| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9944232462577047, | |
| "eval_steps": 500, | |
| "global_step": 1275, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023481068388611682, | |
| "grad_norm": 17.85382376485096, | |
| "learning_rate": 5e-06, | |
| "loss": 0.9488, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.046962136777223364, | |
| "grad_norm": 3.177756281658111, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8343, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07044320516583505, | |
| "grad_norm": 2.950019754054781, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7651, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09392427355444673, | |
| "grad_norm": 1.450856517854765, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7374, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1174053419430584, | |
| "grad_norm": 0.8091667434976095, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7161, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1408864103316701, | |
| "grad_norm": 0.8253122020905036, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6935, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16436747872028176, | |
| "grad_norm": 0.6338190868455624, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6718, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18784854710889345, | |
| "grad_norm": 0.8143184435680945, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6635, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21132961549750515, | |
| "grad_norm": 0.7202907234528798, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6581, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2348106838861168, | |
| "grad_norm": 0.9812703695297975, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6595, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2582917522747285, | |
| "grad_norm": 0.6403918144312425, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6511, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2817728206633402, | |
| "grad_norm": 0.6355110618738598, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6443, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3052538890519519, | |
| "grad_norm": 0.8767568074879388, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6457, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3287349574405635, | |
| "grad_norm": 0.7912634151639979, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6352, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3522160258291752, | |
| "grad_norm": 0.6346769190072642, | |
| "learning_rate": 5e-06, | |
| "loss": 0.642, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3756970942177869, | |
| "grad_norm": 0.6538804073841475, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6453, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3991781626063986, | |
| "grad_norm": 0.524677402567732, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6375, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4226592309950103, | |
| "grad_norm": 0.6983299832658841, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6404, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.44614029938362193, | |
| "grad_norm": 0.5730458718423643, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6282, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4696213677722336, | |
| "grad_norm": 0.5795935762469521, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6258, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4931024361608453, | |
| "grad_norm": 0.6568013132353124, | |
| "learning_rate": 5e-06, | |
| "loss": 0.633, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.516583504549457, | |
| "grad_norm": 0.625002257246399, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6215, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5400645729380686, | |
| "grad_norm": 0.5866557972006909, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6192, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5635456413266804, | |
| "grad_norm": 0.5523814224922182, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6225, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.587026709715292, | |
| "grad_norm": 0.621565965520602, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6176, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6105077781039038, | |
| "grad_norm": 0.5699863716830831, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6184, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6339888464925154, | |
| "grad_norm": 0.5867908049315175, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6214, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.657469914881127, | |
| "grad_norm": 1.0031834057307554, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6204, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6809509832697388, | |
| "grad_norm": 0.5739527115683025, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6166, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7044320516583504, | |
| "grad_norm": 0.6047949935557967, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6096, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7279131200469622, | |
| "grad_norm": 0.5141588768585372, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6076, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7513941884355738, | |
| "grad_norm": 0.689840031854037, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6115, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7748752568241855, | |
| "grad_norm": 0.7551629396423358, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6138, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7983563252127972, | |
| "grad_norm": 0.5356794354442618, | |
| "learning_rate": 5e-06, | |
| "loss": 0.611, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8218373936014088, | |
| "grad_norm": 0.6083117103787592, | |
| "learning_rate": 5e-06, | |
| "loss": 0.611, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8453184619900206, | |
| "grad_norm": 0.7034174178117553, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6104, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8687995303786322, | |
| "grad_norm": 0.5650614816783488, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6047, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8922805987672439, | |
| "grad_norm": 0.6449034585856688, | |
| "learning_rate": 5e-06, | |
| "loss": 0.613, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.9157616671558556, | |
| "grad_norm": 0.6460327839123797, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6104, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9392427355444672, | |
| "grad_norm": 0.6977465772968938, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6124, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.962723803933079, | |
| "grad_norm": 0.6646492018550946, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5957, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9862048723216906, | |
| "grad_norm": 0.48972085408134464, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5979, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9979454065159965, | |
| "eval_loss": 0.6003177165985107, | |
| "eval_runtime": 300.5123, | |
| "eval_samples_per_second": 38.181, | |
| "eval_steps_per_second": 0.599, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.0099794540651599, | |
| "grad_norm": 0.8929971915551214, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6046, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.0334605224537716, | |
| "grad_norm": 0.6204797689157823, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5525, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0569415908423834, | |
| "grad_norm": 0.629777186945133, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5507, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0804226592309951, | |
| "grad_norm": 0.6177917289848706, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5488, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.1039037276196066, | |
| "grad_norm": 0.616801854556511, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5553, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.1273847960082184, | |
| "grad_norm": 0.6202115496799256, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5517, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1508658643968301, | |
| "grad_norm": 0.6869810211842367, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5513, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1743469327854417, | |
| "grad_norm": 0.6134525997635181, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5565, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.1978280011740534, | |
| "grad_norm": 0.6533976679541116, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5508, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.2213090695626652, | |
| "grad_norm": 0.7384172080803894, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5513, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2447901379512767, | |
| "grad_norm": 0.6446266722666449, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5538, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2682712063398884, | |
| "grad_norm": 0.6920463607543151, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5442, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.2917522747285002, | |
| "grad_norm": 0.7090350057008448, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5566, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.3152333431171117, | |
| "grad_norm": 0.7226606579176621, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5494, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.3387144115057235, | |
| "grad_norm": 0.5484819340890661, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5471, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.3621954798943352, | |
| "grad_norm": 0.6982064642691793, | |
| "learning_rate": 5e-06, | |
| "loss": 0.552, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.385676548282947, | |
| "grad_norm": 0.6147097813447182, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5505, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.4091576166715585, | |
| "grad_norm": 0.6598577111107449, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5498, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.4326386850601702, | |
| "grad_norm": 0.5603317744558156, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5562, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.456119753448782, | |
| "grad_norm": 0.6373670868271739, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5555, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4796008218373937, | |
| "grad_norm": 0.5932324800613761, | |
| "learning_rate": 5e-06, | |
| "loss": 0.544, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.5030818902260052, | |
| "grad_norm": 0.5227721794518003, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5451, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.526562958614617, | |
| "grad_norm": 0.6093734754379218, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5587, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.5500440270032287, | |
| "grad_norm": 0.6287567431322201, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5518, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5735250953918403, | |
| "grad_norm": 0.6541153306269628, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5526, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.597006163780452, | |
| "grad_norm": 0.6150418746443832, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5478, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.6204872321690638, | |
| "grad_norm": 0.5475396144251581, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5481, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.6439683005576753, | |
| "grad_norm": 0.6160254516028266, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5515, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.667449368946287, | |
| "grad_norm": 0.843962487015559, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5505, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.6909304373348988, | |
| "grad_norm": 0.5347960520186497, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5496, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.7144115057235103, | |
| "grad_norm": 0.7323294593212619, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5484, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.737892574112122, | |
| "grad_norm": 0.5476336095439653, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5483, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.7613736425007338, | |
| "grad_norm": 0.6011568410465314, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5531, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7848547108893453, | |
| "grad_norm": 0.6797212856687878, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5487, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.8083357792779573, | |
| "grad_norm": 0.5819194256052239, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5485, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.8318168476665688, | |
| "grad_norm": 0.5292485271089171, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5518, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.8552979160551804, | |
| "grad_norm": 0.5799939542823142, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5467, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.8787789844437923, | |
| "grad_norm": 0.5570487573376319, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5468, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.9022600528324038, | |
| "grad_norm": 0.6174505205210491, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5488, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.9257411212210156, | |
| "grad_norm": 0.5693760728585585, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5458, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.9492221896096273, | |
| "grad_norm": 0.5189329244004007, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5447, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.9727032579982389, | |
| "grad_norm": 0.6238194647054416, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5398, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.9961843263868506, | |
| "grad_norm": 0.5651058414473042, | |
| "learning_rate": 5e-06, | |
| "loss": 0.547, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.9985324332257117, | |
| "eval_loss": 0.5846751928329468, | |
| "eval_runtime": 295.576, | |
| "eval_samples_per_second": 38.819, | |
| "eval_steps_per_second": 0.609, | |
| "step": 851 | |
| }, | |
| { | |
| "epoch": 2.0199589081303198, | |
| "grad_norm": 0.6946392563773179, | |
| "learning_rate": 5e-06, | |
| "loss": 0.523, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.0434399765189317, | |
| "grad_norm": 0.8362364731068118, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4924, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.0669210449075432, | |
| "grad_norm": 0.7772390407263537, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4902, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.0904021132961548, | |
| "grad_norm": 0.5219899057565048, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4955, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.1138831816847667, | |
| "grad_norm": 0.6541702370902746, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4969, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.1373642500733783, | |
| "grad_norm": 0.5786919167953266, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4865, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.1608453184619902, | |
| "grad_norm": 0.6257190526717714, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4966, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.1843263868506018, | |
| "grad_norm": 0.6070724867911851, | |
| "learning_rate": 5e-06, | |
| "loss": 0.497, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.2078074552392133, | |
| "grad_norm": 0.7626194518667021, | |
| "learning_rate": 5e-06, | |
| "loss": 0.498, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.2312885236278253, | |
| "grad_norm": 0.66208678281747, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4978, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.254769592016437, | |
| "grad_norm": 0.597091889958803, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4954, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.2782506604050483, | |
| "grad_norm": 0.648113572619813, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5024, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.3017317287936603, | |
| "grad_norm": 0.5800444078314209, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4982, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.325212797182272, | |
| "grad_norm": 0.5914333960587344, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4994, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.3486938655708833, | |
| "grad_norm": 0.7924399848654731, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5002, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.3721749339594953, | |
| "grad_norm": 0.624856284950558, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4994, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.395656002348107, | |
| "grad_norm": 0.6655834278053183, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4906, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.4191370707367184, | |
| "grad_norm": 0.5518645145037842, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4975, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.4426181391253303, | |
| "grad_norm": 0.5785599308848968, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4976, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.466099207513942, | |
| "grad_norm": 0.5834274439157257, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5052, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.4895802759025534, | |
| "grad_norm": 0.777173362933167, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4989, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.5130613442911653, | |
| "grad_norm": 0.929125527693667, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5059, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.536542412679777, | |
| "grad_norm": 0.6950708275354937, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4946, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.560023481068389, | |
| "grad_norm": 0.5542934300294031, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5086, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.5835045494570004, | |
| "grad_norm": 0.7961833486998505, | |
| "learning_rate": 5e-06, | |
| "loss": 0.498, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.606985617845612, | |
| "grad_norm": 0.6237039054057065, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4998, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.6304666862342234, | |
| "grad_norm": 0.5833433757118394, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4944, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.6539477546228354, | |
| "grad_norm": 0.5868493372745182, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5028, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.677428823011447, | |
| "grad_norm": 0.6399452879323836, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4982, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.700909891400059, | |
| "grad_norm": 0.6458178037380802, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5009, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.7243909597886704, | |
| "grad_norm": 0.5439040913583559, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5012, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.747872028177282, | |
| "grad_norm": 0.735794966069211, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5032, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.771353096565894, | |
| "grad_norm": 0.601851566145536, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5033, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.7948341649545054, | |
| "grad_norm": 0.5929336883777777, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5037, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.818315233343117, | |
| "grad_norm": 0.5778177618943612, | |
| "learning_rate": 5e-06, | |
| "loss": 0.508, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.841796301731729, | |
| "grad_norm": 0.5990753577226628, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4957, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.8652773701203404, | |
| "grad_norm": 0.7825195485986434, | |
| "learning_rate": 5e-06, | |
| "loss": 0.499, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.888758438508952, | |
| "grad_norm": 0.5698945641530911, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4982, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.912239506897564, | |
| "grad_norm": 0.5941997062897303, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5006, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.9357205752861755, | |
| "grad_norm": 0.5494008699329855, | |
| "learning_rate": 5e-06, | |
| "loss": 0.494, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.9592016436747874, | |
| "grad_norm": 0.6295305801304111, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5001, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.982682712063399, | |
| "grad_norm": 0.6627594327431557, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5003, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.9944232462577047, | |
| "eval_loss": 0.5840933322906494, | |
| "eval_runtime": 292.1509, | |
| "eval_samples_per_second": 39.274, | |
| "eval_steps_per_second": 0.616, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 2.9944232462577047, | |
| "step": 1275, | |
| "total_flos": 2135463108280320.0, | |
| "train_loss": 0.5660238438026578, | |
| "train_runtime": 41769.8593, | |
| "train_samples_per_second": 15.658, | |
| "train_steps_per_second": 0.031 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1275, | |
| "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": 2135463108280320.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |