| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9956709956709957, | |
| "eval_steps": 58, | |
| "global_step": 115, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008658008658008658, | |
| "grad_norm": 0.11093204468488693, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5798, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008658008658008658, | |
| "eval_loss": 1.570786714553833, | |
| "eval_runtime": 25.8433, | |
| "eval_samples_per_second": 246.718, | |
| "eval_steps_per_second": 30.84, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017316017316017316, | |
| "grad_norm": 0.13193683326244354, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6109, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.025974025974025976, | |
| "grad_norm": 0.12040749937295914, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5904, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03463203463203463, | |
| "grad_norm": 0.1296212375164032, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5825, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04329004329004329, | |
| "grad_norm": 0.15250156819820404, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6009, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05194805194805195, | |
| "grad_norm": 0.19382008910179138, | |
| "learning_rate": 0.00012, | |
| "loss": 1.5556, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06060606060606061, | |
| "grad_norm": 0.22872094810009003, | |
| "learning_rate": 0.00014, | |
| "loss": 1.5656, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06926406926406926, | |
| "grad_norm": 0.23726485669612885, | |
| "learning_rate": 0.00016, | |
| "loss": 1.47, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07792207792207792, | |
| "grad_norm": 0.22901910543441772, | |
| "learning_rate": 0.00018, | |
| "loss": 1.3961, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08658008658008658, | |
| "grad_norm": 0.20660609006881714, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3514, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09523809523809523, | |
| "grad_norm": 0.16906796395778656, | |
| "learning_rate": 0.00019995524322835034, | |
| "loss": 1.254, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1038961038961039, | |
| "grad_norm": 0.16580761969089508, | |
| "learning_rate": 0.0001998210129767735, | |
| "loss": 1.2026, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11255411255411256, | |
| "grad_norm": 0.23203064501285553, | |
| "learning_rate": 0.00019959742939952392, | |
| "loss": 1.1739, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 0.23922611773014069, | |
| "learning_rate": 0.00019928469263418374, | |
| "loss": 1.103, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12987012987012986, | |
| "grad_norm": 0.19562934339046478, | |
| "learning_rate": 0.00019888308262251285, | |
| "loss": 1.0532, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13852813852813853, | |
| "grad_norm": 0.1417841911315918, | |
| "learning_rate": 0.00019839295885986296, | |
| "loss": 1.034, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1471861471861472, | |
| "grad_norm": 0.11438935995101929, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 1.0186, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15584415584415584, | |
| "grad_norm": 0.10540100187063217, | |
| "learning_rate": 0.00019714900382928675, | |
| "loss": 0.9839, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1645021645021645, | |
| "grad_norm": 0.10455407947301865, | |
| "learning_rate": 0.00019639628606958533, | |
| "loss": 0.986, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17316017316017315, | |
| "grad_norm": 0.10251545161008835, | |
| "learning_rate": 0.0001955572805786141, | |
| "loss": 0.9835, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 0.09409354627132416, | |
| "learning_rate": 0.00019463273837991643, | |
| "loss": 0.9595, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 0.08605455607175827, | |
| "learning_rate": 0.00019362348706397373, | |
| "loss": 0.9622, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19913419913419914, | |
| "grad_norm": 0.08584555238485336, | |
| "learning_rate": 0.00019253043004739968, | |
| "loss": 0.9529, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2077922077922078, | |
| "grad_norm": 0.07192489504814148, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.9383, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21645021645021645, | |
| "grad_norm": 0.06461908668279648, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 0.9182, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22510822510822512, | |
| "grad_norm": 0.06550411134958267, | |
| "learning_rate": 0.00018875857890045543, | |
| "loss": 0.8982, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23376623376623376, | |
| "grad_norm": 0.07315943390130997, | |
| "learning_rate": 0.00018734082006171299, | |
| "loss": 0.9074, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 0.07087890803813934, | |
| "learning_rate": 0.00018584487936018661, | |
| "loss": 0.9125, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2510822510822511, | |
| "grad_norm": 0.06873635947704315, | |
| "learning_rate": 0.0001842720958654039, | |
| "loss": 0.8867, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2597402597402597, | |
| "grad_norm": 0.06812155246734619, | |
| "learning_rate": 0.0001826238774315995, | |
| "loss": 0.8891, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2683982683982684, | |
| "grad_norm": 0.08119972795248032, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.8794, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.27705627705627706, | |
| "grad_norm": 0.060435950756073, | |
| "learning_rate": 0.00017910710346563416, | |
| "loss": 0.8807, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 0.057483069598674774, | |
| "learning_rate": 0.00017724169592245995, | |
| "loss": 0.8789, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2943722943722944, | |
| "grad_norm": 0.055934980511665344, | |
| "learning_rate": 0.00017530714660036112, | |
| "loss": 0.8631, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.30303030303030304, | |
| "grad_norm": 0.07267452776432037, | |
| "learning_rate": 0.00017330518718298264, | |
| "loss": 0.838, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3116883116883117, | |
| "grad_norm": 0.05725516006350517, | |
| "learning_rate": 0.0001712376096951345, | |
| "loss": 0.8491, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3203463203463203, | |
| "grad_norm": 0.05821891874074936, | |
| "learning_rate": 0.00016910626489868649, | |
| "loss": 0.8376, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.329004329004329, | |
| "grad_norm": 0.06176719069480896, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.8397, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.33766233766233766, | |
| "grad_norm": 0.051375944167375565, | |
| "learning_rate": 0.00016465996012157995, | |
| "loss": 0.8449, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3463203463203463, | |
| "grad_norm": 0.05730742588639259, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 0.8705, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.354978354978355, | |
| "grad_norm": 0.053983114659786224, | |
| "learning_rate": 0.00015998218946879138, | |
| "loss": 0.8399, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 0.05474100634455681, | |
| "learning_rate": 0.00015756170656856737, | |
| "loss": 0.8219, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3722943722943723, | |
| "grad_norm": 0.0504613034427166, | |
| "learning_rate": 0.00015508969814521025, | |
| "loss": 0.8137, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 0.04792892560362816, | |
| "learning_rate": 0.00015256837698105047, | |
| "loss": 0.8327, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.38961038961038963, | |
| "grad_norm": 0.04982732608914375, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.8509, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.39826839826839827, | |
| "grad_norm": 0.04842912778258324, | |
| "learning_rate": 0.00014738686624729986, | |
| "loss": 0.8114, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4069264069264069, | |
| "grad_norm": 0.04842810332775116, | |
| "learning_rate": 0.00014473131483156327, | |
| "loss": 0.8104, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4155844155844156, | |
| "grad_norm": 0.052241936326026917, | |
| "learning_rate": 0.00014203572283095657, | |
| "loss": 0.8121, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.42424242424242425, | |
| "grad_norm": 0.0497763529419899, | |
| "learning_rate": 0.00013930250316539238, | |
| "loss": 0.8251, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4329004329004329, | |
| "grad_norm": 0.050107311457395554, | |
| "learning_rate": 0.00013653410243663952, | |
| "loss": 0.8286, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.44155844155844154, | |
| "grad_norm": 0.04895767569541931, | |
| "learning_rate": 0.00013373299873828303, | |
| "loss": 0.8227, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.45021645021645024, | |
| "grad_norm": 0.04833944886922836, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.7994, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.4588744588744589, | |
| "grad_norm": 0.050548214465379715, | |
| "learning_rate": 0.00012804273893060028, | |
| "loss": 0.8223, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.4675324675324675, | |
| "grad_norm": 0.05153653398156166, | |
| "learning_rate": 0.00012515867637445086, | |
| "loss": 0.8076, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 0.05172652378678322, | |
| "learning_rate": 0.00012225209339563145, | |
| "loss": 0.8329, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 0.04874265193939209, | |
| "learning_rate": 0.00011932559177955533, | |
| "loss": 0.8061, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.4935064935064935, | |
| "grad_norm": 0.05159593001008034, | |
| "learning_rate": 0.00011638179114151377, | |
| "loss": 0.7794, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.5021645021645021, | |
| "grad_norm": 0.054299090057611465, | |
| "learning_rate": 0.00011342332658176555, | |
| "loss": 0.7984, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5021645021645021, | |
| "eval_loss": 0.788051426410675, | |
| "eval_runtime": 28.9237, | |
| "eval_samples_per_second": 220.442, | |
| "eval_steps_per_second": 27.555, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5108225108225108, | |
| "grad_norm": 0.04983401671051979, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.794, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5194805194805194, | |
| "grad_norm": 0.0501757487654686, | |
| "learning_rate": 0.00010747300935864243, | |
| "loss": 0.7891, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5281385281385281, | |
| "grad_norm": 0.04997857287526131, | |
| "learning_rate": 0.00010448648303505151, | |
| "loss": 0.7903, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5367965367965368, | |
| "grad_norm": 0.048633065074682236, | |
| "learning_rate": 0.00010149594070152638, | |
| "loss": 0.7792, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 0.05213923007249832, | |
| "learning_rate": 9.850405929847366e-05, | |
| "loss": 0.7935, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.5541125541125541, | |
| "grad_norm": 0.04998105391860008, | |
| "learning_rate": 9.551351696494854e-05, | |
| "loss": 0.7744, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5627705627705628, | |
| "grad_norm": 0.05255527049303055, | |
| "learning_rate": 9.252699064135758e-05, | |
| "loss": 0.7837, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.05218357592821121, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.7857, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5800865800865801, | |
| "grad_norm": 0.05224675312638283, | |
| "learning_rate": 8.657667341823448e-05, | |
| "loss": 0.7762, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.5887445887445888, | |
| "grad_norm": 0.050885338336229324, | |
| "learning_rate": 8.361820885848624e-05, | |
| "loss": 0.7722, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.5974025974025974, | |
| "grad_norm": 0.05296636000275612, | |
| "learning_rate": 8.067440822044469e-05, | |
| "loss": 0.7946, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 0.051182664930820465, | |
| "learning_rate": 7.774790660436858e-05, | |
| "loss": 0.7684, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6147186147186147, | |
| "grad_norm": 0.05467361956834793, | |
| "learning_rate": 7.484132362554915e-05, | |
| "loss": 0.8165, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6233766233766234, | |
| "grad_norm": 0.05064595863223076, | |
| "learning_rate": 7.195726106939974e-05, | |
| "loss": 0.7784, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6320346320346321, | |
| "grad_norm": 0.05015125870704651, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.7687, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.6406926406926406, | |
| "grad_norm": 0.0537785179913044, | |
| "learning_rate": 6.626700126171702e-05, | |
| "loss": 0.7766, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.6493506493506493, | |
| "grad_norm": 0.051856957376003265, | |
| "learning_rate": 6.34658975633605e-05, | |
| "loss": 0.7737, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.658008658008658, | |
| "grad_norm": 0.05247452110052109, | |
| "learning_rate": 6.069749683460765e-05, | |
| "loss": 0.7688, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.05488152056932449, | |
| "learning_rate": 5.796427716904347e-05, | |
| "loss": 0.7825, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.6753246753246753, | |
| "grad_norm": 0.053116098046302795, | |
| "learning_rate": 5.526868516843673e-05, | |
| "loss": 0.7796, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.683982683982684, | |
| "grad_norm": 0.05379800498485565, | |
| "learning_rate": 5.261313375270014e-05, | |
| "loss": 0.7976, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.6926406926406926, | |
| "grad_norm": 0.0555279403924942, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.774, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7012987012987013, | |
| "grad_norm": 0.05348188057541847, | |
| "learning_rate": 4.743162301894952e-05, | |
| "loss": 0.7782, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.70995670995671, | |
| "grad_norm": 0.05335194244980812, | |
| "learning_rate": 4.491030185478976e-05, | |
| "loss": 0.769, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.7186147186147186, | |
| "grad_norm": 0.05507886782288551, | |
| "learning_rate": 4.2438293431432665e-05, | |
| "loss": 0.7765, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.05403213948011398, | |
| "learning_rate": 4.001781053120863e-05, | |
| "loss": 0.7684, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.7359307359307359, | |
| "grad_norm": 0.05368750914931297, | |
| "learning_rate": 3.7651019814126654e-05, | |
| "loss": 0.7693, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.7445887445887446, | |
| "grad_norm": 0.0559493824839592, | |
| "learning_rate": 3.534003987842005e-05, | |
| "loss": 0.7867, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.7532467532467533, | |
| "grad_norm": 0.05538685619831085, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.7789, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 0.054037969559431076, | |
| "learning_rate": 3.089373510131354e-05, | |
| "loss": 0.7672, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.7705627705627706, | |
| "grad_norm": 0.054057423025369644, | |
| "learning_rate": 2.876239030486554e-05, | |
| "loss": 0.7759, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.7792207792207793, | |
| "grad_norm": 0.05448087304830551, | |
| "learning_rate": 2.669481281701739e-05, | |
| "loss": 0.7737, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7878787878787878, | |
| "grad_norm": 0.05279451981186867, | |
| "learning_rate": 2.4692853399638917e-05, | |
| "loss": 0.7617, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.7965367965367965, | |
| "grad_norm": 0.055114444345235825, | |
| "learning_rate": 2.275830407754006e-05, | |
| "loss": 0.7658, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.8051948051948052, | |
| "grad_norm": 0.05524512380361557, | |
| "learning_rate": 2.0892896534365904e-05, | |
| "loss": 0.787, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.8138528138528138, | |
| "grad_norm": 0.05598621442914009, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.7608, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.8225108225108225, | |
| "grad_norm": 0.055263664573431015, | |
| "learning_rate": 1.7376122568400532e-05, | |
| "loss": 0.7751, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8311688311688312, | |
| "grad_norm": 0.053236011415719986, | |
| "learning_rate": 1.5727904134596083e-05, | |
| "loss": 0.7541, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.8398268398268398, | |
| "grad_norm": 0.05485166609287262, | |
| "learning_rate": 1.415512063981339e-05, | |
| "loss": 0.7619, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.8484848484848485, | |
| "grad_norm": 0.0545911081135273, | |
| "learning_rate": 1.2659179938287035e-05, | |
| "loss": 0.7705, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.05586208403110504, | |
| "learning_rate": 1.124142109954459e-05, | |
| "loss": 0.7552, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.8658008658008658, | |
| "grad_norm": 0.05504390969872475, | |
| "learning_rate": 9.903113209758096e-06, | |
| "loss": 0.7639, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8744588744588745, | |
| "grad_norm": 0.0530891939997673, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.7605, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.8831168831168831, | |
| "grad_norm": 0.05585161969065666, | |
| "learning_rate": 7.46956995260033e-06, | |
| "loss": 0.7837, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.8917748917748918, | |
| "grad_norm": 0.05504593625664711, | |
| "learning_rate": 6.37651293602628e-06, | |
| "loss": 0.7625, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.9004329004329005, | |
| "grad_norm": 0.05624198541045189, | |
| "learning_rate": 5.367261620083575e-06, | |
| "loss": 0.7876, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 0.05238276347517967, | |
| "learning_rate": 4.442719421385922e-06, | |
| "loss": 0.7626, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.9177489177489178, | |
| "grad_norm": 0.05504492297768593, | |
| "learning_rate": 3.6037139304146762e-06, | |
| "loss": 0.776, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.9264069264069265, | |
| "grad_norm": 0.05449540913105011, | |
| "learning_rate": 2.8509961707132494e-06, | |
| "loss": 0.7873, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.935064935064935, | |
| "grad_norm": 0.054615579545497894, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.7808, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.9437229437229437, | |
| "grad_norm": 0.05515173450112343, | |
| "learning_rate": 1.6070411401370334e-06, | |
| "loss": 0.7746, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 0.05492587760090828, | |
| "learning_rate": 1.1169173774871478e-06, | |
| "loss": 0.7745, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.961038961038961, | |
| "grad_norm": 0.05713028460741043, | |
| "learning_rate": 7.153073658162646e-07, | |
| "loss": 0.7788, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.9696969696969697, | |
| "grad_norm": 0.054508037865161896, | |
| "learning_rate": 4.025706004760932e-07, | |
| "loss": 0.7714, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.9783549783549783, | |
| "grad_norm": 0.058265261352062225, | |
| "learning_rate": 1.7898702322648453e-07, | |
| "loss": 0.7821, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.987012987012987, | |
| "grad_norm": 0.055581748485565186, | |
| "learning_rate": 4.475677164966774e-08, | |
| "loss": 0.7815, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.9956709956709957, | |
| "grad_norm": 0.057229481637477875, | |
| "learning_rate": 0.0, | |
| "loss": 0.779, | |
| "step": 115 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 115, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.04802976275497e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |