| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.1757789535567313, |
| "eval_steps": 42, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0023515579071134627, |
| "eval_loss": 11.93134593963623, |
| "eval_runtime": 10.5205, |
| "eval_samples_per_second": 272.23, |
| "eval_steps_per_second": 8.555, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.007054673721340388, |
| "grad_norm": 0.012463300488889217, |
| "learning_rate": 3e-05, |
| "loss": 11.9313, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.014109347442680775, |
| "grad_norm": 0.015666738152503967, |
| "learning_rate": 6e-05, |
| "loss": 11.9317, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.021164021164021163, |
| "grad_norm": 0.021637123078107834, |
| "learning_rate": 9e-05, |
| "loss": 11.9311, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.02821869488536155, |
| "grad_norm": 0.01769455522298813, |
| "learning_rate": 9.999588943391597e-05, |
| "loss": 11.9313, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.03527336860670194, |
| "grad_norm": 0.018525123596191406, |
| "learning_rate": 9.99743108100344e-05, |
| "loss": 11.9307, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.042328042328042326, |
| "grad_norm": 0.022749891504645348, |
| "learning_rate": 9.993424445916923e-05, |
| "loss": 11.9299, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.04938271604938271, |
| "grad_norm": 0.033247560262680054, |
| "learning_rate": 9.987570520365104e-05, |
| "loss": 11.9297, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.0564373897707231, |
| "grad_norm": 0.03264958783984184, |
| "learning_rate": 9.979871469976196e-05, |
| "loss": 11.9297, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.06349206349206349, |
| "grad_norm": 0.03716759756207466, |
| "learning_rate": 9.970330142972401e-05, |
| "loss": 11.9294, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.07054673721340388, |
| "grad_norm": 0.06127162277698517, |
| "learning_rate": 9.95895006911623e-05, |
| "loss": 11.9286, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.07760141093474426, |
| "grad_norm": 0.04590151831507683, |
| "learning_rate": 9.945735458404681e-05, |
| "loss": 11.9284, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.08465608465608465, |
| "grad_norm": 0.056038279086351395, |
| "learning_rate": 9.930691199511775e-05, |
| "loss": 11.9269, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.09171075837742504, |
| "grad_norm": 0.05783422291278839, |
| "learning_rate": 9.91382285798002e-05, |
| "loss": 11.927, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.09876543209876543, |
| "grad_norm": 0.053165242075920105, |
| "learning_rate": 9.895136674161465e-05, |
| "loss": 11.9254, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.09876543209876543, |
| "eval_loss": 11.925036430358887, |
| "eval_runtime": 10.6532, |
| "eval_samples_per_second": 268.841, |
| "eval_steps_per_second": 8.448, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.10582010582010581, |
| "grad_norm": 0.038137730211019516, |
| "learning_rate": 9.874639560909117e-05, |
| "loss": 11.9253, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.1128747795414462, |
| "grad_norm": 0.047474514693021774, |
| "learning_rate": 9.852339101019574e-05, |
| "loss": 11.9246, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.11992945326278659, |
| "grad_norm": 0.040923334658145905, |
| "learning_rate": 9.828243544427796e-05, |
| "loss": 11.924, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.12698412698412698, |
| "grad_norm": 0.04106362909078598, |
| "learning_rate": 9.802361805155097e-05, |
| "loss": 11.923, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.13403880070546736, |
| "grad_norm": 0.032283883541822433, |
| "learning_rate": 9.774703458011453e-05, |
| "loss": 11.9225, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.14109347442680775, |
| "grad_norm": 0.06524904817342758, |
| "learning_rate": 9.745278735053343e-05, |
| "loss": 11.9216, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.14814814814814814, |
| "grad_norm": 0.030542707070708275, |
| "learning_rate": 9.714098521798465e-05, |
| "loss": 11.9207, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.15520282186948853, |
| "grad_norm": 0.02981523610651493, |
| "learning_rate": 9.681174353198687e-05, |
| "loss": 11.9213, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.16225749559082892, |
| "grad_norm": 0.03491352126002312, |
| "learning_rate": 9.64651840937276e-05, |
| "loss": 11.921, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.1693121693121693, |
| "grad_norm": 0.029117964208126068, |
| "learning_rate": 9.610143511100354e-05, |
| "loss": 11.9203, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.1763668430335097, |
| "grad_norm": 0.03240862861275673, |
| "learning_rate": 9.572063115079063e-05, |
| "loss": 11.9196, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.18342151675485008, |
| "grad_norm": 0.022400949150323868, |
| "learning_rate": 9.53229130894619e-05, |
| "loss": 11.9196, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.19047619047619047, |
| "grad_norm": 0.022678203880786896, |
| "learning_rate": 9.490842806067095e-05, |
| "loss": 11.9205, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "grad_norm": 0.03054334782063961, |
| "learning_rate": 9.44773294009206e-05, |
| "loss": 11.9196, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.19753086419753085, |
| "eval_loss": 11.919329643249512, |
| "eval_runtime": 10.8695, |
| "eval_samples_per_second": 263.49, |
| "eval_steps_per_second": 8.28, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.20458553791887124, |
| "grad_norm": 0.02172757126390934, |
| "learning_rate": 9.40297765928369e-05, |
| "loss": 11.9193, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.21164021164021163, |
| "grad_norm": 0.023694947361946106, |
| "learning_rate": 9.356593520616948e-05, |
| "loss": 11.919, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.21869488536155202, |
| "grad_norm": 0.03806081414222717, |
| "learning_rate": 9.308597683653975e-05, |
| "loss": 11.9175, |
| "step": 93 |
| }, |
| { |
| "epoch": 0.2257495590828924, |
| "grad_norm": 0.02170073799788952, |
| "learning_rate": 9.259007904196023e-05, |
| "loss": 11.9193, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.2328042328042328, |
| "grad_norm": 0.02128906175494194, |
| "learning_rate": 9.207842527714767e-05, |
| "loss": 11.9188, |
| "step": 99 |
| }, |
| { |
| "epoch": 0.23985890652557318, |
| "grad_norm": 0.02206624485552311, |
| "learning_rate": 9.155120482565521e-05, |
| "loss": 11.9186, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.24691358024691357, |
| "grad_norm": 0.021899454295635223, |
| "learning_rate": 9.10086127298478e-05, |
| "loss": 11.918, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.25396825396825395, |
| "grad_norm": 0.030206996947526932, |
| "learning_rate": 9.045084971874738e-05, |
| "loss": 11.9182, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.26102292768959434, |
| "grad_norm": 0.02562589943408966, |
| "learning_rate": 8.987812213377424e-05, |
| "loss": 11.9188, |
| "step": 111 |
| }, |
| { |
| "epoch": 0.26807760141093473, |
| "grad_norm": 0.021965835243463516, |
| "learning_rate": 8.929064185241213e-05, |
| "loss": 11.9183, |
| "step": 114 |
| }, |
| { |
| "epoch": 0.2751322751322751, |
| "grad_norm": 0.02135823480784893, |
| "learning_rate": 8.868862620982534e-05, |
| "loss": 11.9182, |
| "step": 117 |
| }, |
| { |
| "epoch": 0.2821869488536155, |
| "grad_norm": 0.029081886634230614, |
| "learning_rate": 8.807229791845673e-05, |
| "loss": 11.9185, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.2892416225749559, |
| "grad_norm": 0.01876562461256981, |
| "learning_rate": 8.744188498563641e-05, |
| "loss": 11.9178, |
| "step": 123 |
| }, |
| { |
| "epoch": 0.2962962962962963, |
| "grad_norm": 0.026901056990027428, |
| "learning_rate": 8.679762062923175e-05, |
| "loss": 11.9171, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.2962962962962963, |
| "eval_loss": 11.917308807373047, |
| "eval_runtime": 10.6998, |
| "eval_samples_per_second": 267.668, |
| "eval_steps_per_second": 8.411, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.30335097001763667, |
| "grad_norm": 0.02258964441716671, |
| "learning_rate": 8.613974319136958e-05, |
| "loss": 11.9175, |
| "step": 129 |
| }, |
| { |
| "epoch": 0.31040564373897706, |
| "grad_norm": 0.019902532920241356, |
| "learning_rate": 8.54684960502629e-05, |
| "loss": 11.9189, |
| "step": 132 |
| }, |
| { |
| "epoch": 0.31746031746031744, |
| "grad_norm": 0.020657015964388847, |
| "learning_rate": 8.478412753017433e-05, |
| "loss": 11.9177, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.32451499118165783, |
| "grad_norm": 0.02019345760345459, |
| "learning_rate": 8.408689080954998e-05, |
| "loss": 11.9179, |
| "step": 138 |
| }, |
| { |
| "epoch": 0.3315696649029982, |
| "grad_norm": 0.020498735830187798, |
| "learning_rate": 8.33770438273574e-05, |
| "loss": 11.9175, |
| "step": 141 |
| }, |
| { |
| "epoch": 0.3386243386243386, |
| "grad_norm": 0.02337423898279667, |
| "learning_rate": 8.265484918766243e-05, |
| "loss": 11.9178, |
| "step": 144 |
| }, |
| { |
| "epoch": 0.345679012345679, |
| "grad_norm": 0.02081083133816719, |
| "learning_rate": 8.192057406248028e-05, |
| "loss": 11.9165, |
| "step": 147 |
| }, |
| { |
| "epoch": 0.3527336860670194, |
| "grad_norm": 0.01860121265053749, |
| "learning_rate": 8.117449009293668e-05, |
| "loss": 11.9177, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.35978835978835977, |
| "grad_norm": 0.02201470360159874, |
| "learning_rate": 8.041687328877567e-05, |
| "loss": 11.9165, |
| "step": 153 |
| }, |
| { |
| "epoch": 0.36684303350970016, |
| "grad_norm": 0.024001609534025192, |
| "learning_rate": 7.964800392625129e-05, |
| "loss": 11.9168, |
| "step": 156 |
| }, |
| { |
| "epoch": 0.37389770723104054, |
| "grad_norm": 0.02816389873623848, |
| "learning_rate": 7.886816644444098e-05, |
| "loss": 11.9174, |
| "step": 159 |
| }, |
| { |
| "epoch": 0.38095238095238093, |
| "grad_norm": 0.01967223547399044, |
| "learning_rate": 7.807764934001874e-05, |
| "loss": 11.9147, |
| "step": 162 |
| }, |
| { |
| "epoch": 0.3880070546737213, |
| "grad_norm": 0.033686283975839615, |
| "learning_rate": 7.727674506052743e-05, |
| "loss": 11.9176, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "grad_norm": 0.029333915561437607, |
| "learning_rate": 7.646574989618938e-05, |
| "loss": 11.9173, |
| "step": 168 |
| }, |
| { |
| "epoch": 0.3950617283950617, |
| "eval_loss": 11.916316032409668, |
| "eval_runtime": 10.8242, |
| "eval_samples_per_second": 264.592, |
| "eval_steps_per_second": 8.315, |
| "step": 168 |
| }, |
| { |
| "epoch": 0.4021164021164021, |
| "grad_norm": 0.020618749782443047, |
| "learning_rate": 7.564496387029532e-05, |
| "loss": 11.9169, |
| "step": 171 |
| }, |
| { |
| "epoch": 0.4091710758377425, |
| "grad_norm": 0.02999415621161461, |
| "learning_rate": 7.481469062821252e-05, |
| "loss": 11.9169, |
| "step": 174 |
| }, |
| { |
| "epoch": 0.41622574955908287, |
| "grad_norm": 0.01824590004980564, |
| "learning_rate": 7.39752373250527e-05, |
| "loss": 11.9167, |
| "step": 177 |
| }, |
| { |
| "epoch": 0.42328042328042326, |
| "grad_norm": 0.05701108276844025, |
| "learning_rate": 7.312691451204178e-05, |
| "loss": 11.9158, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.43033509700176364, |
| "grad_norm": 0.022198380902409554, |
| "learning_rate": 7.227003602163295e-05, |
| "loss": 11.9165, |
| "step": 183 |
| }, |
| { |
| "epoch": 0.43738977072310403, |
| "grad_norm": 0.022028392180800438, |
| "learning_rate": 7.14049188514063e-05, |
| "loss": 11.9166, |
| "step": 186 |
| }, |
| { |
| "epoch": 0.4444444444444444, |
| "grad_norm": 0.03448006883263588, |
| "learning_rate": 7.05318830467969e-05, |
| "loss": 11.9165, |
| "step": 189 |
| }, |
| { |
| "epoch": 0.4514991181657848, |
| "grad_norm": 0.023939242586493492, |
| "learning_rate": 6.965125158269619e-05, |
| "loss": 11.9164, |
| "step": 192 |
| }, |
| { |
| "epoch": 0.4585537918871252, |
| "grad_norm": 0.01913815177977085, |
| "learning_rate": 6.876335024396872e-05, |
| "loss": 11.9166, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.4656084656084656, |
| "grad_norm": 0.02663358673453331, |
| "learning_rate": 6.786850750493006e-05, |
| "loss": 11.917, |
| "step": 198 |
| }, |
| { |
| "epoch": 0.47266313932980597, |
| "grad_norm": 0.020899388939142227, |
| "learning_rate": 6.696705440782938e-05, |
| "loss": 11.9154, |
| "step": 201 |
| }, |
| { |
| "epoch": 0.47971781305114636, |
| "grad_norm": 0.023673586547374725, |
| "learning_rate": 6.605932444038229e-05, |
| "loss": 11.9157, |
| "step": 204 |
| }, |
| { |
| "epoch": 0.48677248677248675, |
| "grad_norm": 0.025094488635659218, |
| "learning_rate": 6.514565341239861e-05, |
| "loss": 11.9159, |
| "step": 207 |
| }, |
| { |
| "epoch": 0.49382716049382713, |
| "grad_norm": 0.02767755836248398, |
| "learning_rate": 6.422637933155162e-05, |
| "loss": 11.9158, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.49382716049382713, |
| "eval_loss": 11.915718078613281, |
| "eval_runtime": 10.5682, |
| "eval_samples_per_second": 271.003, |
| "eval_steps_per_second": 8.516, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.5008818342151675, |
| "grad_norm": 0.02221379242837429, |
| "learning_rate": 6.330184227833376e-05, |
| "loss": 11.9166, |
| "step": 213 |
| }, |
| { |
| "epoch": 0.5079365079365079, |
| "grad_norm": 0.021963153034448624, |
| "learning_rate": 6.237238428024572e-05, |
| "loss": 11.9161, |
| "step": 216 |
| }, |
| { |
| "epoch": 0.5149911816578483, |
| "grad_norm": 0.026923993602395058, |
| "learning_rate": 6.143834918526527e-05, |
| "loss": 11.9146, |
| "step": 219 |
| }, |
| { |
| "epoch": 0.5220458553791887, |
| "grad_norm": 0.035227347165346146, |
| "learning_rate": 6.0500082534642464e-05, |
| "loss": 11.9154, |
| "step": 222 |
| }, |
| { |
| "epoch": 0.5291005291005291, |
| "grad_norm": 0.021038008853793144, |
| "learning_rate": 5.955793143506863e-05, |
| "loss": 11.9158, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.5361552028218695, |
| "grad_norm": 0.01937274821102619, |
| "learning_rate": 5.861224443026595e-05, |
| "loss": 11.9162, |
| "step": 228 |
| }, |
| { |
| "epoch": 0.5432098765432098, |
| "grad_norm": 0.019016142934560776, |
| "learning_rate": 5.766337137204579e-05, |
| "loss": 11.9163, |
| "step": 231 |
| }, |
| { |
| "epoch": 0.5502645502645502, |
| "grad_norm": 0.027969468384981155, |
| "learning_rate": 5.6711663290882776e-05, |
| "loss": 11.9162, |
| "step": 234 |
| }, |
| { |
| "epoch": 0.5573192239858906, |
| "grad_norm": 0.017542190849781036, |
| "learning_rate": 5.575747226605298e-05, |
| "loss": 11.917, |
| "step": 237 |
| }, |
| { |
| "epoch": 0.564373897707231, |
| "grad_norm": 0.023203639313578606, |
| "learning_rate": 5.480115129538409e-05, |
| "loss": 11.9157, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 0.014958036132156849, |
| "learning_rate": 5.384305416466584e-05, |
| "loss": 11.9154, |
| "step": 243 |
| }, |
| { |
| "epoch": 0.5784832451499118, |
| "grad_norm": 0.027328725904226303, |
| "learning_rate": 5.288353531676873e-05, |
| "loss": 11.9163, |
| "step": 246 |
| }, |
| { |
| "epoch": 0.5855379188712522, |
| "grad_norm": 0.03369058296084404, |
| "learning_rate": 5.192294972051992e-05, |
| "loss": 11.9157, |
| "step": 249 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "grad_norm": 0.019253922626376152, |
| "learning_rate": 5.0961652739384356e-05, |
| "loss": 11.9147, |
| "step": 252 |
| }, |
| { |
| "epoch": 0.5925925925925926, |
| "eval_loss": 11.915318489074707, |
| "eval_runtime": 10.3985, |
| "eval_samples_per_second": 275.425, |
| "eval_steps_per_second": 8.655, |
| "step": 252 |
| }, |
| { |
| "epoch": 0.599647266313933, |
| "grad_norm": 0.024502824991941452, |
| "learning_rate": 5e-05, |
| "loss": 11.9151, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.6067019400352733, |
| "grad_norm": 0.03233085200190544, |
| "learning_rate": 4.903834726061565e-05, |
| "loss": 11.9151, |
| "step": 258 |
| }, |
| { |
| "epoch": 0.6137566137566137, |
| "grad_norm": 0.02394239790737629, |
| "learning_rate": 4.807705027948008e-05, |
| "loss": 11.915, |
| "step": 261 |
| }, |
| { |
| "epoch": 0.6208112874779541, |
| "grad_norm": 0.01676931232213974, |
| "learning_rate": 4.711646468323129e-05, |
| "loss": 11.9164, |
| "step": 264 |
| }, |
| { |
| "epoch": 0.6278659611992945, |
| "grad_norm": 0.02555139549076557, |
| "learning_rate": 4.6156945835334184e-05, |
| "loss": 11.9157, |
| "step": 267 |
| }, |
| { |
| "epoch": 0.6349206349206349, |
| "grad_norm": 0.02273687720298767, |
| "learning_rate": 4.5198848704615914e-05, |
| "loss": 11.9159, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.6419753086419753, |
| "grad_norm": 0.0266796313226223, |
| "learning_rate": 4.424252773394704e-05, |
| "loss": 11.9163, |
| "step": 273 |
| }, |
| { |
| "epoch": 0.6490299823633157, |
| "grad_norm": 0.025090264156460762, |
| "learning_rate": 4.328833670911724e-05, |
| "loss": 11.9164, |
| "step": 276 |
| }, |
| { |
| "epoch": 0.656084656084656, |
| "grad_norm": 0.02523481287062168, |
| "learning_rate": 4.23366286279542e-05, |
| "loss": 11.9157, |
| "step": 279 |
| }, |
| { |
| "epoch": 0.6631393298059964, |
| "grad_norm": 0.021461475640535355, |
| "learning_rate": 4.138775556973406e-05, |
| "loss": 11.9147, |
| "step": 282 |
| }, |
| { |
| "epoch": 0.6701940035273368, |
| "grad_norm": 0.023472610861063004, |
| "learning_rate": 4.04420685649314e-05, |
| "loss": 11.9161, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.6772486772486772, |
| "grad_norm": 0.024858828634023666, |
| "learning_rate": 3.9499917465357534e-05, |
| "loss": 11.9152, |
| "step": 288 |
| }, |
| { |
| "epoch": 0.6843033509700176, |
| "grad_norm": 0.020553085952997208, |
| "learning_rate": 3.856165081473474e-05, |
| "loss": 11.9139, |
| "step": 291 |
| }, |
| { |
| "epoch": 0.691358024691358, |
| "grad_norm": 0.02018040418624878, |
| "learning_rate": 3.762761571975429e-05, |
| "loss": 11.9156, |
| "step": 294 |
| }, |
| { |
| "epoch": 0.691358024691358, |
| "eval_loss": 11.915068626403809, |
| "eval_runtime": 10.6749, |
| "eval_samples_per_second": 268.292, |
| "eval_steps_per_second": 8.431, |
| "step": 294 |
| }, |
| { |
| "epoch": 0.6984126984126984, |
| "grad_norm": 0.01783376932144165, |
| "learning_rate": 3.6698157721666246e-05, |
| "loss": 11.9134, |
| "step": 297 |
| }, |
| { |
| "epoch": 0.7054673721340388, |
| "grad_norm": 0.028524892404675484, |
| "learning_rate": 3.5773620668448384e-05, |
| "loss": 11.9158, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.7125220458553791, |
| "grad_norm": 0.02065563015639782, |
| "learning_rate": 3.48543465876014e-05, |
| "loss": 11.9146, |
| "step": 303 |
| }, |
| { |
| "epoch": 0.7195767195767195, |
| "grad_norm": 0.045134805142879486, |
| "learning_rate": 3.3940675559617724e-05, |
| "loss": 11.9159, |
| "step": 306 |
| }, |
| { |
| "epoch": 0.7266313932980599, |
| "grad_norm": 0.023695290088653564, |
| "learning_rate": 3.303294559217063e-05, |
| "loss": 11.9153, |
| "step": 309 |
| }, |
| { |
| "epoch": 0.7336860670194003, |
| "grad_norm": 0.01704533025622368, |
| "learning_rate": 3.213149249506997e-05, |
| "loss": 11.915, |
| "step": 312 |
| }, |
| { |
| "epoch": 0.7407407407407407, |
| "grad_norm": 0.02306770719587803, |
| "learning_rate": 3.12366497560313e-05, |
| "loss": 11.9155, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.7477954144620811, |
| "grad_norm": 0.023183325305581093, |
| "learning_rate": 3.0348748417303823e-05, |
| "loss": 11.9152, |
| "step": 318 |
| }, |
| { |
| "epoch": 0.7548500881834215, |
| "grad_norm": 0.01855415478348732, |
| "learning_rate": 2.9468116953203107e-05, |
| "loss": 11.9163, |
| "step": 321 |
| }, |
| { |
| "epoch": 0.7619047619047619, |
| "grad_norm": 0.02062196470797062, |
| "learning_rate": 2.8595081148593738e-05, |
| "loss": 11.9154, |
| "step": 324 |
| }, |
| { |
| "epoch": 0.7689594356261023, |
| "grad_norm": 0.025098076090216637, |
| "learning_rate": 2.772996397836704e-05, |
| "loss": 11.9162, |
| "step": 327 |
| }, |
| { |
| "epoch": 0.7760141093474426, |
| "grad_norm": 0.018340418115258217, |
| "learning_rate": 2.687308548795825e-05, |
| "loss": 11.9156, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.783068783068783, |
| "grad_norm": 0.02159620076417923, |
| "learning_rate": 2.6024762674947313e-05, |
| "loss": 11.9144, |
| "step": 333 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "grad_norm": 0.02330397628247738, |
| "learning_rate": 2.5185309371787513e-05, |
| "loss": 11.9156, |
| "step": 336 |
| }, |
| { |
| "epoch": 0.7901234567901234, |
| "eval_loss": 11.914894104003906, |
| "eval_runtime": 10.4255, |
| "eval_samples_per_second": 274.71, |
| "eval_steps_per_second": 8.633, |
| "step": 336 |
| }, |
| { |
| "epoch": 0.7971781305114638, |
| "grad_norm": 0.023469174280762672, |
| "learning_rate": 2.43550361297047e-05, |
| "loss": 11.9143, |
| "step": 339 |
| }, |
| { |
| "epoch": 0.8042328042328042, |
| "grad_norm": 0.01915036514401436, |
| "learning_rate": 2.353425010381063e-05, |
| "loss": 11.917, |
| "step": 342 |
| }, |
| { |
| "epoch": 0.8112874779541446, |
| "grad_norm": 0.021919777616858482, |
| "learning_rate": 2.272325493947257e-05, |
| "loss": 11.9137, |
| "step": 345 |
| }, |
| { |
| "epoch": 0.818342151675485, |
| "grad_norm": 0.03252611309289932, |
| "learning_rate": 2.192235065998126e-05, |
| "loss": 11.9149, |
| "step": 348 |
| }, |
| { |
| "epoch": 0.8253968253968254, |
| "grad_norm": 0.021312009543180466, |
| "learning_rate": 2.1131833555559037e-05, |
| "loss": 11.9156, |
| "step": 351 |
| }, |
| { |
| "epoch": 0.8324514991181657, |
| "grad_norm": 0.02721288986504078, |
| "learning_rate": 2.0351996073748713e-05, |
| "loss": 11.9151, |
| "step": 354 |
| }, |
| { |
| "epoch": 0.8395061728395061, |
| "grad_norm": 0.019871938973665237, |
| "learning_rate": 1.9583126711224343e-05, |
| "loss": 11.9153, |
| "step": 357 |
| }, |
| { |
| "epoch": 0.8465608465608465, |
| "grad_norm": 0.02446158602833748, |
| "learning_rate": 1.8825509907063327e-05, |
| "loss": 11.9161, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.8536155202821869, |
| "grad_norm": 0.028117047622799873, |
| "learning_rate": 1.807942593751973e-05, |
| "loss": 11.9168, |
| "step": 363 |
| }, |
| { |
| "epoch": 0.8606701940035273, |
| "grad_norm": 0.02583438903093338, |
| "learning_rate": 1.7345150812337564e-05, |
| "loss": 11.9152, |
| "step": 366 |
| }, |
| { |
| "epoch": 0.8677248677248677, |
| "grad_norm": 0.026459960266947746, |
| "learning_rate": 1.66229561726426e-05, |
| "loss": 11.9158, |
| "step": 369 |
| }, |
| { |
| "epoch": 0.8747795414462081, |
| "grad_norm": 0.01762359030544758, |
| "learning_rate": 1.5913109190450032e-05, |
| "loss": 11.9162, |
| "step": 372 |
| }, |
| { |
| "epoch": 0.8818342151675485, |
| "grad_norm": 0.02677866630256176, |
| "learning_rate": 1.5215872469825682e-05, |
| "loss": 11.9157, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 0.03301187977194786, |
| "learning_rate": 1.4531503949737108e-05, |
| "loss": 11.9147, |
| "step": 378 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "eval_loss": 11.914801597595215, |
| "eval_runtime": 10.6272, |
| "eval_samples_per_second": 269.497, |
| "eval_steps_per_second": 8.469, |
| "step": 378 |
| }, |
| { |
| "epoch": 0.8959435626102292, |
| "grad_norm": 0.019808808341622353, |
| "learning_rate": 1.3860256808630428e-05, |
| "loss": 11.916, |
| "step": 381 |
| }, |
| { |
| "epoch": 0.9029982363315696, |
| "grad_norm": 0.023428916931152344, |
| "learning_rate": 1.3202379370768252e-05, |
| "loss": 11.916, |
| "step": 384 |
| }, |
| { |
| "epoch": 0.91005291005291, |
| "grad_norm": 0.018417634069919586, |
| "learning_rate": 1.2558115014363592e-05, |
| "loss": 11.9163, |
| "step": 387 |
| }, |
| { |
| "epoch": 0.9171075837742504, |
| "grad_norm": 0.020826270803809166, |
| "learning_rate": 1.1927702081543279e-05, |
| "loss": 11.9157, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.9241622574955908, |
| "grad_norm": 0.02966841123998165, |
| "learning_rate": 1.1311373790174657e-05, |
| "loss": 11.9141, |
| "step": 393 |
| }, |
| { |
| "epoch": 0.9312169312169312, |
| "grad_norm": 0.018212970346212387, |
| "learning_rate": 1.0709358147587884e-05, |
| "loss": 11.9149, |
| "step": 396 |
| }, |
| { |
| "epoch": 0.9382716049382716, |
| "grad_norm": 0.022182345390319824, |
| "learning_rate": 1.0121877866225781e-05, |
| "loss": 11.9147, |
| "step": 399 |
| }, |
| { |
| "epoch": 0.9453262786596119, |
| "grad_norm": 0.0208954568952322, |
| "learning_rate": 9.549150281252633e-06, |
| "loss": 11.9151, |
| "step": 402 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 0.022049158811569214, |
| "learning_rate": 8.991387270152201e-06, |
| "loss": 11.9143, |
| "step": 405 |
| }, |
| { |
| "epoch": 0.9594356261022927, |
| "grad_norm": 0.024066656827926636, |
| "learning_rate": 8.448795174344804e-06, |
| "loss": 11.9147, |
| "step": 408 |
| }, |
| { |
| "epoch": 0.9664902998236331, |
| "grad_norm": 0.0210318211466074, |
| "learning_rate": 7.921574722852343e-06, |
| "loss": 11.9155, |
| "step": 411 |
| }, |
| { |
| "epoch": 0.9735449735449735, |
| "grad_norm": 0.028868673369288445, |
| "learning_rate": 7.409920958039795e-06, |
| "loss": 11.9127, |
| "step": 414 |
| }, |
| { |
| "epoch": 0.9805996472663139, |
| "grad_norm": 0.023974774405360222, |
| "learning_rate": 6.9140231634602485e-06, |
| "loss": 11.9156, |
| "step": 417 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "grad_norm": 0.028788629919290543, |
| "learning_rate": 6.43406479383053e-06, |
| "loss": 11.9142, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.9876543209876543, |
| "eval_loss": 11.914738655090332, |
| "eval_runtime": 10.0919, |
| "eval_samples_per_second": 283.793, |
| "eval_steps_per_second": 8.918, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.9947089947089947, |
| "grad_norm": 0.023696357384324074, |
| "learning_rate": 5.9702234071631e-06, |
| "loss": 11.9155, |
| "step": 423 |
| }, |
| { |
| "epoch": 1.001763668430335, |
| "grad_norm": 0.03524714708328247, |
| "learning_rate": 5.5226705990794155e-06, |
| "loss": 14.6697, |
| "step": 426 |
| }, |
| { |
| "epoch": 1.0088183421516754, |
| "grad_norm": 0.019016897305846214, |
| "learning_rate": 5.091571939329048e-06, |
| "loss": 12.1316, |
| "step": 429 |
| }, |
| { |
| "epoch": 1.0158730158730158, |
| "grad_norm": 0.021377887576818466, |
| "learning_rate": 4.677086910538092e-06, |
| "loss": 12.2558, |
| "step": 432 |
| }, |
| { |
| "epoch": 1.0229276895943562, |
| "grad_norm": 0.02245590090751648, |
| "learning_rate": 4.279368849209381e-06, |
| "loss": 11.7679, |
| "step": 435 |
| }, |
| { |
| "epoch": 1.0299823633156966, |
| "grad_norm": 0.016183845698833466, |
| "learning_rate": 3.898564888996476e-06, |
| "loss": 11.9971, |
| "step": 438 |
| }, |
| { |
| "epoch": 1.037037037037037, |
| "grad_norm": 0.017965037375688553, |
| "learning_rate": 3.534815906272404e-06, |
| "loss": 11.6156, |
| "step": 441 |
| }, |
| { |
| "epoch": 1.0440917107583774, |
| "grad_norm": 0.020000630989670753, |
| "learning_rate": 3.18825646801314e-06, |
| "loss": 12.1001, |
| "step": 444 |
| }, |
| { |
| "epoch": 1.0511463844797178, |
| "grad_norm": 0.021238798275589943, |
| "learning_rate": 2.8590147820153513e-06, |
| "loss": 11.8095, |
| "step": 447 |
| }, |
| { |
| "epoch": 1.0582010582010581, |
| "grad_norm": 0.025096235796809196, |
| "learning_rate": 2.547212649466568e-06, |
| "loss": 11.8153, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.0652557319223985, |
| "grad_norm": 0.02049741894006729, |
| "learning_rate": 2.2529654198854835e-06, |
| "loss": 11.9978, |
| "step": 453 |
| }, |
| { |
| "epoch": 1.072310405643739, |
| "grad_norm": 0.025018183514475822, |
| "learning_rate": 1.9763819484490355e-06, |
| "loss": 11.9496, |
| "step": 456 |
| }, |
| { |
| "epoch": 1.0793650793650793, |
| "grad_norm": 0.021498849615454674, |
| "learning_rate": 1.7175645557220566e-06, |
| "loss": 11.7952, |
| "step": 459 |
| }, |
| { |
| "epoch": 1.0864197530864197, |
| "grad_norm": 0.02332150749862194, |
| "learning_rate": 1.4766089898042678e-06, |
| "loss": 11.7297, |
| "step": 462 |
| }, |
| { |
| "epoch": 1.0864197530864197, |
| "eval_loss": 11.914722442626953, |
| "eval_runtime": 10.3803, |
| "eval_samples_per_second": 275.908, |
| "eval_steps_per_second": 8.67, |
| "step": 462 |
| }, |
| { |
| "epoch": 1.09347442680776, |
| "grad_norm": 0.028014004230499268, |
| "learning_rate": 1.2536043909088191e-06, |
| "loss": 12.2078, |
| "step": 465 |
| }, |
| { |
| "epoch": 1.1005291005291005, |
| "grad_norm": 0.019710175693035126, |
| "learning_rate": 1.0486332583853563e-06, |
| "loss": 11.932, |
| "step": 468 |
| }, |
| { |
| "epoch": 1.1075837742504409, |
| "grad_norm": 0.0251897145062685, |
| "learning_rate": 8.617714201998084e-07, |
| "loss": 11.9246, |
| "step": 471 |
| }, |
| { |
| "epoch": 1.1146384479717812, |
| "grad_norm": 0.020719952881336212, |
| "learning_rate": 6.93088004882253e-07, |
| "loss": 11.9967, |
| "step": 474 |
| }, |
| { |
| "epoch": 1.1216931216931216, |
| "grad_norm": 0.01866576448082924, |
| "learning_rate": 5.426454159531913e-07, |
| "loss": 11.7563, |
| "step": 477 |
| }, |
| { |
| "epoch": 1.128747795414462, |
| "grad_norm": 0.029010610654950142, |
| "learning_rate": 4.104993088376974e-07, |
| "loss": 11.9562, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.1358024691358024, |
| "grad_norm": 0.020120302215218544, |
| "learning_rate": 2.966985702759828e-07, |
| "loss": 12.0342, |
| "step": 483 |
| }, |
| { |
| "epoch": 1.1428571428571428, |
| "grad_norm": 0.02001938596367836, |
| "learning_rate": 2.012853002380466e-07, |
| "loss": 11.7064, |
| "step": 486 |
| }, |
| { |
| "epoch": 1.1499118165784832, |
| "grad_norm": 0.021438777446746826, |
| "learning_rate": 1.2429479634897267e-07, |
| "loss": 11.9928, |
| "step": 489 |
| }, |
| { |
| "epoch": 1.1569664902998236, |
| "grad_norm": 0.016329078003764153, |
| "learning_rate": 6.575554083078084e-08, |
| "loss": 11.9815, |
| "step": 492 |
| }, |
| { |
| "epoch": 1.164021164021164, |
| "grad_norm": 0.05567369982600212, |
| "learning_rate": 2.568918996560532e-08, |
| "loss": 11.9687, |
| "step": 495 |
| }, |
| { |
| "epoch": 1.1710758377425043, |
| "grad_norm": 0.026132524013519287, |
| "learning_rate": 4.110566084036816e-09, |
| "loss": 11.8083, |
| "step": 498 |
| } |
| ], |
| "logging_steps": 3, |
| "max_steps": 500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 42, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 13720076943360.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
