{ "best_metric": 1.8997936248779297, "best_model_checkpoint": "miner_id_24/checkpoint-100", "epoch": 1.6820083682008367, "eval_steps": 50, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.016736401673640166, "grad_norm": 14.671270370483398, "learning_rate": 1.6666666666666668e-07, "loss": 10.2306, "step": 1 }, { "epoch": 0.016736401673640166, "eval_loss": 10.369909286499023, "eval_runtime": 3.2742, "eval_samples_per_second": 30.847, "eval_steps_per_second": 3.97, "step": 1 }, { "epoch": 0.03347280334728033, "grad_norm": 14.328125, "learning_rate": 3.3333333333333335e-07, "loss": 10.2034, "step": 2 }, { "epoch": 0.0502092050209205, "grad_norm": 14.797067642211914, "learning_rate": 5.000000000000001e-07, "loss": 10.2635, "step": 3 }, { "epoch": 0.06694560669456066, "grad_norm": 14.43250560760498, "learning_rate": 6.666666666666667e-07, "loss": 10.26, "step": 4 }, { "epoch": 0.08368200836820083, "grad_norm": 14.240781784057617, "learning_rate": 8.333333333333333e-07, "loss": 10.3516, "step": 5 }, { "epoch": 0.100418410041841, "grad_norm": 14.158472061157227, "learning_rate": 1.0000000000000002e-06, "loss": 10.3179, "step": 6 }, { "epoch": 0.11715481171548117, "grad_norm": 13.55285930633545, "learning_rate": 1.1666666666666668e-06, "loss": 10.2092, "step": 7 }, { "epoch": 0.13389121338912133, "grad_norm": 13.010944366455078, "learning_rate": 1.3333333333333334e-06, "loss": 10.3638, "step": 8 }, { "epoch": 0.1506276150627615, "grad_norm": 13.396709442138672, "learning_rate": 1.5e-06, "loss": 10.5753, "step": 9 }, { "epoch": 0.16736401673640167, "grad_norm": 13.725341796875, "learning_rate": 1.6666666666666667e-06, "loss": 10.3501, "step": 10 }, { "epoch": 0.18410041841004185, "grad_norm": 12.478100776672363, "learning_rate": 1.8333333333333333e-06, "loss": 10.3688, "step": 11 }, { "epoch": 0.200836820083682, "grad_norm": 11.60485553741455, "learning_rate": 2.0000000000000003e-06, "loss": 10.3377, "step": 12 }, { "epoch": 0.2175732217573222, "grad_norm": 11.682891845703125, "learning_rate": 2.166666666666667e-06, "loss": 10.3302, "step": 13 }, { "epoch": 0.23430962343096234, "grad_norm": 12.023148536682129, "learning_rate": 2.3333333333333336e-06, "loss": 10.5306, "step": 14 }, { "epoch": 0.2510460251046025, "grad_norm": 14.947415351867676, "learning_rate": 2.5e-06, "loss": 10.3194, "step": 15 }, { "epoch": 0.26778242677824265, "grad_norm": 14.228991508483887, "learning_rate": 2.666666666666667e-06, "loss": 10.3125, "step": 16 }, { "epoch": 0.28451882845188287, "grad_norm": 13.104813575744629, "learning_rate": 2.8333333333333335e-06, "loss": 9.8595, "step": 17 }, { "epoch": 0.301255230125523, "grad_norm": 13.878166198730469, "learning_rate": 3e-06, "loss": 9.8988, "step": 18 }, { "epoch": 0.3179916317991632, "grad_norm": 14.564827919006348, "learning_rate": 3.1666666666666667e-06, "loss": 10.0827, "step": 19 }, { "epoch": 0.33472803347280333, "grad_norm": 14.366488456726074, "learning_rate": 3.3333333333333333e-06, "loss": 9.8542, "step": 20 }, { "epoch": 0.3514644351464435, "grad_norm": 13.876509666442871, "learning_rate": 3.5e-06, "loss": 9.9533, "step": 21 }, { "epoch": 0.3682008368200837, "grad_norm": 13.74383544921875, "learning_rate": 3.6666666666666666e-06, "loss": 9.7412, "step": 22 }, { "epoch": 0.38493723849372385, "grad_norm": 13.74951171875, "learning_rate": 3.833333333333334e-06, "loss": 9.6477, "step": 23 }, { "epoch": 0.401673640167364, "grad_norm": 13.71518325805664, "learning_rate": 4.000000000000001e-06, "loss": 9.6774, "step": 24 }, { "epoch": 0.41841004184100417, "grad_norm": 13.004035949707031, "learning_rate": 4.166666666666667e-06, "loss": 9.4434, "step": 25 }, { "epoch": 0.4351464435146444, "grad_norm": 13.47214126586914, "learning_rate": 4.333333333333334e-06, "loss": 9.7347, "step": 26 }, { "epoch": 0.45188284518828453, "grad_norm": 11.91252326965332, "learning_rate": 4.5e-06, "loss": 9.3702, "step": 27 }, { "epoch": 0.4686192468619247, "grad_norm": 12.803349494934082, "learning_rate": 4.666666666666667e-06, "loss": 9.4046, "step": 28 }, { "epoch": 0.48535564853556484, "grad_norm": 15.152267456054688, "learning_rate": 4.833333333333333e-06, "loss": 8.7671, "step": 29 }, { "epoch": 0.502092050209205, "grad_norm": 14.327988624572754, "learning_rate": 5e-06, "loss": 8.4576, "step": 30 }, { "epoch": 0.5188284518828452, "grad_norm": 14.064353942871094, "learning_rate": 4.997482666353287e-06, "loss": 8.3482, "step": 31 }, { "epoch": 0.5355648535564853, "grad_norm": 14.080218315124512, "learning_rate": 4.989935734988098e-06, "loss": 8.2583, "step": 32 }, { "epoch": 0.5523012552301255, "grad_norm": 14.388766288757324, "learning_rate": 4.977374404419838e-06, "loss": 7.9582, "step": 33 }, { "epoch": 0.5690376569037657, "grad_norm": 13.374934196472168, "learning_rate": 4.959823971496575e-06, "loss": 7.8623, "step": 34 }, { "epoch": 0.5857740585774058, "grad_norm": 13.262751579284668, "learning_rate": 4.937319780454559e-06, "loss": 7.6083, "step": 35 }, { "epoch": 0.602510460251046, "grad_norm": 13.282503128051758, "learning_rate": 4.909907151739634e-06, "loss": 7.4737, "step": 36 }, { "epoch": 0.6192468619246861, "grad_norm": 13.080615043640137, "learning_rate": 4.8776412907378845e-06, "loss": 7.3853, "step": 37 }, { "epoch": 0.6359832635983264, "grad_norm": 12.566425323486328, "learning_rate": 4.8405871765993435e-06, "loss": 7.478, "step": 38 }, { "epoch": 0.6527196652719666, "grad_norm": 12.705647468566895, "learning_rate": 4.7988194313786275e-06, "loss": 7.0334, "step": 39 }, { "epoch": 0.6694560669456067, "grad_norm": 12.801064491271973, "learning_rate": 4.752422169756048e-06, "loss": 6.9515, "step": 40 }, { "epoch": 0.6861924686192469, "grad_norm": 12.665898323059082, "learning_rate": 4.701488829641845e-06, "loss": 6.9226, "step": 41 }, { "epoch": 0.702928870292887, "grad_norm": 12.849478721618652, "learning_rate": 4.646121984004666e-06, "loss": 7.0246, "step": 42 }, { "epoch": 0.7196652719665272, "grad_norm": 13.124124526977539, "learning_rate": 4.586433134303257e-06, "loss": 5.601, "step": 43 }, { "epoch": 0.7364016736401674, "grad_norm": 12.630464553833008, "learning_rate": 4.522542485937369e-06, "loss": 5.2646, "step": 44 }, { "epoch": 0.7531380753138075, "grad_norm": 12.385834693908691, "learning_rate": 4.454578706170075e-06, "loss": 5.2738, "step": 45 }, { "epoch": 0.7698744769874477, "grad_norm": 12.193803787231445, "learning_rate": 4.382678665009028e-06, "loss": 5.2841, "step": 46 }, { "epoch": 0.7866108786610879, "grad_norm": 12.115005493164062, "learning_rate": 4.3069871595684795e-06, "loss": 5.0223, "step": 47 }, { "epoch": 0.803347280334728, "grad_norm": 11.783625602722168, "learning_rate": 4.227656622467162e-06, "loss": 4.9352, "step": 48 }, { "epoch": 0.8200836820083682, "grad_norm": 11.882129669189453, "learning_rate": 4.144846814849282e-06, "loss": 4.845, "step": 49 }, { "epoch": 0.8368200836820083, "grad_norm": 11.96120834350586, "learning_rate": 4.058724504646834e-06, "loss": 4.6088, "step": 50 }, { "epoch": 0.8368200836820083, "eval_loss": 4.455350399017334, "eval_runtime": 2.9147, "eval_samples_per_second": 34.651, "eval_steps_per_second": 4.46, "step": 50 }, { "epoch": 0.8535564853556485, "grad_norm": 11.589993476867676, "learning_rate": 3.969463130731183e-06, "loss": 4.4304, "step": 51 }, { "epoch": 0.8702928870292888, "grad_norm": 11.4859037399292, "learning_rate": 3.8772424536302565e-06, "loss": 4.2342, "step": 52 }, { "epoch": 0.8870292887029289, "grad_norm": 11.487135887145996, "learning_rate": 3.782248193514766e-06, "loss": 4.3865, "step": 53 }, { "epoch": 0.9037656903765691, "grad_norm": 11.322385787963867, "learning_rate": 3.684671656182497e-06, "loss": 4.2288, "step": 54 }, { "epoch": 0.9205020920502092, "grad_norm": 11.94207763671875, "learning_rate": 3.5847093477938955e-06, "loss": 4.301, "step": 55 }, { "epoch": 0.9372384937238494, "grad_norm": 12.321537017822266, "learning_rate": 3.4825625791348093e-06, "loss": 4.4791, "step": 56 }, { "epoch": 0.9539748953974896, "grad_norm": 9.979578971862793, "learning_rate": 3.3784370602033572e-06, "loss": 3.507, "step": 57 }, { "epoch": 0.9707112970711297, "grad_norm": 9.257335662841797, "learning_rate": 3.272542485937369e-06, "loss": 3.2266, "step": 58 }, { "epoch": 0.9874476987447699, "grad_norm": 10.138155937194824, "learning_rate": 3.165092113916688e-06, "loss": 3.3835, "step": 59 }, { "epoch": 1.0125523012552302, "grad_norm": 16.568193435668945, "learning_rate": 3.056302334890786e-06, "loss": 5.7626, "step": 60 }, { "epoch": 1.0292887029288702, "grad_norm": 9.182647705078125, "learning_rate": 2.946392236996592e-06, "loss": 3.096, "step": 61 }, { "epoch": 1.0460251046025104, "grad_norm": 9.00653076171875, "learning_rate": 2.835583164544139e-06, "loss": 2.8336, "step": 62 }, { "epoch": 1.0627615062761506, "grad_norm": 9.193709373474121, "learning_rate": 2.724098272258584e-06, "loss": 3.0503, "step": 63 }, { "epoch": 1.0794979079497908, "grad_norm": 8.696207046508789, "learning_rate": 2.6121620758762877e-06, "loss": 2.8189, "step": 64 }, { "epoch": 1.096234309623431, "grad_norm": 8.363393783569336, "learning_rate": 2.5e-06, "loss": 2.6297, "step": 65 }, { "epoch": 1.112970711297071, "grad_norm": 8.456080436706543, "learning_rate": 2.3878379241237136e-06, "loss": 2.9043, "step": 66 }, { "epoch": 1.1297071129707112, "grad_norm": 8.101542472839355, "learning_rate": 2.2759017277414165e-06, "loss": 2.6389, "step": 67 }, { "epoch": 1.1464435146443515, "grad_norm": 8.315645217895508, "learning_rate": 2.1644168354558623e-06, "loss": 2.6166, "step": 68 }, { "epoch": 1.1631799163179917, "grad_norm": 8.564580917358398, "learning_rate": 2.053607763003409e-06, "loss": 2.4953, "step": 69 }, { "epoch": 1.1799163179916319, "grad_norm": 8.223039627075195, "learning_rate": 1.9436976651092143e-06, "loss": 2.456, "step": 70 }, { "epoch": 1.196652719665272, "grad_norm": 8.602606773376465, "learning_rate": 1.8349078860833125e-06, "loss": 2.6062, "step": 71 }, { "epoch": 1.213389121338912, "grad_norm": 9.171734809875488, "learning_rate": 1.7274575140626318e-06, "loss": 2.6156, "step": 72 }, { "epoch": 1.2301255230125523, "grad_norm": 9.148757934570312, "learning_rate": 1.6215629397966432e-06, "loss": 2.7131, "step": 73 }, { "epoch": 1.2468619246861925, "grad_norm": 8.442300796508789, "learning_rate": 1.5174374208651913e-06, "loss": 2.3826, "step": 74 }, { "epoch": 1.2635983263598327, "grad_norm": 7.640994548797607, "learning_rate": 1.415290652206105e-06, "loss": 2.1609, "step": 75 }, { "epoch": 1.280334728033473, "grad_norm": 7.487751483917236, "learning_rate": 1.3153283438175036e-06, "loss": 2.1281, "step": 76 }, { "epoch": 1.297071129707113, "grad_norm": 7.00741720199585, "learning_rate": 1.217751806485235e-06, "loss": 2.1177, "step": 77 }, { "epoch": 1.3138075313807531, "grad_norm": 7.51829195022583, "learning_rate": 1.122757546369744e-06, "loss": 2.1449, "step": 78 }, { "epoch": 1.3305439330543933, "grad_norm": 7.0815958976745605, "learning_rate": 1.0305368692688175e-06, "loss": 2.0025, "step": 79 }, { "epoch": 1.3472803347280335, "grad_norm": 7.193976402282715, "learning_rate": 9.412754953531664e-07, "loss": 1.9809, "step": 80 }, { "epoch": 1.3640167364016738, "grad_norm": 7.048132419586182, "learning_rate": 8.551531851507186e-07, "loss": 1.9873, "step": 81 }, { "epoch": 1.3807531380753137, "grad_norm": 7.703879356384277, "learning_rate": 7.723433775328385e-07, "loss": 1.934, "step": 82 }, { "epoch": 1.397489539748954, "grad_norm": 7.33919620513916, "learning_rate": 6.930128404315214e-07, "loss": 1.8851, "step": 83 }, { "epoch": 1.4142259414225942, "grad_norm": 7.545919895172119, "learning_rate": 6.17321334990973e-07, "loss": 2.0397, "step": 84 }, { "epoch": 1.4309623430962344, "grad_norm": 7.975639820098877, "learning_rate": 5.454212938299256e-07, "loss": 1.9447, "step": 85 }, { "epoch": 1.4476987447698746, "grad_norm": 7.5108160972595215, "learning_rate": 4.774575140626317e-07, "loss": 2.1479, "step": 86 }, { "epoch": 1.4644351464435146, "grad_norm": 8.854683876037598, "learning_rate": 4.1356686569674344e-07, "loss": 2.3812, "step": 87 }, { "epoch": 1.4811715481171548, "grad_norm": 7.196176528930664, "learning_rate": 3.538780159953348e-07, "loss": 1.9813, "step": 88 }, { "epoch": 1.497907949790795, "grad_norm": 7.599162578582764, "learning_rate": 2.98511170358155e-07, "loss": 1.7986, "step": 89 }, { "epoch": 1.514644351464435, "grad_norm": 6.548398494720459, "learning_rate": 2.4757783024395244e-07, "loss": 1.8654, "step": 90 }, { "epoch": 1.5313807531380754, "grad_norm": 7.0527873039245605, "learning_rate": 2.0118056862137358e-07, "loss": 1.727, "step": 91 }, { "epoch": 1.5481171548117154, "grad_norm": 7.582221031188965, "learning_rate": 1.59412823400657e-07, "loss": 1.7775, "step": 92 }, { "epoch": 1.5648535564853556, "grad_norm": 6.936417579650879, "learning_rate": 1.223587092621162e-07, "loss": 1.8811, "step": 93 }, { "epoch": 1.5815899581589958, "grad_norm": 6.846926212310791, "learning_rate": 9.00928482603669e-08, "loss": 1.8697, "step": 94 }, { "epoch": 1.5983263598326358, "grad_norm": 7.105048179626465, "learning_rate": 6.268021954544095e-08, "loss": 2.0111, "step": 95 }, { "epoch": 1.6150627615062763, "grad_norm": 6.754130840301514, "learning_rate": 4.017602850342584e-08, "loss": 1.9236, "step": 96 }, { "epoch": 1.6317991631799162, "grad_norm": 7.303762912750244, "learning_rate": 2.262559558016325e-08, "loss": 2.1416, "step": 97 }, { "epoch": 1.6485355648535565, "grad_norm": 6.699948310852051, "learning_rate": 1.006426501190233e-08, "loss": 1.9259, "step": 98 }, { "epoch": 1.6652719665271967, "grad_norm": 7.717144012451172, "learning_rate": 2.5173336467135266e-09, "loss": 2.0842, "step": 99 }, { "epoch": 1.6820083682008367, "grad_norm": 7.345883846282959, "learning_rate": 0.0, "loss": 1.9875, "step": 100 }, { "epoch": 1.6820083682008367, "eval_loss": 1.8997936248779297, "eval_runtime": 2.9211, "eval_samples_per_second": 34.576, "eval_steps_per_second": 4.45, "step": 100 } ], "logging_steps": 1, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 50, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 5, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.69360081928192e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }