miiikiik/Qwen3-8B-music-movie-coa-sft-v2
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: miiikiik/Qwen3-8B-music-movie-coa-sft-v2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 19:48:13 +08:00
commit afd06d12f0
22 changed files with 152971 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

533
trainer_state.json Normal file
View File

@@ -0,0 +1,533 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 705,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.042598509052183174,
"grad_norm": 21.082965129152086,
"learning_rate": 1.267605633802817e-06,
"loss": 2.4664,
"step": 10
},
{
"epoch": 0.08519701810436635,
"grad_norm": 19.188427968641975,
"learning_rate": 2.676056338028169e-06,
"loss": 2.1878,
"step": 20
},
{
"epoch": 0.12779552715654952,
"grad_norm": 9.475226745542779,
"learning_rate": 4.0845070422535216e-06,
"loss": 1.4846,
"step": 30
},
{
"epoch": 0.1703940362087327,
"grad_norm": 5.306762711198587,
"learning_rate": 5.492957746478874e-06,
"loss": 0.9678,
"step": 40
},
{
"epoch": 0.21299254526091588,
"grad_norm": 4.590929790305963,
"learning_rate": 6.901408450704225e-06,
"loss": 0.5819,
"step": 50
},
{
"epoch": 0.25559105431309903,
"grad_norm": 1.6438823894653778,
"learning_rate": 8.309859154929578e-06,
"loss": 0.4161,
"step": 60
},
{
"epoch": 0.29818956336528224,
"grad_norm": 1.5007646688888001,
"learning_rate": 9.71830985915493e-06,
"loss": 0.3151,
"step": 70
},
{
"epoch": 0.3407880724174654,
"grad_norm": 3.1817046176810218,
"learning_rate": 9.996071883688333e-06,
"loss": 0.2595,
"step": 80
},
{
"epoch": 0.38338658146964855,
"grad_norm": 0.9853382945850364,
"learning_rate": 9.980124488638774e-06,
"loss": 0.2459,
"step": 90
},
{
"epoch": 0.42598509052183176,
"grad_norm": 1.0026092175101524,
"learning_rate": 9.951951426568852e-06,
"loss": 0.2227,
"step": 100
},
{
"epoch": 0.4685835995740149,
"grad_norm": 0.9467415606864195,
"learning_rate": 9.91162185929904e-06,
"loss": 0.2181,
"step": 110
},
{
"epoch": 0.5111821086261981,
"grad_norm": 1.018005381246591,
"learning_rate": 9.859234791555356e-06,
"loss": 0.1952,
"step": 120
},
{
"epoch": 0.5537806176783813,
"grad_norm": 1.2269238583843798,
"learning_rate": 9.794918827923458e-06,
"loss": 0.1918,
"step": 130
},
{
"epoch": 0.5963791267305645,
"grad_norm": 0.8698678847845421,
"learning_rate": 9.718831857138308e-06,
"loss": 0.175,
"step": 140
},
{
"epoch": 0.6389776357827476,
"grad_norm": 1.0480947036630484,
"learning_rate": 9.631160664484398e-06,
"loss": 0.1943,
"step": 150
},
{
"epoch": 0.6815761448349308,
"grad_norm": 8.384047626201337,
"learning_rate": 9.532120473258075e-06,
"loss": 0.1566,
"step": 160
},
{
"epoch": 0.724174653887114,
"grad_norm": 0.7386254552014561,
"learning_rate": 9.421954416417624e-06,
"loss": 0.1534,
"step": 170
},
{
"epoch": 0.7667731629392971,
"grad_norm": 0.7400271137846004,
"learning_rate": 9.300932939718159e-06,
"loss": 0.1586,
"step": 180
},
{
"epoch": 0.8093716719914803,
"grad_norm": 1.2075602319421987,
"learning_rate": 9.169353137796533e-06,
"loss": 0.1424,
"step": 190
},
{
"epoch": 0.8519701810436635,
"grad_norm": 1.1410187483647192,
"learning_rate": 9.027538024836143e-06,
"loss": 0.1585,
"step": 200
},
{
"epoch": 0.8945686900958466,
"grad_norm": 0.7379523855872633,
"learning_rate": 8.875835741602031e-06,
"loss": 0.1397,
"step": 210
},
{
"epoch": 0.9371671991480298,
"grad_norm": 0.8356428492042096,
"learning_rate": 8.714618700792975e-06,
"loss": 0.1546,
"step": 220
},
{
"epoch": 0.979765708200213,
"grad_norm": 0.8699813474717787,
"learning_rate": 8.54428267280858e-06,
"loss": 0.1324,
"step": 230
},
{
"epoch": 1.0212992545260915,
"grad_norm": 0.6842065606451512,
"learning_rate": 8.365245814175744e-06,
"loss": 0.1333,
"step": 240
},
{
"epoch": 1.0638977635782747,
"grad_norm": 1.2090377509101662,
"learning_rate": 8.177947641019622e-06,
"loss": 0.0952,
"step": 250
},
{
"epoch": 1.106496272630458,
"grad_norm": 1.0148320458452715,
"learning_rate": 7.982847950099055e-06,
"loss": 0.0946,
"step": 260
},
{
"epoch": 1.1490947816826411,
"grad_norm": 0.7338241692333486,
"learning_rate": 7.780425690055275e-06,
"loss": 0.1067,
"step": 270
},
{
"epoch": 1.1916932907348243,
"grad_norm": 0.6498746772924805,
"learning_rate": 7.571177785644766e-06,
"loss": 0.0897,
"step": 280
},
{
"epoch": 1.2342917997870075,
"grad_norm": 0.6563332988784214,
"learning_rate": 7.355617917842751e-06,
"loss": 0.088,
"step": 290
},
{
"epoch": 1.2768903088391905,
"grad_norm": 0.6389752490843476,
"learning_rate": 7.134275262811935e-06,
"loss": 0.0909,
"step": 300
},
{
"epoch": 1.3194888178913737,
"grad_norm": 0.7462566848514381,
"learning_rate": 6.907693192832263e-06,
"loss": 0.0923,
"step": 310
},
{
"epoch": 1.362087326943557,
"grad_norm": 0.6894751379258567,
"learning_rate": 6.676427942380741e-06,
"loss": 0.0844,
"step": 320
},
{
"epoch": 1.4046858359957402,
"grad_norm": 0.8021156814880915,
"learning_rate": 6.441047242635947e-06,
"loss": 0.0877,
"step": 330
},
{
"epoch": 1.4472843450479234,
"grad_norm": 0.9964737342042037,
"learning_rate": 6.202128927759391e-06,
"loss": 0.0846,
"step": 340
},
{
"epoch": 1.4898828541001066,
"grad_norm": 0.7290481485894376,
"learning_rate": 5.960259516375134e-06,
"loss": 0.0876,
"step": 350
},
{
"epoch": 1.5324813631522898,
"grad_norm": 0.8198141163509329,
"learning_rate": 5.716032771730008e-06,
"loss": 0.0869,
"step": 360
},
{
"epoch": 1.5750798722044728,
"grad_norm": 0.6135413073318677,
"learning_rate": 5.470048244069055e-06,
"loss": 0.0771,
"step": 370
},
{
"epoch": 1.617678381256656,
"grad_norm": 0.668818900512361,
"learning_rate": 5.222909798804515e-06,
"loss": 0.0766,
"step": 380
},
{
"epoch": 1.6602768903088392,
"grad_norm": 0.9193125817511787,
"learning_rate": 4.975224134091551e-06,
"loss": 0.0717,
"step": 390
},
{
"epoch": 1.7028753993610224,
"grad_norm": 0.615193996483177,
"learning_rate": 4.727599291449887e-06,
"loss": 0.0845,
"step": 400
},
{
"epoch": 1.7454739084132056,
"grad_norm": 0.6604596855515968,
"learning_rate": 4.480643163087644e-06,
"loss": 0.0717,
"step": 410
},
{
"epoch": 1.7880724174653886,
"grad_norm": 1.2030577374834739,
"learning_rate": 4.234961999591706e-06,
"loss": 0.0789,
"step": 420
},
{
"epoch": 1.830670926517572,
"grad_norm": 0.7106477349898497,
"learning_rate": 3.991158921648096e-06,
"loss": 0.0795,
"step": 430
},
{
"epoch": 1.873269435569755,
"grad_norm": 1.0462717462476079,
"learning_rate": 3.7498324394459253e-06,
"loss": 0.0718,
"step": 440
},
{
"epoch": 1.9158679446219382,
"grad_norm": 0.7333608814823522,
"learning_rate": 3.511574983399599e-06,
"loss": 0.0592,
"step": 450
},
{
"epoch": 1.9584664536741214,
"grad_norm": 0.7101356242832322,
"learning_rate": 3.2769714497962235e-06,
"loss": 0.0631,
"step": 460
},
{
"epoch": 2.0,
"grad_norm": 0.7020066069562629,
"learning_rate": 3.0465977649384813e-06,
"loss": 0.0568,
"step": 470
},
{
"epoch": 2.042598509052183,
"grad_norm": 0.6143078466051928,
"learning_rate": 2.8210194713078408e-06,
"loss": 0.0342,
"step": 480
},
{
"epoch": 2.0851970181043664,
"grad_norm": 0.6960923290338111,
"learning_rate": 2.600790339218926e-06,
"loss": 0.029,
"step": 490
},
{
"epoch": 2.1277955271565494,
"grad_norm": 0.9794654564748295,
"learning_rate": 2.3864510073732914e-06,
"loss": 0.0317,
"step": 500
},
{
"epoch": 2.170394036208733,
"grad_norm": 0.6109166519427666,
"learning_rate": 2.178527655649868e-06,
"loss": 0.0308,
"step": 510
},
{
"epoch": 2.212992545260916,
"grad_norm": 0.6909646211341572,
"learning_rate": 1.977530713390281e-06,
"loss": 0.0287,
"step": 520
},
{
"epoch": 2.255591054313099,
"grad_norm": 0.6589603986660724,
"learning_rate": 1.783953606350005e-06,
"loss": 0.0284,
"step": 530
},
{
"epoch": 2.2981895633652822,
"grad_norm": 0.6418548129511306,
"learning_rate": 1.5982715453915082e-06,
"loss": 0.0282,
"step": 540
},
{
"epoch": 2.3407880724174652,
"grad_norm": 0.6688667188008208,
"learning_rate": 1.4209403598929711e-06,
"loss": 0.0298,
"step": 550
},
{
"epoch": 2.3833865814696487,
"grad_norm": 0.7442269287548521,
"learning_rate": 1.2523953787364723e-06,
"loss": 0.0269,
"step": 560
},
{
"epoch": 2.4259850905218316,
"grad_norm": 0.6780001132564086,
"learning_rate": 1.0930503616226495e-06,
"loss": 0.0258,
"step": 570
},
{
"epoch": 2.468583599574015,
"grad_norm": 0.6994808194521467,
"learning_rate": 9.432964833353947e-07,
"loss": 0.0285,
"step": 580
},
{
"epoch": 2.511182108626198,
"grad_norm": 0.6396237745490303,
"learning_rate": 8.035013734500557e-07,
"loss": 0.0304,
"step": 590
},
{
"epoch": 2.553780617678381,
"grad_norm": 0.8456007385218226,
"learning_rate": 6.740082138425963e-07,
"loss": 0.0284,
"step": 600
},
{
"epoch": 2.5963791267305645,
"grad_norm": 0.6627352659197506,
"learning_rate": 5.551348962151965e-07,
"loss": 0.0249,
"step": 610
},
{
"epoch": 2.6389776357827475,
"grad_norm": 0.5102316456936122,
"learning_rate": 4.471732417065144e-07,
"loss": 0.0227,
"step": 620
},
{
"epoch": 2.681576144834931,
"grad_norm": 0.7802646932680122,
"learning_rate": 3.5038828450233874e-07,
"loss": 0.0229,
"step": 630
},
{
"epoch": 2.724174653887114,
"grad_norm": 0.5730030349099514,
"learning_rate": 2.65017621205339e-07,
"loss": 0.025,
"step": 640
},
{
"epoch": 2.7667731629392973,
"grad_norm": 0.6632255868965671,
"learning_rate": 1.9127082756109138e-07,
"loss": 0.0281,
"step": 650
},
{
"epoch": 2.8093716719914803,
"grad_norm": 0.797692366915009,
"learning_rate": 1.293289439722961e-07,
"loss": 0.0222,
"step": 660
},
{
"epoch": 2.8519701810436633,
"grad_norm": 0.6808158703012352,
"learning_rate": 7.934403106416245e-08,
"loss": 0.0249,
"step": 670
},
{
"epoch": 2.8945686900958467,
"grad_norm": 0.6210288358669318,
"learning_rate": 4.1438796392025416e-08,
"loss": 0.0221,
"step": 680
},
{
"epoch": 2.9371671991480297,
"grad_norm": 0.6568231883800221,
"learning_rate": 1.5706293207561896e-08,
"loss": 0.0227,
"step": 690
},
{
"epoch": 2.979765708200213,
"grad_norm": 0.5276073549263733,
"learning_rate": 2.209692023126819e-09,
"loss": 0.0223,
"step": 700
},
{
"epoch": 3.0,
"step": 705,
"total_flos": 629471101583360.0,
"train_loss": 0.1980447881822045,
"train_runtime": 15010.1192,
"train_samples_per_second": 3.003,
"train_steps_per_second": 0.047
}
],
"logging_steps": 10,
"max_steps": 705,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 629471101583360.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}