| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01616285694659388, | |
| "eval_steps": 125, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.232571389318776e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 577.2541, | |
| "eval_samples_per_second": 45.129, | |
| "eval_steps_per_second": 22.565, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.697714167956328e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00019395428335912656, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002909314250386898, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003879085667182531, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999588943391597e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0004848857083978164, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99743108100344e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005818628500773796, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.993424445916923e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006788399917569429, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987570520365104e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0007758171334365062, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.979871469976196e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0008727942751160696, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.970330142972401e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0009697714167956328, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.95895006911623e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0010667485584751962, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.945735458404681e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0011637257001547593, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.930691199511775e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0012607028418343226, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.91382285798002e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0013576799835138859, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.895136674161465e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0014546571251934492, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0015516342668730125, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.852339101019574e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0016486114085525758, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.828243544427796e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.001745588550232139, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.802361805155097e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0018425656919117024, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.774703458011453e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0019395428335912655, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.745278735053343e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.002036519975270829, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.714098521798465e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0021334971169503923, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.681174353198687e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0022304742586299556, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.64651840937276e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0023274514003095185, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.610143511100354e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.002424428541989082, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.572063115079063e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.002521405683668645, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.53229130894619e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.0026183828253482084, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.490842806067095e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.0027153599670277717, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.44773294009206e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.002812337108707335, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.40297765928369e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.0029093142503868984, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.356593520616948e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0030062913920664617, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.308597683653975e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.003103268533746025, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.259007904196023e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.0032002456754255883, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.207842527714767e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.0032972228171051516, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.155120482565521e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.003394199958784715, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.10086127298478e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.003491177100464278, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.0035881542421438415, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.987812213377424e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.003685131383823405, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.929064185241213e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.0037821085255029677, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.868862620982534e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.003879085667182531, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.807229791845673e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.003976062808862094, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.744188498563641e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.00404071423664847, | |
| "eval_loss": NaN, | |
| "eval_runtime": 574.6926, | |
| "eval_samples_per_second": 45.33, | |
| "eval_steps_per_second": 22.666, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.004073039950541658, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.679762062923175e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.004170017092221221, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.613974319136958e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.004266994233900785, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.54684960502629e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.0043639713755803475, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.478412753017433e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.004460948517259911, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.408689080954998e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.004557925658939474, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.33770438273574e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.004654902800619037, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.265484918766243e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.004751879942298601, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.192057406248028e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.004848857083978164, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.004945834225657727, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.041687328877567e-05, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.00504281136733729, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.964800392625129e-05, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.005139788509016854, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.886816644444098e-05, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.005236765650696417, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.807764934001874e-05, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.005333742792375981, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.727674506052743e-05, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.0054307199340555435, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.646574989618938e-05, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.005527697075735107, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.564496387029532e-05, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.00562467421741467, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.481469062821252e-05, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.005721651359094234, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.39752373250527e-05, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.005818628500773797, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.312691451204178e-05, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.0059156056424533605, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.227003602163295e-05, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.006012582784132923, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.14049188514063e-05, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.006109559925812486, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.05318830467969e-05, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.00620653706749205, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.965125158269619e-05, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.006303514209171613, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.876335024396872e-05, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.006400491350851177, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.786850750493006e-05, | |
| "loss": 0.0, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.0064974684925307395, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.696705440782938e-05, | |
| "loss": 0.0, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.006594445634210303, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.605932444038229e-05, | |
| "loss": 0.0, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.006691422775889866, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.514565341239861e-05, | |
| "loss": 0.0, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.00678839991756943, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.422637933155162e-05, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.006885377059248993, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.330184227833376e-05, | |
| "loss": 0.0, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.006982354200928556, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.237238428024572e-05, | |
| "loss": 0.0, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.007079331342608119, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.143834918526527e-05, | |
| "loss": 0.0, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.007176308484287683, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0500082534642464e-05, | |
| "loss": 0.0, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.007273285625967246, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.955793143506863e-05, | |
| "loss": 0.0, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.00737026276764681, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.861224443026595e-05, | |
| "loss": 0.0, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.0074672399093263725, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.766337137204579e-05, | |
| "loss": 0.0, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.007564217051005935, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6711663290882776e-05, | |
| "loss": 0.0, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.007661194192685499, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.575747226605298e-05, | |
| "loss": 0.0, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.007758171334365062, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.480115129538409e-05, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.007855148476044625, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.384305416466584e-05, | |
| "loss": 0.0, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.007952125617724189, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.288353531676873e-05, | |
| "loss": 0.0, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.008049102759403752, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.192294972051992e-05, | |
| "loss": 0.0, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.00808142847329694, | |
| "eval_loss": NaN, | |
| "eval_runtime": 575.6933, | |
| "eval_samples_per_second": 45.252, | |
| "eval_steps_per_second": 22.627, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.008146079901083316, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.0961652739384356e-05, | |
| "loss": 0.0, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.008243057042762878, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.008340034184442442, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.903834726061565e-05, | |
| "loss": 0.0, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.008437011326122006, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.807705027948008e-05, | |
| "loss": 0.0, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.00853398846780157, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.711646468323129e-05, | |
| "loss": 0.0, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.008630965609481131, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6156945835334184e-05, | |
| "loss": 0.0, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.008727942751160695, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5198848704615914e-05, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.008824919892840259, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.424252773394704e-05, | |
| "loss": 0.0, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.008921897034519823, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.328833670911724e-05, | |
| "loss": 0.0, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.009018874176199385, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.23366286279542e-05, | |
| "loss": 0.0, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.009115851317878948, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.138775556973406e-05, | |
| "loss": 0.0, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.009212828459558512, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.04420685649314e-05, | |
| "loss": 0.0, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.009309805601238074, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9499917465357534e-05, | |
| "loss": 0.0, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.009406782742917638, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.856165081473474e-05, | |
| "loss": 0.0, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.009503759884597202, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.762761571975429e-05, | |
| "loss": 0.0, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.009600737026276765, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6698157721666246e-05, | |
| "loss": 0.0, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.009697714167956327, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5773620668448384e-05, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.009794691309635891, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.48543465876014e-05, | |
| "loss": 0.0, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.009891668451315455, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3940675559617724e-05, | |
| "loss": 0.0, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.009988645592995019, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.303294559217063e-05, | |
| "loss": 0.0, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.01008562273467458, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.213149249506997e-05, | |
| "loss": 0.0, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.010182599876354144, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.12366497560313e-05, | |
| "loss": 0.0, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.010279577018033708, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0348748417303823e-05, | |
| "loss": 0.0, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.010376554159713272, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9468116953203107e-05, | |
| "loss": 0.0, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.010473531301392834, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8595081148593738e-05, | |
| "loss": 0.0, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.010570508443072398, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.772996397836704e-05, | |
| "loss": 0.0, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.010667485584751961, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.687308548795825e-05, | |
| "loss": 0.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.010764462726431523, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6024762674947313e-05, | |
| "loss": 0.0, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.010861439868111087, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5185309371787513e-05, | |
| "loss": 0.0, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.01095841700979065, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.43550361297047e-05, | |
| "loss": 0.0, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.011055394151470214, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.353425010381063e-05, | |
| "loss": 0.0, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.011152371293149776, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.272325493947257e-05, | |
| "loss": 0.0, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.01124934843482934, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.192235065998126e-05, | |
| "loss": 0.0, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.011346325576508904, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1131833555559037e-05, | |
| "loss": 0.0, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.011443302718188468, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0351996073748713e-05, | |
| "loss": 0.0, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.01154027985986803, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9583126711224343e-05, | |
| "loss": 0.0, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.011637257001547593, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.011734234143227157, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.807942593751973e-05, | |
| "loss": 0.0, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.011831211284906721, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7345150812337564e-05, | |
| "loss": 0.0, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.011928188426586283, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.66229561726426e-05, | |
| "loss": 0.0, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.012025165568265847, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5913109190450032e-05, | |
| "loss": 0.0, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.01212214270994541, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5215872469825682e-05, | |
| "loss": 0.0, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.01212214270994541, | |
| "eval_loss": NaN, | |
| "eval_runtime": 573.9041, | |
| "eval_samples_per_second": 45.393, | |
| "eval_steps_per_second": 22.697, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.012219119851624972, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4531503949737108e-05, | |
| "loss": 0.0, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.012316096993304536, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3860256808630428e-05, | |
| "loss": 0.0, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.0124130741349841, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3202379370768252e-05, | |
| "loss": 0.0, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.012510051276663664, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2558115014363592e-05, | |
| "loss": 0.0, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.012607028418343226, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1927702081543279e-05, | |
| "loss": 0.0, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.01270400556002279, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1311373790174657e-05, | |
| "loss": 0.0, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.012800982701702353, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0709358147587884e-05, | |
| "loss": 0.0, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.012897959843381917, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0121877866225781e-05, | |
| "loss": 0.0, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.012994936985061479, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.013091914126741043, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.991387270152201e-06, | |
| "loss": 0.0, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.013188891268420606, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.448795174344804e-06, | |
| "loss": 0.0, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.01328586841010017, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.921574722852343e-06, | |
| "loss": 0.0, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.013382845551779732, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.409920958039795e-06, | |
| "loss": 0.0, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.013479822693459296, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.9140231634602485e-06, | |
| "loss": 0.0, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.01357679983513886, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.43406479383053e-06, | |
| "loss": 0.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.013673776976818422, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9702234071631e-06, | |
| "loss": 0.0, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.013770754118497985, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.5226705990794155e-06, | |
| "loss": 0.0, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.013867731260177549, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.091571939329048e-06, | |
| "loss": 0.0, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.013964708401857113, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.677086910538092e-06, | |
| "loss": 0.0, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.014061685543536675, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.279368849209381e-06, | |
| "loss": 0.0, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.014158662685216239, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.898564888996476e-06, | |
| "loss": 0.0, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.014255639826895802, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.534815906272404e-06, | |
| "loss": 0.0, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.014352616968575366, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.18825646801314e-06, | |
| "loss": 0.0, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.014449594110254928, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8590147820153513e-06, | |
| "loss": 0.0, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.014546571251934492, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.547212649466568e-06, | |
| "loss": 0.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.014643548393614056, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2529654198854835e-06, | |
| "loss": 0.0, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.01474052553529362, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9763819484490355e-06, | |
| "loss": 0.0, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.014837502676973181, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7175645557220566e-06, | |
| "loss": 0.0, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.014934479818652745, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4766089898042678e-06, | |
| "loss": 0.0, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.015031456960332309, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.01512843410201187, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0486332583853563e-06, | |
| "loss": 0.0, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.015225411243691435, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.617714201998084e-07, | |
| "loss": 0.0, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.015322388385370998, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.93088004882253e-07, | |
| "loss": 0.0, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.015419365527050562, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.426454159531913e-07, | |
| "loss": 0.0, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.015516342668730124, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.104993088376974e-07, | |
| "loss": 0.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.015613319810409688, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.966985702759828e-07, | |
| "loss": 0.0, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.01571029695208925, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.012853002380466e-07, | |
| "loss": 0.0, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.015807274093768815, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2429479634897267e-07, | |
| "loss": 0.0, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.015904251235448377, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.575554083078084e-08, | |
| "loss": 0.0, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.016001228377127943, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.568918996560532e-08, | |
| "loss": 0.0, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.016098205518807505, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.110566084036816e-09, | |
| "loss": 0.0, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.01616285694659388, | |
| "eval_loss": NaN, | |
| "eval_runtime": 660.3671, | |
| "eval_samples_per_second": 39.449, | |
| "eval_steps_per_second": 19.725, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 125, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.401809133568e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |