| { | |
| "best_metric": 2.743666648864746, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-1350", | |
| "epoch": 0.028963959180126862, | |
| "eval_steps": 150, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.9309306120084574e-05, | |
| "eval_loss": 3.0466506481170654, | |
| "eval_runtime": 330.8111, | |
| "eval_samples_per_second": 131.834, | |
| "eval_steps_per_second": 32.958, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019309306120084574, | |
| "grad_norm": 17.619115829467773, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3433, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003861861224016915, | |
| "grad_norm": 18.392913818359375, | |
| "learning_rate": 0.0001, | |
| "loss": 10.498, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005792791836025373, | |
| "grad_norm": 18.08405113220215, | |
| "learning_rate": 0.0001, | |
| "loss": 11.2262, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.000772372244803383, | |
| "grad_norm": 17.59492301940918, | |
| "learning_rate": 0.0001, | |
| "loss": 12.7306, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0009654653060042288, | |
| "grad_norm": 37.0333251953125, | |
| "learning_rate": 0.0001, | |
| "loss": 15.2312, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0011585583672050746, | |
| "grad_norm": 13.556602478027344, | |
| "learning_rate": 0.0001, | |
| "loss": 10.201, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0013516514284059203, | |
| "grad_norm": 16.682050704956055, | |
| "learning_rate": 0.0001, | |
| "loss": 9.9751, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.001544744489606766, | |
| "grad_norm": 20.121063232421875, | |
| "learning_rate": 0.0001, | |
| "loss": 10.9688, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0017378375508076116, | |
| "grad_norm": 17.53766632080078, | |
| "learning_rate": 0.0001, | |
| "loss": 12.1271, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0019309306120084576, | |
| "grad_norm": 33.57805252075195, | |
| "learning_rate": 0.0001, | |
| "loss": 14.9867, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.002124023673209303, | |
| "grad_norm": 19.4736385345459, | |
| "learning_rate": 0.0001, | |
| "loss": 9.7775, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.002317116734410149, | |
| "grad_norm": 21.09294319152832, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0451, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.002510209795610995, | |
| "grad_norm": 16.475950241088867, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4069, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0027033028568118405, | |
| "grad_norm": 24.737951278686523, | |
| "learning_rate": 0.0001, | |
| "loss": 11.6022, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0028963959180126862, | |
| "grad_norm": 38.39281463623047, | |
| "learning_rate": 0.0001, | |
| "loss": 14.6671, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0028963959180126862, | |
| "eval_loss": 2.891888380050659, | |
| "eval_runtime": 329.6932, | |
| "eval_samples_per_second": 132.281, | |
| "eval_steps_per_second": 33.07, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.003089488979213532, | |
| "grad_norm": 13.83809757232666, | |
| "learning_rate": 0.0001, | |
| "loss": 10.1709, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0032825820404143776, | |
| "grad_norm": 17.797067642211914, | |
| "learning_rate": 0.0001, | |
| "loss": 10.6159, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0034756751016152233, | |
| "grad_norm": 17.597434997558594, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8431, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.003668768162816069, | |
| "grad_norm": 20.05368995666504, | |
| "learning_rate": 0.0001, | |
| "loss": 12.1154, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.003861861224016915, | |
| "grad_norm": 88.2765121459961, | |
| "learning_rate": 0.0001, | |
| "loss": 14.0078, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.00405495428521776, | |
| "grad_norm": 19.025007247924805, | |
| "learning_rate": 0.0001, | |
| "loss": 10.7787, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.004248047346418606, | |
| "grad_norm": 16.219017028808594, | |
| "learning_rate": 0.0001, | |
| "loss": 10.2578, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.004441140407619453, | |
| "grad_norm": 19.783754348754883, | |
| "learning_rate": 0.0001, | |
| "loss": 10.7105, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.004634233468820298, | |
| "grad_norm": 15.023333549499512, | |
| "learning_rate": 0.0001, | |
| "loss": 11.5988, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.004827326530021144, | |
| "grad_norm": 33.46087646484375, | |
| "learning_rate": 0.0001, | |
| "loss": 13.6889, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.00502041959122199, | |
| "grad_norm": 11.918452262878418, | |
| "learning_rate": 0.0001, | |
| "loss": 9.8579, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.005213512652422835, | |
| "grad_norm": 11.418573379516602, | |
| "learning_rate": 0.0001, | |
| "loss": 9.7857, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.005406605713623681, | |
| "grad_norm": 12.96380615234375, | |
| "learning_rate": 0.0001, | |
| "loss": 10.7496, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.005599698774824527, | |
| "grad_norm": 20.210433959960938, | |
| "learning_rate": 0.0001, | |
| "loss": 11.8999, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.0057927918360253725, | |
| "grad_norm": 39.24753952026367, | |
| "learning_rate": 0.0001, | |
| "loss": 13.6284, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.0057927918360253725, | |
| "eval_loss": 2.8597412109375, | |
| "eval_runtime": 332.7905, | |
| "eval_samples_per_second": 131.049, | |
| "eval_steps_per_second": 32.762, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.005985884897226218, | |
| "grad_norm": 8.188671112060547, | |
| "learning_rate": 0.0001, | |
| "loss": 10.261, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.006178977958427064, | |
| "grad_norm": 13.034982681274414, | |
| "learning_rate": 0.0001, | |
| "loss": 10.359, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.0063720710196279095, | |
| "grad_norm": 10.07932186126709, | |
| "learning_rate": 0.0001, | |
| "loss": 10.7766, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.006565164080828755, | |
| "grad_norm": 14.22851848602295, | |
| "learning_rate": 0.0001, | |
| "loss": 11.6996, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.006758257142029601, | |
| "grad_norm": 29.241413116455078, | |
| "learning_rate": 0.0001, | |
| "loss": 14.314, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.006951350203230447, | |
| "grad_norm": 14.328963279724121, | |
| "learning_rate": 0.0001, | |
| "loss": 10.5319, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.007144443264431292, | |
| "grad_norm": 11.2478609085083, | |
| "learning_rate": 0.0001, | |
| "loss": 10.2886, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.007337536325632138, | |
| "grad_norm": 11.479792594909668, | |
| "learning_rate": 0.0001, | |
| "loss": 10.5397, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.0075306293868329845, | |
| "grad_norm": 16.216135025024414, | |
| "learning_rate": 0.0001, | |
| "loss": 11.4221, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.00772372244803383, | |
| "grad_norm": 40.46977996826172, | |
| "learning_rate": 0.0001, | |
| "loss": 13.6267, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.007916815509234676, | |
| "grad_norm": 7.014930725097656, | |
| "learning_rate": 0.0001, | |
| "loss": 9.8201, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.00810990857043552, | |
| "grad_norm": 9.932273864746094, | |
| "learning_rate": 0.0001, | |
| "loss": 10.2837, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.008303001631636367, | |
| "grad_norm": 10.231171607971191, | |
| "learning_rate": 0.0001, | |
| "loss": 10.6085, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.008496094692837212, | |
| "grad_norm": 14.54490852355957, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7488, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.008689187754038059, | |
| "grad_norm": 48.76640701293945, | |
| "learning_rate": 0.0001, | |
| "loss": 14.019, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.008689187754038059, | |
| "eval_loss": 2.8116047382354736, | |
| "eval_runtime": 332.18, | |
| "eval_samples_per_second": 131.29, | |
| "eval_steps_per_second": 32.823, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.008882280815238905, | |
| "grad_norm": 12.235373497009277, | |
| "learning_rate": 0.0001, | |
| "loss": 10.1831, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.00907537387643975, | |
| "grad_norm": 10.786988258361816, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3065, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.009268466937640597, | |
| "grad_norm": 14.656991004943848, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4513, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.009461559998841441, | |
| "grad_norm": 16.273334503173828, | |
| "learning_rate": 0.0001, | |
| "loss": 11.6948, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.009654653060042288, | |
| "grad_norm": 25.74225425720215, | |
| "learning_rate": 0.0001, | |
| "loss": 13.6766, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.009847746121243133, | |
| "grad_norm": 7.88370943069458, | |
| "learning_rate": 0.0001, | |
| "loss": 10.2527, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.01004083918244398, | |
| "grad_norm": 12.4476318359375, | |
| "learning_rate": 0.0001, | |
| "loss": 10.1829, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.010233932243644824, | |
| "grad_norm": 11.75400447845459, | |
| "learning_rate": 0.0001, | |
| "loss": 10.2371, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.01042702530484567, | |
| "grad_norm": 28.32915496826172, | |
| "learning_rate": 0.0001, | |
| "loss": 11.4662, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.010620118366046516, | |
| "grad_norm": 26.942928314208984, | |
| "learning_rate": 0.0001, | |
| "loss": 13.5862, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.010813211427247362, | |
| "grad_norm": 10.243542671203613, | |
| "learning_rate": 0.0001, | |
| "loss": 9.9785, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.011006304488448207, | |
| "grad_norm": 10.225203514099121, | |
| "learning_rate": 0.0001, | |
| "loss": 9.6087, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.011199397549649054, | |
| "grad_norm": 10.439690589904785, | |
| "learning_rate": 0.0001, | |
| "loss": 10.6501, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.011392490610849898, | |
| "grad_norm": 13.22080135345459, | |
| "learning_rate": 0.0001, | |
| "loss": 11.5253, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.011585583672050745, | |
| "grad_norm": 28.21418571472168, | |
| "learning_rate": 0.0001, | |
| "loss": 13.6289, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.011585583672050745, | |
| "eval_loss": 2.7912118434906006, | |
| "eval_runtime": 333.6509, | |
| "eval_samples_per_second": 130.711, | |
| "eval_steps_per_second": 32.678, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.011778676733251591, | |
| "grad_norm": 10.044217109680176, | |
| "learning_rate": 0.0001, | |
| "loss": 10.1053, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.011971769794452436, | |
| "grad_norm": 12.914101600646973, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.012164862855653283, | |
| "grad_norm": 11.664057731628418, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3879, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.012357955916854128, | |
| "grad_norm": 13.065714836120605, | |
| "learning_rate": 0.0001, | |
| "loss": 11.5201, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.012551048978054974, | |
| "grad_norm": 33.389984130859375, | |
| "learning_rate": 0.0001, | |
| "loss": 13.5861, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.012744142039255819, | |
| "grad_norm": 11.64077091217041, | |
| "learning_rate": 0.0001, | |
| "loss": 10.2282, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.012937235100456666, | |
| "grad_norm": 10.479111671447754, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0161, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.01313032816165751, | |
| "grad_norm": 35.55380630493164, | |
| "learning_rate": 0.0001, | |
| "loss": 10.6205, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.013323421222858357, | |
| "grad_norm": 13.887811660766602, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7771, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.013516514284059202, | |
| "grad_norm": 27.93064308166504, | |
| "learning_rate": 0.0001, | |
| "loss": 13.5786, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.013709607345260048, | |
| "grad_norm": 11.809444427490234, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0317, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.013902700406460893, | |
| "grad_norm": 10.49244499206543, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3579, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.01409579346766174, | |
| "grad_norm": 13.255899429321289, | |
| "learning_rate": 0.0001, | |
| "loss": 10.6709, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.014288886528862585, | |
| "grad_norm": 16.088109970092773, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7847, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.014481979590063431, | |
| "grad_norm": 43.44777297973633, | |
| "learning_rate": 0.0001, | |
| "loss": 13.5673, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.014481979590063431, | |
| "eval_loss": 2.783721446990967, | |
| "eval_runtime": 332.0115, | |
| "eval_samples_per_second": 131.357, | |
| "eval_steps_per_second": 32.839, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.014675072651264276, | |
| "grad_norm": 22.703245162963867, | |
| "learning_rate": 0.0001, | |
| "loss": 10.1566, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.014868165712465123, | |
| "grad_norm": 15.799572944641113, | |
| "learning_rate": 0.0001, | |
| "loss": 10.1408, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.015061258773665969, | |
| "grad_norm": 14.325783729553223, | |
| "learning_rate": 0.0001, | |
| "loss": 10.6599, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.015254351834866814, | |
| "grad_norm": 16.357566833496094, | |
| "learning_rate": 0.0001, | |
| "loss": 11.5767, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.01544744489606766, | |
| "grad_norm": 38.33959197998047, | |
| "learning_rate": 0.0001, | |
| "loss": 13.598, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.015640537957268507, | |
| "grad_norm": 14.860721588134766, | |
| "learning_rate": 0.0001, | |
| "loss": 10.2319, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.015833631018469352, | |
| "grad_norm": 9.913568496704102, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0176, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.016026724079670197, | |
| "grad_norm": 8.6304931640625, | |
| "learning_rate": 0.0001, | |
| "loss": 10.7353, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.01621981714087104, | |
| "grad_norm": 12.518475532531738, | |
| "learning_rate": 0.0001, | |
| "loss": 11.1827, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.01641291020207189, | |
| "grad_norm": 26.06439781188965, | |
| "learning_rate": 0.0001, | |
| "loss": 13.8205, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.016606003263272735, | |
| "grad_norm": 7.715124130249023, | |
| "learning_rate": 0.0001, | |
| "loss": 10.1191, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.01679909632447358, | |
| "grad_norm": 8.914071083068848, | |
| "learning_rate": 0.0001, | |
| "loss": 10.2188, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.016992189385674424, | |
| "grad_norm": 14.51268196105957, | |
| "learning_rate": 0.0001, | |
| "loss": 10.603, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.017185282446875273, | |
| "grad_norm": 12.584301948547363, | |
| "learning_rate": 0.0001, | |
| "loss": 11.345, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.017378375508076117, | |
| "grad_norm": 21.21172523498535, | |
| "learning_rate": 0.0001, | |
| "loss": 13.4406, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.017378375508076117, | |
| "eval_loss": 2.7644200325012207, | |
| "eval_runtime": 328.7945, | |
| "eval_samples_per_second": 132.642, | |
| "eval_steps_per_second": 33.161, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.017571468569276962, | |
| "grad_norm": 10.428869247436523, | |
| "learning_rate": 0.0001, | |
| "loss": 9.9264, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.01776456163047781, | |
| "grad_norm": 7.778339385986328, | |
| "learning_rate": 0.0001, | |
| "loss": 9.967, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.017957654691678655, | |
| "grad_norm": 8.562960624694824, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4493, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.0181507477528795, | |
| "grad_norm": 10.700459480285645, | |
| "learning_rate": 0.0001, | |
| "loss": 11.288, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.018343840814080345, | |
| "grad_norm": 27.12032699584961, | |
| "learning_rate": 0.0001, | |
| "loss": 13.3088, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.018536933875281193, | |
| "grad_norm": 7.569306373596191, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0856, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.018730026936482038, | |
| "grad_norm": 8.432563781738281, | |
| "learning_rate": 0.0001, | |
| "loss": 9.8671, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.018923119997682883, | |
| "grad_norm": 9.893686294555664, | |
| "learning_rate": 0.0001, | |
| "loss": 10.1824, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.019116213058883728, | |
| "grad_norm": 13.275106430053711, | |
| "learning_rate": 0.0001, | |
| "loss": 11.4841, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.019309306120084576, | |
| "grad_norm": 23.891876220703125, | |
| "learning_rate": 0.0001, | |
| "loss": 13.3897, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.01950239918128542, | |
| "grad_norm": 8.6790771484375, | |
| "learning_rate": 0.0001, | |
| "loss": 9.6344, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.019695492242486266, | |
| "grad_norm": 10.20168399810791, | |
| "learning_rate": 0.0001, | |
| "loss": 9.6956, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.01988858530368711, | |
| "grad_norm": 9.794075012207031, | |
| "learning_rate": 0.0001, | |
| "loss": 10.6165, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.02008167836488796, | |
| "grad_norm": 13.980074882507324, | |
| "learning_rate": 0.0001, | |
| "loss": 11.8835, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.020274771426088804, | |
| "grad_norm": 31.785160064697266, | |
| "learning_rate": 0.0001, | |
| "loss": 13.106, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.020274771426088804, | |
| "eval_loss": 2.7701072692871094, | |
| "eval_runtime": 337.2345, | |
| "eval_samples_per_second": 129.322, | |
| "eval_steps_per_second": 32.331, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.02046786448728965, | |
| "grad_norm": 7.864306926727295, | |
| "learning_rate": 0.0001, | |
| "loss": 10.2408, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.020660957548490497, | |
| "grad_norm": 8.912210464477539, | |
| "learning_rate": 0.0001, | |
| "loss": 9.9443, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.02085405060969134, | |
| "grad_norm": 9.936532974243164, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8666, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.021047143670892186, | |
| "grad_norm": 11.113265991210938, | |
| "learning_rate": 0.0001, | |
| "loss": 11.2062, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.02124023673209303, | |
| "grad_norm": 30.588726043701172, | |
| "learning_rate": 0.0001, | |
| "loss": 13.0672, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.02143332979329388, | |
| "grad_norm": 8.092857360839844, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0935, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.021626422854494724, | |
| "grad_norm": 11.335000991821289, | |
| "learning_rate": 0.0001, | |
| "loss": 9.9106, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.02181951591569557, | |
| "grad_norm": 12.082404136657715, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4083, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.022012608976896414, | |
| "grad_norm": 14.026704788208008, | |
| "learning_rate": 0.0001, | |
| "loss": 11.4077, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.022205702038097262, | |
| "grad_norm": 32.28516387939453, | |
| "learning_rate": 0.0001, | |
| "loss": 13.261, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.022398795099298107, | |
| "grad_norm": 10.577113151550293, | |
| "learning_rate": 0.0001, | |
| "loss": 9.9731, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.022591888160498952, | |
| "grad_norm": 9.278578758239746, | |
| "learning_rate": 0.0001, | |
| "loss": 9.6304, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.022784981221699797, | |
| "grad_norm": 10.110872268676758, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4382, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.022978074282900645, | |
| "grad_norm": 12.344923973083496, | |
| "learning_rate": 0.0001, | |
| "loss": 11.3848, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.02317116734410149, | |
| "grad_norm": 27.385581970214844, | |
| "learning_rate": 0.0001, | |
| "loss": 13.5253, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.02317116734410149, | |
| "eval_loss": 2.7528042793273926, | |
| "eval_runtime": 333.2124, | |
| "eval_samples_per_second": 130.883, | |
| "eval_steps_per_second": 32.721, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.023364260405302335, | |
| "grad_norm": 11.155953407287598, | |
| "learning_rate": 0.0001, | |
| "loss": 9.898, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.023557353466503183, | |
| "grad_norm": 10.302549362182617, | |
| "learning_rate": 0.0001, | |
| "loss": 10.058, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.023750446527704028, | |
| "grad_norm": 11.402131080627441, | |
| "learning_rate": 0.0001, | |
| "loss": 10.707, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.023943539588904873, | |
| "grad_norm": 13.274065971374512, | |
| "learning_rate": 0.0001, | |
| "loss": 11.5189, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.024136632650105717, | |
| "grad_norm": 22.315773010253906, | |
| "learning_rate": 0.0001, | |
| "loss": 13.4052, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.024329725711306566, | |
| "grad_norm": 8.078880310058594, | |
| "learning_rate": 0.0001, | |
| "loss": 9.8327, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.02452281877250741, | |
| "grad_norm": 7.619024753570557, | |
| "learning_rate": 0.0001, | |
| "loss": 9.8486, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.024715911833708255, | |
| "grad_norm": 10.089761734008789, | |
| "learning_rate": 0.0001, | |
| "loss": 10.4484, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.0249090048949091, | |
| "grad_norm": 12.1000394821167, | |
| "learning_rate": 0.0001, | |
| "loss": 11.3575, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.02510209795610995, | |
| "grad_norm": 23.944225311279297, | |
| "learning_rate": 0.0001, | |
| "loss": 13.2124, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.025295191017310793, | |
| "grad_norm": 6.652422904968262, | |
| "learning_rate": 0.0001, | |
| "loss": 9.6957, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.025488284078511638, | |
| "grad_norm": 10.389664649963379, | |
| "learning_rate": 0.0001, | |
| "loss": 9.8489, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.025681377139712483, | |
| "grad_norm": 10.09528636932373, | |
| "learning_rate": 0.0001, | |
| "loss": 10.5627, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.02587447020091333, | |
| "grad_norm": 13.287434577941895, | |
| "learning_rate": 0.0001, | |
| "loss": 11.8588, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.026067563262114176, | |
| "grad_norm": 23.052188873291016, | |
| "learning_rate": 0.0001, | |
| "loss": 12.9806, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.026067563262114176, | |
| "eval_loss": 2.743666648864746, | |
| "eval_runtime": 333.1086, | |
| "eval_samples_per_second": 130.924, | |
| "eval_steps_per_second": 32.731, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.02626065632331502, | |
| "grad_norm": 6.833707809448242, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0071, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.026453749384515866, | |
| "grad_norm": 8.814143180847168, | |
| "learning_rate": 0.0001, | |
| "loss": 9.8842, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.026646842445716714, | |
| "grad_norm": 10.0423583984375, | |
| "learning_rate": 0.0001, | |
| "loss": 10.6022, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.02683993550691756, | |
| "grad_norm": 11.296242713928223, | |
| "learning_rate": 0.0001, | |
| "loss": 11.2607, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.027033028568118404, | |
| "grad_norm": 21.390296936035156, | |
| "learning_rate": 0.0001, | |
| "loss": 12.9834, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.027226121629319252, | |
| "grad_norm": 8.968457221984863, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0666, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.027419214690520097, | |
| "grad_norm": 11.966334342956543, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0537, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.02761230775172094, | |
| "grad_norm": 13.229506492614746, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3221, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.027805400812921786, | |
| "grad_norm": 20.169370651245117, | |
| "learning_rate": 0.0001, | |
| "loss": 11.0951, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.027998493874122635, | |
| "grad_norm": 43.70033264160156, | |
| "learning_rate": 0.0001, | |
| "loss": 13.0941, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.02819158693532348, | |
| "grad_norm": 9.215312957763672, | |
| "learning_rate": 0.0001, | |
| "loss": 10.0646, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.028384679996524324, | |
| "grad_norm": 20.890764236450195, | |
| "learning_rate": 0.0001, | |
| "loss": 9.7248, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.02857777305772517, | |
| "grad_norm": 12.14108943939209, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3096, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.028770866118926017, | |
| "grad_norm": 15.33022689819336, | |
| "learning_rate": 0.0001, | |
| "loss": 11.5878, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.028963959180126862, | |
| "grad_norm": 29.498929977416992, | |
| "learning_rate": 0.0001, | |
| "loss": 13.2048, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.028963959180126862, | |
| "eval_loss": 2.7453110218048096, | |
| "eval_runtime": 336.37, | |
| "eval_samples_per_second": 129.655, | |
| "eval_steps_per_second": 32.414, | |
| "step": 1500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 150, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.0944605381853184e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |