| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.997968855788761, | |
| "eval_steps": 50, | |
| "global_step": 1107, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013540961408259987, | |
| "grad_norm": 18.463732975176427, | |
| "learning_rate": 5e-07, | |
| "loss": 1.749, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.027081922816519974, | |
| "grad_norm": 12.15126324106773, | |
| "learning_rate": 1e-06, | |
| "loss": 1.5921, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.040622884224779957, | |
| "grad_norm": 7.7718176367972, | |
| "learning_rate": 9.9994874230328e-07, | |
| "loss": 1.2948, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05416384563303995, | |
| "grad_norm": 4.024003853982352, | |
| "learning_rate": 9.997949797225268e-07, | |
| "loss": 1.1393, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06770480704129993, | |
| "grad_norm": 3.796718690402949, | |
| "learning_rate": 9.995387437838025e-07, | |
| "loss": 1.0604, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08124576844955991, | |
| "grad_norm": 3.4511274356883295, | |
| "learning_rate": 9.991800870233637e-07, | |
| "loss": 1.0272, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0947867298578199, | |
| "grad_norm": 3.6605756447735724, | |
| "learning_rate": 9.98719082976888e-07, | |
| "loss": 1.003, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1083276912660799, | |
| "grad_norm": 3.5416553128618156, | |
| "learning_rate": 9.981558261643982e-07, | |
| "loss": 0.9719, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12186865267433988, | |
| "grad_norm": 3.5000585696846245, | |
| "learning_rate": 9.97490432070881e-07, | |
| "loss": 0.9584, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13540961408259986, | |
| "grad_norm": 3.805541453776684, | |
| "learning_rate": 9.967230371226118e-07, | |
| "loss": 0.9444, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13540961408259986, | |
| "eval_loss": 0.9377400875091553, | |
| "eval_runtime": 182.856, | |
| "eval_samples_per_second": 57.422, | |
| "eval_steps_per_second": 0.902, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14895057549085985, | |
| "grad_norm": 3.6018765357986844, | |
| "learning_rate": 9.958537986591803e-07, | |
| "loss": 0.9198, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.16249153689911983, | |
| "grad_norm": 3.5280703732572545, | |
| "learning_rate": 9.948828949012327e-07, | |
| "loss": 0.9181, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17603249830737983, | |
| "grad_norm": 3.6595010678642925, | |
| "learning_rate": 9.938105249139305e-07, | |
| "loss": 0.9296, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1895734597156398, | |
| "grad_norm": 3.323630668058957, | |
| "learning_rate": 9.92636908566136e-07, | |
| "loss": 0.9241, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2031144211238998, | |
| "grad_norm": 3.425849289666098, | |
| "learning_rate": 9.913622864853324e-07, | |
| "loss": 0.8917, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2166553825321598, | |
| "grad_norm": 3.9967436509747025, | |
| "learning_rate": 9.89986920008288e-07, | |
| "loss": 0.8988, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.23019634394041977, | |
| "grad_norm": 3.436149937331634, | |
| "learning_rate": 9.885110911274738e-07, | |
| "loss": 0.8774, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.24373730534867977, | |
| "grad_norm": 3.642660003309155, | |
| "learning_rate": 9.869351024332466e-07, | |
| "loss": 0.8787, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.25727826675693977, | |
| "grad_norm": 3.3574313517064978, | |
| "learning_rate": 9.852592770518082e-07, | |
| "loss": 0.8897, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.2708192281651997, | |
| "grad_norm": 3.534867148811258, | |
| "learning_rate": 9.834839585789557e-07, | |
| "loss": 0.8668, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2708192281651997, | |
| "eval_loss": 0.8815732002258301, | |
| "eval_runtime": 182.989, | |
| "eval_samples_per_second": 57.38, | |
| "eval_steps_per_second": 0.902, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2843601895734597, | |
| "grad_norm": 3.476334412992533, | |
| "learning_rate": 9.816095110096324e-07, | |
| "loss": 0.8806, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.2979011509817197, | |
| "grad_norm": 3.5218146742622856, | |
| "learning_rate": 9.796363186632983e-07, | |
| "loss": 0.8895, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.3114421123899797, | |
| "grad_norm": 3.6344919656503545, | |
| "learning_rate": 9.775647861051328e-07, | |
| "loss": 0.8675, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.32498307379823965, | |
| "grad_norm": 3.8058175800193537, | |
| "learning_rate": 9.753953380630862e-07, | |
| "loss": 0.8739, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.33852403520649965, | |
| "grad_norm": 3.5458347600694515, | |
| "learning_rate": 9.731284193407981e-07, | |
| "loss": 0.8536, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.35206499661475965, | |
| "grad_norm": 3.4919069279296138, | |
| "learning_rate": 9.707644947263975e-07, | |
| "loss": 0.8598, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.36560595802301965, | |
| "grad_norm": 3.2003162498092848, | |
| "learning_rate": 9.683040488972086e-07, | |
| "loss": 0.8628, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.3791469194312796, | |
| "grad_norm": 3.337658064243358, | |
| "learning_rate": 9.657475863203756e-07, | |
| "loss": 0.8633, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3926878808395396, | |
| "grad_norm": 3.4844992093115987, | |
| "learning_rate": 9.63095631149432e-07, | |
| "loss": 0.859, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.4062288422477996, | |
| "grad_norm": 3.5999127416589296, | |
| "learning_rate": 9.603487271168336e-07, | |
| "loss": 0.8436, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4062288422477996, | |
| "eval_loss": 0.8559273481369019, | |
| "eval_runtime": 182.9208, | |
| "eval_samples_per_second": 57.402, | |
| "eval_steps_per_second": 0.902, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4197698036560596, | |
| "grad_norm": 3.4543800855029807, | |
| "learning_rate": 9.575074374224758e-07, | |
| "loss": 0.8431, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.4333107650643196, | |
| "grad_norm": 3.574884162982998, | |
| "learning_rate": 9.545723446182201e-07, | |
| "loss": 0.8466, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.44685172647257954, | |
| "grad_norm": 3.230714522717894, | |
| "learning_rate": 9.515440504884539e-07, | |
| "loss": 0.829, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.46039268788083954, | |
| "grad_norm": 3.38192753716993, | |
| "learning_rate": 9.484231759267054e-07, | |
| "loss": 0.8462, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.47393364928909953, | |
| "grad_norm": 3.562118447176729, | |
| "learning_rate": 9.452103608083417e-07, | |
| "loss": 0.8602, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.48747461069735953, | |
| "grad_norm": 3.2476691940428353, | |
| "learning_rate": 9.419062638593748e-07, | |
| "loss": 0.8266, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5010155721056195, | |
| "grad_norm": 3.494748883924626, | |
| "learning_rate": 9.385115625214021e-07, | |
| "loss": 0.8219, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.5145565335138795, | |
| "grad_norm": 3.4365818103766452, | |
| "learning_rate": 9.350269528127101e-07, | |
| "loss": 0.8438, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5280974949221394, | |
| "grad_norm": 3.245299565361765, | |
| "learning_rate": 9.31453149185569e-07, | |
| "loss": 0.8337, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.5416384563303994, | |
| "grad_norm": 3.603292666759954, | |
| "learning_rate": 9.277908843797492e-07, | |
| "loss": 0.8192, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5416384563303994, | |
| "eval_loss": 0.8383815884590149, | |
| "eval_runtime": 183.0029, | |
| "eval_samples_per_second": 57.376, | |
| "eval_steps_per_second": 0.902, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5551794177386594, | |
| "grad_norm": 3.3561089172228797, | |
| "learning_rate": 9.240409092722852e-07, | |
| "loss": 0.8483, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.5687203791469194, | |
| "grad_norm": 3.351512113878825, | |
| "learning_rate": 9.20203992723524e-07, | |
| "loss": 0.8109, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5822613405551794, | |
| "grad_norm": 3.4763361691712293, | |
| "learning_rate": 9.162809214194851e-07, | |
| "loss": 0.8335, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.5958023019634394, | |
| "grad_norm": 3.292224110319897, | |
| "learning_rate": 9.122724997105646e-07, | |
| "loss": 0.8465, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6093432633716994, | |
| "grad_norm": 3.566456464228769, | |
| "learning_rate": 9.0817954944662e-07, | |
| "loss": 0.8257, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.6228842247799594, | |
| "grad_norm": 3.6677580289310088, | |
| "learning_rate": 9.040029098084643e-07, | |
| "loss": 0.8479, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.6364251861882194, | |
| "grad_norm": 3.4606320291357546, | |
| "learning_rate": 8.997434371358092e-07, | |
| "loss": 0.8412, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.6499661475964793, | |
| "grad_norm": 3.2432058195015467, | |
| "learning_rate": 8.954020047516884e-07, | |
| "loss": 0.7984, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6635071090047393, | |
| "grad_norm": 3.24817794736711, | |
| "learning_rate": 8.909795027833996e-07, | |
| "loss": 0.834, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.6770480704129993, | |
| "grad_norm": 3.653634156312455, | |
| "learning_rate": 8.864768379800016e-07, | |
| "loss": 0.8285, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6770480704129993, | |
| "eval_loss": 0.8261091709136963, | |
| "eval_runtime": 182.9038, | |
| "eval_samples_per_second": 57.407, | |
| "eval_steps_per_second": 0.902, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6905890318212593, | |
| "grad_norm": 3.5255613554356384, | |
| "learning_rate": 8.81894933526402e-07, | |
| "loss": 0.8322, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.7041299932295193, | |
| "grad_norm": 3.727303124024427, | |
| "learning_rate": 8.772347288540763e-07, | |
| "loss": 0.8384, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.7176709546377793, | |
| "grad_norm": 3.731075409838065, | |
| "learning_rate": 8.724971794484555e-07, | |
| "loss": 0.8263, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.7312119160460393, | |
| "grad_norm": 3.6981830618689484, | |
| "learning_rate": 8.676832566530221e-07, | |
| "loss": 0.8165, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.7447528774542993, | |
| "grad_norm": 3.498794505216147, | |
| "learning_rate": 8.62793947470155e-07, | |
| "loss": 0.8037, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.7582938388625592, | |
| "grad_norm": 3.5635605377852024, | |
| "learning_rate": 8.578302543587629e-07, | |
| "loss": 0.7896, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.7718348002708192, | |
| "grad_norm": 3.63798214652303, | |
| "learning_rate": 8.527931950287506e-07, | |
| "loss": 0.8129, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.7853757616790792, | |
| "grad_norm": 3.518857236471562, | |
| "learning_rate": 8.47683802232356e-07, | |
| "loss": 0.8182, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7989167230873392, | |
| "grad_norm": 3.5608373625732694, | |
| "learning_rate": 8.425031235524045e-07, | |
| "loss": 0.8256, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.8124576844955992, | |
| "grad_norm": 3.6755850332375286, | |
| "learning_rate": 8.372522211875224e-07, | |
| "loss": 0.8132, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.8124576844955992, | |
| "eval_loss": 0.8165345191955566, | |
| "eval_runtime": 182.8879, | |
| "eval_samples_per_second": 57.412, | |
| "eval_steps_per_second": 0.902, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.8259986459038592, | |
| "grad_norm": 3.596321476724727, | |
| "learning_rate": 8.319321717343535e-07, | |
| "loss": 0.8149, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.8395396073121192, | |
| "grad_norm": 3.7225323914645747, | |
| "learning_rate": 8.265440659668234e-07, | |
| "loss": 0.8124, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.8530805687203792, | |
| "grad_norm": 3.5663300158516016, | |
| "learning_rate": 8.210890086124977e-07, | |
| "loss": 0.7906, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.8666215301286392, | |
| "grad_norm": 3.4256587260000604, | |
| "learning_rate": 8.155681181260776e-07, | |
| "loss": 0.81, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.8801624915368991, | |
| "grad_norm": 3.4929314527584077, | |
| "learning_rate": 8.099825264600842e-07, | |
| "loss": 0.818, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.8937034529451591, | |
| "grad_norm": 3.5559616159997742, | |
| "learning_rate": 8.04333378832772e-07, | |
| "loss": 0.8067, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.9072444143534191, | |
| "grad_norm": 3.3786924383796544, | |
| "learning_rate": 7.98621833493324e-07, | |
| "loss": 0.802, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.9207853757616791, | |
| "grad_norm": 3.6281675631205377, | |
| "learning_rate": 7.928490614843757e-07, | |
| "loss": 0.7991, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.9343263371699391, | |
| "grad_norm": 3.5783671775239068, | |
| "learning_rate": 7.870162464019143e-07, | |
| "loss": 0.7961, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.9478672985781991, | |
| "grad_norm": 3.523112182862875, | |
| "learning_rate": 7.811245841526062e-07, | |
| "loss": 0.7997, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.9478672985781991, | |
| "eval_loss": 0.8075853586196899, | |
| "eval_runtime": 182.8371, | |
| "eval_samples_per_second": 57.428, | |
| "eval_steps_per_second": 0.902, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.9614082599864591, | |
| "grad_norm": 3.327823061584991, | |
| "learning_rate": 7.75175282708598e-07, | |
| "loss": 0.7955, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.9749492213947191, | |
| "grad_norm": 3.353254883691996, | |
| "learning_rate": 7.691695618598466e-07, | |
| "loss": 0.7945, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.988490182802979, | |
| "grad_norm": 3.4573365027199547, | |
| "learning_rate": 7.631086529640229e-07, | |
| "loss": 0.8037, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 1.002031144211239, | |
| "grad_norm": 3.704603819142361, | |
| "learning_rate": 7.569937986940475e-07, | |
| "loss": 0.7833, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.015572105619499, | |
| "grad_norm": 3.338765249405955, | |
| "learning_rate": 7.508262527833028e-07, | |
| "loss": 0.736, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.029113067027759, | |
| "grad_norm": 3.5005014577141154, | |
| "learning_rate": 7.446072797685799e-07, | |
| "loss": 0.7393, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.042654028436019, | |
| "grad_norm": 3.5415652623772753, | |
| "learning_rate": 7.383381547308099e-07, | |
| "loss": 0.7461, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.0561949898442788, | |
| "grad_norm": 3.430934641227424, | |
| "learning_rate": 7.320201630336318e-07, | |
| "loss": 0.7359, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.0697359512525388, | |
| "grad_norm": 3.6468766296195896, | |
| "learning_rate": 7.256546000598551e-07, | |
| "loss": 0.7306, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.0832769126607988, | |
| "grad_norm": 4.055674159253643, | |
| "learning_rate": 7.192427709458655e-07, | |
| "loss": 0.7335, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0832769126607988, | |
| "eval_loss": 0.804972231388092, | |
| "eval_runtime": 182.8412, | |
| "eval_samples_per_second": 57.427, | |
| "eval_steps_per_second": 0.902, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0968178740690588, | |
| "grad_norm": 3.7131013971600244, | |
| "learning_rate": 7.127859903140311e-07, | |
| "loss": 0.7346, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.1103588354773188, | |
| "grad_norm": 3.496845579088122, | |
| "learning_rate": 7.062855820031659e-07, | |
| "loss": 0.7409, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.1238997968855788, | |
| "grad_norm": 3.652963743841258, | |
| "learning_rate": 6.997428787971005e-07, | |
| "loss": 0.7236, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.1374407582938388, | |
| "grad_norm": 3.6316016258989916, | |
| "learning_rate": 6.93159222151422e-07, | |
| "loss": 0.734, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.1509817197020988, | |
| "grad_norm": 4.106556416672479, | |
| "learning_rate": 6.86535961918433e-07, | |
| "loss": 0.7425, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.1645226811103588, | |
| "grad_norm": 3.4406596945092764, | |
| "learning_rate": 6.798744560703904e-07, | |
| "loss": 0.7271, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.1780636425186188, | |
| "grad_norm": 3.5644142212223886, | |
| "learning_rate": 6.731760704210802e-07, | |
| "loss": 0.729, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.1916046039268788, | |
| "grad_norm": 3.5207779341108316, | |
| "learning_rate": 6.66442178345783e-07, | |
| "loss": 0.7295, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.2051455653351388, | |
| "grad_norm": 3.8426763234364643, | |
| "learning_rate": 6.596741604996897e-07, | |
| "loss": 0.7285, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 1.2186865267433988, | |
| "grad_norm": 3.537416567969802, | |
| "learning_rate": 6.528734045348248e-07, | |
| "loss": 0.7466, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.2186865267433988, | |
| "eval_loss": 0.7996942400932312, | |
| "eval_runtime": 182.8629, | |
| "eval_samples_per_second": 57.42, | |
| "eval_steps_per_second": 0.902, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.2322274881516588, | |
| "grad_norm": 3.5566566741869603, | |
| "learning_rate": 6.460413048155354e-07, | |
| "loss": 0.7291, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.2457684495599188, | |
| "grad_norm": 3.6983928953608323, | |
| "learning_rate": 6.391792621326027e-07, | |
| "loss": 0.7502, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.2593094109681786, | |
| "grad_norm": 3.679881191981186, | |
| "learning_rate": 6.322886834160377e-07, | |
| "loss": 0.7375, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.2728503723764386, | |
| "grad_norm": 3.635647992456833, | |
| "learning_rate": 6.253709814466167e-07, | |
| "loss": 0.7446, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.2863913337846986, | |
| "grad_norm": 3.7784368285832675, | |
| "learning_rate": 6.184275745662179e-07, | |
| "loss": 0.7307, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.2999322951929586, | |
| "grad_norm": 3.975716487359526, | |
| "learning_rate": 6.114598863870178e-07, | |
| "loss": 0.727, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.3134732566012186, | |
| "grad_norm": 3.8898112879763818, | |
| "learning_rate": 6.044693454996059e-07, | |
| "loss": 0.7351, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 1.3270142180094786, | |
| "grad_norm": 3.883701681898452, | |
| "learning_rate": 5.974573851800817e-07, | |
| "loss": 0.7376, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.3405551794177386, | |
| "grad_norm": 3.5463439014644695, | |
| "learning_rate": 5.904254430961869e-07, | |
| "loss": 0.7413, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 1.3540961408259986, | |
| "grad_norm": 3.5029550543033374, | |
| "learning_rate": 5.833749610125401e-07, | |
| "loss": 0.7264, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.3540961408259986, | |
| "eval_loss": 0.7957150340080261, | |
| "eval_runtime": 182.9392, | |
| "eval_samples_per_second": 57.396, | |
| "eval_steps_per_second": 0.902, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.3676371022342586, | |
| "grad_norm": 3.9766897722099124, | |
| "learning_rate": 5.763073844950309e-07, | |
| "loss": 0.7327, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 1.3811780636425186, | |
| "grad_norm": 3.80954804006231, | |
| "learning_rate": 5.69224162614434e-07, | |
| "loss": 0.7443, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.3947190250507786, | |
| "grad_norm": 3.524183540063996, | |
| "learning_rate": 5.621267476493052e-07, | |
| "loss": 0.7345, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 1.4082599864590386, | |
| "grad_norm": 3.620522282934874, | |
| "learning_rate": 5.550165947882196e-07, | |
| "loss": 0.7236, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.4218009478672986, | |
| "grad_norm": 3.768208934721801, | |
| "learning_rate": 5.478951618314132e-07, | |
| "loss": 0.7165, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.4353419092755586, | |
| "grad_norm": 3.5182066154018345, | |
| "learning_rate": 5.407639088918888e-07, | |
| "loss": 0.7297, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.4488828706838186, | |
| "grad_norm": 3.824867160497226, | |
| "learning_rate": 5.33624298096048e-07, | |
| "loss": 0.7307, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 1.4624238320920786, | |
| "grad_norm": 3.488297423659722, | |
| "learning_rate": 5.264777932839104e-07, | |
| "loss": 0.7487, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.4759647935003386, | |
| "grad_norm": 3.493644177453455, | |
| "learning_rate": 5.193258597089809e-07, | |
| "loss": 0.7291, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 1.4895057549085986, | |
| "grad_norm": 3.6179715470055824, | |
| "learning_rate": 5.121699637378282e-07, | |
| "loss": 0.7286, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.4895057549085986, | |
| "eval_loss": 0.7910673022270203, | |
| "eval_runtime": 182.8784, | |
| "eval_samples_per_second": 57.415, | |
| "eval_steps_per_second": 0.902, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.5030467163168586, | |
| "grad_norm": 3.5922430809215777, | |
| "learning_rate": 5.050115725494339e-07, | |
| "loss": 0.7179, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 1.5165876777251186, | |
| "grad_norm": 3.4032672519789786, | |
| "learning_rate": 4.978521538343764e-07, | |
| "loss": 0.7366, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.5301286391333786, | |
| "grad_norm": 3.6567954327498327, | |
| "learning_rate": 4.906931754939083e-07, | |
| "loss": 0.7391, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 1.5436696005416386, | |
| "grad_norm": 3.5644839916468243, | |
| "learning_rate": 4.835361053389921e-07, | |
| "loss": 0.7288, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.5572105619498986, | |
| "grad_norm": 3.650299513434273, | |
| "learning_rate": 4.763824107893532e-07, | |
| "loss": 0.729, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.5707515233581584, | |
| "grad_norm": 3.8055072261605116, | |
| "learning_rate": 4.692335585726145e-07, | |
| "loss": 0.7177, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.5842924847664184, | |
| "grad_norm": 3.5985047420048697, | |
| "learning_rate": 4.6209101442357116e-07, | |
| "loss": 0.7224, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 1.5978334461746784, | |
| "grad_norm": 3.547274876419971, | |
| "learning_rate": 4.549562427836701e-07, | |
| "loss": 0.7327, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.6113744075829384, | |
| "grad_norm": 3.511159114275773, | |
| "learning_rate": 4.4783070650075537e-07, | |
| "loss": 0.7406, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 1.6249153689911984, | |
| "grad_norm": 3.46127753253687, | |
| "learning_rate": 4.407158665291376e-07, | |
| "loss": 0.7251, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.6249153689911984, | |
| "eval_loss": 0.7875649333000183, | |
| "eval_runtime": 182.8944, | |
| "eval_samples_per_second": 57.41, | |
| "eval_steps_per_second": 0.902, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.6384563303994584, | |
| "grad_norm": 3.409510769647259, | |
| "learning_rate": 4.336131816300548e-07, | |
| "loss": 0.719, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 1.6519972918077184, | |
| "grad_norm": 3.5447361212717925, | |
| "learning_rate": 4.265241080725808e-07, | |
| "loss": 0.7287, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.6655382532159784, | |
| "grad_norm": 4.059666587103208, | |
| "learning_rate": 4.194500993350453e-07, | |
| "loss": 0.7399, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 1.6790792146242384, | |
| "grad_norm": 3.774832103683009, | |
| "learning_rate": 4.1239260580702634e-07, | |
| "loss": 0.7386, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.6926201760324981, | |
| "grad_norm": 3.5490582421055885, | |
| "learning_rate": 4.053530744919749e-07, | |
| "loss": 0.7246, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.7061611374407581, | |
| "grad_norm": 3.747116763144729, | |
| "learning_rate": 3.983329487105363e-07, | |
| "loss": 0.7372, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.7197020988490181, | |
| "grad_norm": 3.4822384940575795, | |
| "learning_rate": 3.913336678046232e-07, | |
| "loss": 0.7323, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 1.7332430602572781, | |
| "grad_norm": 3.825022969793332, | |
| "learning_rate": 3.8435666684230726e-07, | |
| "loss": 0.7097, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.7467840216655381, | |
| "grad_norm": 3.696972226883697, | |
| "learning_rate": 3.774033763235861e-07, | |
| "loss": 0.7304, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 1.7603249830737981, | |
| "grad_norm": 3.821368374115622, | |
| "learning_rate": 3.7047522188708606e-07, | |
| "loss": 0.727, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.7603249830737981, | |
| "eval_loss": 0.7839689254760742, | |
| "eval_runtime": 182.875, | |
| "eval_samples_per_second": 57.416, | |
| "eval_steps_per_second": 0.902, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.7738659444820581, | |
| "grad_norm": 3.665010892266409, | |
| "learning_rate": 3.635736240177627e-07, | |
| "loss": 0.7223, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 1.7874069058903181, | |
| "grad_norm": 3.8705676996293916, | |
| "learning_rate": 3.5669999775565816e-07, | |
| "loss": 0.7313, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.8009478672985781, | |
| "grad_norm": 3.5842111135660057, | |
| "learning_rate": 3.4985575240577365e-07, | |
| "loss": 0.7321, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 1.8144888287068381, | |
| "grad_norm": 3.4424140077908767, | |
| "learning_rate": 3.4304229124911856e-07, | |
| "loss": 0.7316, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.8280297901150981, | |
| "grad_norm": 3.4068267304866646, | |
| "learning_rate": 3.362610112549955e-07, | |
| "loss": 0.704, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.8415707515233581, | |
| "grad_norm": 3.685081317112416, | |
| "learning_rate": 3.295133027945778e-07, | |
| "loss": 0.7167, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.8551117129316181, | |
| "grad_norm": 3.7176624860947345, | |
| "learning_rate": 3.228005493558402e-07, | |
| "loss": 0.7094, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 1.8686526743398781, | |
| "grad_norm": 3.718001701556429, | |
| "learning_rate": 3.1612412725990305e-07, | |
| "loss": 0.7312, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.8821936357481381, | |
| "grad_norm": 3.491455379714816, | |
| "learning_rate": 3.0948540537884185e-07, | |
| "loss": 0.7264, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 1.8957345971563981, | |
| "grad_norm": 3.7382317800607376, | |
| "learning_rate": 3.0288574485502756e-07, | |
| "loss": 0.7277, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.8957345971563981, | |
| "eval_loss": 0.7811039090156555, | |
| "eval_runtime": 182.9386, | |
| "eval_samples_per_second": 57.396, | |
| "eval_steps_per_second": 0.902, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.9092755585646581, | |
| "grad_norm": 3.4296946924569442, | |
| "learning_rate": 2.9632649882205083e-07, | |
| "loss": 0.7287, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 1.9228165199729181, | |
| "grad_norm": 3.810691598305239, | |
| "learning_rate": 2.8980901212728723e-07, | |
| "loss": 0.7193, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.9363574813811781, | |
| "grad_norm": 3.3584278752072496, | |
| "learning_rate": 2.833346210561619e-07, | |
| "loss": 0.7112, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 1.9498984427894381, | |
| "grad_norm": 3.5743899932997185, | |
| "learning_rate": 2.769046530581708e-07, | |
| "loss": 0.7235, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.9634394041976981, | |
| "grad_norm": 3.8331759574897375, | |
| "learning_rate": 2.705204264747125e-07, | |
| "loss": 0.724, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.9769803656059581, | |
| "grad_norm": 3.6084594988279908, | |
| "learning_rate": 2.6418325026878665e-07, | |
| "loss": 0.7156, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.9905213270142181, | |
| "grad_norm": 3.56873955236049, | |
| "learning_rate": 2.578944237566174e-07, | |
| "loss": 0.7163, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 2.004062288422478, | |
| "grad_norm": 4.103162581101771, | |
| "learning_rate": 2.5165523634125337e-07, | |
| "loss": 0.7161, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.017603249830738, | |
| "grad_norm": 3.7064092978900844, | |
| "learning_rate": 2.454669672481996e-07, | |
| "loss": 0.6754, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 2.031144211238998, | |
| "grad_norm": 3.6900542156905196, | |
| "learning_rate": 2.393308852631373e-07, | |
| "loss": 0.6724, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.031144211238998, | |
| "eval_loss": 0.7857776880264282, | |
| "eval_runtime": 183.0378, | |
| "eval_samples_per_second": 57.365, | |
| "eval_steps_per_second": 0.901, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.044685172647258, | |
| "grad_norm": 3.5536516436485255, | |
| "learning_rate": 2.3324824847178494e-07, | |
| "loss": 0.6887, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 2.058226134055518, | |
| "grad_norm": 3.7965121612299564, | |
| "learning_rate": 2.2722030400194975e-07, | |
| "loss": 0.666, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.071767095463778, | |
| "grad_norm": 3.7936989153822007, | |
| "learning_rate": 2.2124828776782955e-07, | |
| "loss": 0.6789, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 2.085308056872038, | |
| "grad_norm": 3.5401816973807043, | |
| "learning_rate": 2.1533342421661228e-07, | |
| "loss": 0.6665, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.0988490182802977, | |
| "grad_norm": 3.7787164350636555, | |
| "learning_rate": 2.0947692607742618e-07, | |
| "loss": 0.6755, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 2.1123899796885577, | |
| "grad_norm": 3.9382718196335267, | |
| "learning_rate": 2.0367999411269282e-07, | |
| "loss": 0.6821, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.1259309410968177, | |
| "grad_norm": 3.8112238429444782, | |
| "learning_rate": 1.9794381687193456e-07, | |
| "loss": 0.6805, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 2.1394719025050777, | |
| "grad_norm": 3.8744335724512204, | |
| "learning_rate": 1.9226957044808494e-07, | |
| "loss": 0.6657, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.1530128639133377, | |
| "grad_norm": 3.7804638456283346, | |
| "learning_rate": 1.866584182363528e-07, | |
| "loss": 0.6789, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 2.1665538253215977, | |
| "grad_norm": 3.8021451485147963, | |
| "learning_rate": 1.811115106956918e-07, | |
| "loss": 0.6883, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.1665538253215977, | |
| "eval_loss": 0.7850033044815063, | |
| "eval_runtime": 182.9949, | |
| "eval_samples_per_second": 57.379, | |
| "eval_steps_per_second": 0.902, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.1800947867298577, | |
| "grad_norm": 3.864215108703362, | |
| "learning_rate": 1.7562998511291943e-07, | |
| "loss": 0.6811, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 2.1936357481381177, | |
| "grad_norm": 3.8300913859664667, | |
| "learning_rate": 1.702149653695395e-07, | |
| "loss": 0.6766, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.2071767095463777, | |
| "grad_norm": 3.8635188226813666, | |
| "learning_rate": 1.6486756171131062e-07, | |
| "loss": 0.675, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 2.2207176709546377, | |
| "grad_norm": 3.9283113465457355, | |
| "learning_rate": 1.595888705206128e-07, | |
| "loss": 0.6678, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.2342586323628977, | |
| "grad_norm": 3.726732058605602, | |
| "learning_rate": 1.5437997409165476e-07, | |
| "loss": 0.6733, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 2.2477995937711577, | |
| "grad_norm": 3.6073721199402318, | |
| "learning_rate": 1.4924194040856973e-07, | |
| "loss": 0.6794, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.2613405551794177, | |
| "grad_norm": 3.920320006141431, | |
| "learning_rate": 1.4417582292644691e-07, | |
| "loss": 0.6871, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 2.2748815165876777, | |
| "grad_norm": 3.781911882917061, | |
| "learning_rate": 1.3918266035534027e-07, | |
| "loss": 0.6774, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.2884224779959377, | |
| "grad_norm": 4.013058729107201, | |
| "learning_rate": 1.3426347644730047e-07, | |
| "loss": 0.6816, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 2.3019634394041977, | |
| "grad_norm": 3.776810144116961, | |
| "learning_rate": 1.2941927978647526e-07, | |
| "loss": 0.6709, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.3019634394041977, | |
| "eval_loss": 0.7840232253074646, | |
| "eval_runtime": 182.9773, | |
| "eval_samples_per_second": 57.384, | |
| "eval_steps_per_second": 0.902, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.3155044008124577, | |
| "grad_norm": 4.0267886200903344, | |
| "learning_rate": 1.2465106358231753e-07, | |
| "loss": 0.6765, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 2.3290453622207177, | |
| "grad_norm": 3.79514301881657, | |
| "learning_rate": 1.1995980546594775e-07, | |
| "loss": 0.6633, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.3425863236289777, | |
| "grad_norm": 3.7026026349952086, | |
| "learning_rate": 1.153464672897091e-07, | |
| "loss": 0.678, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 2.3561272850372377, | |
| "grad_norm": 3.977299316585606, | |
| "learning_rate": 1.108119949299578e-07, | |
| "loss": 0.6875, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.3696682464454977, | |
| "grad_norm": 3.9505974017459544, | |
| "learning_rate": 1.0635731809312992e-07, | |
| "loss": 0.6955, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 2.3832092078537577, | |
| "grad_norm": 3.9944161998447116, | |
| "learning_rate": 1.0198335012512271e-07, | |
| "loss": 0.6843, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.3967501692620177, | |
| "grad_norm": 4.08644897660094, | |
| "learning_rate": 9.769098782403041e-08, | |
| "loss": 0.7081, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 2.4102911306702777, | |
| "grad_norm": 4.033807984306314, | |
| "learning_rate": 9.348111125627278e-08, | |
| "loss": 0.6758, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.4238320920785377, | |
| "grad_norm": 3.615156557294799, | |
| "learning_rate": 8.935458357615583e-08, | |
| "loss": 0.6718, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 2.4373730534867977, | |
| "grad_norm": 3.876477554855966, | |
| "learning_rate": 8.531225084889654e-08, | |
| "loss": 0.6598, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.4373730534867977, | |
| "eval_loss": 0.7834283113479614, | |
| "eval_runtime": 183.0709, | |
| "eval_samples_per_second": 57.355, | |
| "eval_steps_per_second": 0.901, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.4509140148950577, | |
| "grad_norm": 3.6988949380997336, | |
| "learning_rate": 8.135494187715475e-08, | |
| "loss": 0.6603, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 2.4644549763033177, | |
| "grad_norm": 3.931452073089016, | |
| "learning_rate": 7.748346803110295e-08, | |
| "loss": 0.6832, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.4779959377115777, | |
| "grad_norm": 3.8160191178139047, | |
| "learning_rate": 7.369862308207025e-08, | |
| "loss": 0.6583, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 2.4915368991198377, | |
| "grad_norm": 3.8469114382677874, | |
| "learning_rate": 7.000118303979463e-08, | |
| "loss": 0.6808, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.5050778605280977, | |
| "grad_norm": 3.7497256852290115, | |
| "learning_rate": 6.639190599331746e-08, | |
| "loss": 0.6762, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 2.518618821936357, | |
| "grad_norm": 3.663314489242292, | |
| "learning_rate": 6.287153195555173e-08, | |
| "loss": 0.6663, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.5321597833446177, | |
| "grad_norm": 3.8930436232018333, | |
| "learning_rate": 5.944078271155639e-08, | |
| "loss": 0.6648, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 2.545700744752877, | |
| "grad_norm": 3.6616608952378904, | |
| "learning_rate": 5.610036167054838e-08, | |
| "loss": 0.6596, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.5592417061611377, | |
| "grad_norm": 3.986331709466641, | |
| "learning_rate": 5.2850953721682635e-08, | |
| "loss": 0.669, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 2.572782667569397, | |
| "grad_norm": 3.960581833122488, | |
| "learning_rate": 4.969322509362761e-08, | |
| "loss": 0.674, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.572782667569397, | |
| "eval_loss": 0.7830283641815186, | |
| "eval_runtime": 182.8342, | |
| "eval_samples_per_second": 57.429, | |
| "eval_steps_per_second": 0.902, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.5863236289776577, | |
| "grad_norm": 3.8618441431288217, | |
| "learning_rate": 4.662782321796849e-08, | |
| "loss": 0.6713, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 2.599864590385917, | |
| "grad_norm": 3.5409233232724335, | |
| "learning_rate": 4.365537659646418e-08, | |
| "loss": 0.6747, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.6134055517941777, | |
| "grad_norm": 3.744738202206873, | |
| "learning_rate": 4.0776494672184356e-08, | |
| "loss": 0.6846, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 2.626946513202437, | |
| "grad_norm": 3.727245201869487, | |
| "learning_rate": 3.799176770455526e-08, | |
| "loss": 0.6616, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.640487474610697, | |
| "grad_norm": 3.7258573002382147, | |
| "learning_rate": 3.530176664833834e-08, | |
| "loss": 0.675, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 2.654028436018957, | |
| "grad_norm": 3.869690791825916, | |
| "learning_rate": 3.270704303656696e-08, | |
| "loss": 0.6875, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.667569397427217, | |
| "grad_norm": 4.064616477774205, | |
| "learning_rate": 3.020812886746477e-08, | |
| "loss": 0.6808, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 2.681110358835477, | |
| "grad_norm": 3.704371552936023, | |
| "learning_rate": 2.7805536495370373e-08, | |
| "loss": 0.6687, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.694651320243737, | |
| "grad_norm": 4.055603563401218, | |
| "learning_rate": 2.5499758525688197e-08, | |
| "loss": 0.6584, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 2.708192281651997, | |
| "grad_norm": 3.749384489878185, | |
| "learning_rate": 2.329126771388995e-08, | |
| "loss": 0.656, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.708192281651997, | |
| "eval_loss": 0.7828182578086853, | |
| "eval_runtime": 182.6838, | |
| "eval_samples_per_second": 57.476, | |
| "eval_steps_per_second": 0.903, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.721733243060257, | |
| "grad_norm": 3.869599930871293, | |
| "learning_rate": 2.1180516868584464e-08, | |
| "loss": 0.6716, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 2.735274204468517, | |
| "grad_norm": 3.930506514677681, | |
| "learning_rate": 1.916793875867839e-08, | |
| "loss": 0.6822, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.748815165876777, | |
| "grad_norm": 3.8320813018837616, | |
| "learning_rate": 1.7253946024645472e-08, | |
| "loss": 0.6627, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 2.762356127285037, | |
| "grad_norm": 3.986150848206186, | |
| "learning_rate": 1.5438931093921804e-08, | |
| "loss": 0.6727, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.775897088693297, | |
| "grad_norm": 3.764718626888124, | |
| "learning_rate": 1.372326610044705e-08, | |
| "loss": 0.6618, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 2.789438050101557, | |
| "grad_norm": 3.7384921853849393, | |
| "learning_rate": 1.2107302808364638e-08, | |
| "loss": 0.6614, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.802979011509817, | |
| "grad_norm": 3.8134941063063867, | |
| "learning_rate": 1.0591372539900056e-08, | |
| "loss": 0.6665, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 2.816519972918077, | |
| "grad_norm": 3.7735093872780197, | |
| "learning_rate": 9.175786107429085e-09, | |
| "loss": 0.6643, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.830060934326337, | |
| "grad_norm": 3.987550484105897, | |
| "learning_rate": 7.860833749751772e-09, | |
| "loss": 0.6739, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 2.843601895734597, | |
| "grad_norm": 3.9380769036431893, | |
| "learning_rate": 6.6467850725848705e-09, | |
| "loss": 0.6741, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.843601895734597, | |
| "eval_loss": 0.7824584245681763, | |
| "eval_runtime": 183.0944, | |
| "eval_samples_per_second": 57.347, | |
| "eval_steps_per_second": 0.901, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 4.011659897593238, | |
| "learning_rate": 5.5338889932838306e-09, | |
| "loss": 0.6842, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 2.870683818551117, | |
| "grad_norm": 3.808051194891409, | |
| "learning_rate": 4.5223736898076235e-09, | |
| "loss": 0.6806, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.884224779959377, | |
| "grad_norm": 3.8839001927108856, | |
| "learning_rate": 3.612446553934723e-09, | |
| "loss": 0.6679, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 2.897765741367637, | |
| "grad_norm": 3.9713825006231054, | |
| "learning_rate": 2.804294148741948e-09, | |
| "loss": 0.6733, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.911306702775897, | |
| "grad_norm": 3.783696934827739, | |
| "learning_rate": 2.0980821703527886e-09, | |
| "loss": 0.6736, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 2.924847664184157, | |
| "grad_norm": 3.770344601359413, | |
| "learning_rate": 1.4939554139648536e-09, | |
| "loss": 0.6649, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.938388625592417, | |
| "grad_norm": 3.8357523688679565, | |
| "learning_rate": 9.920377441623994e-10, | |
| "loss": 0.6718, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 2.951929587000677, | |
| "grad_norm": 4.03615476407359, | |
| "learning_rate": 5.92432069520199e-10, | |
| "loss": 0.6805, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.9654705484089368, | |
| "grad_norm": 3.8321791456875283, | |
| "learning_rate": 2.9522032150419705e-10, | |
| "loss": 0.6629, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 2.979011509817197, | |
| "grad_norm": 3.9373632743696056, | |
| "learning_rate": 1.0046343767294852e-10, | |
| "loss": 0.6592, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.979011509817197, | |
| "eval_loss": 0.7824262976646423, | |
| "eval_runtime": 182.8708, | |
| "eval_samples_per_second": 57.418, | |
| "eval_steps_per_second": 0.902, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.9925524712254568, | |
| "grad_norm": 3.6875439191522075, | |
| "learning_rate": 8.201349183611927e-12, | |
| "loss": 0.6534, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 2.997968855788761, | |
| "step": 1107, | |
| "total_flos": 6527139780231168.0, | |
| "train_loss": 0.7629147509572306, | |
| "train_runtime": 18558.2767, | |
| "train_samples_per_second": 15.276, | |
| "train_steps_per_second": 0.06 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1107, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 10000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6527139780231168.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |