/git/minimaxmusic.cpp/training/checkpoints/v1/best.pt",
"epoch": 17,
"reported_validation_loss": 5.292583839459852,
"source_commit": "d19efe9f94e41ac4c900aa30d56fe90c8dac7ef1",
"source_url": "https://github.com/ServeurpersoCom/minimaxmusic.cpp/commit/d19efe9f94e41ac4c900aa30d56fe90c8dac7ef1"
},
"model_id": "serveurperso-v1",
"parameter_count": 40978944,
"predicted_code_condition_cosine": {
"count": 130,
"max": 0.7290002703666687,
"mean": 0.6633286081827604,
"min": 0.6026018261909485,
"quantiles": {
"0.0": 0.6026018261909485,
"0.05": 0.6280524551868438,
"0.25": 0.6483299732208252,
"0.5": 0.6645751297473907,
"0.75": 0.6784153282642365,
"0.95": 0.6963281780481339,
"1.0": 0.7290002703666687
},
"std": 0.02217457298933777
},
"true_code_control": {
"count": 130,
"max": 0.999957263469696,
"mean": 0.9999072317893688,
"min": 0.9983662366867065,
"quantiles": {
"0.0": 0.9983662366867065,
"0.05": 0.999821075797081,
"0.25": 0.9999240636825562,
"0.5": 0.9999381899833679,
"0.75": 0.9999445825815201,
"0.95": 0.9999500513076782,
"1.0": 0.999957263469696
},
"std": 0.00015022638681815362
}
},
{
"checkpoint": {
"checkpoint": "full/output/final",
"checkpoint_bytes": 163931632,
"checkpoint_sha256": "1cea88dddf7a48583c13ac661a548b7a3535b933a76356bb158420d24da32f22",
"global_step": 17640
},
"model_id": "simpletuner-v1",
"parameter_count": 40978944,
"predicted_code_condition_cosine": {
"count": 130,
"max": 0.8286042809486389,
"mean": 0.7624421353523548,
"min": 0.7123062014579773,
"quantiles": {
"0.0": 0.7123062014579773,
"0.05": 0.7345191180706024,
"0.25": 0.747437372803688,
"0.5": 0.7631425857543945,
"0.75": 0.7765287756919861,
"0.95": 0.7904498308897019,
"1.0": 0.8286042809486389
},
"std": 0.019549602827450108
},
"true_code_control": {
"count": 130,
"max": 0.999957263469696,
"mean": 0.9999072317893688,
"min": 0.9983662366867065,
"quantiles": {
"0.0": 0.9983662366867065,
"0.05": 0.999821075797081,
"0.25": 0.9999240636825562,
"0.5": 0.9999381899833679,
"0.75": 0.9999445825815201,
"0.95": 0.9999500513076782,
"1.0": 0.999957263469696
},
"std": 0.00015022638681815362
}
},
{
"checkpoint": {
"checkpoint": "v2/output/final",
"checkpoint_bytes": 618960456,
"checkpoint_sha256": "47dfffb7a76d95589752df0c59ff6eaf3496f6fcf5408d324218887e471023c7",
"global_step": 17660
},
"model_id": "simpletuner-v2",
"parameter_count": 154736064,
"predicted_code_condition_cosine": {
"count": 130,
"max": 0.8361330032348633,
"mean": 0.7698414775041433,
"min": 0.7206224203109741,
"quantiles": {
"0.0": 0.7206224203109741,
"0.05": 0.7429912149906158,
"0.25": 0.7548101097345352,
"0.5": 0.770626574754715,
"0.75": 0.7835157215595245,
"0.95": 0.7986360996961593,
"1.0": 0.8361330032348633
},
"std": 0.019062989675575924
},
"true_code_control": {
"count": 130,
"max": 0.999957263469696,
"mean": 0.9999072317893688,
"min": 0.9983662366867065,
"quantiles": {
"0.0": 0.9983662366867065,
"0.05": 0.999821075797081,
"0.25": 0.9999240636825562,
"0.5": 0.9999381899833679,
"0.75": 0.9999445825815201,
"0.95": 0.9999500513076782,
"1.0": 0.999957263469696
},
"std": 0.00015022638681815362
}
},
{
"checkpoint": {
"checkpoint": "v3/output/final",
"checkpoint_bytes": 618960456,
"checkpoint_sha256": "356e97fea65c486a28814dc778b52645807ab8f784c6021d2403f688a2bfe788",
"global_step": 17660
},
"model_id": "simpletuner-v3",
"parameter_count": 154736064,
"predicted_code_condition_cosine": {
"count": 130,
"max": 0.8356426954269409,
"mean": 0.7702590204202212,
"min": 0.7236603498458862,
"quantiles": {
"0.0": 0.7236603498458862,
"0.05": 0.7415853887796402,
"0.25": 0.7547859847545624,
"0.5": 0.7704743146896362,
"0.75": 0.7837727516889572,
"0.95": 0.8004916191101075,
"1.0": 0.8356426954269409
},
"std": 0.019273954474224628
},
"true_code_control": {
"count": 130,
"max": 0.999957263469696,
"mean": 0.9999072317893688,
"min": 0.9983662366867065,
"quantiles": {
"0.0": 0.9983662366867065,
"0.05": 0.999821075797081,
"0.25": 0.9999240636825562,
"0.5": 0.9999381899833679,
"0.75": 0.9999445825815201,
"0.95": 0.9999500513076782,
"1.0": 0.999957263469696
},
"std": 0.00015022638681815362
}
},
{
"checkpoint": {
"checkpoint": "v4/output/final",
"checkpoint_bytes": 676055232,
"checkpoint_sha256": "e8fa93a7db2e5a090442d9492ea3f9f07664ce5bdb2ea7890559a4408f049744",
"global_step": 17660
},
"model_id": "simpletuner-v4",
"parameter_count": 169008576,
"predicted_code_condition_cosine": {
"count": 130,
"max": 0.897747814655304,
"mean": 0.8747961479883928,
"min": 0.8091457486152649,
"quantiles": {
"0.0": 0.8091457486152649,
"0.05": 0.8453496336936951,
"0.25": 0.8675179928541183,
"0.5": 0.879057914018631,
"0.75": 0.8857778161764145,
"0.95": 0.8938389658927918,
"1.0": 0.897747814655304
},
"std": 0.015662041602848998
},
"true_code_control": {
"count": 130,
"max": 0.999957263469696,
"mean": 0.9999072317893688,
"min": 0.9983662366867065,
"quantiles": {
"0.0": 0.9983662366867065,
"0.05": 0.999821075797081,
"0.25": 0.9999240636825562,
"0.5": 0.9999381899833679,
"0.75": 0.9999445825815201,
"0.95": 0.9999500513076782,
"1.0": 0.999957263469696
},
"std": 0.00015022638681815362
}
}
]
}