| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 12.8, | |
| "eval_steps": 500, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 2.2721662521362305, | |
| "learning_rate": 4.999643406399275e-05, | |
| "loss": 4.0376, | |
| "num_input_tokens_seen": 6208, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 2.1794309616088867, | |
| "learning_rate": 4.998573727324295e-05, | |
| "loss": 3.9633, | |
| "num_input_tokens_seen": 11968, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 1.3466308116912842, | |
| "learning_rate": 4.9967912679276316e-05, | |
| "loss": 3.7175, | |
| "num_input_tokens_seen": 18016, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 1.3052715063095093, | |
| "learning_rate": 4.994296536700177e-05, | |
| "loss": 3.6465, | |
| "num_input_tokens_seen": 23760, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.289433479309082, | |
| "learning_rate": 4.9910902453260824e-05, | |
| "loss": 3.6384, | |
| "num_input_tokens_seen": 29648, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 1.0926741361618042, | |
| "learning_rate": 4.987173308479738e-05, | |
| "loss": 3.5703, | |
| "num_input_tokens_seen": 35968, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 1.3285070657730103, | |
| "learning_rate": 4.982546843564834e-05, | |
| "loss": 3.5096, | |
| "num_input_tokens_seen": 42112, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 1.691308856010437, | |
| "learning_rate": 4.977212170395598e-05, | |
| "loss": 3.2806, | |
| "num_input_tokens_seen": 48352, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 1.3265893459320068, | |
| "learning_rate": 4.971170810820279e-05, | |
| "loss": 3.4431, | |
| "num_input_tokens_seen": 54144, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.2742599248886108, | |
| "learning_rate": 4.964424488287009e-05, | |
| "loss": 3.2597, | |
| "num_input_tokens_seen": 60224, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 1.2702339887619019, | |
| "learning_rate": 4.9569751273521454e-05, | |
| "loss": 3.275, | |
| "num_input_tokens_seen": 66512, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 1.6329398155212402, | |
| "learning_rate": 4.948824853131236e-05, | |
| "loss": 3.1563, | |
| "num_input_tokens_seen": 72208, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 1.348823070526123, | |
| "learning_rate": 4.939975990692789e-05, | |
| "loss": 3.1883, | |
| "num_input_tokens_seen": 78368, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 1.441171646118164, | |
| "learning_rate": 4.930431064394977e-05, | |
| "loss": 3.2454, | |
| "num_input_tokens_seen": 84288, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 1.3091288805007935, | |
| "learning_rate": 4.920192797165511e-05, | |
| "loss": 3.1905, | |
| "num_input_tokens_seen": 90464, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 1.6830319166183472, | |
| "learning_rate": 4.909264109724853e-05, | |
| "loss": 3.0087, | |
| "num_input_tokens_seen": 96704, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.7199999999999998, | |
| "grad_norm": 1.941502332687378, | |
| "learning_rate": 4.897648119753006e-05, | |
| "loss": 3.0016, | |
| "num_input_tokens_seen": 102352, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 1.8244129419326782, | |
| "learning_rate": 4.885348141000122e-05, | |
| "loss": 3.1813, | |
| "num_input_tokens_seen": 108112, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "grad_norm": 1.6675082445144653, | |
| "learning_rate": 4.872367682341173e-05, | |
| "loss": 3.1158, | |
| "num_input_tokens_seen": 114240, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 1.8476835489273071, | |
| "learning_rate": 4.858710446774951e-05, | |
| "loss": 2.9404, | |
| "num_input_tokens_seen": 119936, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "grad_norm": 1.8608956336975098, | |
| "learning_rate": 4.844380330367701e-05, | |
| "loss": 2.9749, | |
| "num_input_tokens_seen": 125984, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "grad_norm": 1.9425894021987915, | |
| "learning_rate": 4.829381421141671e-05, | |
| "loss": 2.9456, | |
| "num_input_tokens_seen": 131808, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "grad_norm": 2.114993095397949, | |
| "learning_rate": 4.8137179979088995e-05, | |
| "loss": 2.8505, | |
| "num_input_tokens_seen": 137792, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "grad_norm": 1.7963783740997314, | |
| "learning_rate": 4.7973945290505766e-05, | |
| "loss": 3.0044, | |
| "num_input_tokens_seen": 144336, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.7597969770431519, | |
| "learning_rate": 4.780415671242334e-05, | |
| "loss": 3.0709, | |
| "num_input_tokens_seen": 150336, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "grad_norm": 1.8621456623077393, | |
| "learning_rate": 4.7627862681258037e-05, | |
| "loss": 2.912, | |
| "num_input_tokens_seen": 156768, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "grad_norm": 2.021226167678833, | |
| "learning_rate": 4.7445113489268544e-05, | |
| "loss": 2.8063, | |
| "num_input_tokens_seen": 163232, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "grad_norm": 2.2448067665100098, | |
| "learning_rate": 4.725596127020879e-05, | |
| "loss": 2.7714, | |
| "num_input_tokens_seen": 169616, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "grad_norm": 5.535823822021484, | |
| "learning_rate": 4.706045998445548e-05, | |
| "loss": 2.8277, | |
| "num_input_tokens_seen": 175664, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "grad_norm": 2.4096429347991943, | |
| "learning_rate": 4.685866540361456e-05, | |
| "loss": 2.7456, | |
| "num_input_tokens_seen": 181232, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "grad_norm": 2.699846029281616, | |
| "learning_rate": 4.665063509461097e-05, | |
| "loss": 2.7187, | |
| "num_input_tokens_seen": 186960, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "grad_norm": 2.661548376083374, | |
| "learning_rate": 4.643642840326627e-05, | |
| "loss": 2.7918, | |
| "num_input_tokens_seen": 192640, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "grad_norm": 2.395092725753784, | |
| "learning_rate": 4.621610643736878e-05, | |
| "loss": 2.6223, | |
| "num_input_tokens_seen": 198672, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "grad_norm": 2.329503059387207, | |
| "learning_rate": 4.598973204924097e-05, | |
| "loss": 2.654, | |
| "num_input_tokens_seen": 204976, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "grad_norm": 2.3466107845306396, | |
| "learning_rate": 4.5757369817809415e-05, | |
| "loss": 2.7321, | |
| "num_input_tokens_seen": 211168, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "grad_norm": 2.9179327487945557, | |
| "learning_rate": 4.551908603018191e-05, | |
| "loss": 2.71, | |
| "num_input_tokens_seen": 217072, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "grad_norm": 2.7011966705322266, | |
| "learning_rate": 4.527494866273753e-05, | |
| "loss": 2.7663, | |
| "num_input_tokens_seen": 223136, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "grad_norm": 2.610811948776245, | |
| "learning_rate": 4.502502736173462e-05, | |
| "loss": 2.4595, | |
| "num_input_tokens_seen": 229088, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "grad_norm": 2.6016838550567627, | |
| "learning_rate": 4.476939342344246e-05, | |
| "loss": 2.5734, | |
| "num_input_tokens_seen": 235184, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "grad_norm": 3.063948392868042, | |
| "learning_rate": 4.45081197738023e-05, | |
| "loss": 2.3804, | |
| "num_input_tokens_seen": 241152, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.5600000000000005, | |
| "grad_norm": 3.9621613025665283, | |
| "learning_rate": 4.424128094762331e-05, | |
| "loss": 2.4395, | |
| "num_input_tokens_seen": 247136, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "grad_norm": 2.887089967727661, | |
| "learning_rate": 4.3968953067319777e-05, | |
| "loss": 2.3477, | |
| "num_input_tokens_seen": 253232, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "grad_norm": 2.8491384983062744, | |
| "learning_rate": 4.369121382119523e-05, | |
| "loss": 2.5377, | |
| "num_input_tokens_seen": 258992, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "grad_norm": 3.3222053050994873, | |
| "learning_rate": 4.340814244127993e-05, | |
| "loss": 2.5576, | |
| "num_input_tokens_seen": 265392, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "grad_norm": 3.4029548168182373, | |
| "learning_rate": 4.3119819680728e-05, | |
| "loss": 2.2721, | |
| "num_input_tokens_seen": 271344, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "grad_norm": 3.4295144081115723, | |
| "learning_rate": 4.282632779078051e-05, | |
| "loss": 2.4025, | |
| "num_input_tokens_seen": 277120, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "grad_norm": 3.2438597679138184, | |
| "learning_rate": 4.2527750497301323e-05, | |
| "loss": 2.2175, | |
| "num_input_tokens_seen": 283152, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "grad_norm": 3.3982954025268555, | |
| "learning_rate": 4.222417297689217e-05, | |
| "loss": 2.1803, | |
| "num_input_tokens_seen": 289136, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "grad_norm": 2.70150089263916, | |
| "learning_rate": 4.191568183259394e-05, | |
| "loss": 2.4197, | |
| "num_input_tokens_seen": 295968, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 3.426187515258789, | |
| "learning_rate": 4.160236506918098e-05, | |
| "loss": 2.2351, | |
| "num_input_tokens_seen": 301472, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "grad_norm": 4.023019313812256, | |
| "learning_rate": 4.128431206805557e-05, | |
| "loss": 2.1748, | |
| "num_input_tokens_seen": 307216, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "grad_norm": 3.1614391803741455, | |
| "learning_rate": 4.096161356174959e-05, | |
| "loss": 2.1173, | |
| "num_input_tokens_seen": 313424, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "grad_norm": 3.4006361961364746, | |
| "learning_rate": 4.063436160804092e-05, | |
| "loss": 2.0966, | |
| "num_input_tokens_seen": 319472, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "grad_norm": 4.167815208435059, | |
| "learning_rate": 4.030264956369157e-05, | |
| "loss": 2.0825, | |
| "num_input_tokens_seen": 325504, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "grad_norm": 4.040388584136963, | |
| "learning_rate": 3.9966572057815373e-05, | |
| "loss": 2.0189, | |
| "num_input_tokens_seen": 331520, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "grad_norm": 5.056305885314941, | |
| "learning_rate": 3.962622496488269e-05, | |
| "loss": 2.0671, | |
| "num_input_tokens_seen": 337680, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "grad_norm": 4.466280937194824, | |
| "learning_rate": 3.928170537736981e-05, | |
| "loss": 2.0337, | |
| "num_input_tokens_seen": 343936, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "grad_norm": 4.8046698570251465, | |
| "learning_rate": 3.893311157806091e-05, | |
| "loss": 1.7892, | |
| "num_input_tokens_seen": 349632, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "grad_norm": 5.066511631011963, | |
| "learning_rate": 3.858054301201047e-05, | |
| "loss": 1.8558, | |
| "num_input_tokens_seen": 356080, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "grad_norm": 4.678648948669434, | |
| "learning_rate": 3.822410025817406e-05, | |
| "loss": 1.9685, | |
| "num_input_tokens_seen": 362048, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "grad_norm": 4.883659839630127, | |
| "learning_rate": 3.786388500071572e-05, | |
| "loss": 1.6883, | |
| "num_input_tokens_seen": 368128, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "grad_norm": 4.799614429473877, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 1.8049, | |
| "num_input_tokens_seen": 373920, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "grad_norm": 4.910759925842285, | |
| "learning_rate": 3.713254906327703e-05, | |
| "loss": 1.8785, | |
| "num_input_tokens_seen": 379920, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "grad_norm": 6.2078447341918945, | |
| "learning_rate": 3.67616370150689e-05, | |
| "loss": 1.8797, | |
| "num_input_tokens_seen": 386464, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "grad_norm": 6.023489952087402, | |
| "learning_rate": 3.638736966726585e-05, | |
| "loss": 1.6139, | |
| "num_input_tokens_seen": 392608, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "grad_norm": 5.2762017250061035, | |
| "learning_rate": 3.600985378894086e-05, | |
| "loss": 1.4428, | |
| "num_input_tokens_seen": 398224, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 10.72, | |
| "grad_norm": 6.009916305541992, | |
| "learning_rate": 3.562919707589102e-05, | |
| "loss": 1.6858, | |
| "num_input_tokens_seen": 404480, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "grad_norm": 5.862870216369629, | |
| "learning_rate": 3.5245508119914687e-05, | |
| "loss": 1.5669, | |
| "num_input_tokens_seen": 410448, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "grad_norm": 5.693241119384766, | |
| "learning_rate": 3.4858896377832966e-05, | |
| "loss": 1.5857, | |
| "num_input_tokens_seen": 416544, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "grad_norm": 7.012350082397461, | |
| "learning_rate": 3.44694721402644e-05, | |
| "loss": 1.4511, | |
| "num_input_tokens_seen": 422032, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "grad_norm": 6.417391777038574, | |
| "learning_rate": 3.407734650016187e-05, | |
| "loss": 1.4448, | |
| "num_input_tokens_seen": 428224, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "grad_norm": 5.746353626251221, | |
| "learning_rate": 3.3682631321120504e-05, | |
| "loss": 1.4648, | |
| "num_input_tokens_seen": 434368, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "grad_norm": 6.427619457244873, | |
| "learning_rate": 3.32854392054659e-05, | |
| "loss": 1.4896, | |
| "num_input_tokens_seen": 440816, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "grad_norm": 6.434299468994141, | |
| "learning_rate": 3.2885883462131394e-05, | |
| "loss": 1.2713, | |
| "num_input_tokens_seen": 446992, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 6.6553521156311035, | |
| "learning_rate": 3.2484078074333954e-05, | |
| "loss": 1.4016, | |
| "num_input_tokens_seen": 452864, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "grad_norm": 6.007937431335449, | |
| "learning_rate": 3.2080137667057595e-05, | |
| "loss": 1.1953, | |
| "num_input_tokens_seen": 458800, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "grad_norm": 7.414127826690674, | |
| "learning_rate": 3.167417747435379e-05, | |
| "loss": 1.235, | |
| "num_input_tokens_seen": 465040, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "grad_norm": 7.6087565422058105, | |
| "learning_rate": 3.126631330646802e-05, | |
| "loss": 1.1375, | |
| "num_input_tokens_seen": 470544, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "grad_norm": 7.889481067657471, | |
| "learning_rate": 3.0856661516802054e-05, | |
| "loss": 1.1427, | |
| "num_input_tokens_seen": 476608, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "grad_norm": 5.883874416351318, | |
| "learning_rate": 3.0445338968721287e-05, | |
| "loss": 1.3749, | |
| "num_input_tokens_seen": 483136, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 930, | |
| "num_input_tokens_seen": 483136, | |
| "num_train_epochs": 30, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3827069386555392.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |