| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8325008325008325, | |
| "global_step": 230000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.996983692635866e-05, | |
| "loss": 9.3743, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.9939673852717336e-05, | |
| "loss": 8.6211, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 8.523540496826172, | |
| "eval_runtime": 4.1116, | |
| "eval_samples_per_second": 243.213, | |
| "eval_steps_per_second": 15.322, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9909510779075997e-05, | |
| "loss": 8.3996, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9879347705434663e-05, | |
| "loss": 8.2439, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 8.210819244384766, | |
| "eval_runtime": 4.2077, | |
| "eval_samples_per_second": 237.661, | |
| "eval_steps_per_second": 14.973, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.984924495794061e-05, | |
| "loss": 8.1275, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.981908188429928e-05, | |
| "loss": 8.0166, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 7.937699317932129, | |
| "eval_runtime": 4.3727, | |
| "eval_samples_per_second": 228.692, | |
| "eval_steps_per_second": 14.408, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.978891881065794e-05, | |
| "loss": 7.922, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.975875573701661e-05, | |
| "loss": 7.8304, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 7.840174674987793, | |
| "eval_runtime": 4.2845, | |
| "eval_samples_per_second": 233.399, | |
| "eval_steps_per_second": 14.704, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9728592663375274e-05, | |
| "loss": 7.7459, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9698489915881224e-05, | |
| "loss": 7.705, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 7.6650848388671875, | |
| "eval_runtime": 4.3176, | |
| "eval_samples_per_second": 231.609, | |
| "eval_steps_per_second": 14.591, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.966832684223989e-05, | |
| "loss": 7.653, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.963816376859856e-05, | |
| "loss": 7.5734, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 7.5711894035339355, | |
| "eval_runtime": 4.3326, | |
| "eval_samples_per_second": 230.807, | |
| "eval_steps_per_second": 14.541, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.960800069495722e-05, | |
| "loss": 7.5223, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.9577837621315885e-05, | |
| "loss": 7.4853, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 7.468273639678955, | |
| "eval_runtime": 4.3863, | |
| "eval_samples_per_second": 227.982, | |
| "eval_steps_per_second": 14.363, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.9547734873821834e-05, | |
| "loss": 7.419, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.9517571800180494e-05, | |
| "loss": 7.3788, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 7.432778358459473, | |
| "eval_runtime": 4.2901, | |
| "eval_samples_per_second": 233.096, | |
| "eval_steps_per_second": 14.685, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.948740872653916e-05, | |
| "loss": 7.3405, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.945724565289783e-05, | |
| "loss": 7.2813, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 7.341405868530273, | |
| "eval_runtime": 4.4257, | |
| "eval_samples_per_second": 225.951, | |
| "eval_steps_per_second": 14.235, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.9427082579256495e-05, | |
| "loss": 7.2549, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.9396919505615156e-05, | |
| "loss": 7.213, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 7.239240646362305, | |
| "eval_runtime": 4.2885, | |
| "eval_samples_per_second": 233.181, | |
| "eval_steps_per_second": 14.69, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.936675643197383e-05, | |
| "loss": 7.1898, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.933659335833249e-05, | |
| "loss": 7.1662, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 7.204339504241943, | |
| "eval_runtime": 4.306, | |
| "eval_samples_per_second": 232.234, | |
| "eval_steps_per_second": 14.631, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.930655093698572e-05, | |
| "loss": 7.1373, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.927638786334439e-05, | |
| "loss": 7.0908, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 7.1362996101379395, | |
| "eval_runtime": 4.278, | |
| "eval_samples_per_second": 233.752, | |
| "eval_steps_per_second": 14.726, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9246224789703056e-05, | |
| "loss": 7.0629, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9216061716061716e-05, | |
| "loss": 7.0458, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 7.110766410827637, | |
| "eval_runtime": 4.4164, | |
| "eval_samples_per_second": 226.429, | |
| "eval_steps_per_second": 14.265, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.918589864242038e-05, | |
| "loss": 7.0147, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.915573556877905e-05, | |
| "loss": 6.9895, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 6.985559940338135, | |
| "eval_runtime": 4.3309, | |
| "eval_samples_per_second": 230.901, | |
| "eval_steps_per_second": 14.547, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.912563282128499e-05, | |
| "loss": 6.9634, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9095469747643666e-05, | |
| "loss": 6.9537, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 7.012362480163574, | |
| "eval_runtime": 4.2388, | |
| "eval_samples_per_second": 235.918, | |
| "eval_steps_per_second": 14.863, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.9065306674002326e-05, | |
| "loss": 6.9295, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.903514360036099e-05, | |
| "loss": 6.9067, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 6.980933666229248, | |
| "eval_runtime": 4.272, | |
| "eval_samples_per_second": 234.082, | |
| "eval_steps_per_second": 14.747, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.900504085286694e-05, | |
| "loss": 6.8896, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.897487777922561e-05, | |
| "loss": 6.8678, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 6.871150493621826, | |
| "eval_runtime": 4.2596, | |
| "eval_samples_per_second": 234.765, | |
| "eval_steps_per_second": 14.79, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.894471470558427e-05, | |
| "loss": 6.8301, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.891455163194294e-05, | |
| "loss": 6.8388, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 6.891202449798584, | |
| "eval_runtime": 4.2654, | |
| "eval_samples_per_second": 234.445, | |
| "eval_steps_per_second": 14.77, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.8884388558301604e-05, | |
| "loss": 6.8197, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.885422548466027e-05, | |
| "loss": 6.8031, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 6.856838703155518, | |
| "eval_runtime": 4.3078, | |
| "eval_samples_per_second": 232.139, | |
| "eval_steps_per_second": 14.625, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.882406241101893e-05, | |
| "loss": 6.7821, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.8793899337377605e-05, | |
| "loss": 6.7818, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 6.831137180328369, | |
| "eval_runtime": 4.3011, | |
| "eval_samples_per_second": 232.498, | |
| "eval_steps_per_second": 14.647, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.876379658988355e-05, | |
| "loss": 6.7754, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.8733633516242215e-05, | |
| "loss": 6.7548, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 6.813143253326416, | |
| "eval_runtime": 6.2764, | |
| "eval_samples_per_second": 159.326, | |
| "eval_steps_per_second": 10.038, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.870347044260088e-05, | |
| "loss": 6.7458, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.867330736895955e-05, | |
| "loss": 6.7351, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 6.724792957305908, | |
| "eval_runtime": 4.2249, | |
| "eval_samples_per_second": 236.695, | |
| "eval_steps_per_second": 14.912, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.864314429531821e-05, | |
| "loss": 6.7107, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.8612981221676876e-05, | |
| "loss": 6.6927, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 6.75374698638916, | |
| "eval_runtime": 4.3504, | |
| "eval_samples_per_second": 229.864, | |
| "eval_steps_per_second": 14.481, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.8582878474182825e-05, | |
| "loss": 6.6837, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.8552715400541485e-05, | |
| "loss": 6.6863, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 6.72822380065918, | |
| "eval_runtime": 4.384, | |
| "eval_samples_per_second": 228.102, | |
| "eval_steps_per_second": 14.37, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.852255232690016e-05, | |
| "loss": 6.6608, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.849238925325882e-05, | |
| "loss": 6.6452, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 6.719581604003906, | |
| "eval_runtime": 4.3427, | |
| "eval_samples_per_second": 230.271, | |
| "eval_steps_per_second": 14.507, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.8462226179617486e-05, | |
| "loss": 6.6261, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.8432123432123436e-05, | |
| "loss": 6.6153, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 6.65714168548584, | |
| "eval_runtime": 4.3559, | |
| "eval_samples_per_second": 229.574, | |
| "eval_steps_per_second": 14.463, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.84019603584821e-05, | |
| "loss": 6.6081, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.837179728484076e-05, | |
| "loss": 6.6114, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 6.6556854248046875, | |
| "eval_runtime": 4.4221, | |
| "eval_samples_per_second": 226.135, | |
| "eval_steps_per_second": 14.247, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.834163421119943e-05, | |
| "loss": 6.5909, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.831153146370538e-05, | |
| "loss": 6.6003, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 6.645580291748047, | |
| "eval_runtime": 4.321, | |
| "eval_samples_per_second": 231.43, | |
| "eval_steps_per_second": 14.58, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.8281368390064047e-05, | |
| "loss": 6.5773, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.825120531642271e-05, | |
| "loss": 6.5656, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 6.621737480163574, | |
| "eval_runtime": 4.2363, | |
| "eval_samples_per_second": 236.056, | |
| "eval_steps_per_second": 14.872, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.822104224278138e-05, | |
| "loss": 6.5753, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.819087916914004e-05, | |
| "loss": 6.5518, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 6.60227632522583, | |
| "eval_runtime": 4.3472, | |
| "eval_samples_per_second": 230.034, | |
| "eval_steps_per_second": 14.492, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.816071609549871e-05, | |
| "loss": 6.5431, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.813061334800466e-05, | |
| "loss": 6.5407, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 6.591599464416504, | |
| "eval_runtime": 4.2945, | |
| "eval_samples_per_second": 232.858, | |
| "eval_steps_per_second": 14.67, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.810045027436332e-05, | |
| "loss": 6.5197, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.8070287200721984e-05, | |
| "loss": 6.5069, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 6.563199996948242, | |
| "eval_runtime": 4.2853, | |
| "eval_samples_per_second": 233.356, | |
| "eval_steps_per_second": 14.701, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.804012412708065e-05, | |
| "loss": 6.508, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.800996105343932e-05, | |
| "loss": 6.5031, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 6.495542526245117, | |
| "eval_runtime": 4.2956, | |
| "eval_samples_per_second": 232.797, | |
| "eval_steps_per_second": 14.666, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.797979797979798e-05, | |
| "loss": 6.4874, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.7949634906156645e-05, | |
| "loss": 6.4795, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 6.54636812210083, | |
| "eval_runtime": 4.3345, | |
| "eval_samples_per_second": 230.706, | |
| "eval_steps_per_second": 14.534, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.7919532158662595e-05, | |
| "loss": 6.4765, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.788936908502126e-05, | |
| "loss": 6.4749, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 6.562394142150879, | |
| "eval_runtime": 4.214, | |
| "eval_samples_per_second": 237.303, | |
| "eval_steps_per_second": 14.95, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.785920601137993e-05, | |
| "loss": 6.4512, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.7829042937738596e-05, | |
| "loss": 6.4453, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 6.480181694030762, | |
| "eval_runtime": 4.3457, | |
| "eval_samples_per_second": 230.112, | |
| "eval_steps_per_second": 14.497, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.779894019024454e-05, | |
| "loss": 6.471, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.7768777116603206e-05, | |
| "loss": 6.4371, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 6.513635635375977, | |
| "eval_runtime": 4.3597, | |
| "eval_samples_per_second": 229.373, | |
| "eval_steps_per_second": 14.45, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.773861404296187e-05, | |
| "loss": 6.4295, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.770845096932054e-05, | |
| "loss": 6.4302, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 6.495160102844238, | |
| "eval_runtime": 4.2204, | |
| "eval_samples_per_second": 236.944, | |
| "eval_steps_per_second": 14.927, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.76782878956792e-05, | |
| "loss": 6.4215, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.764818514818515e-05, | |
| "loss": 6.4062, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 6.4935173988342285, | |
| "eval_runtime": 4.366, | |
| "eval_samples_per_second": 229.044, | |
| "eval_steps_per_second": 14.43, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.7618022074543816e-05, | |
| "loss": 6.3908, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.7587859000902476e-05, | |
| "loss": 6.4109, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 6.459984302520752, | |
| "eval_runtime": 4.3414, | |
| "eval_samples_per_second": 230.343, | |
| "eval_steps_per_second": 14.512, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.755769592726115e-05, | |
| "loss": 6.3959, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.752753285361981e-05, | |
| "loss": 6.3828, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 6.429795265197754, | |
| "eval_runtime": 4.3398, | |
| "eval_samples_per_second": 230.427, | |
| "eval_steps_per_second": 14.517, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.749736977997848e-05, | |
| "loss": 6.3775, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.7467206706337144e-05, | |
| "loss": 6.3739, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 6.406271457672119, | |
| "eval_runtime": 4.3187, | |
| "eval_samples_per_second": 231.553, | |
| "eval_steps_per_second": 14.588, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.743704363269581e-05, | |
| "loss": 6.3638, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.7406940885201754e-05, | |
| "loss": 6.3449, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 6.363914489746094, | |
| "eval_runtime": 6.5899, | |
| "eval_samples_per_second": 151.748, | |
| "eval_steps_per_second": 9.56, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.737677781156043e-05, | |
| "loss": 6.3654, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.734661473791909e-05, | |
| "loss": 6.3473, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 6.375613212585449, | |
| "eval_runtime": 4.323, | |
| "eval_samples_per_second": 231.319, | |
| "eval_steps_per_second": 14.573, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.7316451664277755e-05, | |
| "loss": 6.3486, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.7286348916783704e-05, | |
| "loss": 6.3462, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 6.379289150238037, | |
| "eval_runtime": 4.2624, | |
| "eval_samples_per_second": 234.609, | |
| "eval_steps_per_second": 14.78, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.725624616928965e-05, | |
| "loss": 6.3313, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.7226083095648314e-05, | |
| "loss": 6.3323, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 6.387815475463867, | |
| "eval_runtime": 4.3758, | |
| "eval_samples_per_second": 228.53, | |
| "eval_steps_per_second": 14.397, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.719592002200698e-05, | |
| "loss": 6.3256, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.716575694836565e-05, | |
| "loss": 6.3098, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 6.394986629486084, | |
| "eval_runtime": 4.3311, | |
| "eval_samples_per_second": 230.889, | |
| "eval_steps_per_second": 14.546, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.713559387472431e-05, | |
| "loss": 6.3082, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.7105430801082975e-05, | |
| "loss": 6.298, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 6.3571929931640625, | |
| "eval_runtime": 4.3274, | |
| "eval_samples_per_second": 231.084, | |
| "eval_steps_per_second": 14.558, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.707526772744164e-05, | |
| "loss": 6.3032, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.704510465380031e-05, | |
| "loss": 6.3095, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 6.37529182434082, | |
| "eval_runtime": 4.2983, | |
| "eval_samples_per_second": 232.652, | |
| "eval_steps_per_second": 14.657, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.701500190630625e-05, | |
| "loss": 6.2991, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.6984838832664926e-05, | |
| "loss": 6.2891, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 6.396151542663574, | |
| "eval_runtime": 4.4316, | |
| "eval_samples_per_second": 225.65, | |
| "eval_steps_per_second": 14.216, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.6954675759023586e-05, | |
| "loss": 6.2902, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.692451268538225e-05, | |
| "loss": 6.2847, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 6.3496623039245605, | |
| "eval_runtime": 4.3566, | |
| "eval_samples_per_second": 229.537, | |
| "eval_steps_per_second": 14.461, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.689434961174092e-05, | |
| "loss": 6.278, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.686424686424687e-05, | |
| "loss": 6.2635, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 6.37539005279541, | |
| "eval_runtime": 4.338, | |
| "eval_samples_per_second": 230.523, | |
| "eval_steps_per_second": 14.523, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.683408379060553e-05, | |
| "loss": 6.2571, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.68039207169642e-05, | |
| "loss": 6.2554, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 6.27804708480835, | |
| "eval_runtime": 4.3755, | |
| "eval_samples_per_second": 228.546, | |
| "eval_steps_per_second": 14.398, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.6773757643322863e-05, | |
| "loss": 6.2548, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.6743594569681524e-05, | |
| "loss": 6.2407, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 6.285305023193359, | |
| "eval_runtime": 4.3656, | |
| "eval_samples_per_second": 229.064, | |
| "eval_steps_per_second": 14.431, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.67134314960402e-05, | |
| "loss": 6.2262, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.668326842239886e-05, | |
| "loss": 6.2222, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 6.287919044494629, | |
| "eval_runtime": 4.3582, | |
| "eval_samples_per_second": 229.452, | |
| "eval_steps_per_second": 14.455, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.6653105348757525e-05, | |
| "loss": 6.2463, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.6623002601263474e-05, | |
| "loss": 6.2233, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 6.290223598480225, | |
| "eval_runtime": 4.3327, | |
| "eval_samples_per_second": 230.801, | |
| "eval_steps_per_second": 14.54, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.659283952762214e-05, | |
| "loss": 6.2253, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.65626764539808e-05, | |
| "loss": 6.2147, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 6.265440464019775, | |
| "eval_runtime": 4.367, | |
| "eval_samples_per_second": 228.992, | |
| "eval_steps_per_second": 14.426, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.653251338033947e-05, | |
| "loss": 6.2245, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.650241063284542e-05, | |
| "loss": 6.2118, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 6.265470504760742, | |
| "eval_runtime": 4.2827, | |
| "eval_samples_per_second": 233.497, | |
| "eval_steps_per_second": 14.71, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.6472247559204085e-05, | |
| "loss": 6.2082, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.6442084485562745e-05, | |
| "loss": 6.2039, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 6.2890191078186035, | |
| "eval_runtime": 4.3624, | |
| "eval_samples_per_second": 229.229, | |
| "eval_steps_per_second": 14.441, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.641192141192142e-05, | |
| "loss": 6.2145, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.638175833828008e-05, | |
| "loss": 6.1805, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 6.290516376495361, | |
| "eval_runtime": 4.3339, | |
| "eval_samples_per_second": 230.741, | |
| "eval_steps_per_second": 14.537, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.6351595264638746e-05, | |
| "loss": 6.1993, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.632143219099741e-05, | |
| "loss": 6.1947, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 6.219234466552734, | |
| "eval_runtime": 4.3446, | |
| "eval_samples_per_second": 230.172, | |
| "eval_steps_per_second": 14.501, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.6291329443503356e-05, | |
| "loss": 6.2058, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.626116636986202e-05, | |
| "loss": 6.1748, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 6.209784030914307, | |
| "eval_runtime": 4.371, | |
| "eval_samples_per_second": 228.781, | |
| "eval_steps_per_second": 14.413, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.623100329622069e-05, | |
| "loss": 6.1758, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.6200840222579356e-05, | |
| "loss": 6.1761, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 6.212859153747559, | |
| "eval_runtime": 4.4203, | |
| "eval_samples_per_second": 226.231, | |
| "eval_steps_per_second": 14.253, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.617067714893802e-05, | |
| "loss": 6.1741, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.6140514075296684e-05, | |
| "loss": 6.156, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 6.214317321777344, | |
| "eval_runtime": 4.3952, | |
| "eval_samples_per_second": 227.52, | |
| "eval_steps_per_second": 14.334, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.611035100165535e-05, | |
| "loss": 6.1674, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.608018792801402e-05, | |
| "loss": 6.1669, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 6.188581943511963, | |
| "eval_runtime": 4.4051, | |
| "eval_samples_per_second": 227.008, | |
| "eval_steps_per_second": 14.302, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.605008518051997e-05, | |
| "loss": 6.16, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.6019922106878634e-05, | |
| "loss": 6.1483, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 6.198948383331299, | |
| "eval_runtime": 4.3438, | |
| "eval_samples_per_second": 230.215, | |
| "eval_steps_per_second": 14.504, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.5989759033237294e-05, | |
| "loss": 6.1433, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.595959595959596e-05, | |
| "loss": 6.1573, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 6.161040782928467, | |
| "eval_runtime": 6.3766, | |
| "eval_samples_per_second": 156.823, | |
| "eval_steps_per_second": 9.88, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.592943288595463e-05, | |
| "loss": 6.1463, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.589933013846058e-05, | |
| "loss": 6.1414, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 6.161304473876953, | |
| "eval_runtime": 4.3109, | |
| "eval_samples_per_second": 231.972, | |
| "eval_steps_per_second": 14.614, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.586916706481924e-05, | |
| "loss": 6.1435, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.583900399117791e-05, | |
| "loss": 6.1202, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 6.174992561340332, | |
| "eval_runtime": 4.3065, | |
| "eval_samples_per_second": 232.209, | |
| "eval_steps_per_second": 14.629, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.580884091753657e-05, | |
| "loss": 6.1219, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.577867784389523e-05, | |
| "loss": 6.115, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 6.18692684173584, | |
| "eval_runtime": 4.3917, | |
| "eval_samples_per_second": 227.7, | |
| "eval_steps_per_second": 14.345, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.5748514770253906e-05, | |
| "loss": 6.1257, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.571841202275985e-05, | |
| "loss": 6.1381, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 6.09669828414917, | |
| "eval_runtime": 4.3181, | |
| "eval_samples_per_second": 231.583, | |
| "eval_steps_per_second": 14.59, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.5688248949118515e-05, | |
| "loss": 6.1158, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.565808587547718e-05, | |
| "loss": 6.1182, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 6.138221740722656, | |
| "eval_runtime": 4.3099, | |
| "eval_samples_per_second": 232.023, | |
| "eval_steps_per_second": 14.617, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.562792280183585e-05, | |
| "loss": 6.1063, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.559775972819451e-05, | |
| "loss": 6.096, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 6.156211853027344, | |
| "eval_runtime": 4.3788, | |
| "eval_samples_per_second": 228.373, | |
| "eval_steps_per_second": 14.388, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.5567596654553177e-05, | |
| "loss": 6.117, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.5537433580911844e-05, | |
| "loss": 6.1019, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 6.182168483734131, | |
| "eval_runtime": 4.3493, | |
| "eval_samples_per_second": 229.923, | |
| "eval_steps_per_second": 14.485, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.550727050727051e-05, | |
| "loss": 6.0936, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.547716775977646e-05, | |
| "loss": 6.0907, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 6.1323113441467285, | |
| "eval_runtime": 4.3544, | |
| "eval_samples_per_second": 229.654, | |
| "eval_steps_per_second": 14.468, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.544706501228241e-05, | |
| "loss": 6.086, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.541690193864107e-05, | |
| "loss": 6.0914, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 6.1409149169921875, | |
| "eval_runtime": 4.3453, | |
| "eval_samples_per_second": 230.134, | |
| "eval_steps_per_second": 14.498, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.538673886499974e-05, | |
| "loss": 6.0774, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.5356575791358404e-05, | |
| "loss": 6.0911, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 6.122730255126953, | |
| "eval_runtime": 4.2779, | |
| "eval_samples_per_second": 233.759, | |
| "eval_steps_per_second": 14.727, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.5326412717717064e-05, | |
| "loss": 6.0764, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.5296309970223013e-05, | |
| "loss": 6.0789, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 6.096778392791748, | |
| "eval_runtime": 6.4313, | |
| "eval_samples_per_second": 155.49, | |
| "eval_steps_per_second": 9.796, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.526614689658168e-05, | |
| "loss": 6.0659, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.523598382294035e-05, | |
| "loss": 6.0649, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 6.110874176025391, | |
| "eval_runtime": 4.3543, | |
| "eval_samples_per_second": 229.655, | |
| "eval_steps_per_second": 14.468, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.520582074929901e-05, | |
| "loss": 6.0598, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.517565767565768e-05, | |
| "loss": 6.0721, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 6.144255638122559, | |
| "eval_runtime": 4.2916, | |
| "eval_samples_per_second": 233.012, | |
| "eval_steps_per_second": 14.68, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.5145554928163624e-05, | |
| "loss": 6.0663, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.511539185452229e-05, | |
| "loss": 6.0543, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 6.099493980407715, | |
| "eval_runtime": 4.4139, | |
| "eval_samples_per_second": 226.556, | |
| "eval_steps_per_second": 14.273, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.508522878088096e-05, | |
| "loss": 6.0371, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.5055065707239625e-05, | |
| "loss": 6.0491, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 6.0733723640441895, | |
| "eval_runtime": 4.3153, | |
| "eval_samples_per_second": 231.736, | |
| "eval_steps_per_second": 14.599, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.5024902633598285e-05, | |
| "loss": 6.0488, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.499473955995695e-05, | |
| "loss": 6.0392, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 6.062073230743408, | |
| "eval_runtime": 4.372, | |
| "eval_samples_per_second": 228.728, | |
| "eval_steps_per_second": 14.41, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.496457648631562e-05, | |
| "loss": 6.0402, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.4934413412674286e-05, | |
| "loss": 6.0487, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 6.08383321762085, | |
| "eval_runtime": 6.5143, | |
| "eval_samples_per_second": 153.507, | |
| "eval_steps_per_second": 9.671, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.4904310665180236e-05, | |
| "loss": 6.0402, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.487420791768618e-05, | |
| "loss": 6.0314, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 6.082727432250977, | |
| "eval_runtime": 4.3196, | |
| "eval_samples_per_second": 231.502, | |
| "eval_steps_per_second": 14.585, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.4844044844044845e-05, | |
| "loss": 6.0249, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.481388177040351e-05, | |
| "loss": 6.0329, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 6.075023651123047, | |
| "eval_runtime": 4.2685, | |
| "eval_samples_per_second": 234.274, | |
| "eval_steps_per_second": 14.759, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.478371869676218e-05, | |
| "loss": 6.0329, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.475361594926812e-05, | |
| "loss": 6.0233, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 6.072445392608643, | |
| "eval_runtime": 4.3773, | |
| "eval_samples_per_second": 228.453, | |
| "eval_steps_per_second": 14.393, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.472345287562679e-05, | |
| "loss": 6.032, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.4693289801985456e-05, | |
| "loss": 6.0296, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 6.064884185791016, | |
| "eval_runtime": 4.3333, | |
| "eval_samples_per_second": 230.771, | |
| "eval_steps_per_second": 14.539, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.466312672834412e-05, | |
| "loss": 6.0324, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.463296365470278e-05, | |
| "loss": 6.0141, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 6.0311689376831055, | |
| "eval_runtime": 4.3204, | |
| "eval_samples_per_second": 231.461, | |
| "eval_steps_per_second": 14.582, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.460280058106146e-05, | |
| "loss": 6.0171, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.457263750742012e-05, | |
| "loss": 6.0109, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 6.072292804718018, | |
| "eval_runtime": 6.2611, | |
| "eval_samples_per_second": 159.717, | |
| "eval_steps_per_second": 10.062, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.4542474433778784e-05, | |
| "loss": 6.001, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.4512371686284734e-05, | |
| "loss": 5.9988, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 6.042818546295166, | |
| "eval_runtime": 4.3121, | |
| "eval_samples_per_second": 231.908, | |
| "eval_steps_per_second": 14.61, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.44822086126434e-05, | |
| "loss": 6.0103, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.445210586514934e-05, | |
| "loss": 6.0061, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 6.017780303955078, | |
| "eval_runtime": 4.3583, | |
| "eval_samples_per_second": 229.448, | |
| "eval_steps_per_second": 14.455, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.442194279150801e-05, | |
| "loss": 6.0035, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.439177971786668e-05, | |
| "loss": 6.0009, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 6.078599452972412, | |
| "eval_runtime": 4.3628, | |
| "eval_samples_per_second": 229.211, | |
| "eval_steps_per_second": 14.44, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.436161664422534e-05, | |
| "loss": 6.0004, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.433145357058401e-05, | |
| "loss": 5.9976, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 6.076462745666504, | |
| "eval_runtime": 4.4135, | |
| "eval_samples_per_second": 226.579, | |
| "eval_steps_per_second": 14.274, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.4301350823089954e-05, | |
| "loss": 6.004, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.427118774944862e-05, | |
| "loss": 5.9857, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 6.037008762359619, | |
| "eval_runtime": 4.3059, | |
| "eval_samples_per_second": 232.239, | |
| "eval_steps_per_second": 14.631, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.424102467580729e-05, | |
| "loss": 5.9964, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.4210861602165955e-05, | |
| "loss": 5.9927, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 6.015842914581299, | |
| "eval_runtime": 4.2524, | |
| "eval_samples_per_second": 235.159, | |
| "eval_steps_per_second": 14.815, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.4180698528524615e-05, | |
| "loss": 5.999, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.415053545488328e-05, | |
| "loss": 5.9784, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 6.02786111831665, | |
| "eval_runtime": 4.3676, | |
| "eval_samples_per_second": 228.957, | |
| "eval_steps_per_second": 14.424, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.412037238124195e-05, | |
| "loss": 5.9761, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.4090329959895174e-05, | |
| "loss": 5.9748, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 6.014493465423584, | |
| "eval_runtime": 4.2894, | |
| "eval_samples_per_second": 233.134, | |
| "eval_steps_per_second": 14.687, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.406016688625385e-05, | |
| "loss": 5.9804, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.403000381261251e-05, | |
| "loss": 5.9741, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 6.044219493865967, | |
| "eval_runtime": 4.3247, | |
| "eval_samples_per_second": 231.229, | |
| "eval_steps_per_second": 14.567, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.3999840738971175e-05, | |
| "loss": 5.9778, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.396967766532984e-05, | |
| "loss": 5.9699, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 6.005799293518066, | |
| "eval_runtime": 4.3718, | |
| "eval_samples_per_second": 228.741, | |
| "eval_steps_per_second": 14.411, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 4.393951459168851e-05, | |
| "loss": 5.9631, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.390935151804717e-05, | |
| "loss": 5.9899, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 5.946277618408203, | |
| "eval_runtime": 4.3243, | |
| "eval_samples_per_second": 231.25, | |
| "eval_steps_per_second": 14.569, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.3879188444405836e-05, | |
| "loss": 5.9565, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.38490253707645e-05, | |
| "loss": 5.9728, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 6.005879878997803, | |
| "eval_runtime": 4.4401, | |
| "eval_samples_per_second": 225.223, | |
| "eval_steps_per_second": 14.189, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.381886229712317e-05, | |
| "loss": 5.9722, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.378869922348183e-05, | |
| "loss": 5.9503, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 5.96213436126709, | |
| "eval_runtime": 4.349, | |
| "eval_samples_per_second": 229.939, | |
| "eval_steps_per_second": 14.486, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.3758536149840504e-05, | |
| "loss": 5.9631, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.3728373076199164e-05, | |
| "loss": 5.9573, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 6.019954681396484, | |
| "eval_runtime": 4.3963, | |
| "eval_samples_per_second": 227.464, | |
| "eval_steps_per_second": 14.33, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.3698270328705114e-05, | |
| "loss": 5.9604, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.366810725506378e-05, | |
| "loss": 5.9563, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 6.00137996673584, | |
| "eval_runtime": 4.4013, | |
| "eval_samples_per_second": 227.207, | |
| "eval_steps_per_second": 14.314, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.363794418142245e-05, | |
| "loss": 5.9479, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.360778110778111e-05, | |
| "loss": 5.9414, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 5.9667510986328125, | |
| "eval_runtime": 4.2409, | |
| "eval_samples_per_second": 235.8, | |
| "eval_steps_per_second": 14.855, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.357773868643434e-05, | |
| "loss": 5.9349, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.354757561279301e-05, | |
| "loss": 5.9311, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 6.016119956970215, | |
| "eval_runtime": 6.3445, | |
| "eval_samples_per_second": 157.617, | |
| "eval_steps_per_second": 9.93, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.351741253915167e-05, | |
| "loss": 5.9398, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.348724946551034e-05, | |
| "loss": 5.9357, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 5.970701217651367, | |
| "eval_runtime": 4.3817, | |
| "eval_samples_per_second": 228.222, | |
| "eval_steps_per_second": 14.378, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.3457086391869e-05, | |
| "loss": 5.9368, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.342698364437495e-05, | |
| "loss": 5.9312, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 5.961437702178955, | |
| "eval_runtime": 4.3658, | |
| "eval_samples_per_second": 229.052, | |
| "eval_steps_per_second": 14.43, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.339682057073362e-05, | |
| "loss": 5.9306, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.3366657497092285e-05, | |
| "loss": 5.9337, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 5.9670586585998535, | |
| "eval_runtime": 4.3639, | |
| "eval_samples_per_second": 229.152, | |
| "eval_steps_per_second": 14.437, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.3336494423450945e-05, | |
| "loss": 5.9424, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.330633134980961e-05, | |
| "loss": 5.9361, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 6.001840591430664, | |
| "eval_runtime": 4.3398, | |
| "eval_samples_per_second": 230.423, | |
| "eval_steps_per_second": 14.517, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.327616827616828e-05, | |
| "loss": 5.9411, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.324606552867423e-05, | |
| "loss": 5.9163, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 5.968799114227295, | |
| "eval_runtime": 4.2961, | |
| "eval_samples_per_second": 232.767, | |
| "eval_steps_per_second": 14.664, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.321596278118018e-05, | |
| "loss": 5.9305, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.318579970753884e-05, | |
| "loss": 5.9078, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 5.962240219116211, | |
| "eval_runtime": 4.405, | |
| "eval_samples_per_second": 227.013, | |
| "eval_steps_per_second": 14.302, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.3155636633897505e-05, | |
| "loss": 5.9165, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.312547356025617e-05, | |
| "loss": 5.9351, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 5.99934196472168, | |
| "eval_runtime": 4.3193, | |
| "eval_samples_per_second": 231.518, | |
| "eval_steps_per_second": 14.586, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.309531048661484e-05, | |
| "loss": 5.9126, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.30651474129735e-05, | |
| "loss": 5.9191, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 5.963631629943848, | |
| "eval_runtime": 6.2259, | |
| "eval_samples_per_second": 160.621, | |
| "eval_steps_per_second": 10.119, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.3034984339332166e-05, | |
| "loss": 5.9279, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.300482126569083e-05, | |
| "loss": 5.9058, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 5.989487171173096, | |
| "eval_runtime": 4.3475, | |
| "eval_samples_per_second": 230.019, | |
| "eval_steps_per_second": 14.491, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.29746581920495e-05, | |
| "loss": 5.9151, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.294449511840816e-05, | |
| "loss": 5.9031, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 5.9690752029418945, | |
| "eval_runtime": 4.1678, | |
| "eval_samples_per_second": 239.936, | |
| "eval_steps_per_second": 15.116, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.2914332044766834e-05, | |
| "loss": 5.9153, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.288422929727278e-05, | |
| "loss": 5.9167, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 5.953476428985596, | |
| "eval_runtime": 4.2534, | |
| "eval_samples_per_second": 235.107, | |
| "eval_steps_per_second": 14.812, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.2854066223631444e-05, | |
| "loss": 5.8958, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.282390314999011e-05, | |
| "loss": 5.9013, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 5.934565544128418, | |
| "eval_runtime": 4.1119, | |
| "eval_samples_per_second": 243.194, | |
| "eval_steps_per_second": 15.321, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.279374007634878e-05, | |
| "loss": 5.8967, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.276357700270744e-05, | |
| "loss": 5.9066, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 5.935710906982422, | |
| "eval_runtime": 4.1492, | |
| "eval_samples_per_second": 241.009, | |
| "eval_steps_per_second": 15.184, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.2733413929066105e-05, | |
| "loss": 5.9031, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.270325085542477e-05, | |
| "loss": 5.8929, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 5.922500133514404, | |
| "eval_runtime": 3.9626, | |
| "eval_samples_per_second": 252.362, | |
| "eval_steps_per_second": 15.899, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.2673148107930715e-05, | |
| "loss": 5.9005, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.264298503428938e-05, | |
| "loss": 5.9015, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 5.941558361053467, | |
| "eval_runtime": 4.1057, | |
| "eval_samples_per_second": 243.562, | |
| "eval_steps_per_second": 15.344, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.261282196064805e-05, | |
| "loss": 5.8931, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.2582658887006715e-05, | |
| "loss": 5.8834, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 5.9397172927856445, | |
| "eval_runtime": 4.1106, | |
| "eval_samples_per_second": 243.275, | |
| "eval_steps_per_second": 15.326, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.2552495813365376e-05, | |
| "loss": 5.8849, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.252239306587133e-05, | |
| "loss": 5.8941, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 5.900291919708252, | |
| "eval_runtime": 4.2978, | |
| "eval_samples_per_second": 232.678, | |
| "eval_steps_per_second": 14.659, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.249222999222999e-05, | |
| "loss": 5.8869, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.246206691858866e-05, | |
| "loss": 5.8926, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 5.94087028503418, | |
| "eval_runtime": 4.2807, | |
| "eval_samples_per_second": 233.609, | |
| "eval_steps_per_second": 14.717, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.2431903844947326e-05, | |
| "loss": 5.8719, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.2401801097453276e-05, | |
| "loss": 5.8807, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 5.909360408782959, | |
| "eval_runtime": 4.3061, | |
| "eval_samples_per_second": 232.228, | |
| "eval_steps_per_second": 14.63, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.2371638023811936e-05, | |
| "loss": 5.8892, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.234147495017061e-05, | |
| "loss": 5.8809, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 5.925731658935547, | |
| "eval_runtime": 4.3535, | |
| "eval_samples_per_second": 229.703, | |
| "eval_steps_per_second": 14.471, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.231131187652927e-05, | |
| "loss": 5.8775, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.228120912903521e-05, | |
| "loss": 5.8816, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 5.949062347412109, | |
| "eval_runtime": 6.324, | |
| "eval_samples_per_second": 158.127, | |
| "eval_steps_per_second": 9.962, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.2251046055393886e-05, | |
| "loss": 5.8887, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.2220882981752546e-05, | |
| "loss": 5.8612, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 5.9013543128967285, | |
| "eval_runtime": 4.2793, | |
| "eval_samples_per_second": 233.683, | |
| "eval_steps_per_second": 14.722, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.2190719908111213e-05, | |
| "loss": 5.876, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.216055683446988e-05, | |
| "loss": 5.8685, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 5.895120143890381, | |
| "eval_runtime": 4.4394, | |
| "eval_samples_per_second": 225.255, | |
| "eval_steps_per_second": 14.191, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.213039376082855e-05, | |
| "loss": 5.8975, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.210029101333449e-05, | |
| "loss": 5.8759, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 5.904821872711182, | |
| "eval_runtime": 6.1491, | |
| "eval_samples_per_second": 162.626, | |
| "eval_steps_per_second": 10.245, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.207012793969316e-05, | |
| "loss": 5.8635, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.2039964866051824e-05, | |
| "loss": 5.875, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 5.9182329177856445, | |
| "eval_runtime": 4.3366, | |
| "eval_samples_per_second": 230.597, | |
| "eval_steps_per_second": 14.528, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.200980179241049e-05, | |
| "loss": 5.8747, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.197963871876915e-05, | |
| "loss": 5.8686, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 5.91906213760376, | |
| "eval_runtime": 4.3148, | |
| "eval_samples_per_second": 231.759, | |
| "eval_steps_per_second": 14.601, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.194953597127511e-05, | |
| "loss": 5.8716, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.191937289763377e-05, | |
| "loss": 5.8808, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 5.845741271972656, | |
| "eval_runtime": 4.3065, | |
| "eval_samples_per_second": 232.206, | |
| "eval_steps_per_second": 14.629, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.1889209823992435e-05, | |
| "loss": 5.8677, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.18590467503511e-05, | |
| "loss": 5.8624, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 5.901210308074951, | |
| "eval_runtime": 4.2572, | |
| "eval_samples_per_second": 234.896, | |
| "eval_steps_per_second": 14.798, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.182888367670977e-05, | |
| "loss": 5.8513, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.179872060306843e-05, | |
| "loss": 5.865, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 5.93388557434082, | |
| "eval_runtime": 4.3004, | |
| "eval_samples_per_second": 232.539, | |
| "eval_steps_per_second": 14.65, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.17685575294271e-05, | |
| "loss": 5.8666, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.173839445578576e-05, | |
| "loss": 5.8595, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 5.921290874481201, | |
| "eval_runtime": 4.3562, | |
| "eval_samples_per_second": 229.559, | |
| "eval_steps_per_second": 14.462, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.170823138214443e-05, | |
| "loss": 5.8616, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.167812863465038e-05, | |
| "loss": 5.8664, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 5.8725409507751465, | |
| "eval_runtime": 4.2779, | |
| "eval_samples_per_second": 233.757, | |
| "eval_steps_per_second": 14.727, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.164796556100904e-05, | |
| "loss": 5.8355, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.1617802487367706e-05, | |
| "loss": 5.8529, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 5.918557643890381, | |
| "eval_runtime": 4.3121, | |
| "eval_samples_per_second": 231.903, | |
| "eval_steps_per_second": 14.61, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.1587699739873656e-05, | |
| "loss": 5.8408, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.155753666623232e-05, | |
| "loss": 5.8419, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 5.910894870758057, | |
| "eval_runtime": 4.3311, | |
| "eval_samples_per_second": 230.888, | |
| "eval_steps_per_second": 14.546, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.152737359259098e-05, | |
| "loss": 5.8523, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.149721051894965e-05, | |
| "loss": 5.8436, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 5.868130207061768, | |
| "eval_runtime": 4.3137, | |
| "eval_samples_per_second": 231.819, | |
| "eval_steps_per_second": 14.605, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.146704744530832e-05, | |
| "loss": 5.8501, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.143694469781427e-05, | |
| "loss": 5.8394, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 5.902928829193115, | |
| "eval_runtime": 4.3712, | |
| "eval_samples_per_second": 228.77, | |
| "eval_steps_per_second": 14.412, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.140678162417293e-05, | |
| "loss": 5.843, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.13766185505316e-05, | |
| "loss": 5.8433, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 5.870312690734863, | |
| "eval_runtime": 4.2876, | |
| "eval_samples_per_second": 233.229, | |
| "eval_steps_per_second": 14.693, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.134645547689026e-05, | |
| "loss": 5.8436, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.131629240324893e-05, | |
| "loss": 5.8415, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 5.892139434814453, | |
| "eval_runtime": 4.3156, | |
| "eval_samples_per_second": 231.716, | |
| "eval_steps_per_second": 14.598, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.1286129329607595e-05, | |
| "loss": 5.8496, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.125602658211354e-05, | |
| "loss": 5.8489, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 5.9164910316467285, | |
| "eval_runtime": 4.382, | |
| "eval_samples_per_second": 228.207, | |
| "eval_steps_per_second": 14.377, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.1225863508472204e-05, | |
| "loss": 5.8353, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.119570043483087e-05, | |
| "loss": 5.8531, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 5.896515846252441, | |
| "eval_runtime": 4.3161, | |
| "eval_samples_per_second": 231.693, | |
| "eval_steps_per_second": 14.597, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.116553736118954e-05, | |
| "loss": 5.833, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.11353742875482e-05, | |
| "loss": 5.8285, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 5.857729911804199, | |
| "eval_runtime": 4.3275, | |
| "eval_samples_per_second": 231.083, | |
| "eval_steps_per_second": 14.558, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.110521121390687e-05, | |
| "loss": 5.8368, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.107504814026553e-05, | |
| "loss": 5.8258, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 5.907439231872559, | |
| "eval_runtime": 4.3373, | |
| "eval_samples_per_second": 230.556, | |
| "eval_steps_per_second": 14.525, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.10448850666242e-05, | |
| "loss": 5.8369, | |
| "step": 148500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.101478231913015e-05, | |
| "loss": 5.8342, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 5.867617130279541, | |
| "eval_runtime": 4.3431, | |
| "eval_samples_per_second": 230.249, | |
| "eval_steps_per_second": 14.506, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.0984619245488816e-05, | |
| "loss": 5.8303, | |
| "step": 149500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.0954456171847476e-05, | |
| "loss": 5.8182, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 5.870373725891113, | |
| "eval_runtime": 4.346, | |
| "eval_samples_per_second": 230.099, | |
| "eval_steps_per_second": 14.496, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.092429309820614e-05, | |
| "loss": 5.8311, | |
| "step": 150500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.089419035071209e-05, | |
| "loss": 5.8423, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 5.850360870361328, | |
| "eval_runtime": 4.3581, | |
| "eval_samples_per_second": 229.46, | |
| "eval_steps_per_second": 14.456, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.086402727707076e-05, | |
| "loss": 5.8341, | |
| "step": 151500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.083386420342942e-05, | |
| "loss": 5.8201, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 5.889283180236816, | |
| "eval_runtime": 6.4869, | |
| "eval_samples_per_second": 154.156, | |
| "eval_steps_per_second": 9.712, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.080370112978809e-05, | |
| "loss": 5.8177, | |
| "step": 152500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.0773538056146754e-05, | |
| "loss": 5.8277, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 5.80609130859375, | |
| "eval_runtime": 4.3836, | |
| "eval_samples_per_second": 228.121, | |
| "eval_steps_per_second": 14.372, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.0743374982505414e-05, | |
| "loss": 5.8206, | |
| "step": 153500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.071321190886409e-05, | |
| "loss": 5.8245, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 5.86394739151001, | |
| "eval_runtime": 4.2559, | |
| "eval_samples_per_second": 234.966, | |
| "eval_steps_per_second": 14.803, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.068310916137003e-05, | |
| "loss": 5.8145, | |
| "step": 154500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.06529460877287e-05, | |
| "loss": 5.8244, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 5.874474048614502, | |
| "eval_runtime": 4.2932, | |
| "eval_samples_per_second": 232.925, | |
| "eval_steps_per_second": 14.674, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.0622783014087364e-05, | |
| "loss": 5.828, | |
| "step": 155500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.059261994044603e-05, | |
| "loss": 5.8241, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 5.891319274902344, | |
| "eval_runtime": 4.1898, | |
| "eval_samples_per_second": 238.672, | |
| "eval_steps_per_second": 15.036, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.0562517192951974e-05, | |
| "loss": 5.8099, | |
| "step": 156500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.053235411931065e-05, | |
| "loss": 5.816, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 5.805520534515381, | |
| "eval_runtime": 4.1865, | |
| "eval_samples_per_second": 238.861, | |
| "eval_steps_per_second": 15.048, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.050219104566931e-05, | |
| "loss": 5.8202, | |
| "step": 157500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.0472027972027975e-05, | |
| "loss": 5.8128, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 5.84921407699585, | |
| "eval_runtime": 5.9007, | |
| "eval_samples_per_second": 169.472, | |
| "eval_steps_per_second": 10.677, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.044186489838664e-05, | |
| "loss": 5.8166, | |
| "step": 158500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.041170182474531e-05, | |
| "loss": 5.8186, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 5.864505290985107, | |
| "eval_runtime": 4.302, | |
| "eval_samples_per_second": 232.451, | |
| "eval_steps_per_second": 14.644, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.038159907725125e-05, | |
| "loss": 5.7966, | |
| "step": 159500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.035143600360992e-05, | |
| "loss": 5.8179, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 5.826276779174805, | |
| "eval_runtime": 4.3186, | |
| "eval_samples_per_second": 231.558, | |
| "eval_steps_per_second": 14.588, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.0321272929968586e-05, | |
| "loss": 5.8101, | |
| "step": 160500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.0291109856327246e-05, | |
| "loss": 5.8193, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 5.851203918457031, | |
| "eval_runtime": 6.3135, | |
| "eval_samples_per_second": 158.39, | |
| "eval_steps_per_second": 9.979, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.0261007108833195e-05, | |
| "loss": 5.8154, | |
| "step": 161500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.023084403519186e-05, | |
| "loss": 5.7945, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 5.839649677276611, | |
| "eval_runtime": 4.357, | |
| "eval_samples_per_second": 229.515, | |
| "eval_steps_per_second": 14.459, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.020068096155053e-05, | |
| "loss": 5.801, | |
| "step": 162500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.017051788790919e-05, | |
| "loss": 5.804, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 5.798958778381348, | |
| "eval_runtime": 4.3729, | |
| "eval_samples_per_second": 228.679, | |
| "eval_steps_per_second": 14.407, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.014035481426786e-05, | |
| "loss": 5.8083, | |
| "step": 163500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.0110252066773806e-05, | |
| "loss": 5.8002, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 5.807581424713135, | |
| "eval_runtime": 6.5612, | |
| "eval_samples_per_second": 152.412, | |
| "eval_steps_per_second": 9.602, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.008008899313247e-05, | |
| "loss": 5.8106, | |
| "step": 164500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.004992591949114e-05, | |
| "loss": 5.8056, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 5.79323673248291, | |
| "eval_runtime": 4.3218, | |
| "eval_samples_per_second": 231.385, | |
| "eval_steps_per_second": 14.577, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.001976284584981e-05, | |
| "loss": 5.8112, | |
| "step": 165500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.998966009835575e-05, | |
| "loss": 5.7934, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 5.81195592880249, | |
| "eval_runtime": 4.3688, | |
| "eval_samples_per_second": 228.895, | |
| "eval_steps_per_second": 14.42, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.9959497024714423e-05, | |
| "loss": 5.7962, | |
| "step": 166500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.9929333951073084e-05, | |
| "loss": 5.8154, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 5.7888407707214355, | |
| "eval_runtime": 4.3098, | |
| "eval_samples_per_second": 232.032, | |
| "eval_steps_per_second": 14.618, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.9899170877431744e-05, | |
| "loss": 5.802, | |
| "step": 167500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.986900780379042e-05, | |
| "loss": 5.8044, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 5.808478355407715, | |
| "eval_runtime": 4.3839, | |
| "eval_samples_per_second": 228.11, | |
| "eval_steps_per_second": 14.371, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.983884473014908e-05, | |
| "loss": 5.7986, | |
| "step": 168500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.980874198265503e-05, | |
| "loss": 5.8019, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 5.862877368927002, | |
| "eval_runtime": 4.306, | |
| "eval_samples_per_second": 232.233, | |
| "eval_steps_per_second": 14.631, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.9778578909013694e-05, | |
| "loss": 5.7873, | |
| "step": 169500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.974841583537236e-05, | |
| "loss": 5.7818, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 5.815363883972168, | |
| "eval_runtime": 6.2718, | |
| "eval_samples_per_second": 159.444, | |
| "eval_steps_per_second": 10.045, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.971825276173102e-05, | |
| "loss": 5.801, | |
| "step": 170500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.968808968808969e-05, | |
| "loss": 5.8158, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 5.889772415161133, | |
| "eval_runtime": 4.3105, | |
| "eval_samples_per_second": 231.99, | |
| "eval_steps_per_second": 14.615, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.965798694059564e-05, | |
| "loss": 5.7831, | |
| "step": 171500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.9627823866954305e-05, | |
| "loss": 5.7964, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 5.8176398277282715, | |
| "eval_runtime": 4.2897, | |
| "eval_samples_per_second": 233.118, | |
| "eval_steps_per_second": 14.686, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.9597660793312965e-05, | |
| "loss": 5.8032, | |
| "step": 172500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.956749771967164e-05, | |
| "loss": 5.7874, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 5.859738349914551, | |
| "eval_runtime": 4.2313, | |
| "eval_samples_per_second": 236.336, | |
| "eval_steps_per_second": 14.889, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.953739497217758e-05, | |
| "loss": 5.7942, | |
| "step": 173500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.950723189853625e-05, | |
| "loss": 5.7831, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 5.804076194763184, | |
| "eval_runtime": 4.3301, | |
| "eval_samples_per_second": 230.94, | |
| "eval_steps_per_second": 14.549, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.9477068824894915e-05, | |
| "loss": 5.7912, | |
| "step": 174500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.9446905751253576e-05, | |
| "loss": 5.7917, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 5.769659042358398, | |
| "eval_runtime": 4.3337, | |
| "eval_samples_per_second": 230.752, | |
| "eval_steps_per_second": 14.537, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.941674267761224e-05, | |
| "loss": 5.7979, | |
| "step": 175500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.938663993011819e-05, | |
| "loss": 5.7897, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 5.812716007232666, | |
| "eval_runtime": 6.3065, | |
| "eval_samples_per_second": 158.566, | |
| "eval_steps_per_second": 9.99, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.935647685647686e-05, | |
| "loss": 5.7918, | |
| "step": 176500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.932631378283552e-05, | |
| "loss": 5.787, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 5.8294172286987305, | |
| "eval_runtime": 4.4089, | |
| "eval_samples_per_second": 226.814, | |
| "eval_steps_per_second": 14.289, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.929615070919419e-05, | |
| "loss": 5.78, | |
| "step": 177500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.926598763555285e-05, | |
| "loss": 5.7881, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 5.794092178344727, | |
| "eval_runtime": 4.3295, | |
| "eval_samples_per_second": 230.971, | |
| "eval_steps_per_second": 14.551, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.92358848880588e-05, | |
| "loss": 5.776, | |
| "step": 178500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.920572181441747e-05, | |
| "loss": 5.7757, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 5.8026957511901855, | |
| "eval_runtime": 6.3375, | |
| "eval_samples_per_second": 157.79, | |
| "eval_steps_per_second": 9.941, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.917555874077614e-05, | |
| "loss": 5.7966, | |
| "step": 179500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.91453956671348e-05, | |
| "loss": 5.7837, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 5.851541519165039, | |
| "eval_runtime": 4.3261, | |
| "eval_samples_per_second": 231.153, | |
| "eval_steps_per_second": 14.563, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.9115232593493464e-05, | |
| "loss": 5.7852, | |
| "step": 180500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.908506951985213e-05, | |
| "loss": 5.7766, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 5.806175708770752, | |
| "eval_runtime": 4.2789, | |
| "eval_samples_per_second": 233.704, | |
| "eval_steps_per_second": 14.723, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.90549064462108e-05, | |
| "loss": 5.7912, | |
| "step": 181500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.902474337256946e-05, | |
| "loss": 5.7799, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 5.806212425231934, | |
| "eval_runtime": 4.4158, | |
| "eval_samples_per_second": 226.461, | |
| "eval_steps_per_second": 14.267, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.899464062507541e-05, | |
| "loss": 5.787, | |
| "step": 182500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.896453787758136e-05, | |
| "loss": 5.7831, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 5.78677225112915, | |
| "eval_runtime": 4.3143, | |
| "eval_samples_per_second": 231.789, | |
| "eval_steps_per_second": 14.603, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.8934374803940024e-05, | |
| "loss": 5.7735, | |
| "step": 183500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.890421173029869e-05, | |
| "loss": 5.7758, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 5.771059513092041, | |
| "eval_runtime": 4.2501, | |
| "eval_samples_per_second": 235.289, | |
| "eval_steps_per_second": 14.823, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.887404865665735e-05, | |
| "loss": 5.7717, | |
| "step": 184500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.884388558301602e-05, | |
| "loss": 5.7854, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 5.744887828826904, | |
| "eval_runtime": 4.38, | |
| "eval_samples_per_second": 228.313, | |
| "eval_steps_per_second": 14.384, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.881378283552197e-05, | |
| "loss": 5.7759, | |
| "step": 185500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.8783619761880635e-05, | |
| "loss": 5.782, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 5.777120113372803, | |
| "eval_runtime": 4.3199, | |
| "eval_samples_per_second": 231.487, | |
| "eval_steps_per_second": 14.584, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.8753456688239295e-05, | |
| "loss": 5.7735, | |
| "step": 186500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.872329361459797e-05, | |
| "loss": 5.7806, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 5.791393280029297, | |
| "eval_runtime": 4.2777, | |
| "eval_samples_per_second": 233.768, | |
| "eval_steps_per_second": 14.727, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.869319086710391e-05, | |
| "loss": 5.7717, | |
| "step": 187500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.866302779346258e-05, | |
| "loss": 5.7649, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 5.816986560821533, | |
| "eval_runtime": 6.3859, | |
| "eval_samples_per_second": 156.596, | |
| "eval_steps_per_second": 9.866, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.8632864719821245e-05, | |
| "loss": 5.7693, | |
| "step": 188500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.8602701646179906e-05, | |
| "loss": 5.776, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 5.79604959487915, | |
| "eval_runtime": 4.3399, | |
| "eval_samples_per_second": 230.421, | |
| "eval_steps_per_second": 14.516, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.857253857253857e-05, | |
| "loss": 5.7631, | |
| "step": 189500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.854243582504452e-05, | |
| "loss": 5.7604, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 5.783555507659912, | |
| "eval_runtime": 4.4137, | |
| "eval_samples_per_second": 226.565, | |
| "eval_steps_per_second": 14.274, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.851227275140319e-05, | |
| "loss": 5.7713, | |
| "step": 190500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.848210967776185e-05, | |
| "loss": 5.7778, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 5.775600433349609, | |
| "eval_runtime": 4.2997, | |
| "eval_samples_per_second": 232.575, | |
| "eval_steps_per_second": 14.652, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.845194660412052e-05, | |
| "loss": 5.7759, | |
| "step": 191500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.842178353047918e-05, | |
| "loss": 5.7705, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 5.826145648956299, | |
| "eval_runtime": 4.2643, | |
| "eval_samples_per_second": 234.504, | |
| "eval_steps_per_second": 14.774, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.839162045683785e-05, | |
| "loss": 5.7729, | |
| "step": 192500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.836145738319652e-05, | |
| "loss": 5.7658, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 5.824615001678467, | |
| "eval_runtime": 4.3664, | |
| "eval_samples_per_second": 229.021, | |
| "eval_steps_per_second": 14.428, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.833135463570247e-05, | |
| "loss": 5.767, | |
| "step": 193500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.830119156206113e-05, | |
| "loss": 5.7687, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 5.796684741973877, | |
| "eval_runtime": 4.322, | |
| "eval_samples_per_second": 231.375, | |
| "eval_steps_per_second": 14.577, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.8271028488419794e-05, | |
| "loss": 5.7601, | |
| "step": 194500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.824086541477846e-05, | |
| "loss": 5.7589, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 5.798003673553467, | |
| "eval_runtime": 6.0617, | |
| "eval_samples_per_second": 164.97, | |
| "eval_steps_per_second": 10.393, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.821070234113713e-05, | |
| "loss": 5.7691, | |
| "step": 195500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.818053926749579e-05, | |
| "loss": 5.7713, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 5.799909591674805, | |
| "eval_runtime": 4.3023, | |
| "eval_samples_per_second": 232.433, | |
| "eval_steps_per_second": 14.643, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.815043652000174e-05, | |
| "loss": 5.7676, | |
| "step": 196500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.8120273446360404e-05, | |
| "loss": 5.7616, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 5.801938533782959, | |
| "eval_runtime": 4.062, | |
| "eval_samples_per_second": 246.183, | |
| "eval_steps_per_second": 15.51, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.8090110372719065e-05, | |
| "loss": 5.7518, | |
| "step": 197500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.805994729907774e-05, | |
| "loss": 5.7643, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 5.786435127258301, | |
| "eval_runtime": 4.2697, | |
| "eval_samples_per_second": 234.21, | |
| "eval_steps_per_second": 14.755, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.802984455158368e-05, | |
| "loss": 5.7582, | |
| "step": 198500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.799968147794235e-05, | |
| "loss": 5.7634, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 5.755306720733643, | |
| "eval_runtime": 4.4039, | |
| "eval_samples_per_second": 227.072, | |
| "eval_steps_per_second": 14.306, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.7969518404301015e-05, | |
| "loss": 5.7523, | |
| "step": 199500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 3.793935533065968e-05, | |
| "loss": 5.7582, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 5.787529468536377, | |
| "eval_runtime": 4.2787, | |
| "eval_samples_per_second": 233.717, | |
| "eval_steps_per_second": 14.724, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.790919225701834e-05, | |
| "loss": 5.7647, | |
| "step": 200500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.7879029183377016e-05, | |
| "loss": 5.7548, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 5.7919721603393555, | |
| "eval_runtime": 4.347, | |
| "eval_samples_per_second": 230.043, | |
| "eval_steps_per_second": 14.493, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.7848866109735676e-05, | |
| "loss": 5.7659, | |
| "step": 201500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.781870303609434e-05, | |
| "loss": 5.7602, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 5.796759605407715, | |
| "eval_runtime": 4.367, | |
| "eval_samples_per_second": 228.988, | |
| "eval_steps_per_second": 14.426, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.778860028860029e-05, | |
| "loss": 5.7507, | |
| "step": 202500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.7758497541106235e-05, | |
| "loss": 5.7575, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 5.792579174041748, | |
| "eval_runtime": 4.2917, | |
| "eval_samples_per_second": 233.009, | |
| "eval_steps_per_second": 14.68, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.77283344674649e-05, | |
| "loss": 5.7526, | |
| "step": 203500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.769817139382357e-05, | |
| "loss": 5.76, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 5.783504962921143, | |
| "eval_runtime": 4.2736, | |
| "eval_samples_per_second": 233.996, | |
| "eval_steps_per_second": 14.742, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.7668008320182236e-05, | |
| "loss": 5.7642, | |
| "step": 204500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.7637845246540896e-05, | |
| "loss": 5.7455, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 5.809587478637695, | |
| "eval_runtime": 6.5273, | |
| "eval_samples_per_second": 153.202, | |
| "eval_steps_per_second": 9.652, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 3.760774249904685e-05, | |
| "loss": 5.7621, | |
| "step": 205500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.757757942540551e-05, | |
| "loss": 5.7508, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 5.8115620613098145, | |
| "eval_runtime": 4.3241, | |
| "eval_samples_per_second": 231.263, | |
| "eval_steps_per_second": 14.57, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.754741635176418e-05, | |
| "loss": 5.7566, | |
| "step": 206500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.751725327812285e-05, | |
| "loss": 5.7472, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 5.75007963180542, | |
| "eval_runtime": 4.2843, | |
| "eval_samples_per_second": 233.408, | |
| "eval_steps_per_second": 14.705, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.7487090204481514e-05, | |
| "loss": 5.7621, | |
| "step": 207500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.745698745698746e-05, | |
| "loss": 5.7459, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 5.7589802742004395, | |
| "eval_runtime": 4.249, | |
| "eval_samples_per_second": 235.35, | |
| "eval_steps_per_second": 14.827, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.7426824383346124e-05, | |
| "loss": 5.748, | |
| "step": 208500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.739666130970479e-05, | |
| "loss": 5.7457, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 5.755953788757324, | |
| "eval_runtime": 4.381, | |
| "eval_samples_per_second": 228.257, | |
| "eval_steps_per_second": 14.38, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.736649823606346e-05, | |
| "loss": 5.7559, | |
| "step": 209500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.733633516242212e-05, | |
| "loss": 5.7514, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 5.743694305419922, | |
| "eval_runtime": 4.3893, | |
| "eval_samples_per_second": 227.825, | |
| "eval_steps_per_second": 14.353, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.730623241492807e-05, | |
| "loss": 5.7522, | |
| "step": 210500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.7276069341286734e-05, | |
| "loss": 5.758, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 5.809187889099121, | |
| "eval_runtime": 4.3578, | |
| "eval_samples_per_second": 229.472, | |
| "eval_steps_per_second": 14.457, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.7245906267645394e-05, | |
| "loss": 5.7386, | |
| "step": 211500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.721574319400407e-05, | |
| "loss": 5.7412, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 5.790631294250488, | |
| "eval_runtime": 6.9155, | |
| "eval_samples_per_second": 144.603, | |
| "eval_steps_per_second": 9.11, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.718564044651001e-05, | |
| "loss": 5.7447, | |
| "step": 212500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.715547737286868e-05, | |
| "loss": 5.7564, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 5.766078472137451, | |
| "eval_runtime": 4.3057, | |
| "eval_samples_per_second": 232.248, | |
| "eval_steps_per_second": 14.632, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.7125314299227345e-05, | |
| "loss": 5.7403, | |
| "step": 213500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.7095211551733294e-05, | |
| "loss": 5.7473, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 5.826783657073975, | |
| "eval_runtime": 4.2915, | |
| "eval_samples_per_second": 233.02, | |
| "eval_steps_per_second": 14.68, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.7065048478091955e-05, | |
| "loss": 5.7359, | |
| "step": 214500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.703488540445063e-05, | |
| "loss": 5.7439, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 5.752542018890381, | |
| "eval_runtime": 6.2452, | |
| "eval_samples_per_second": 160.123, | |
| "eval_steps_per_second": 10.088, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.700472233080929e-05, | |
| "loss": 5.7517, | |
| "step": 215500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.6974559257167956e-05, | |
| "loss": 5.7482, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 5.75383996963501, | |
| "eval_runtime": 4.2741, | |
| "eval_samples_per_second": 233.968, | |
| "eval_steps_per_second": 14.74, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.694439618352662e-05, | |
| "loss": 5.7552, | |
| "step": 216500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.691429343603257e-05, | |
| "loss": 5.7498, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 5.778792858123779, | |
| "eval_runtime": 4.3819, | |
| "eval_samples_per_second": 228.21, | |
| "eval_steps_per_second": 14.377, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.688413036239123e-05, | |
| "loss": 5.7418, | |
| "step": 217500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.68539672887499e-05, | |
| "loss": 5.7276, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 5.756528377532959, | |
| "eval_runtime": 4.3385, | |
| "eval_samples_per_second": 230.495, | |
| "eval_steps_per_second": 14.521, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.6823804215108566e-05, | |
| "loss": 5.7493, | |
| "step": 218500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.6793641141467226e-05, | |
| "loss": 5.7559, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 5.770053863525391, | |
| "eval_runtime": 4.3798, | |
| "eval_samples_per_second": 228.323, | |
| "eval_steps_per_second": 14.384, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.676347806782589e-05, | |
| "loss": 5.7309, | |
| "step": 219500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.673331499418456e-05, | |
| "loss": 5.7466, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 5.751831531524658, | |
| "eval_runtime": 4.3885, | |
| "eval_samples_per_second": 227.868, | |
| "eval_steps_per_second": 14.356, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.670315192054323e-05, | |
| "loss": 5.754, | |
| "step": 220500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.667304917304917e-05, | |
| "loss": 5.7441, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 5.766170024871826, | |
| "eval_runtime": 4.4111, | |
| "eval_samples_per_second": 226.7, | |
| "eval_steps_per_second": 14.282, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.6642886099407844e-05, | |
| "loss": 5.739, | |
| "step": 221500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.6612723025766504e-05, | |
| "loss": 5.7352, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 5.74399995803833, | |
| "eval_runtime": 4.3561, | |
| "eval_samples_per_second": 229.561, | |
| "eval_steps_per_second": 14.462, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.658255995212517e-05, | |
| "loss": 5.7368, | |
| "step": 222500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.655239687848384e-05, | |
| "loss": 5.739, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 5.763323783874512, | |
| "eval_runtime": 4.3227, | |
| "eval_samples_per_second": 231.335, | |
| "eval_steps_per_second": 14.574, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.652229413098979e-05, | |
| "loss": 5.7403, | |
| "step": 223500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.649213105734845e-05, | |
| "loss": 5.7391, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 5.7649736404418945, | |
| "eval_runtime": 4.3622, | |
| "eval_samples_per_second": 229.24, | |
| "eval_steps_per_second": 14.442, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.646196798370712e-05, | |
| "loss": 5.744, | |
| "step": 224500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 3.643180491006578e-05, | |
| "loss": 5.7363, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 5.732951641082764, | |
| "eval_runtime": 4.3989, | |
| "eval_samples_per_second": 227.33, | |
| "eval_steps_per_second": 14.322, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.6401702162571724e-05, | |
| "loss": 5.7421, | |
| "step": 225500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.63715390889304e-05, | |
| "loss": 5.7414, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 5.73438024520874, | |
| "eval_runtime": 4.3577, | |
| "eval_samples_per_second": 229.481, | |
| "eval_steps_per_second": 14.457, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.634137601528906e-05, | |
| "loss": 5.7274, | |
| "step": 226500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.6311212941647725e-05, | |
| "loss": 5.7385, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 5.781483173370361, | |
| "eval_runtime": 4.3808, | |
| "eval_samples_per_second": 228.267, | |
| "eval_steps_per_second": 14.381, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.628104986800639e-05, | |
| "loss": 5.7458, | |
| "step": 227500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.625094712051234e-05, | |
| "loss": 5.7521, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 5.737205982208252, | |
| "eval_runtime": 4.3898, | |
| "eval_samples_per_second": 227.799, | |
| "eval_steps_per_second": 14.351, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.6220784046871e-05, | |
| "loss": 5.7272, | |
| "step": 228500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.619062097322967e-05, | |
| "loss": 5.7258, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 5.73113489151001, | |
| "eval_runtime": 4.264, | |
| "eval_samples_per_second": 234.524, | |
| "eval_steps_per_second": 14.775, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.6160457899588336e-05, | |
| "loss": 5.7354, | |
| "step": 229500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.6130294825947e-05, | |
| "loss": 5.7256, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 5.771120071411133, | |
| "eval_runtime": 4.2667, | |
| "eval_samples_per_second": 234.371, | |
| "eval_steps_per_second": 14.765, | |
| "step": 230000 | |
| } | |
| ], | |
| "max_steps": 828828, | |
| "num_train_epochs": 3, | |
| "total_flos": 2.819512759114629e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |