| { | |
| "best_global_step": 244, | |
| "best_metric": 0.24269719421863556, | |
| "best_model_checkpoint": "./lora_qwen7b_java_abdiff_v1/checkpoint-244", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 732, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.041109969167523124, | |
| "grad_norm": 0.175823375582695, | |
| "learning_rate": 3.648648648648649e-06, | |
| "loss": 0.5537, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08221993833504625, | |
| "grad_norm": 0.12845267355442047, | |
| "learning_rate": 7.702702702702703e-06, | |
| "loss": 0.5427, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12332990750256938, | |
| "grad_norm": 0.13613902032375336, | |
| "learning_rate": 1.1756756756756757e-05, | |
| "loss": 0.5252, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1644398766700925, | |
| "grad_norm": 0.23862598836421967, | |
| "learning_rate": 1.5810810810810808e-05, | |
| "loss": 0.4838, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.20554984583761562, | |
| "grad_norm": 0.2705032229423523, | |
| "learning_rate": 1.9864864864864866e-05, | |
| "loss": 0.395, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24665981500513876, | |
| "grad_norm": 0.10224032402038574, | |
| "learning_rate": 2.3918918918918917e-05, | |
| "loss": 0.3266, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.28776978417266186, | |
| "grad_norm": 0.06852829456329346, | |
| "learning_rate": 2.7972972972972975e-05, | |
| "loss": 0.2972, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.328879753340185, | |
| "grad_norm": 0.0726822167634964, | |
| "learning_rate": 2.9772036474164135e-05, | |
| "loss": 0.2954, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3699897225077081, | |
| "grad_norm": 0.06372971087694168, | |
| "learning_rate": 2.9316109422492404e-05, | |
| "loss": 0.277, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.41109969167523125, | |
| "grad_norm": 0.05797314643859863, | |
| "learning_rate": 2.886018237082067e-05, | |
| "loss": 0.2666, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4522096608427544, | |
| "grad_norm": 0.062011413276195526, | |
| "learning_rate": 2.8404255319148935e-05, | |
| "loss": 0.2726, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4933196300102775, | |
| "grad_norm": 0.06568919867277145, | |
| "learning_rate": 2.7948328267477204e-05, | |
| "loss": 0.2705, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5344295991778006, | |
| "grad_norm": 0.06438654661178589, | |
| "learning_rate": 2.7492401215805473e-05, | |
| "loss": 0.2489, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5755395683453237, | |
| "grad_norm": 0.0740242451429367, | |
| "learning_rate": 2.7036474164133738e-05, | |
| "loss": 0.2513, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6166495375128469, | |
| "grad_norm": 0.0648876503109932, | |
| "learning_rate": 2.6580547112462007e-05, | |
| "loss": 0.2418, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.65775950668037, | |
| "grad_norm": 0.0961170569062233, | |
| "learning_rate": 2.6124620060790272e-05, | |
| "loss": 0.2444, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6988694758478932, | |
| "grad_norm": 0.07387962192296982, | |
| "learning_rate": 2.566869300911854e-05, | |
| "loss": 0.245, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7399794450154162, | |
| "grad_norm": 0.0894966870546341, | |
| "learning_rate": 2.521276595744681e-05, | |
| "loss": 0.237, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7810894141829393, | |
| "grad_norm": 0.09798130393028259, | |
| "learning_rate": 2.4756838905775076e-05, | |
| "loss": 0.2486, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8221993833504625, | |
| "grad_norm": 0.14110679924488068, | |
| "learning_rate": 2.4300911854103345e-05, | |
| "loss": 0.2421, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8633093525179856, | |
| "grad_norm": 0.09954896569252014, | |
| "learning_rate": 2.3844984802431613e-05, | |
| "loss": 0.2265, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9044193216855088, | |
| "grad_norm": 0.1187966987490654, | |
| "learning_rate": 2.338905775075988e-05, | |
| "loss": 0.2277, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9455292908530318, | |
| "grad_norm": 0.11565206199884415, | |
| "learning_rate": 2.2933130699088144e-05, | |
| "loss": 0.2123, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.986639260020555, | |
| "grad_norm": 0.13377656042575836, | |
| "learning_rate": 2.2477203647416413e-05, | |
| "loss": 0.2153, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.24269719421863556, | |
| "eval_runtime": 48.0797, | |
| "eval_samples_per_second": 13.561, | |
| "eval_steps_per_second": 6.78, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 1.024665981500514, | |
| "grad_norm": 0.1225612610578537, | |
| "learning_rate": 2.2021276595744682e-05, | |
| "loss": 0.2103, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.065775950668037, | |
| "grad_norm": 0.13030505180358887, | |
| "learning_rate": 2.156534954407295e-05, | |
| "loss": 0.1987, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.10688591983556, | |
| "grad_norm": 0.18434269726276398, | |
| "learning_rate": 2.1109422492401216e-05, | |
| "loss": 0.2066, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.1479958890030832, | |
| "grad_norm": 0.16637080907821655, | |
| "learning_rate": 2.0653495440729482e-05, | |
| "loss": 0.1856, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.1891058581706064, | |
| "grad_norm": 0.2880594730377197, | |
| "learning_rate": 2.019756838905775e-05, | |
| "loss": 0.1776, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.2302158273381294, | |
| "grad_norm": 0.19819965958595276, | |
| "learning_rate": 1.974164133738602e-05, | |
| "loss": 0.183, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.2713257965056526, | |
| "grad_norm": 0.2154921293258667, | |
| "learning_rate": 1.928571428571429e-05, | |
| "loss": 0.1866, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.3124357656731758, | |
| "grad_norm": 0.23189011216163635, | |
| "learning_rate": 1.8829787234042554e-05, | |
| "loss": 0.1647, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.353545734840699, | |
| "grad_norm": 0.3233238160610199, | |
| "learning_rate": 1.837386018237082e-05, | |
| "loss": 0.165, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.394655704008222, | |
| "grad_norm": 0.2513398826122284, | |
| "learning_rate": 1.7917933130699088e-05, | |
| "loss": 0.1634, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.435765673175745, | |
| "grad_norm": 0.2593567669391632, | |
| "learning_rate": 1.7462006079027357e-05, | |
| "loss": 0.1493, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.4768756423432683, | |
| "grad_norm": 0.271638959646225, | |
| "learning_rate": 1.7006079027355622e-05, | |
| "loss": 0.1479, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.5179856115107913, | |
| "grad_norm": 0.39938974380493164, | |
| "learning_rate": 1.655015197568389e-05, | |
| "loss": 0.1378, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.5590955806783144, | |
| "grad_norm": 0.295703649520874, | |
| "learning_rate": 1.609422492401216e-05, | |
| "loss": 0.1308, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.6002055498458376, | |
| "grad_norm": 0.36513808369636536, | |
| "learning_rate": 1.5638297872340426e-05, | |
| "loss": 0.1365, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.6413155190133608, | |
| "grad_norm": 0.3656638264656067, | |
| "learning_rate": 1.5182370820668691e-05, | |
| "loss": 0.1331, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.682425488180884, | |
| "grad_norm": 0.3298315703868866, | |
| "learning_rate": 1.4726443768996962e-05, | |
| "loss": 0.1225, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.723535457348407, | |
| "grad_norm": 0.32461678981781006, | |
| "learning_rate": 1.4270516717325229e-05, | |
| "loss": 0.1275, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.7646454265159301, | |
| "grad_norm": 0.34484782814979553, | |
| "learning_rate": 1.3814589665653496e-05, | |
| "loss": 0.106, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.8057553956834531, | |
| "grad_norm": 0.3689672350883484, | |
| "learning_rate": 1.3358662613981763e-05, | |
| "loss": 0.1263, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.8468653648509763, | |
| "grad_norm": 0.3288673460483551, | |
| "learning_rate": 1.2902735562310032e-05, | |
| "loss": 0.1109, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.8879753340184995, | |
| "grad_norm": 0.44610464572906494, | |
| "learning_rate": 1.2446808510638298e-05, | |
| "loss": 0.0947, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.9290853031860227, | |
| "grad_norm": 0.40308764576911926, | |
| "learning_rate": 1.1990881458966566e-05, | |
| "loss": 0.1079, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.9701952723535459, | |
| "grad_norm": 0.373699814081192, | |
| "learning_rate": 1.1534954407294832e-05, | |
| "loss": 0.1024, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.2866329252719879, | |
| "eval_runtime": 47.8166, | |
| "eval_samples_per_second": 13.635, | |
| "eval_steps_per_second": 6.818, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 2.0082219938335046, | |
| "grad_norm": 0.4223463237285614, | |
| "learning_rate": 1.10790273556231e-05, | |
| "loss": 0.0966, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.049331963001028, | |
| "grad_norm": 0.47280973196029663, | |
| "learning_rate": 1.0623100303951368e-05, | |
| "loss": 0.0964, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.090441932168551, | |
| "grad_norm": 0.3964370787143707, | |
| "learning_rate": 1.0167173252279635e-05, | |
| "loss": 0.0793, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.131551901336074, | |
| "grad_norm": 0.3224450349807739, | |
| "learning_rate": 9.711246200607902e-06, | |
| "loss": 0.0882, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.172661870503597, | |
| "grad_norm": 0.3572905659675598, | |
| "learning_rate": 9.255319148936171e-06, | |
| "loss": 0.0942, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.21377183967112, | |
| "grad_norm": 0.33426856994628906, | |
| "learning_rate": 8.799392097264438e-06, | |
| "loss": 0.0817, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.2548818088386433, | |
| "grad_norm": 0.4117780327796936, | |
| "learning_rate": 8.343465045592705e-06, | |
| "loss": 0.0929, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.2959917780061665, | |
| "grad_norm": 0.3415227234363556, | |
| "learning_rate": 7.887537993920974e-06, | |
| "loss": 0.0736, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.3371017471736897, | |
| "grad_norm": 0.40296557545661926, | |
| "learning_rate": 7.43161094224924e-06, | |
| "loss": 0.0773, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.378211716341213, | |
| "grad_norm": 0.4592924416065216, | |
| "learning_rate": 6.975683890577508e-06, | |
| "loss": 0.0723, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.419321685508736, | |
| "grad_norm": 0.3444889783859253, | |
| "learning_rate": 6.519756838905775e-06, | |
| "loss": 0.0804, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.460431654676259, | |
| "grad_norm": 0.3752576410770416, | |
| "learning_rate": 6.063829787234042e-06, | |
| "loss": 0.0703, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.501541623843782, | |
| "grad_norm": 0.37996989488601685, | |
| "learning_rate": 5.607902735562311e-06, | |
| "loss": 0.0742, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.542651593011305, | |
| "grad_norm": 0.3391105532646179, | |
| "learning_rate": 5.151975683890578e-06, | |
| "loss": 0.0673, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.5837615621788284, | |
| "grad_norm": 0.4533815085887909, | |
| "learning_rate": 4.696048632218845e-06, | |
| "loss": 0.0753, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.6248715313463515, | |
| "grad_norm": 0.45329344272613525, | |
| "learning_rate": 4.240121580547112e-06, | |
| "loss": 0.0692, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.6659815005138747, | |
| "grad_norm": 0.3419000506401062, | |
| "learning_rate": 3.7841945288753804e-06, | |
| "loss": 0.0673, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.707091469681398, | |
| "grad_norm": 0.31973302364349365, | |
| "learning_rate": 3.3282674772036475e-06, | |
| "loss": 0.0775, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.7482014388489207, | |
| "grad_norm": 0.3348669707775116, | |
| "learning_rate": 2.872340425531915e-06, | |
| "loss": 0.0627, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.789311408016444, | |
| "grad_norm": 0.4823591113090515, | |
| "learning_rate": 2.4164133738601823e-06, | |
| "loss": 0.0709, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.830421377183967, | |
| "grad_norm": 0.31249356269836426, | |
| "learning_rate": 1.96048632218845e-06, | |
| "loss": 0.0746, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.87153134635149, | |
| "grad_norm": 0.3754122257232666, | |
| "learning_rate": 1.5045592705167174e-06, | |
| "loss": 0.0682, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.9126413155190134, | |
| "grad_norm": 0.34814003109931946, | |
| "learning_rate": 1.0486322188449848e-06, | |
| "loss": 0.07, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.9537512846865366, | |
| "grad_norm": 0.38488245010375977, | |
| "learning_rate": 5.927051671732523e-07, | |
| "loss": 0.0644, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.9948612538540598, | |
| "grad_norm": 0.2890647053718567, | |
| "learning_rate": 1.3677811550151974e-07, | |
| "loss": 0.0744, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.3053460121154785, | |
| "eval_runtime": 47.839, | |
| "eval_samples_per_second": 13.629, | |
| "eval_steps_per_second": 6.815, | |
| "step": 732 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 732, | |
| "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": 9.438141914069729e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |