| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 58, | |
| "global_step": 116, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008620689655172414, | |
| "grad_norm": 0.7549098134040833, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3785, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008620689655172414, | |
| "eval_loss": 2.582935094833374, | |
| "eval_runtime": 7.6921, | |
| "eval_samples_per_second": 25.351, | |
| "eval_steps_per_second": 3.25, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017241379310344827, | |
| "grad_norm": 0.720708966255188, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2748, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02586206896551724, | |
| "grad_norm": 0.6924182176589966, | |
| "learning_rate": 6e-05, | |
| "loss": 2.4147, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.034482758620689655, | |
| "grad_norm": 0.8156349658966064, | |
| "learning_rate": 8e-05, | |
| "loss": 2.3778, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04310344827586207, | |
| "grad_norm": 0.7163665294647217, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4918, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05172413793103448, | |
| "grad_norm": 0.9344202280044556, | |
| "learning_rate": 0.00012, | |
| "loss": 2.5429, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0603448275862069, | |
| "grad_norm": 0.8686364889144897, | |
| "learning_rate": 0.00014, | |
| "loss": 2.0592, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06896551724137931, | |
| "grad_norm": 0.9987367987632751, | |
| "learning_rate": 0.00016, | |
| "loss": 1.8856, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07758620689655173, | |
| "grad_norm": 1.5086486339569092, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8125, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08620689655172414, | |
| "grad_norm": 1.8301935195922852, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1144, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09482758620689655, | |
| "grad_norm": 2.5455808639526367, | |
| "learning_rate": 0.00019995608365087946, | |
| "loss": 1.4668, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10344827586206896, | |
| "grad_norm": 3.3915581703186035, | |
| "learning_rate": 0.00019982437317643217, | |
| "loss": 1.3056, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11206896551724138, | |
| "grad_norm": 3.114424705505371, | |
| "learning_rate": 0.0001996049842615217, | |
| "loss": 1.0526, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1206896551724138, | |
| "grad_norm": 2.363276243209839, | |
| "learning_rate": 0.00019929810960135172, | |
| "loss": 0.729, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12931034482758622, | |
| "grad_norm": 2.7170567512512207, | |
| "learning_rate": 0.0001989040187322164, | |
| "loss": 0.5538, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "grad_norm": 2.299168109893799, | |
| "learning_rate": 0.00019842305779475968, | |
| "loss": 0.3469, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14655172413793102, | |
| "grad_norm": 1.1169408559799194, | |
| "learning_rate": 0.0001978556492299504, | |
| "loss": 0.1737, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15517241379310345, | |
| "grad_norm": 8.511645317077637, | |
| "learning_rate": 0.0001972022914080411, | |
| "loss": 0.2247, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16379310344827586, | |
| "grad_norm": 1.6103713512420654, | |
| "learning_rate": 0.00019646355819083589, | |
| "loss": 0.1969, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1724137931034483, | |
| "grad_norm": 1.5031853914260864, | |
| "learning_rate": 0.00019564009842765225, | |
| "loss": 0.1419, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1810344827586207, | |
| "grad_norm": 1.3411375284194946, | |
| "learning_rate": 0.00019473263538541914, | |
| "loss": 0.111, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1896551724137931, | |
| "grad_norm": 0.4128853678703308, | |
| "learning_rate": 0.0001937419661134121, | |
| "loss": 0.0782, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19827586206896552, | |
| "grad_norm": 0.40607255697250366, | |
| "learning_rate": 0.00019266896074318334, | |
| "loss": 0.0601, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.20689655172413793, | |
| "grad_norm": 1.0385711193084717, | |
| "learning_rate": 0.00019151456172430183, | |
| "loss": 0.0881, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21551724137931033, | |
| "grad_norm": 0.5099380016326904, | |
| "learning_rate": 0.00019027978299657436, | |
| "loss": 0.1187, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22413793103448276, | |
| "grad_norm": 0.2118569314479828, | |
| "learning_rate": 0.00018896570909947475, | |
| "loss": 0.1058, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23275862068965517, | |
| "grad_norm": 0.37697386741638184, | |
| "learning_rate": 0.0001875734942195637, | |
| "loss": 0.0779, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2413793103448276, | |
| "grad_norm": 0.5538561940193176, | |
| "learning_rate": 0.00018610436117673555, | |
| "loss": 0.1473, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.13844181597232819, | |
| "learning_rate": 0.0001845596003501826, | |
| "loss": 0.0387, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.25862068965517243, | |
| "grad_norm": 0.28886792063713074, | |
| "learning_rate": 0.0001829405685450202, | |
| "loss": 0.0484, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2672413793103448, | |
| "grad_norm": 0.40534093976020813, | |
| "learning_rate": 0.00018124868780056814, | |
| "loss": 0.0506, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 0.28827980160713196, | |
| "learning_rate": 0.00017948544414133534, | |
| "loss": 0.0386, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.28448275862068967, | |
| "grad_norm": 0.19116564095020294, | |
| "learning_rate": 0.00017765238627180424, | |
| "loss": 0.0344, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.29310344827586204, | |
| "grad_norm": 0.2074674665927887, | |
| "learning_rate": 0.00017575112421616202, | |
| "loss": 0.0587, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3017241379310345, | |
| "grad_norm": 0.18823839724063873, | |
| "learning_rate": 0.00017378332790417273, | |
| "loss": 0.0449, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3103448275862069, | |
| "grad_norm": 0.2116956263780594, | |
| "learning_rate": 0.00017175072570443312, | |
| "loss": 0.0547, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.31896551724137934, | |
| "grad_norm": 0.2971654534339905, | |
| "learning_rate": 0.00016965510290629972, | |
| "loss": 0.0417, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3275862068965517, | |
| "grad_norm": 0.11563872545957565, | |
| "learning_rate": 0.00016749830015182107, | |
| "loss": 0.0196, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.33620689655172414, | |
| "grad_norm": 0.09132111817598343, | |
| "learning_rate": 0.00016528221181905217, | |
| "loss": 0.015, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 0.11758074164390564, | |
| "learning_rate": 0.00016300878435817113, | |
| "loss": 0.0264, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.35344827586206895, | |
| "grad_norm": 0.26003605127334595, | |
| "learning_rate": 0.00016068001458185936, | |
| "loss": 0.0701, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3620689655172414, | |
| "grad_norm": 0.16987216472625732, | |
| "learning_rate": 0.0001582979479114472, | |
| "loss": 0.0232, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3706896551724138, | |
| "grad_norm": 0.16075719892978668, | |
| "learning_rate": 0.00015586467658036524, | |
| "loss": 0.0257, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3793103448275862, | |
| "grad_norm": 0.08301292359828949, | |
| "learning_rate": 0.0001533823377964791, | |
| "loss": 0.0059, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3879310344827586, | |
| "grad_norm": 0.13616588711738586, | |
| "learning_rate": 0.00015085311186492206, | |
| "loss": 0.0207, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.39655172413793105, | |
| "grad_norm": 0.7669395804405212, | |
| "learning_rate": 0.00014827922027307451, | |
| "loss": 0.0992, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4051724137931034, | |
| "grad_norm": 0.2077718824148178, | |
| "learning_rate": 0.0001456629237393713, | |
| "loss": 0.0193, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.41379310344827586, | |
| "grad_norm": 0.08794950693845749, | |
| "learning_rate": 0.00014300652022765207, | |
| "loss": 0.0107, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4224137931034483, | |
| "grad_norm": 0.1444607675075531, | |
| "learning_rate": 0.00014031234292879725, | |
| "loss": 0.0269, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.43103448275862066, | |
| "grad_norm": 0.22816063463687897, | |
| "learning_rate": 0.00013758275821142382, | |
| "loss": 0.0201, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4396551724137931, | |
| "grad_norm": 0.24295277893543243, | |
| "learning_rate": 0.0001348201635434399, | |
| "loss": 0.0304, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.4482758620689655, | |
| "grad_norm": 0.22172880172729492, | |
| "learning_rate": 0.00013202698538628376, | |
| "loss": 0.0128, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.45689655172413796, | |
| "grad_norm": 0.12180917710065842, | |
| "learning_rate": 0.00012920567706369758, | |
| "loss": 0.016, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.46551724137931033, | |
| "grad_norm": 0.278648316860199, | |
| "learning_rate": 0.00012635871660690676, | |
| "loss": 0.0337, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.47413793103448276, | |
| "grad_norm": 0.0709623172879219, | |
| "learning_rate": 0.00012348860457809838, | |
| "loss": 0.0126, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.4827586206896552, | |
| "grad_norm": 0.1974678933620453, | |
| "learning_rate": 0.00012059786187410984, | |
| "loss": 0.019, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.49137931034482757, | |
| "grad_norm": 0.08393372595310211, | |
| "learning_rate": 0.0001176890275122573, | |
| "loss": 0.0083, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.12021597474813461, | |
| "learning_rate": 0.00011476465640024814, | |
| "loss": 0.0084, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.02141181007027626, | |
| "eval_runtime": 7.7496, | |
| "eval_samples_per_second": 25.163, | |
| "eval_steps_per_second": 3.226, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5086206896551724, | |
| "grad_norm": 0.12311367690563202, | |
| "learning_rate": 0.00011182731709213659, | |
| "loss": 0.0259, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5172413793103449, | |
| "grad_norm": 0.03950917348265648, | |
| "learning_rate": 0.00010887958953229349, | |
| "loss": 0.0033, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5258620689655172, | |
| "grad_norm": 0.12783688306808472, | |
| "learning_rate": 0.00010592406278937144, | |
| "loss": 0.0094, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5344827586206896, | |
| "grad_norm": 0.23351043462753296, | |
| "learning_rate": 0.00010296333278225599, | |
| "loss": 0.0405, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5431034482758621, | |
| "grad_norm": 0.07918150722980499, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0189, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": 0.129180446267128, | |
| "learning_rate": 9.703666721774402e-05, | |
| "loss": 0.0118, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5603448275862069, | |
| "grad_norm": 0.20834843814373016, | |
| "learning_rate": 9.407593721062859e-05, | |
| "loss": 0.0106, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5689655172413793, | |
| "grad_norm": 0.03432063013315201, | |
| "learning_rate": 9.112041046770653e-05, | |
| "loss": 0.0031, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5775862068965517, | |
| "grad_norm": 0.3878253698348999, | |
| "learning_rate": 8.817268290786343e-05, | |
| "loss": 0.0199, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.5862068965517241, | |
| "grad_norm": 0.19941666722297668, | |
| "learning_rate": 8.523534359975189e-05, | |
| "loss": 0.0282, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.5948275862068966, | |
| "grad_norm": 0.28532180190086365, | |
| "learning_rate": 8.231097248774274e-05, | |
| "loss": 0.0231, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.603448275862069, | |
| "grad_norm": 0.19040793180465698, | |
| "learning_rate": 7.940213812589018e-05, | |
| "loss": 0.0239, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6120689655172413, | |
| "grad_norm": 0.15338897705078125, | |
| "learning_rate": 7.651139542190164e-05, | |
| "loss": 0.0096, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6206896551724138, | |
| "grad_norm": 0.21563775837421417, | |
| "learning_rate": 7.364128339309326e-05, | |
| "loss": 0.0182, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6293103448275862, | |
| "grad_norm": 0.11136949807405472, | |
| "learning_rate": 7.079432293630244e-05, | |
| "loss": 0.0198, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.6379310344827587, | |
| "grad_norm": 0.06761553883552551, | |
| "learning_rate": 6.797301461371625e-05, | |
| "loss": 0.0061, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.646551724137931, | |
| "grad_norm": 0.17843712866306305, | |
| "learning_rate": 6.517983645656014e-05, | |
| "loss": 0.0105, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6551724137931034, | |
| "grad_norm": 0.12946659326553345, | |
| "learning_rate": 6.24172417885762e-05, | |
| "loss": 0.0148, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.6637931034482759, | |
| "grad_norm": 0.04445435479283333, | |
| "learning_rate": 5.96876570712028e-05, | |
| "loss": 0.0046, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.6724137931034483, | |
| "grad_norm": 0.12194405496120453, | |
| "learning_rate": 5.699347977234799e-05, | |
| "loss": 0.021, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.6810344827586207, | |
| "grad_norm": 0.1209009662270546, | |
| "learning_rate": 5.43370762606287e-05, | |
| "loss": 0.0038, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "grad_norm": 0.18816731870174408, | |
| "learning_rate": 5.172077972692553e-05, | |
| "loss": 0.0175, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6982758620689655, | |
| "grad_norm": 0.0713019147515297, | |
| "learning_rate": 4.914688813507797e-05, | |
| "loss": 0.0033, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.7068965517241379, | |
| "grad_norm": 0.06428212672472, | |
| "learning_rate": 4.661766220352097e-05, | |
| "loss": 0.0111, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.7155172413793104, | |
| "grad_norm": 0.06654125452041626, | |
| "learning_rate": 4.4135323419634766e-05, | |
| "loss": 0.0088, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.7241379310344828, | |
| "grad_norm": 0.08924495428800583, | |
| "learning_rate": 4.170205208855281e-05, | |
| "loss": 0.0104, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.7327586206896551, | |
| "grad_norm": 0.1306809037923813, | |
| "learning_rate": 3.931998541814069e-05, | |
| "loss": 0.014, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.7413793103448276, | |
| "grad_norm": 0.6109310984611511, | |
| "learning_rate": 3.69912156418289e-05, | |
| "loss": 0.0169, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.1788921356201172, | |
| "learning_rate": 3.471778818094785e-05, | |
| "loss": 0.0139, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.7586206896551724, | |
| "grad_norm": 0.07347411662340164, | |
| "learning_rate": 3.250169984817897e-05, | |
| "loss": 0.0113, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.7672413793103449, | |
| "grad_norm": 0.2131931632757187, | |
| "learning_rate": 3.034489709370033e-05, | |
| "loss": 0.0268, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.7758620689655172, | |
| "grad_norm": 0.06642799824476242, | |
| "learning_rate": 2.8249274295566864e-05, | |
| "loss": 0.0124, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7844827586206896, | |
| "grad_norm": 0.26418986916542053, | |
| "learning_rate": 2.6216672095827266e-05, | |
| "loss": 0.013, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.7931034482758621, | |
| "grad_norm": 0.016451340168714523, | |
| "learning_rate": 2.4248875783837987e-05, | |
| "loss": 0.0018, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.8017241379310345, | |
| "grad_norm": 0.10589156299829483, | |
| "learning_rate": 2.234761372819577e-05, | |
| "loss": 0.0198, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.8103448275862069, | |
| "grad_norm": 0.09367933124303818, | |
| "learning_rate": 2.0514555858664663e-05, | |
| "loss": 0.0067, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.8189655172413793, | |
| "grad_norm": 0.04479554295539856, | |
| "learning_rate": 1.875131219943187e-05, | |
| "loss": 0.0029, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8275862068965517, | |
| "grad_norm": 0.06302911043167114, | |
| "learning_rate": 1.7059431454979824e-05, | |
| "loss": 0.0052, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.8362068965517241, | |
| "grad_norm": 0.05771315097808838, | |
| "learning_rate": 1.5440399649817385e-05, | |
| "loss": 0.0082, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.8448275862068966, | |
| "grad_norm": 0.2593729794025421, | |
| "learning_rate": 1.3895638823264446e-05, | |
| "loss": 0.0174, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.853448275862069, | |
| "grad_norm": 0.0901479423046112, | |
| "learning_rate": 1.2426505780436326e-05, | |
| "loss": 0.0059, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.8620689655172413, | |
| "grad_norm": 0.3058486580848694, | |
| "learning_rate": 1.103429090052528e-05, | |
| "loss": 0.0136, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8706896551724138, | |
| "grad_norm": 0.13096828758716583, | |
| "learning_rate": 9.720217003425647e-06, | |
| "loss": 0.0102, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.8793103448275862, | |
| "grad_norm": 0.04190494120121002, | |
| "learning_rate": 8.485438275698154e-06, | |
| "loss": 0.0055, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.8879310344827587, | |
| "grad_norm": 0.247361958026886, | |
| "learning_rate": 7.331039256816663e-06, | |
| "loss": 0.0212, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.896551724137931, | |
| "grad_norm": 0.07285796105861664, | |
| "learning_rate": 6.258033886587911e-06, | |
| "loss": 0.0116, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.9051724137931034, | |
| "grad_norm": 0.08532743901014328, | |
| "learning_rate": 5.267364614580861e-06, | |
| "loss": 0.0147, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.9137931034482759, | |
| "grad_norm": 0.042795587331056595, | |
| "learning_rate": 4.359901572347758e-06, | |
| "loss": 0.0031, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.9224137931034483, | |
| "grad_norm": 0.05108323693275452, | |
| "learning_rate": 3.5364418091641373e-06, | |
| "loss": 0.0042, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.9310344827586207, | |
| "grad_norm": 0.14668087661266327, | |
| "learning_rate": 2.7977085919589254e-06, | |
| "loss": 0.0108, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.9396551724137931, | |
| "grad_norm": 0.0402313657104969, | |
| "learning_rate": 2.144350770049597e-06, | |
| "loss": 0.0029, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.9482758620689655, | |
| "grad_norm": 0.19336402416229248, | |
| "learning_rate": 1.576942205240317e-06, | |
| "loss": 0.0202, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9568965517241379, | |
| "grad_norm": 0.5075563192367554, | |
| "learning_rate": 1.0959812677835968e-06, | |
| "loss": 0.0196, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.9655172413793104, | |
| "grad_norm": 0.13074348866939545, | |
| "learning_rate": 7.018903986483083e-07, | |
| "loss": 0.0208, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.9741379310344828, | |
| "grad_norm": 0.09440784156322479, | |
| "learning_rate": 3.950157384783104e-07, | |
| "loss": 0.0137, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.9827586206896551, | |
| "grad_norm": 0.11262812465429306, | |
| "learning_rate": 1.7562682356786487e-07, | |
| "loss": 0.0164, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.9913793103448276, | |
| "grad_norm": 0.09802548587322235, | |
| "learning_rate": 4.391634912056519e-08, | |
| "loss": 0.0046, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.1202988475561142, | |
| "learning_rate": 0.0, | |
| "loss": 0.0165, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.013442743569612503, | |
| "eval_runtime": 7.6757, | |
| "eval_samples_per_second": 25.405, | |
| "eval_steps_per_second": 3.257, | |
| "step": 116 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 116, | |
| "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": 8011375527854080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |