{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 1205, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0008298755186721991, "grad_norm": 23.66355396613384, "learning_rate": 8.264462809917357e-08, "loss": 1.4427, "step": 1 }, { "epoch": 0.004149377593360996, "grad_norm": 23.666427649458576, "learning_rate": 4.132231404958678e-07, "loss": 1.4251, "step": 5 }, { "epoch": 0.008298755186721992, "grad_norm": 8.13472184690251, "learning_rate": 8.264462809917356e-07, "loss": 1.3136, "step": 10 }, { "epoch": 0.012448132780082987, "grad_norm": 10.227426110416495, "learning_rate": 1.2396694214876035e-06, "loss": 1.1782, "step": 15 }, { "epoch": 0.016597510373443983, "grad_norm": 2.9983433935088764, "learning_rate": 1.6528925619834712e-06, "loss": 1.0153, "step": 20 }, { "epoch": 0.02074688796680498, "grad_norm": 2.7990610124740405, "learning_rate": 2.066115702479339e-06, "loss": 0.9803, "step": 25 }, { "epoch": 0.024896265560165973, "grad_norm": 2.4757391776519464, "learning_rate": 2.479338842975207e-06, "loss": 0.9414, "step": 30 }, { "epoch": 0.029045643153526972, "grad_norm": 2.369524052256136, "learning_rate": 2.8925619834710743e-06, "loss": 0.9136, "step": 35 }, { "epoch": 0.03319502074688797, "grad_norm": 2.2685836127457777, "learning_rate": 3.3057851239669424e-06, "loss": 0.9046, "step": 40 }, { "epoch": 0.03734439834024896, "grad_norm": 2.280617723317066, "learning_rate": 3.71900826446281e-06, "loss": 0.8837, "step": 45 }, { "epoch": 0.04149377593360996, "grad_norm": 2.5321104543831545, "learning_rate": 4.132231404958678e-06, "loss": 0.8832, "step": 50 }, { "epoch": 0.04564315352697095, "grad_norm": 2.431703080743525, "learning_rate": 4.5454545454545455e-06, "loss": 0.8805, "step": 55 }, { "epoch": 0.04979253112033195, "grad_norm": 2.3196841399300054, "learning_rate": 4.958677685950414e-06, "loss": 0.8701, "step": 60 }, { "epoch": 0.05394190871369295, "grad_norm": 2.3618202415732195, "learning_rate": 5.371900826446281e-06, "loss": 0.8579, "step": 65 }, { "epoch": 0.058091286307053944, "grad_norm": 2.3717003204055405, "learning_rate": 5.785123966942149e-06, "loss": 0.8505, "step": 70 }, { "epoch": 0.06224066390041494, "grad_norm": 2.524204535368378, "learning_rate": 6.198347107438017e-06, "loss": 0.8402, "step": 75 }, { "epoch": 0.06639004149377593, "grad_norm": 2.4015926775695804, "learning_rate": 6.611570247933885e-06, "loss": 0.8402, "step": 80 }, { "epoch": 0.07053941908713693, "grad_norm": 2.388794422413219, "learning_rate": 7.0247933884297525e-06, "loss": 0.8355, "step": 85 }, { "epoch": 0.07468879668049792, "grad_norm": 2.4148605854925704, "learning_rate": 7.43801652892562e-06, "loss": 0.8256, "step": 90 }, { "epoch": 0.07883817427385892, "grad_norm": 2.4479657967512414, "learning_rate": 7.851239669421489e-06, "loss": 0.8126, "step": 95 }, { "epoch": 0.08298755186721991, "grad_norm": 2.4560082465511863, "learning_rate": 8.264462809917356e-06, "loss": 0.8226, "step": 100 }, { "epoch": 0.08713692946058091, "grad_norm": 2.3573417388565976, "learning_rate": 8.677685950413224e-06, "loss": 0.8175, "step": 105 }, { "epoch": 0.0912863070539419, "grad_norm": 2.468662387879913, "learning_rate": 9.090909090909091e-06, "loss": 0.8158, "step": 110 }, { "epoch": 0.0954356846473029, "grad_norm": 2.5046573038316837, "learning_rate": 9.50413223140496e-06, "loss": 0.8116, "step": 115 }, { "epoch": 0.0995850622406639, "grad_norm": 2.539643690091556, "learning_rate": 9.917355371900828e-06, "loss": 0.8005, "step": 120 }, { "epoch": 0.1037344398340249, "grad_norm": 2.911760533276573, "learning_rate": 9.999664033241933e-06, "loss": 0.7939, "step": 125 }, { "epoch": 0.1078838174273859, "grad_norm": 2.582851539753205, "learning_rate": 9.9982992456671e-06, "loss": 0.8055, "step": 130 }, { "epoch": 0.11203319502074689, "grad_norm": 2.4256847202133356, "learning_rate": 9.99588492570789e-06, "loss": 0.7868, "step": 135 }, { "epoch": 0.11618257261410789, "grad_norm": 2.363704333423417, "learning_rate": 9.992421580318146e-06, "loss": 0.7931, "step": 140 }, { "epoch": 0.12033195020746888, "grad_norm": 2.5814735842129646, "learning_rate": 9.98790993672386e-06, "loss": 0.792, "step": 145 }, { "epoch": 0.12448132780082988, "grad_norm": 2.3697758205953496, "learning_rate": 9.982350942270482e-06, "loss": 0.7803, "step": 150 }, { "epoch": 0.12863070539419086, "grad_norm": 2.715505233595166, "learning_rate": 9.975745764224003e-06, "loss": 0.7801, "step": 155 }, { "epoch": 0.13278008298755187, "grad_norm": 2.408139672943199, "learning_rate": 9.968095789525844e-06, "loss": 0.7752, "step": 160 }, { "epoch": 0.13692946058091288, "grad_norm": 2.6010481805450576, "learning_rate": 9.959402624501636e-06, "loss": 0.7643, "step": 165 }, { "epoch": 0.14107883817427386, "grad_norm": 2.296000230707304, "learning_rate": 9.949668094523923e-06, "loss": 0.7693, "step": 170 }, { "epoch": 0.14522821576763487, "grad_norm": 2.3353134794630943, "learning_rate": 9.938894243628876e-06, "loss": 0.76, "step": 175 }, { "epoch": 0.14937759336099585, "grad_norm": 2.4548337376467226, "learning_rate": 9.927083334087095e-06, "loss": 0.7553, "step": 180 }, { "epoch": 0.15352697095435686, "grad_norm": 2.4799784321191325, "learning_rate": 9.914237845928574e-06, "loss": 0.7466, "step": 185 }, { "epoch": 0.15767634854771784, "grad_norm": 2.3334152911020754, "learning_rate": 9.900360476421953e-06, "loss": 0.7469, "step": 190 }, { "epoch": 0.16182572614107885, "grad_norm": 2.8513960305920065, "learning_rate": 9.885454139508156e-06, "loss": 0.7478, "step": 195 }, { "epoch": 0.16597510373443983, "grad_norm": 2.3540844011309288, "learning_rate": 9.869521965188516e-06, "loss": 0.7419, "step": 200 }, { "epoch": 0.17012448132780084, "grad_norm": 2.4949727451490458, "learning_rate": 9.852567298867557e-06, "loss": 0.7443, "step": 205 }, { "epoch": 0.17427385892116182, "grad_norm": 2.4359748708393196, "learning_rate": 9.83459370065053e-06, "loss": 0.715, "step": 210 }, { "epoch": 0.17842323651452283, "grad_norm": 2.194244707564717, "learning_rate": 9.815604944595856e-06, "loss": 0.732, "step": 215 }, { "epoch": 0.1825726141078838, "grad_norm": 2.3813196851718668, "learning_rate": 9.79560501792268e-06, "loss": 0.7133, "step": 220 }, { "epoch": 0.18672199170124482, "grad_norm": 2.323752421674217, "learning_rate": 9.774598120173625e-06, "loss": 0.7241, "step": 225 }, { "epoch": 0.1908713692946058, "grad_norm": 2.3526306711964797, "learning_rate": 9.752588662332986e-06, "loss": 0.7043, "step": 230 }, { "epoch": 0.1950207468879668, "grad_norm": 2.2642342063534096, "learning_rate": 9.729581265900524e-06, "loss": 0.7103, "step": 235 }, { "epoch": 0.1991701244813278, "grad_norm": 2.516182372123314, "learning_rate": 9.70558076192105e-06, "loss": 0.7267, "step": 240 }, { "epoch": 0.2033195020746888, "grad_norm": 2.370762773316826, "learning_rate": 9.680592189970015e-06, "loss": 0.7123, "step": 245 }, { "epoch": 0.2074688796680498, "grad_norm": 2.207456321652819, "learning_rate": 9.654620797095307e-06, "loss": 0.6962, "step": 250 }, { "epoch": 0.21161825726141079, "grad_norm": 2.2364777487963643, "learning_rate": 9.627672036715484e-06, "loss": 0.6898, "step": 255 }, { "epoch": 0.2157676348547718, "grad_norm": 2.3651072953613754, "learning_rate": 9.599751567474695e-06, "loss": 0.6759, "step": 260 }, { "epoch": 0.21991701244813278, "grad_norm": 2.450633099288444, "learning_rate": 9.570865252054462e-06, "loss": 0.7034, "step": 265 }, { "epoch": 0.22406639004149378, "grad_norm": 2.3473986013625963, "learning_rate": 9.541019155942663e-06, "loss": 0.6822, "step": 270 }, { "epoch": 0.22821576763485477, "grad_norm": 2.548163258213224, "learning_rate": 9.51021954615992e-06, "loss": 0.6789, "step": 275 }, { "epoch": 0.23236514522821577, "grad_norm": 2.5379693961647303, "learning_rate": 9.478472889943644e-06, "loss": 0.6625, "step": 280 }, { "epoch": 0.23651452282157676, "grad_norm": 2.327924483215091, "learning_rate": 9.445785853390074e-06, "loss": 0.6721, "step": 285 }, { "epoch": 0.24066390041493776, "grad_norm": 2.262881099755119, "learning_rate": 9.412165300054536e-06, "loss": 0.6566, "step": 290 }, { "epoch": 0.24481327800829875, "grad_norm": 2.265488203072667, "learning_rate": 9.377618289510251e-06, "loss": 0.6608, "step": 295 }, { "epoch": 0.24896265560165975, "grad_norm": 2.5878567494362175, "learning_rate": 9.34215207586598e-06, "loss": 0.6499, "step": 300 }, { "epoch": 0.25311203319502074, "grad_norm": 2.3658001383539733, "learning_rate": 9.305774106242825e-06, "loss": 0.6484, "step": 305 }, { "epoch": 0.2572614107883817, "grad_norm": 2.243961082145765, "learning_rate": 9.268492019210486e-06, "loss": 0.6564, "step": 310 }, { "epoch": 0.26141078838174275, "grad_norm": 2.380897449863462, "learning_rate": 9.23031364318335e-06, "loss": 0.6348, "step": 315 }, { "epoch": 0.26556016597510373, "grad_norm": 2.5103759793912817, "learning_rate": 9.191246994776676e-06, "loss": 0.6363, "step": 320 }, { "epoch": 0.2697095435684647, "grad_norm": 2.249912565836941, "learning_rate": 9.1513002771233e-06, "loss": 0.6419, "step": 325 }, { "epoch": 0.27385892116182575, "grad_norm": 2.163581249856587, "learning_rate": 9.110481878151147e-06, "loss": 0.6301, "step": 330 }, { "epoch": 0.27800829875518673, "grad_norm": 2.190865179892157, "learning_rate": 9.068800368821957e-06, "loss": 0.6325, "step": 335 }, { "epoch": 0.2821576763485477, "grad_norm": 2.265573915661597, "learning_rate": 9.026264501331571e-06, "loss": 0.6322, "step": 340 }, { "epoch": 0.2863070539419087, "grad_norm": 2.2910874776204286, "learning_rate": 8.982883207272164e-06, "loss": 0.623, "step": 345 }, { "epoch": 0.29045643153526973, "grad_norm": 2.384654294302928, "learning_rate": 8.938665595756807e-06, "loss": 0.6246, "step": 350 }, { "epoch": 0.2946058091286307, "grad_norm": 2.4124577641889537, "learning_rate": 8.893620951506755e-06, "loss": 0.6136, "step": 355 }, { "epoch": 0.2987551867219917, "grad_norm": 2.6221754387144562, "learning_rate": 8.84775873290186e-06, "loss": 0.6187, "step": 360 }, { "epoch": 0.3029045643153527, "grad_norm": 2.2955995327624277, "learning_rate": 8.801088569994523e-06, "loss": 0.6048, "step": 365 }, { "epoch": 0.3070539419087137, "grad_norm": 2.138665428419567, "learning_rate": 8.75362026248759e-06, "loss": 0.6031, "step": 370 }, { "epoch": 0.3112033195020747, "grad_norm": 2.1328698825170593, "learning_rate": 8.705363777676641e-06, "loss": 0.6063, "step": 375 }, { "epoch": 0.3153526970954357, "grad_norm": 2.1479776795024783, "learning_rate": 8.656329248357065e-06, "loss": 0.5942, "step": 380 }, { "epoch": 0.31950207468879666, "grad_norm": 2.134654863907731, "learning_rate": 8.60652697069641e-06, "loss": 0.5904, "step": 385 }, { "epoch": 0.3236514522821577, "grad_norm": 2.374467014031146, "learning_rate": 8.555967402072402e-06, "loss": 0.5995, "step": 390 }, { "epoch": 0.3278008298755187, "grad_norm": 2.40926239385975, "learning_rate": 8.50466115887714e-06, "loss": 0.5927, "step": 395 }, { "epoch": 0.33195020746887965, "grad_norm": 2.3502075362637767, "learning_rate": 8.452619014287882e-06, "loss": 0.5847, "step": 400 }, { "epoch": 0.3360995850622407, "grad_norm": 2.4126500802319097, "learning_rate": 8.399851896004914e-06, "loss": 0.5862, "step": 405 }, { "epoch": 0.34024896265560167, "grad_norm": 2.2950749664456227, "learning_rate": 8.346370883956975e-06, "loss": 0.5855, "step": 410 }, { "epoch": 0.34439834024896265, "grad_norm": 2.161036752273593, "learning_rate": 8.292187207974723e-06, "loss": 0.5746, "step": 415 }, { "epoch": 0.34854771784232363, "grad_norm": 2.4188236778063352, "learning_rate": 8.237312245432709e-06, "loss": 0.5879, "step": 420 }, { "epoch": 0.35269709543568467, "grad_norm": 2.2090916593497636, "learning_rate": 8.181757518860387e-06, "loss": 0.5773, "step": 425 }, { "epoch": 0.35684647302904565, "grad_norm": 2.3146906711334734, "learning_rate": 8.125534693522639e-06, "loss": 0.5735, "step": 430 }, { "epoch": 0.36099585062240663, "grad_norm": 2.239996996129289, "learning_rate": 8.068655574970316e-06, "loss": 0.554, "step": 435 }, { "epoch": 0.3651452282157676, "grad_norm": 2.363097757813145, "learning_rate": 8.011132106561347e-06, "loss": 0.5545, "step": 440 }, { "epoch": 0.36929460580912865, "grad_norm": 2.27029308132692, "learning_rate": 7.952976366952888e-06, "loss": 0.5683, "step": 445 }, { "epoch": 0.37344398340248963, "grad_norm": 2.1074572809534375, "learning_rate": 7.894200567565075e-06, "loss": 0.5648, "step": 450 }, { "epoch": 0.3775933609958506, "grad_norm": 2.273342227929578, "learning_rate": 7.834817050016899e-06, "loss": 0.5679, "step": 455 }, { "epoch": 0.3817427385892116, "grad_norm": 2.2797216207901383, "learning_rate": 7.774838283534724e-06, "loss": 0.5559, "step": 460 }, { "epoch": 0.38589211618257263, "grad_norm": 2.104532263164514, "learning_rate": 7.714276862334051e-06, "loss": 0.54, "step": 465 }, { "epoch": 0.3900414937759336, "grad_norm": 2.1184787555923212, "learning_rate": 7.653145502974982e-06, "loss": 0.555, "step": 470 }, { "epoch": 0.3941908713692946, "grad_norm": 2.1723348338228328, "learning_rate": 7.591457041692045e-06, "loss": 0.546, "step": 475 }, { "epoch": 0.3983402489626556, "grad_norm": 2.1840500746464295, "learning_rate": 7.529224431698858e-06, "loss": 0.547, "step": 480 }, { "epoch": 0.4024896265560166, "grad_norm": 2.318164164245411, "learning_rate": 7.466460740468246e-06, "loss": 0.542, "step": 485 }, { "epoch": 0.4066390041493776, "grad_norm": 2.3138151208917126, "learning_rate": 7.40317914698835e-06, "loss": 0.5445, "step": 490 }, { "epoch": 0.4107883817427386, "grad_norm": 2.1331277286671186, "learning_rate": 7.339392938995349e-06, "loss": 0.5319, "step": 495 }, { "epoch": 0.4149377593360996, "grad_norm": 2.2351009447186803, "learning_rate": 7.2751155101833095e-06, "loss": 0.5273, "step": 500 }, { "epoch": 0.4190871369294606, "grad_norm": 2.135991611803002, "learning_rate": 7.210360357391818e-06, "loss": 0.5376, "step": 505 }, { "epoch": 0.42323651452282157, "grad_norm": 2.5539346756615906, "learning_rate": 7.145141077771938e-06, "loss": 0.5273, "step": 510 }, { "epoch": 0.42738589211618255, "grad_norm": 2.047264916869935, "learning_rate": 7.0794713659311145e-06, "loss": 0.5277, "step": 515 }, { "epoch": 0.4315352697095436, "grad_norm": 2.2988994571475994, "learning_rate": 7.0133650110576e-06, "loss": 0.5124, "step": 520 }, { "epoch": 0.43568464730290457, "grad_norm": 2.185194372325859, "learning_rate": 6.946835894025037e-06, "loss": 0.526, "step": 525 }, { "epoch": 0.43983402489626555, "grad_norm": 2.1924305119120095, "learning_rate": 6.879897984477778e-06, "loss": 0.5297, "step": 530 }, { "epoch": 0.44398340248962653, "grad_norm": 2.2531761041789458, "learning_rate": 6.8125653378975675e-06, "loss": 0.5135, "step": 535 }, { "epoch": 0.44813278008298757, "grad_norm": 2.1140660080628217, "learning_rate": 6.7448520926522084e-06, "loss": 0.5209, "step": 540 }, { "epoch": 0.45228215767634855, "grad_norm": 2.2942813216608995, "learning_rate": 6.676772467026809e-06, "loss": 0.5153, "step": 545 }, { "epoch": 0.45643153526970953, "grad_norm": 2.1380478037125026, "learning_rate": 6.608340756238261e-06, "loss": 0.5205, "step": 550 }, { "epoch": 0.4605809128630705, "grad_norm": 2.2305987813784665, "learning_rate": 6.539571329433562e-06, "loss": 0.5042, "step": 555 }, { "epoch": 0.46473029045643155, "grad_norm": 2.0259829999672583, "learning_rate": 6.470478626672607e-06, "loss": 0.5063, "step": 560 }, { "epoch": 0.46887966804979253, "grad_norm": 2.1482954433368966, "learning_rate": 6.401077155896098e-06, "loss": 0.5037, "step": 565 }, { "epoch": 0.4730290456431535, "grad_norm": 2.0722196480572967, "learning_rate": 6.3313814898792e-06, "loss": 0.5119, "step": 570 }, { "epoch": 0.47717842323651455, "grad_norm": 2.0766008318122116, "learning_rate": 6.261406263171574e-06, "loss": 0.4936, "step": 575 }, { "epoch": 0.48132780082987553, "grad_norm": 2.170054524337145, "learning_rate": 6.191166169024449e-06, "loss": 0.5115, "step": 580 }, { "epoch": 0.4854771784232365, "grad_norm": 2.165392386687399, "learning_rate": 6.120675956305363e-06, "loss": 0.506, "step": 585 }, { "epoch": 0.4896265560165975, "grad_norm": 2.1917064615978865, "learning_rate": 6.049950426401224e-06, "loss": 0.4922, "step": 590 }, { "epoch": 0.49377593360995853, "grad_norm": 2.1320846413675754, "learning_rate": 5.979004430110356e-06, "loss": 0.4962, "step": 595 }, { "epoch": 0.4979253112033195, "grad_norm": 2.2214982569308943, "learning_rate": 5.907852864524141e-06, "loss": 0.4798, "step": 600 }, { "epoch": 0.5020746887966805, "grad_norm": 2.1478446403131017, "learning_rate": 5.836510669898984e-06, "loss": 0.488, "step": 605 }, { "epoch": 0.5062240663900415, "grad_norm": 2.0711442564532683, "learning_rate": 5.7649928265191625e-06, "loss": 0.4809, "step": 610 }, { "epoch": 0.5103734439834025, "grad_norm": 2.0362299353680875, "learning_rate": 5.693314351551317e-06, "loss": 0.4779, "step": 615 }, { "epoch": 0.5145228215767634, "grad_norm": 2.223869208837942, "learning_rate": 5.621490295891172e-06, "loss": 0.4816, "step": 620 }, { "epoch": 0.5186721991701245, "grad_norm": 2.184093648016579, "learning_rate": 5.5495357410031805e-06, "loss": 0.4767, "step": 625 }, { "epoch": 0.5228215767634855, "grad_norm": 2.0615628269463455, "learning_rate": 5.477465795753744e-06, "loss": 0.4721, "step": 630 }, { "epoch": 0.5269709543568465, "grad_norm": 2.139010346072537, "learning_rate": 5.405295593238701e-06, "loss": 0.4695, "step": 635 }, { "epoch": 0.5311203319502075, "grad_norm": 2.123946607015628, "learning_rate": 5.333040287605687e-06, "loss": 0.4723, "step": 640 }, { "epoch": 0.5352697095435685, "grad_norm": 2.3651276982269964, "learning_rate": 5.260715050872119e-06, "loss": 0.4624, "step": 645 }, { "epoch": 0.5394190871369294, "grad_norm": 2.287295610466921, "learning_rate": 5.1883350697394e-06, "loss": 0.4644, "step": 650 }, { "epoch": 0.5435684647302904, "grad_norm": 2.105320559946653, "learning_rate": 5.115915542404045e-06, "loss": 0.4584, "step": 655 }, { "epoch": 0.5477178423236515, "grad_norm": 2.170432310241974, "learning_rate": 5.0434716753663984e-06, "loss": 0.4612, "step": 660 }, { "epoch": 0.5518672199170125, "grad_norm": 2.194690777716423, "learning_rate": 4.971018680237602e-06, "loss": 0.4607, "step": 665 }, { "epoch": 0.5560165975103735, "grad_norm": 1.9776501173869443, "learning_rate": 4.8985717705455e-06, "loss": 0.4611, "step": 670 }, { "epoch": 0.5601659751037344, "grad_norm": 2.108677954477835, "learning_rate": 4.826146158540125e-06, "loss": 0.464, "step": 675 }, { "epoch": 0.5643153526970954, "grad_norm": 2.2306541731963265, "learning_rate": 4.753757051999468e-06, "loss": 0.4575, "step": 680 }, { "epoch": 0.5684647302904564, "grad_norm": 2.177699396676135, "learning_rate": 4.681419651036177e-06, "loss": 0.4515, "step": 685 }, { "epoch": 0.5726141078838174, "grad_norm": 2.1123134999189603, "learning_rate": 4.609149144905874e-06, "loss": 0.4609, "step": 690 }, { "epoch": 0.5767634854771784, "grad_norm": 2.2267780701787343, "learning_rate": 4.536960708817743e-06, "loss": 0.4517, "step": 695 }, { "epoch": 0.5809128630705395, "grad_norm": 2.0878112877178725, "learning_rate": 4.464869500748075e-06, "loss": 0.4532, "step": 700 }, { "epoch": 0.5850622406639004, "grad_norm": 2.064093943237562, "learning_rate": 4.392890658257421e-06, "loss": 0.4545, "step": 705 }, { "epoch": 0.5892116182572614, "grad_norm": 2.091722197853374, "learning_rate": 4.321039295312048e-06, "loss": 0.4346, "step": 710 }, { "epoch": 0.5933609958506224, "grad_norm": 1.9233248459765655, "learning_rate": 4.249330499110334e-06, "loss": 0.436, "step": 715 }, { "epoch": 0.5975103734439834, "grad_norm": 1.9972967400785588, "learning_rate": 4.177779326914793e-06, "loss": 0.435, "step": 720 }, { "epoch": 0.6016597510373444, "grad_norm": 2.0247163429595743, "learning_rate": 4.106400802890377e-06, "loss": 0.438, "step": 725 }, { "epoch": 0.6058091286307054, "grad_norm": 2.082262528377969, "learning_rate": 4.03520991494974e-06, "loss": 0.4419, "step": 730 }, { "epoch": 0.6099585062240664, "grad_norm": 2.1097886512141386, "learning_rate": 3.964221611606108e-06, "loss": 0.4355, "step": 735 }, { "epoch": 0.6141078838174274, "grad_norm": 2.055338754378088, "learning_rate": 3.893450798834412e-06, "loss": 0.4365, "step": 740 }, { "epoch": 0.6182572614107884, "grad_norm": 2.0758265457246154, "learning_rate": 3.822912336941375e-06, "loss": 0.4316, "step": 745 }, { "epoch": 0.6224066390041494, "grad_norm": 2.0060803377407788, "learning_rate": 3.7526210374451665e-06, "loss": 0.4336, "step": 750 }, { "epoch": 0.6265560165975104, "grad_norm": 2.1438017129720324, "learning_rate": 3.6825916599653177e-06, "loss": 0.432, "step": 755 }, { "epoch": 0.6307053941908713, "grad_norm": 2.066973580119617, "learning_rate": 3.6128389091235207e-06, "loss": 0.439, "step": 760 }, { "epoch": 0.6348547717842323, "grad_norm": 2.0587913853717947, "learning_rate": 3.543377431455991e-06, "loss": 0.4278, "step": 765 }, { "epoch": 0.6390041493775933, "grad_norm": 2.0295102232187894, "learning_rate": 3.4742218123380085e-06, "loss": 0.4141, "step": 770 }, { "epoch": 0.6431535269709544, "grad_norm": 2.1211936908053803, "learning_rate": 3.4053865729213267e-06, "loss": 0.4269, "step": 775 }, { "epoch": 0.6473029045643154, "grad_norm": 2.073558611545013, "learning_rate": 3.3368861670850316e-06, "loss": 0.4242, "step": 780 }, { "epoch": 0.6514522821576764, "grad_norm": 2.1028200278850906, "learning_rate": 3.268734978400564e-06, "loss": 0.4255, "step": 785 }, { "epoch": 0.6556016597510373, "grad_norm": 2.074338043700759, "learning_rate": 3.2009473171114748e-06, "loss": 0.4127, "step": 790 }, { "epoch": 0.6597510373443983, "grad_norm": 2.0169788933206965, "learning_rate": 3.1335374171285993e-06, "loss": 0.4273, "step": 795 }, { "epoch": 0.6639004149377593, "grad_norm": 2.132031529237029, "learning_rate": 3.0665194330412453e-06, "loss": 0.4199, "step": 800 }, { "epoch": 0.6680497925311203, "grad_norm": 1.974289618100589, "learning_rate": 2.999907437145042e-06, "loss": 0.4141, "step": 805 }, { "epoch": 0.6721991701244814, "grad_norm": 1.9950951128394907, "learning_rate": 2.9337154164870723e-06, "loss": 0.4141, "step": 810 }, { "epoch": 0.6763485477178424, "grad_norm": 2.0422579243315298, "learning_rate": 2.8679572699288993e-06, "loss": 0.4117, "step": 815 }, { "epoch": 0.6804979253112033, "grad_norm": 2.049127089823568, "learning_rate": 2.802646805228115e-06, "loss": 0.4055, "step": 820 }, { "epoch": 0.6846473029045643, "grad_norm": 2.0129580531205686, "learning_rate": 2.7377977361390118e-06, "loss": 0.4032, "step": 825 }, { "epoch": 0.6887966804979253, "grad_norm": 2.1533361617257496, "learning_rate": 2.673423679533003e-06, "loss": 0.4049, "step": 830 }, { "epoch": 0.6929460580912863, "grad_norm": 2.012532576052599, "learning_rate": 2.609538152539375e-06, "loss": 0.4112, "step": 835 }, { "epoch": 0.6970954356846473, "grad_norm": 2.0005545981205013, "learning_rate": 2.546154569706991e-06, "loss": 0.4062, "step": 840 }, { "epoch": 0.7012448132780082, "grad_norm": 1.9763702850969325, "learning_rate": 2.483286240187538e-06, "loss": 0.4076, "step": 845 }, { "epoch": 0.7053941908713693, "grad_norm": 1.9363754039901064, "learning_rate": 2.420946364940885e-06, "loss": 0.3983, "step": 850 }, { "epoch": 0.7095435684647303, "grad_norm": 1.9964976216880392, "learning_rate": 2.359148033963195e-06, "loss": 0.4012, "step": 855 }, { "epoch": 0.7136929460580913, "grad_norm": 1.9539357011094127, "learning_rate": 2.297904223538289e-06, "loss": 0.4014, "step": 860 }, { "epoch": 0.7178423236514523, "grad_norm": 2.003285264891127, "learning_rate": 2.237227793512935e-06, "loss": 0.4005, "step": 865 }, { "epoch": 0.7219917012448133, "grad_norm": 2.0469841226757826, "learning_rate": 2.1771314845965485e-06, "loss": 0.3919, "step": 870 }, { "epoch": 0.7261410788381742, "grad_norm": 2.0771139142501482, "learning_rate": 2.1176279156859396e-06, "loss": 0.3967, "step": 875 }, { "epoch": 0.7302904564315352, "grad_norm": 2.0143075674387734, "learning_rate": 2.0587295812156117e-06, "loss": 0.4042, "step": 880 }, { "epoch": 0.7344398340248963, "grad_norm": 2.033797194926859, "learning_rate": 2.000448848534209e-06, "loss": 0.3889, "step": 885 }, { "epoch": 0.7385892116182573, "grad_norm": 2.123163913068704, "learning_rate": 1.942797955307655e-06, "loss": 0.3927, "step": 890 }, { "epoch": 0.7427385892116183, "grad_norm": 2.1029028753084855, "learning_rate": 1.8857890069494983e-06, "loss": 0.3862, "step": 895 }, { "epoch": 0.7468879668049793, "grad_norm": 1.9596988626179463, "learning_rate": 1.8294339740790595e-06, "loss": 0.3926, "step": 900 }, { "epoch": 0.7510373443983402, "grad_norm": 2.045654702642933, "learning_rate": 1.7737446900078503e-06, "loss": 0.3902, "step": 905 }, { "epoch": 0.7551867219917012, "grad_norm": 1.8714455878320024, "learning_rate": 1.7187328482548543e-06, "loss": 0.3858, "step": 910 }, { "epoch": 0.7593360995850622, "grad_norm": 1.9719509461323035, "learning_rate": 1.6644100000911312e-06, "loss": 0.3858, "step": 915 }, { "epoch": 0.7634854771784232, "grad_norm": 2.0199806220076995, "learning_rate": 1.61078755211432e-06, "loss": 0.3901, "step": 920 }, { "epoch": 0.7676348547717843, "grad_norm": 1.8860408333074137, "learning_rate": 1.557876763853493e-06, "loss": 0.3789, "step": 925 }, { "epoch": 0.7717842323651453, "grad_norm": 2.0409354742092725, "learning_rate": 1.5056887454049129e-06, "loss": 0.3977, "step": 930 }, { "epoch": 0.7759336099585062, "grad_norm": 1.986307727470136, "learning_rate": 1.4542344550991538e-06, "loss": 0.3908, "step": 935 }, { "epoch": 0.7800829875518672, "grad_norm": 1.8832678493109687, "learning_rate": 1.4035246972000922e-06, "loss": 0.3935, "step": 940 }, { "epoch": 0.7842323651452282, "grad_norm": 2.020212496636967, "learning_rate": 1.353570119636255e-06, "loss": 0.379, "step": 945 }, { "epoch": 0.7883817427385892, "grad_norm": 2.0199477511715638, "learning_rate": 1.3043812117649846e-06, "loss": 0.3931, "step": 950 }, { "epoch": 0.7925311203319502, "grad_norm": 2.015693992608451, "learning_rate": 1.2559683021699132e-06, "loss": 0.3774, "step": 955 }, { "epoch": 0.7966804979253111, "grad_norm": 2.0495350044403113, "learning_rate": 1.2083415564921775e-06, "loss": 0.3845, "step": 960 }, { "epoch": 0.8008298755186722, "grad_norm": 2.1357993118322, "learning_rate": 1.1615109752958715e-06, "loss": 0.3781, "step": 965 }, { "epoch": 0.8049792531120332, "grad_norm": 2.0787734920639553, "learning_rate": 1.1154863919681358e-06, "loss": 0.3786, "step": 970 }, { "epoch": 0.8091286307053942, "grad_norm": 2.0147166599927817, "learning_rate": 1.0702774706543772e-06, "loss": 0.3801, "step": 975 }, { "epoch": 0.8132780082987552, "grad_norm": 2.1274229351405682, "learning_rate": 1.0258937042289986e-06, "loss": 0.3758, "step": 980 }, { "epoch": 0.8174273858921162, "grad_norm": 2.020236024053247, "learning_rate": 9.82344412302117e-07, "loss": 0.3745, "step": 985 }, { "epoch": 0.8215767634854771, "grad_norm": 2.0310388332900224, "learning_rate": 9.396387392626399e-07, "loss": 0.3716, "step": 990 }, { "epoch": 0.8257261410788381, "grad_norm": 2.1668749663108717, "learning_rate": 8.97785652358158e-07, "loss": 0.3697, "step": 995 }, { "epoch": 0.8298755186721992, "grad_norm": 2.0045742016058914, "learning_rate": 8.567939398120095e-07, "loss": 0.376, "step": 1000 }, { "epoch": 0.8340248962655602, "grad_norm": 1.9913802328205135, "learning_rate": 8.166722089779539e-07, "loss": 0.3662, "step": 1005 }, { "epoch": 0.8381742738589212, "grad_norm": 2.054785546661835, "learning_rate": 7.774288845328193e-07, "loss": 0.3797, "step": 1010 }, { "epoch": 0.8423236514522822, "grad_norm": 2.066321355843617, "learning_rate": 7.390722067075024e-07, "loss": 0.3836, "step": 1015 }, { "epoch": 0.8464730290456431, "grad_norm": 1.9972704924078868, "learning_rate": 7.016102295567046e-07, "loss": 0.3654, "step": 1020 }, { "epoch": 0.8506224066390041, "grad_norm": 1.9358010759861928, "learning_rate": 6.650508192677546e-07, "loss": 0.3649, "step": 1025 }, { "epoch": 0.8547717842323651, "grad_norm": 2.0175675008368645, "learning_rate": 6.294016525088914e-07, "loss": 0.3682, "step": 1030 }, { "epoch": 0.8589211618257261, "grad_norm": 2.046261015462815, "learning_rate": 5.946702148173211e-07, "loss": 0.3601, "step": 1035 }, { "epoch": 0.8630705394190872, "grad_norm": 2.08234471232173, "learning_rate": 5.608637990274335e-07, "loss": 0.3675, "step": 1040 }, { "epoch": 0.8672199170124482, "grad_norm": 2.061640652779725, "learning_rate": 5.279895037394567e-07, "loss": 0.3675, "step": 1045 }, { "epoch": 0.8713692946058091, "grad_norm": 2.050116976236056, "learning_rate": 4.960542318289118e-07, "loss": 0.3663, "step": 1050 }, { "epoch": 0.8755186721991701, "grad_norm": 2.072309354512263, "learning_rate": 4.6506468899716607e-07, "loss": 0.372, "step": 1055 }, { "epoch": 0.8796680497925311, "grad_norm": 2.152457552234192, "learning_rate": 4.3502738236337605e-07, "loss": 0.3593, "step": 1060 }, { "epoch": 0.8838174273858921, "grad_norm": 1.996868735465177, "learning_rate": 4.0594861909814266e-07, "loss": 0.3604, "step": 1065 }, { "epoch": 0.8879668049792531, "grad_norm": 1.9994915003373548, "learning_rate": 3.7783450509914e-07, "loss": 0.3656, "step": 1070 }, { "epoch": 0.8921161825726142, "grad_norm": 1.9740173742965879, "learning_rate": 3.5069094370901613e-07, "loss": 0.3633, "step": 1075 }, { "epoch": 0.8962655601659751, "grad_norm": 1.961688927842617, "learning_rate": 3.245236344758179e-07, "loss": 0.3634, "step": 1080 }, { "epoch": 0.9004149377593361, "grad_norm": 2.0299031717626463, "learning_rate": 2.9933807195621446e-07, "loss": 0.3643, "step": 1085 }, { "epoch": 0.9045643153526971, "grad_norm": 1.9933810295199255, "learning_rate": 2.751395445617594e-07, "loss": 0.3611, "step": 1090 }, { "epoch": 0.9087136929460581, "grad_norm": 1.9428008804611876, "learning_rate": 2.5193313344844427e-07, "loss": 0.3647, "step": 1095 }, { "epoch": 0.9128630705394191, "grad_norm": 2.070451744064332, "learning_rate": 2.2972371144976524e-07, "loss": 0.3578, "step": 1100 }, { "epoch": 0.91701244813278, "grad_norm": 2.004094672792972, "learning_rate": 2.0851594205353543e-07, "loss": 0.3682, "step": 1105 }, { "epoch": 0.921161825726141, "grad_norm": 1.99685429733088, "learning_rate": 1.8831427842266047e-07, "loss": 0.3629, "step": 1110 }, { "epoch": 0.9253112033195021, "grad_norm": 2.0362204051502495, "learning_rate": 1.6912296246006544e-07, "loss": 0.3619, "step": 1115 }, { "epoch": 0.9294605809128631, "grad_norm": 1.9954463784544125, "learning_rate": 1.5094602391799606e-07, "loss": 0.359, "step": 1120 }, { "epoch": 0.9336099585062241, "grad_norm": 2.101222001014506, "learning_rate": 1.3378727955185243e-07, "loss": 0.3643, "step": 1125 }, { "epoch": 0.9377593360995851, "grad_norm": 2.0097408515894477, "learning_rate": 1.1765033231876332e-07, "loss": 0.365, "step": 1130 }, { "epoch": 0.941908713692946, "grad_norm": 2.083152089600553, "learning_rate": 1.0253857062103579e-07, "loss": 0.356, "step": 1135 }, { "epoch": 0.946058091286307, "grad_norm": 2.1343299677958565, "learning_rate": 8.845516759467432e-08, "loss": 0.3637, "step": 1140 }, { "epoch": 0.950207468879668, "grad_norm": 2.0339392745318854, "learning_rate": 7.540308044308442e-08, "loss": 0.3654, "step": 1145 }, { "epoch": 0.9543568464730291, "grad_norm": 2.0235713792250674, "learning_rate": 6.338504981613037e-08, "loss": 0.3601, "step": 1150 }, { "epoch": 0.9585062240663901, "grad_norm": 2.109608243011711, "learning_rate": 5.2403599234658876e-08, "loss": 0.356, "step": 1155 }, { "epoch": 0.9626556016597511, "grad_norm": 2.0760547345374603, "learning_rate": 4.246103456061246e-08, "loss": 0.3595, "step": 1160 }, { "epoch": 0.966804979253112, "grad_norm": 2.052680320906187, "learning_rate": 3.355944351285278e-08, "loss": 0.3664, "step": 1165 }, { "epoch": 0.970954356846473, "grad_norm": 2.0133846012871484, "learning_rate": 2.5700695228783045e-08, "loss": 0.3602, "step": 1170 }, { "epoch": 0.975103734439834, "grad_norm": 2.0460051222086517, "learning_rate": 1.8886439871874662e-08, "loss": 0.3614, "step": 1175 }, { "epoch": 0.979253112033195, "grad_norm": 1.9713443728652713, "learning_rate": 1.31181082851628e-08, "loss": 0.3634, "step": 1180 }, { "epoch": 0.983402489626556, "grad_norm": 1.9598526108360579, "learning_rate": 8.396911690807253e-09, "loss": 0.3633, "step": 1185 }, { "epoch": 0.9875518672199171, "grad_norm": 2.018358583132368, "learning_rate": 4.723841435759769e-09, "loss": 0.3678, "step": 1190 }, { "epoch": 0.991701244813278, "grad_norm": 2.0932112430813317, "learning_rate": 2.0996687836016825e-09, "loss": 0.364, "step": 1195 }, { "epoch": 0.995850622406639, "grad_norm": 2.064858475016426, "learning_rate": 5.249447525995654e-10, "loss": 0.3573, "step": 1200 }, { "epoch": 1.0, "grad_norm": 2.020766577175708, "learning_rate": 0.0, "loss": 0.3623, "step": 1205 }, { "epoch": 1.0, "eval_loss": 0.3198564946651459, "eval_runtime": 1.1889, "eval_samples_per_second": 2.523, "eval_steps_per_second": 0.841, "step": 1205 }, { "epoch": 1.0, "step": 1205, "total_flos": 252197795266560.0, "train_loss": 0.5424416576678327, "train_runtime": 23511.1257, "train_samples_per_second": 1.639, "train_steps_per_second": 0.051 } ], "logging_steps": 5, "max_steps": 1205, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 252197795266560.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }