| { | |
| "best_metric": 0.763276994228363, | |
| "best_model_checkpoint": "/mnt/bn/qingyi-bn-lq/llama/saved-belle1.5m7b/checkpoint-12000", | |
| "epoch": 0.9965122072745392, | |
| "global_step": 12000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.7631, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.4784, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 1.1332, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.0665, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0003, | |
| "loss": 1.0418, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00029949757159604753, | |
| "loss": 1.0246, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0002989951431920951, | |
| "loss": 1.0054, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00029849271478814266, | |
| "loss": 1.002, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0002979902863841902, | |
| "loss": 0.9908, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0002974878579802378, | |
| "loss": 0.9784, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 0.9920349717140198, | |
| "eval_runtime": 8.2147, | |
| "eval_samples_per_second": 243.465, | |
| "eval_steps_per_second": 1.948, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00029698542957628534, | |
| "loss": 0.9817, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0002964830011723329, | |
| "loss": 0.983, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00029598057276838046, | |
| "loss": 0.9637, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.000295478144364428, | |
| "loss": 0.9534, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0002949757159604756, | |
| "loss": 0.9475, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00029447328755652315, | |
| "loss": 0.9502, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002939708591525707, | |
| "loss": 0.946, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00029346843074861827, | |
| "loss": 0.9545, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00029296600234466583, | |
| "loss": 0.946, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002924635739407134, | |
| "loss": 0.9295, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 0.9477736949920654, | |
| "eval_runtime": 8.229, | |
| "eval_samples_per_second": 243.042, | |
| "eval_steps_per_second": 1.944, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00029196114553676095, | |
| "loss": 0.9232, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002914587171328085, | |
| "loss": 0.9201, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00029095628872885613, | |
| "loss": 0.9212, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002904538603249037, | |
| "loss": 0.9131, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00028995143192095125, | |
| "loss": 0.922, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002894490035169988, | |
| "loss": 0.9176, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002889465751130464, | |
| "loss": 0.9177, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00028844414670909393, | |
| "loss": 0.9132, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002879417183051415, | |
| "loss": 0.921, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00028743928990118906, | |
| "loss": 0.9013, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 0.9194319248199463, | |
| "eval_runtime": 8.23, | |
| "eval_samples_per_second": 243.013, | |
| "eval_steps_per_second": 1.944, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002869368614972366, | |
| "loss": 0.904, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0002864344330932842, | |
| "loss": 0.9016, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00028593200468933174, | |
| "loss": 0.8931, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002854295762853793, | |
| "loss": 0.9, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00028492714788142686, | |
| "loss": 0.896, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002844247194774744, | |
| "loss": 0.8982, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00028392229107352204, | |
| "loss": 0.9, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002834198626695696, | |
| "loss": 0.8861, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00028291743426561716, | |
| "loss": 0.8926, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002824150058616647, | |
| "loss": 0.8853, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 0.8987648487091064, | |
| "eval_runtime": 8.2248, | |
| "eval_samples_per_second": 243.167, | |
| "eval_steps_per_second": 1.945, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002819125774577123, | |
| "loss": 0.8922, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00028141014905375984, | |
| "loss": 0.8813, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002809077206498074, | |
| "loss": 0.8825, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00028040529224585497, | |
| "loss": 0.8821, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00027990286384190253, | |
| "loss": 0.8853, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002794004354379501, | |
| "loss": 0.8806, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00027889800703399765, | |
| "loss": 0.8774, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002783955786300452, | |
| "loss": 0.8783, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00027789315022609277, | |
| "loss": 0.876, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00027739072182214033, | |
| "loss": 0.8656, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": 0.8842049241065979, | |
| "eval_runtime": 8.2372, | |
| "eval_samples_per_second": 242.8, | |
| "eval_steps_per_second": 1.942, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002768882934181879, | |
| "loss": 0.8776, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00027638586501423546, | |
| "loss": 0.8751, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.000275883436610283, | |
| "loss": 0.8701, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002753810082063306, | |
| "loss": 0.8618, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00027487857980237814, | |
| "loss": 0.8604, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002743761513984257, | |
| "loss": 0.8516, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00027387372299447326, | |
| "loss": 0.8553, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002733712945905208, | |
| "loss": 0.8638, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002728688661865684, | |
| "loss": 0.8528, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00027236643778261595, | |
| "loss": 0.8641, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.871113121509552, | |
| "eval_runtime": 8.2308, | |
| "eval_samples_per_second": 242.989, | |
| "eval_steps_per_second": 1.944, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002718640093786635, | |
| "loss": 0.8656, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00027136158097471107, | |
| "loss": 0.8534, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00027085915257075863, | |
| "loss": 0.8512, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002703567241668062, | |
| "loss": 0.8472, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00026985429576285375, | |
| "loss": 0.8584, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002693518673589013, | |
| "loss": 0.8557, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002688494389549489, | |
| "loss": 0.8547, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00026834701055099643, | |
| "loss": 0.8576, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.000267844582147044, | |
| "loss": 0.8499, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00026734215374309156, | |
| "loss": 0.839, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 0.8613501191139221, | |
| "eval_runtime": 8.2712, | |
| "eval_samples_per_second": 241.802, | |
| "eval_steps_per_second": 1.934, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002668397253391391, | |
| "loss": 0.8538, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002663372969351867, | |
| "loss": 0.8541, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002658348685312343, | |
| "loss": 0.8381, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00026533244012728186, | |
| "loss": 0.8527, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002648300117233294, | |
| "loss": 0.8493, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.000264327583319377, | |
| "loss": 0.846, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00026382515491542454, | |
| "loss": 0.8435, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002633227265114721, | |
| "loss": 0.8517, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00026282029810751966, | |
| "loss": 0.8403, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002623178697035672, | |
| "loss": 0.8419, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 0.8518173098564148, | |
| "eval_runtime": 8.2505, | |
| "eval_samples_per_second": 242.411, | |
| "eval_steps_per_second": 1.939, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002618154412996148, | |
| "loss": 0.8393, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00026131301289566234, | |
| "loss": 0.8471, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002608105844917099, | |
| "loss": 0.85, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00026030815608775747, | |
| "loss": 0.8388, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00025980572768380503, | |
| "loss": 0.8394, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002593032992798526, | |
| "loss": 0.8333, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00025880087087590015, | |
| "loss": 0.8343, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002582984424719477, | |
| "loss": 0.8303, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00025779601406799533, | |
| "loss": 0.8247, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002572935856640429, | |
| "loss": 0.8282, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 0.8434953689575195, | |
| "eval_runtime": 8.2633, | |
| "eval_samples_per_second": 242.034, | |
| "eval_steps_per_second": 1.936, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00025679115726009045, | |
| "loss": 0.8348, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.000256288728856138, | |
| "loss": 0.8393, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00025578630045218557, | |
| "loss": 0.8304, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00025528387204823313, | |
| "loss": 0.8309, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002547814436442807, | |
| "loss": 0.8382, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00025427901524032826, | |
| "loss": 0.841, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002537765868363758, | |
| "loss": 0.8354, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002532741584324234, | |
| "loss": 0.8334, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00025277173002847094, | |
| "loss": 0.8243, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002522693016245185, | |
| "loss": 0.8337, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 0.8386329412460327, | |
| "eval_runtime": 8.2418, | |
| "eval_samples_per_second": 242.666, | |
| "eval_steps_per_second": 1.941, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00025176687322056606, | |
| "loss": 0.8237, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002512644448166136, | |
| "loss": 0.8206, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002507620164126612, | |
| "loss": 0.8277, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00025025958800870874, | |
| "loss": 0.8271, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002497571596047563, | |
| "loss": 0.8353, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00024925473120080387, | |
| "loss": 0.8253, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00024875230279685143, | |
| "loss": 0.8212, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.000248249874392899, | |
| "loss": 0.8192, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00024774744598894655, | |
| "loss": 0.8292, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002472450175849941, | |
| "loss": 0.825, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 0.8326684236526489, | |
| "eval_runtime": 8.2602, | |
| "eval_samples_per_second": 242.126, | |
| "eval_steps_per_second": 1.937, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00024674258918104167, | |
| "loss": 0.8308, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00024624016077708923, | |
| "loss": 0.8324, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002457377323731368, | |
| "loss": 0.8257, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00024523530396918436, | |
| "loss": 0.8181, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002447328755652319, | |
| "loss": 0.8126, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002442304471612795, | |
| "loss": 0.819, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00024372801875732707, | |
| "loss": 0.8198, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00024322559035337463, | |
| "loss": 0.8188, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002427231619494222, | |
| "loss": 0.8145, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00024222073354546975, | |
| "loss": 0.81, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 0.8278167843818665, | |
| "eval_runtime": 8.2577, | |
| "eval_samples_per_second": 242.198, | |
| "eval_steps_per_second": 1.938, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002417183051415173, | |
| "loss": 0.8142, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00024121587673756487, | |
| "loss": 0.8059, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00024071344833361243, | |
| "loss": 0.826, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00024021101992966, | |
| "loss": 0.8173, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00023970859152570756, | |
| "loss": 0.8063, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00023920616312175512, | |
| "loss": 0.812, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00023870373471780268, | |
| "loss": 0.82, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00023820130631385024, | |
| "loss": 0.8207, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002376988779098978, | |
| "loss": 0.8113, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00023719644950594536, | |
| "loss": 0.8175, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 0.8231886029243469, | |
| "eval_runtime": 8.2627, | |
| "eval_samples_per_second": 242.052, | |
| "eval_steps_per_second": 1.936, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00023669402110199295, | |
| "loss": 0.8105, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002361915926980405, | |
| "loss": 0.8106, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00023568916429408807, | |
| "loss": 0.8114, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00023518673589013563, | |
| "loss": 0.8152, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002346843074861832, | |
| "loss": 0.8059, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00023418187908223076, | |
| "loss": 0.8065, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00023367945067827832, | |
| "loss": 0.8147, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00023317702227432588, | |
| "loss": 0.8006, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00023267459387037344, | |
| "loss": 0.805, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.000232172165466421, | |
| "loss": 0.8142, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 0.8191845417022705, | |
| "eval_runtime": 8.28, | |
| "eval_samples_per_second": 241.547, | |
| "eval_steps_per_second": 1.932, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00023166973706246856, | |
| "loss": 0.8134, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00023116730865851612, | |
| "loss": 0.8066, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00023066488025456368, | |
| "loss": 0.8049, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00023016245185061124, | |
| "loss": 0.7987, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00022966002344665886, | |
| "loss": 0.8113, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00022915759504270642, | |
| "loss": 0.8086, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00022865516663875398, | |
| "loss": 0.8019, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00022815273823480154, | |
| "loss": 0.8051, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002276503098308491, | |
| "loss": 0.8032, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00022714788142689667, | |
| "loss": 0.8058, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.8153129816055298, | |
| "eval_runtime": 8.2727, | |
| "eval_samples_per_second": 241.759, | |
| "eval_steps_per_second": 1.934, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00022664545302294423, | |
| "loss": 0.801, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002261430246189918, | |
| "loss": 0.801, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00022564059621503935, | |
| "loss": 0.8037, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002251381678110869, | |
| "loss": 0.7992, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00022463573940713447, | |
| "loss": 0.8036, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00022413331100318203, | |
| "loss": 0.8064, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002236308825992296, | |
| "loss": 0.7966, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00022312845419527716, | |
| "loss": 0.8047, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00022262602579132472, | |
| "loss": 0.7986, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00022212359738737228, | |
| "loss": 0.8026, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 0.8119255304336548, | |
| "eval_runtime": 8.288, | |
| "eval_samples_per_second": 241.313, | |
| "eval_steps_per_second": 1.931, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00022162116898341984, | |
| "loss": 0.8028, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002211187405794674, | |
| "loss": 0.7987, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.000220616312175515, | |
| "loss": 0.8148, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00022011388377156255, | |
| "loss": 0.7932, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002196114553676101, | |
| "loss": 0.8027, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00021910902696365767, | |
| "loss": 0.7989, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00021860659855970523, | |
| "loss": 0.7983, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002181041701557528, | |
| "loss": 0.7977, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00021760174175180035, | |
| "loss": 0.7972, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00021709931334784792, | |
| "loss": 0.8025, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.8084473609924316, | |
| "eval_runtime": 8.2772, | |
| "eval_samples_per_second": 241.627, | |
| "eval_steps_per_second": 1.933, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00021659688494389548, | |
| "loss": 0.7993, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00021609445653994304, | |
| "loss": 0.7919, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002155920281359906, | |
| "loss": 0.8062, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00021508959973203816, | |
| "loss": 0.7937, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00021458717132808572, | |
| "loss": 0.7947, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00021408474292413328, | |
| "loss": 0.7973, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00021358231452018084, | |
| "loss": 0.7964, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002130798861162284, | |
| "loss": 0.7994, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00021257745771227597, | |
| "loss": 0.7911, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00021207502930832353, | |
| "loss": 0.805, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 0.8064665794372559, | |
| "eval_runtime": 8.2739, | |
| "eval_samples_per_second": 241.725, | |
| "eval_steps_per_second": 1.934, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00021157260090437112, | |
| "loss": 0.8014, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00021107017250041868, | |
| "loss": 0.7941, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00021056774409646624, | |
| "loss": 0.793, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0002100653156925138, | |
| "loss": 0.7918, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00020956288728856136, | |
| "loss": 0.7926, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00020906045888460892, | |
| "loss": 0.797, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00020855803048065648, | |
| "loss": 0.7965, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00020805560207670404, | |
| "loss": 0.7963, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0002075531736727516, | |
| "loss": 0.7924, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00020705074526879917, | |
| "loss": 0.788, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": 0.8037804961204529, | |
| "eval_runtime": 8.3133, | |
| "eval_samples_per_second": 240.579, | |
| "eval_steps_per_second": 1.925, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00020654831686484673, | |
| "loss": 0.794, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002060458884608943, | |
| "loss": 0.7946, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00020554346005694185, | |
| "loss": 0.7934, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002050410316529894, | |
| "loss": 0.7935, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00020453860324903697, | |
| "loss": 0.7864, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00020403617484508453, | |
| "loss": 0.8026, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002035337464411321, | |
| "loss": 0.7902, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00020303131803717966, | |
| "loss": 0.7915, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00020252888963322724, | |
| "loss": 0.798, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002020264612292748, | |
| "loss": 0.7989, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 0.8007607460021973, | |
| "eval_runtime": 8.2882, | |
| "eval_samples_per_second": 241.308, | |
| "eval_steps_per_second": 1.93, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002015240328253224, | |
| "loss": 0.7831, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00020102160442136995, | |
| "loss": 0.7877, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00020051917601741752, | |
| "loss": 0.7855, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00020001674761346508, | |
| "loss": 0.7889, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00019951431920951264, | |
| "loss": 0.7958, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0001990118908055602, | |
| "loss": 0.7934, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00019850946240160776, | |
| "loss": 0.785, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00019800703399765532, | |
| "loss": 0.7987, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00019750460559370288, | |
| "loss": 0.7886, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00019702729860994808, | |
| "loss": 0.79, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 0.7986196279525757, | |
| "eval_runtime": 8.2739, | |
| "eval_samples_per_second": 241.724, | |
| "eval_steps_per_second": 1.934, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00019652487020599565, | |
| "loss": 0.7889, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0001960224418020432, | |
| "loss": 0.7883, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00019552001339809077, | |
| "loss": 0.7895, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00019501758499413833, | |
| "loss": 0.7838, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0001945151565901859, | |
| "loss": 0.7957, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00019401272818623345, | |
| "loss": 0.7915, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.000193510299782281, | |
| "loss": 0.7987, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00019300787137832857, | |
| "loss": 0.7811, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00019250544297437613, | |
| "loss": 0.7921, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0001920030145704237, | |
| "loss": 0.7928, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 0.7964197993278503, | |
| "eval_runtime": 8.2761, | |
| "eval_samples_per_second": 241.66, | |
| "eval_steps_per_second": 1.933, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00019150058616647126, | |
| "loss": 0.7924, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00019099815776251885, | |
| "loss": 0.7898, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0001904957293585664, | |
| "loss": 0.7893, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00018999330095461397, | |
| "loss": 0.795, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00018949087255066153, | |
| "loss": 0.7832, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0001889884441467091, | |
| "loss": 0.7835, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00018848601574275665, | |
| "loss": 0.7809, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0001879835873388042, | |
| "loss": 0.7792, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00018748115893485177, | |
| "loss": 0.7884, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00018697873053089933, | |
| "loss": 0.7859, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.794753909111023, | |
| "eval_runtime": 8.2787, | |
| "eval_samples_per_second": 241.584, | |
| "eval_steps_per_second": 1.933, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0001864763021269469, | |
| "loss": 0.7709, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00018597387372299446, | |
| "loss": 0.7786, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00018547144531904202, | |
| "loss": 0.7786, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00018496901691508958, | |
| "loss": 0.7824, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00018446658851113714, | |
| "loss": 0.7741, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0001839641601071847, | |
| "loss": 0.78, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00018346173170323226, | |
| "loss": 0.782, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00018295930329927982, | |
| "loss": 0.7808, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001824568748953274, | |
| "loss": 0.7776, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00018195444649137497, | |
| "loss": 0.7824, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.7927345633506775, | |
| "eval_runtime": 8.2706, | |
| "eval_samples_per_second": 241.82, | |
| "eval_steps_per_second": 1.935, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00018145201808742253, | |
| "loss": 0.7843, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001809495896834701, | |
| "loss": 0.7908, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00018044716127951766, | |
| "loss": 0.7872, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00017994473287556522, | |
| "loss": 0.7763, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00017944230447161278, | |
| "loss": 0.7846, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00017893987606766034, | |
| "loss": 0.7775, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0001784374476637079, | |
| "loss": 0.793, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00017793501925975546, | |
| "loss": 0.7814, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00017743259085580302, | |
| "loss": 0.7913, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00017693016245185058, | |
| "loss": 0.7755, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.7912722826004028, | |
| "eval_runtime": 8.285, | |
| "eval_samples_per_second": 241.401, | |
| "eval_steps_per_second": 1.931, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00017642773404789815, | |
| "loss": 0.7848, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0001759253056439457, | |
| "loss": 0.7826, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00017542287723999327, | |
| "loss": 0.7753, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00017492044883604083, | |
| "loss": 0.7786, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0001744180204320884, | |
| "loss": 0.7929, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00017391559202813595, | |
| "loss": 0.7836, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00017341316362418354, | |
| "loss": 0.7802, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0001729107352202311, | |
| "loss": 0.7808, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00017240830681627866, | |
| "loss": 0.7784, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00017190587841232622, | |
| "loss": 0.7803, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 0.7892646193504333, | |
| "eval_runtime": 8.297, | |
| "eval_samples_per_second": 241.05, | |
| "eval_steps_per_second": 1.928, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00017140345000837378, | |
| "loss": 0.7872, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00017090102160442135, | |
| "loss": 0.7795, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0001703985932004689, | |
| "loss": 0.7777, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00016989616479651647, | |
| "loss": 0.7775, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00016939373639256406, | |
| "loss": 0.7789, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00016889130798861162, | |
| "loss": 0.7863, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00016838887958465918, | |
| "loss": 0.7774, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00016788645118070674, | |
| "loss": 0.7856, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0001673840227767543, | |
| "loss": 0.78, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00016688159437280186, | |
| "loss": 0.7929, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 0.7884517908096313, | |
| "eval_runtime": 8.3482, | |
| "eval_samples_per_second": 239.571, | |
| "eval_steps_per_second": 1.917, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00016637916596884945, | |
| "loss": 0.7728, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.000165876737564897, | |
| "loss": 0.7827, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00016537430916094457, | |
| "loss": 0.767, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00016487188075699213, | |
| "loss": 0.7768, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0001643694523530397, | |
| "loss": 0.776, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00016386702394908726, | |
| "loss": 0.77, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00016336459554513482, | |
| "loss": 0.7825, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00016286216714118238, | |
| "loss": 0.7829, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00016235973873722994, | |
| "loss": 0.791, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0001618573103332775, | |
| "loss": 0.7807, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.7869579792022705, | |
| "eval_runtime": 8.297, | |
| "eval_samples_per_second": 241.051, | |
| "eval_steps_per_second": 1.928, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00016135488192932506, | |
| "loss": 0.7762, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00016085245352537262, | |
| "loss": 0.7805, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00016035002512142018, | |
| "loss": 0.7797, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00015984759671746774, | |
| "loss": 0.7832, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0001593451683135153, | |
| "loss": 0.7739, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00015884273990956287, | |
| "loss": 0.7703, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00015834031150561043, | |
| "loss": 0.7707, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.000157837883101658, | |
| "loss": 0.7649, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00015733545469770558, | |
| "loss": 0.7713, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00015683302629375314, | |
| "loss": 0.7753, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.7855839729309082, | |
| "eval_runtime": 8.3158, | |
| "eval_samples_per_second": 240.507, | |
| "eval_steps_per_second": 1.924, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0001563305978898007, | |
| "loss": 0.7795, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00015582816948584826, | |
| "loss": 0.7714, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00015532574108189582, | |
| "loss": 0.7772, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00015482331267794338, | |
| "loss": 0.7784, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00015432088427399094, | |
| "loss": 0.7628, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0001538184558700385, | |
| "loss": 0.7848, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00015331602746608607, | |
| "loss": 0.78, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00015281359906213363, | |
| "loss": 0.7856, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0001523111706581812, | |
| "loss": 0.776, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00015180874225422875, | |
| "loss": 0.7752, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.7837858200073242, | |
| "eval_runtime": 8.2979, | |
| "eval_samples_per_second": 241.025, | |
| "eval_steps_per_second": 1.928, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0001513063138502763, | |
| "loss": 0.7719, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00015080388544632387, | |
| "loss": 0.7841, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00015030145704237143, | |
| "loss": 0.7779, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.000149799028638419, | |
| "loss": 0.7706, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00014929660023446656, | |
| "loss": 0.762, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00014879417183051412, | |
| "loss": 0.7854, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0001482917434265617, | |
| "loss": 0.7803, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00014778931502260927, | |
| "loss": 0.7769, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00014728688661865683, | |
| "loss": 0.7773, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0001467844582147044, | |
| "loss": 0.7725, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.7822731137275696, | |
| "eval_runtime": 8.3078, | |
| "eval_samples_per_second": 240.738, | |
| "eval_steps_per_second": 1.926, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00014630715123094956, | |
| "loss": 0.7797, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00014580472282699713, | |
| "loss": 0.77, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00014530229442304469, | |
| "loss": 0.7699, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00014479986601909225, | |
| "loss": 0.7769, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00014429743761513984, | |
| "loss": 0.7755, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0001437950092111874, | |
| "loss": 0.7752, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00014329258080723496, | |
| "loss": 0.7791, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00014279015240328252, | |
| "loss": 0.7606, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00014228772399933008, | |
| "loss": 0.7733, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00014178529559537764, | |
| "loss": 0.7855, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 0.7812179923057556, | |
| "eval_runtime": 8.2896, | |
| "eval_samples_per_second": 241.265, | |
| "eval_steps_per_second": 1.93, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0001412828671914252, | |
| "loss": 0.7718, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00014078043878747276, | |
| "loss": 0.7676, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00014027801038352035, | |
| "loss": 0.7732, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0001397755819795679, | |
| "loss": 0.7745, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00013927315357561547, | |
| "loss": 0.7747, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00013877072517166304, | |
| "loss": 0.7648, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0001382682967677106, | |
| "loss": 0.7767, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00013776586836375816, | |
| "loss": 0.7735, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00013726343995980572, | |
| "loss": 0.7684, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00013676101155585328, | |
| "loss": 0.7783, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.7797773480415344, | |
| "eval_runtime": 8.2853, | |
| "eval_samples_per_second": 241.391, | |
| "eval_steps_per_second": 1.931, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00013625858315190084, | |
| "loss": 0.7755, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0001357561547479484, | |
| "loss": 0.7813, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00013525372634399596, | |
| "loss": 0.7721, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00013475129794004352, | |
| "loss": 0.7621, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00013424886953609109, | |
| "loss": 0.7703, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00013374644113213865, | |
| "loss": 0.7795, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0001332440127281862, | |
| "loss": 0.779, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00013274158432423377, | |
| "loss": 0.7762, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00013223915592028133, | |
| "loss": 0.7769, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0001317367275163289, | |
| "loss": 0.7762, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 0.7790360450744629, | |
| "eval_runtime": 8.301, | |
| "eval_samples_per_second": 240.935, | |
| "eval_steps_per_second": 1.927, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00013123429911237648, | |
| "loss": 0.7587, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00013073187070842404, | |
| "loss": 0.7667, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0001302294423044716, | |
| "loss": 0.7575, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00012972701390051916, | |
| "loss": 0.7755, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00012922458549656672, | |
| "loss": 0.7718, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00012872215709261429, | |
| "loss": 0.7715, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00012821972868866185, | |
| "loss": 0.7679, | |
| "step": 6940 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00012771730028470944, | |
| "loss": 0.7691, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.000127214871880757, | |
| "loss": 0.7766, | |
| "step": 6980 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00012671244347680456, | |
| "loss": 0.7708, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.7774990200996399, | |
| "eval_runtime": 8.2721, | |
| "eval_samples_per_second": 241.778, | |
| "eval_steps_per_second": 1.934, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00012621001507285212, | |
| "loss": 0.7687, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00012570758666889968, | |
| "loss": 0.7675, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00012520515826494724, | |
| "loss": 0.7746, | |
| "step": 7060 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0001247027298609948, | |
| "loss": 0.7626, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00012420030145704236, | |
| "loss": 0.764, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00012369787305308992, | |
| "loss": 0.7734, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00012319544464913749, | |
| "loss": 0.7642, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00012269301624518505, | |
| "loss": 0.7715, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0001221905878412326, | |
| "loss": 0.7619, | |
| "step": 7180 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00012168815943728017, | |
| "loss": 0.7674, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.777417004108429, | |
| "eval_runtime": 8.2947, | |
| "eval_samples_per_second": 241.117, | |
| "eval_steps_per_second": 1.929, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00012118573103332774, | |
| "loss": 0.7709, | |
| "step": 7220 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0001206833026293753, | |
| "loss": 0.7682, | |
| "step": 7240 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00012018087422542287, | |
| "loss": 0.7604, | |
| "step": 7260 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00011967844582147043, | |
| "loss": 0.767, | |
| "step": 7280 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00011917601741751799, | |
| "loss": 0.7707, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00011867358901356555, | |
| "loss": 0.7602, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00011817116060961311, | |
| "loss": 0.7584, | |
| "step": 7340 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00011766873220566067, | |
| "loss": 0.7696, | |
| "step": 7360 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00011716630380170823, | |
| "loss": 0.7675, | |
| "step": 7380 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00011666387539775581, | |
| "loss": 0.7716, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 0.7760618329048157, | |
| "eval_runtime": 8.2995, | |
| "eval_samples_per_second": 240.98, | |
| "eval_steps_per_second": 1.928, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00011616144699380338, | |
| "loss": 0.7648, | |
| "step": 7420 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00011565901858985094, | |
| "loss": 0.7643, | |
| "step": 7440 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0001151565901858985, | |
| "loss": 0.759, | |
| "step": 7460 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00011465416178194607, | |
| "loss": 0.7694, | |
| "step": 7480 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00011415173337799363, | |
| "loss": 0.7633, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00011364930497404119, | |
| "loss": 0.773, | |
| "step": 7520 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00011314687657008876, | |
| "loss": 0.76, | |
| "step": 7540 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00011264444816613632, | |
| "loss": 0.7708, | |
| "step": 7560 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00011214201976218388, | |
| "loss": 0.7757, | |
| "step": 7580 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00011163959135823145, | |
| "loss": 0.7655, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": 0.7751550078392029, | |
| "eval_runtime": 8.2715, | |
| "eval_samples_per_second": 241.793, | |
| "eval_steps_per_second": 1.934, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00011113716295427901, | |
| "loss": 0.7607, | |
| "step": 7620 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00011063473455032657, | |
| "loss": 0.7703, | |
| "step": 7640 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00011013230614637413, | |
| "loss": 0.7653, | |
| "step": 7660 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00010962987774242169, | |
| "loss": 0.7753, | |
| "step": 7680 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00010912744933846925, | |
| "loss": 0.7639, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00010862502093451683, | |
| "loss": 0.7701, | |
| "step": 7720 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00010812259253056439, | |
| "loss": 0.7614, | |
| "step": 7740 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00010762016412661195, | |
| "loss": 0.7612, | |
| "step": 7760 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00010711773572265951, | |
| "loss": 0.7597, | |
| "step": 7780 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00010661530731870707, | |
| "loss": 0.7621, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.7740359902381897, | |
| "eval_runtime": 8.2962, | |
| "eval_samples_per_second": 241.075, | |
| "eval_steps_per_second": 1.929, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00010611287891475463, | |
| "loss": 0.7592, | |
| "step": 7820 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0001056104505108022, | |
| "loss": 0.7665, | |
| "step": 7840 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00010510802210684975, | |
| "loss": 0.7646, | |
| "step": 7860 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00010460559370289732, | |
| "loss": 0.7668, | |
| "step": 7880 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00010410316529894489, | |
| "loss": 0.7756, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00010360073689499245, | |
| "loss": 0.7684, | |
| "step": 7920 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00010309830849104001, | |
| "loss": 0.7566, | |
| "step": 7940 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00010259588008708757, | |
| "loss": 0.7581, | |
| "step": 7960 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00010209345168313515, | |
| "loss": 0.7624, | |
| "step": 7980 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00010159102327918271, | |
| "loss": 0.7594, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 0.7729437351226807, | |
| "eval_runtime": 8.2949, | |
| "eval_samples_per_second": 241.112, | |
| "eval_steps_per_second": 1.929, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00010108859487523028, | |
| "loss": 0.7657, | |
| "step": 8020 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00010058616647127785, | |
| "loss": 0.7604, | |
| "step": 8040 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0001000837380673254, | |
| "loss": 0.7659, | |
| "step": 8060 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 9.958130966337297e-05, | |
| "loss": 0.7688, | |
| "step": 8080 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 9.907888125942053e-05, | |
| "loss": 0.7702, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 9.857645285546809e-05, | |
| "loss": 0.7572, | |
| "step": 8120 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.807402445151565e-05, | |
| "loss": 0.7603, | |
| "step": 8140 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.757159604756321e-05, | |
| "loss": 0.761, | |
| "step": 8160 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.706916764361077e-05, | |
| "loss": 0.7649, | |
| "step": 8180 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.656673923965835e-05, | |
| "loss": 0.7554, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.7727349996566772, | |
| "eval_runtime": 8.2811, | |
| "eval_samples_per_second": 241.515, | |
| "eval_steps_per_second": 1.932, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.606431083570591e-05, | |
| "loss": 0.7634, | |
| "step": 8220 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.556188243175347e-05, | |
| "loss": 0.7611, | |
| "step": 8240 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.505945402780103e-05, | |
| "loss": 0.7606, | |
| "step": 8260 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.455702562384859e-05, | |
| "loss": 0.7703, | |
| "step": 8280 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.405459721989615e-05, | |
| "loss": 0.7616, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.355216881594372e-05, | |
| "loss": 0.7638, | |
| "step": 8320 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.30748618321889e-05, | |
| "loss": 0.7461, | |
| "step": 8340 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.257243342823646e-05, | |
| "loss": 0.7577, | |
| "step": 8360 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.207000502428403e-05, | |
| "loss": 0.7553, | |
| "step": 8380 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.15675766203316e-05, | |
| "loss": 0.7564, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 0.771743893623352, | |
| "eval_runtime": 8.2767, | |
| "eval_samples_per_second": 241.642, | |
| "eval_steps_per_second": 1.933, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.106514821637916e-05, | |
| "loss": 0.7605, | |
| "step": 8420 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.056271981242672e-05, | |
| "loss": 0.773, | |
| "step": 8440 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.006029140847428e-05, | |
| "loss": 0.7657, | |
| "step": 8460 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 8.955786300452185e-05, | |
| "loss": 0.7597, | |
| "step": 8480 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.90554346005694e-05, | |
| "loss": 0.7687, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.855300619661697e-05, | |
| "loss": 0.7545, | |
| "step": 8520 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.805057779266453e-05, | |
| "loss": 0.7575, | |
| "step": 8540 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.754814938871209e-05, | |
| "loss": 0.771, | |
| "step": 8560 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.704572098475966e-05, | |
| "loss": 0.7622, | |
| "step": 8580 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.654329258080723e-05, | |
| "loss": 0.7621, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 0.7706981897354126, | |
| "eval_runtime": 8.2852, | |
| "eval_samples_per_second": 241.394, | |
| "eval_steps_per_second": 1.931, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.604086417685479e-05, | |
| "loss": 0.7516, | |
| "step": 8620 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.553843577290235e-05, | |
| "loss": 0.7526, | |
| "step": 8640 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.503600736894991e-05, | |
| "loss": 0.7639, | |
| "step": 8660 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.453357896499747e-05, | |
| "loss": 0.7561, | |
| "step": 8680 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.403115056104506e-05, | |
| "loss": 0.7643, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.352872215709262e-05, | |
| "loss": 0.7665, | |
| "step": 8720 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.302629375314018e-05, | |
| "loss": 0.7681, | |
| "step": 8740 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.252386534918774e-05, | |
| "loss": 0.7655, | |
| "step": 8760 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.20214369452353e-05, | |
| "loss": 0.7603, | |
| "step": 8780 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.151900854128286e-05, | |
| "loss": 0.7624, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 0.7699927687644958, | |
| "eval_runtime": 8.2872, | |
| "eval_samples_per_second": 241.335, | |
| "eval_steps_per_second": 1.931, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.101658013733043e-05, | |
| "loss": 0.7666, | |
| "step": 8820 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.051415173337799e-05, | |
| "loss": 0.752, | |
| "step": 8840 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 8.001172332942555e-05, | |
| "loss": 0.7654, | |
| "step": 8860 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 7.950929492547312e-05, | |
| "loss": 0.7546, | |
| "step": 8880 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 7.900686652152068e-05, | |
| "loss": 0.755, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 7.850443811756824e-05, | |
| "loss": 0.7578, | |
| "step": 8920 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 7.80020097136158e-05, | |
| "loss": 0.7527, | |
| "step": 8940 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 7.749958130966337e-05, | |
| "loss": 0.7622, | |
| "step": 8960 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.699715290571093e-05, | |
| "loss": 0.7681, | |
| "step": 8980 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.649472450175849e-05, | |
| "loss": 0.7641, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 0.7696471214294434, | |
| "eval_runtime": 8.269, | |
| "eval_samples_per_second": 241.867, | |
| "eval_steps_per_second": 1.935, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.599229609780605e-05, | |
| "loss": 0.7622, | |
| "step": 9020 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.548986769385361e-05, | |
| "loss": 0.7608, | |
| "step": 9040 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.498743928990119e-05, | |
| "loss": 0.7613, | |
| "step": 9060 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.448501088594875e-05, | |
| "loss": 0.759, | |
| "step": 9080 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 7.398258248199631e-05, | |
| "loss": 0.7585, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 7.348015407804387e-05, | |
| "loss": 0.7609, | |
| "step": 9120 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 7.297772567409144e-05, | |
| "loss": 0.76, | |
| "step": 9140 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 7.2475297270139e-05, | |
| "loss": 0.7621, | |
| "step": 9160 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 7.197286886618657e-05, | |
| "loss": 0.7587, | |
| "step": 9180 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 7.147044046223413e-05, | |
| "loss": 0.7589, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.7685341835021973, | |
| "eval_runtime": 8.3378, | |
| "eval_samples_per_second": 239.872, | |
| "eval_steps_per_second": 1.919, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 7.096801205828169e-05, | |
| "loss": 0.7708, | |
| "step": 9220 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 7.046558365432925e-05, | |
| "loss": 0.7468, | |
| "step": 9240 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 6.996315525037681e-05, | |
| "loss": 0.7669, | |
| "step": 9260 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 6.946072684642437e-05, | |
| "loss": 0.7639, | |
| "step": 9280 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 6.895829844247193e-05, | |
| "loss": 0.764, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 6.845587003851951e-05, | |
| "loss": 0.7605, | |
| "step": 9320 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 6.795344163456707e-05, | |
| "loss": 0.7638, | |
| "step": 9340 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 6.745101323061463e-05, | |
| "loss": 0.753, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 6.694858482666219e-05, | |
| "loss": 0.7567, | |
| "step": 9380 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 6.644615642270977e-05, | |
| "loss": 0.7604, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 0.7682663798332214, | |
| "eval_runtime": 8.2956, | |
| "eval_samples_per_second": 241.092, | |
| "eval_steps_per_second": 1.929, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 6.594372801875733e-05, | |
| "loss": 0.7603, | |
| "step": 9420 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 6.544129961480489e-05, | |
| "loss": 0.7677, | |
| "step": 9440 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 6.493887121085245e-05, | |
| "loss": 0.7692, | |
| "step": 9460 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 6.443644280690001e-05, | |
| "loss": 0.7637, | |
| "step": 9480 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 6.393401440294757e-05, | |
| "loss": 0.756, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 6.343158599899513e-05, | |
| "loss": 0.7572, | |
| "step": 9520 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 6.29291575950427e-05, | |
| "loss": 0.7696, | |
| "step": 9540 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 6.242672919109027e-05, | |
| "loss": 0.753, | |
| "step": 9560 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 6.192430078713783e-05, | |
| "loss": 0.7619, | |
| "step": 9580 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 6.142187238318539e-05, | |
| "loss": 0.7574, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 0.7677283883094788, | |
| "eval_runtime": 8.2754, | |
| "eval_samples_per_second": 241.68, | |
| "eval_steps_per_second": 1.933, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 6.091944397923295e-05, | |
| "loss": 0.7624, | |
| "step": 9620 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 6.0417015575280514e-05, | |
| "loss": 0.7554, | |
| "step": 9640 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 5.9914587171328075e-05, | |
| "loss": 0.7635, | |
| "step": 9660 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 5.941215876737565e-05, | |
| "loss": 0.7586, | |
| "step": 9680 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 5.890973036342321e-05, | |
| "loss": 0.755, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 5.840730195947077e-05, | |
| "loss": 0.7584, | |
| "step": 9720 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 5.7904873555518333e-05, | |
| "loss": 0.7528, | |
| "step": 9740 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 5.74024451515659e-05, | |
| "loss": 0.7597, | |
| "step": 9760 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 5.690001674761346e-05, | |
| "loss": 0.7527, | |
| "step": 9780 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 5.6397588343661024e-05, | |
| "loss": 0.7617, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 0.7668038010597229, | |
| "eval_runtime": 8.3597, | |
| "eval_samples_per_second": 239.242, | |
| "eval_steps_per_second": 1.914, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 5.5895159939708585e-05, | |
| "loss": 0.7584, | |
| "step": 9820 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 5.5392731535756146e-05, | |
| "loss": 0.762, | |
| "step": 9840 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 5.4890303131803714e-05, | |
| "loss": 0.7586, | |
| "step": 9860 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 5.4387874727851275e-05, | |
| "loss": 0.7569, | |
| "step": 9880 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 5.3885446323898836e-05, | |
| "loss": 0.7611, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 5.33830179199464e-05, | |
| "loss": 0.7581, | |
| "step": 9920 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.2880589515993965e-05, | |
| "loss": 0.7657, | |
| "step": 9940 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.237816111204153e-05, | |
| "loss": 0.7504, | |
| "step": 9960 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.1875732708089094e-05, | |
| "loss": 0.7547, | |
| "step": 9980 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.1373304304136655e-05, | |
| "loss": 0.7588, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": 0.766875147819519, | |
| "eval_runtime": 8.3125, | |
| "eval_samples_per_second": 240.603, | |
| "eval_steps_per_second": 1.925, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.0870875900184223e-05, | |
| "loss": 0.7588, | |
| "step": 10020 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.0368447496231785e-05, | |
| "loss": 0.7544, | |
| "step": 10040 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.9866019092279346e-05, | |
| "loss": 0.7588, | |
| "step": 10060 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.936359068832691e-05, | |
| "loss": 0.7547, | |
| "step": 10080 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.8861162284374475e-05, | |
| "loss": 0.7608, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.8358733880422036e-05, | |
| "loss": 0.7539, | |
| "step": 10120 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.78563054764696e-05, | |
| "loss": 0.7639, | |
| "step": 10140 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.735387707251716e-05, | |
| "loss": 0.7622, | |
| "step": 10160 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.6851448668564726e-05, | |
| "loss": 0.7528, | |
| "step": 10180 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.634902026461229e-05, | |
| "loss": 0.7566, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 0.7660693526268005, | |
| "eval_runtime": 8.2951, | |
| "eval_samples_per_second": 241.107, | |
| "eval_steps_per_second": 1.929, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.584659186065985e-05, | |
| "loss": 0.7545, | |
| "step": 10220 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.5344163456707416e-05, | |
| "loss": 0.7505, | |
| "step": 10240 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.4841735052754984e-05, | |
| "loss": 0.7645, | |
| "step": 10260 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.4339306648802545e-05, | |
| "loss": 0.7566, | |
| "step": 10280 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.383687824485011e-05, | |
| "loss": 0.7509, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.333444984089767e-05, | |
| "loss": 0.7546, | |
| "step": 10320 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.285714285714285e-05, | |
| "loss": 0.7533, | |
| "step": 10340 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.235471445319041e-05, | |
| "loss": 0.7509, | |
| "step": 10360 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.185228604923798e-05, | |
| "loss": 0.7558, | |
| "step": 10380 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.1349857645285547e-05, | |
| "loss": 0.7624, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 0.7657083868980408, | |
| "eval_runtime": 8.2828, | |
| "eval_samples_per_second": 241.464, | |
| "eval_steps_per_second": 1.932, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.084742924133311e-05, | |
| "loss": 0.7509, | |
| "step": 10420 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.0345000837380676e-05, | |
| "loss": 0.7509, | |
| "step": 10440 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.984257243342824e-05, | |
| "loss": 0.761, | |
| "step": 10460 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.93401440294758e-05, | |
| "loss": 0.7546, | |
| "step": 10480 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.883771562552336e-05, | |
| "loss": 0.764, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.833528722157092e-05, | |
| "loss": 0.765, | |
| "step": 10520 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.783285881761849e-05, | |
| "loss": 0.7551, | |
| "step": 10540 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.733043041366605e-05, | |
| "loss": 0.7554, | |
| "step": 10560 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.682800200971361e-05, | |
| "loss": 0.7574, | |
| "step": 10580 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.632557360576117e-05, | |
| "loss": 0.7647, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 0.7651572227478027, | |
| "eval_runtime": 8.2868, | |
| "eval_samples_per_second": 241.347, | |
| "eval_steps_per_second": 1.931, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.584826662200636e-05, | |
| "loss": 0.7508, | |
| "step": 10620 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.534583821805393e-05, | |
| "loss": 0.7636, | |
| "step": 10640 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.484340981410149e-05, | |
| "loss": 0.7584, | |
| "step": 10660 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.434098141014905e-05, | |
| "loss": 0.7677, | |
| "step": 10680 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.383855300619661e-05, | |
| "loss": 0.7493, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.333612460224418e-05, | |
| "loss": 0.7557, | |
| "step": 10720 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.283369619829174e-05, | |
| "loss": 0.7528, | |
| "step": 10740 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.23312677943393e-05, | |
| "loss": 0.7573, | |
| "step": 10760 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.182883939038687e-05, | |
| "loss": 0.7471, | |
| "step": 10780 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.132641098643443e-05, | |
| "loss": 0.7537, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 0.7651455402374268, | |
| "eval_runtime": 8.2847, | |
| "eval_samples_per_second": 241.409, | |
| "eval_steps_per_second": 1.931, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.082398258248199e-05, | |
| "loss": 0.7538, | |
| "step": 10820 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.0321554178529556e-05, | |
| "loss": 0.7585, | |
| "step": 10840 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.981912577457712e-05, | |
| "loss": 0.7533, | |
| "step": 10860 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.9316697370624682e-05, | |
| "loss": 0.7607, | |
| "step": 10880 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.8814268966672247e-05, | |
| "loss": 0.7522, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.831184056271981e-05, | |
| "loss": 0.7581, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.7809412158767376e-05, | |
| "loss": 0.7597, | |
| "step": 10940 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.7306983754814937e-05, | |
| "loss": 0.7649, | |
| "step": 10960 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.68045553508625e-05, | |
| "loss": 0.7645, | |
| "step": 10980 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.6302126946910063e-05, | |
| "loss": 0.743, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 0.7645469903945923, | |
| "eval_runtime": 8.314, | |
| "eval_samples_per_second": 240.558, | |
| "eval_steps_per_second": 1.924, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.5799698542957624e-05, | |
| "loss": 0.7488, | |
| "step": 11020 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.529727013900519e-05, | |
| "loss": 0.7515, | |
| "step": 11040 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.4794841735052756e-05, | |
| "loss": 0.7582, | |
| "step": 11060 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.4292413331100317e-05, | |
| "loss": 0.7564, | |
| "step": 11080 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.378998492714788e-05, | |
| "loss": 0.7486, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.3287556523195443e-05, | |
| "loss": 0.7537, | |
| "step": 11120 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.2785128119243004e-05, | |
| "loss": 0.7593, | |
| "step": 11140 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.228269971529057e-05, | |
| "loss": 0.7435, | |
| "step": 11160 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.178027131133813e-05, | |
| "loss": 0.7646, | |
| "step": 11180 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.1277842907385698e-05, | |
| "loss": 0.7445, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 0.7643282413482666, | |
| "eval_runtime": 8.2655, | |
| "eval_samples_per_second": 241.97, | |
| "eval_steps_per_second": 1.936, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.077541450343326e-05, | |
| "loss": 0.7576, | |
| "step": 11220 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.0272986099480824e-05, | |
| "loss": 0.7553, | |
| "step": 11240 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.9770557695528385e-05, | |
| "loss": 0.7567, | |
| "step": 11260 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.926812929157595e-05, | |
| "loss": 0.7501, | |
| "step": 11280 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.876570088762351e-05, | |
| "loss": 0.7502, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.8263272483671075e-05, | |
| "loss": 0.756, | |
| "step": 11320 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.776084407971864e-05, | |
| "loss": 0.7528, | |
| "step": 11340 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.72584156757662e-05, | |
| "loss": 0.7578, | |
| "step": 11360 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.6755987271813765e-05, | |
| "loss": 0.7588, | |
| "step": 11380 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.625355886786133e-05, | |
| "loss": 0.7486, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 0.7640262842178345, | |
| "eval_runtime": 8.2822, | |
| "eval_samples_per_second": 241.482, | |
| "eval_steps_per_second": 1.932, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.575113046390889e-05, | |
| "loss": 0.7527, | |
| "step": 11420 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.5248702059956454e-05, | |
| "loss": 0.7472, | |
| "step": 11440 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.4746273656004018e-05, | |
| "loss": 0.7476, | |
| "step": 11460 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.4243845252051581e-05, | |
| "loss": 0.7551, | |
| "step": 11480 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.3741416848099144e-05, | |
| "loss": 0.7609, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.3238988444146708e-05, | |
| "loss": 0.7496, | |
| "step": 11520 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.2736560040194271e-05, | |
| "loss": 0.7528, | |
| "step": 11540 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.2234131636241834e-05, | |
| "loss": 0.7541, | |
| "step": 11560 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.1731703232289399e-05, | |
| "loss": 0.7492, | |
| "step": 11580 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.1229274828336962e-05, | |
| "loss": 0.7464, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.7637657523155212, | |
| "eval_runtime": 8.2732, | |
| "eval_samples_per_second": 241.743, | |
| "eval_steps_per_second": 1.934, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.0726846424384524e-05, | |
| "loss": 0.7549, | |
| "step": 11620 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.0224418020432087e-05, | |
| "loss": 0.7532, | |
| "step": 11640 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.721989616479652e-06, | |
| "loss": 0.7513, | |
| "step": 11660 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 9.219561212527215e-06, | |
| "loss": 0.7657, | |
| "step": 11680 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 8.717132808574777e-06, | |
| "loss": 0.7445, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 8.21470440462234e-06, | |
| "loss": 0.7574, | |
| "step": 11720 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.712276000669905e-06, | |
| "loss": 0.7576, | |
| "step": 11740 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 7.209847596717467e-06, | |
| "loss": 0.7599, | |
| "step": 11760 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 6.7074191927650305e-06, | |
| "loss": 0.7558, | |
| "step": 11780 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 6.204990788812593e-06, | |
| "loss": 0.7541, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": 0.7635765671730042, | |
| "eval_runtime": 8.2847, | |
| "eval_samples_per_second": 241.409, | |
| "eval_steps_per_second": 1.931, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 5.702562384860157e-06, | |
| "loss": 0.758, | |
| "step": 11820 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 5.20013398090772e-06, | |
| "loss": 0.7381, | |
| "step": 11840 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 4.697705576955284e-06, | |
| "loss": 0.7636, | |
| "step": 11860 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.1952771730028464e-06, | |
| "loss": 0.7548, | |
| "step": 11880 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.6928487690504097e-06, | |
| "loss": 0.7537, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 3.1904203650979734e-06, | |
| "loss": 0.7548, | |
| "step": 11920 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.6879919611455367e-06, | |
| "loss": 0.7515, | |
| "step": 11940 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.1855635571931e-06, | |
| "loss": 0.7458, | |
| "step": 11960 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.683135153240663e-06, | |
| "loss": 0.7466, | |
| "step": 11980 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.1807067492882263e-06, | |
| "loss": 0.7565, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.763276994228363, | |
| "eval_runtime": 8.2818, | |
| "eval_samples_per_second": 241.494, | |
| "eval_steps_per_second": 1.932, | |
| "step": 12000 | |
| } | |
| ], | |
| "max_steps": 12042, | |
| "num_train_epochs": 1, | |
| "total_flos": 3.119715122549883e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |