| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.34371643394199786, | |
| "eval_steps": 100, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008592910848549946, | |
| "eval_loss": 10.365389823913574, | |
| "eval_runtime": 2.1768, | |
| "eval_samples_per_second": 225.103, | |
| "eval_steps_per_second": 112.552, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004296455424274973, | |
| "grad_norm": 0.07286953181028366, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 10.3669, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008592910848549946, | |
| "grad_norm": 0.10085838288068771, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 10.3651, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01288936627282492, | |
| "grad_norm": 0.10518611967563629, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3647, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017185821697099892, | |
| "grad_norm": 0.10583748668432236, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 10.3637, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021482277121374866, | |
| "grad_norm": 0.11692497134208679, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 10.3636, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02577873254564984, | |
| "grad_norm": 0.11737966537475586, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3622, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03007518796992481, | |
| "grad_norm": 0.09924237430095673, | |
| "learning_rate": 9.995494831023409e-05, | |
| "loss": 10.3611, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.034371643394199784, | |
| "grad_norm": 0.11419631540775299, | |
| "learning_rate": 9.981987442712633e-05, | |
| "loss": 10.3595, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03866809881847476, | |
| "grad_norm": 0.10765424370765686, | |
| "learning_rate": 9.959502176294383e-05, | |
| "loss": 10.3585, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04296455424274973, | |
| "grad_norm": 0.09559302777051926, | |
| "learning_rate": 9.928079551738543e-05, | |
| "loss": 10.3587, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.047261009667024706, | |
| "grad_norm": 0.08157297968864441, | |
| "learning_rate": 9.887776194738432e-05, | |
| "loss": 10.3608, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.05155746509129968, | |
| "grad_norm": 0.12234725803136826, | |
| "learning_rate": 9.838664734667495e-05, | |
| "loss": 10.3568, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.055853920515574654, | |
| "grad_norm": 0.14145438373088837, | |
| "learning_rate": 9.780833673696254e-05, | |
| "loss": 10.3542, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.06015037593984962, | |
| "grad_norm": 0.13747857511043549, | |
| "learning_rate": 9.714387227305422e-05, | |
| "loss": 10.3524, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0644468313641246, | |
| "grad_norm": 0.15347330272197723, | |
| "learning_rate": 9.639445136482548e-05, | |
| "loss": 10.3495, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06874328678839957, | |
| "grad_norm": 0.15859973430633545, | |
| "learning_rate": 9.55614245194068e-05, | |
| "loss": 10.3467, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07303974221267455, | |
| "grad_norm": 0.17187100648880005, | |
| "learning_rate": 9.464629290747842e-05, | |
| "loss": 10.3441, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.07733619763694952, | |
| "grad_norm": 0.15804657340049744, | |
| "learning_rate": 9.365070565805941e-05, | |
| "loss": 10.3429, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 0.13526834547519684, | |
| "learning_rate": 9.257645688666556e-05, | |
| "loss": 10.3418, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.08592910848549946, | |
| "grad_norm": 0.12908455729484558, | |
| "learning_rate": 9.142548246219212e-05, | |
| "loss": 10.343, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08592910848549946, | |
| "eval_loss": 10.338217735290527, | |
| "eval_runtime": 2.1648, | |
| "eval_samples_per_second": 226.353, | |
| "eval_steps_per_second": 113.176, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09022556390977443, | |
| "grad_norm": 0.13095244765281677, | |
| "learning_rate": 9.019985651834703e-05, | |
| "loss": 10.3475, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.09452201933404941, | |
| "grad_norm": 0.15576040744781494, | |
| "learning_rate": 8.890178771592199e-05, | |
| "loss": 10.3365, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.09881847475832438, | |
| "grad_norm": 0.15617074072360992, | |
| "learning_rate": 8.753361526263621e-05, | |
| "loss": 10.3317, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.10311493018259936, | |
| "grad_norm": 0.15280985832214355, | |
| "learning_rate": 8.609780469772623e-05, | |
| "loss": 10.3277, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.10741138560687433, | |
| "grad_norm": 0.14411042630672455, | |
| "learning_rate": 8.459694344887732e-05, | |
| "loss": 10.3259, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.11170784103114931, | |
| "grad_norm": 0.13951170444488525, | |
| "learning_rate": 8.303373616950408e-05, | |
| "loss": 10.3209, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.11600429645542427, | |
| "grad_norm": 0.1300823837518692, | |
| "learning_rate": 8.141099986478212e-05, | |
| "loss": 10.3194, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.12030075187969924, | |
| "grad_norm": 0.1237272247672081, | |
| "learning_rate": 7.973165881521434e-05, | |
| "loss": 10.3182, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.12459720730397422, | |
| "grad_norm": 0.1246255561709404, | |
| "learning_rate": 7.799873930687978e-05, | |
| "loss": 10.3188, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.1288936627282492, | |
| "grad_norm": 0.11004636436700821, | |
| "learning_rate": 7.621536417786159e-05, | |
| "loss": 10.322, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.13319011815252416, | |
| "grad_norm": 0.1266869306564331, | |
| "learning_rate": 7.438474719068173e-05, | |
| "loss": 10.3235, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.13748657357679914, | |
| "grad_norm": 0.10802991688251495, | |
| "learning_rate": 7.251018724088367e-05, | |
| "loss": 10.3126, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.14178302900107412, | |
| "grad_norm": 0.10975682735443115, | |
| "learning_rate": 7.059506241219965e-05, | |
| "loss": 10.3084, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.1460794844253491, | |
| "grad_norm": 0.10861735790967941, | |
| "learning_rate": 6.864282388901544e-05, | |
| "loss": 10.3059, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.15037593984962405, | |
| "grad_norm": 0.11129958182573318, | |
| "learning_rate": 6.665698973710288e-05, | |
| "loss": 10.3043, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.15467239527389903, | |
| "grad_norm": 0.1110716313123703, | |
| "learning_rate": 6.464113856382752e-05, | |
| "loss": 10.3021, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.158968850698174, | |
| "grad_norm": 0.10098284482955933, | |
| "learning_rate": 6.259890306925627e-05, | |
| "loss": 10.3031, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 0.08908476680517197, | |
| "learning_rate": 6.0533963499786314e-05, | |
| "loss": 10.3043, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.16756176154672395, | |
| "grad_norm": 0.09452126920223236, | |
| "learning_rate": 5.8450041016092464e-05, | |
| "loss": 10.3035, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.17185821697099893, | |
| "grad_norm": 0.10022512823343277, | |
| "learning_rate": 5.6350890987343944e-05, | |
| "loss": 10.3059, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.17185821697099893, | |
| "eval_loss": 10.300703048706055, | |
| "eval_runtime": 2.1709, | |
| "eval_samples_per_second": 225.717, | |
| "eval_steps_per_second": 112.859, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1761546723952739, | |
| "grad_norm": 0.12360203266143799, | |
| "learning_rate": 5.4240296223775465e-05, | |
| "loss": 10.3138, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.18045112781954886, | |
| "grad_norm": 0.08811464160680771, | |
| "learning_rate": 5.212206015980742e-05, | |
| "loss": 10.2979, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.18474758324382384, | |
| "grad_norm": 0.09015189856290817, | |
| "learning_rate": 5e-05, | |
| "loss": 10.2951, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.18904403866809882, | |
| "grad_norm": 0.09212949126958847, | |
| "learning_rate": 4.78779398401926e-05, | |
| "loss": 10.2947, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.1933404940923738, | |
| "grad_norm": 0.0850977972149849, | |
| "learning_rate": 4.575970377622456e-05, | |
| "loss": 10.2922, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.19763694951664876, | |
| "grad_norm": 0.1262769252061844, | |
| "learning_rate": 4.364910901265606e-05, | |
| "loss": 10.293, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.20193340494092374, | |
| "grad_norm": 0.06989829242229462, | |
| "learning_rate": 4.1549958983907555e-05, | |
| "loss": 10.2938, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.20622986036519872, | |
| "grad_norm": 0.07775533199310303, | |
| "learning_rate": 3.94660365002137e-05, | |
| "loss": 10.2939, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 0.08431865274906158, | |
| "learning_rate": 3.740109693074375e-05, | |
| "loss": 10.296, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.21482277121374865, | |
| "grad_norm": 0.1112353652715683, | |
| "learning_rate": 3.5358861436172485e-05, | |
| "loss": 10.3006, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.21911922663802363, | |
| "grad_norm": 0.1300688087940216, | |
| "learning_rate": 3.334301026289712e-05, | |
| "loss": 10.3033, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.22341568206229862, | |
| "grad_norm": 0.08653448522090912, | |
| "learning_rate": 3.135717611098458e-05, | |
| "loss": 10.2941, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.22771213748657357, | |
| "grad_norm": 0.07097543030977249, | |
| "learning_rate": 2.9404937587800375e-05, | |
| "loss": 10.2889, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.23200859291084855, | |
| "grad_norm": 0.0754798948764801, | |
| "learning_rate": 2.748981275911633e-05, | |
| "loss": 10.2886, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.23630504833512353, | |
| "grad_norm": 0.08331610262393951, | |
| "learning_rate": 2.5615252809318284e-05, | |
| "loss": 10.2872, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.24060150375939848, | |
| "grad_norm": 0.09955774992704391, | |
| "learning_rate": 2.3784635822138424e-05, | |
| "loss": 10.2898, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": 0.07286366075277328, | |
| "learning_rate": 2.2001260693120233e-05, | |
| "loss": 10.291, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.24919441460794844, | |
| "grad_norm": 0.06244928762316704, | |
| "learning_rate": 2.026834118478567e-05, | |
| "loss": 10.2917, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2534908700322234, | |
| "grad_norm": 0.07061257213354111, | |
| "learning_rate": 1.858900013521788e-05, | |
| "loss": 10.2929, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.2577873254564984, | |
| "grad_norm": 0.07385751605033875, | |
| "learning_rate": 1.6966263830495936e-05, | |
| "loss": 10.2938, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2577873254564984, | |
| "eval_loss": 10.291213035583496, | |
| "eval_runtime": 2.1699, | |
| "eval_samples_per_second": 225.82, | |
| "eval_steps_per_second": 112.91, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2620837808807734, | |
| "grad_norm": 0.12838312983512878, | |
| "learning_rate": 1.5403056551122697e-05, | |
| "loss": 10.3068, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.2663802363050483, | |
| "grad_norm": 0.0748727023601532, | |
| "learning_rate": 1.3902195302273779e-05, | |
| "loss": 10.2909, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.2706766917293233, | |
| "grad_norm": 0.06014459207653999, | |
| "learning_rate": 1.246638473736378e-05, | |
| "loss": 10.2888, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.2749731471535983, | |
| "grad_norm": 0.06609732657670975, | |
| "learning_rate": 1.1098212284078036e-05, | |
| "loss": 10.286, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.27926960257787325, | |
| "grad_norm": 0.08444568514823914, | |
| "learning_rate": 9.800143481652979e-06, | |
| "loss": 10.2851, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.28356605800214824, | |
| "grad_norm": 0.10820266604423523, | |
| "learning_rate": 8.574517537807897e-06, | |
| "loss": 10.2849, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.2878625134264232, | |
| "grad_norm": 0.05920971930027008, | |
| "learning_rate": 7.423543113334436e-06, | |
| "loss": 10.2876, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.2921589688506982, | |
| "grad_norm": 0.0520319864153862, | |
| "learning_rate": 6.349294341940593e-06, | |
| "loss": 10.2905, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.2964554242749731, | |
| "grad_norm": 0.06108549237251282, | |
| "learning_rate": 5.353707092521582e-06, | |
| "loss": 10.2909, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.3007518796992481, | |
| "grad_norm": 0.08654540032148361, | |
| "learning_rate": 4.43857548059321e-06, | |
| "loss": 10.297, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.3050483351235231, | |
| "grad_norm": 0.14339615404605865, | |
| "learning_rate": 3.605548635174533e-06, | |
| "loss": 10.3028, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.30934479054779807, | |
| "grad_norm": 0.07507804781198502, | |
| "learning_rate": 2.85612772694579e-06, | |
| "loss": 10.2928, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.31364124597207305, | |
| "grad_norm": 0.05845225602388382, | |
| "learning_rate": 2.191663263037458e-06, | |
| "loss": 10.2871, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.317937701396348, | |
| "grad_norm": 0.06766950339078903, | |
| "learning_rate": 1.6133526533250565e-06, | |
| "loss": 10.2856, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.322234156820623, | |
| "grad_norm": 0.0721559226512909, | |
| "learning_rate": 1.1222380526156928e-06, | |
| "loss": 10.2873, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 0.09494008868932724, | |
| "learning_rate": 7.192044826145771e-07, | |
| "loss": 10.2862, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.3308270676691729, | |
| "grad_norm": 0.059854406863451004, | |
| "learning_rate": 4.049782370561583e-07, | |
| "loss": 10.2869, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.3351235230934479, | |
| "grad_norm": 0.05713344365358353, | |
| "learning_rate": 1.8012557287367392e-07, | |
| "loss": 10.2907, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.3394199785177229, | |
| "grad_norm": 0.06379101425409317, | |
| "learning_rate": 4.5051689765929214e-08, | |
| "loss": 10.2901, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.34371643394199786, | |
| "grad_norm": 0.08994629234075546, | |
| "learning_rate": 0.0, | |
| "loss": 10.298, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.34371643394199786, | |
| "eval_loss": 10.29015827178955, | |
| "eval_runtime": 2.1666, | |
| "eval_samples_per_second": 226.166, | |
| "eval_steps_per_second": 113.083, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 16913627873280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |