| { | |
| "best_metric": 0.7937971949577332, | |
| "best_model_checkpoint": "models/checkpoints/checkpoint-14500", | |
| "epoch": 7.611468311245243, | |
| "global_step": 14500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9895013123359582e-05, | |
| "loss": 1.3844, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9790026246719162e-05, | |
| "loss": 1.1178, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.9685039370078743e-05, | |
| "loss": 1.0595, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.9580052493438323e-05, | |
| "loss": 1.0309, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 1.94750656167979e-05, | |
| "loss": 1.0043, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 0.9238424897193909, | |
| "eval_runtime": 78.6171, | |
| "eval_samples_per_second": 179.77, | |
| "eval_steps_per_second": 11.244, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.937007874015748e-05, | |
| "loss": 1.0168, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.9265091863517064e-05, | |
| "loss": 0.959, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.916010498687664e-05, | |
| "loss": 0.9599, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.905511811023622e-05, | |
| "loss": 0.947, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.89501312335958e-05, | |
| "loss": 0.9886, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 0.8911218047142029, | |
| "eval_runtime": 58.2514, | |
| "eval_samples_per_second": 242.621, | |
| "eval_steps_per_second": 15.176, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.8845144356955382e-05, | |
| "loss": 0.97, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.8740157480314962e-05, | |
| "loss": 0.9091, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.8635170603674542e-05, | |
| "loss": 0.9672, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.8530183727034123e-05, | |
| "loss": 0.9028, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.8425196850393703e-05, | |
| "loss": 0.8951, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 0.85249924659729, | |
| "eval_runtime": 58.049, | |
| "eval_samples_per_second": 243.467, | |
| "eval_steps_per_second": 15.229, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.8320209973753283e-05, | |
| "loss": 0.8988, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.821522309711286e-05, | |
| "loss": 0.9257, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.811023622047244e-05, | |
| "loss": 0.9391, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.8005249343832024e-05, | |
| "loss": 0.9006, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.79002624671916e-05, | |
| "loss": 0.8434, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 0.855362594127655, | |
| "eval_runtime": 59.1417, | |
| "eval_samples_per_second": 238.968, | |
| "eval_steps_per_second": 14.947, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 1.779527559055118e-05, | |
| "loss": 0.897, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1.7690288713910762e-05, | |
| "loss": 0.9001, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.7585301837270342e-05, | |
| "loss": 0.8561, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.7480314960629923e-05, | |
| "loss": 0.8814, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 1.7375328083989503e-05, | |
| "loss": 0.84, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 0.8605416417121887, | |
| "eval_runtime": 58.7215, | |
| "eval_samples_per_second": 240.679, | |
| "eval_steps_per_second": 15.054, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.7270341207349083e-05, | |
| "loss": 0.8514, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 1.7165354330708663e-05, | |
| "loss": 0.8332, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 1.7060367454068244e-05, | |
| "loss": 0.8546, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 1.695538057742782e-05, | |
| "loss": 0.8452, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 1.68503937007874e-05, | |
| "loss": 0.8434, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 0.8366661667823792, | |
| "eval_runtime": 59.2216, | |
| "eval_samples_per_second": 238.646, | |
| "eval_steps_per_second": 14.927, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 1.6745406824146985e-05, | |
| "loss": 0.8221, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 1.6640419947506562e-05, | |
| "loss": 0.8596, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 1.6535433070866142e-05, | |
| "loss": 0.8533, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.6430446194225722e-05, | |
| "loss": 0.833, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.6325459317585303e-05, | |
| "loss": 0.8043, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 0.8364191651344299, | |
| "eval_runtime": 59.4819, | |
| "eval_samples_per_second": 237.602, | |
| "eval_steps_per_second": 14.862, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 1.6220472440944883e-05, | |
| "loss": 0.7932, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.6115485564304463e-05, | |
| "loss": 0.8283, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.6010498687664044e-05, | |
| "loss": 0.8467, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.5905511811023624e-05, | |
| "loss": 0.788, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.5800524934383204e-05, | |
| "loss": 0.761, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_loss": 0.8275307416915894, | |
| "eval_runtime": 58.9069, | |
| "eval_samples_per_second": 239.921, | |
| "eval_steps_per_second": 15.007, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.5695538057742785e-05, | |
| "loss": 0.7742, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.559055118110236e-05, | |
| "loss": 0.787, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.5485564304461945e-05, | |
| "loss": 0.7856, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.5380577427821522e-05, | |
| "loss": 0.8009, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.5275590551181102e-05, | |
| "loss": 0.7899, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 0.854367733001709, | |
| "eval_runtime": 58.9597, | |
| "eval_samples_per_second": 239.706, | |
| "eval_steps_per_second": 14.993, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 1.5170603674540683e-05, | |
| "loss": 0.8067, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 1.5065616797900265e-05, | |
| "loss": 0.7733, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 1.4960629921259843e-05, | |
| "loss": 0.7509, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 1.4855643044619424e-05, | |
| "loss": 0.7775, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 1.4750656167979002e-05, | |
| "loss": 0.7918, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_loss": 0.8410710692405701, | |
| "eval_runtime": 59.1309, | |
| "eval_samples_per_second": 239.012, | |
| "eval_steps_per_second": 14.95, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 1.4645669291338584e-05, | |
| "loss": 0.773, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 1.4540682414698165e-05, | |
| "loss": 0.7716, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.4435695538057743e-05, | |
| "loss": 0.7745, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.4330708661417324e-05, | |
| "loss": 0.7727, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 1.4225721784776904e-05, | |
| "loss": 0.7582, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_loss": 0.8356336355209351, | |
| "eval_runtime": 59.0698, | |
| "eval_samples_per_second": 239.259, | |
| "eval_steps_per_second": 14.965, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.4120734908136484e-05, | |
| "loss": 0.7688, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.4015748031496063e-05, | |
| "loss": 0.7512, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 1.3910761154855643e-05, | |
| "loss": 0.7398, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 1.3805774278215225e-05, | |
| "loss": 0.7089, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 1.3700787401574804e-05, | |
| "loss": 0.7462, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "eval_loss": 0.833259105682373, | |
| "eval_runtime": 58.7017, | |
| "eval_samples_per_second": 240.76, | |
| "eval_steps_per_second": 15.059, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 1.3595800524934384e-05, | |
| "loss": 0.7512, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 1.3490813648293963e-05, | |
| "loss": 0.7273, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 1.3385826771653545e-05, | |
| "loss": 0.7368, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 1.3280839895013125e-05, | |
| "loss": 0.7253, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 1.3175853018372704e-05, | |
| "loss": 0.7325, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "eval_loss": 0.8515605926513672, | |
| "eval_runtime": 59.4138, | |
| "eval_samples_per_second": 237.874, | |
| "eval_steps_per_second": 14.879, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 1.3070866141732284e-05, | |
| "loss": 0.7574, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 1.2965879265091864e-05, | |
| "loss": 0.7424, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 1.2860892388451445e-05, | |
| "loss": 0.7412, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 1.2755905511811025e-05, | |
| "loss": 0.7244, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1.2650918635170604e-05, | |
| "loss": 0.7218, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "eval_loss": 0.8130525946617126, | |
| "eval_runtime": 58.9752, | |
| "eval_samples_per_second": 239.643, | |
| "eval_steps_per_second": 14.989, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 1.2545931758530186e-05, | |
| "loss": 0.7289, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 1.2440944881889764e-05, | |
| "loss": 0.7444, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 1.2335958005249345e-05, | |
| "loss": 0.7574, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 1.2230971128608923e-05, | |
| "loss": 0.7504, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 1.2125984251968505e-05, | |
| "loss": 0.7344, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "eval_loss": 0.8257057666778564, | |
| "eval_runtime": 59.7911, | |
| "eval_samples_per_second": 236.373, | |
| "eval_steps_per_second": 14.785, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 1.2020997375328086e-05, | |
| "loss": 0.7239, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 1.1916010498687664e-05, | |
| "loss": 0.7317, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 1.1811023622047245e-05, | |
| "loss": 0.7116, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 1.1706036745406827e-05, | |
| "loss": 0.7089, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 1.1601049868766405e-05, | |
| "loss": 0.7383, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "eval_loss": 0.8250786066055298, | |
| "eval_runtime": 59.5177, | |
| "eval_samples_per_second": 237.459, | |
| "eval_steps_per_second": 14.853, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 1.1496062992125985e-05, | |
| "loss": 0.6883, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 1.1391076115485564e-05, | |
| "loss": 0.7232, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 1.1286089238845146e-05, | |
| "loss": 0.6993, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 1.1181102362204725e-05, | |
| "loss": 0.7232, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 1.1076115485564305e-05, | |
| "loss": 0.6693, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "eval_loss": 0.8354575037956238, | |
| "eval_runtime": 59.8496, | |
| "eval_samples_per_second": 236.142, | |
| "eval_steps_per_second": 14.77, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 1.0971128608923884e-05, | |
| "loss": 0.6875, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 1.0866141732283466e-05, | |
| "loss": 0.6938, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 1.0761154855643046e-05, | |
| "loss": 0.7113, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 1.0656167979002625e-05, | |
| "loss": 0.6836, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 1.0551181102362205e-05, | |
| "loss": 0.7016, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "eval_loss": 0.8524064421653748, | |
| "eval_runtime": 58.806, | |
| "eval_samples_per_second": 240.333, | |
| "eval_steps_per_second": 15.032, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 1.0446194225721787e-05, | |
| "loss": 0.7148, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 1.0341207349081366e-05, | |
| "loss": 0.7192, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 1.0236220472440946e-05, | |
| "loss": 0.7382, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 1.0131233595800525e-05, | |
| "loss": 0.7054, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 1.0026246719160107e-05, | |
| "loss": 0.7045, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_loss": 0.825893223285675, | |
| "eval_runtime": 58.4492, | |
| "eval_samples_per_second": 241.8, | |
| "eval_steps_per_second": 15.124, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 9.921259842519685e-06, | |
| "loss": 0.6797, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 9.816272965879266e-06, | |
| "loss": 0.6586, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 9.711286089238846e-06, | |
| "loss": 0.6772, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 9.606299212598426e-06, | |
| "loss": 0.6732, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 9.501312335958006e-06, | |
| "loss": 0.6653, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "eval_loss": 0.8119387626647949, | |
| "eval_runtime": 59.2296, | |
| "eval_samples_per_second": 238.614, | |
| "eval_steps_per_second": 14.925, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 9.396325459317585e-06, | |
| "loss": 0.6568, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 9.291338582677165e-06, | |
| "loss": 0.6598, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 9.186351706036746e-06, | |
| "loss": 0.6752, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 9.081364829396326e-06, | |
| "loss": 0.6568, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 8.976377952755906e-06, | |
| "loss": 0.6642, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "eval_loss": 0.8364242911338806, | |
| "eval_runtime": 59.3425, | |
| "eval_samples_per_second": 238.16, | |
| "eval_steps_per_second": 14.897, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 8.871391076115487e-06, | |
| "loss": 0.6672, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 8.766404199475065e-06, | |
| "loss": 0.6929, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 8.661417322834647e-06, | |
| "loss": 0.6719, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 8.556430446194226e-06, | |
| "loss": 0.6864, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 8.451443569553806e-06, | |
| "loss": 0.7038, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "eval_loss": 0.8415279984474182, | |
| "eval_runtime": 60.2905, | |
| "eval_samples_per_second": 234.415, | |
| "eval_steps_per_second": 14.662, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 8.346456692913387e-06, | |
| "loss": 0.6463, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 8.241469816272967e-06, | |
| "loss": 0.6362, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 8.136482939632546e-06, | |
| "loss": 0.6833, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "learning_rate": 8.031496062992128e-06, | |
| "loss": 0.6493, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 7.926509186351706e-06, | |
| "loss": 0.6482, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "eval_loss": 0.8445884585380554, | |
| "eval_runtime": 60.3998, | |
| "eval_samples_per_second": 233.991, | |
| "eval_steps_per_second": 14.636, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 7.821522309711287e-06, | |
| "loss": 0.6318, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 7.716535433070867e-06, | |
| "loss": 0.6638, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 7.611548556430447e-06, | |
| "loss": 0.6958, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 7.506561679790027e-06, | |
| "loss": 0.6516, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 7.401574803149607e-06, | |
| "loss": 0.6401, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "eval_loss": 0.8119750022888184, | |
| "eval_runtime": 58.8481, | |
| "eval_samples_per_second": 240.161, | |
| "eval_steps_per_second": 15.022, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 7.2965879265091864e-06, | |
| "loss": 0.6509, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 7.191601049868768e-06, | |
| "loss": 0.6664, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 7.086614173228347e-06, | |
| "loss": 0.6701, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 6.981627296587927e-06, | |
| "loss": 0.6489, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 6.876640419947507e-06, | |
| "loss": 0.6666, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "eval_loss": 0.8412150740623474, | |
| "eval_runtime": 58.9938, | |
| "eval_samples_per_second": 239.568, | |
| "eval_steps_per_second": 14.985, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 6.771653543307087e-06, | |
| "loss": 0.6648, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.6549, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 6.561679790026248e-06, | |
| "loss": 0.6372, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 6.77, | |
| "learning_rate": 6.456692913385827e-06, | |
| "loss": 0.6321, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 6.351706036745408e-06, | |
| "loss": 0.6529, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "eval_loss": 0.8355860710144043, | |
| "eval_runtime": 59.1629, | |
| "eval_samples_per_second": 238.883, | |
| "eval_steps_per_second": 14.942, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 6.246719160104987e-06, | |
| "loss": 0.6384, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 6.141732283464567e-06, | |
| "loss": 0.6409, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "learning_rate": 6.036745406824147e-06, | |
| "loss": 0.6385, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 5.931758530183728e-06, | |
| "loss": 0.639, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 5.8267716535433075e-06, | |
| "loss": 0.6462, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "eval_loss": 0.8167649507522583, | |
| "eval_runtime": 59.7264, | |
| "eval_samples_per_second": 236.629, | |
| "eval_steps_per_second": 14.801, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 5.721784776902888e-06, | |
| "loss": 0.6125, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 5.616797900262467e-06, | |
| "loss": 0.6371, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 5.511811023622048e-06, | |
| "loss": 0.6003, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 5.406824146981627e-06, | |
| "loss": 0.6322, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 5.301837270341208e-06, | |
| "loss": 0.6313, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "eval_loss": 0.8006855249404907, | |
| "eval_runtime": 60.1264, | |
| "eval_samples_per_second": 235.055, | |
| "eval_steps_per_second": 14.702, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 5.196850393700788e-06, | |
| "loss": 0.6166, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 5.091863517060368e-06, | |
| "loss": 0.6192, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 4.986876640419948e-06, | |
| "loss": 0.648, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 4.881889763779528e-06, | |
| "loss": 0.6441, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 4.776902887139108e-06, | |
| "loss": 0.64, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "eval_loss": 0.7937971949577332, | |
| "eval_runtime": 61.4082, | |
| "eval_samples_per_second": 230.149, | |
| "eval_steps_per_second": 14.395, | |
| "step": 14500 | |
| } | |
| ], | |
| "max_steps": 19050, | |
| "num_train_epochs": 10, | |
| "total_flos": 5.068483991811235e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |