| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3952569169960474, | |
| "eval_steps": 38, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002635046113306983, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002635046113306983, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6332, | |
| "eval_samples_per_second": 10.235, | |
| "eval_steps_per_second": 5.117, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005270092226613966, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007905138339920948, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010540184453227932, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013175230566534914, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015810276679841896, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00024, | |
| "loss": 6.5685, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01844532279314888, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.021080368906455864, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00032, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.023715415019762844, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00036, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.026350461133069828, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0004, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.028985507246376812, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003999496469885013, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03162055335968379, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00039979861330826294, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.034255599472990776, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003995469750092912, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03689064558629776, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00039919485879904784, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.039525691699604744, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00039874244197864856, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04216073781291173, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00039818995235358696, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04479578392621871, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00039753766811902755, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04743083003952569, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003967859177197259, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05006587615283267, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00039593507968464716, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.052700922266139656, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003949855824363647, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05533596837944664, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003939379040753374, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.057971014492753624, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00039279257213917066, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06060606060606061, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003915501633369861, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06324110671936758, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00039021130325903074, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06587615283267458, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00038877666606167355, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06851119894598155, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00038724697412794747, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07114624505928854, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003856229977038078, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07378129117259552, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003839055545102902, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0764163372859025, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00038209550933176323, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07905138339920949, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003801937735804838, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08168642951251646, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003782013048376736, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08432147562582346, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003761191063713476, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08695652173913043, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003739482266311391, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08959156785243742, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00037168975872037323, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0922266139657444, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00036934483984565685, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09486166007905138, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00036691465074426054, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09749670619235837, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00036440041508958203, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10013175230566534, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003618033988749895, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10013175230566534, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.097, | |
| "eval_samples_per_second": 11.35, | |
| "eval_steps_per_second": 5.675, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10276679841897234, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00035912490977635625, | |
| "loss": 2.2343, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10540184453227931, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000356366296493606, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1080368906455863, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003535289480716022, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11067193675889328, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00035061429320072223, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11330698287220026, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00034762379949746815, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11594202898550725, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003445589727654783, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11857707509881422, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003414213562373095, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00033821252979737297, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12384716732542819, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003349341091864149, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12648221343873517, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00033158774518794254, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12911725955204217, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003281751227970048, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13175230566534915, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00032469796037174674, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13438735177865613, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000321158008768164, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.1370223978919631, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00031755705045849464, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.13965744400527008, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003138968986336904, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.1422924901185771, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0003101793962904205, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.14492753623188406, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00030640641530306733, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.14756258234519104, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00030257985548118126, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.15019762845849802, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002987016436128694, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.152832674571805, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002947737324945997, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.155467720685112, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00029079809994790937, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.15810276679841898, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028677674782351165, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16073781291172595, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00028271170099330415, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.16337285902503293, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027860500633078477, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.16600790513833993, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00027445873168038907, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.1686429512516469, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002702749648162686, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.1712779973649539, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00026605581239103347, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.17391304347826086, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00026180339887498953, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.17654808959156784, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00025751986548640346, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.17918313570487485, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00025320736911333503, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002488680812275788, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.1844532279314888, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002445041867912629, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18708827404479578, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00024011788315665458, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.18972332015810275, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00023571137895972733, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.19235836627140976, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002312868930080462, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.19499341238471674, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002268466531635311, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.1976284584980237, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00022239289522066157, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2002635046113307, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00021792786178068672, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.2002635046113307, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.106, | |
| "eval_samples_per_second": 11.343, | |
| "eval_steps_per_second": 5.671, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.2028985507246377, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00021345380112240797, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.20553359683794467, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00020897296607010301, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.20816864295125165, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00020448761285916104, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.21080368906455862, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2134387351778656, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019551238714083903, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.2160737812911726, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019102703392989709, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.21870882740447958, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018654619887759207, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.22134387351778656, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018207213821931333, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.22397891963109354, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017760710477933845, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.22661396574440051, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017315334683646897, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.22924901185770752, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016871310699195379, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.2318840579710145, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016428862104027268, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.23451910408432147, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015988211684334546, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.23715415019762845, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015549581320873715, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23978919631093545, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015113191877242117, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014679263088666499, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.2450592885375494, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014248013451359656, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.24769433465085638, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013819660112501054, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.2503293807641634, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013394418760896666, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.25296442687747034, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012972503518373144, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.25559947299077734, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012554126831961098, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.25823451910408435, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001213949936692153, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.2608695652173913, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011728829900669591, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.2635046113306983, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011322325217648839, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26613965744400525, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010920190005209065, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.26877470355731226, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010522626750540028, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.27140974967061926, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010129835638713063, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.2740447957839262, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.74201445188188e-05, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.2766798418972332, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.359358469693271e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.27931488801054016, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.982060370957952e-05, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.28194993412384717, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.610310136630962e-05, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.2845849802371542, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.24429495415054e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.2872200263504611, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.884199123183605e-05, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.2898550724637681, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.530203962825331e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2924901185770751, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.182487720299517e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.2951251646903821, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.841225481205749e-05, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.2977602108036891, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.506589081358514e-05, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.30039525691699603, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.178747020262707e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.30039525691699603, | |
| "eval_loss": NaN, | |
| "eval_runtime": 14.1098, | |
| "eval_samples_per_second": 11.34, | |
| "eval_steps_per_second": 5.67, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.30303030303030304, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.857864376269051e-05, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.30566534914361, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.544102723452171e-05, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.308300395256917, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.237620050253189e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.310935441370224, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.938570679927783e-05, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.31357048748353095, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.647105192839778e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.31620553359683795, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.363370350639404e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3188405797101449, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.087509022364382e-05, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.3214756258234519, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.819660112501053e-05, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.3241106719367589, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5599584910418035e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.32674571805006586, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3085349255739474e-05, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.32938076416337286, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0655160154343174e-05, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.33201581027667987, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.831024127962678e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.3346508563899868, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6051773368860934e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.3372859025032938, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.38808936286524e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.33992094861660077, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1798695162326442e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.3425559947299078, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9806226419516192e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3451910408432148, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.790449066823683e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6094445489709885e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.35046113306982873, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4377002296192233e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.3530961791831357, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.275302587205256e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.3557312252964427, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1223333938326485e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.3583662714097497, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.788696740969295e-06, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.36100131752305664, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.44983666301391e-06, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.2074278608293525e-06, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.3662714097496706, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.062095924662625e-06, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.3689064558629776, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0144175636352765e-06, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3715415019762846, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.064920315352904e-06, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.37417654808959155, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2140822802740668e-06, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.37681159420289856, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.462331880972468e-06, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.3794466403162055, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.81004764641306e-06, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.3820816864295125, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2575580213514792e-06, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.3847167325428195, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.051412009521864e-07, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.38735177865612647, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.530249907087836e-07, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.38998682476943347, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0138669173708213e-07, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.3926218708827404, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.035301149869387e-08, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.3952569169960474, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 38, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8626338709635072.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |