| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.21976512602156445, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010988256301078224, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.499999999999999e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010988256301078224, | |
| "eval_loss": NaN, | |
| "eval_runtime": 586.4445, | |
| "eval_samples_per_second": 5.228, | |
| "eval_steps_per_second": 2.614, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021976512602156447, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003296476890323467, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2499999999999998e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0043953025204312894, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005494128150539112, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.75e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006592953780646934, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4999999999999996e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007691779410754756, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2499999999999995e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008790605040862579, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0098894306709704, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.75e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010988256301078223, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012087081931186044, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.25e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013185907561293867, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014284733191401689, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.75e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.015383558821509512, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010499999999999999, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.016482384451617333, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001125, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017581210081725158, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01868003571183298, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012749999999999998, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0197788613419408, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000135, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02087768697204862, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001425, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.021976512602156446, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.023075338232264268, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014998857713672935, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02417416386237209, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014995431202643217, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.025272989492479914, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000149897215106593, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.026371815122587735, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001498173037694868, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.027470640752695556, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001497146023568809, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.028569466382803377, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014958914215262048, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.029668292012911202, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014944096137309914, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.030767117643019024, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014927010515561776, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03186594327312685, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014907662554463532, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.032964768903234666, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001488605814759156, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03406359453334249, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014862203875857477, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.035162420163450316, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001483610700550354, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03626124579355813, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014807775485889264, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03736007142366596, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001477721794706997, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.038458897053773776, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001474444369716801, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0395577226838816, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001470946271953739, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.040656548313989425, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014672285669722765, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04175537394409724, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014632923872213652, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04285419957420507, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014591389316994876, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04395302520431289, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001454769465589431, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04505185083442071, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014501853198729012, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.046150676464528535, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014453878909250904, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04724950209463636, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014403786400893302, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04834832772474418, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014351590932319504, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.049447153354852, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014297308402774875, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05054597898495983, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001424095534724375, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.051644804615067645, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014182548931412757, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05274363024517547, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001412210694644195, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05384245587528329, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014059647803545467, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05494128150539111, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001399519052838329, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05494128150539111, | |
| "eval_loss": NaN, | |
| "eval_runtime": 638.0326, | |
| "eval_samples_per_second": 4.805, | |
| "eval_steps_per_second": 2.403, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05604010713549894, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013928754755265842, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.057138932765606755, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013860360721173193, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.05823775839571458, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001379002925959068, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.059336584025822404, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001371778179416281, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.06043540965593022, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013643640332167438, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.06153423528603805, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013567627457812106, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.06263306091614587, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013489766325354695, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0637318865462537, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013410080652050412, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.06483071217636151, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001332859471092728, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.06592953780646933, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013245333323392333, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06702836343657716, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001316032185167079, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.06812718906668498, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013073586191080457, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0692260146967928, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012985152762143778, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.07032484032690063, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012895048502539882, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.07142366595700844, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012803300858899104, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.07252249158711627, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001270993777844248, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.07362131721722409, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001261498770046874, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.07472014284733192, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012518479547691435, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.07581896847743974, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012420442717428804, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.07691779410754755, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012320907072649044, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07801661973765538, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001221990293287378, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0791154453677632, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012117461064942435, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.08021427099787103, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012013612673640363, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.08131309662797885, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011908389392193547, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.08241192225808668, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011801823272632844, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.08351074788819449, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011693946776030599, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.08460957351830231, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011584792762612703, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.08570839914841014, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011474394481749035, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.08680722477851796, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011362785561825406, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.08790605040862579, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001125, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08900487603873361, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011136072151847529, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.09010370166884142, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011021036720894179, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.09120252729894925, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010904928748046599, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.09230135292905707, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001078778360091808, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.0934001785591649, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010669636963055245, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.09449900418927272, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010550524823068502, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.09559782981938053, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010430483463669551, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.09669665544948836, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001030954945061934, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.09779548107959618, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001018775962158975, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.098894306709704, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010065151074942516, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.09999313233981183, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.941761158428674e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.10109195796991965, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.817627457812105e-05, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.10219078360002747, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.692787785420525e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.10328960923013529, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.567280168627493e-05, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.10438843486024312, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.441142838268905e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.10548726049035094, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.314414216997507e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.10658608612045876, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.187132907578987e-05, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.10768491175056658, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.059337681133192e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.1087837373806744, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.931067465324085e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.10988256301078222, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.802361332501978e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10988256301078222, | |
| "eval_loss": NaN, | |
| "eval_runtime": 637.0136, | |
| "eval_samples_per_second": 4.813, | |
| "eval_steps_per_second": 2.407, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11098138864089005, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.673258487801731e-05, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.11208021427099787, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.54379825720049e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.1131790399011057, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.414020075538605e-05, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.11427786553121351, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.2839634745074e-05, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.11537669116132133, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.153668070607437e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.11647551679142916, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.023173553080938e-05, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.11757434242153698, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.89251967182208e-05, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.11867316805164481, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.761746225268758e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.11977199368175263, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.630893048279627e-05, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.12087081931186044, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.12196964494196827, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.369106951720373e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.1230684705720761, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.238253774731244e-05, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.12416729620218392, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.10748032817792e-05, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.12526612183229174, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.976826446919059e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.12636494746239957, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.846331929392562e-05, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.1274637730925074, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.7160365254926e-05, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.12856259872261522, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.585979924461394e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.12966142435272301, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.45620174279951e-05, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.13076024998283084, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.326741512198266e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.13185907561293866, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.197638667498022e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.1329579012430465, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.068932534675913e-05, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.1340567268731543, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9406623188668055e-05, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.13515555250326214, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.812867092421013e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.13625437813336996, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.685585783002493e-05, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.1373532037634778, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.558857161731093e-05, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.1384520293935856, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4327198313725064e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.13955085502369344, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.307212214579474e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.14064968065380126, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.182372542187895e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.14174850628390906, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.058238841571326e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.14284733191401688, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.934848925057484e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1439461575441247, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.812240378410248e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.14504498317423253, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.690450549380659e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.14614380880434036, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.569516536330447e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.14724263443444818, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.449475176931499e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.148341460064556, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3303630369447554e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.14944028569466383, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.212216399081918e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.15053911132477166, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.095071251953399e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.15163793695487948, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.978963279105821e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.1527367625849873, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.863927848152472e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.1538355882150951, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.750000000000001e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.15493441384520293, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.637214438174593e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.15603323947531075, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.525605518250964e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.15713206510541858, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.415207237387297e-05, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.1582308907355264, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3060532239693994e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.15932971636563423, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.198176727367156e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.16042854199574205, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.091610607806452e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.16152736762584988, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.986387326359637e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.1626261932559577, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8825389350575624e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.16372501888606553, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.78009706712622e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.16482384451617335, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6790929273509545e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16482384451617335, | |
| "eval_loss": NaN, | |
| "eval_runtime": 585.8565, | |
| "eval_samples_per_second": 5.233, | |
| "eval_steps_per_second": 2.617, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16592267014628115, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.579557282571196e-05, | |
| "loss": 0.0, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.16702149577638897, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4815204523085654e-05, | |
| "loss": 0.0, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.1681203214064968, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.385012299531262e-05, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.16921914703660462, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2900622215575197e-05, | |
| "loss": 0.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.17031797266671245, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1966991411008938e-05, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.17141679829682027, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1049514974601175e-05, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.1725156239269281, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0148472378562215e-05, | |
| "loss": 0.0, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.17361444955703592, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.926413808919542e-05, | |
| "loss": 0.0, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.17471327518714375, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8396781483292098e-05, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.17581210081725157, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7546666766076655e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.1769109264473594, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.671405289072718e-05, | |
| "loss": 0.0, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.17800975207746722, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5899193479495857e-05, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.17910857770757502, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5102336746453053e-05, | |
| "loss": 0.0, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.18020740333768284, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4323725421878949e-05, | |
| "loss": 0.0, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.18130622896779067, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3563596678325606e-05, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.1824050545978985, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2822182058371878e-05, | |
| "loss": 0.0, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.18350388022800632, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2099707404093203e-05, | |
| "loss": 0.0, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.18460270585811414, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1396392788268052e-05, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.18570153148822197, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0712452447341582e-05, | |
| "loss": 0.0, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.1868003571183298, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0048094716167095e-05, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.18789918274843762, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.40352196454532e-06, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.18899800837854544, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.778930535580474e-06, | |
| "loss": 0.0, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.19009683400865326, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.174510685872415e-06, | |
| "loss": 0.0, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.19119565963876106, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.5904465275624884e-06, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.1922944852688689, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.026915972251254e-06, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.1933933108989767, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.484090676804926e-06, | |
| "loss": 0.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.19449213652908454, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.962135991066971e-06, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.19559096215919236, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.461210907490951e-06, | |
| "loss": 0.0, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.19668978778930019, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.981468012709877e-06, | |
| "loss": 0.0, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.197788613419408, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.523053441056876e-06, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.19888743904951584, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.086106830051236e-06, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.19998626467962366, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.670761277863485e-06, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.20108509030973148, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.277143302772342e-06, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.2021839159398393, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9053728046260825e-06, | |
| "loss": 0.0, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.2032827415699471, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.555563028319885e-06, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.20438156720005493, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.227820529300264e-06, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.20548039283016276, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9222451411073645e-06, | |
| "loss": 0.0, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.20657921846027058, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6389299449645733e-06, | |
| "loss": 0.0, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.2076780440903784, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3779612414252017e-06, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.20877686972048623, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1394185240843983e-06, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.20987569535059405, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.233744553646754e-07, | |
| "loss": 0.0, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.21097452098070188, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.298948443822228e-07, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.2120733466108097, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.590386269008512e-07, | |
| "loss": 0.0, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.21317217224091753, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.108578473795032e-07, | |
| "loss": 0.0, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.21427099787102535, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8539764311908407e-07, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.21536982350113315, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8269623051318515e-07, | |
| "loss": 0.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.21646864913124098, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.027848934069625e-07, | |
| "loss": 0.0, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.2175674747613488, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.568797356781784e-08, | |
| "loss": 0.0, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.21866630039145663, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.142286327065478e-08, | |
| "loss": 0.0, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.21976512602156445, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21976512602156445, | |
| "eval_loss": NaN, | |
| "eval_runtime": 585.7642, | |
| "eval_samples_per_second": 5.234, | |
| "eval_steps_per_second": 2.617, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 17, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.168190096566911e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |