| { | |
| "best_metric": 1.3216674327850342, | |
| "best_model_checkpoint": "model_training/reprover_proving/checkpoints-random-09-08-17-37/checkpoint-425", | |
| "epoch": 6.896551724137931, | |
| "eval_steps": 25, | |
| "global_step": 425, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08113590263691683, | |
| "grad_norm": 23.381454467773438, | |
| "learning_rate": 5.102040816326531e-05, | |
| "loss": 13.7285, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.16227180527383367, | |
| "grad_norm": 14.872354507446289, | |
| "learning_rate": 0.00010204081632653062, | |
| "loss": 8.8328, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2434077079107505, | |
| "grad_norm": 0.6985018849372864, | |
| "learning_rate": 0.00015306122448979594, | |
| "loss": 4.2009, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.32454361054766734, | |
| "grad_norm": 0.24331903457641602, | |
| "learning_rate": 0.00020408163265306123, | |
| "loss": 3.7482, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4056795131845842, | |
| "grad_norm": 0.22634823620319366, | |
| "learning_rate": 0.00025510204081632655, | |
| "loss": 3.6305, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4056795131845842, | |
| "eval_loss": 3.498396396636963, | |
| "eval_runtime": 42.1381, | |
| "eval_samples_per_second": 23.732, | |
| "eval_steps_per_second": 1.495, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.486815415821501, | |
| "grad_norm": 0.8556441068649292, | |
| "learning_rate": 0.0003061224489795919, | |
| "loss": 3.5821, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5679513184584178, | |
| "grad_norm": 1.5031307935714722, | |
| "learning_rate": 0.00035714285714285714, | |
| "loss": 2.8239, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6490872210953347, | |
| "grad_norm": 0.7835573554039001, | |
| "learning_rate": 0.00040816326530612246, | |
| "loss": 2.158, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7302231237322515, | |
| "grad_norm": 0.49232250452041626, | |
| "learning_rate": 0.0004591836734693878, | |
| "loss": 1.8947, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8113590263691683, | |
| "grad_norm": 0.5629563331604004, | |
| "learning_rate": 0.0004999935985425297, | |
| "loss": 1.7676, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8113590263691683, | |
| "eval_loss": 1.5309563875198364, | |
| "eval_runtime": 41.744, | |
| "eval_samples_per_second": 23.956, | |
| "eval_steps_per_second": 1.509, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8924949290060852, | |
| "grad_norm": 2.9327845573425293, | |
| "learning_rate": 0.0004997695819512612, | |
| "loss": 1.7081, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.973630831643002, | |
| "grad_norm": 0.5285796523094177, | |
| "learning_rate": 0.0004992258202402822, | |
| "loss": 1.6423, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.054766734279919, | |
| "grad_norm": 0.27397045493125916, | |
| "learning_rate": 0.0004983630095117843, | |
| "loss": 1.5808, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.1359026369168357, | |
| "grad_norm": 0.19275762140750885, | |
| "learning_rate": 0.0004971822543018662, | |
| "loss": 1.5512, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.2170385395537526, | |
| "grad_norm": 0.24138106405735016, | |
| "learning_rate": 0.0004956850661665511, | |
| "loss": 1.5823, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.2170385395537526, | |
| "eval_loss": 1.4183236360549927, | |
| "eval_runtime": 41.7019, | |
| "eval_samples_per_second": 23.98, | |
| "eval_steps_per_second": 1.511, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.2981744421906694, | |
| "grad_norm": 0.27136123180389404, | |
| "learning_rate": 0.0004938733617467517, | |
| "loss": 1.5641, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3793103448275863, | |
| "grad_norm": 0.17292170226573944, | |
| "learning_rate": 0.0004917494603146632, | |
| "loss": 1.532, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.460446247464503, | |
| "grad_norm": 0.3078462481498718, | |
| "learning_rate": 0.0004893160808047222, | |
| "loss": 1.5332, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.5415821501014197, | |
| "grad_norm": 0.21065960824489594, | |
| "learning_rate": 0.00048657633833293557, | |
| "loss": 1.5567, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.6227180527383367, | |
| "grad_norm": 0.3646738827228546, | |
| "learning_rate": 0.0004835337402090316, | |
| "loss": 1.5243, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6227180527383367, | |
| "eval_loss": 1.4111393690109253, | |
| "eval_runtime": 41.9674, | |
| "eval_samples_per_second": 23.828, | |
| "eval_steps_per_second": 1.501, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.7038539553752536, | |
| "grad_norm": 1.1830989122390747, | |
| "learning_rate": 0.0004801921814465414, | |
| "loss": 1.5343, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.7849898580121704, | |
| "grad_norm": 0.285373717546463, | |
| "learning_rate": 0.00047655593977655674, | |
| "loss": 1.5254, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.866125760649087, | |
| "grad_norm": 0.27493494749069214, | |
| "learning_rate": 0.0004726296701715489, | |
| "loss": 1.5083, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.947261663286004, | |
| "grad_norm": 0.16316387057304382, | |
| "learning_rate": 0.00046841839888625623, | |
| "loss": 1.4953, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.028397565922921, | |
| "grad_norm": 0.1423080563545227, | |
| "learning_rate": 0.0004639275170232734, | |
| "loss": 1.5183, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.028397565922921, | |
| "eval_loss": 1.3866875171661377, | |
| "eval_runtime": 41.7133, | |
| "eval_samples_per_second": 23.973, | |
| "eval_steps_per_second": 1.51, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.109533468559838, | |
| "grad_norm": 0.11375881731510162, | |
| "learning_rate": 0.0004591627736315743, | |
| "loss": 1.4912, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.1906693711967544, | |
| "grad_norm": 0.18000248074531555, | |
| "learning_rate": 0.0004541302683468084, | |
| "loss": 1.4759, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.2718052738336714, | |
| "grad_norm": 0.2928003668785095, | |
| "learning_rate": 0.0004488364435827881, | |
| "loss": 1.4897, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.2769507169723511, | |
| "learning_rate": 0.00044328807628416644, | |
| "loss": 1.5346, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.4340770791075053, | |
| "grad_norm": 0.3308449685573578, | |
| "learning_rate": 0.0004374922692508611, | |
| "loss": 1.5186, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.4340770791075053, | |
| "eval_loss": 1.394946813583374, | |
| "eval_runtime": 41.7538, | |
| "eval_samples_per_second": 23.95, | |
| "eval_steps_per_second": 1.509, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.5152129817444218, | |
| "grad_norm": 0.6130169034004211, | |
| "learning_rate": 0.0004314564420453311, | |
| "loss": 1.5019, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.5963488843813387, | |
| "grad_norm": 0.2663266062736511, | |
| "learning_rate": 0.0004251883214943475, | |
| "loss": 1.4881, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.6774847870182557, | |
| "grad_norm": 0.20422033965587616, | |
| "learning_rate": 0.0004186959317974155, | |
| "loss": 1.4864, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.7586206896551726, | |
| "grad_norm": 0.1979188621044159, | |
| "learning_rate": 0.00041198758425451266, | |
| "loss": 1.4771, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.839756592292089, | |
| "grad_norm": 0.11998000741004944, | |
| "learning_rate": 0.00040507186662629185, | |
| "loss": 1.486, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.839756592292089, | |
| "eval_loss": 1.363732933998108, | |
| "eval_runtime": 42.0053, | |
| "eval_samples_per_second": 23.807, | |
| "eval_steps_per_second": 1.5, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.920892494929006, | |
| "grad_norm": 0.48267611861228943, | |
| "learning_rate": 0.0003979576321403705, | |
| "loss": 1.4653, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.002028397565923, | |
| "grad_norm": 0.9161086082458496, | |
| "learning_rate": 0.0003906539881577793, | |
| "loss": 1.5062, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 3.08316430020284, | |
| "grad_norm": 0.3533921241760254, | |
| "learning_rate": 0.0003831702845140801, | |
| "loss": 1.5027, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.1643002028397564, | |
| "grad_norm": 0.3786797821521759, | |
| "learning_rate": 0.00037551610155007613, | |
| "loss": 1.5009, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 3.2454361054766734, | |
| "grad_norm": 0.3626890778541565, | |
| "learning_rate": 0.00036770123784744027, | |
| "loss": 1.4689, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.2454361054766734, | |
| "eval_loss": 1.3820106983184814, | |
| "eval_runtime": 41.9752, | |
| "eval_samples_per_second": 23.824, | |
| "eval_steps_per_second": 1.501, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.3265720081135903, | |
| "grad_norm": 0.5597763657569885, | |
| "learning_rate": 0.00035973569768495855, | |
| "loss": 1.4783, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 3.4077079107505073, | |
| "grad_norm": 0.22316162288188934, | |
| "learning_rate": 0.0003516296782314491, | |
| "loss": 1.458, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.4888438133874238, | |
| "grad_norm": 0.2465822696685791, | |
| "learning_rate": 0.00034339355649175095, | |
| "loss": 1.4803, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 3.5699797160243407, | |
| "grad_norm": 0.1777486950159073, | |
| "learning_rate": 0.00033503787602249364, | |
| "loss": 1.4493, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.6511156186612577, | |
| "grad_norm": 0.12559564411640167, | |
| "learning_rate": 0.00032657333343465356, | |
| "loss": 1.4349, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.6511156186612577, | |
| "eval_loss": 1.344743251800537, | |
| "eval_runtime": 41.8458, | |
| "eval_samples_per_second": 23.897, | |
| "eval_steps_per_second": 1.506, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.732251521298174, | |
| "grad_norm": 0.1277971714735031, | |
| "learning_rate": 0.0003180107647001769, | |
| "loss": 1.4245, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.813387423935091, | |
| "grad_norm": 0.13526912033557892, | |
| "learning_rate": 0.0003093611312801979, | |
| "loss": 1.4433, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 3.894523326572008, | |
| "grad_norm": 0.16969378292560577, | |
| "learning_rate": 0.00030063550609261025, | |
| "loss": 1.4468, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.975659229208925, | |
| "grad_norm": 0.12927880883216858, | |
| "learning_rate": 0.000291845059336957, | |
| "loss": 1.4555, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 4.056795131845842, | |
| "grad_norm": 0.12625518441200256, | |
| "learning_rate": 0.0002830010441947834, | |
| "loss": 1.4352, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.056795131845842, | |
| "eval_loss": 1.3391929864883423, | |
| "eval_runtime": 41.9506, | |
| "eval_samples_per_second": 23.838, | |
| "eval_steps_per_second": 1.502, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.137931034482759, | |
| "grad_norm": 0.09084944427013397, | |
| "learning_rate": 0.00027411478242376017, | |
| "loss": 1.4307, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 4.219066937119676, | |
| "grad_norm": 0.0855906680226326, | |
| "learning_rate": 0.00026519764986401774, | |
| "loss": 1.4426, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.300202839756592, | |
| "grad_norm": 0.1407158076763153, | |
| "learning_rate": 0.000256261061875247, | |
| "loss": 1.4097, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 4.381338742393509, | |
| "grad_norm": 0.2571726441383362, | |
| "learning_rate": 0.0002473164587232079, | |
| "loss": 1.4414, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.462474645030426, | |
| "grad_norm": 0.2552030682563782, | |
| "learning_rate": 0.0002383752909343547, | |
| "loss": 1.4387, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.462474645030426, | |
| "eval_loss": 1.3391071557998657, | |
| "eval_runtime": 41.9602, | |
| "eval_samples_per_second": 23.832, | |
| "eval_steps_per_second": 1.501, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.543610547667343, | |
| "grad_norm": 0.22119635343551636, | |
| "learning_rate": 0.0002294490046373259, | |
| "loss": 1.4405, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.62474645030426, | |
| "grad_norm": 0.1968819946050644, | |
| "learning_rate": 0.00022054902691006405, | |
| "loss": 1.4416, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 0.27252131700515747, | |
| "learning_rate": 0.00021168675115132315, | |
| "loss": 1.4322, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.787018255578094, | |
| "grad_norm": 0.30559447407722473, | |
| "learning_rate": 0.00020287352249529153, | |
| "loss": 1.4417, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 4.8681541582150105, | |
| "grad_norm": 0.202793151140213, | |
| "learning_rate": 0.00019412062328800044, | |
| "loss": 1.4194, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.8681541582150105, | |
| "eval_loss": 1.3287636041641235, | |
| "eval_runtime": 41.6499, | |
| "eval_samples_per_second": 24.01, | |
| "eval_steps_per_second": 1.513, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.9492900608519275, | |
| "grad_norm": 0.1644078493118286, | |
| "learning_rate": 0.000185439258644112, | |
| "loss": 1.4281, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 5.0304259634888435, | |
| "grad_norm": 0.36123207211494446, | |
| "learning_rate": 0.00017684054210257517, | |
| "loss": 1.3923, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.1115618661257605, | |
| "grad_norm": 1.3023096323013306, | |
| "learning_rate": 0.00016833548139951395, | |
| "loss": 1.4163, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 5.192697768762677, | |
| "grad_norm": 0.2667650878429413, | |
| "learning_rate": 0.0001599349643765599, | |
| "loss": 1.4299, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.273833671399594, | |
| "grad_norm": 0.6209434866905212, | |
| "learning_rate": 0.0001516497450426686, | |
| "loss": 1.4546, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 5.273833671399594, | |
| "eval_loss": 1.3360823392868042, | |
| "eval_runtime": 41.6974, | |
| "eval_samples_per_second": 23.982, | |
| "eval_steps_per_second": 1.511, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 5.354969574036511, | |
| "grad_norm": 0.3910903334617615, | |
| "learning_rate": 0.00014349042980726362, | |
| "loss": 1.4003, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.436105476673428, | |
| "grad_norm": 0.1629013866186142, | |
| "learning_rate": 0.0001354674639023318, | |
| "loss": 1.4308, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 5.517241379310345, | |
| "grad_norm": 0.11925800144672394, | |
| "learning_rate": 0.00012759111801085066, | |
| "loss": 1.4154, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.598377281947261, | |
| "grad_norm": 0.17776216566562653, | |
| "learning_rate": 0.00011987147511866788, | |
| "loss": 1.4322, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 5.679513184584178, | |
| "grad_norm": 0.17757736146450043, | |
| "learning_rate": 0.00011231841760666186, | |
| "loss": 1.4136, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.679513184584178, | |
| "eval_loss": 1.3244247436523438, | |
| "eval_runtime": 41.8991, | |
| "eval_samples_per_second": 23.867, | |
| "eval_steps_per_second": 1.504, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.760649087221095, | |
| "grad_norm": 0.16734164953231812, | |
| "learning_rate": 0.0001049416145997094, | |
| "loss": 1.434, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 5.841784989858012, | |
| "grad_norm": 0.1208333671092987, | |
| "learning_rate": 9.775050958865584e-05, | |
| "loss": 1.4383, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.922920892494929, | |
| "grad_norm": 0.09565079212188721, | |
| "learning_rate": 9.075430834113152e-05, | |
| "loss": 1.3854, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 6.004056795131846, | |
| "grad_norm": 0.08396822959184647, | |
| "learning_rate": 8.396196711669335e-05, | |
| "loss": 1.4139, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.085192697768763, | |
| "grad_norm": 0.08815029263496399, | |
| "learning_rate": 7.738218120137671e-05, | |
| "loss": 1.3972, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.085192697768763, | |
| "eval_loss": 1.3242241144180298, | |
| "eval_runtime": 41.9432, | |
| "eval_samples_per_second": 23.842, | |
| "eval_steps_per_second": 1.502, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.16632860040568, | |
| "grad_norm": 0.07709522545337677, | |
| "learning_rate": 7.102337377633394e-05, | |
| "loss": 1.4098, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.247464503042596, | |
| "grad_norm": 0.09170571714639664, | |
| "learning_rate": 6.489368513481228e-05, | |
| "loss": 1.4198, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 6.328600405679513, | |
| "grad_norm": 0.08237478137016296, | |
| "learning_rate": 5.9000962261273136e-05, | |
| "loss": 1.4168, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.40973630831643, | |
| "grad_norm": 0.1285756379365921, | |
| "learning_rate": 5.3352748785993164e-05, | |
| "loss": 1.4374, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 6.490872210953347, | |
| "grad_norm": 0.07434211671352386, | |
| "learning_rate": 4.795627532800806e-05, | |
| "loss": 1.4049, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.490872210953347, | |
| "eval_loss": 1.3239072561264038, | |
| "eval_runtime": 41.9088, | |
| "eval_samples_per_second": 23.861, | |
| "eval_steps_per_second": 1.503, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.572008113590264, | |
| "grad_norm": 0.07087664306163788, | |
| "learning_rate": 4.281845023876074e-05, | |
| "loss": 1.3987, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 6.653144016227181, | |
| "grad_norm": 0.05918489769101143, | |
| "learning_rate": 3.794585075830329e-05, | |
| "loss": 1.3934, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.734279918864098, | |
| "grad_norm": 0.06427238136529922, | |
| "learning_rate": 3.334471459537497e-05, | |
| "loss": 1.4361, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 6.8154158215010145, | |
| "grad_norm": 0.058615412563085556, | |
| "learning_rate": 2.902093194213526e-05, | |
| "loss": 1.4155, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.896551724137931, | |
| "grad_norm": 0.07955154776573181, | |
| "learning_rate": 2.4980037933772488e-05, | |
| "loss": 1.437, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 6.896551724137931, | |
| "eval_loss": 1.3216674327850342, | |
| "eval_runtime": 41.9961, | |
| "eval_samples_per_second": 23.812, | |
| "eval_steps_per_second": 1.5, | |
| "step": 425 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 488, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.024840513050624e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |