| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.005, | |
| "eval_steps": 200, | |
| "global_step": 8000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.8e-05, | |
| "loss": 3.468, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.800000000000001e-05, | |
| "loss": 1.6094, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.000146, | |
| "loss": 0.7047, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00019600000000000002, | |
| "loss": 0.5096, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.000246, | |
| "loss": 0.2824, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.000296, | |
| "loss": 0.2412, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.000346, | |
| "loss": 0.2304, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00039600000000000003, | |
| "loss": 0.2296, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 0.7733328342437744, | |
| "eval_runtime": 180.822, | |
| "eval_samples_per_second": 5.53, | |
| "eval_steps_per_second": 0.348, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.000446, | |
| "loss": 0.2218, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.000496, | |
| "loss": 0.2205, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.000546, | |
| "loss": 0.2075, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.000596, | |
| "loss": 0.2097, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.000646, | |
| "loss": 0.2106, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.000696, | |
| "loss": 0.189, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.000746, | |
| "loss": 0.2029, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.000796, | |
| "loss": 0.1965, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 0.7896425127983093, | |
| "eval_runtime": 168.5574, | |
| "eval_samples_per_second": 5.933, | |
| "eval_steps_per_second": 0.374, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.000846, | |
| "loss": 0.2017, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.000896, | |
| "loss": 0.1978, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.000946, | |
| "loss": 0.1993, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.000996, | |
| "loss": 0.1952, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.000997578947368421, | |
| "loss": 0.205, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0009949473684210525, | |
| "loss": 0.2025, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0009923157894736842, | |
| "loss": 0.2041, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0009896842105263158, | |
| "loss": 0.1977, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.8415733575820923, | |
| "eval_runtime": 164.6978, | |
| "eval_samples_per_second": 6.072, | |
| "eval_steps_per_second": 0.383, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0009870526315789473, | |
| "loss": 0.2165, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.000984421052631579, | |
| "loss": 0.2, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0009817894736842106, | |
| "loss": 0.2076, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0009791578947368422, | |
| "loss": 0.1968, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0009765263157894737, | |
| "loss": 0.2049, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0009738947368421052, | |
| "loss": 0.2025, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0009712631578947369, | |
| "loss": 0.1938, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0009686315789473684, | |
| "loss": 0.196, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 0.8182218074798584, | |
| "eval_runtime": 158.2545, | |
| "eval_samples_per_second": 6.319, | |
| "eval_steps_per_second": 0.398, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.000966, | |
| "loss": 0.1932, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0009633684210526316, | |
| "loss": 0.1916, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0009607368421052631, | |
| "loss": 0.1885, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0009581052631578947, | |
| "loss": 0.2073, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0009554736842105264, | |
| "loss": 0.1932, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.000952842105263158, | |
| "loss": 0.2027, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0009502105263157895, | |
| "loss": 0.1896, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.000947578947368421, | |
| "loss": 0.2029, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.8397456407546997, | |
| "eval_runtime": 152.911, | |
| "eval_samples_per_second": 6.54, | |
| "eval_steps_per_second": 0.412, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0009449473684210527, | |
| "loss": 0.1854, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0009423157894736842, | |
| "loss": 0.1865, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0009396842105263158, | |
| "loss": 0.1802, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0009370526315789474, | |
| "loss": 0.2021, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.000934421052631579, | |
| "loss": 0.4772, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0009317894736842105, | |
| "loss": 0.5212, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0009291578947368421, | |
| "loss": 0.4989, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0009265263157894737, | |
| "loss": 0.4785, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 0.452649861574173, | |
| "eval_runtime": 174.5425, | |
| "eval_samples_per_second": 5.729, | |
| "eval_steps_per_second": 0.361, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0009238947368421052, | |
| "loss": 0.519, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.000921263157894737, | |
| "loss": 0.4156, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0009186315789473685, | |
| "loss": 0.4183, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.000916, | |
| "loss": 0.3673, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0009133684210526316, | |
| "loss": 0.3905, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0009107368421052632, | |
| "loss": 0.2184, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0009081052631578948, | |
| "loss": 0.2004, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0009054736842105263, | |
| "loss": 0.1987, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 0.503150999546051, | |
| "eval_runtime": 157.8672, | |
| "eval_samples_per_second": 6.334, | |
| "eval_steps_per_second": 0.399, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0009028421052631579, | |
| "loss": 0.1961, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0009002105263157895, | |
| "loss": 0.1809, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.000897578947368421, | |
| "loss": 0.181, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0008949473684210527, | |
| "loss": 0.1783, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0008923157894736842, | |
| "loss": 0.1798, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0008896842105263157, | |
| "loss": 0.1711, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0008870526315789473, | |
| "loss": 0.173, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.000884421052631579, | |
| "loss": 0.1639, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 0.5385903120040894, | |
| "eval_runtime": 170.0837, | |
| "eval_samples_per_second": 5.879, | |
| "eval_steps_per_second": 0.37, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0008817894736842106, | |
| "loss": 0.1624, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0008791578947368421, | |
| "loss": 0.1666, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0008765263157894738, | |
| "loss": 0.1479, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0008738947368421053, | |
| "loss": 0.1599, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0008712631578947368, | |
| "loss": 0.1592, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0008686315789473685, | |
| "loss": 0.1629, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.000866, | |
| "loss": 0.1545, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0008633684210526316, | |
| "loss": 0.1562, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 0.6111131310462952, | |
| "eval_runtime": 168.0854, | |
| "eval_samples_per_second": 5.949, | |
| "eval_steps_per_second": 0.375, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0008607368421052632, | |
| "loss": 0.1545, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0008581052631578947, | |
| "loss": 0.1599, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0008554736842105263, | |
| "loss": 0.1528, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0008528421052631578, | |
| "loss": 0.1546, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0008502105263157896, | |
| "loss": 0.1467, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0008475789473684211, | |
| "loss": 0.1607, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.0008449473684210526, | |
| "loss": 0.1452, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0008423157894736843, | |
| "loss": 0.1483, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 0.6245921850204468, | |
| "eval_runtime": 163.3861, | |
| "eval_samples_per_second": 6.12, | |
| "eval_steps_per_second": 0.386, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0008396842105263158, | |
| "loss": 0.1406, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0008370526315789474, | |
| "loss": 0.1502, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.000834421052631579, | |
| "loss": 0.1471, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0008317894736842105, | |
| "loss": 0.1382, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0008291578947368421, | |
| "loss": 0.1442, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0008265263157894737, | |
| "loss": 0.1424, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0008238947368421053, | |
| "loss": 0.146, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0008212631578947368, | |
| "loss": 0.1386, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 0.6221749782562256, | |
| "eval_runtime": 152.1153, | |
| "eval_samples_per_second": 6.574, | |
| "eval_steps_per_second": 0.414, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0008186315789473683, | |
| "loss": 0.1473, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.000816, | |
| "loss": 0.1395, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0008133684210526316, | |
| "loss": 0.1501, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0008107368421052632, | |
| "loss": 0.144, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0008081052631578948, | |
| "loss": 0.1475, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0008054736842105264, | |
| "loss": 0.1389, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0008028421052631579, | |
| "loss": 0.1404, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0008002105263157895, | |
| "loss": 0.134, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 0.6407124996185303, | |
| "eval_runtime": 156.566, | |
| "eval_samples_per_second": 6.387, | |
| "eval_steps_per_second": 0.402, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0007975789473684211, | |
| "loss": 0.1509, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0007949473684210526, | |
| "loss": 0.3648, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0007923157894736842, | |
| "loss": 0.4236, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0007896842105263158, | |
| "loss": 0.4066, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0007870526315789473, | |
| "loss": 0.4014, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0007844210526315789, | |
| "loss": 0.43, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0007817894736842105, | |
| "loss": 0.352, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0007791578947368422, | |
| "loss": 0.3437, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 0.3637486696243286, | |
| "eval_runtime": 153.8929, | |
| "eval_samples_per_second": 6.498, | |
| "eval_steps_per_second": 0.409, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0007765263157894737, | |
| "loss": 0.3056, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0007738947368421054, | |
| "loss": 0.321, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0007712631578947369, | |
| "loss": 0.1717, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0007686315789473684, | |
| "loss": 0.1569, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0007660000000000001, | |
| "loss": 0.1624, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0007633684210526316, | |
| "loss": 0.1591, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0007607368421052632, | |
| "loss": 0.1465, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0007581052631578947, | |
| "loss": 0.1422, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 0.49110493063926697, | |
| "eval_runtime": 154.3598, | |
| "eval_samples_per_second": 6.478, | |
| "eval_steps_per_second": 0.408, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0007554736842105263, | |
| "loss": 0.1447, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0007528421052631579, | |
| "loss": 0.1482, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0007502105263157894, | |
| "loss": 0.1392, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0007475789473684211, | |
| "loss": 0.1402, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.0007449473684210526, | |
| "loss": 0.1338, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.0007423157894736842, | |
| "loss": 0.1321, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.0007396842105263159, | |
| "loss": 0.1343, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0007370526315789474, | |
| "loss": 0.1239, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 0.5311547517776489, | |
| "eval_runtime": 154.495, | |
| "eval_samples_per_second": 6.473, | |
| "eval_steps_per_second": 0.408, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.000734421052631579, | |
| "loss": 0.1302, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0007317894736842106, | |
| "loss": 0.1288, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0007291578947368422, | |
| "loss": 0.1325, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0007265263157894737, | |
| "loss": 0.1254, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0007238947368421052, | |
| "loss": 0.1264, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0007212631578947369, | |
| "loss": 0.1225, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.0007186315789473684, | |
| "loss": 0.1295, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.000716, | |
| "loss": 0.1241, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 0.5532392263412476, | |
| "eval_runtime": 161.3652, | |
| "eval_samples_per_second": 6.197, | |
| "eval_steps_per_second": 0.39, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.0007133684210526316, | |
| "loss": 0.1222, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.0007107368421052631, | |
| "loss": 0.1165, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.0007081052631578947, | |
| "loss": 0.1287, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.0007054736842105264, | |
| "loss": 0.1129, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.000702842105263158, | |
| "loss": 0.116, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0007002105263157895, | |
| "loss": 0.115, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.000697578947368421, | |
| "loss": 0.1211, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0006949473684210527, | |
| "loss": 0.1175, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 0.5794956088066101, | |
| "eval_runtime": 161.0963, | |
| "eval_samples_per_second": 6.207, | |
| "eval_steps_per_second": 0.391, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0006923157894736842, | |
| "loss": 0.1117, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0006896842105263158, | |
| "loss": 0.115, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0006870526315789474, | |
| "loss": 0.1181, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0006844210526315789, | |
| "loss": 0.1191, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0006817894736842105, | |
| "loss": 0.1108, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0006791578947368421, | |
| "loss": 0.1164, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0006765263157894737, | |
| "loss": 0.1128, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0006738947368421052, | |
| "loss": 0.1199, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_loss": 0.5748582482337952, | |
| "eval_runtime": 163.5225, | |
| "eval_samples_per_second": 6.115, | |
| "eval_steps_per_second": 0.385, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.000671263157894737, | |
| "loss": 0.1165, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0006686315789473685, | |
| "loss": 0.1191, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.000666, | |
| "loss": 0.1129, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.0006633684210526316, | |
| "loss": 0.1135, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0006607368421052632, | |
| "loss": 0.1059, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0006581052631578948, | |
| "loss": 0.1212, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0006554736842105263, | |
| "loss": 0.2933, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0006528421052631579, | |
| "loss": 0.3481, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 0.39570415019989014, | |
| "eval_runtime": 164.1519, | |
| "eval_samples_per_second": 6.092, | |
| "eval_steps_per_second": 0.384, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0006502105263157895, | |
| "loss": 0.3412, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.000647578947368421, | |
| "loss": 0.3363, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0006449473684210527, | |
| "loss": 0.3672, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.0006423157894736842, | |
| "loss": 0.2955, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0006396842105263157, | |
| "loss": 0.2928, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0006370526315789473, | |
| "loss": 0.2553, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.000634421052631579, | |
| "loss": 0.2714, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0006317894736842106, | |
| "loss": 0.1408, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.4420510530471802, | |
| "eval_runtime": 166.5973, | |
| "eval_samples_per_second": 6.002, | |
| "eval_steps_per_second": 0.378, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0006291578947368421, | |
| "loss": 0.1292, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.0006265263157894738, | |
| "loss": 0.1333, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.0006238947368421053, | |
| "loss": 0.1309, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.0006212631578947368, | |
| "loss": 0.1196, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.0006186315789473685, | |
| "loss": 0.1202, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.000616, | |
| "loss": 0.1201, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.0006133684210526315, | |
| "loss": 0.1209, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.0006107368421052632, | |
| "loss": 0.1157, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_loss": 0.47497323155403137, | |
| "eval_runtime": 166.7685, | |
| "eval_samples_per_second": 5.996, | |
| "eval_steps_per_second": 0.378, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 0.0006081052631578947, | |
| "loss": 0.1178, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 0.0006054736842105263, | |
| "loss": 0.1094, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 0.0006028421052631578, | |
| "loss": 0.1092, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 0.0006002105263157896, | |
| "loss": 0.1092, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 0.0005975789473684211, | |
| "loss": 0.104, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 0.0005949473684210526, | |
| "loss": 0.1083, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 0.0005923157894736843, | |
| "loss": 0.1077, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 0.0005897894736842105, | |
| "loss": 0.111, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_loss": 0.4977476894855499, | |
| "eval_runtime": 192.3591, | |
| "eval_samples_per_second": 5.199, | |
| "eval_steps_per_second": 0.328, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 0.0005871578947368421, | |
| "loss": 0.1055, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.0005845263157894737, | |
| "loss": 0.1057, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.0005818947368421052, | |
| "loss": 0.1019, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.0005792631578947368, | |
| "loss": 0.1083, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.0005766315789473684, | |
| "loss": 0.1034, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.000574, | |
| "loss": 0.1027, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.0005713684210526315, | |
| "loss": 0.0995, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.0005687368421052633, | |
| "loss": 0.1075, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "eval_loss": 0.5218893885612488, | |
| "eval_runtime": 179.252, | |
| "eval_samples_per_second": 5.579, | |
| "eval_steps_per_second": 0.351, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 0.0005661052631578948, | |
| "loss": 0.0951, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.0005634736842105263, | |
| "loss": 0.0977, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.000560842105263158, | |
| "loss": 0.0948, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.0005582105263157895, | |
| "loss": 0.0995, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.0005555789473684211, | |
| "loss": 0.0983, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.0005529473684210526, | |
| "loss": 0.0918, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.0005503157894736842, | |
| "loss": 0.0947, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.0005476842105263158, | |
| "loss": 0.0977, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "eval_loss": 0.5334329605102539, | |
| "eval_runtime": 188.1844, | |
| "eval_samples_per_second": 5.314, | |
| "eval_steps_per_second": 0.335, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.0005450526315789473, | |
| "loss": 0.0984, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 0.000542421052631579, | |
| "loss": 0.0899, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 0.0005397894736842105, | |
| "loss": 0.0936, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 0.000537157894736842, | |
| "loss": 0.0908, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.0005345263157894738, | |
| "loss": 0.0965, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.0005318947368421053, | |
| "loss": 0.0921, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.0005292631578947369, | |
| "loss": 0.0958, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.0005266315789473685, | |
| "loss": 0.0926, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "eval_loss": 0.5344287753105164, | |
| "eval_runtime": 188.2054, | |
| "eval_samples_per_second": 5.313, | |
| "eval_steps_per_second": 0.335, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 0.000524, | |
| "loss": 0.0913, | |
| "step": 5025 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.0005213684210526316, | |
| "loss": 0.0851, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.0005187368421052631, | |
| "loss": 0.0952, | |
| "step": 5075 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.0005161052631578948, | |
| "loss": 0.226, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.0005134736842105263, | |
| "loss": 0.2836, | |
| "step": 5125 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.0005108421052631578, | |
| "loss": 0.2701, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.0005082105263157895, | |
| "loss": 0.2744, | |
| "step": 5175 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.000505578947368421, | |
| "loss": 0.2973, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "eval_loss": 0.39320918917655945, | |
| "eval_runtime": 169.1872, | |
| "eval_samples_per_second": 5.911, | |
| "eval_steps_per_second": 0.372, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 0.0005029473684210526, | |
| "loss": 0.2424, | |
| "step": 5225 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 0.0005003157894736842, | |
| "loss": 0.2401, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 0.0004976842105263158, | |
| "loss": 0.2125, | |
| "step": 5275 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 0.0004950526315789474, | |
| "loss": 0.2256, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.0004924210526315789, | |
| "loss": 0.1144, | |
| "step": 5325 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.0004897894736842106, | |
| "loss": 0.1079, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 0.0004871578947368421, | |
| "loss": 0.1099, | |
| "step": 5375 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 0.0004845263157894737, | |
| "loss": 0.1106, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "eval_loss": 0.4229947328567505, | |
| "eval_runtime": 227.4665, | |
| "eval_samples_per_second": 4.396, | |
| "eval_steps_per_second": 0.277, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 0.00048189473684210525, | |
| "loss": 0.098, | |
| "step": 5425 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 0.00047926315789473684, | |
| "loss": 0.0979, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 0.00047663157894736844, | |
| "loss": 0.099, | |
| "step": 5475 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 0.000474, | |
| "loss": 0.0984, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 0.0004713684210526316, | |
| "loss": 0.0909, | |
| "step": 5525 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.00046873684210526316, | |
| "loss": 0.0939, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.00046610526315789475, | |
| "loss": 0.0891, | |
| "step": 5575 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.00046347368421052634, | |
| "loss": 0.0897, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "eval_loss": 0.4496651291847229, | |
| "eval_runtime": 167.4869, | |
| "eval_samples_per_second": 5.971, | |
| "eval_steps_per_second": 0.376, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.0004608421052631579, | |
| "loss": 0.0896, | |
| "step": 5625 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 0.00045821052631578947, | |
| "loss": 0.0848, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 0.000455578947368421, | |
| "loss": 0.0871, | |
| "step": 5675 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 0.00045294736842105266, | |
| "loss": 0.0847, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 0.00045031578947368425, | |
| "loss": 0.0919, | |
| "step": 5725 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 0.0004476842105263158, | |
| "loss": 0.0847, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.0004450526315789474, | |
| "loss": 0.0846, | |
| "step": 5775 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.00044242105263157897, | |
| "loss": 0.0827, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "eval_loss": 0.47082841396331787, | |
| "eval_runtime": 171.4765, | |
| "eval_samples_per_second": 5.832, | |
| "eval_steps_per_second": 0.367, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.0004397894736842105, | |
| "loss": 0.0862, | |
| "step": 5825 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 0.0004371578947368421, | |
| "loss": 0.0826, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 0.0004345263157894737, | |
| "loss": 0.0823, | |
| "step": 5875 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 0.0004318947368421053, | |
| "loss": 0.0776, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 0.0004292631578947369, | |
| "loss": 0.0868, | |
| "step": 5925 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 0.0004266315789473684, | |
| "loss": 0.0756, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 0.000424, | |
| "loss": 0.0787, | |
| "step": 5975 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 0.00042136842105263154, | |
| "loss": 0.0757, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "eval_loss": 0.4866788387298584, | |
| "eval_runtime": 177.0911, | |
| "eval_samples_per_second": 5.647, | |
| "eval_steps_per_second": 0.356, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 0.0004187368421052632, | |
| "loss": 0.0808, | |
| "step": 6025 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 0.0004161052631578948, | |
| "loss": 0.078, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 0.0004134736842105263, | |
| "loss": 0.0745, | |
| "step": 6075 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 0.0004108421052631579, | |
| "loss": 0.0764, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 0.00040821052631578945, | |
| "loss": 0.0778, | |
| "step": 6125 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 0.00040557894736842104, | |
| "loss": 0.079, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.00040294736842105263, | |
| "loss": 0.0724, | |
| "step": 6175 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.0004003157894736842, | |
| "loss": 0.0744, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "eval_loss": 0.4966813623905182, | |
| "eval_runtime": 176.5697, | |
| "eval_samples_per_second": 5.663, | |
| "eval_steps_per_second": 0.357, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.0003976842105263158, | |
| "loss": 0.0736, | |
| "step": 6225 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 0.0003950526315789474, | |
| "loss": 0.0777, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 0.00039242105263157895, | |
| "loss": 0.0744, | |
| "step": 6275 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 0.00038978947368421054, | |
| "loss": 0.0767, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 0.0003871578947368421, | |
| "loss": 0.0744, | |
| "step": 6325 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 0.00038452631578947367, | |
| "loss": 0.0733, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 0.0003818947368421053, | |
| "loss": 0.0674, | |
| "step": 6375 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 0.00037926315789473685, | |
| "loss": 0.0757, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "eval_loss": 0.49180907011032104, | |
| "eval_runtime": 183.5419, | |
| "eval_samples_per_second": 5.448, | |
| "eval_steps_per_second": 0.343, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 0.00037663157894736845, | |
| "loss": 0.1732, | |
| "step": 6425 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 0.000374, | |
| "loss": 0.2279, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 0.0003713684210526316, | |
| "loss": 0.2115, | |
| "step": 6475 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 0.00036873684210526317, | |
| "loss": 0.2127, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 0.0003661052631578947, | |
| "loss": 0.2352, | |
| "step": 6525 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 0.00036347368421052635, | |
| "loss": 0.1931, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 0.0003608421052631579, | |
| "loss": 0.1898, | |
| "step": 6575 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 0.0003582105263157895, | |
| "loss": 0.1703, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "eval_loss": 0.35250428318977356, | |
| "eval_runtime": 180.9786, | |
| "eval_samples_per_second": 5.526, | |
| "eval_steps_per_second": 0.348, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 0.0003555789473684211, | |
| "loss": 0.1775, | |
| "step": 6625 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0003529473684210526, | |
| "loss": 0.0902, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0003503157894736842, | |
| "loss": 0.0857, | |
| "step": 6675 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 0.0003476842105263158, | |
| "loss": 0.0874, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 0.0003450526315789474, | |
| "loss": 0.0906, | |
| "step": 6725 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 0.000342421052631579, | |
| "loss": 0.0795, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 0.0003397894736842105, | |
| "loss": 0.0787, | |
| "step": 6775 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 0.0003371578947368421, | |
| "loss": 0.0798, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "eval_loss": 0.41625910997390747, | |
| "eval_runtime": 196.0559, | |
| "eval_samples_per_second": 5.101, | |
| "eval_steps_per_second": 0.321, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 0.0003345263157894737, | |
| "loss": 0.0806, | |
| "step": 6825 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 0.00033189473684210524, | |
| "loss": 0.0729, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 0.0003292631578947369, | |
| "loss": 0.0756, | |
| "step": 6875 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 0.0003266315789473684, | |
| "loss": 0.0701, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 0.000324, | |
| "loss": 0.0719, | |
| "step": 6925 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 0.0003213684210526316, | |
| "loss": 0.0719, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 0.00031873684210526314, | |
| "loss": 0.0696, | |
| "step": 6975 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 0.00031610526315789474, | |
| "loss": 0.0706, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "eval_loss": 0.4390297532081604, | |
| "eval_runtime": 187.2668, | |
| "eval_samples_per_second": 5.34, | |
| "eval_steps_per_second": 0.336, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 0.0003134736842105263, | |
| "loss": 0.0672, | |
| "step": 7025 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 0.0003109473684210526, | |
| "loss": 0.0732, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 5.04, | |
| "learning_rate": 0.0003083157894736842, | |
| "loss": 0.0666, | |
| "step": 7075 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.0003056842105263158, | |
| "loss": 0.0679, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.00030305263157894734, | |
| "loss": 0.0651, | |
| "step": 7125 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.00030042105263157893, | |
| "loss": 0.0708, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.0002977894736842106, | |
| "loss": 0.0657, | |
| "step": 7175 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 0.0002951578947368421, | |
| "loss": 0.0663, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "eval_loss": 0.44457703828811646, | |
| "eval_runtime": 165.8281, | |
| "eval_samples_per_second": 6.03, | |
| "eval_steps_per_second": 0.38, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 0.0002925263157894737, | |
| "loss": 0.0612, | |
| "step": 7225 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 0.00028989473684210525, | |
| "loss": 0.069, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 0.00028726315789473684, | |
| "loss": 0.0611, | |
| "step": 7275 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 0.00028463157894736843, | |
| "loss": 0.0614, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 0.00028199999999999997, | |
| "loss": 0.0592, | |
| "step": 7325 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 0.0002793684210526316, | |
| "loss": 0.0649, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 0.00027673684210526315, | |
| "loss": 0.0611, | |
| "step": 7375 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 0.00027410526315789475, | |
| "loss": 0.0583, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "eval_loss": 0.47715672850608826, | |
| "eval_runtime": 184.0238, | |
| "eval_samples_per_second": 5.434, | |
| "eval_steps_per_second": 0.342, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 0.00027147368421052634, | |
| "loss": 0.0594, | |
| "step": 7425 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 0.0002688421052631579, | |
| "loss": 0.0607, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 0.00026621052631578947, | |
| "loss": 0.06, | |
| "step": 7475 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 0.00026357894736842106, | |
| "loss": 0.0573, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 0.00026094736842105265, | |
| "loss": 0.0597, | |
| "step": 7525 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 0.00025831578947368424, | |
| "loss": 0.058, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 0.0002556842105263158, | |
| "loss": 0.061, | |
| "step": 7575 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 0.0002530526315789474, | |
| "loss": 0.0593, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "eval_loss": 0.47001564502716064, | |
| "eval_runtime": 175.7366, | |
| "eval_samples_per_second": 5.69, | |
| "eval_steps_per_second": 0.358, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 0.0002504210526315789, | |
| "loss": 0.0591, | |
| "step": 7625 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 0.00024778947368421056, | |
| "loss": 0.0595, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.0002451578947368421, | |
| "loss": 0.0579, | |
| "step": 7675 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.0002425263157894737, | |
| "loss": 0.0532, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.00023989473684210528, | |
| "loss": 0.0585, | |
| "step": 7725 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.00023726315789473684, | |
| "loss": 0.1318, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 0.0002346315789473684, | |
| "loss": 0.1778, | |
| "step": 7775 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 0.00023200000000000003, | |
| "loss": 0.167, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "eval_loss": 0.3735247254371643, | |
| "eval_runtime": 158.6047, | |
| "eval_samples_per_second": 6.305, | |
| "eval_steps_per_second": 0.397, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 0.0002293684210526316, | |
| "loss": 0.1615, | |
| "step": 7825 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 0.00022673684210526316, | |
| "loss": 0.1775, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 0.00022410526315789472, | |
| "loss": 0.15, | |
| "step": 7875 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 0.00022147368421052632, | |
| "loss": 0.1501, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 0.0002188421052631579, | |
| "loss": 0.1359, | |
| "step": 7925 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 0.00021621052631578947, | |
| "loss": 0.137, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.00021357894736842106, | |
| "loss": 0.0694, | |
| "step": 7975 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.00021094736842105263, | |
| "loss": 0.0687, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.3816312253475189, | |
| "eval_runtime": 240.2019, | |
| "eval_samples_per_second": 4.163, | |
| "eval_steps_per_second": 0.262, | |
| "step": 8000 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 10000, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 400, | |
| "total_flos": 1.5035963132952576e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |