| { | |
| "best_metric": 1.151181697845459, | |
| "best_model_checkpoint": "miner_id_besimray/checkpoint-80", | |
| "epoch": 5.894736842105263, | |
| "eval_steps": 20, | |
| "global_step": 280, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.021052631578947368, | |
| "grad_norm": 0.25488582253456116, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2983, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.021052631578947368, | |
| "eval_loss": 1.2585705518722534, | |
| "eval_runtime": 14.9372, | |
| "eval_samples_per_second": 6.695, | |
| "eval_steps_per_second": 0.669, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": 0.2551250755786896, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4576, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06315789473684211, | |
| "grad_norm": 0.22965364158153534, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2758, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "grad_norm": 0.25596627593040466, | |
| "learning_rate": 8e-05, | |
| "loss": 1.4291, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 0.21169574558734894, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2482, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12631578947368421, | |
| "grad_norm": 0.2537442147731781, | |
| "learning_rate": 0.00012, | |
| "loss": 1.4111, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14736842105263157, | |
| "grad_norm": 0.22837992012500763, | |
| "learning_rate": 0.00014, | |
| "loss": 1.338, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": 0.16500858962535858, | |
| "learning_rate": 0.00016, | |
| "loss": 1.2243, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.18947368421052632, | |
| "grad_norm": 0.2048870176076889, | |
| "learning_rate": 0.00018, | |
| "loss": 1.2117, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 0.22877398133277893, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3922, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.23157894736842105, | |
| "grad_norm": 0.25871542096138, | |
| "learning_rate": 0.0001999999780359183, | |
| "loss": 1.2073, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.25263157894736843, | |
| "grad_norm": 0.18334853649139404, | |
| "learning_rate": 0.00019999991214368284, | |
| "loss": 1.2268, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2736842105263158, | |
| "grad_norm": 0.1385767012834549, | |
| "learning_rate": 0.0001999998023233226, | |
| "loss": 1.0728, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.29473684210526313, | |
| "grad_norm": 0.12759718298912048, | |
| "learning_rate": 0.0001999996485748858, | |
| "loss": 1.0786, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 0.13563676178455353, | |
| "learning_rate": 0.00019999945089843994, | |
| "loss": 1.0021, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": 0.12118455767631531, | |
| "learning_rate": 0.0001999992092940719, | |
| "loss": 1.2168, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.35789473684210527, | |
| "grad_norm": 0.17731498181819916, | |
| "learning_rate": 0.00019999892376188782, | |
| "loss": 1.2883, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.37894736842105264, | |
| "grad_norm": 0.1495707631111145, | |
| "learning_rate": 0.0001999985943020131, | |
| "loss": 1.2307, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.14801433682441711, | |
| "learning_rate": 0.00019999822091459248, | |
| "loss": 1.2703, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.15497420728206635, | |
| "learning_rate": 0.00019999780359979, | |
| "loss": 1.3601, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "eval_loss": 1.1756575107574463, | |
| "eval_runtime": 15.1128, | |
| "eval_samples_per_second": 6.617, | |
| "eval_steps_per_second": 0.662, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4421052631578947, | |
| "grad_norm": 0.154701828956604, | |
| "learning_rate": 0.00019999734235778894, | |
| "loss": 1.0972, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4631578947368421, | |
| "grad_norm": 0.12257974594831467, | |
| "learning_rate": 0.00019999683718879195, | |
| "loss": 1.1799, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4842105263157895, | |
| "grad_norm": 0.14035549759864807, | |
| "learning_rate": 0.0001999962880930209, | |
| "loss": 1.2342, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5052631578947369, | |
| "grad_norm": 0.1992308348417282, | |
| "learning_rate": 0.00019999569507071706, | |
| "loss": 1.2253, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 0.1479017287492752, | |
| "learning_rate": 0.00019999505812214085, | |
| "loss": 1.2039, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5473684210526316, | |
| "grad_norm": 0.16983704268932343, | |
| "learning_rate": 0.00019999437724757218, | |
| "loss": 1.2489, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5684210526315789, | |
| "grad_norm": 0.1630581021308899, | |
| "learning_rate": 0.00019999365244731, | |
| "loss": 1.2576, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5894736842105263, | |
| "grad_norm": 0.15563088655471802, | |
| "learning_rate": 0.00019999288372167287, | |
| "loss": 1.231, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6105263157894737, | |
| "grad_norm": 0.15619848668575287, | |
| "learning_rate": 0.00019999207107099834, | |
| "loss": 1.3292, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 0.1286384016275406, | |
| "learning_rate": 0.00019999121449564347, | |
| "loss": 1.1393, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6526315789473685, | |
| "grad_norm": 0.13140268623828888, | |
| "learning_rate": 0.0001999903139959845, | |
| "loss": 1.0837, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "grad_norm": 0.13603107631206512, | |
| "learning_rate": 0.000199989369572417, | |
| "loss": 1.1516, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6947368421052632, | |
| "grad_norm": 0.1404484510421753, | |
| "learning_rate": 0.00019998838122535585, | |
| "loss": 1.235, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7157894736842105, | |
| "grad_norm": 0.18797928094863892, | |
| "learning_rate": 0.00019998734895523525, | |
| "loss": 1.1864, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 0.1484900712966919, | |
| "learning_rate": 0.00019998627276250858, | |
| "loss": 1.1262, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7578947368421053, | |
| "grad_norm": 0.14105963706970215, | |
| "learning_rate": 0.0001999851526476487, | |
| "loss": 1.238, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7789473684210526, | |
| "grad_norm": 0.1366693079471588, | |
| "learning_rate": 0.00019998398861114752, | |
| "loss": 1.2757, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.16491512954235077, | |
| "learning_rate": 0.00019998278065351646, | |
| "loss": 1.2666, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8210526315789474, | |
| "grad_norm": 0.13820528984069824, | |
| "learning_rate": 0.0001999815287752862, | |
| "loss": 1.1497, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.15959441661834717, | |
| "learning_rate": 0.00019998023297700658, | |
| "loss": 1.2034, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "eval_loss": 1.1566897630691528, | |
| "eval_runtime": 15.1159, | |
| "eval_samples_per_second": 6.616, | |
| "eval_steps_per_second": 0.662, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8631578947368421, | |
| "grad_norm": 0.18244534730911255, | |
| "learning_rate": 0.00019997889325924683, | |
| "loss": 1.2506, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8842105263157894, | |
| "grad_norm": 0.13269871473312378, | |
| "learning_rate": 0.0001999775096225955, | |
| "loss": 1.1754, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9052631578947369, | |
| "grad_norm": 0.14465025067329407, | |
| "learning_rate": 0.00019997608206766038, | |
| "loss": 1.1623, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9263157894736842, | |
| "grad_norm": 0.14105112850666046, | |
| "learning_rate": 0.00019997461059506857, | |
| "loss": 1.15, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 0.14860253036022186, | |
| "learning_rate": 0.00019997309520546647, | |
| "loss": 1.2272, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.968421052631579, | |
| "grad_norm": 0.14539220929145813, | |
| "learning_rate": 0.00019997153589951973, | |
| "loss": 1.1894, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.9894736842105263, | |
| "grad_norm": 0.1519959717988968, | |
| "learning_rate": 0.00019996993267791337, | |
| "loss": 1.0394, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0105263157894737, | |
| "grad_norm": 0.14171597361564636, | |
| "learning_rate": 0.00019996828554135162, | |
| "loss": 1.3091, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0315789473684212, | |
| "grad_norm": 0.1611461490392685, | |
| "learning_rate": 0.0001999665944905581, | |
| "loss": 1.1096, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 0.18341802060604095, | |
| "learning_rate": 0.00019996485952627552, | |
| "loss": 1.1828, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0736842105263158, | |
| "grad_norm": 0.15702421963214874, | |
| "learning_rate": 0.00019996308064926615, | |
| "loss": 1.1569, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.0947368421052632, | |
| "grad_norm": 0.16117393970489502, | |
| "learning_rate": 0.00019996125786031138, | |
| "loss": 1.1337, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.1157894736842104, | |
| "grad_norm": 0.16280895471572876, | |
| "learning_rate": 0.00019995939116021193, | |
| "loss": 1.2093, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.1368421052631579, | |
| "grad_norm": 0.16143617033958435, | |
| "learning_rate": 0.00019995748054978777, | |
| "loss": 1.1394, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.1578947368421053, | |
| "grad_norm": 0.1600114107131958, | |
| "learning_rate": 0.00019995552602987827, | |
| "loss": 1.0491, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.1789473684210527, | |
| "grad_norm": 0.148758202791214, | |
| "learning_rate": 0.00019995352760134193, | |
| "loss": 1.0947, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.18547968566417694, | |
| "learning_rate": 0.00019995148526505665, | |
| "loss": 1.0401, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.2210526315789474, | |
| "grad_norm": 0.16114592552185059, | |
| "learning_rate": 0.00019994939902191964, | |
| "loss": 1.0556, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.2421052631578948, | |
| "grad_norm": 0.21020422875881195, | |
| "learning_rate": 0.0001999472688728473, | |
| "loss": 1.1656, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "grad_norm": 0.16495747864246368, | |
| "learning_rate": 0.00019994509481877537, | |
| "loss": 1.1302, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.263157894736842, | |
| "eval_loss": 1.1534416675567627, | |
| "eval_runtime": 15.0862, | |
| "eval_samples_per_second": 6.629, | |
| "eval_steps_per_second": 0.663, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.2842105263157895, | |
| "grad_norm": 0.18857495486736298, | |
| "learning_rate": 0.00019994287686065886, | |
| "loss": 1.0208, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.305263157894737, | |
| "grad_norm": 0.15040083229541779, | |
| "learning_rate": 0.00019994061499947212, | |
| "loss": 1.0189, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.3263157894736843, | |
| "grad_norm": 0.18986788392066956, | |
| "learning_rate": 0.00019993830923620872, | |
| "loss": 1.0854, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.3473684210526315, | |
| "grad_norm": 0.18154074251651764, | |
| "learning_rate": 0.00019993595957188152, | |
| "loss": 1.1744, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.368421052631579, | |
| "grad_norm": 0.1574270874261856, | |
| "learning_rate": 0.00019993356600752276, | |
| "loss": 1.1356, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.3894736842105262, | |
| "grad_norm": 0.19574891030788422, | |
| "learning_rate": 0.0001999311285441838, | |
| "loss": 1.0907, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.4105263157894736, | |
| "grad_norm": 0.20714887976646423, | |
| "learning_rate": 0.0001999286471829354, | |
| "loss": 1.1834, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.431578947368421, | |
| "grad_norm": 0.21967269480228424, | |
| "learning_rate": 0.0001999261219248676, | |
| "loss": 1.2089, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.4526315789473685, | |
| "grad_norm": 0.21682047843933105, | |
| "learning_rate": 0.00019992355277108966, | |
| "loss": 1.1635, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.4736842105263157, | |
| "grad_norm": 0.17350642383098602, | |
| "learning_rate": 0.00019992093972273018, | |
| "loss": 1.015, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.4947368421052631, | |
| "grad_norm": 0.2019474357366562, | |
| "learning_rate": 0.00019991828278093706, | |
| "loss": 1.2032, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.5157894736842106, | |
| "grad_norm": 0.2160518765449524, | |
| "learning_rate": 0.0001999155819468774, | |
| "loss": 1.0798, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.5368421052631578, | |
| "grad_norm": 0.17687132954597473, | |
| "learning_rate": 0.00019991283722173764, | |
| "loss": 1.1356, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.5578947368421052, | |
| "grad_norm": 0.16519969701766968, | |
| "learning_rate": 0.0001999100486067235, | |
| "loss": 1.0129, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.5789473684210527, | |
| "grad_norm": 0.15248972177505493, | |
| "learning_rate": 0.00019990721610305996, | |
| "loss": 1.0204, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.1959000527858734, | |
| "learning_rate": 0.00019990433971199125, | |
| "loss": 1.026, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.6210526315789475, | |
| "grad_norm": 0.20230266451835632, | |
| "learning_rate": 0.00019990141943478098, | |
| "loss": 1.0012, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.6421052631578947, | |
| "grad_norm": 0.18247124552726746, | |
| "learning_rate": 0.00019989845527271195, | |
| "loss": 1.1552, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.663157894736842, | |
| "grad_norm": 0.21317291259765625, | |
| "learning_rate": 0.00019989544722708618, | |
| "loss": 1.1461, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "grad_norm": 0.2219182848930359, | |
| "learning_rate": 0.0001998923952992252, | |
| "loss": 1.0958, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.6842105263157894, | |
| "eval_loss": 1.151181697845459, | |
| "eval_runtime": 15.09, | |
| "eval_samples_per_second": 6.627, | |
| "eval_steps_per_second": 0.663, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.7052631578947368, | |
| "grad_norm": 0.20883385837078094, | |
| "learning_rate": 0.00019988929949046958, | |
| "loss": 1.1361, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.7263157894736842, | |
| "grad_norm": 0.23448118567466736, | |
| "learning_rate": 0.00019988615980217925, | |
| "loss": 1.1583, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.7473684210526317, | |
| "grad_norm": 0.19605010747909546, | |
| "learning_rate": 0.00019988297623573344, | |
| "loss": 1.2165, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.768421052631579, | |
| "grad_norm": 0.2519710063934326, | |
| "learning_rate": 0.0001998797487925306, | |
| "loss": 1.188, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.7894736842105263, | |
| "grad_norm": 0.2063812017440796, | |
| "learning_rate": 0.00019987647747398852, | |
| "loss": 1.2146, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.8105263157894735, | |
| "grad_norm": 0.18549425899982452, | |
| "learning_rate": 0.00019987316228154423, | |
| "loss": 1.1634, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.831578947368421, | |
| "grad_norm": 0.22328101098537445, | |
| "learning_rate": 0.00019986980321665403, | |
| "loss": 1.4089, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.8526315789473684, | |
| "grad_norm": 0.23256567120552063, | |
| "learning_rate": 0.00019986640028079347, | |
| "loss": 0.9991, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.8736842105263158, | |
| "grad_norm": 0.23284031450748444, | |
| "learning_rate": 0.0001998629534754574, | |
| "loss": 1.1857, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.8947368421052633, | |
| "grad_norm": 0.25720322132110596, | |
| "learning_rate": 0.00019985946280215994, | |
| "loss": 1.1692, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.9157894736842105, | |
| "grad_norm": 0.25529375672340393, | |
| "learning_rate": 0.00019985592826243453, | |
| "loss": 1.1913, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.936842105263158, | |
| "grad_norm": 0.21553778648376465, | |
| "learning_rate": 0.0001998523498578338, | |
| "loss": 1.0827, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.9578947368421051, | |
| "grad_norm": 0.22560931742191315, | |
| "learning_rate": 0.00019984872758992963, | |
| "loss": 1.2614, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.9789473684210526, | |
| "grad_norm": 0.21169520914554596, | |
| "learning_rate": 0.00019984506146031325, | |
| "loss": 1.1164, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.22062988579273224, | |
| "learning_rate": 0.00019984135147059514, | |
| "loss": 1.1638, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 2.0210526315789474, | |
| "grad_norm": 0.21019504964351654, | |
| "learning_rate": 0.00019983759762240503, | |
| "loss": 1.0949, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.042105263157895, | |
| "grad_norm": 0.19634267687797546, | |
| "learning_rate": 0.00019983379991739188, | |
| "loss": 1.0106, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 2.0631578947368423, | |
| "grad_norm": 0.24126608669757843, | |
| "learning_rate": 0.00019982995835722398, | |
| "loss": 0.9002, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 2.0842105263157893, | |
| "grad_norm": 0.22683700919151306, | |
| "learning_rate": 0.0001998260729435889, | |
| "loss": 1.0105, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 0.27286496758461, | |
| "learning_rate": 0.00019982214367819328, | |
| "loss": 1.0285, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "eval_loss": 1.1652569770812988, | |
| "eval_runtime": 15.0915, | |
| "eval_samples_per_second": 6.626, | |
| "eval_steps_per_second": 0.663, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.126315789473684, | |
| "grad_norm": 0.24511495232582092, | |
| "learning_rate": 0.00019981817056276337, | |
| "loss": 1.0178, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 2.1473684210526316, | |
| "grad_norm": 0.23129835724830627, | |
| "learning_rate": 0.00019981415359904435, | |
| "loss": 0.9067, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.168421052631579, | |
| "grad_norm": 0.25192540884017944, | |
| "learning_rate": 0.00019981009278880087, | |
| "loss": 1.0198, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 2.1894736842105265, | |
| "grad_norm": 0.28074589371681213, | |
| "learning_rate": 0.0001998059881338167, | |
| "loss": 0.9983, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.2105263157894735, | |
| "grad_norm": 0.22504180669784546, | |
| "learning_rate": 0.00019980183963589504, | |
| "loss": 0.9203, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.231578947368421, | |
| "grad_norm": 0.25999030470848083, | |
| "learning_rate": 0.00019979764729685813, | |
| "loss": 1.1073, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 2.2526315789473683, | |
| "grad_norm": 0.2536907196044922, | |
| "learning_rate": 0.00019979341111854768, | |
| "loss": 1.1423, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 2.2736842105263158, | |
| "grad_norm": 0.24934524297714233, | |
| "learning_rate": 0.0001997891311028245, | |
| "loss": 0.854, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.294736842105263, | |
| "grad_norm": 0.24719196557998657, | |
| "learning_rate": 0.0001997848072515688, | |
| "loss": 1.0318, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 2.3157894736842106, | |
| "grad_norm": 0.2829945385456085, | |
| "learning_rate": 0.0001997804395666799, | |
| "loss": 0.9709, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.336842105263158, | |
| "grad_norm": 0.29261600971221924, | |
| "learning_rate": 0.00019977602805007648, | |
| "loss": 0.942, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 2.3578947368421055, | |
| "grad_norm": 0.26871809363365173, | |
| "learning_rate": 0.0001997715727036964, | |
| "loss": 1.1248, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.3789473684210525, | |
| "grad_norm": 0.2754141390323639, | |
| "learning_rate": 0.00019976707352949684, | |
| "loss": 1.1282, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.26692995429039, | |
| "learning_rate": 0.00019976253052945425, | |
| "loss": 0.8413, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.4210526315789473, | |
| "grad_norm": 0.30057746171951294, | |
| "learning_rate": 0.00019975794370556417, | |
| "loss": 1.118, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.442105263157895, | |
| "grad_norm": 0.2569466531276703, | |
| "learning_rate": 0.0001997533130598416, | |
| "loss": 1.0404, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.463157894736842, | |
| "grad_norm": 0.30639445781707764, | |
| "learning_rate": 0.00019974863859432068, | |
| "loss": 1.0001, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 2.4842105263157896, | |
| "grad_norm": 0.26039522886276245, | |
| "learning_rate": 0.00019974392031105482, | |
| "loss": 1.1001, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.5052631578947366, | |
| "grad_norm": 0.31316864490509033, | |
| "learning_rate": 0.00019973915821211666, | |
| "loss": 0.9833, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "grad_norm": 0.28356632590293884, | |
| "learning_rate": 0.00019973435229959813, | |
| "loss": 1.1265, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.526315789473684, | |
| "eval_loss": 1.1785136461257935, | |
| "eval_runtime": 15.0968, | |
| "eval_samples_per_second": 6.624, | |
| "eval_steps_per_second": 0.662, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.5473684210526315, | |
| "grad_norm": 0.3286098837852478, | |
| "learning_rate": 0.0001997295025756103, | |
| "loss": 0.9399, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 2.568421052631579, | |
| "grad_norm": 0.29396986961364746, | |
| "learning_rate": 0.00019972460904228365, | |
| "loss": 0.9961, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.5894736842105264, | |
| "grad_norm": 0.31531810760498047, | |
| "learning_rate": 0.0001997196717017678, | |
| "loss": 1.0899, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.610526315789474, | |
| "grad_norm": 0.2522255480289459, | |
| "learning_rate": 0.00019971469055623162, | |
| "loss": 0.94, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 0.2962912917137146, | |
| "learning_rate": 0.00019970966560786324, | |
| "loss": 0.976, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.6526315789473687, | |
| "grad_norm": 0.2782577872276306, | |
| "learning_rate": 0.00019970459685887, | |
| "loss": 0.985, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.6736842105263157, | |
| "grad_norm": 0.31023719906806946, | |
| "learning_rate": 0.00019969948431147858, | |
| "loss": 0.9228, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 2.694736842105263, | |
| "grad_norm": 0.35043251514434814, | |
| "learning_rate": 0.00019969432796793478, | |
| "loss": 1.0626, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.7157894736842105, | |
| "grad_norm": 0.28269392251968384, | |
| "learning_rate": 0.00019968912783050366, | |
| "loss": 0.9771, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.736842105263158, | |
| "grad_norm": 0.3904775381088257, | |
| "learning_rate": 0.0001996838839014696, | |
| "loss": 1.0986, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.7578947368421054, | |
| "grad_norm": 0.3603789806365967, | |
| "learning_rate": 0.00019967859618313612, | |
| "loss": 0.8981, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 2.7789473684210524, | |
| "grad_norm": 0.3876775801181793, | |
| "learning_rate": 0.00019967326467782605, | |
| "loss": 0.999, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 0.33544307947158813, | |
| "learning_rate": 0.0001996678893878814, | |
| "loss": 0.9868, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 2.8210526315789473, | |
| "grad_norm": 0.27033519744873047, | |
| "learning_rate": 0.00019966247031566345, | |
| "loss": 0.969, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.8421052631578947, | |
| "grad_norm": 0.29576611518859863, | |
| "learning_rate": 0.0001996570074635527, | |
| "loss": 1.1384, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.863157894736842, | |
| "grad_norm": 0.2918352484703064, | |
| "learning_rate": 0.00019965150083394885, | |
| "loss": 0.9385, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.8842105263157896, | |
| "grad_norm": 0.26381438970565796, | |
| "learning_rate": 0.00019964595042927088, | |
| "loss": 0.9742, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 2.905263157894737, | |
| "grad_norm": 0.3624316155910492, | |
| "learning_rate": 0.000199640356251957, | |
| "loss": 1.1089, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.9263157894736844, | |
| "grad_norm": 0.3607443869113922, | |
| "learning_rate": 0.00019963471830446462, | |
| "loss": 1.0243, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "grad_norm": 0.3374713063240051, | |
| "learning_rate": 0.00019962903658927037, | |
| "loss": 1.0215, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.9473684210526314, | |
| "eval_loss": 1.1921439170837402, | |
| "eval_runtime": 15.1014, | |
| "eval_samples_per_second": 6.622, | |
| "eval_steps_per_second": 0.662, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.968421052631579, | |
| "grad_norm": 0.2549107074737549, | |
| "learning_rate": 0.00019962331110887015, | |
| "loss": 0.9862, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.9894736842105263, | |
| "grad_norm": 0.28837814927101135, | |
| "learning_rate": 0.00019961754186577902, | |
| "loss": 1.0686, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 3.0105263157894737, | |
| "grad_norm": 0.2922016978263855, | |
| "learning_rate": 0.00019961172886253135, | |
| "loss": 0.9724, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 3.031578947368421, | |
| "grad_norm": 0.3212421238422394, | |
| "learning_rate": 0.00019960587210168064, | |
| "loss": 0.9277, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 3.0526315789473686, | |
| "grad_norm": 0.2664543390274048, | |
| "learning_rate": 0.00019959997158579967, | |
| "loss": 0.851, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 3.0736842105263156, | |
| "grad_norm": 0.25021764636039734, | |
| "learning_rate": 0.00019959402731748046, | |
| "loss": 0.8162, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 3.094736842105263, | |
| "grad_norm": 0.2933099567890167, | |
| "learning_rate": 0.00019958803929933421, | |
| "loss": 0.8726, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 3.1157894736842104, | |
| "grad_norm": 0.2778937518596649, | |
| "learning_rate": 0.0001995820075339913, | |
| "loss": 0.8583, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 3.136842105263158, | |
| "grad_norm": 0.3159140646457672, | |
| "learning_rate": 0.0001995759320241014, | |
| "loss": 0.9162, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 3.1578947368421053, | |
| "grad_norm": 0.3638457655906677, | |
| "learning_rate": 0.0001995698127723334, | |
| "loss": 0.8698, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.1789473684210527, | |
| "grad_norm": 0.3314703702926636, | |
| "learning_rate": 0.00019956364978137534, | |
| "loss": 0.7974, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.3441965878009796, | |
| "learning_rate": 0.00019955744305393452, | |
| "loss": 0.8227, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 3.221052631578947, | |
| "grad_norm": 0.3249785304069519, | |
| "learning_rate": 0.00019955119259273743, | |
| "loss": 1.0359, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 3.2421052631578946, | |
| "grad_norm": 0.3665757477283478, | |
| "learning_rate": 0.0001995448984005298, | |
| "loss": 0.8252, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 3.263157894736842, | |
| "grad_norm": 0.36660316586494446, | |
| "learning_rate": 0.00019953856048007652, | |
| "loss": 0.951, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 3.2842105263157895, | |
| "grad_norm": 0.3821450173854828, | |
| "learning_rate": 0.0001995321788341618, | |
| "loss": 0.8429, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 3.305263157894737, | |
| "grad_norm": 0.3389227092266083, | |
| "learning_rate": 0.0001995257534655889, | |
| "loss": 0.8443, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 3.3263157894736843, | |
| "grad_norm": 0.37333276867866516, | |
| "learning_rate": 0.00019951928437718039, | |
| "loss": 0.8121, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 3.3473684210526318, | |
| "grad_norm": 0.3941514194011688, | |
| "learning_rate": 0.000199512771571778, | |
| "loss": 0.7905, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 3.3684210526315788, | |
| "grad_norm": 0.36983492970466614, | |
| "learning_rate": 0.00019950621505224273, | |
| "loss": 0.8495, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.3684210526315788, | |
| "eval_loss": 1.2672936916351318, | |
| "eval_runtime": 15.1025, | |
| "eval_samples_per_second": 6.621, | |
| "eval_steps_per_second": 0.662, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.389473684210526, | |
| "grad_norm": 0.3236539363861084, | |
| "learning_rate": 0.00019949961482145474, | |
| "loss": 0.7451, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 3.4105263157894736, | |
| "grad_norm": 0.3834153413772583, | |
| "learning_rate": 0.00019949297088231335, | |
| "loss": 0.8501, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 3.431578947368421, | |
| "grad_norm": 0.40946483612060547, | |
| "learning_rate": 0.00019948628323773716, | |
| "loss": 0.7928, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 3.4526315789473685, | |
| "grad_norm": 0.3998974859714508, | |
| "learning_rate": 0.00019947955189066388, | |
| "loss": 0.8213, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 3.473684210526316, | |
| "grad_norm": 0.3378157317638397, | |
| "learning_rate": 0.00019947277684405056, | |
| "loss": 0.8236, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 3.4947368421052634, | |
| "grad_norm": 0.3661404848098755, | |
| "learning_rate": 0.00019946595810087323, | |
| "loss": 0.8427, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 3.515789473684211, | |
| "grad_norm": 0.3834976255893707, | |
| "learning_rate": 0.0001994590956641273, | |
| "loss": 0.7935, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 3.536842105263158, | |
| "grad_norm": 0.38265261054039, | |
| "learning_rate": 0.00019945218953682734, | |
| "loss": 0.8425, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 3.557894736842105, | |
| "grad_norm": 0.3965548276901245, | |
| "learning_rate": 0.00019944523972200705, | |
| "loss": 0.7629, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 3.5789473684210527, | |
| "grad_norm": 0.33844998478889465, | |
| "learning_rate": 0.00019943824622271935, | |
| "loss": 0.8272, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "grad_norm": 0.3963635563850403, | |
| "learning_rate": 0.0001994312090420364, | |
| "loss": 0.8769, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 3.6210526315789475, | |
| "grad_norm": 0.4465744197368622, | |
| "learning_rate": 0.00019942412818304943, | |
| "loss": 0.8587, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 3.6421052631578945, | |
| "grad_norm": 0.4285814166069031, | |
| "learning_rate": 0.00019941700364886899, | |
| "loss": 0.8129, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 3.663157894736842, | |
| "grad_norm": 0.4269882142543793, | |
| "learning_rate": 0.00019940983544262472, | |
| "loss": 1.0085, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 3.6842105263157894, | |
| "grad_norm": 0.4019848108291626, | |
| "learning_rate": 0.00019940262356746554, | |
| "loss": 0.8352, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 3.705263157894737, | |
| "grad_norm": 0.3888452351093292, | |
| "learning_rate": 0.00019939536802655945, | |
| "loss": 0.9718, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 3.7263157894736842, | |
| "grad_norm": 0.4387454688549042, | |
| "learning_rate": 0.00019938806882309368, | |
| "loss": 1.1492, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 3.7473684210526317, | |
| "grad_norm": 0.47144615650177, | |
| "learning_rate": 0.00019938072596027462, | |
| "loss": 0.8351, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 3.768421052631579, | |
| "grad_norm": 0.37782907485961914, | |
| "learning_rate": 0.0001993733394413279, | |
| "loss": 0.8221, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 3.7894736842105265, | |
| "grad_norm": 0.3969016969203949, | |
| "learning_rate": 0.0001993659092694982, | |
| "loss": 0.901, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.7894736842105265, | |
| "eval_loss": 1.2610888481140137, | |
| "eval_runtime": 15.0998, | |
| "eval_samples_per_second": 6.623, | |
| "eval_steps_per_second": 0.662, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.8105263157894735, | |
| "grad_norm": 0.34853246808052063, | |
| "learning_rate": 0.00019935843544804956, | |
| "loss": 0.9159, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 3.831578947368421, | |
| "grad_norm": 0.3776082396507263, | |
| "learning_rate": 0.00019935091798026507, | |
| "loss": 0.9256, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 3.8526315789473684, | |
| "grad_norm": 0.42846596240997314, | |
| "learning_rate": 0.00019934335686944694, | |
| "loss": 0.9343, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 3.873684210526316, | |
| "grad_norm": 0.38637641072273254, | |
| "learning_rate": 0.0001993357521189167, | |
| "loss": 0.9058, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 3.8947368421052633, | |
| "grad_norm": 0.35184672474861145, | |
| "learning_rate": 0.00019932810373201495, | |
| "loss": 0.8512, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 3.9157894736842103, | |
| "grad_norm": 0.3937157690525055, | |
| "learning_rate": 0.00019932041171210151, | |
| "loss": 0.926, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 3.9368421052631577, | |
| "grad_norm": 0.4368656277656555, | |
| "learning_rate": 0.0001993126760625553, | |
| "loss": 1.0166, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 3.957894736842105, | |
| "grad_norm": 0.3807603418827057, | |
| "learning_rate": 0.0001993048967867745, | |
| "loss": 0.9002, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 3.9789473684210526, | |
| "grad_norm": 0.3753417432308197, | |
| "learning_rate": 0.00019929707388817637, | |
| "loss": 0.9097, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.4108405113220215, | |
| "learning_rate": 0.00019928920737019733, | |
| "loss": 0.9339, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.021052631578947, | |
| "grad_norm": 0.3922579288482666, | |
| "learning_rate": 0.0001992812972362931, | |
| "loss": 0.7981, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 4.042105263157895, | |
| "grad_norm": 0.377907931804657, | |
| "learning_rate": 0.00019927334348993837, | |
| "loss": 0.7216, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 4.063157894736842, | |
| "grad_norm": 0.3310043513774872, | |
| "learning_rate": 0.00019926534613462707, | |
| "loss": 0.6362, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 4.08421052631579, | |
| "grad_norm": 0.38383597135543823, | |
| "learning_rate": 0.00019925730517387239, | |
| "loss": 0.6881, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 4.105263157894737, | |
| "grad_norm": 0.4816322326660156, | |
| "learning_rate": 0.00019924922061120644, | |
| "loss": 0.6735, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 4.126315789473685, | |
| "grad_norm": 0.4419063329696655, | |
| "learning_rate": 0.00019924109245018072, | |
| "loss": 0.6995, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 4.147368421052631, | |
| "grad_norm": 0.4181762933731079, | |
| "learning_rate": 0.00019923292069436578, | |
| "loss": 0.7638, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 4.168421052631579, | |
| "grad_norm": 0.4450121521949768, | |
| "learning_rate": 0.00019922470534735123, | |
| "loss": 0.6745, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 4.189473684210526, | |
| "grad_norm": 0.4250476658344269, | |
| "learning_rate": 0.000199216446412746, | |
| "loss": 0.8314, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 4.2105263157894735, | |
| "grad_norm": 0.4420212507247925, | |
| "learning_rate": 0.0001992081438941781, | |
| "loss": 0.7058, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.2105263157894735, | |
| "eval_loss": 1.3737410306930542, | |
| "eval_runtime": 15.0784, | |
| "eval_samples_per_second": 6.632, | |
| "eval_steps_per_second": 0.663, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.231578947368421, | |
| "grad_norm": 0.4359537363052368, | |
| "learning_rate": 0.00019919979779529462, | |
| "loss": 0.7697, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 4.252631578947368, | |
| "grad_norm": 0.44620540738105774, | |
| "learning_rate": 0.0001991914081197619, | |
| "loss": 0.6539, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 4.273684210526316, | |
| "grad_norm": 0.4683506488800049, | |
| "learning_rate": 0.0001991829748712653, | |
| "loss": 0.6729, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 4.294736842105263, | |
| "grad_norm": 0.45054468512535095, | |
| "learning_rate": 0.00019917449805350947, | |
| "loss": 0.7936, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 4.315789473684211, | |
| "grad_norm": 0.3688434958457947, | |
| "learning_rate": 0.00019916597767021807, | |
| "loss": 0.7257, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 4.336842105263158, | |
| "grad_norm": 0.44829288125038147, | |
| "learning_rate": 0.00019915741372513398, | |
| "loss": 0.8966, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 4.3578947368421055, | |
| "grad_norm": 0.5000961422920227, | |
| "learning_rate": 0.00019914880622201912, | |
| "loss": 0.6876, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 4.378947368421053, | |
| "grad_norm": 0.4218606948852539, | |
| "learning_rate": 0.0001991401551646547, | |
| "loss": 0.6577, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "grad_norm": 0.41971078515052795, | |
| "learning_rate": 0.00019913146055684092, | |
| "loss": 0.6466, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 4.421052631578947, | |
| "grad_norm": 0.5077884793281555, | |
| "learning_rate": 0.00019912272240239716, | |
| "loss": 0.6927, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 4.442105263157894, | |
| "grad_norm": 0.4335264265537262, | |
| "learning_rate": 0.00019911394070516194, | |
| "loss": 0.6726, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 4.463157894736842, | |
| "grad_norm": 0.4315473139286041, | |
| "learning_rate": 0.0001991051154689929, | |
| "loss": 0.6704, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 4.484210526315789, | |
| "grad_norm": 0.41848331689834595, | |
| "learning_rate": 0.0001990962466977668, | |
| "loss": 0.7625, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 4.505263157894737, | |
| "grad_norm": 0.43444666266441345, | |
| "learning_rate": 0.0001990873343953795, | |
| "loss": 0.6806, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 4.526315789473684, | |
| "grad_norm": 0.45425352454185486, | |
| "learning_rate": 0.00019907837856574607, | |
| "loss": 0.6422, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 4.5473684210526315, | |
| "grad_norm": 0.39107388257980347, | |
| "learning_rate": 0.0001990693792128006, | |
| "loss": 0.6979, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 4.568421052631579, | |
| "grad_norm": 0.5015237927436829, | |
| "learning_rate": 0.00019906033634049637, | |
| "loss": 0.76, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 4.589473684210526, | |
| "grad_norm": 0.5905852317810059, | |
| "learning_rate": 0.00019905124995280572, | |
| "loss": 0.6172, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 4.610526315789474, | |
| "grad_norm": 0.4459174573421478, | |
| "learning_rate": 0.0001990421200537201, | |
| "loss": 0.6808, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 4.631578947368421, | |
| "grad_norm": 0.4470289647579193, | |
| "learning_rate": 0.0001990329466472502, | |
| "loss": 0.7428, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.631578947368421, | |
| "eval_loss": 1.3823609352111816, | |
| "eval_runtime": 15.1002, | |
| "eval_samples_per_second": 6.622, | |
| "eval_steps_per_second": 0.662, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.652631578947369, | |
| "grad_norm": 0.5562801361083984, | |
| "learning_rate": 0.00019902372973742565, | |
| "loss": 0.6417, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 4.673684210526316, | |
| "grad_norm": 0.4418918788433075, | |
| "learning_rate": 0.00019901446932829532, | |
| "loss": 0.6833, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 4.6947368421052635, | |
| "grad_norm": 0.4580042064189911, | |
| "learning_rate": 0.00019900516542392712, | |
| "loss": 0.7247, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 4.715789473684211, | |
| "grad_norm": 0.4451601207256317, | |
| "learning_rate": 0.00019899581802840802, | |
| "loss": 0.6519, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 4.7368421052631575, | |
| "grad_norm": 0.46985530853271484, | |
| "learning_rate": 0.00019898642714584428, | |
| "loss": 0.6464, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 4.757894736842105, | |
| "grad_norm": 0.4769364893436432, | |
| "learning_rate": 0.00019897699278036108, | |
| "loss": 0.6946, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 4.778947368421052, | |
| "grad_norm": 0.4480087459087372, | |
| "learning_rate": 0.00019896751493610272, | |
| "loss": 0.5716, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "grad_norm": 0.4228164851665497, | |
| "learning_rate": 0.00019895799361723272, | |
| "loss": 0.6828, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 4.821052631578947, | |
| "grad_norm": 0.488390177488327, | |
| "learning_rate": 0.00019894842882793362, | |
| "loss": 0.7358, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 4.842105263157895, | |
| "grad_norm": 0.4492754340171814, | |
| "learning_rate": 0.000198938820572407, | |
| "loss": 0.6468, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 4.863157894736842, | |
| "grad_norm": 0.48078247904777527, | |
| "learning_rate": 0.00019892916885487356, | |
| "loss": 0.7425, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 4.88421052631579, | |
| "grad_norm": 0.3910196125507355, | |
| "learning_rate": 0.00019891947367957322, | |
| "loss": 0.7077, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 4.905263157894737, | |
| "grad_norm": 0.5010913610458374, | |
| "learning_rate": 0.00019890973505076485, | |
| "loss": 0.791, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 4.926315789473684, | |
| "grad_norm": 0.3905860483646393, | |
| "learning_rate": 0.00019889995297272647, | |
| "loss": 0.6987, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 4.947368421052632, | |
| "grad_norm": 0.5714398622512817, | |
| "learning_rate": 0.00019889012744975508, | |
| "loss": 0.6656, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 4.968421052631579, | |
| "grad_norm": 0.47835731506347656, | |
| "learning_rate": 0.00019888025848616695, | |
| "loss": 0.6948, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 4.989473684210527, | |
| "grad_norm": 0.4666154086589813, | |
| "learning_rate": 0.00019887034608629734, | |
| "loss": 0.7628, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 5.010526315789473, | |
| "grad_norm": 0.470474511384964, | |
| "learning_rate": 0.0001988603902545005, | |
| "loss": 0.529, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 5.031578947368421, | |
| "grad_norm": 0.4203038513660431, | |
| "learning_rate": 0.00019885039099514992, | |
| "loss": 0.529, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 5.052631578947368, | |
| "grad_norm": 0.46336621046066284, | |
| "learning_rate": 0.00019884034831263808, | |
| "loss": 0.4866, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 5.052631578947368, | |
| "eval_loss": 1.4474551677703857, | |
| "eval_runtime": 15.0991, | |
| "eval_samples_per_second": 6.623, | |
| "eval_steps_per_second": 0.662, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 5.073684210526316, | |
| "grad_norm": 0.4180259704589844, | |
| "learning_rate": 0.00019883026221137652, | |
| "loss": 0.526, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 5.094736842105263, | |
| "grad_norm": 0.42054420709609985, | |
| "learning_rate": 0.00019882013269579584, | |
| "loss": 0.4412, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 5.11578947368421, | |
| "grad_norm": 0.5846607089042664, | |
| "learning_rate": 0.00019880995977034584, | |
| "loss": 0.5306, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 5.136842105263158, | |
| "grad_norm": 0.6321561932563782, | |
| "learning_rate": 0.00019879974343949526, | |
| "loss": 0.575, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 5.157894736842105, | |
| "grad_norm": 0.48956233263015747, | |
| "learning_rate": 0.00019878948370773193, | |
| "loss": 0.4667, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 5.178947368421053, | |
| "grad_norm": 0.49197542667388916, | |
| "learning_rate": 0.00019877918057956278, | |
| "loss": 0.473, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "grad_norm": 0.5268818736076355, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 0.6249, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 5.221052631578948, | |
| "grad_norm": 0.4883573651313782, | |
| "learning_rate": 0.00019875844415212997, | |
| "loss": 0.5239, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 5.242105263157895, | |
| "grad_norm": 0.45860010385513306, | |
| "learning_rate": 0.00019874801086197544, | |
| "loss": 0.5462, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 5.2631578947368425, | |
| "grad_norm": 0.41302675008773804, | |
| "learning_rate": 0.00019873753419363336, | |
| "loss": 0.5144, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 5.284210526315789, | |
| "grad_norm": 0.550791323184967, | |
| "learning_rate": 0.00019872701415170593, | |
| "loss": 0.5071, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 5.3052631578947365, | |
| "grad_norm": 0.4419604539871216, | |
| "learning_rate": 0.00019871645074081434, | |
| "loss": 0.4598, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 5.326315789473684, | |
| "grad_norm": 0.5271047353744507, | |
| "learning_rate": 0.00019870584396559902, | |
| "loss": 0.5444, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 5.347368421052631, | |
| "grad_norm": 0.4978967308998108, | |
| "learning_rate": 0.00019869519383071928, | |
| "loss": 0.5829, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 5.368421052631579, | |
| "grad_norm": 0.5046519041061401, | |
| "learning_rate": 0.00019868450034085352, | |
| "loss": 0.5343, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 5.389473684210526, | |
| "grad_norm": 0.5924373865127563, | |
| "learning_rate": 0.0001986737635006992, | |
| "loss": 0.514, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 5.410526315789474, | |
| "grad_norm": 0.47235432267189026, | |
| "learning_rate": 0.00019866298331497283, | |
| "loss": 0.4899, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 5.431578947368421, | |
| "grad_norm": 0.49679791927337646, | |
| "learning_rate": 0.0001986521597884099, | |
| "loss": 0.5483, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 5.4526315789473685, | |
| "grad_norm": 0.4871433973312378, | |
| "learning_rate": 0.00019864129292576505, | |
| "loss": 0.5544, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 5.473684210526316, | |
| "grad_norm": 0.5678947567939758, | |
| "learning_rate": 0.00019863038273181186, | |
| "loss": 0.5298, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 5.473684210526316, | |
| "eval_loss": 1.5484461784362793, | |
| "eval_runtime": 15.0951, | |
| "eval_samples_per_second": 6.625, | |
| "eval_steps_per_second": 0.662, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 5.494736842105263, | |
| "grad_norm": 0.541333019733429, | |
| "learning_rate": 0.00019861942921134298, | |
| "loss": 0.5321, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 5.515789473684211, | |
| "grad_norm": 0.45463690161705017, | |
| "learning_rate": 0.0001986084323691701, | |
| "loss": 0.5239, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 5.536842105263158, | |
| "grad_norm": 0.5732460618019104, | |
| "learning_rate": 0.0001985973922101239, | |
| "loss": 0.4861, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 5.557894736842105, | |
| "grad_norm": 0.4361143112182617, | |
| "learning_rate": 0.00019858630873905418, | |
| "loss": 0.5427, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 5.578947368421053, | |
| "grad_norm": 0.48954471945762634, | |
| "learning_rate": 0.00019857518196082964, | |
| "loss": 0.5614, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "grad_norm": 0.5832586884498596, | |
| "learning_rate": 0.0001985640118803381, | |
| "loss": 0.4603, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 5.621052631578947, | |
| "grad_norm": 0.5026202201843262, | |
| "learning_rate": 0.0001985527985024864, | |
| "loss": 0.6399, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 5.6421052631578945, | |
| "grad_norm": 0.4579145908355713, | |
| "learning_rate": 0.0001985415418322003, | |
| "loss": 0.5354, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 5.663157894736842, | |
| "grad_norm": 0.545054018497467, | |
| "learning_rate": 0.00019853024187442472, | |
| "loss": 0.5158, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 5.684210526315789, | |
| "grad_norm": 0.48174452781677246, | |
| "learning_rate": 0.00019851889863412345, | |
| "loss": 0.5014, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 5.705263157894737, | |
| "grad_norm": 0.5417779684066772, | |
| "learning_rate": 0.00019850751211627945, | |
| "loss": 0.54, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 5.726315789473684, | |
| "grad_norm": 0.46869099140167236, | |
| "learning_rate": 0.00019849608232589457, | |
| "loss": 0.5416, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 5.747368421052632, | |
| "grad_norm": 0.6471317410469055, | |
| "learning_rate": 0.00019848460926798968, | |
| "loss": 0.5962, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 5.768421052631579, | |
| "grad_norm": 0.5855197310447693, | |
| "learning_rate": 0.00019847309294760473, | |
| "loss": 0.6314, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 5.7894736842105265, | |
| "grad_norm": 0.5380208492279053, | |
| "learning_rate": 0.00019846153336979856, | |
| "loss": 0.5651, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 5.810526315789474, | |
| "grad_norm": 0.46017733216285706, | |
| "learning_rate": 0.00019844993053964917, | |
| "loss": 0.5575, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 5.831578947368421, | |
| "grad_norm": 0.49735313653945923, | |
| "learning_rate": 0.00019843828446225342, | |
| "loss": 0.5628, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 5.852631578947369, | |
| "grad_norm": 0.5164270401000977, | |
| "learning_rate": 0.0001984265951427272, | |
| "loss": 0.5026, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 5.873684210526315, | |
| "grad_norm": 0.5263252258300781, | |
| "learning_rate": 0.00019841486258620545, | |
| "loss": 0.5588, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 5.894736842105263, | |
| "grad_norm": 0.47757405042648315, | |
| "learning_rate": 0.00019840308679784207, | |
| "loss": 0.5671, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.894736842105263, | |
| "eval_loss": 1.5009753704071045, | |
| "eval_runtime": 15.1017, | |
| "eval_samples_per_second": 6.622, | |
| "eval_steps_per_second": 0.662, | |
| "step": 280 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 4750, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 102, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 10, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 10 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.740650038525952e+17, | |
| "train_batch_size": 10, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |