| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.026574188490718964, | |
| "eval_steps": 42, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.314837698143793e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2370.1618, | |
| "eval_samples_per_second": 13.37, | |
| "eval_steps_per_second": 1.672, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001594451309443138, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003188902618886276, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00047833539283294134, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006377805237772552, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999588943391597e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.000797225654721569, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99743108100344e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009566707856658827, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.993424445916923e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0011161159166101966, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987570520365104e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0012755610475545104, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.979871469976196e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0014350061784988242, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.970330142972401e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.001594451309443138, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.95895006911623e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0017538964403874516, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.945735458404681e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0019133415713317654, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.930691199511775e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0020727867022760794, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.91382285798002e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.002232231833220393, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.895136674161465e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.002232231833220393, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2370.4375, | |
| "eval_samples_per_second": 13.368, | |
| "eval_steps_per_second": 1.671, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.002391676964164707, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0025511220951090208, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.852339101019574e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0027105672260533346, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.828243544427796e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0028700123569976484, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.802361805155097e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.003029457487941962, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.774703458011453e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.003188902618886276, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.745278735053343e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0033483477498305898, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.714098521798465e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.003507792880774903, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.681174353198687e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.003667238011719217, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.64651840937276e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0038266831426635307, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.610143511100354e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.003986128273607845, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.572063115079063e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.004145573404552159, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.53229130894619e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.0043050185354964726, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.490842806067095e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.004464463666440786, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.44773294009206e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.004464463666440786, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2370.6582, | |
| "eval_samples_per_second": 13.367, | |
| "eval_steps_per_second": 1.671, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.0046239087973851, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.40297765928369e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.004783353928329414, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.356593520616948e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.004942799059273728, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.308597683653975e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.0051022441902180415, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.259007904196023e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.005261689321162355, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.207842527714767e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.005421134452106669, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.155120482565521e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.005580579583050983, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.10086127298478e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.005740024713995297, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.0058994698449396105, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.987812213377424e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.006058914975883924, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.929064185241213e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.006218360106828238, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.868862620982534e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.006377805237772552, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.807229791845673e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.006537250368716866, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.744188498563641e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.0066966954996611795, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.679762062923175e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.0066966954996611795, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2369.9319, | |
| "eval_samples_per_second": 13.371, | |
| "eval_steps_per_second": 1.672, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.0068561406306054925, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.613974319136958e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.007015585761549806, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.54684960502629e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.00717503089249412, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.478412753017433e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.007334476023438434, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.408689080954998e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.007493921154382748, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.33770438273574e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.0076533662853270614, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.265484918766243e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.007812811416271376, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.192057406248028e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.00797225654721569, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.008131701678160004, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.041687328877567e-05, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.008291146809104318, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.964800392625129e-05, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.008450591940048631, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.886816644444098e-05, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.008610037070992945, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.807764934001874e-05, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.008769482201937259, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.727674506052743e-05, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.008928927332881573, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.646574989618938e-05, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.008928927332881573, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2369.2438, | |
| "eval_samples_per_second": 13.375, | |
| "eval_steps_per_second": 1.672, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.009088372463825886, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.564496387029532e-05, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.0092478175947702, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.481469062821252e-05, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.009407262725714514, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.39752373250527e-05, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.009566707856658828, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.312691451204178e-05, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.009726152987603142, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.227003602163295e-05, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.009885598118547455, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.14049188514063e-05, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.01004504324949177, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.05318830467969e-05, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.010204488380436083, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.965125158269619e-05, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.010363933511380397, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.876335024396872e-05, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.01052337864232471, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.786850750493006e-05, | |
| "loss": 0.0, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.010682823773269024, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.696705440782938e-05, | |
| "loss": 0.0, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.010842268904213338, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.605932444038229e-05, | |
| "loss": 0.0, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.011001714035157652, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.514565341239861e-05, | |
| "loss": 0.0, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.011161159166101966, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.422637933155162e-05, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.011161159166101966, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2369.0806, | |
| "eval_samples_per_second": 13.376, | |
| "eval_steps_per_second": 1.672, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.01132060429704628, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.330184227833376e-05, | |
| "loss": 0.0, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.011480049427990593, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.237238428024572e-05, | |
| "loss": 0.0, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.011639494558934907, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.143834918526527e-05, | |
| "loss": 0.0, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.011798939689879221, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0500082534642464e-05, | |
| "loss": 0.0, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.011958384820823535, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.955793143506863e-05, | |
| "loss": 0.0, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.012117829951767849, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.861224443026595e-05, | |
| "loss": 0.0, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.012277275082712162, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.766337137204579e-05, | |
| "loss": 0.0, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.012436720213656476, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6711663290882776e-05, | |
| "loss": 0.0, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.01259616534460079, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.575747226605298e-05, | |
| "loss": 0.0, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.012755610475545104, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.480115129538409e-05, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.012915055606489418, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.384305416466584e-05, | |
| "loss": 0.0, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.013074500737433731, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.288353531676873e-05, | |
| "loss": 0.0, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.013233945868378045, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.192294972051992e-05, | |
| "loss": 0.0, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.013393390999322359, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0961652739384356e-05, | |
| "loss": 0.0, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.013393390999322359, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2368.9779, | |
| "eval_samples_per_second": 13.377, | |
| "eval_steps_per_second": 1.672, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.013552836130266673, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.013712281261210985, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.903834726061565e-05, | |
| "loss": 0.0, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.013871726392155299, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.807705027948008e-05, | |
| "loss": 0.0, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.014031171523099613, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.711646468323129e-05, | |
| "loss": 0.0, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.014190616654043926, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6156945835334184e-05, | |
| "loss": 0.0, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.01435006178498824, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5198848704615914e-05, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.014509506915932554, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.424252773394704e-05, | |
| "loss": 0.0, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.014668952046876868, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.328833670911724e-05, | |
| "loss": 0.0, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.014828397177821181, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.23366286279542e-05, | |
| "loss": 0.0, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.014987842308765495, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.138775556973406e-05, | |
| "loss": 0.0, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.015147287439709809, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.04420685649314e-05, | |
| "loss": 0.0, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.015306732570654123, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9499917465357534e-05, | |
| "loss": 0.0, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.015466177701598437, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.856165081473474e-05, | |
| "loss": 0.0, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.015625622832542752, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.762761571975429e-05, | |
| "loss": 0.0, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.015625622832542752, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2367.8949, | |
| "eval_samples_per_second": 13.383, | |
| "eval_steps_per_second": 1.673, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.015785067963487064, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6698157721666246e-05, | |
| "loss": 0.0, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.01594451309443138, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5773620668448384e-05, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.016103958225375692, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.48543465876014e-05, | |
| "loss": 0.0, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.016263403356320007, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3940675559617724e-05, | |
| "loss": 0.0, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.01642284848726432, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.303294559217063e-05, | |
| "loss": 0.0, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.016582293618208635, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.213149249506997e-05, | |
| "loss": 0.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.016741738749152947, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.12366497560313e-05, | |
| "loss": 0.0, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.016901183880097263, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0348748417303823e-05, | |
| "loss": 0.0, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.017060629011041575, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9468116953203107e-05, | |
| "loss": 0.0, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.01722007414198589, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8595081148593738e-05, | |
| "loss": 0.0, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.017379519272930202, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.772996397836704e-05, | |
| "loss": 0.0, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.017538964403874518, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.687308548795825e-05, | |
| "loss": 0.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.01769840953481883, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6024762674947313e-05, | |
| "loss": 0.0, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.017857854665763145, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5185309371787513e-05, | |
| "loss": 0.0, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.017857854665763145, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2368.7091, | |
| "eval_samples_per_second": 13.378, | |
| "eval_steps_per_second": 1.673, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.018017299796707457, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.43550361297047e-05, | |
| "loss": 0.0, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.018176744927651773, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.353425010381063e-05, | |
| "loss": 0.0, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.018336190058596085, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.272325493947257e-05, | |
| "loss": 0.0, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.0184956351895404, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.192235065998126e-05, | |
| "loss": 0.0, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.018655080320484713, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1131833555559037e-05, | |
| "loss": 0.0, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.018814525451429028, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0351996073748713e-05, | |
| "loss": 0.0, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.01897397058237334, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9583126711224343e-05, | |
| "loss": 0.0, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.019133415713317656, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.019292860844261968, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.807942593751973e-05, | |
| "loss": 0.0, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.019452305975206283, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7345150812337564e-05, | |
| "loss": 0.0, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.019611751106150595, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.66229561726426e-05, | |
| "loss": 0.0, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.01977119623709491, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5913109190450032e-05, | |
| "loss": 0.0, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.019930641368039223, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5215872469825682e-05, | |
| "loss": 0.0, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.02009008649898354, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4531503949737108e-05, | |
| "loss": 0.0, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.02009008649898354, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2368.4689, | |
| "eval_samples_per_second": 13.38, | |
| "eval_steps_per_second": 1.673, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.02024953162992785, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3860256808630428e-05, | |
| "loss": 0.0, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.020408976760872166, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3202379370768252e-05, | |
| "loss": 0.0, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.020568421891816478, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2558115014363592e-05, | |
| "loss": 0.0, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.020727867022760794, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1927702081543279e-05, | |
| "loss": 0.0, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.020887312153705106, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1311373790174657e-05, | |
| "loss": 0.0, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.02104675728464942, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0709358147587884e-05, | |
| "loss": 0.0, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.021206202415593733, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0121877866225781e-05, | |
| "loss": 0.0, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.02136564754653805, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.02152509267748236, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.991387270152201e-06, | |
| "loss": 0.0, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.021684537808426677, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.448795174344804e-06, | |
| "loss": 0.0, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.02184398293937099, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.921574722852343e-06, | |
| "loss": 0.0, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.022003428070315304, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.409920958039795e-06, | |
| "loss": 0.0, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.022162873201259616, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.9140231634602485e-06, | |
| "loss": 0.0, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.022322318332203932, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.43406479383053e-06, | |
| "loss": 0.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.022322318332203932, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2368.3875, | |
| "eval_samples_per_second": 13.38, | |
| "eval_steps_per_second": 1.673, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.022481763463148244, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9702234071631e-06, | |
| "loss": 0.0, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.02264120859409256, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5226705990794155e-06, | |
| "loss": 0.0, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.02280065372503687, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.091571939329048e-06, | |
| "loss": 0.0, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.022960098855981187, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.677086910538092e-06, | |
| "loss": 0.0, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.0231195439869255, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.279368849209381e-06, | |
| "loss": 0.0, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.023278989117869815, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.898564888996476e-06, | |
| "loss": 0.0, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.023438434248814127, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.534815906272404e-06, | |
| "loss": 0.0, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.023597879379758442, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.18825646801314e-06, | |
| "loss": 0.0, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.023757324510702754, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8590147820153513e-06, | |
| "loss": 0.0, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.02391676964164707, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.547212649466568e-06, | |
| "loss": 0.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.024076214772591382, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2529654198854835e-06, | |
| "loss": 0.0, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.024235659903535697, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9763819484490355e-06, | |
| "loss": 0.0, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.02439510503448001, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7175645557220566e-06, | |
| "loss": 0.0, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.024554550165424325, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4766089898042678e-06, | |
| "loss": 0.0, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.024554550165424325, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2367.962, | |
| "eval_samples_per_second": 13.382, | |
| "eval_steps_per_second": 1.673, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.024713995296368637, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.024873440427312953, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0486332583853563e-06, | |
| "loss": 0.0, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.025032885558257265, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.617714201998084e-07, | |
| "loss": 0.0, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.02519233068920158, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.93088004882253e-07, | |
| "loss": 0.0, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.025351775820145892, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.426454159531913e-07, | |
| "loss": 0.0, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.025511220951090208, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.104993088376974e-07, | |
| "loss": 0.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.02567066608203452, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.966985702759828e-07, | |
| "loss": 0.0, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.025830111212978835, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.012853002380466e-07, | |
| "loss": 0.0, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.025989556343923147, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2429479634897267e-07, | |
| "loss": 0.0, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.026149001474867463, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.575554083078084e-08, | |
| "loss": 0.0, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.026308446605811775, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.568918996560532e-08, | |
| "loss": 0.0, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.02646789173675609, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.110566084036816e-09, | |
| "loss": 0.0, | |
| "step": 498 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 7.670791547922678e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |