| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.20783550986385108, | |
| "eval_steps": 34, | |
| "global_step": 374, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005557099194220616, | |
| "eval_loss": 2.150275230407715, | |
| "eval_runtime": 385.5335, | |
| "eval_samples_per_second": 7.862, | |
| "eval_steps_per_second": 0.983, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016671297582661851, | |
| "grad_norm": 0.9782189726829529, | |
| "learning_rate": 1.5e-05, | |
| "loss": 8.4821, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0033342595165323703, | |
| "grad_norm": 9.340497970581055, | |
| "learning_rate": 3e-05, | |
| "loss": 8.0841, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005001389274798555, | |
| "grad_norm": 1.2668017148971558, | |
| "learning_rate": 4.5e-05, | |
| "loss": 9.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0066685190330647405, | |
| "grad_norm": 1.2630752325057983, | |
| "learning_rate": 4.999675562428437e-05, | |
| "loss": 8.5273, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008335648791330925, | |
| "grad_norm": 1.4245824813842773, | |
| "learning_rate": 4.9979724954289244e-05, | |
| "loss": 8.1841, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01000277854959711, | |
| "grad_norm": 1.4201760292053223, | |
| "learning_rate": 4.994810682835951e-05, | |
| "loss": 7.569, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011669908307863295, | |
| "grad_norm": 1.8734160661697388, | |
| "learning_rate": 4.990191971059033e-05, | |
| "loss": 7.0022, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013337038066129481, | |
| "grad_norm": 1.1166455745697021, | |
| "learning_rate": 4.984119057295783e-05, | |
| "loss": 6.704, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.015004167824395665, | |
| "grad_norm": 1.3420771360397339, | |
| "learning_rate": 4.976595487956823e-05, | |
| "loss": 7.354, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01667129758266185, | |
| "grad_norm": 1.4245537519454956, | |
| "learning_rate": 4.967625656594782e-05, | |
| "loss": 6.7949, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.018338427340928037, | |
| "grad_norm": 1.3899712562561035, | |
| "learning_rate": 4.957214801338581e-05, | |
| "loss": 6.8879, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.018894137260350097, | |
| "eval_loss": 1.6003342866897583, | |
| "eval_runtime": 387.5811, | |
| "eval_samples_per_second": 7.82, | |
| "eval_steps_per_second": 0.978, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02000555709919422, | |
| "grad_norm": 1.2631561756134033, | |
| "learning_rate": 4.9453690018345144e-05, | |
| "loss": 6.9872, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.021672686857460405, | |
| "grad_norm": 1.1402790546417236, | |
| "learning_rate": 4.932095175695911e-05, | |
| "loss": 6.2949, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02333981661572659, | |
| "grad_norm": 1.0827226638793945, | |
| "learning_rate": 4.917401074463441e-05, | |
| "loss": 6.049, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.025006946373992776, | |
| "grad_norm": 1.1316773891448975, | |
| "learning_rate": 4.901295279078431e-05, | |
| "loss": 6.1119, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.026674076132258962, | |
| "grad_norm": 1.0732563734054565, | |
| "learning_rate": 4.883787194871841e-05, | |
| "loss": 5.899, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.028341205890525144, | |
| "grad_norm": 1.0603082180023193, | |
| "learning_rate": 4.864887046071813e-05, | |
| "loss": 5.7208, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.03000833564879133, | |
| "grad_norm": 1.1684924364089966, | |
| "learning_rate": 4.8446058698330115e-05, | |
| "loss": 6.4161, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.03167546540705751, | |
| "grad_norm": 1.147234320640564, | |
| "learning_rate": 4.822955509791233e-05, | |
| "loss": 6.0586, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.0333425951653237, | |
| "grad_norm": 1.4725079536437988, | |
| "learning_rate": 4.799948609147061e-05, | |
| "loss": 6.2541, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.035009724923589884, | |
| "grad_norm": 1.3403408527374268, | |
| "learning_rate": 4.7755986032825864e-05, | |
| "loss": 6.0201, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.03667685468185607, | |
| "grad_norm": 1.272765040397644, | |
| "learning_rate": 4.74991971191553e-05, | |
| "loss": 5.6225, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.037788274520700195, | |
| "eval_loss": 1.4521716833114624, | |
| "eval_runtime": 387.3586, | |
| "eval_samples_per_second": 7.825, | |
| "eval_steps_per_second": 0.978, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.038343984440122256, | |
| "grad_norm": 1.3769108057022095, | |
| "learning_rate": 4.7229269307953235e-05, | |
| "loss": 5.515, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.04001111419838844, | |
| "grad_norm": 1.1973274946212769, | |
| "learning_rate": 4.694636022946012e-05, | |
| "loss": 5.7673, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.04167824395665463, | |
| "grad_norm": 1.3785252571105957, | |
| "learning_rate": 4.665063509461097e-05, | |
| "loss": 5.945, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.04334537371492081, | |
| "grad_norm": 1.3699363470077515, | |
| "learning_rate": 4.6342266598556814e-05, | |
| "loss": 5.5223, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.045012503473187, | |
| "grad_norm": 1.2516443729400635, | |
| "learning_rate": 4.6021434819815555e-05, | |
| "loss": 5.6879, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.04667963323145318, | |
| "grad_norm": 1.6110479831695557, | |
| "learning_rate": 4.568832711511125e-05, | |
| "loss": 5.6658, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.048346762989719363, | |
| "grad_norm": 1.2466659545898438, | |
| "learning_rate": 4.534313800996299e-05, | |
| "loss": 5.6652, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.05001389274798555, | |
| "grad_norm": 1.5405720472335815, | |
| "learning_rate": 4.498606908508754e-05, | |
| "loss": 5.4541, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.051681022506251735, | |
| "grad_norm": 1.4913195371627808, | |
| "learning_rate": 4.46173288586818e-05, | |
| "loss": 6.3391, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.053348152264517924, | |
| "grad_norm": 1.4445130825042725, | |
| "learning_rate": 4.4237132664654154e-05, | |
| "loss": 5.5362, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.05501528202278411, | |
| "grad_norm": 1.4353359937667847, | |
| "learning_rate": 4.384570252687542e-05, | |
| "loss": 5.6292, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.05668241178105029, | |
| "grad_norm": 1.515329122543335, | |
| "learning_rate": 4.344326702952326e-05, | |
| "loss": 5.9767, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.05668241178105029, | |
| "eval_loss": 1.3901065587997437, | |
| "eval_runtime": 387.1962, | |
| "eval_samples_per_second": 7.828, | |
| "eval_steps_per_second": 0.979, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.05834954153931648, | |
| "grad_norm": 1.3371084928512573, | |
| "learning_rate": 4.303006118359537e-05, | |
| "loss": 5.0829, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.06001667129758266, | |
| "grad_norm": 1.3986601829528809, | |
| "learning_rate": 4.260632628966974e-05, | |
| "loss": 4.9783, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.06168380105584885, | |
| "grad_norm": 1.6927534341812134, | |
| "learning_rate": 4.217230979699188e-05, | |
| "loss": 5.5207, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.06335093081411503, | |
| "grad_norm": 1.4875972270965576, | |
| "learning_rate": 4.172826515897146e-05, | |
| "loss": 4.9577, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.06501806057238121, | |
| "grad_norm": 1.5819252729415894, | |
| "learning_rate": 4.12744516851726e-05, | |
| "loss": 5.5329, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.0666851903306474, | |
| "grad_norm": 1.7034679651260376, | |
| "learning_rate": 4.0811134389884433e-05, | |
| "loss": 5.8642, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06835232008891359, | |
| "grad_norm": 1.4892022609710693, | |
| "learning_rate": 4.0338583837360225e-05, | |
| "loss": 4.9988, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.07001944984717977, | |
| "grad_norm": 1.8653110265731812, | |
| "learning_rate": 3.985707598381544e-05, | |
| "loss": 5.5333, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.07168657960544596, | |
| "grad_norm": 1.6267685890197754, | |
| "learning_rate": 3.9366892016277096e-05, | |
| "loss": 5.5853, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.07335370936371215, | |
| "grad_norm": 1.710310935974121, | |
| "learning_rate": 3.886831818837847e-05, | |
| "loss": 5.5769, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.07502083912197832, | |
| "grad_norm": 2.016270160675049, | |
| "learning_rate": 3.8361645653195026e-05, | |
| "loss": 5.5546, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.07557654904140039, | |
| "eval_loss": 1.3533298969268799, | |
| "eval_runtime": 387.1489, | |
| "eval_samples_per_second": 7.829, | |
| "eval_steps_per_second": 0.979, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.07668796888024451, | |
| "grad_norm": 2.021454095840454, | |
| "learning_rate": 3.784717029321922e-05, | |
| "loss": 5.2784, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.0783550986385107, | |
| "grad_norm": 1.5546106100082397, | |
| "learning_rate": 3.732519254757344e-05, | |
| "loss": 5.21, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.08002222839677688, | |
| "grad_norm": 1.662156343460083, | |
| "learning_rate": 3.679601723656205e-05, | |
| "loss": 5.3778, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.08168935815504307, | |
| "grad_norm": 1.6201971769332886, | |
| "learning_rate": 3.625995338366492e-05, | |
| "loss": 5.4251, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.08335648791330925, | |
| "grad_norm": 1.6661242246627808, | |
| "learning_rate": 3.5717314035076355e-05, | |
| "loss": 5.292, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.08502361767157544, | |
| "grad_norm": 1.595383644104004, | |
| "learning_rate": 3.516841607689501e-05, | |
| "loss": 5.128, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.08669074742984162, | |
| "grad_norm": 1.7640243768692017, | |
| "learning_rate": 3.461358005007128e-05, | |
| "loss": 5.2638, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.08835787718810781, | |
| "grad_norm": 2.1148338317871094, | |
| "learning_rate": 3.405312996322042e-05, | |
| "loss": 5.1089, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.090025006946374, | |
| "grad_norm": 1.9622715711593628, | |
| "learning_rate": 3.348739310341068e-05, | |
| "loss": 4.7301, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.09169213670464017, | |
| "grad_norm": 1.920733094215393, | |
| "learning_rate": 3.2916699845036816e-05, | |
| "loss": 5.0066, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.09335926646290636, | |
| "grad_norm": 1.6611617803573608, | |
| "learning_rate": 3.234138345689077e-05, | |
| "loss": 5.198, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.09447068630175048, | |
| "eval_loss": 1.3297733068466187, | |
| "eval_runtime": 387.3661, | |
| "eval_samples_per_second": 7.825, | |
| "eval_steps_per_second": 0.978, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.09502639622117255, | |
| "grad_norm": 1.5192731618881226, | |
| "learning_rate": 3.17617799075421e-05, | |
| "loss": 4.9727, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.09669352597943873, | |
| "grad_norm": 2.1325037479400635, | |
| "learning_rate": 3.1178227669141744e-05, | |
| "loss": 5.287, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.09836065573770492, | |
| "grad_norm": 1.6394548416137695, | |
| "learning_rate": 3.0591067519763895e-05, | |
| "loss": 5.0878, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.1000277854959711, | |
| "grad_norm": 1.954785704612732, | |
| "learning_rate": 3.0000642344401113e-05, | |
| "loss": 5.7474, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1016949152542373, | |
| "grad_norm": 1.7333064079284668, | |
| "learning_rate": 2.9407296934729227e-05, | |
| "loss": 5.2069, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.10336204501250347, | |
| "grad_norm": 1.7775465250015259, | |
| "learning_rate": 2.8811377787758636e-05, | |
| "loss": 4.8365, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.10502917477076966, | |
| "grad_norm": 1.766340970993042, | |
| "learning_rate": 2.8213232903489865e-05, | |
| "loss": 4.8806, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.10669630452903585, | |
| "grad_norm": 2.064275026321411, | |
| "learning_rate": 2.761321158169134e-05, | |
| "loss": 5.1876, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.10836343428730202, | |
| "grad_norm": 1.731985330581665, | |
| "learning_rate": 2.7011664217918154e-05, | |
| "loss": 4.6924, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.11003056404556821, | |
| "grad_norm": 1.8852187395095825, | |
| "learning_rate": 2.6408942098890936e-05, | |
| "loss": 5.0911, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.1116976938038344, | |
| "grad_norm": 1.8446505069732666, | |
| "learning_rate": 2.580539719735433e-05, | |
| "loss": 5.0379, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.11336482356210058, | |
| "grad_norm": 1.863871455192566, | |
| "learning_rate": 2.5201381966534748e-05, | |
| "loss": 5.3173, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.11336482356210058, | |
| "eval_loss": 1.3148518800735474, | |
| "eval_runtime": 387.4809, | |
| "eval_samples_per_second": 7.822, | |
| "eval_steps_per_second": 0.978, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.11503195332036677, | |
| "grad_norm": 2.1243629455566406, | |
| "learning_rate": 2.459724913431772e-05, | |
| "loss": 5.1268, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.11669908307863296, | |
| "grad_norm": 1.8287479877471924, | |
| "learning_rate": 2.399335149726463e-05, | |
| "loss": 4.8911, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.11836621283689913, | |
| "grad_norm": 1.827951431274414, | |
| "learning_rate": 2.3390041714589514e-05, | |
| "loss": 5.0788, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.12003334259516532, | |
| "grad_norm": 1.9181324243545532, | |
| "learning_rate": 2.2787672102216042e-05, | |
| "loss": 5.2716, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.12170047235343151, | |
| "grad_norm": 2.334996461868286, | |
| "learning_rate": 2.2186594427034864e-05, | |
| "loss": 5.4529, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.1233676021116977, | |
| "grad_norm": 2.042280673980713, | |
| "learning_rate": 2.1587159701481716e-05, | |
| "loss": 4.8902, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.1250347318699639, | |
| "grad_norm": 1.9080718755722046, | |
| "learning_rate": 2.098971797855599e-05, | |
| "loss": 4.933, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.12670186162823005, | |
| "grad_norm": 1.7101670503616333, | |
| "learning_rate": 2.0394618147399713e-05, | |
| "loss": 5.0186, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.12836899138649624, | |
| "grad_norm": 2.011359453201294, | |
| "learning_rate": 1.980220772955602e-05, | |
| "loss": 4.7936, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.13003612114476243, | |
| "grad_norm": 2.302273750305176, | |
| "learning_rate": 1.921283267602643e-05, | |
| "loss": 5.1487, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.13170325090302862, | |
| "grad_norm": 2.4797189235687256, | |
| "learning_rate": 1.8626837165245165e-05, | |
| "loss": 5.2862, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.13225896082245067, | |
| "eval_loss": 1.303543210029602, | |
| "eval_runtime": 387.3037, | |
| "eval_samples_per_second": 7.826, | |
| "eval_steps_per_second": 0.979, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.1333703806612948, | |
| "grad_norm": 1.8348701000213623, | |
| "learning_rate": 1.8044563402088684e-05, | |
| "loss": 5.0605, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.135037510419561, | |
| "grad_norm": 2.109149217605591, | |
| "learning_rate": 1.746635141803761e-05, | |
| "loss": 4.9242, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.13670464017782719, | |
| "grad_norm": 2.1694352626800537, | |
| "learning_rate": 1.6892538872607937e-05, | |
| "loss": 5.0852, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.13837176993609335, | |
| "grad_norm": 2.145925998687744, | |
| "learning_rate": 1.6323460856167426e-05, | |
| "loss": 4.9473, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.14003889969435954, | |
| "grad_norm": 2.4143218994140625, | |
| "learning_rate": 1.5759449694252226e-05, | |
| "loss": 5.2909, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.14170602945262573, | |
| "grad_norm": 2.154897689819336, | |
| "learning_rate": 1.5200834753498128e-05, | |
| "loss": 5.2477, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.14337315921089192, | |
| "grad_norm": 2.189666986465454, | |
| "learning_rate": 1.4647942249299707e-05, | |
| "loss": 5.4482, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.1450402889691581, | |
| "grad_norm": 1.9108495712280273, | |
| "learning_rate": 1.4101095055309746e-05, | |
| "loss": 5.1046, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.1467074187274243, | |
| "grad_norm": 1.8444137573242188, | |
| "learning_rate": 1.356061251489012e-05, | |
| "loss": 5.0423, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.14837454848569048, | |
| "grad_norm": 2.031024694442749, | |
| "learning_rate": 1.302681025462424e-05, | |
| "loss": 4.5857, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.15004167824395664, | |
| "grad_norm": 2.1987197399139404, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 5.381, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.15115309808280078, | |
| "eval_loss": 1.2963863611221313, | |
| "eval_runtime": 387.5334, | |
| "eval_samples_per_second": 7.821, | |
| "eval_steps_per_second": 0.978, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.15170880800222283, | |
| "grad_norm": 1.8340719938278198, | |
| "learning_rate": 1.1980489393370938e-05, | |
| "loss": 5.4333, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.15337593776048902, | |
| "grad_norm": 2.617314577102661, | |
| "learning_rate": 1.1468581814301717e-05, | |
| "loss": 5.757, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.1550430675187552, | |
| "grad_norm": 2.0526530742645264, | |
| "learning_rate": 1.096457620240298e-05, | |
| "loss": 4.9528, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.1567101972770214, | |
| "grad_norm": 2.3239846229553223, | |
| "learning_rate": 1.0468766882759094e-05, | |
| "loss": 5.2481, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.1583773270352876, | |
| "grad_norm": 2.1533966064453125, | |
| "learning_rate": 9.981443394050525e-06, | |
| "loss": 5.6509, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.16004445679355375, | |
| "grad_norm": 1.9592647552490234, | |
| "learning_rate": 9.502890319471491e-06, | |
| "loss": 4.9243, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.16171158655181994, | |
| "grad_norm": 2.204939126968384, | |
| "learning_rate": 9.033387120541306e-06, | |
| "loss": 5.2745, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.16337871631008613, | |
| "grad_norm": 2.236279010772705, | |
| "learning_rate": 8.573207973906735e-06, | |
| "loss": 5.4374, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.16504584606835232, | |
| "grad_norm": 2.4140145778656006, | |
| "learning_rate": 8.1226216112306e-06, | |
| "loss": 5.4428, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.1667129758266185, | |
| "grad_norm": 2.0701277256011963, | |
| "learning_rate": 7.681891162260015e-06, | |
| "loss": 5.4502, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.1683801055848847, | |
| "grad_norm": 2.154461622238159, | |
| "learning_rate": 7.251274001166044e-06, | |
| "loss": 5.0715, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.1700472353431509, | |
| "grad_norm": 2.3085010051727295, | |
| "learning_rate": 6.831021596244424e-06, | |
| "loss": 4.8451, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.1700472353431509, | |
| "eval_loss": 1.2917685508728027, | |
| "eval_runtime": 387.2177, | |
| "eval_samples_per_second": 7.828, | |
| "eval_steps_per_second": 0.979, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.17171436510141705, | |
| "grad_norm": 2.220491886138916, | |
| "learning_rate": 6.421379363065142e-06, | |
| "loss": 5.3908, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.17338149485968324, | |
| "grad_norm": 2.2047910690307617, | |
| "learning_rate": 6.022586521156715e-06, | |
| "loss": 5.2721, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.17504862461794943, | |
| "grad_norm": 2.1623401641845703, | |
| "learning_rate": 5.634875954308638e-06, | |
| "loss": 5.5073, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.17671575437621562, | |
| "grad_norm": 1.9954192638397217, | |
| "learning_rate": 5.258474074573877e-06, | |
| "loss": 5.1791, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.1783828841344818, | |
| "grad_norm": 2.24808669090271, | |
| "learning_rate": 4.893600690050579e-06, | |
| "loss": 5.0704, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.180050013892748, | |
| "grad_norm": 2.2592039108276367, | |
| "learning_rate": 4.540468876520323e-06, | |
| "loss": 5.0177, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.18171714365101416, | |
| "grad_norm": 1.9192252159118652, | |
| "learning_rate": 4.199284853017896e-06, | |
| "loss": 5.2738, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.18338427340928035, | |
| "grad_norm": 2.021440267562866, | |
| "learning_rate": 3.8702478614051355e-06, | |
| "loss": 4.6439, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.18505140316754654, | |
| "grad_norm": 2.309406042098999, | |
| "learning_rate": 3.5535500500193357e-06, | |
| "loss": 5.4409, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.18671853292581272, | |
| "grad_norm": 2.2390878200531006, | |
| "learning_rate": 3.249376361464021e-06, | |
| "loss": 5.1074, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.18838566268407891, | |
| "grad_norm": 2.540015697479248, | |
| "learning_rate": 2.957904424607652e-06, | |
| "loss": 5.2675, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.18894137260350097, | |
| "eval_loss": 1.2895426750183105, | |
| "eval_runtime": 387.2989, | |
| "eval_samples_per_second": 7.826, | |
| "eval_steps_per_second": 0.979, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.1900527924423451, | |
| "grad_norm": 2.492077112197876, | |
| "learning_rate": 2.679304450853401e-06, | |
| "loss": 5.211, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.1917199222006113, | |
| "grad_norm": 1.7696568965911865, | |
| "learning_rate": 2.4137391347404476e-06, | |
| "loss": 5.3133, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.19338705195887745, | |
| "grad_norm": 1.9813653230667114, | |
| "learning_rate": 2.1613635589349756e-06, | |
| "loss": 5.0046, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.19505418171714364, | |
| "grad_norm": 2.0188918113708496, | |
| "learning_rate": 1.922325103666281e-06, | |
| "loss": 5.1457, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.19672131147540983, | |
| "grad_norm": 2.231536865234375, | |
| "learning_rate": 1.696763360660808e-06, | |
| "loss": 4.8438, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.19838844123367602, | |
| "grad_norm": 2.102440357208252, | |
| "learning_rate": 1.4848100516245717e-06, | |
| "loss": 5.4079, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.2000555709919422, | |
| "grad_norm": 2.369569778442383, | |
| "learning_rate": 1.286588951321363e-06, | |
| "loss": 5.661, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.2017227007502084, | |
| "grad_norm": 1.8659355640411377, | |
| "learning_rate": 1.102215815291774e-06, | |
| "loss": 4.9097, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.2033898305084746, | |
| "grad_norm": 2.071213722229004, | |
| "learning_rate": 9.317983122552332e-07, | |
| "loss": 5.0217, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.20505696026674075, | |
| "grad_norm": 2.435093402862549, | |
| "learning_rate": 7.754359612344859e-07, | |
| "loss": 5.44, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.20672409002500694, | |
| "grad_norm": 2.3098435401916504, | |
| "learning_rate": 6.332200734393057e-07, | |
| "loss": 5.2669, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.20783550986385108, | |
| "eval_loss": 1.2886923551559448, | |
| "eval_runtime": 387.521, | |
| "eval_samples_per_second": 7.822, | |
| "eval_steps_per_second": 0.978, | |
| "step": 374 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 34, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.43602420813824e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |