| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10402444574475002, | |
| "eval_steps": 100, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000260061114361875, | |
| "eval_loss": 3.210697650909424, | |
| "eval_runtime": 46.7762, | |
| "eval_samples_per_second": 138.468, | |
| "eval_steps_per_second": 17.316, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001300305571809375, | |
| "grad_norm": 0.1656179130077362, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2144, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00260061114361875, | |
| "grad_norm": 0.19077427685260773, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1656, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0039009167154281255, | |
| "grad_norm": 0.20196713507175446, | |
| "learning_rate": 9.995944990857849e-05, | |
| "loss": 3.1702, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0052012222872375, | |
| "grad_norm": 0.24549086391925812, | |
| "learning_rate": 9.983786540671051e-05, | |
| "loss": 3.1669, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006501527859046876, | |
| "grad_norm": 0.2799537777900696, | |
| "learning_rate": 9.96354437049027e-05, | |
| "loss": 3.0444, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007801833430856251, | |
| "grad_norm": 0.2620985209941864, | |
| "learning_rate": 9.935251313189564e-05, | |
| "loss": 2.9902, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009102139002665627, | |
| "grad_norm": 0.25993800163269043, | |
| "learning_rate": 9.898953260211338e-05, | |
| "loss": 2.7868, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010402444574475, | |
| "grad_norm": 0.25809502601623535, | |
| "learning_rate": 9.85470908713026e-05, | |
| "loss": 2.9121, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011702750146284377, | |
| "grad_norm": 0.23389342427253723, | |
| "learning_rate": 9.802590558156862e-05, | |
| "loss": 2.7214, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.013003055718093752, | |
| "grad_norm": 0.22849056124687195, | |
| "learning_rate": 9.742682209735727e-05, | |
| "loss": 2.7599, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014303361289903128, | |
| "grad_norm": 0.2257491499185562, | |
| "learning_rate": 9.675081213427076e-05, | |
| "loss": 2.6229, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.015603666861712502, | |
| "grad_norm": 0.22627227008342743, | |
| "learning_rate": 9.599897218294122e-05, | |
| "loss": 2.6735, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.016903972433521878, | |
| "grad_norm": 0.21060359477996826, | |
| "learning_rate": 9.517252173051911e-05, | |
| "loss": 2.6384, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.018204278005331254, | |
| "grad_norm": 0.20334959030151367, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 2.5622, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01950458357714063, | |
| "grad_norm": 0.19899047911167145, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.605, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02080488914895, | |
| "grad_norm": 0.21144025027751923, | |
| "learning_rate": 9.225950427718975e-05, | |
| "loss": 2.5366, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.022105194720759377, | |
| "grad_norm": 0.19850236177444458, | |
| "learning_rate": 9.114919329468282e-05, | |
| "loss": 2.4836, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.023405500292568753, | |
| "grad_norm": 0.20592238008975983, | |
| "learning_rate": 8.997213817017507e-05, | |
| "loss": 2.4513, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02470580586437813, | |
| "grad_norm": 0.233050137758255, | |
| "learning_rate": 8.873024809138272e-05, | |
| "loss": 2.4859, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.026006111436187505, | |
| "grad_norm": 0.2322545349597931, | |
| "learning_rate": 8.742553740855506e-05, | |
| "loss": 2.4244, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.026006111436187505, | |
| "eval_loss": 2.4954044818878174, | |
| "eval_runtime": 46.5346, | |
| "eval_samples_per_second": 139.187, | |
| "eval_steps_per_second": 17.406, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02730641700799688, | |
| "grad_norm": 0.20528066158294678, | |
| "learning_rate": 8.606012236719073e-05, | |
| "loss": 2.4713, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.028606722579806256, | |
| "grad_norm": 0.20817121863365173, | |
| "learning_rate": 8.463621767547998e-05, | |
| "loss": 2.504, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02990702815161563, | |
| "grad_norm": 0.19070002436637878, | |
| "learning_rate": 8.315613291203976e-05, | |
| "loss": 2.4456, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.031207333723425004, | |
| "grad_norm": 0.2086874395608902, | |
| "learning_rate": 8.162226877976887e-05, | |
| "loss": 2.4541, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03250763929523438, | |
| "grad_norm": 0.21223700046539307, | |
| "learning_rate": 8.003711321189895e-05, | |
| "loss": 2.4791, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.033807944867043756, | |
| "grad_norm": 0.20589032769203186, | |
| "learning_rate": 7.840323733655778e-05, | |
| "loss": 2.5583, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.03510825043885313, | |
| "grad_norm": 0.21625283360481262, | |
| "learning_rate": 7.672329130639005e-05, | |
| "loss": 2.4741, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.03640855601066251, | |
| "grad_norm": 0.2250359058380127, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.5563, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03770886158247188, | |
| "grad_norm": 0.22031283378601074, | |
| "learning_rate": 7.323615860218843e-05, | |
| "loss": 2.4719, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.03900916715428126, | |
| "grad_norm": 0.21579761803150177, | |
| "learning_rate": 7.143462807015271e-05, | |
| "loss": 2.4485, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.04030947272609063, | |
| "grad_norm": 0.2309805005788803, | |
| "learning_rate": 6.959833049300377e-05, | |
| "loss": 2.4822, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.0416097782979, | |
| "grad_norm": 0.19943702220916748, | |
| "learning_rate": 6.773024435212678e-05, | |
| "loss": 2.4214, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.04291008386970938, | |
| "grad_norm": 0.21527348458766937, | |
| "learning_rate": 6.583339969007363e-05, | |
| "loss": 2.3161, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.044210389441518755, | |
| "grad_norm": 0.2162819504737854, | |
| "learning_rate": 6.391087319582264e-05, | |
| "loss": 2.4201, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.045510695013328134, | |
| "grad_norm": 0.2415967732667923, | |
| "learning_rate": 6.19657832143779e-05, | |
| "loss": 2.3804, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.046811000585137506, | |
| "grad_norm": 0.22041171789169312, | |
| "learning_rate": 6.0001284688802226e-05, | |
| "loss": 2.4879, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.048111306156946886, | |
| "grad_norm": 0.2270502895116806, | |
| "learning_rate": 5.8020564042888015e-05, | |
| "loss": 2.3864, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.04941161172875626, | |
| "grad_norm": 0.2288903146982193, | |
| "learning_rate": 5.602683401276615e-05, | |
| "loss": 2.4525, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.05071191730056563, | |
| "grad_norm": 0.2158132791519165, | |
| "learning_rate": 5.402332843583631e-05, | |
| "loss": 2.3903, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.05201222287237501, | |
| "grad_norm": 0.23484806716442108, | |
| "learning_rate": 5.201329700547076e-05, | |
| "loss": 2.4632, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05201222287237501, | |
| "eval_loss": 2.43571400642395, | |
| "eval_runtime": 48.746, | |
| "eval_samples_per_second": 132.872, | |
| "eval_steps_per_second": 16.617, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05331252844418438, | |
| "grad_norm": 0.22658920288085938, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4468, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.05461283401599376, | |
| "grad_norm": 0.22382205724716187, | |
| "learning_rate": 4.798670299452926e-05, | |
| "loss": 2.4227, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.05591313958780313, | |
| "grad_norm": 0.2128317654132843, | |
| "learning_rate": 4.597667156416371e-05, | |
| "loss": 2.394, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.05721344515961251, | |
| "grad_norm": 0.20399969816207886, | |
| "learning_rate": 4.397316598723385e-05, | |
| "loss": 2.3722, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.058513750731421885, | |
| "grad_norm": 0.22103694081306458, | |
| "learning_rate": 4.197943595711198e-05, | |
| "loss": 2.4722, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.05981405630323126, | |
| "grad_norm": 0.19609223306179047, | |
| "learning_rate": 3.9998715311197785e-05, | |
| "loss": 2.4358, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.061114361875040636, | |
| "grad_norm": 0.20797300338745117, | |
| "learning_rate": 3.803421678562213e-05, | |
| "loss": 2.4147, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.06241466744685001, | |
| "grad_norm": 0.23733116686344147, | |
| "learning_rate": 3.608912680417737e-05, | |
| "loss": 2.5038, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.06371497301865939, | |
| "grad_norm": 0.20630250871181488, | |
| "learning_rate": 3.4166600309926387e-05, | |
| "loss": 2.43, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.06501527859046877, | |
| "grad_norm": 0.21626047790050507, | |
| "learning_rate": 3.226975564787322e-05, | |
| "loss": 2.3791, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.06631558416227813, | |
| "grad_norm": 0.22082562744617462, | |
| "learning_rate": 3.0401669506996256e-05, | |
| "loss": 2.3927, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.06761588973408751, | |
| "grad_norm": 0.2386007159948349, | |
| "learning_rate": 2.8565371929847284e-05, | |
| "loss": 2.4492, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.06891619530589689, | |
| "grad_norm": 0.23111873865127563, | |
| "learning_rate": 2.6763841397811573e-05, | |
| "loss": 2.4282, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.07021650087770626, | |
| "grad_norm": 0.23999303579330444, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.4116, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.07151680644951564, | |
| "grad_norm": 0.23608632385730743, | |
| "learning_rate": 2.3276708693609943e-05, | |
| "loss": 2.5647, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.07281711202132501, | |
| "grad_norm": 0.22393612563610077, | |
| "learning_rate": 2.1596762663442218e-05, | |
| "loss": 2.516, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.07411741759313438, | |
| "grad_norm": 0.2267947643995285, | |
| "learning_rate": 1.996288678810105e-05, | |
| "loss": 2.4214, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.07541772316494376, | |
| "grad_norm": 0.21349841356277466, | |
| "learning_rate": 1.837773122023114e-05, | |
| "loss": 2.4265, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.07671802873675314, | |
| "grad_norm": 0.21270251274108887, | |
| "learning_rate": 1.684386708796025e-05, | |
| "loss": 2.4332, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.07801833430856252, | |
| "grad_norm": 0.23567631840705872, | |
| "learning_rate": 1.536378232452003e-05, | |
| "loss": 2.396, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.07801833430856252, | |
| "eval_loss": 2.4196038246154785, | |
| "eval_runtime": 47.2697, | |
| "eval_samples_per_second": 137.022, | |
| "eval_steps_per_second": 17.136, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.07931863988037188, | |
| "grad_norm": 0.22273465991020203, | |
| "learning_rate": 1.3939877632809278e-05, | |
| "loss": 2.4052, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.08061894545218126, | |
| "grad_norm": 0.24445375800132751, | |
| "learning_rate": 1.257446259144494e-05, | |
| "loss": 2.3494, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.08191925102399064, | |
| "grad_norm": 0.21784046292304993, | |
| "learning_rate": 1.1269751908617277e-05, | |
| "loss": 2.385, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.0832195565958, | |
| "grad_norm": 0.2166690081357956, | |
| "learning_rate": 1.0027861829824952e-05, | |
| "loss": 2.402, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.08451986216760939, | |
| "grad_norm": 0.2369987815618515, | |
| "learning_rate": 8.850806705317183e-06, | |
| "loss": 2.3636, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.08582016773941877, | |
| "grad_norm": 0.2313825637102127, | |
| "learning_rate": 7.740495722810271e-06, | |
| "loss": 2.3894, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.08712047331122814, | |
| "grad_norm": 0.227387934923172, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.3997, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.08842077888303751, | |
| "grad_norm": 0.25343969464302063, | |
| "learning_rate": 5.727198717339511e-06, | |
| "loss": 2.3717, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.08972108445484689, | |
| "grad_norm": 0.2612355053424835, | |
| "learning_rate": 4.827478269480895e-06, | |
| "loss": 2.3807, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.09102139002665627, | |
| "grad_norm": 0.23141621053218842, | |
| "learning_rate": 4.001027817058789e-06, | |
| "loss": 2.3814, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.09232169559846563, | |
| "grad_norm": 0.22887873649597168, | |
| "learning_rate": 3.249187865729264e-06, | |
| "loss": 2.3882, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.09362200117027501, | |
| "grad_norm": 0.2551928758621216, | |
| "learning_rate": 2.573177902642726e-06, | |
| "loss": 2.4097, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.09492230674208439, | |
| "grad_norm": 0.22297078371047974, | |
| "learning_rate": 1.974094418431388e-06, | |
| "loss": 2.3652, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.09622261231389377, | |
| "grad_norm": 0.24526731669902802, | |
| "learning_rate": 1.4529091286973995e-06, | |
| "loss": 2.4906, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.09752291788570314, | |
| "grad_norm": 0.23062212765216827, | |
| "learning_rate": 1.0104673978866164e-06, | |
| "loss": 2.4328, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.09882322345751252, | |
| "grad_norm": 0.23222170770168304, | |
| "learning_rate": 6.474868681043578e-07, | |
| "loss": 2.2888, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.1001235290293219, | |
| "grad_norm": 0.25198790431022644, | |
| "learning_rate": 3.6455629509730136e-07, | |
| "loss": 2.3814, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.10142383460113126, | |
| "grad_norm": 0.23422600328922272, | |
| "learning_rate": 1.6213459328950352e-07, | |
| "loss": 2.443, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.10272414017294064, | |
| "grad_norm": 0.22208155691623688, | |
| "learning_rate": 4.055009142152067e-08, | |
| "loss": 2.3945, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.10402444574475002, | |
| "grad_norm": 0.22670188546180725, | |
| "learning_rate": 0.0, | |
| "loss": 2.3587, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.10402444574475002, | |
| "eval_loss": 2.4172396659851074, | |
| "eval_runtime": 46.3757, | |
| "eval_samples_per_second": 139.664, | |
| "eval_steps_per_second": 17.466, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.5375418471153664e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |