{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9998451612903225, "eval_steps": 500, "global_step": 4843, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002064516129032258, "grad_norm": 2.7178148753284264, "learning_rate": 2.0618556701030925e-08, "loss": 0.4276, "step": 10 }, { "epoch": 0.004129032258064516, "grad_norm": 2.5625384878679336, "learning_rate": 4.123711340206185e-08, "loss": 0.4189, "step": 20 }, { "epoch": 0.006193548387096774, "grad_norm": 2.267409247602629, "learning_rate": 6.185567010309278e-08, "loss": 0.4065, "step": 30 }, { "epoch": 0.008258064516129033, "grad_norm": 1.9532754064444633, "learning_rate": 8.24742268041237e-08, "loss": 0.3945, "step": 40 }, { "epoch": 0.01032258064516129, "grad_norm": 1.585906241951902, "learning_rate": 1.0309278350515462e-07, "loss": 0.376, "step": 50 }, { "epoch": 0.012387096774193548, "grad_norm": 1.2402093228097, "learning_rate": 1.2371134020618556e-07, "loss": 0.3589, "step": 60 }, { "epoch": 0.014451612903225806, "grad_norm": 1.0130242074966187, "learning_rate": 1.4432989690721648e-07, "loss": 0.3489, "step": 70 }, { "epoch": 0.016516129032258065, "grad_norm": 0.8517244513870358, "learning_rate": 1.649484536082474e-07, "loss": 0.3286, "step": 80 }, { "epoch": 0.01858064516129032, "grad_norm": 0.6911175913558477, "learning_rate": 1.8556701030927835e-07, "loss": 0.3177, "step": 90 }, { "epoch": 0.02064516129032258, "grad_norm": 0.604894441447739, "learning_rate": 2.0618556701030925e-07, "loss": 0.3146, "step": 100 }, { "epoch": 0.02270967741935484, "grad_norm": 0.5731491989954443, "learning_rate": 2.268041237113402e-07, "loss": 0.3156, "step": 110 }, { "epoch": 0.024774193548387096, "grad_norm": 0.5622949683109659, "learning_rate": 2.474226804123711e-07, "loss": 0.3053, "step": 120 }, { "epoch": 0.026838709677419356, "grad_norm": 0.5173328385018767, "learning_rate": 2.6804123711340204e-07, "loss": 0.3021, "step": 130 }, { "epoch": 0.02890322580645161, "grad_norm": 0.502383112182359, "learning_rate": 2.8865979381443296e-07, "loss": 0.3024, "step": 140 }, { "epoch": 0.03096774193548387, "grad_norm": 0.5056646956646865, "learning_rate": 3.0927835051546394e-07, "loss": 0.299, "step": 150 }, { "epoch": 0.03303225806451613, "grad_norm": 0.48413086309965675, "learning_rate": 3.298969072164948e-07, "loss": 0.2947, "step": 160 }, { "epoch": 0.03509677419354839, "grad_norm": 0.46867700011688224, "learning_rate": 3.5051546391752573e-07, "loss": 0.295, "step": 170 }, { "epoch": 0.03716129032258064, "grad_norm": 0.463440589569122, "learning_rate": 3.711340206185567e-07, "loss": 0.2938, "step": 180 }, { "epoch": 0.0392258064516129, "grad_norm": 0.46043148110607285, "learning_rate": 3.917525773195876e-07, "loss": 0.2829, "step": 190 }, { "epoch": 0.04129032258064516, "grad_norm": 0.4452081751770784, "learning_rate": 4.123711340206185e-07, "loss": 0.2914, "step": 200 }, { "epoch": 0.04335483870967742, "grad_norm": 0.4389480699132875, "learning_rate": 4.3298969072164947e-07, "loss": 0.2875, "step": 210 }, { "epoch": 0.04541935483870968, "grad_norm": 0.44451224796794, "learning_rate": 4.536082474226804e-07, "loss": 0.2891, "step": 220 }, { "epoch": 0.04748387096774193, "grad_norm": 0.44134552800104987, "learning_rate": 4.742268041237113e-07, "loss": 0.2824, "step": 230 }, { "epoch": 0.04954838709677419, "grad_norm": 0.4447117928290257, "learning_rate": 4.948453608247422e-07, "loss": 0.2833, "step": 240 }, { "epoch": 0.05161290322580645, "grad_norm": 0.42778123230774645, "learning_rate": 5.154639175257731e-07, "loss": 0.288, "step": 250 }, { "epoch": 0.05367741935483871, "grad_norm": 0.4310604168679218, "learning_rate": 5.360824742268041e-07, "loss": 0.2848, "step": 260 }, { "epoch": 0.05574193548387097, "grad_norm": 0.44369498025891935, "learning_rate": 5.56701030927835e-07, "loss": 0.2781, "step": 270 }, { "epoch": 0.05780645161290322, "grad_norm": 0.4352776941276996, "learning_rate": 5.773195876288659e-07, "loss": 0.2765, "step": 280 }, { "epoch": 0.05987096774193548, "grad_norm": 0.43125432618608434, "learning_rate": 5.979381443298969e-07, "loss": 0.2868, "step": 290 }, { "epoch": 0.06193548387096774, "grad_norm": 0.4088432228941457, "learning_rate": 6.185567010309279e-07, "loss": 0.2767, "step": 300 }, { "epoch": 0.064, "grad_norm": 0.40838698266390966, "learning_rate": 6.391752577319586e-07, "loss": 0.2805, "step": 310 }, { "epoch": 0.06606451612903226, "grad_norm": 0.450287079898162, "learning_rate": 6.597938144329896e-07, "loss": 0.2861, "step": 320 }, { "epoch": 0.06812903225806452, "grad_norm": 0.44464718825256144, "learning_rate": 6.804123711340206e-07, "loss": 0.2806, "step": 330 }, { "epoch": 0.07019354838709678, "grad_norm": 0.4173477445677872, "learning_rate": 7.010309278350515e-07, "loss": 0.2775, "step": 340 }, { "epoch": 0.07225806451612904, "grad_norm": 0.4247873010801217, "learning_rate": 7.216494845360824e-07, "loss": 0.2841, "step": 350 }, { "epoch": 0.07432258064516128, "grad_norm": 0.42839718840105573, "learning_rate": 7.422680412371134e-07, "loss": 0.2805, "step": 360 }, { "epoch": 0.07638709677419354, "grad_norm": 0.43388241770267927, "learning_rate": 7.628865979381443e-07, "loss": 0.2716, "step": 370 }, { "epoch": 0.0784516129032258, "grad_norm": 0.4326840727745175, "learning_rate": 7.835051546391752e-07, "loss": 0.2791, "step": 380 }, { "epoch": 0.08051612903225806, "grad_norm": 0.4446793301639306, "learning_rate": 8.041237113402062e-07, "loss": 0.2754, "step": 390 }, { "epoch": 0.08258064516129032, "grad_norm": 0.4088616982234986, "learning_rate": 8.24742268041237e-07, "loss": 0.2776, "step": 400 }, { "epoch": 0.08464516129032258, "grad_norm": 0.4305234378372906, "learning_rate": 8.45360824742268e-07, "loss": 0.275, "step": 410 }, { "epoch": 0.08670967741935484, "grad_norm": 0.4178542921488476, "learning_rate": 8.659793814432989e-07, "loss": 0.2712, "step": 420 }, { "epoch": 0.0887741935483871, "grad_norm": 0.4295628808236906, "learning_rate": 8.865979381443298e-07, "loss": 0.2783, "step": 430 }, { "epoch": 0.09083870967741936, "grad_norm": 0.42059850195120757, "learning_rate": 9.072164948453608e-07, "loss": 0.2778, "step": 440 }, { "epoch": 0.09290322580645162, "grad_norm": 0.41033574022465774, "learning_rate": 9.278350515463918e-07, "loss": 0.2791, "step": 450 }, { "epoch": 0.09496774193548387, "grad_norm": 0.44298494519621506, "learning_rate": 9.484536082474226e-07, "loss": 0.2791, "step": 460 }, { "epoch": 0.09703225806451612, "grad_norm": 0.4272735948398401, "learning_rate": 9.690721649484535e-07, "loss": 0.277, "step": 470 }, { "epoch": 0.09909677419354838, "grad_norm": 0.4425115953914259, "learning_rate": 9.896907216494845e-07, "loss": 0.2718, "step": 480 }, { "epoch": 0.10116129032258064, "grad_norm": 0.43188220880067546, "learning_rate": 9.999967520836107e-07, "loss": 0.2747, "step": 490 }, { "epoch": 0.1032258064516129, "grad_norm": 0.45764678748045984, "learning_rate": 9.999707690056706e-07, "loss": 0.2829, "step": 500 }, { "epoch": 0.10529032258064516, "grad_norm": 0.4165688525515349, "learning_rate": 9.999188042000401e-07, "loss": 0.2766, "step": 510 }, { "epoch": 0.10735483870967742, "grad_norm": 0.3946488524350012, "learning_rate": 9.998408603671476e-07, "loss": 0.2777, "step": 520 }, { "epoch": 0.10941935483870968, "grad_norm": 0.4371786129352002, "learning_rate": 9.997369415574612e-07, "loss": 0.2698, "step": 530 }, { "epoch": 0.11148387096774194, "grad_norm": 0.42687492357393675, "learning_rate": 9.996070531712766e-07, "loss": 0.272, "step": 540 }, { "epoch": 0.1135483870967742, "grad_norm": 0.4388895511669077, "learning_rate": 9.99451201958438e-07, "loss": 0.2752, "step": 550 }, { "epoch": 0.11561290322580645, "grad_norm": 0.4078057120806041, "learning_rate": 9.992693960179864e-07, "loss": 0.2714, "step": 560 }, { "epoch": 0.1176774193548387, "grad_norm": 0.43339623355818996, "learning_rate": 9.99061644797739e-07, "loss": 0.2794, "step": 570 }, { "epoch": 0.11974193548387096, "grad_norm": 0.417329955629982, "learning_rate": 9.988279590937983e-07, "loss": 0.2748, "step": 580 }, { "epoch": 0.12180645161290322, "grad_norm": 0.40923444925031505, "learning_rate": 9.985683510499907e-07, "loss": 0.2689, "step": 590 }, { "epoch": 0.12387096774193548, "grad_norm": 0.42272165886149954, "learning_rate": 9.982828341572362e-07, "loss": 0.2728, "step": 600 }, { "epoch": 0.12593548387096773, "grad_norm": 0.40035391344182425, "learning_rate": 9.979714232528463e-07, "loss": 0.2676, "step": 610 }, { "epoch": 0.128, "grad_norm": 0.41930822994047545, "learning_rate": 9.97634134519754e-07, "loss": 0.2754, "step": 620 }, { "epoch": 0.13006451612903225, "grad_norm": 0.41319545992748746, "learning_rate": 9.972709854856716e-07, "loss": 0.2747, "step": 630 }, { "epoch": 0.13212903225806452, "grad_norm": 0.42917202090046985, "learning_rate": 9.968819950221812e-07, "loss": 0.2665, "step": 640 }, { "epoch": 0.13419354838709677, "grad_norm": 0.41071088182465415, "learning_rate": 9.964671833437533e-07, "loss": 0.2735, "step": 650 }, { "epoch": 0.13625806451612904, "grad_norm": 0.42770202579067185, "learning_rate": 9.960265720066961e-07, "loss": 0.2655, "step": 660 }, { "epoch": 0.13832258064516129, "grad_norm": 0.43110284554769446, "learning_rate": 9.95560183908036e-07, "loss": 0.2676, "step": 670 }, { "epoch": 0.14038709677419356, "grad_norm": 0.4085540494229492, "learning_rate": 9.950680432843267e-07, "loss": 0.2711, "step": 680 }, { "epoch": 0.1424516129032258, "grad_norm": 0.4399277307424629, "learning_rate": 9.94550175710391e-07, "loss": 0.2714, "step": 690 }, { "epoch": 0.14451612903225808, "grad_norm": 0.4022098269924505, "learning_rate": 9.940066080979909e-07, "loss": 0.2692, "step": 700 }, { "epoch": 0.14658064516129032, "grad_norm": 0.4138221392891085, "learning_rate": 9.934373686944286e-07, "loss": 0.2706, "step": 710 }, { "epoch": 0.14864516129032257, "grad_norm": 0.3973539996922592, "learning_rate": 9.928424870810804e-07, "loss": 0.2678, "step": 720 }, { "epoch": 0.15070967741935484, "grad_norm": 0.43845088028338314, "learning_rate": 9.922219941718576e-07, "loss": 0.2686, "step": 730 }, { "epoch": 0.1527741935483871, "grad_norm": 0.4127024501370914, "learning_rate": 9.915759222116008e-07, "loss": 0.2714, "step": 740 }, { "epoch": 0.15483870967741936, "grad_norm": 0.4164519302523563, "learning_rate": 9.909043047744044e-07, "loss": 0.2761, "step": 750 }, { "epoch": 0.1569032258064516, "grad_norm": 0.41330928847821996, "learning_rate": 9.902071767618715e-07, "loss": 0.27, "step": 760 }, { "epoch": 0.15896774193548388, "grad_norm": 0.4049309153933818, "learning_rate": 9.894845744013002e-07, "loss": 0.2738, "step": 770 }, { "epoch": 0.16103225806451613, "grad_norm": 0.4074346893357789, "learning_rate": 9.887365352438015e-07, "loss": 0.2662, "step": 780 }, { "epoch": 0.1630967741935484, "grad_norm": 0.43051997768812966, "learning_rate": 9.879630981623475e-07, "loss": 0.2762, "step": 790 }, { "epoch": 0.16516129032258065, "grad_norm": 0.4649279575587385, "learning_rate": 9.871643033497512e-07, "loss": 0.2711, "step": 800 }, { "epoch": 0.1672258064516129, "grad_norm": 0.40771616358626656, "learning_rate": 9.863401923165778e-07, "loss": 0.2712, "step": 810 }, { "epoch": 0.16929032258064516, "grad_norm": 0.43542803830446203, "learning_rate": 9.854908078889881e-07, "loss": 0.2696, "step": 820 }, { "epoch": 0.1713548387096774, "grad_norm": 0.41224099984054274, "learning_rate": 9.846161942065123e-07, "loss": 0.27, "step": 830 }, { "epoch": 0.17341935483870968, "grad_norm": 0.40015212561755775, "learning_rate": 9.837163967197567e-07, "loss": 0.2697, "step": 840 }, { "epoch": 0.17548387096774193, "grad_norm": 0.4145538327172374, "learning_rate": 9.827914621880412e-07, "loss": 0.2719, "step": 850 }, { "epoch": 0.1775483870967742, "grad_norm": 0.4343877153779256, "learning_rate": 9.818414386769702e-07, "loss": 0.2724, "step": 860 }, { "epoch": 0.17961290322580645, "grad_norm": 0.417050446508891, "learning_rate": 9.808663755559345e-07, "loss": 0.2685, "step": 870 }, { "epoch": 0.18167741935483872, "grad_norm": 0.38732244862938475, "learning_rate": 9.798663234955452e-07, "loss": 0.2712, "step": 880 }, { "epoch": 0.18374193548387097, "grad_norm": 0.4004094471829026, "learning_rate": 9.788413344650013e-07, "loss": 0.2685, "step": 890 }, { "epoch": 0.18580645161290324, "grad_norm": 0.43063415997314575, "learning_rate": 9.777914617293884e-07, "loss": 0.2625, "step": 900 }, { "epoch": 0.18787096774193549, "grad_norm": 0.420456518146896, "learning_rate": 9.767167598469108e-07, "loss": 0.2697, "step": 910 }, { "epoch": 0.18993548387096773, "grad_norm": 0.40480539094398127, "learning_rate": 9.756172846660576e-07, "loss": 0.2707, "step": 920 }, { "epoch": 0.192, "grad_norm": 0.40767383426144205, "learning_rate": 9.744930933226977e-07, "loss": 0.2725, "step": 930 }, { "epoch": 0.19406451612903225, "grad_norm": 0.40584494188825865, "learning_rate": 9.73344244237114e-07, "loss": 0.27, "step": 940 }, { "epoch": 0.19612903225806452, "grad_norm": 0.3945980426880921, "learning_rate": 9.721707971109645e-07, "loss": 0.2677, "step": 950 }, { "epoch": 0.19819354838709677, "grad_norm": 0.4092447523280703, "learning_rate": 9.709728129241817e-07, "loss": 0.2644, "step": 960 }, { "epoch": 0.20025806451612904, "grad_norm": 0.4269916844465542, "learning_rate": 9.69750353931803e-07, "loss": 0.2666, "step": 970 }, { "epoch": 0.2023225806451613, "grad_norm": 0.4269986054049296, "learning_rate": 9.685034836607358e-07, "loss": 0.274, "step": 980 }, { "epoch": 0.20438709677419356, "grad_norm": 0.39811569845801287, "learning_rate": 9.672322669064552e-07, "loss": 0.2713, "step": 990 }, { "epoch": 0.2064516129032258, "grad_norm": 0.4061545807740594, "learning_rate": 9.659367697296393e-07, "loss": 0.2703, "step": 1000 }, { "epoch": 0.20851612903225805, "grad_norm": 0.4275991643602954, "learning_rate": 9.646170594527327e-07, "loss": 0.2667, "step": 1010 }, { "epoch": 0.21058064516129033, "grad_norm": 0.41304510032617703, "learning_rate": 9.632732046564517e-07, "loss": 0.2783, "step": 1020 }, { "epoch": 0.21264516129032257, "grad_norm": 0.4321186888978969, "learning_rate": 9.619052751762172e-07, "loss": 0.2697, "step": 1030 }, { "epoch": 0.21470967741935484, "grad_norm": 0.4143847837898666, "learning_rate": 9.605133420985276e-07, "loss": 0.2646, "step": 1040 }, { "epoch": 0.2167741935483871, "grad_norm": 0.39735153219116426, "learning_rate": 9.590974777572643e-07, "loss": 0.2643, "step": 1050 }, { "epoch": 0.21883870967741936, "grad_norm": 0.4471117773040206, "learning_rate": 9.576577557299323e-07, "loss": 0.2684, "step": 1060 }, { "epoch": 0.2209032258064516, "grad_norm": 0.41005490851887794, "learning_rate": 9.561942508338368e-07, "loss": 0.2724, "step": 1070 }, { "epoch": 0.22296774193548388, "grad_norm": 0.39495815975173343, "learning_rate": 9.547070391221953e-07, "loss": 0.2672, "step": 1080 }, { "epoch": 0.22503225806451613, "grad_norm": 0.41286773837253543, "learning_rate": 9.531961978801855e-07, "loss": 0.2736, "step": 1090 }, { "epoch": 0.2270967741935484, "grad_norm": 0.40880461152364334, "learning_rate": 9.516618056209291e-07, "loss": 0.2629, "step": 1100 }, { "epoch": 0.22916129032258065, "grad_norm": 0.4082631780670623, "learning_rate": 9.501039420814111e-07, "loss": 0.2697, "step": 1110 }, { "epoch": 0.2312258064516129, "grad_norm": 0.42142149331893225, "learning_rate": 9.485226882183372e-07, "loss": 0.2726, "step": 1120 }, { "epoch": 0.23329032258064517, "grad_norm": 0.4228180963201584, "learning_rate": 9.469181262039256e-07, "loss": 0.2735, "step": 1130 }, { "epoch": 0.2353548387096774, "grad_norm": 0.4068752038231123, "learning_rate": 9.45290339421638e-07, "loss": 0.2633, "step": 1140 }, { "epoch": 0.23741935483870968, "grad_norm": 0.4525962035081602, "learning_rate": 9.436394124618454e-07, "loss": 0.2756, "step": 1150 }, { "epoch": 0.23948387096774193, "grad_norm": 0.4317406005985711, "learning_rate": 9.419654311174329e-07, "loss": 0.2649, "step": 1160 }, { "epoch": 0.2415483870967742, "grad_norm": 0.40937736054209056, "learning_rate": 9.40268482379341e-07, "loss": 0.2726, "step": 1170 }, { "epoch": 0.24361290322580645, "grad_norm": 0.4032924973019577, "learning_rate": 9.385486544320451e-07, "loss": 0.2682, "step": 1180 }, { "epoch": 0.24567741935483872, "grad_norm": 0.41250674679202737, "learning_rate": 9.368060366489732e-07, "loss": 0.2636, "step": 1190 }, { "epoch": 0.24774193548387097, "grad_norm": 0.4110118676412479, "learning_rate": 9.350407195878607e-07, "loss": 0.2692, "step": 1200 }, { "epoch": 0.2498064516129032, "grad_norm": 0.4071563287492707, "learning_rate": 9.332527949860451e-07, "loss": 0.2721, "step": 1210 }, { "epoch": 0.25187096774193546, "grad_norm": 0.4207844628857985, "learning_rate": 9.314423557556986e-07, "loss": 0.2707, "step": 1220 }, { "epoch": 0.25393548387096776, "grad_norm": 0.39530786208260144, "learning_rate": 9.296094959789994e-07, "loss": 0.2625, "step": 1230 }, { "epoch": 0.256, "grad_norm": 0.41291391579777315, "learning_rate": 9.277543109032433e-07, "loss": 0.268, "step": 1240 }, { "epoch": 0.25806451612903225, "grad_norm": 0.4069311969256028, "learning_rate": 9.258768969358933e-07, "loss": 0.2691, "step": 1250 }, { "epoch": 0.2601290322580645, "grad_norm": 0.4266996746716126, "learning_rate": 9.2397735163957e-07, "loss": 0.264, "step": 1260 }, { "epoch": 0.2621935483870968, "grad_norm": 0.4168110125071047, "learning_rate": 9.220557737269816e-07, "loss": 0.2671, "step": 1270 }, { "epoch": 0.26425806451612904, "grad_norm": 0.402938966442535, "learning_rate": 9.201122630557943e-07, "loss": 0.2721, "step": 1280 }, { "epoch": 0.2663225806451613, "grad_norm": 0.4433703754564369, "learning_rate": 9.181469206234422e-07, "loss": 0.2724, "step": 1290 }, { "epoch": 0.26838709677419353, "grad_norm": 0.4146953645023786, "learning_rate": 9.161598485618803e-07, "loss": 0.2686, "step": 1300 }, { "epoch": 0.2704516129032258, "grad_norm": 0.40920394467675797, "learning_rate": 9.141511501322758e-07, "loss": 0.2654, "step": 1310 }, { "epoch": 0.2725161290322581, "grad_norm": 0.4291563961337551, "learning_rate": 9.121209297196424e-07, "loss": 0.2698, "step": 1320 }, { "epoch": 0.2745806451612903, "grad_norm": 0.4197741898993113, "learning_rate": 9.100692928274158e-07, "loss": 0.2678, "step": 1330 }, { "epoch": 0.27664516129032257, "grad_norm": 0.40761323746825606, "learning_rate": 9.079963460719714e-07, "loss": 0.2606, "step": 1340 }, { "epoch": 0.2787096774193548, "grad_norm": 0.4102466153208199, "learning_rate": 9.059021971770828e-07, "loss": 0.2686, "step": 1350 }, { "epoch": 0.2807741935483871, "grad_norm": 0.42536876796556666, "learning_rate": 9.037869549683252e-07, "loss": 0.2619, "step": 1360 }, { "epoch": 0.28283870967741936, "grad_norm": 0.3915639897213394, "learning_rate": 9.016507293674187e-07, "loss": 0.27, "step": 1370 }, { "epoch": 0.2849032258064516, "grad_norm": 0.40399941997235145, "learning_rate": 8.994936313865171e-07, "loss": 0.2728, "step": 1380 }, { "epoch": 0.28696774193548386, "grad_norm": 0.39944877551284785, "learning_rate": 8.973157731224385e-07, "loss": 0.274, "step": 1390 }, { "epoch": 0.28903225806451616, "grad_norm": 0.4092856245914817, "learning_rate": 8.9511726775084e-07, "loss": 0.2681, "step": 1400 }, { "epoch": 0.2910967741935484, "grad_norm": 0.481471630902478, "learning_rate": 8.928982295203367e-07, "loss": 0.2653, "step": 1410 }, { "epoch": 0.29316129032258065, "grad_norm": 0.4198523321425174, "learning_rate": 8.906587737465642e-07, "loss": 0.2683, "step": 1420 }, { "epoch": 0.2952258064516129, "grad_norm": 0.4293784170337724, "learning_rate": 8.883990168061863e-07, "loss": 0.2667, "step": 1430 }, { "epoch": 0.29729032258064514, "grad_norm": 0.409021082775393, "learning_rate": 8.861190761308472e-07, "loss": 0.2669, "step": 1440 }, { "epoch": 0.29935483870967744, "grad_norm": 0.43214579094992417, "learning_rate": 8.838190702010693e-07, "loss": 0.268, "step": 1450 }, { "epoch": 0.3014193548387097, "grad_norm": 0.4323768086041837, "learning_rate": 8.814991185400951e-07, "loss": 0.2657, "step": 1460 }, { "epoch": 0.30348387096774193, "grad_norm": 0.4140826556545066, "learning_rate": 8.791593417076781e-07, "loss": 0.2616, "step": 1470 }, { "epoch": 0.3055483870967742, "grad_norm": 0.412829397246139, "learning_rate": 8.767998612938152e-07, "loss": 0.2679, "step": 1480 }, { "epoch": 0.3076129032258065, "grad_norm": 0.42525391109992733, "learning_rate": 8.744207999124301e-07, "loss": 0.272, "step": 1490 }, { "epoch": 0.3096774193548387, "grad_norm": 0.41049108158888165, "learning_rate": 8.720222811950004e-07, "loss": 0.262, "step": 1500 }, { "epoch": 0.31174193548387097, "grad_norm": 0.40142790659401983, "learning_rate": 8.696044297841334e-07, "loss": 0.2637, "step": 1510 }, { "epoch": 0.3138064516129032, "grad_norm": 0.40612502217256863, "learning_rate": 8.671673713270886e-07, "loss": 0.2623, "step": 1520 }, { "epoch": 0.31587096774193546, "grad_norm": 0.4174546028220698, "learning_rate": 8.647112324692481e-07, "loss": 0.2648, "step": 1530 }, { "epoch": 0.31793548387096776, "grad_norm": 0.4075955189469561, "learning_rate": 8.622361408475361e-07, "loss": 0.2671, "step": 1540 }, { "epoch": 0.32, "grad_norm": 0.42757900653877373, "learning_rate": 8.597422250837848e-07, "loss": 0.2692, "step": 1550 }, { "epoch": 0.32206451612903225, "grad_norm": 0.4104754908146659, "learning_rate": 8.572296147780515e-07, "loss": 0.2627, "step": 1560 }, { "epoch": 0.3241290322580645, "grad_norm": 0.43397940214884867, "learning_rate": 8.546984405018834e-07, "loss": 0.2711, "step": 1570 }, { "epoch": 0.3261935483870968, "grad_norm": 0.43370385059956773, "learning_rate": 8.521488337915318e-07, "loss": 0.2731, "step": 1580 }, { "epoch": 0.32825806451612904, "grad_norm": 0.44403794562813276, "learning_rate": 8.49580927141117e-07, "loss": 0.2681, "step": 1590 }, { "epoch": 0.3303225806451613, "grad_norm": 0.40739732247633187, "learning_rate": 8.469948539957432e-07, "loss": 0.2704, "step": 1600 }, { "epoch": 0.33238709677419354, "grad_norm": 0.43367593462825726, "learning_rate": 8.443907487445634e-07, "loss": 0.2622, "step": 1610 }, { "epoch": 0.3344516129032258, "grad_norm": 0.40927201300965355, "learning_rate": 8.417687467137964e-07, "loss": 0.2682, "step": 1620 }, { "epoch": 0.3365161290322581, "grad_norm": 0.417183568246897, "learning_rate": 8.391289841596934e-07, "loss": 0.2623, "step": 1630 }, { "epoch": 0.33858064516129033, "grad_norm": 0.4099669038108638, "learning_rate": 8.364715982614577e-07, "loss": 0.2679, "step": 1640 }, { "epoch": 0.3406451612903226, "grad_norm": 0.40232008744229203, "learning_rate": 8.337967271141164e-07, "loss": 0.2686, "step": 1650 }, { "epoch": 0.3427096774193548, "grad_norm": 0.39988507473787327, "learning_rate": 8.311045097213431e-07, "loss": 0.274, "step": 1660 }, { "epoch": 0.3447741935483871, "grad_norm": 0.4279758729822823, "learning_rate": 8.283950859882358e-07, "loss": 0.2744, "step": 1670 }, { "epoch": 0.34683870967741937, "grad_norm": 0.4113391707725698, "learning_rate": 8.256685967140449e-07, "loss": 0.2658, "step": 1680 }, { "epoch": 0.3489032258064516, "grad_norm": 0.41525159484662594, "learning_rate": 8.229251835848573e-07, "loss": 0.2655, "step": 1690 }, { "epoch": 0.35096774193548386, "grad_norm": 0.4107278132335921, "learning_rate": 8.201649891662334e-07, "loss": 0.269, "step": 1700 }, { "epoch": 0.3530322580645161, "grad_norm": 0.43928129973031016, "learning_rate": 8.173881568957986e-07, "loss": 0.2654, "step": 1710 }, { "epoch": 0.3550967741935484, "grad_norm": 0.43005570640611046, "learning_rate": 8.145948310757886e-07, "loss": 0.2644, "step": 1720 }, { "epoch": 0.35716129032258065, "grad_norm": 0.41366298799946843, "learning_rate": 8.117851568655517e-07, "loss": 0.2664, "step": 1730 }, { "epoch": 0.3592258064516129, "grad_norm": 0.4107479182292912, "learning_rate": 8.089592802740039e-07, "loss": 0.2668, "step": 1740 }, { "epoch": 0.36129032258064514, "grad_norm": 0.4356758167861173, "learning_rate": 8.061173481520429e-07, "loss": 0.2636, "step": 1750 }, { "epoch": 0.36335483870967744, "grad_norm": 0.37618623784174804, "learning_rate": 8.032595081849154e-07, "loss": 0.2614, "step": 1760 }, { "epoch": 0.3654193548387097, "grad_norm": 0.41446607257101076, "learning_rate": 8.003859088845436e-07, "loss": 0.2642, "step": 1770 }, { "epoch": 0.36748387096774193, "grad_norm": 0.42523528400660005, "learning_rate": 7.974966995818066e-07, "loss": 0.2729, "step": 1780 }, { "epoch": 0.3695483870967742, "grad_norm": 0.3875366408745518, "learning_rate": 7.945920304187806e-07, "loss": 0.2667, "step": 1790 }, { "epoch": 0.3716129032258065, "grad_norm": 0.4057888088552019, "learning_rate": 7.916720523409366e-07, "loss": 0.2658, "step": 1800 }, { "epoch": 0.3736774193548387, "grad_norm": 0.4246975366858289, "learning_rate": 7.887369170892964e-07, "loss": 0.2704, "step": 1810 }, { "epoch": 0.37574193548387097, "grad_norm": 0.405560542887072, "learning_rate": 7.857867771925468e-07, "loss": 0.2645, "step": 1820 }, { "epoch": 0.3778064516129032, "grad_norm": 0.3976055398193886, "learning_rate": 7.828217859591133e-07, "loss": 0.266, "step": 1830 }, { "epoch": 0.37987096774193546, "grad_norm": 0.4071477013255938, "learning_rate": 7.798420974691935e-07, "loss": 0.267, "step": 1840 }, { "epoch": 0.38193548387096776, "grad_norm": 0.42926938061270814, "learning_rate": 7.7684786656675e-07, "loss": 0.267, "step": 1850 }, { "epoch": 0.384, "grad_norm": 0.40068409678383476, "learning_rate": 7.738392488514627e-07, "loss": 0.2638, "step": 1860 }, { "epoch": 0.38606451612903225, "grad_norm": 0.41545866046107405, "learning_rate": 7.70816400670645e-07, "loss": 0.2648, "step": 1870 }, { "epoch": 0.3881290322580645, "grad_norm": 0.4023140436496999, "learning_rate": 7.677794791111168e-07, "loss": 0.2637, "step": 1880 }, { "epoch": 0.3901935483870968, "grad_norm": 0.4196388286712214, "learning_rate": 7.647286419910426e-07, "loss": 0.2647, "step": 1890 }, { "epoch": 0.39225806451612905, "grad_norm": 0.40124208669384503, "learning_rate": 7.616640478517293e-07, "loss": 0.2654, "step": 1900 }, { "epoch": 0.3943225806451613, "grad_norm": 0.41126451275454146, "learning_rate": 7.585858559493885e-07, "loss": 0.2631, "step": 1910 }, { "epoch": 0.39638709677419354, "grad_norm": 0.41848510984577836, "learning_rate": 7.554942262468593e-07, "loss": 0.2682, "step": 1920 }, { "epoch": 0.3984516129032258, "grad_norm": 0.43454563702411014, "learning_rate": 7.523893194052966e-07, "loss": 0.2619, "step": 1930 }, { "epoch": 0.4005161290322581, "grad_norm": 0.43881054463213787, "learning_rate": 7.49271296775821e-07, "loss": 0.2664, "step": 1940 }, { "epoch": 0.40258064516129033, "grad_norm": 0.4027456476422296, "learning_rate": 7.461403203911355e-07, "loss": 0.2659, "step": 1950 }, { "epoch": 0.4046451612903226, "grad_norm": 0.4130317888357524, "learning_rate": 7.429965529571036e-07, "loss": 0.261, "step": 1960 }, { "epoch": 0.4067096774193548, "grad_norm": 0.40488753602787214, "learning_rate": 7.398401578442952e-07, "loss": 0.263, "step": 1970 }, { "epoch": 0.4087741935483871, "grad_norm": 0.40658072770043274, "learning_rate": 7.366712990794961e-07, "loss": 0.2706, "step": 1980 }, { "epoch": 0.41083870967741937, "grad_norm": 0.4417207769552733, "learning_rate": 7.334901413371847e-07, "loss": 0.2695, "step": 1990 }, { "epoch": 0.4129032258064516, "grad_norm": 0.40600956756974876, "learning_rate": 7.302968499309737e-07, "loss": 0.265, "step": 2000 }, { "epoch": 0.41496774193548386, "grad_norm": 0.421884057260553, "learning_rate": 7.270915908050204e-07, "loss": 0.2631, "step": 2010 }, { "epoch": 0.4170322580645161, "grad_norm": 0.4060635608602976, "learning_rate": 7.238745305254019e-07, "loss": 0.2697, "step": 2020 }, { "epoch": 0.4190967741935484, "grad_norm": 0.44059203724336116, "learning_rate": 7.206458362714602e-07, "loss": 0.2565, "step": 2030 }, { "epoch": 0.42116129032258065, "grad_norm": 0.3968336903067748, "learning_rate": 7.17405675827114e-07, "loss": 0.2717, "step": 2040 }, { "epoch": 0.4232258064516129, "grad_norm": 0.41171391357598364, "learning_rate": 7.1415421757214e-07, "loss": 0.2645, "step": 2050 }, { "epoch": 0.42529032258064514, "grad_norm": 0.3876345602992099, "learning_rate": 7.10891630473422e-07, "loss": 0.2652, "step": 2060 }, { "epoch": 0.42735483870967744, "grad_norm": 0.39450051059803076, "learning_rate": 7.076180840761714e-07, "loss": 0.2632, "step": 2070 }, { "epoch": 0.4294193548387097, "grad_norm": 0.4358288881727055, "learning_rate": 7.043337484951154e-07, "loss": 0.2642, "step": 2080 }, { "epoch": 0.43148387096774193, "grad_norm": 0.41920035477123707, "learning_rate": 7.010387944056576e-07, "loss": 0.261, "step": 2090 }, { "epoch": 0.4335483870967742, "grad_norm": 0.4059103398768672, "learning_rate": 6.97733393035008e-07, "loss": 0.2628, "step": 2100 }, { "epoch": 0.4356129032258064, "grad_norm": 0.3982345695440609, "learning_rate": 6.944177161532851e-07, "loss": 0.2597, "step": 2110 }, { "epoch": 0.4376774193548387, "grad_norm": 0.4144966185638575, "learning_rate": 6.910919360645902e-07, "loss": 0.27, "step": 2120 }, { "epoch": 0.43974193548387097, "grad_norm": 0.4233480513748313, "learning_rate": 6.877562255980519e-07, "loss": 0.2681, "step": 2130 }, { "epoch": 0.4418064516129032, "grad_norm": 0.40910710385731447, "learning_rate": 6.844107580988471e-07, "loss": 0.2662, "step": 2140 }, { "epoch": 0.44387096774193546, "grad_norm": 0.4069330452268534, "learning_rate": 6.810557074191899e-07, "loss": 0.2633, "step": 2150 }, { "epoch": 0.44593548387096776, "grad_norm": 0.4033815804757132, "learning_rate": 6.776912479093001e-07, "loss": 0.2606, "step": 2160 }, { "epoch": 0.448, "grad_norm": 0.41960546237510354, "learning_rate": 6.743175544083403e-07, "loss": 0.2623, "step": 2170 }, { "epoch": 0.45006451612903225, "grad_norm": 0.41168810646722503, "learning_rate": 6.709348022353318e-07, "loss": 0.264, "step": 2180 }, { "epoch": 0.4521290322580645, "grad_norm": 0.40385762651618623, "learning_rate": 6.675431671800436e-07, "loss": 0.2651, "step": 2190 }, { "epoch": 0.4541935483870968, "grad_norm": 0.4032346492996413, "learning_rate": 6.64142825493856e-07, "loss": 0.2632, "step": 2200 }, { "epoch": 0.45625806451612905, "grad_norm": 0.4053652025972668, "learning_rate": 6.607339538806034e-07, "loss": 0.2608, "step": 2210 }, { "epoch": 0.4583225806451613, "grad_norm": 0.41770642881401504, "learning_rate": 6.573167294873898e-07, "loss": 0.2558, "step": 2220 }, { "epoch": 0.46038709677419354, "grad_norm": 0.4112896752142016, "learning_rate": 6.538913298953845e-07, "loss": 0.2646, "step": 2230 }, { "epoch": 0.4624516129032258, "grad_norm": 0.41305858313874766, "learning_rate": 6.504579331105928e-07, "loss": 0.2661, "step": 2240 }, { "epoch": 0.4645161290322581, "grad_norm": 0.3990060429263245, "learning_rate": 6.470167175546063e-07, "loss": 0.2552, "step": 2250 }, { "epoch": 0.46658064516129033, "grad_norm": 0.4068327568812493, "learning_rate": 6.435678620553306e-07, "loss": 0.2625, "step": 2260 }, { "epoch": 0.4686451612903226, "grad_norm": 0.4122018568807427, "learning_rate": 6.401115458376924e-07, "loss": 0.2561, "step": 2270 }, { "epoch": 0.4707096774193548, "grad_norm": 0.4075890652073717, "learning_rate": 6.366479485143257e-07, "loss": 0.2655, "step": 2280 }, { "epoch": 0.4727741935483871, "grad_norm": 0.4041531603835199, "learning_rate": 6.331772500762382e-07, "loss": 0.2608, "step": 2290 }, { "epoch": 0.47483870967741937, "grad_norm": 0.401347899960604, "learning_rate": 6.296996308834575e-07, "loss": 0.2626, "step": 2300 }, { "epoch": 0.4769032258064516, "grad_norm": 0.4046833913093797, "learning_rate": 6.262152716556586e-07, "loss": 0.2645, "step": 2310 }, { "epoch": 0.47896774193548386, "grad_norm": 0.4112501171173604, "learning_rate": 6.227243534627724e-07, "loss": 0.2627, "step": 2320 }, { "epoch": 0.4810322580645161, "grad_norm": 0.4119800419244549, "learning_rate": 6.192270577155764e-07, "loss": 0.2666, "step": 2330 }, { "epoch": 0.4830967741935484, "grad_norm": 0.4067394550798155, "learning_rate": 6.157235661562672e-07, "loss": 0.2609, "step": 2340 }, { "epoch": 0.48516129032258065, "grad_norm": 0.4161737935572665, "learning_rate": 6.122140608490157e-07, "loss": 0.2631, "step": 2350 }, { "epoch": 0.4872258064516129, "grad_norm": 0.41837478258205407, "learning_rate": 6.086987241705066e-07, "loss": 0.2613, "step": 2360 }, { "epoch": 0.48929032258064514, "grad_norm": 0.37786501702152653, "learning_rate": 6.051777388004603e-07, "loss": 0.2659, "step": 2370 }, { "epoch": 0.49135483870967744, "grad_norm": 0.4026726334273472, "learning_rate": 6.0165128771214e-07, "loss": 0.2668, "step": 2380 }, { "epoch": 0.4934193548387097, "grad_norm": 0.43109902087561547, "learning_rate": 5.981195541628431e-07, "loss": 0.2665, "step": 2390 }, { "epoch": 0.49548387096774194, "grad_norm": 0.40800799018925554, "learning_rate": 5.945827216843779e-07, "loss": 0.2637, "step": 2400 }, { "epoch": 0.4975483870967742, "grad_norm": 0.40953889079215977, "learning_rate": 5.910409740735263e-07, "loss": 0.267, "step": 2410 }, { "epoch": 0.4996129032258064, "grad_norm": 0.40899543891195417, "learning_rate": 5.874944953824919e-07, "loss": 0.2583, "step": 2420 }, { "epoch": 0.5016774193548387, "grad_norm": 0.4251510009606146, "learning_rate": 5.83943469909337e-07, "loss": 0.268, "step": 2430 }, { "epoch": 0.5037419354838709, "grad_norm": 0.4058826730393694, "learning_rate": 5.803880821884032e-07, "loss": 0.2579, "step": 2440 }, { "epoch": 0.5058064516129033, "grad_norm": 0.4240346499686985, "learning_rate": 5.768285169807233e-07, "loss": 0.2618, "step": 2450 }, { "epoch": 0.5078709677419355, "grad_norm": 0.4054651824039119, "learning_rate": 5.73264959264419e-07, "loss": 0.2587, "step": 2460 }, { "epoch": 0.5099354838709678, "grad_norm": 0.4264297129067109, "learning_rate": 5.696975942250896e-07, "loss": 0.2608, "step": 2470 }, { "epoch": 0.512, "grad_norm": 0.38763232793736896, "learning_rate": 5.661266072461866e-07, "loss": 0.2624, "step": 2480 }, { "epoch": 0.5140645161290323, "grad_norm": 0.39972658320821614, "learning_rate": 5.625521838993814e-07, "loss": 0.2628, "step": 2490 }, { "epoch": 0.5161290322580645, "grad_norm": 0.4094650932180596, "learning_rate": 5.589745099349219e-07, "loss": 0.2654, "step": 2500 }, { "epoch": 0.5181935483870967, "grad_norm": 0.40303191617270684, "learning_rate": 5.55393771271978e-07, "loss": 0.2626, "step": 2510 }, { "epoch": 0.520258064516129, "grad_norm": 0.4432634297156684, "learning_rate": 5.518101539889828e-07, "loss": 0.2631, "step": 2520 }, { "epoch": 0.5223225806451612, "grad_norm": 0.4019002372120617, "learning_rate": 5.482238443139597e-07, "loss": 0.2641, "step": 2530 }, { "epoch": 0.5243870967741936, "grad_norm": 0.3922554382852571, "learning_rate": 5.446350286148471e-07, "loss": 0.2588, "step": 2540 }, { "epoch": 0.5264516129032258, "grad_norm": 0.41838300381220644, "learning_rate": 5.410438933898127e-07, "loss": 0.2603, "step": 2550 }, { "epoch": 0.5285161290322581, "grad_norm": 0.4056835013387469, "learning_rate": 5.374506252575612e-07, "loss": 0.2655, "step": 2560 }, { "epoch": 0.5305806451612903, "grad_norm": 0.40888463409102277, "learning_rate": 5.338554109476379e-07, "loss": 0.2661, "step": 2570 }, { "epoch": 0.5326451612903226, "grad_norm": 0.4221212778601083, "learning_rate": 5.302584372907236e-07, "loss": 0.2643, "step": 2580 }, { "epoch": 0.5347096774193548, "grad_norm": 0.40948851318864904, "learning_rate": 5.266598912089259e-07, "loss": 0.2646, "step": 2590 }, { "epoch": 0.5367741935483871, "grad_norm": 0.3945682130480978, "learning_rate": 5.230599597060666e-07, "loss": 0.2622, "step": 2600 }, { "epoch": 0.5388387096774193, "grad_norm": 0.3959558379054268, "learning_rate": 5.194588298579623e-07, "loss": 0.2631, "step": 2610 }, { "epoch": 0.5409032258064516, "grad_norm": 0.4081097575523178, "learning_rate": 5.158566888027038e-07, "loss": 0.2596, "step": 2620 }, { "epoch": 0.5429677419354839, "grad_norm": 0.39268286624553117, "learning_rate": 5.122537237309305e-07, "loss": 0.2604, "step": 2630 }, { "epoch": 0.5450322580645162, "grad_norm": 0.39342604284402627, "learning_rate": 5.086501218761033e-07, "loss": 0.2586, "step": 2640 }, { "epoch": 0.5470967741935484, "grad_norm": 0.40285421355756235, "learning_rate": 5.050460705047742e-07, "loss": 0.2572, "step": 2650 }, { "epoch": 0.5491612903225807, "grad_norm": 0.4020063207626797, "learning_rate": 5.014417569068554e-07, "loss": 0.2643, "step": 2660 }, { "epoch": 0.5512258064516129, "grad_norm": 0.42131953987445797, "learning_rate": 4.978373683858858e-07, "loss": 0.2643, "step": 2670 }, { "epoch": 0.5532903225806451, "grad_norm": 0.3945931863557437, "learning_rate": 4.942330922492975e-07, "loss": 0.2645, "step": 2680 }, { "epoch": 0.5553548387096774, "grad_norm": 0.40345218634673974, "learning_rate": 4.906291157986834e-07, "loss": 0.2629, "step": 2690 }, { "epoch": 0.5574193548387096, "grad_norm": 0.4053650394538655, "learning_rate": 4.870256263200616e-07, "loss": 0.2596, "step": 2700 }, { "epoch": 0.5594838709677419, "grad_norm": 0.38082232410527134, "learning_rate": 4.834228110741447e-07, "loss": 0.2686, "step": 2710 }, { "epoch": 0.5615483870967742, "grad_norm": 0.4244897702153668, "learning_rate": 4.798208572866074e-07, "loss": 0.2654, "step": 2720 }, { "epoch": 0.5636129032258065, "grad_norm": 0.4168979030949182, "learning_rate": 4.762199521383575e-07, "loss": 0.2656, "step": 2730 }, { "epoch": 0.5656774193548387, "grad_norm": 0.4008885860052325, "learning_rate": 4.72620282755809e-07, "loss": 0.2641, "step": 2740 }, { "epoch": 0.567741935483871, "grad_norm": 0.4133977944936882, "learning_rate": 4.690220362011573e-07, "loss": 0.2624, "step": 2750 }, { "epoch": 0.5698064516129032, "grad_norm": 0.39400301829128825, "learning_rate": 4.6542539946265823e-07, "loss": 0.2598, "step": 2760 }, { "epoch": 0.5718709677419355, "grad_norm": 0.40929967482891283, "learning_rate": 4.618305594449113e-07, "loss": 0.263, "step": 2770 }, { "epoch": 0.5739354838709677, "grad_norm": 0.4056920391576304, "learning_rate": 4.5823770295914706e-07, "loss": 0.2595, "step": 2780 }, { "epoch": 0.576, "grad_norm": 0.4107265334626862, "learning_rate": 4.5464701671351815e-07, "loss": 0.2647, "step": 2790 }, { "epoch": 0.5780645161290323, "grad_norm": 0.3913927583282506, "learning_rate": 4.5105868730339785e-07, "loss": 0.2597, "step": 2800 }, { "epoch": 0.5801290322580646, "grad_norm": 0.41022478158711445, "learning_rate": 4.4747290120168316e-07, "loss": 0.2614, "step": 2810 }, { "epoch": 0.5821935483870968, "grad_norm": 0.4048943417693181, "learning_rate": 4.438898447491036e-07, "loss": 0.2623, "step": 2820 }, { "epoch": 0.584258064516129, "grad_norm": 0.41841621193034295, "learning_rate": 4.403097041445395e-07, "loss": 0.2626, "step": 2830 }, { "epoch": 0.5863225806451613, "grad_norm": 0.41332586169270713, "learning_rate": 4.367326654353436e-07, "loss": 0.2619, "step": 2840 }, { "epoch": 0.5883870967741935, "grad_norm": 0.42980292999632475, "learning_rate": 4.331589145076746e-07, "loss": 0.2662, "step": 2850 }, { "epoch": 0.5904516129032258, "grad_norm": 0.4085925990454811, "learning_rate": 4.295886370768367e-07, "loss": 0.2661, "step": 2860 }, { "epoch": 0.592516129032258, "grad_norm": 0.3938359040261475, "learning_rate": 4.2602201867762875e-07, "loss": 0.2549, "step": 2870 }, { "epoch": 0.5945806451612903, "grad_norm": 0.4009963393291789, "learning_rate": 4.224592446547024e-07, "loss": 0.2584, "step": 2880 }, { "epoch": 0.5966451612903226, "grad_norm": 0.40377828376876823, "learning_rate": 4.1890050015293036e-07, "loss": 0.2642, "step": 2890 }, { "epoch": 0.5987096774193549, "grad_norm": 0.4084739109095333, "learning_rate": 4.153459701077856e-07, "loss": 0.2637, "step": 2900 }, { "epoch": 0.6007741935483871, "grad_norm": 0.4355917374420026, "learning_rate": 4.117958392357303e-07, "loss": 0.267, "step": 2910 }, { "epoch": 0.6028387096774194, "grad_norm": 0.4111357071539257, "learning_rate": 4.082502920246173e-07, "loss": 0.2571, "step": 2920 }, { "epoch": 0.6049032258064516, "grad_norm": 0.4300310059373518, "learning_rate": 4.047095127241026e-07, "loss": 0.2663, "step": 2930 }, { "epoch": 0.6069677419354839, "grad_norm": 0.41504350370170773, "learning_rate": 4.011736853360702e-07, "loss": 0.2668, "step": 2940 }, { "epoch": 0.6090322580645161, "grad_norm": 0.39347081849396953, "learning_rate": 3.976429936050709e-07, "loss": 0.262, "step": 2950 }, { "epoch": 0.6110967741935484, "grad_norm": 0.4001140349315572, "learning_rate": 3.941176210087737e-07, "loss": 0.2607, "step": 2960 }, { "epoch": 0.6131612903225806, "grad_norm": 0.41999186019603213, "learning_rate": 3.905977507484304e-07, "loss": 0.2631, "step": 2970 }, { "epoch": 0.615225806451613, "grad_norm": 0.40433153562642776, "learning_rate": 3.870835657393558e-07, "loss": 0.2674, "step": 2980 }, { "epoch": 0.6172903225806452, "grad_norm": 0.41600570415494387, "learning_rate": 3.8357524860142205e-07, "loss": 0.2633, "step": 2990 }, { "epoch": 0.6193548387096774, "grad_norm": 0.39498755788207757, "learning_rate": 3.8007298164956866e-07, "loss": 0.2677, "step": 3000 }, { "epoch": 0.6214193548387097, "grad_norm": 0.4222886993315553, "learning_rate": 3.765769468843284e-07, "loss": 0.2513, "step": 3010 }, { "epoch": 0.6234838709677419, "grad_norm": 0.3886939892314166, "learning_rate": 3.7308732598236896e-07, "loss": 0.2589, "step": 3020 }, { "epoch": 0.6255483870967742, "grad_norm": 0.41019034012665107, "learning_rate": 3.696043002870521e-07, "loss": 0.2602, "step": 3030 }, { "epoch": 0.6276129032258064, "grad_norm": 0.41109492024152083, "learning_rate": 3.6612805079900954e-07, "loss": 0.2615, "step": 3040 }, { "epoch": 0.6296774193548387, "grad_norm": 0.40387895619985564, "learning_rate": 3.6265875816673784e-07, "loss": 0.2623, "step": 3050 }, { "epoch": 0.6317419354838709, "grad_norm": 0.41900812828527817, "learning_rate": 3.591966026772096e-07, "loss": 0.2588, "step": 3060 }, { "epoch": 0.6338064516129033, "grad_norm": 0.40787156582167655, "learning_rate": 3.557417642465055e-07, "loss": 0.2639, "step": 3070 }, { "epoch": 0.6358709677419355, "grad_norm": 0.3898972418936542, "learning_rate": 3.522944224104643e-07, "loss": 0.2649, "step": 3080 }, { "epoch": 0.6379354838709678, "grad_norm": 0.4141718763979276, "learning_rate": 3.4885475631535253e-07, "loss": 0.2692, "step": 3090 }, { "epoch": 0.64, "grad_norm": 0.41506013689499804, "learning_rate": 3.4542294470855626e-07, "loss": 0.2602, "step": 3100 }, { "epoch": 0.6420645161290323, "grad_norm": 0.39476928102019726, "learning_rate": 3.4199916592929055e-07, "loss": 0.261, "step": 3110 }, { "epoch": 0.6441290322580645, "grad_norm": 0.416429380761246, "learning_rate": 3.3858359789933313e-07, "loss": 0.2627, "step": 3120 }, { "epoch": 0.6461935483870968, "grad_norm": 0.40310812066816015, "learning_rate": 3.351764181137771e-07, "loss": 0.2636, "step": 3130 }, { "epoch": 0.648258064516129, "grad_norm": 0.3946905030128788, "learning_rate": 3.3177780363180923e-07, "loss": 0.2622, "step": 3140 }, { "epoch": 0.6503225806451612, "grad_norm": 0.42397756082438576, "learning_rate": 3.2838793106750625e-07, "loss": 0.2603, "step": 3150 }, { "epoch": 0.6523870967741936, "grad_norm": 0.4169594318618278, "learning_rate": 3.250069765806586e-07, "loss": 0.2613, "step": 3160 }, { "epoch": 0.6544516129032258, "grad_norm": 0.41756086123454705, "learning_rate": 3.2163511586761566e-07, "loss": 0.2617, "step": 3170 }, { "epoch": 0.6565161290322581, "grad_norm": 0.40493296338507545, "learning_rate": 3.1827252415215454e-07, "loss": 0.2656, "step": 3180 }, { "epoch": 0.6585806451612903, "grad_norm": 0.4086571674620378, "learning_rate": 3.149193761763764e-07, "loss": 0.2611, "step": 3190 }, { "epoch": 0.6606451612903226, "grad_norm": 0.4171128006614707, "learning_rate": 3.115758461916229e-07, "loss": 0.2597, "step": 3200 }, { "epoch": 0.6627096774193548, "grad_norm": 0.3880167728055982, "learning_rate": 3.0824210794942333e-07, "loss": 0.263, "step": 3210 }, { "epoch": 0.6647741935483871, "grad_norm": 0.40448031317959615, "learning_rate": 3.049183346924643e-07, "loss": 0.2632, "step": 3220 }, { "epoch": 0.6668387096774193, "grad_norm": 0.41914072800271474, "learning_rate": 3.016046991455865e-07, "loss": 0.2579, "step": 3230 }, { "epoch": 0.6689032258064516, "grad_norm": 0.3860018527353455, "learning_rate": 2.983013735068105e-07, "loss": 0.2647, "step": 3240 }, { "epoch": 0.6709677419354839, "grad_norm": 0.40975610194833284, "learning_rate": 2.9500852943838603e-07, "loss": 0.2573, "step": 3250 }, { "epoch": 0.6730322580645162, "grad_norm": 0.42646644618083696, "learning_rate": 2.9172633805787293e-07, "loss": 0.2653, "step": 3260 }, { "epoch": 0.6750967741935484, "grad_norm": 0.4086698532968832, "learning_rate": 2.88454969929248e-07, "loss": 0.2574, "step": 3270 }, { "epoch": 0.6771612903225807, "grad_norm": 0.4178375142437365, "learning_rate": 2.851945950540419e-07, "loss": 0.2623, "step": 3280 }, { "epoch": 0.6792258064516129, "grad_norm": 0.4057288769351614, "learning_rate": 2.819453828625038e-07, "loss": 0.2651, "step": 3290 }, { "epoch": 0.6812903225806451, "grad_norm": 0.4158815157531405, "learning_rate": 2.787075022047981e-07, "loss": 0.263, "step": 3300 }, { "epoch": 0.6833548387096774, "grad_norm": 0.4049970316693273, "learning_rate": 2.754811213422288e-07, "loss": 0.2645, "step": 3310 }, { "epoch": 0.6854193548387096, "grad_norm": 0.39671368245623034, "learning_rate": 2.722664079384954e-07, "loss": 0.2589, "step": 3320 }, { "epoch": 0.6874838709677419, "grad_norm": 0.4039120828242038, "learning_rate": 2.6906352905098116e-07, "loss": 0.2614, "step": 3330 }, { "epoch": 0.6895483870967742, "grad_norm": 0.4170702189116275, "learning_rate": 2.658726511220712e-07, "loss": 0.2657, "step": 3340 }, { "epoch": 0.6916129032258065, "grad_norm": 0.4237911525616141, "learning_rate": 2.6269393997050205e-07, "loss": 0.2618, "step": 3350 }, { "epoch": 0.6936774193548387, "grad_norm": 0.4111737496158447, "learning_rate": 2.595275607827457e-07, "loss": 0.2606, "step": 3360 }, { "epoch": 0.695741935483871, "grad_norm": 0.38990938914606454, "learning_rate": 2.563736781044262e-07, "loss": 0.2577, "step": 3370 }, { "epoch": 0.6978064516129032, "grad_norm": 0.407914899989363, "learning_rate": 2.5323245583176667e-07, "loss": 0.2609, "step": 3380 }, { "epoch": 0.6998709677419355, "grad_norm": 0.39451690942708684, "learning_rate": 2.5010405720307355e-07, "loss": 0.2595, "step": 3390 }, { "epoch": 0.7019354838709677, "grad_norm": 0.4092342022576978, "learning_rate": 2.469886447902541e-07, "loss": 0.2627, "step": 3400 }, { "epoch": 0.704, "grad_norm": 0.39988371342369805, "learning_rate": 2.438863804903666e-07, "loss": 0.262, "step": 3410 }, { "epoch": 0.7060645161290322, "grad_norm": 0.3964335866793338, "learning_rate": 2.4079742551720887e-07, "loss": 0.2592, "step": 3420 }, { "epoch": 0.7081290322580646, "grad_norm": 0.4315689515435995, "learning_rate": 2.3772194039293896e-07, "loss": 0.2629, "step": 3430 }, { "epoch": 0.7101935483870968, "grad_norm": 0.4070533032882783, "learning_rate": 2.3466008493973477e-07, "loss": 0.2634, "step": 3440 }, { "epoch": 0.712258064516129, "grad_norm": 0.4139707970034922, "learning_rate": 2.3161201827148725e-07, "loss": 0.2668, "step": 3450 }, { "epoch": 0.7143225806451613, "grad_norm": 0.4080257693965919, "learning_rate": 2.2857789878553309e-07, "loss": 0.2639, "step": 3460 }, { "epoch": 0.7163870967741935, "grad_norm": 0.38944573511805763, "learning_rate": 2.2555788415442288e-07, "loss": 0.2591, "step": 3470 }, { "epoch": 0.7184516129032258, "grad_norm": 0.40451831206378125, "learning_rate": 2.22552131317727e-07, "loss": 0.2608, "step": 3480 }, { "epoch": 0.720516129032258, "grad_norm": 0.40945571442698814, "learning_rate": 2.1956079647388025e-07, "loss": 0.254, "step": 3490 }, { "epoch": 0.7225806451612903, "grad_norm": 0.4120262445632641, "learning_rate": 2.165840350720655e-07, "loss": 0.2634, "step": 3500 }, { "epoch": 0.7246451612903225, "grad_norm": 0.38102966990936765, "learning_rate": 2.1362200180413481e-07, "loss": 0.2612, "step": 3510 }, { "epoch": 0.7267096774193549, "grad_norm": 0.40448293811396235, "learning_rate": 2.1067485059657032e-07, "loss": 0.2654, "step": 3520 }, { "epoch": 0.7287741935483871, "grad_norm": 0.42379282553088654, "learning_rate": 2.0774273460248577e-07, "loss": 0.266, "step": 3530 }, { "epoch": 0.7308387096774194, "grad_norm": 0.3958635594454363, "learning_rate": 2.0482580619366796e-07, "loss": 0.2599, "step": 3540 }, { "epoch": 0.7329032258064516, "grad_norm": 0.3929275138734596, "learning_rate": 2.019242169526581e-07, "loss": 0.2614, "step": 3550 }, { "epoch": 0.7349677419354839, "grad_norm": 0.4099908819814468, "learning_rate": 1.9903811766487426e-07, "loss": 0.2595, "step": 3560 }, { "epoch": 0.7370322580645161, "grad_norm": 0.4136881756772272, "learning_rate": 1.9616765831077603e-07, "loss": 0.268, "step": 3570 }, { "epoch": 0.7390967741935484, "grad_norm": 0.4103952583965791, "learning_rate": 1.9331298805807095e-07, "loss": 0.2667, "step": 3580 }, { "epoch": 0.7411612903225806, "grad_norm": 0.4043875841263039, "learning_rate": 1.9047425525396161e-07, "loss": 0.2591, "step": 3590 }, { "epoch": 0.743225806451613, "grad_norm": 0.40432519757481955, "learning_rate": 1.876516074174379e-07, "loss": 0.2583, "step": 3600 }, { "epoch": 0.7452903225806452, "grad_norm": 0.3923980263069265, "learning_rate": 1.848451912316103e-07, "loss": 0.2622, "step": 3610 }, { "epoch": 0.7473548387096774, "grad_norm": 0.41193174262995386, "learning_rate": 1.8205515253608688e-07, "loss": 0.2591, "step": 3620 }, { "epoch": 0.7494193548387097, "grad_norm": 0.3997627378786646, "learning_rate": 1.792816363193952e-07, "loss": 0.2632, "step": 3630 }, { "epoch": 0.7514838709677419, "grad_norm": 0.4203820131288817, "learning_rate": 1.7652478671144755e-07, "loss": 0.2603, "step": 3640 }, { "epoch": 0.7535483870967742, "grad_norm": 0.41133420796621517, "learning_rate": 1.7378474697605128e-07, "loss": 0.2642, "step": 3650 }, { "epoch": 0.7556129032258064, "grad_norm": 0.4037148313043383, "learning_rate": 1.7106165950346318e-07, "loss": 0.2656, "step": 3660 }, { "epoch": 0.7576774193548387, "grad_norm": 0.4010420205215928, "learning_rate": 1.683556658029903e-07, "loss": 0.2601, "step": 3670 }, { "epoch": 0.7597419354838709, "grad_norm": 0.4278976559359214, "learning_rate": 1.656669064956368e-07, "loss": 0.2586, "step": 3680 }, { "epoch": 0.7618064516129033, "grad_norm": 0.41318596694086984, "learning_rate": 1.6299552130679578e-07, "loss": 0.2652, "step": 3690 }, { "epoch": 0.7638709677419355, "grad_norm": 0.41756399746678385, "learning_rate": 1.6034164905898768e-07, "loss": 0.2634, "step": 3700 }, { "epoch": 0.7659354838709678, "grad_norm": 0.45439314697770533, "learning_rate": 1.5770542766464773e-07, "loss": 0.2616, "step": 3710 }, { "epoch": 0.768, "grad_norm": 0.3959443888976775, "learning_rate": 1.5508699411895738e-07, "loss": 0.2668, "step": 3720 }, { "epoch": 0.7700645161290323, "grad_norm": 0.39850312610937977, "learning_rate": 1.524864844927266e-07, "loss": 0.2646, "step": 3730 }, { "epoch": 0.7721290322580645, "grad_norm": 0.41376874719752166, "learning_rate": 1.4990403392532159e-07, "loss": 0.2577, "step": 3740 }, { "epoch": 0.7741935483870968, "grad_norm": 0.4063544496998586, "learning_rate": 1.473397766176431e-07, "loss": 0.2649, "step": 3750 }, { "epoch": 0.776258064516129, "grad_norm": 0.4353014336434687, "learning_rate": 1.4479384582515153e-07, "loss": 0.2643, "step": 3760 }, { "epoch": 0.7783225806451612, "grad_norm": 0.4018175153121587, "learning_rate": 1.4226637385094247e-07, "loss": 0.2618, "step": 3770 }, { "epoch": 0.7803870967741936, "grad_norm": 0.42157127333864497, "learning_rate": 1.3975749203887228e-07, "loss": 0.2651, "step": 3780 }, { "epoch": 0.7824516129032258, "grad_norm": 0.43186635599469986, "learning_rate": 1.3726733076673085e-07, "loss": 0.2633, "step": 3790 }, { "epoch": 0.7845161290322581, "grad_norm": 0.3964540005139217, "learning_rate": 1.3479601943946761e-07, "loss": 0.2566, "step": 3800 }, { "epoch": 0.7865806451612903, "grad_norm": 0.44845859907363916, "learning_rate": 1.323436864824664e-07, "loss": 0.2635, "step": 3810 }, { "epoch": 0.7886451612903226, "grad_norm": 0.39439621730318203, "learning_rate": 1.299104593348721e-07, "loss": 0.267, "step": 3820 }, { "epoch": 0.7907096774193548, "grad_norm": 0.4258443910811124, "learning_rate": 1.2749646444296703e-07, "loss": 0.2629, "step": 3830 }, { "epoch": 0.7927741935483871, "grad_norm": 0.4061749201396272, "learning_rate": 1.2510182725360086e-07, "loss": 0.256, "step": 3840 }, { "epoch": 0.7948387096774193, "grad_norm": 0.4053363945100216, "learning_rate": 1.2272667220767158e-07, "loss": 0.267, "step": 3850 }, { "epoch": 0.7969032258064516, "grad_norm": 0.39724264268663745, "learning_rate": 1.2037112273365818e-07, "loss": 0.2601, "step": 3860 }, { "epoch": 0.7989677419354839, "grad_norm": 0.40962689626618026, "learning_rate": 1.1803530124120714e-07, "loss": 0.2614, "step": 3870 }, { "epoch": 0.8010322580645162, "grad_norm": 0.39171805970284057, "learning_rate": 1.157193291147705e-07, "loss": 0.2604, "step": 3880 }, { "epoch": 0.8030967741935484, "grad_norm": 0.38720737774209957, "learning_rate": 1.1342332670729882e-07, "loss": 0.258, "step": 3890 }, { "epoch": 0.8051612903225807, "grad_norm": 0.398012624254619, "learning_rate": 1.1114741333398592e-07, "loss": 0.2621, "step": 3900 }, { "epoch": 0.8072258064516129, "grad_norm": 0.40289439621605116, "learning_rate": 1.0889170726606933e-07, "loss": 0.2586, "step": 3910 }, { "epoch": 0.8092903225806451, "grad_norm": 0.4232682123948614, "learning_rate": 1.066563257246838e-07, "loss": 0.2569, "step": 3920 }, { "epoch": 0.8113548387096774, "grad_norm": 0.4028783048716607, "learning_rate": 1.0444138487476944e-07, "loss": 0.2609, "step": 3930 }, { "epoch": 0.8134193548387096, "grad_norm": 0.4002686348680681, "learning_rate": 1.0224699981903517e-07, "loss": 0.2654, "step": 3940 }, { "epoch": 0.8154838709677419, "grad_norm": 0.39543469139493387, "learning_rate": 1.0007328459197778e-07, "loss": 0.2628, "step": 3950 }, { "epoch": 0.8175483870967742, "grad_norm": 0.4157630096664263, "learning_rate": 9.792035215395556e-08, "loss": 0.263, "step": 3960 }, { "epoch": 0.8196129032258065, "grad_norm": 0.41685800951642293, "learning_rate": 9.578831438531776e-08, "loss": 0.2669, "step": 3970 }, { "epoch": 0.8216774193548387, "grad_norm": 0.4061936200965336, "learning_rate": 9.3677282080591e-08, "loss": 0.2622, "step": 3980 }, { "epoch": 0.823741935483871, "grad_norm": 0.40925273863210293, "learning_rate": 9.158736494272179e-08, "loss": 0.2612, "step": 3990 }, { "epoch": 0.8258064516129032, "grad_norm": 0.40618534177947946, "learning_rate": 8.951867157737558e-08, "loss": 0.2682, "step": 4000 }, { "epoch": 0.8278709677419355, "grad_norm": 0.3979706890222173, "learning_rate": 8.747130948729226e-08, "loss": 0.2596, "step": 4010 }, { "epoch": 0.8299354838709677, "grad_norm": 0.4071872432393417, "learning_rate": 8.544538506670074e-08, "loss": 0.2587, "step": 4020 }, { "epoch": 0.832, "grad_norm": 0.40836170061759924, "learning_rate": 8.344100359578904e-08, "loss": 0.2588, "step": 4030 }, { "epoch": 0.8340645161290322, "grad_norm": 0.3895000386110786, "learning_rate": 8.145826923523358e-08, "loss": 0.2547, "step": 4040 }, { "epoch": 0.8361290322580646, "grad_norm": 0.40154696748699115, "learning_rate": 7.949728502078668e-08, "loss": 0.2584, "step": 4050 }, { "epoch": 0.8381935483870968, "grad_norm": 0.4376818236899298, "learning_rate": 7.755815285792172e-08, "loss": 0.2688, "step": 4060 }, { "epoch": 0.840258064516129, "grad_norm": 0.4046160460755729, "learning_rate": 7.564097351653742e-08, "loss": 0.2705, "step": 4070 }, { "epoch": 0.8423225806451613, "grad_norm": 0.39547101151078623, "learning_rate": 7.374584662572142e-08, "loss": 0.2659, "step": 4080 }, { "epoch": 0.8443870967741935, "grad_norm": 0.37332809148900736, "learning_rate": 7.187287066857289e-08, "loss": 0.2574, "step": 4090 }, { "epoch": 0.8464516129032258, "grad_norm": 0.46033640896289585, "learning_rate": 7.002214297708481e-08, "loss": 0.2569, "step": 4100 }, { "epoch": 0.848516129032258, "grad_norm": 0.39191927118713255, "learning_rate": 6.819375972708536e-08, "loss": 0.258, "step": 4110 }, { "epoch": 0.8505806451612903, "grad_norm": 0.41428077941004704, "learning_rate": 6.6387815933241e-08, "loss": 0.2618, "step": 4120 }, { "epoch": 0.8526451612903225, "grad_norm": 0.4107387220224137, "learning_rate": 6.460440544411777e-08, "loss": 0.2622, "step": 4130 }, { "epoch": 0.8547096774193549, "grad_norm": 0.39642375544117775, "learning_rate": 6.284362093730545e-08, "loss": 0.2585, "step": 4140 }, { "epoch": 0.8567741935483871, "grad_norm": 0.37930337406912923, "learning_rate": 6.110555391460026e-08, "loss": 0.2617, "step": 4150 }, { "epoch": 0.8588387096774194, "grad_norm": 0.377232478401539, "learning_rate": 5.9390294697251045e-08, "loss": 0.2583, "step": 4160 }, { "epoch": 0.8609032258064516, "grad_norm": 0.3888835569603603, "learning_rate": 5.7697932421264415e-08, "loss": 0.2529, "step": 4170 }, { "epoch": 0.8629677419354839, "grad_norm": 0.3934785671025381, "learning_rate": 5.602855503277376e-08, "loss": 0.2593, "step": 4180 }, { "epoch": 0.8650322580645161, "grad_norm": 0.38987380628908475, "learning_rate": 5.438224928346791e-08, "loss": 0.2611, "step": 4190 }, { "epoch": 0.8670967741935484, "grad_norm": 0.40191458902063176, "learning_rate": 5.275910072608408e-08, "loss": 0.2648, "step": 4200 }, { "epoch": 0.8691612903225806, "grad_norm": 0.40555133430607165, "learning_rate": 5.115919370996097e-08, "loss": 0.2646, "step": 4210 }, { "epoch": 0.8712258064516128, "grad_norm": 0.39189346564182975, "learning_rate": 4.9582611376655924e-08, "loss": 0.2697, "step": 4220 }, { "epoch": 0.8732903225806452, "grad_norm": 0.3977403739928427, "learning_rate": 4.8029435655624785e-08, "loss": 0.256, "step": 4230 }, { "epoch": 0.8753548387096775, "grad_norm": 0.4107418168891212, "learning_rate": 4.6499747259963254e-08, "loss": 0.2618, "step": 4240 }, { "epoch": 0.8774193548387097, "grad_norm": 0.4152156746116232, "learning_rate": 4.499362568221327e-08, "loss": 0.2562, "step": 4250 }, { "epoch": 0.8794838709677419, "grad_norm": 0.41269224554676137, "learning_rate": 4.351114919023197e-08, "loss": 0.2638, "step": 4260 }, { "epoch": 0.8815483870967742, "grad_norm": 0.39019715520848103, "learning_rate": 4.205239482312445e-08, "loss": 0.2608, "step": 4270 }, { "epoch": 0.8836129032258064, "grad_norm": 0.39460366251134543, "learning_rate": 4.0617438387239746e-08, "loss": 0.2644, "step": 4280 }, { "epoch": 0.8856774193548387, "grad_norm": 0.38841049201774, "learning_rate": 3.9206354452232135e-08, "loss": 0.2586, "step": 4290 }, { "epoch": 0.8877419354838709, "grad_norm": 0.3995452257322332, "learning_rate": 3.7819216347185715e-08, "loss": 0.2632, "step": 4300 }, { "epoch": 0.8898064516129032, "grad_norm": 0.3921492973317569, "learning_rate": 3.6456096156803616e-08, "loss": 0.2591, "step": 4310 }, { "epoch": 0.8918709677419355, "grad_norm": 0.37963166184003594, "learning_rate": 3.5117064717662406e-08, "loss": 0.2574, "step": 4320 }, { "epoch": 0.8939354838709678, "grad_norm": 0.4129813226681988, "learning_rate": 3.380219161453063e-08, "loss": 0.2662, "step": 4330 }, { "epoch": 0.896, "grad_norm": 0.40974368918108645, "learning_rate": 3.251154517675264e-08, "loss": 0.2604, "step": 4340 }, { "epoch": 0.8980645161290323, "grad_norm": 0.4245296466579207, "learning_rate": 3.124519247469814e-08, "loss": 0.2607, "step": 4350 }, { "epoch": 0.9001290322580645, "grad_norm": 0.42346220490081854, "learning_rate": 3.0003199316276486e-08, "loss": 0.2568, "step": 4360 }, { "epoch": 0.9021935483870968, "grad_norm": 0.384390730131664, "learning_rate": 2.8785630243517156e-08, "loss": 0.2554, "step": 4370 }, { "epoch": 0.904258064516129, "grad_norm": 0.4161617174420004, "learning_rate": 2.759254852921522e-08, "loss": 0.2611, "step": 4380 }, { "epoch": 0.9063225806451612, "grad_norm": 0.4096140142802804, "learning_rate": 2.6424016173643816e-08, "loss": 0.2613, "step": 4390 }, { "epoch": 0.9083870967741936, "grad_norm": 0.4036134224250512, "learning_rate": 2.5280093901331957e-08, "loss": 0.2564, "step": 4400 }, { "epoch": 0.9104516129032258, "grad_norm": 0.3951213596923248, "learning_rate": 2.4160841157908894e-08, "loss": 0.2626, "step": 4410 }, { "epoch": 0.9125161290322581, "grad_norm": 0.4255511159427451, "learning_rate": 2.3066316107014984e-08, "loss": 0.267, "step": 4420 }, { "epoch": 0.9145806451612903, "grad_norm": 0.39941397499664477, "learning_rate": 2.199657562727919e-08, "loss": 0.2644, "step": 4430 }, { "epoch": 0.9166451612903226, "grad_norm": 0.41202712449315076, "learning_rate": 2.0951675309363038e-08, "loss": 0.2662, "step": 4440 }, { "epoch": 0.9187096774193548, "grad_norm": 0.4141354253620865, "learning_rate": 1.9931669453072064e-08, "loss": 0.2682, "step": 4450 }, { "epoch": 0.9207741935483871, "grad_norm": 0.407975000927539, "learning_rate": 1.893661106453387e-08, "loss": 0.2657, "step": 4460 }, { "epoch": 0.9228387096774193, "grad_norm": 0.4080505082932939, "learning_rate": 1.7966551853443813e-08, "loss": 0.2591, "step": 4470 }, { "epoch": 0.9249032258064516, "grad_norm": 0.4177794728607882, "learning_rate": 1.7021542230377495e-08, "loss": 0.2602, "step": 4480 }, { "epoch": 0.9269677419354839, "grad_norm": 0.4337602592447264, "learning_rate": 1.610163130417119e-08, "loss": 0.2629, "step": 4490 }, { "epoch": 0.9290322580645162, "grad_norm": 0.40025965085906845, "learning_rate": 1.520686687937006e-08, "loss": 0.2601, "step": 4500 }, { "epoch": 0.9310967741935484, "grad_norm": 0.3954536343382873, "learning_rate": 1.4337295453743848e-08, "loss": 0.2625, "step": 4510 }, { "epoch": 0.9331612903225807, "grad_norm": 0.4030179174929269, "learning_rate": 1.3492962215870208e-08, "loss": 0.2625, "step": 4520 }, { "epoch": 0.9352258064516129, "grad_norm": 0.40819467221659395, "learning_rate": 1.2673911042786812e-08, "loss": 0.2623, "step": 4530 }, { "epoch": 0.9372903225806452, "grad_norm": 0.3975548605776835, "learning_rate": 1.188018449771111e-08, "loss": 0.2587, "step": 4540 }, { "epoch": 0.9393548387096774, "grad_norm": 0.38620015604289587, "learning_rate": 1.1111823827828438e-08, "loss": 0.2629, "step": 4550 }, { "epoch": 0.9414193548387096, "grad_norm": 0.3915952951322532, "learning_rate": 1.0368868962148446e-08, "loss": 0.2602, "step": 4560 }, { "epoch": 0.9434838709677419, "grad_norm": 0.42822828805165253, "learning_rate": 9.651358509430385e-09, "loss": 0.2668, "step": 4570 }, { "epoch": 0.9455483870967742, "grad_norm": 0.4110557870118209, "learning_rate": 8.959329756176359e-09, "loss": 0.2614, "step": 4580 }, { "epoch": 0.9476129032258065, "grad_norm": 0.4051400508982645, "learning_rate": 8.292818664694223e-09, "loss": 0.2579, "step": 4590 }, { "epoch": 0.9496774193548387, "grad_norm": 0.41096745151064146, "learning_rate": 7.651859871228072e-09, "loss": 0.2638, "step": 4600 }, { "epoch": 0.951741935483871, "grad_norm": 0.40156811491530275, "learning_rate": 7.0364866841589045e-09, "loss": 0.2631, "step": 4610 }, { "epoch": 0.9538064516129032, "grad_norm": 0.4336183195339135, "learning_rate": 6.446731082273449e-09, "loss": 0.2626, "step": 4620 }, { "epoch": 0.9558709677419355, "grad_norm": 0.41525878972145586, "learning_rate": 5.8826237131022196e-09, "loss": 0.2637, "step": 4630 }, { "epoch": 0.9579354838709677, "grad_norm": 0.39563865795758707, "learning_rate": 5.344193891327286e-09, "loss": 0.2599, "step": 4640 }, { "epoch": 0.96, "grad_norm": 0.3902289846827882, "learning_rate": 4.831469597258331e-09, "loss": 0.2588, "step": 4650 }, { "epoch": 0.9620645161290322, "grad_norm": 0.4265778114435462, "learning_rate": 4.344477475379027e-09, "loss": 0.263, "step": 4660 }, { "epoch": 0.9641290322580646, "grad_norm": 0.3952736993136822, "learning_rate": 3.883242832962319e-09, "loss": 0.266, "step": 4670 }, { "epoch": 0.9661935483870968, "grad_norm": 0.4204128593760075, "learning_rate": 3.4477896387552497e-09, "loss": 0.2632, "step": 4680 }, { "epoch": 0.9682580645161291, "grad_norm": 0.39870257721591323, "learning_rate": 3.0381405217333457e-09, "loss": 0.2598, "step": 4690 }, { "epoch": 0.9703225806451613, "grad_norm": 0.40504192880628953, "learning_rate": 2.6543167699247248e-09, "loss": 0.2663, "step": 4700 }, { "epoch": 0.9723870967741935, "grad_norm": 0.4276504248620953, "learning_rate": 2.2963383293039264e-09, "loss": 0.2681, "step": 4710 }, { "epoch": 0.9744516129032258, "grad_norm": 0.4194237088370349, "learning_rate": 1.964223802755238e-09, "loss": 0.2642, "step": 4720 }, { "epoch": 0.976516129032258, "grad_norm": 0.41830150874097594, "learning_rate": 1.6579904491059726e-09, "loss": 0.257, "step": 4730 }, { "epoch": 0.9785806451612903, "grad_norm": 0.381130263031969, "learning_rate": 1.3776541822297926e-09, "loss": 0.2652, "step": 4740 }, { "epoch": 0.9806451612903225, "grad_norm": 0.4000580182685434, "learning_rate": 1.1232295702193751e-09, "loss": 0.2635, "step": 4750 }, { "epoch": 0.9827096774193549, "grad_norm": 0.41681278877265543, "learning_rate": 8.947298346296816e-10, "loss": 0.2683, "step": 4760 }, { "epoch": 0.9847741935483871, "grad_norm": 0.40430126615446177, "learning_rate": 6.921668497907873e-10, "loss": 0.262, "step": 4770 }, { "epoch": 0.9868387096774194, "grad_norm": 0.41793940361219006, "learning_rate": 5.155511421906511e-10, "loss": 0.2619, "step": 4780 }, { "epoch": 0.9889032258064516, "grad_norm": 0.4020044075973662, "learning_rate": 3.64891889928276e-10, "loss": 0.262, "step": 4790 }, { "epoch": 0.9909677419354839, "grad_norm": 0.39705009551285064, "learning_rate": 2.4019692223675727e-10, "loss": 0.2597, "step": 4800 }, { "epoch": 0.9930322580645161, "grad_norm": 0.41207414069949416, "learning_rate": 1.4147271907621883e-10, "loss": 0.2605, "step": 4810 }, { "epoch": 0.9950967741935484, "grad_norm": 0.4262315482989849, "learning_rate": 6.87244107974716e-11, "loss": 0.2601, "step": 4820 }, { "epoch": 0.9971612903225806, "grad_norm": 0.4195255805487681, "learning_rate": 2.1955777874838045e-11, "loss": 0.2636, "step": 4830 }, { "epoch": 0.9992258064516129, "grad_norm": 0.40670072777909505, "learning_rate": 1.1692507103089334e-12, "loss": 0.2565, "step": 4840 }, { "epoch": 0.9998451612903225, "step": 4843, "total_flos": 1061427576569856.0, "train_loss": 0.09964955267816591, "train_runtime": 121089.0768, "train_samples_per_second": 10.24, "train_steps_per_second": 0.04 } ], "logging_steps": 10, "max_steps": 4843, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1061427576569856.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }