| { | |
| "best_metric": 0.5579236745834351, | |
| "best_model_checkpoint": "deberta-v3-large-finetuned-squadv2/checkpoint-3620", | |
| "epoch": 2.550269740068661, | |
| "eval_steps": 20, | |
| "global_step": 5200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.0000000000000002e-07, | |
| "loss": 6.0843, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 6.0629, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 6.0196, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 5.9309, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 5.768, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 5.4721, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.3900000000000002e-06, | |
| "loss": 5.1112, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.5900000000000002e-06, | |
| "loss": 4.6482, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.79e-06, | |
| "loss": 4.2226, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9900000000000004e-06, | |
| "loss": 3.7989, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.19e-06, | |
| "loss": 3.4023, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.39e-06, | |
| "loss": 3.0793, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.59e-06, | |
| "loss": 2.5037, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.7900000000000004e-06, | |
| "loss": 1.9528, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.99e-06, | |
| "loss": 1.736, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 3.1900000000000004e-06, | |
| "loss": 1.5742, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 3.3900000000000006e-06, | |
| "loss": 1.4485, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 3.58e-06, | |
| "loss": 1.4103, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.7800000000000002e-06, | |
| "loss": 1.3205, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.980000000000001e-06, | |
| "loss": 1.2793, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.18e-06, | |
| "loss": 1.1896, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.38e-06, | |
| "loss": 1.1228, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.57e-06, | |
| "loss": 1.0661, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.77e-06, | |
| "loss": 1.0459, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.970000000000001e-06, | |
| "loss": 1.0062, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 5.1700000000000005e-06, | |
| "loss": 0.9441, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 5.370000000000001e-06, | |
| "loss": 0.9871, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 5.570000000000001e-06, | |
| "loss": 0.9291, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 5.77e-06, | |
| "loss": 0.9635, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 5.9700000000000004e-06, | |
| "loss": 0.9874, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 6.17e-06, | |
| "loss": 0.8922, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.370000000000001e-06, | |
| "loss": 0.9304, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.570000000000001e-06, | |
| "loss": 0.8742, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.770000000000001e-06, | |
| "loss": 0.8423, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 6.97e-06, | |
| "loss": 0.8286, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 7.17e-06, | |
| "loss": 0.8192, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 7.370000000000001e-06, | |
| "loss": 0.8451, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 7.57e-06, | |
| "loss": 0.7954, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 7.77e-06, | |
| "loss": 0.8322, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 7.970000000000002e-06, | |
| "loss": 0.8318, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 8.17e-06, | |
| "loss": 0.8396, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 8.370000000000001e-06, | |
| "loss": 0.7922, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 8.570000000000001e-06, | |
| "loss": 0.7931, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.77e-06, | |
| "loss": 0.7942, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 8.97e-06, | |
| "loss": 0.8017, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 9.17e-06, | |
| "loss": 0.7346, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 9.370000000000002e-06, | |
| "loss": 0.6792, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 9.57e-06, | |
| "loss": 0.8069, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 9.770000000000001e-06, | |
| "loss": 0.8058, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 9.970000000000001e-06, | |
| "loss": 0.8398, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 9.95952380952381e-06, | |
| "loss": 0.8148, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 9.911904761904762e-06, | |
| "loss": 0.7888, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.864285714285715e-06, | |
| "loss": 0.7423, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 9.816666666666667e-06, | |
| "loss": 0.7855, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 9.76904761904762e-06, | |
| "loss": 0.7303, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.721428571428573e-06, | |
| "loss": 0.7156, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 9.673809523809525e-06, | |
| "loss": 0.7542, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.626190476190477e-06, | |
| "loss": 0.723, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.57857142857143e-06, | |
| "loss": 0.7025, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 9.530952380952381e-06, | |
| "loss": 0.7755, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 9.483333333333335e-06, | |
| "loss": 0.7225, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.435714285714286e-06, | |
| "loss": 0.7389, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 9.388095238095238e-06, | |
| "loss": 0.7083, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.340476190476191e-06, | |
| "loss": 0.6863, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.292857142857144e-06, | |
| "loss": 0.7167, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.245238095238096e-06, | |
| "loss": 0.7006, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 9.197619047619049e-06, | |
| "loss": 0.7058, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 9.15e-06, | |
| "loss": 0.7068, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.102380952380954e-06, | |
| "loss": 0.713, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.054761904761905e-06, | |
| "loss": 0.743, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.007142857142857e-06, | |
| "loss": 0.6588, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.95952380952381e-06, | |
| "loss": 0.7087, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.911904761904763e-06, | |
| "loss": 0.7172, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.864285714285715e-06, | |
| "loss": 0.6935, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 8.816666666666668e-06, | |
| "loss": 0.7049, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 8.76904761904762e-06, | |
| "loss": 0.6749, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 8.721428571428571e-06, | |
| "loss": 0.6773, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 8.673809523809524e-06, | |
| "loss": 0.7028, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 8.626190476190478e-06, | |
| "loss": 0.6754, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 8.57857142857143e-06, | |
| "loss": 0.744, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 8.530952380952382e-06, | |
| "loss": 0.6175, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 8.483333333333334e-06, | |
| "loss": 0.6788, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 8.435714285714286e-06, | |
| "loss": 0.6728, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.388095238095239e-06, | |
| "loss": 0.7451, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.34047619047619e-06, | |
| "loss": 0.6392, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.292857142857144e-06, | |
| "loss": 0.6522, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 8.245238095238097e-06, | |
| "loss": 0.6665, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 8.197619047619048e-06, | |
| "loss": 0.6178, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 8.15e-06, | |
| "loss": 0.6699, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 8.102380952380953e-06, | |
| "loss": 0.6543, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 8.054761904761905e-06, | |
| "loss": 0.6724, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 8.007142857142858e-06, | |
| "loss": 0.7194, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 7.959523809523811e-06, | |
| "loss": 0.6695, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 7.911904761904763e-06, | |
| "loss": 0.6542, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 7.864285714285716e-06, | |
| "loss": 0.6986, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 7.816666666666667e-06, | |
| "loss": 0.6527, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 7.769047619047619e-06, | |
| "loss": 0.6036, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.721428571428572e-06, | |
| "loss": 0.6309, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.673809523809524e-06, | |
| "loss": 0.6647, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.626190476190477e-06, | |
| "loss": 0.6625, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.5785714285714295e-06, | |
| "loss": 0.673, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 7.530952380952381e-06, | |
| "loss": 0.6615, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 7.483333333333333e-06, | |
| "loss": 0.5771, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 7.435714285714286e-06, | |
| "loss": 0.5824, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 7.388095238095239e-06, | |
| "loss": 0.5038, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 7.3404761904761914e-06, | |
| "loss": 0.5524, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 7.292857142857144e-06, | |
| "loss": 0.5903, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 7.245238095238096e-06, | |
| "loss": 0.609, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 7.197619047619048e-06, | |
| "loss": 0.5303, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 7.15e-06, | |
| "loss": 0.5637, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 7.1023809523809525e-06, | |
| "loss": 0.5513, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 7.054761904761906e-06, | |
| "loss": 0.5648, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 7.007142857142858e-06, | |
| "loss": 0.5907, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 6.9595238095238106e-06, | |
| "loss": 0.5791, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 6.911904761904763e-06, | |
| "loss": 0.5485, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 6.8642857142857145e-06, | |
| "loss": 0.5279, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 6.816666666666667e-06, | |
| "loss": 0.5283, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 6.769047619047619e-06, | |
| "loss": 0.5294, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 6.721428571428572e-06, | |
| "loss": 0.4647, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 6.673809523809525e-06, | |
| "loss": 0.5571, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 6.626190476190477e-06, | |
| "loss": 0.5188, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6.578571428571429e-06, | |
| "loss": 0.5099, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 6.530952380952381e-06, | |
| "loss": 0.5371, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 6.483333333333334e-06, | |
| "loss": 0.55, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 6.435714285714286e-06, | |
| "loss": 0.5546, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 6.3880952380952384e-06, | |
| "loss": 0.5465, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 6.340476190476192e-06, | |
| "loss": 0.4944, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 6.292857142857144e-06, | |
| "loss": 0.5248, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 6.245238095238096e-06, | |
| "loss": 0.5585, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 6.197619047619048e-06, | |
| "loss": 0.5562, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 6.15e-06, | |
| "loss": 0.5402, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 6.102380952380953e-06, | |
| "loss": 0.5674, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.054761904761905e-06, | |
| "loss": 0.5641, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 6.0071428571428584e-06, | |
| "loss": 0.4678, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 5.959523809523809e-06, | |
| "loss": 0.5162, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 5.911904761904762e-06, | |
| "loss": 0.5826, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 5.864285714285715e-06, | |
| "loss": 0.518, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 5.816666666666667e-06, | |
| "loss": 0.512, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 5.7690476190476196e-06, | |
| "loss": 0.5848, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 5.721428571428572e-06, | |
| "loss": 0.526, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 5.673809523809525e-06, | |
| "loss": 0.5419, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 5.626190476190476e-06, | |
| "loss": 0.5642, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 5.578571428571429e-06, | |
| "loss": 0.5126, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 5.5309523809523815e-06, | |
| "loss": 0.5687, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 5.483333333333334e-06, | |
| "loss": 0.5498, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.435714285714286e-06, | |
| "loss": 0.5213, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 5.388095238095239e-06, | |
| "loss": 0.575, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 5.34047619047619e-06, | |
| "loss": 0.5524, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 5.292857142857143e-06, | |
| "loss": 0.5304, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 5.245238095238096e-06, | |
| "loss": 0.4706, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 5.197619047619048e-06, | |
| "loss": 0.5716, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 5.150000000000001e-06, | |
| "loss": 0.4976, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 5.102380952380953e-06, | |
| "loss": 0.5022, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 5.0547619047619055e-06, | |
| "loss": 0.556, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 5.007142857142857e-06, | |
| "loss": 0.5023, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 4.95952380952381e-06, | |
| "loss": 0.5613, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 4.911904761904762e-06, | |
| "loss": 0.6031, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 4.864285714285715e-06, | |
| "loss": 0.5346, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 4.816666666666667e-06, | |
| "loss": 0.5665, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 4.769047619047619e-06, | |
| "loss": 0.5293, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 0.5739259123802185, | |
| "eval_runtime": 277.0719, | |
| "eval_samples_per_second": 43.133, | |
| "eval_steps_per_second": 5.392, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.721428571428572e-06, | |
| "loss": 0.5106, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "eval_loss": 0.5783331990242004, | |
| "eval_runtime": 276.9686, | |
| "eval_samples_per_second": 43.149, | |
| "eval_steps_per_second": 5.394, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 4.673809523809525e-06, | |
| "loss": 0.5338, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 0.5718061327934265, | |
| "eval_runtime": 276.8816, | |
| "eval_samples_per_second": 43.163, | |
| "eval_steps_per_second": 5.396, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 4.626190476190476e-06, | |
| "loss": 0.5128, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 0.5826650261878967, | |
| "eval_runtime": 276.9662, | |
| "eval_samples_per_second": 43.15, | |
| "eval_steps_per_second": 5.394, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.5785714285714285e-06, | |
| "loss": 0.5205, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 0.6044849157333374, | |
| "eval_runtime": 276.8959, | |
| "eval_samples_per_second": 43.161, | |
| "eval_steps_per_second": 5.396, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.530952380952382e-06, | |
| "loss": 0.5114, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 0.5880448818206787, | |
| "eval_runtime": 276.8767, | |
| "eval_samples_per_second": 43.164, | |
| "eval_steps_per_second": 5.396, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.483333333333333e-06, | |
| "loss": 0.5072, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_loss": 0.5788173079490662, | |
| "eval_runtime": 276.8866, | |
| "eval_samples_per_second": 43.162, | |
| "eval_steps_per_second": 5.396, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.435714285714286e-06, | |
| "loss": 0.5512, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 0.5863245725631714, | |
| "eval_runtime": 276.8934, | |
| "eval_samples_per_second": 43.161, | |
| "eval_steps_per_second": 5.396, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 4.388095238095238e-06, | |
| "loss": 0.4723, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 0.5898299813270569, | |
| "eval_runtime": 276.9062, | |
| "eval_samples_per_second": 43.159, | |
| "eval_steps_per_second": 5.395, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.340476190476191e-06, | |
| "loss": 0.5011, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 0.5917273163795471, | |
| "eval_runtime": 276.8734, | |
| "eval_samples_per_second": 43.164, | |
| "eval_steps_per_second": 5.396, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 4.292857142857143e-06, | |
| "loss": 0.5419, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_loss": 0.6026594042778015, | |
| "eval_runtime": 276.8544, | |
| "eval_samples_per_second": 43.167, | |
| "eval_steps_per_second": 5.396, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 4.245238095238095e-06, | |
| "loss": 0.5425, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 0.5699217915534973, | |
| "eval_runtime": 276.8159, | |
| "eval_samples_per_second": 43.173, | |
| "eval_steps_per_second": 5.397, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.1976190476190485e-06, | |
| "loss": 0.5703, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 0.5897491574287415, | |
| "eval_runtime": 276.8228, | |
| "eval_samples_per_second": 43.172, | |
| "eval_steps_per_second": 5.397, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 4.15e-06, | |
| "loss": 0.4646, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 0.5916581153869629, | |
| "eval_runtime": 276.8047, | |
| "eval_samples_per_second": 43.175, | |
| "eval_steps_per_second": 5.397, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 4.1023809523809525e-06, | |
| "loss": 0.4652, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 0.5745313167572021, | |
| "eval_runtime": 276.8115, | |
| "eval_samples_per_second": 43.174, | |
| "eval_steps_per_second": 5.397, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 4.054761904761905e-06, | |
| "loss": 0.5323, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 0.5859553217887878, | |
| "eval_runtime": 276.8471, | |
| "eval_samples_per_second": 43.168, | |
| "eval_steps_per_second": 5.396, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 4.007142857142857e-06, | |
| "loss": 0.5129, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 0.5655719637870789, | |
| "eval_runtime": 276.8529, | |
| "eval_samples_per_second": 43.167, | |
| "eval_steps_per_second": 5.396, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 3.95952380952381e-06, | |
| "loss": 0.5441, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 0.5642224550247192, | |
| "eval_runtime": 276.8896, | |
| "eval_samples_per_second": 43.162, | |
| "eval_steps_per_second": 5.396, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.911904761904762e-06, | |
| "loss": 0.5624, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 0.5872688293457031, | |
| "eval_runtime": 276.8743, | |
| "eval_samples_per_second": 43.164, | |
| "eval_steps_per_second": 5.396, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 3.864285714285715e-06, | |
| "loss": 0.4645, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 0.5890788435935974, | |
| "eval_runtime": 276.8469, | |
| "eval_samples_per_second": 43.168, | |
| "eval_steps_per_second": 5.396, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 3.816666666666667e-06, | |
| "loss": 0.5577, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 0.5816096663475037, | |
| "eval_runtime": 276.8584, | |
| "eval_samples_per_second": 43.166, | |
| "eval_steps_per_second": 5.396, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.7690476190476192e-06, | |
| "loss": 0.5199, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_loss": 0.5579236745834351, | |
| "eval_runtime": 276.8666, | |
| "eval_samples_per_second": 43.165, | |
| "eval_steps_per_second": 5.396, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.721428571428572e-06, | |
| "loss": 0.5061, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 0.5837463140487671, | |
| "eval_runtime": 276.8995, | |
| "eval_samples_per_second": 43.16, | |
| "eval_steps_per_second": 5.395, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 3.673809523809524e-06, | |
| "loss": 0.484, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 0.5721494555473328, | |
| "eval_runtime": 277.0285, | |
| "eval_samples_per_second": 43.14, | |
| "eval_steps_per_second": 5.393, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.6261904761904764e-06, | |
| "loss": 0.5095, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 0.5820609927177429, | |
| "eval_runtime": 277.1157, | |
| "eval_samples_per_second": 43.126, | |
| "eval_steps_per_second": 5.391, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.5785714285714292e-06, | |
| "loss": 0.5342, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 0.5602211356163025, | |
| "eval_runtime": 277.1392, | |
| "eval_samples_per_second": 43.123, | |
| "eval_steps_per_second": 5.391, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 3.530952380952381e-06, | |
| "loss": 0.5435, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 0.5910717248916626, | |
| "eval_runtime": 277.1237, | |
| "eval_samples_per_second": 43.125, | |
| "eval_steps_per_second": 5.391, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 3.4833333333333336e-06, | |
| "loss": 0.5288, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_loss": 0.5647350549697876, | |
| "eval_runtime": 277.1519, | |
| "eval_samples_per_second": 43.121, | |
| "eval_steps_per_second": 5.391, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.435714285714286e-06, | |
| "loss": 0.5476, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 0.5733036398887634, | |
| "eval_runtime": 277.012, | |
| "eval_samples_per_second": 43.143, | |
| "eval_steps_per_second": 5.393, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 3.388095238095238e-06, | |
| "loss": 0.5199, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 0.5674840807914734, | |
| "eval_runtime": 276.9911, | |
| "eval_samples_per_second": 43.146, | |
| "eval_steps_per_second": 5.394, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 3.3404761904761908e-06, | |
| "loss": 0.5067, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 0.5838811993598938, | |
| "eval_runtime": 276.9655, | |
| "eval_samples_per_second": 43.15, | |
| "eval_steps_per_second": 5.394, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.292857142857143e-06, | |
| "loss": 0.5418, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 0.5757073163986206, | |
| "eval_runtime": 277.0012, | |
| "eval_samples_per_second": 43.144, | |
| "eval_steps_per_second": 5.393, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 3.2452380952380955e-06, | |
| "loss": 0.4965, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 0.5763747692108154, | |
| "eval_runtime": 276.9993, | |
| "eval_samples_per_second": 43.145, | |
| "eval_steps_per_second": 5.394, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.197619047619048e-06, | |
| "loss": 0.5273, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 0.5905867218971252, | |
| "eval_runtime": 276.9687, | |
| "eval_samples_per_second": 43.149, | |
| "eval_steps_per_second": 5.394, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.1500000000000003e-06, | |
| "loss": 0.5808, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_loss": 0.5761615633964539, | |
| "eval_runtime": 276.9979, | |
| "eval_samples_per_second": 43.145, | |
| "eval_steps_per_second": 5.394, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 3.1023809523809527e-06, | |
| "loss": 0.5161, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 0.5611954927444458, | |
| "eval_runtime": 276.9358, | |
| "eval_samples_per_second": 43.154, | |
| "eval_steps_per_second": 5.395, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.0547619047619047e-06, | |
| "loss": 0.4863, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 0.5804067254066467, | |
| "eval_runtime": 276.9544, | |
| "eval_samples_per_second": 43.152, | |
| "eval_steps_per_second": 5.394, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 3.0071428571428575e-06, | |
| "loss": 0.4827, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 0.584104597568512, | |
| "eval_runtime": 276.9708, | |
| "eval_samples_per_second": 43.149, | |
| "eval_steps_per_second": 5.394, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 2.95952380952381e-06, | |
| "loss": 0.4643, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 0.5822347402572632, | |
| "eval_runtime": 276.9742, | |
| "eval_samples_per_second": 43.148, | |
| "eval_steps_per_second": 5.394, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.911904761904762e-06, | |
| "loss": 0.5029, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 0.6052400469779968, | |
| "eval_runtime": 276.9537, | |
| "eval_samples_per_second": 43.152, | |
| "eval_steps_per_second": 5.394, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 2.8642857142857143e-06, | |
| "loss": 0.509, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 0.5799996852874756, | |
| "eval_runtime": 276.9867, | |
| "eval_samples_per_second": 43.146, | |
| "eval_steps_per_second": 5.394, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.816666666666667e-06, | |
| "loss": 0.5382, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 0.5645180940628052, | |
| "eval_runtime": 277.0026, | |
| "eval_samples_per_second": 43.144, | |
| "eval_steps_per_second": 5.393, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 2.7690476190476195e-06, | |
| "loss": 0.469, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 0.5685124397277832, | |
| "eval_runtime": 276.9786, | |
| "eval_samples_per_second": 43.148, | |
| "eval_steps_per_second": 5.394, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.7214285714285714e-06, | |
| "loss": 0.5032, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 0.5778502225875854, | |
| "eval_runtime": 277.0026, | |
| "eval_samples_per_second": 43.144, | |
| "eval_steps_per_second": 5.393, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.6738095238095243e-06, | |
| "loss": 0.5171, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.5685559511184692, | |
| "eval_runtime": 277.0003, | |
| "eval_samples_per_second": 43.144, | |
| "eval_steps_per_second": 5.393, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.6261904761904767e-06, | |
| "loss": 0.3938, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_loss": 0.5889346599578857, | |
| "eval_runtime": 277.0343, | |
| "eval_samples_per_second": 43.139, | |
| "eval_steps_per_second": 5.393, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 2.5785714285714286e-06, | |
| "loss": 0.4321, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 0.6039115190505981, | |
| "eval_runtime": 276.9943, | |
| "eval_samples_per_second": 43.145, | |
| "eval_steps_per_second": 5.394, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 2.530952380952381e-06, | |
| "loss": 0.4185, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 0.599577009677887, | |
| "eval_runtime": 277.0077, | |
| "eval_samples_per_second": 43.143, | |
| "eval_steps_per_second": 5.393, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.4833333333333334e-06, | |
| "loss": 0.4782, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 0.580022931098938, | |
| "eval_runtime": 277.0163, | |
| "eval_samples_per_second": 43.142, | |
| "eval_steps_per_second": 5.393, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.435714285714286e-06, | |
| "loss": 0.424, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_loss": 0.6373934745788574, | |
| "eval_runtime": 277.0011, | |
| "eval_samples_per_second": 43.144, | |
| "eval_steps_per_second": 5.393, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 2.388095238095238e-06, | |
| "loss": 0.3766, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 0.6096173524856567, | |
| "eval_runtime": 276.9796, | |
| "eval_samples_per_second": 43.148, | |
| "eval_steps_per_second": 5.394, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.3404761904761906e-06, | |
| "loss": 0.415, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_loss": 0.6220654249191284, | |
| "eval_runtime": 277.0595, | |
| "eval_samples_per_second": 43.135, | |
| "eval_steps_per_second": 5.392, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 2.292857142857143e-06, | |
| "loss": 0.4352, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 0.615013599395752, | |
| "eval_runtime": 277.0601, | |
| "eval_samples_per_second": 43.135, | |
| "eval_steps_per_second": 5.392, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.2452380952380954e-06, | |
| "loss": 0.4336, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_loss": 0.6055351495742798, | |
| "eval_runtime": 277.0825, | |
| "eval_samples_per_second": 43.132, | |
| "eval_steps_per_second": 5.392, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.1976190476190478e-06, | |
| "loss": 0.4289, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_loss": 0.6138429641723633, | |
| "eval_runtime": 277.0898, | |
| "eval_samples_per_second": 43.13, | |
| "eval_steps_per_second": 5.392, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 2.15e-06, | |
| "loss": 0.4433, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 0.5946049094200134, | |
| "eval_runtime": 277.0747, | |
| "eval_samples_per_second": 43.133, | |
| "eval_steps_per_second": 5.392, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 2.1023809523809526e-06, | |
| "loss": 0.4478, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 0.611806333065033, | |
| "eval_runtime": 277.0164, | |
| "eval_samples_per_second": 43.142, | |
| "eval_steps_per_second": 5.393, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.054761904761905e-06, | |
| "loss": 0.4787, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 0.5969259738922119, | |
| "eval_runtime": 277.0423, | |
| "eval_samples_per_second": 43.138, | |
| "eval_steps_per_second": 5.393, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 2.0071428571428573e-06, | |
| "loss": 0.4432, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_loss": 0.6047642230987549, | |
| "eval_runtime": 277.0355, | |
| "eval_samples_per_second": 43.139, | |
| "eval_steps_per_second": 5.393, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 1.9595238095238097e-06, | |
| "loss": 0.4319, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "eval_loss": 0.5948361158370972, | |
| "eval_runtime": 277.1353, | |
| "eval_samples_per_second": 43.123, | |
| "eval_steps_per_second": 5.391, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.911904761904762e-06, | |
| "loss": 0.3939, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 0.6115566492080688, | |
| "eval_runtime": 277.1102, | |
| "eval_samples_per_second": 43.127, | |
| "eval_steps_per_second": 5.391, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.8642857142857143e-06, | |
| "loss": 0.3921, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_loss": 0.608245849609375, | |
| "eval_runtime": 277.1416, | |
| "eval_samples_per_second": 43.122, | |
| "eval_steps_per_second": 5.391, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 1.816666666666667e-06, | |
| "loss": 0.4381, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 0.6282362937927246, | |
| "eval_runtime": 277.0787, | |
| "eval_samples_per_second": 43.132, | |
| "eval_steps_per_second": 5.392, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.769047619047619e-06, | |
| "loss": 0.4461, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "eval_loss": 0.6083888411521912, | |
| "eval_runtime": 277.0933, | |
| "eval_samples_per_second": 43.13, | |
| "eval_steps_per_second": 5.392, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 1.7214285714285717e-06, | |
| "loss": 0.4012, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_loss": 0.6091529726982117, | |
| "eval_runtime": 277.0771, | |
| "eval_samples_per_second": 43.132, | |
| "eval_steps_per_second": 5.392, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.6738095238095239e-06, | |
| "loss": 0.3849, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_loss": 0.6152328848838806, | |
| "eval_runtime": 277.2346, | |
| "eval_samples_per_second": 43.108, | |
| "eval_steps_per_second": 5.389, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.6261904761904763e-06, | |
| "loss": 0.4178, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 0.6003779172897339, | |
| "eval_runtime": 277.2625, | |
| "eval_samples_per_second": 43.104, | |
| "eval_steps_per_second": 5.388, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 1.5785714285714287e-06, | |
| "loss": 0.4163, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "eval_loss": 0.6059258580207825, | |
| "eval_runtime": 277.3365, | |
| "eval_samples_per_second": 43.092, | |
| "eval_steps_per_second": 5.387, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.530952380952381e-06, | |
| "loss": 0.4006, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 0.6115380525588989, | |
| "eval_runtime": 277.2201, | |
| "eval_samples_per_second": 43.11, | |
| "eval_steps_per_second": 5.389, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.4833333333333337e-06, | |
| "loss": 0.4225, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "eval_loss": 0.6130145192146301, | |
| "eval_runtime": 277.4178, | |
| "eval_samples_per_second": 43.079, | |
| "eval_steps_per_second": 5.385, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.4357142857142859e-06, | |
| "loss": 0.4008, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "eval_loss": 0.6094552278518677, | |
| "eval_runtime": 277.5161, | |
| "eval_samples_per_second": 43.064, | |
| "eval_steps_per_second": 5.383, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.388095238095238e-06, | |
| "loss": 0.4706, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 0.6135911345481873, | |
| "eval_runtime": 277.6184, | |
| "eval_samples_per_second": 43.048, | |
| "eval_steps_per_second": 5.381, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.3404761904761906e-06, | |
| "loss": 0.3902, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 0.6103312373161316, | |
| "eval_runtime": 277.532, | |
| "eval_samples_per_second": 43.062, | |
| "eval_steps_per_second": 5.383, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.2928571428571428e-06, | |
| "loss": 0.4048, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "eval_loss": 0.608475923538208, | |
| "eval_runtime": 277.3473, | |
| "eval_samples_per_second": 43.09, | |
| "eval_steps_per_second": 5.387, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.2452380952380954e-06, | |
| "loss": 0.4411, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "eval_loss": 0.6138780117034912, | |
| "eval_runtime": 277.4196, | |
| "eval_samples_per_second": 43.079, | |
| "eval_steps_per_second": 5.385, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.1976190476190478e-06, | |
| "loss": 0.403, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_loss": 0.6047297120094299, | |
| "eval_runtime": 277.4316, | |
| "eval_samples_per_second": 43.077, | |
| "eval_steps_per_second": 5.385, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 1.1500000000000002e-06, | |
| "loss": 0.4799, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_loss": 0.6043194532394409, | |
| "eval_runtime": 277.378, | |
| "eval_samples_per_second": 43.086, | |
| "eval_steps_per_second": 5.386, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 1.1023809523809524e-06, | |
| "loss": 0.4316, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_loss": 0.5959681868553162, | |
| "eval_runtime": 277.4868, | |
| "eval_samples_per_second": 43.069, | |
| "eval_steps_per_second": 5.384, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.0547619047619048e-06, | |
| "loss": 0.4198, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_loss": 0.6030734181404114, | |
| "eval_runtime": 277.3901, | |
| "eval_samples_per_second": 43.084, | |
| "eval_steps_per_second": 5.386, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.0071428571428572e-06, | |
| "loss": 0.4254, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_loss": 0.60329669713974, | |
| "eval_runtime": 277.3302, | |
| "eval_samples_per_second": 43.093, | |
| "eval_steps_per_second": 5.387, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 9.595238095238096e-07, | |
| "loss": 0.387, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "eval_loss": 0.611955463886261, | |
| "eval_runtime": 277.4816, | |
| "eval_samples_per_second": 43.07, | |
| "eval_steps_per_second": 5.384, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 9.119047619047621e-07, | |
| "loss": 0.3882, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "eval_loss": 0.612755298614502, | |
| "eval_runtime": 277.4062, | |
| "eval_samples_per_second": 43.081, | |
| "eval_steps_per_second": 5.386, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 8.642857142857144e-07, | |
| "loss": 0.4307, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_loss": 0.6149932742118835, | |
| "eval_runtime": 277.4451, | |
| "eval_samples_per_second": 43.075, | |
| "eval_steps_per_second": 5.385, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 8.166666666666668e-07, | |
| "loss": 0.434, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_loss": 0.6077226400375366, | |
| "eval_runtime": 277.2986, | |
| "eval_samples_per_second": 43.098, | |
| "eval_steps_per_second": 5.388, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 7.690476190476191e-07, | |
| "loss": 0.4225, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "eval_loss": 0.6070570945739746, | |
| "eval_runtime": 277.4566, | |
| "eval_samples_per_second": 43.073, | |
| "eval_steps_per_second": 5.385, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 7.214285714285715e-07, | |
| "loss": 0.4134, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 0.6035702228546143, | |
| "eval_runtime": 277.4001, | |
| "eval_samples_per_second": 43.082, | |
| "eval_steps_per_second": 5.386, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 6.738095238095238e-07, | |
| "loss": 0.3846, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_loss": 0.612420380115509, | |
| "eval_runtime": 277.4205, | |
| "eval_samples_per_second": 43.079, | |
| "eval_steps_per_second": 5.385, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 6.261904761904762e-07, | |
| "loss": 0.3943, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_loss": 0.6291103959083557, | |
| "eval_runtime": 277.2666, | |
| "eval_samples_per_second": 43.103, | |
| "eval_steps_per_second": 5.388, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 5.785714285714286e-07, | |
| "loss": 0.4455, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "eval_loss": 0.6184937953948975, | |
| "eval_runtime": 277.2863, | |
| "eval_samples_per_second": 43.1, | |
| "eval_steps_per_second": 5.388, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 5.30952380952381e-07, | |
| "loss": 0.4104, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_loss": 0.6063624620437622, | |
| "eval_runtime": 277.3406, | |
| "eval_samples_per_second": 43.091, | |
| "eval_steps_per_second": 5.387, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 4.833333333333334e-07, | |
| "loss": 0.4158, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_loss": 0.6095247268676758, | |
| "eval_runtime": 277.4398, | |
| "eval_samples_per_second": 43.076, | |
| "eval_steps_per_second": 5.385, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 4.357142857142858e-07, | |
| "loss": 0.4135, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "eval_loss": 0.6154703497886658, | |
| "eval_runtime": 277.3849, | |
| "eval_samples_per_second": 43.085, | |
| "eval_steps_per_second": 5.386, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 3.8809523809523813e-07, | |
| "loss": 0.3789, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_loss": 0.6208740472793579, | |
| "eval_runtime": 277.33, | |
| "eval_samples_per_second": 43.093, | |
| "eval_steps_per_second": 5.387, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 3.404761904761905e-07, | |
| "loss": 0.418, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_loss": 0.6106104850769043, | |
| "eval_runtime": 277.377, | |
| "eval_samples_per_second": 43.086, | |
| "eval_steps_per_second": 5.386, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 2.9285714285714287e-07, | |
| "loss": 0.3931, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "eval_loss": 0.604749858379364, | |
| "eval_runtime": 277.377, | |
| "eval_samples_per_second": 43.086, | |
| "eval_steps_per_second": 5.386, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 2.4523809523809526e-07, | |
| "loss": 0.4289, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_loss": 0.6055382490158081, | |
| "eval_runtime": 277.4628, | |
| "eval_samples_per_second": 43.072, | |
| "eval_steps_per_second": 5.385, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 1.9761904761904763e-07, | |
| "loss": 0.4051, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_loss": 0.6083624958992004, | |
| "eval_runtime": 277.3533, | |
| "eval_samples_per_second": 43.089, | |
| "eval_steps_per_second": 5.387, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 1.5000000000000002e-07, | |
| "loss": 0.4217, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "eval_loss": 0.611778736114502, | |
| "eval_runtime": 277.4092, | |
| "eval_samples_per_second": 43.081, | |
| "eval_steps_per_second": 5.386, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 1.023809523809524e-07, | |
| "loss": 0.3843, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 0.613944411277771, | |
| "eval_runtime": 277.3668, | |
| "eval_samples_per_second": 43.087, | |
| "eval_steps_per_second": 5.386, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 5.4761904761904766e-08, | |
| "loss": 0.4435, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 0.6125811338424683, | |
| "eval_runtime": 277.4188, | |
| "eval_samples_per_second": 43.079, | |
| "eval_steps_per_second": 5.385, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.142857142857144e-09, | |
| "loss": 0.4274, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_loss": 0.6120193600654602, | |
| "eval_runtime": 277.4157, | |
| "eval_samples_per_second": 43.08, | |
| "eval_steps_per_second": 5.385, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "step": 5200, | |
| "total_flos": 3.09073923350188e+17, | |
| "train_loss": 0.820626282783655, | |
| "train_runtime": 52836.9017, | |
| "train_samples_per_second": 6.299, | |
| "train_steps_per_second": 0.098 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 5200, | |
| "num_train_epochs": 3, | |
| "save_steps": 20, | |
| "total_flos": 3.09073923350188e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |