| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.697350069735007, | |
| "eval_steps": 25, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 7.222222222222222e-05, | |
| "loss": 2.2776, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00014444444444444444, | |
| "loss": 2.2089, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00021666666666666666, | |
| "loss": 2.2124, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0002888888888888889, | |
| "loss": 2.0872, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0003611111111111111, | |
| "loss": 1.9608, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0004333333333333333, | |
| "loss": 1.9254, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0005055555555555555, | |
| "loss": 1.8716, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0005777777777777778, | |
| "loss": 1.8424, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00065, | |
| "loss": 1.8139, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0006499909512851264, | |
| "loss": 1.8298, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006499638056443784, | |
| "loss": 1.735, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006499185645893443, | |
| "loss": 1.707, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006498552306392452, | |
| "loss": 1.7144, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006497738073207941, | |
| "loss": 1.6774, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0006496742991679994, | |
| "loss": 1.6373, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006495567117219131, | |
| "loss": 1.5874, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006494210515303213, | |
| "loss": 1.5767, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006492673261473803, | |
| "loss": 1.3921, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0006490955441331957, | |
| "loss": 1.2696, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006489057150533456, | |
| "loss": 1.065, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006486978494783486, | |
| "loss": 0.9967, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006484719589830741, | |
| "loss": 0.8554, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0006482280561460987, | |
| "loss": 0.8944, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0006479661545490054, | |
| "loss": 0.8563, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.000647686268775627, | |
| "loss": 0.9036, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.782578706741333, | |
| "eval_runtime": 47.3187, | |
| "eval_samples_per_second": 2.113, | |
| "eval_steps_per_second": 0.528, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0006473884144112352, | |
| "loss": 0.8622, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0006470726080416708, | |
| "loss": 0.8543, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.000646738867252422, | |
| "loss": 0.821, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006463872106276441, | |
| "loss": 0.798, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006460176577491251, | |
| "loss": 0.7795, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006456302291951948, | |
| "loss": 0.845, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0006452249465395796, | |
| "loss": 0.8199, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0006448018323502008, | |
| "loss": 0.8371, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0006443609101879176, | |
| "loss": 0.8235, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0006439022046052159, | |
| "loss": 0.8063, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0006434257411448404, | |
| "loss": 0.8153, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006429315463383726, | |
| "loss": 0.8219, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006424196477047534, | |
| "loss": 0.8167, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006418900737487508, | |
| "loss": 0.7766, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0006413428539593724, | |
| "loss": 0.8465, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006407780188082232, | |
| "loss": 0.7966, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006401955997478094, | |
| "loss": 0.8225, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006395956292097865, | |
| "loss": 0.7915, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006389781406031534, | |
| "loss": 0.7923, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0006383431683123921, | |
| "loss": 0.8051, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0006376907476955534, | |
| "loss": 0.8127, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.000637020915082287, | |
| "loss": 0.7747, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00063633370777182, | |
| "loss": 0.797, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0006356291640308783, | |
| "loss": 0.743, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.000634907323091557, | |
| "loss": 0.8201, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 0.7397407293319702, | |
| "eval_runtime": 47.3134, | |
| "eval_samples_per_second": 2.114, | |
| "eval_steps_per_second": 0.528, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.000634168225149135, | |
| "loss": 0.8621, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0006334119113598372, | |
| "loss": 0.8159, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0006326384238385426, | |
| "loss": 0.7929, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0006318478056564394, | |
| "loss": 0.8438, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0006310401008386257, | |
| "loss": 0.7576, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0006302153543616592, | |
| "loss": 0.7918, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0006293736121510519, | |
| "loss": 0.8314, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0006285149210787133, | |
| "loss": 0.7491, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0006276393289603396, | |
| "loss": 0.78, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0006267468845527521, | |
| "loss": 0.786, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0006258376375511813, | |
| "loss": 0.7788, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0006249116385865004, | |
| "loss": 0.7504, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0006239689392224053, | |
| "loss": 0.7997, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0006230095919525438, | |
| "loss": 0.7863, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0006220336501975922, | |
| "loss": 0.7892, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0006210411683022809, | |
| "loss": 0.7872, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0006200322015323679, | |
| "loss": 0.7779, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0006190068060715616, | |
| "loss": 0.8178, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0006179650390183923, | |
| "loss": 0.7521, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0006169069583830324, | |
| "loss": 0.8174, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0006158326230840664, | |
| "loss": 0.7539, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0006147420929452101, | |
| "loss": 0.7906, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0006136354286919789, | |
| "loss": 0.7639, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.000612512691948307, | |
| "loss": 0.7884, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0006113739452331156, | |
| "loss": 0.809, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 0.7233907580375671, | |
| "eval_runtime": 47.3612, | |
| "eval_samples_per_second": 2.111, | |
| "eval_steps_per_second": 0.528, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0006102192519568312, | |
| "loss": 0.7317, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0006090486764178553, | |
| "loss": 0.7376, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0006078622837989834, | |
| "loss": 0.7396, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0006066601401637757, | |
| "loss": 0.7247, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0006054423124528785, | |
| "loss": 0.7662, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0006042088684802962, | |
| "loss": 0.7529, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0006029598769296152, | |
| "loss": 0.7951, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0006016954073501798, | |
| "loss": 0.774, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0006004155301532189, | |
| "loss": 0.7052, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0005991203166079252, | |
| "loss": 0.6928, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0005978098388374867, | |
| "loss": 0.7521, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.000596484169815071, | |
| "loss": 0.7285, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.000595143383359761, | |
| "loss": 0.6915, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.000593787554132445, | |
| "loss": 0.7301, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.000592416757631659, | |
| "loss": 0.7669, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0005910310701893825, | |
| "loss": 0.7103, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0005896305689667885, | |
| "loss": 0.7646, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0005882153319499459, | |
| "loss": 0.743, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0005867854379454778, | |
| "loss": 0.6911, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0005853409665761729, | |
| "loss": 0.7662, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0005838819982765514, | |
| "loss": 0.7422, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0005824086142883867, | |
| "loss": 0.8344, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.000580920896656181, | |
| "loss": 0.7714, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0005794189282225969, | |
| "loss": 0.6885, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0005779027926238441, | |
| "loss": 0.7355, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 0.7278771996498108, | |
| "eval_runtime": 47.3492, | |
| "eval_samples_per_second": 2.112, | |
| "eval_steps_per_second": 0.528, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0005763725742850227, | |
| "loss": 0.7363, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0005748283584154215, | |
| "loss": 0.7931, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0005732702310037735, | |
| "loss": 0.7028, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0005716982788134676, | |
| "loss": 0.7677, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.000570112589377717, | |
| "loss": 0.7406, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0005685132509946853, | |
| "loss": 0.7332, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0005669003527225695, | |
| "loss": 0.729, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0005652739843746411, | |
| "loss": 0.7529, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0005636342365142442, | |
| "loss": 0.7445, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0005619812004497534, | |
| "loss": 0.7615, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0005603149682294887, | |
| "loss": 0.7293, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0005586356326365904, | |
| "loss": 0.7309, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0005569432871838522, | |
| "loss": 0.7496, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0005552380261085136, | |
| "loss": 0.7039, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0005535199443670132, | |
| "loss": 0.7672, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0005517891376297008, | |
| "loss": 0.7628, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0005500457022755095, | |
| "loss": 0.7324, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0005482897353865897, | |
| "loss": 0.7217, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0005465213347429026, | |
| "loss": 0.7041, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0005447405988167756, | |
| "loss": 0.7194, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.000542947626767419, | |
| "loss": 0.7496, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0005411425184354042, | |
| "loss": 0.7347, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0005393253743371041, | |
| "loss": 0.7196, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0005374962956590962, | |
| "loss": 0.7344, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0005356553842525278, | |
| "loss": 0.7568, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 0.7157579064369202, | |
| "eval_runtime": 47.3884, | |
| "eval_samples_per_second": 2.11, | |
| "eval_steps_per_second": 0.528, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0005338027426274445, | |
| "loss": 0.7667, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0005319384739470821, | |
| "loss": 0.7153, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0005300626820221224, | |
| "loss": 0.7016, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0005281754713049115, | |
| "loss": 0.6928, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0005262769468836446, | |
| "loss": 0.7486, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0005243672144765132, | |
| "loss": 0.7203, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0005224463804258194, | |
| "loss": 0.7265, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0005205145516920532, | |
| "loss": 0.6776, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0005185718358479369, | |
| "loss": 0.7298, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0005166183410724353, | |
| "loss": 0.7512, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0005146541761447313, | |
| "loss": 0.7544, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0005126794504381689, | |
| "loss": 0.7438, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0005106942739141625, | |
| "loss": 0.7278, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0005086987571160746, | |
| "loss": 0.7458, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0005066930111630589, | |
| "loss": 0.8019, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0005046771477438739, | |
| "loss": 0.7742, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.000502651279110663, | |
| "loss": 0.7462, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0005006155180727038, | |
| "loss": 0.7004, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0004985699779901268, | |
| "loss": 0.7311, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0004965147727676027, | |
| "loss": 0.7191, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0004944500168479995, | |
| "loss": 0.7011, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0004923758252060099, | |
| "loss": 0.7394, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0004902923133417497, | |
| "loss": 0.7402, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00048819959727432503, | |
| "loss": 0.6991, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.000486097793535373, | |
| "loss": 0.721, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 0.7129714488983154, | |
| "eval_runtime": 47.3388, | |
| "eval_samples_per_second": 2.112, | |
| "eval_steps_per_second": 0.528, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0004839870191625722, | |
| "loss": 0.6554, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00048186739169312517, | |
| "loss": 0.6815, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0004797390291572145, | |
| "loss": 0.7029, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0004776020500714291, | |
| "loss": 0.7292, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0004754565734321654, | |
| "loss": 0.6858, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0004733027187090013, | |
| "loss": 0.7268, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0004711406058380429, | |
| "loss": 0.6895, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00046897035521524673, | |
| "loss": 0.6827, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0004667920876897147, | |
| "loss": 0.7203, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0004646059245569654, | |
| "loss": 0.7267, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0004624119875521793, | |
| "loss": 0.7001, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0004602103988434206, | |
| "loss": 0.6973, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00045800128102483376, | |
| "loss": 0.7663, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0004557847571098175, | |
| "loss": 0.699, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0004535609505241742, | |
| "loss": 0.7609, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00045132998509923763, | |
| "loss": 0.6936, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0004490919850649773, | |
| "loss": 0.6748, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0004468470750430804, | |
| "loss": 0.6764, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00044459538004001275, | |
| "loss": 0.7278, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.000442337025440058, | |
| "loss": 0.7622, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0004400721369983352, | |
| "loss": 0.7125, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0004378008408337966, | |
| "loss": 0.7045, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0004355232634222044, | |
| "loss": 0.6474, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0004332395315890887, | |
| "loss": 0.7072, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0004309497725026844, | |
| "loss": 0.71, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 0.7100925445556641, | |
| "eval_runtime": 47.2576, | |
| "eval_samples_per_second": 2.116, | |
| "eval_steps_per_second": 0.529, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0004286541136668506, | |
| "loss": 0.7112, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00042635268291397056, | |
| "loss": 0.7192, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00042404560839783294, | |
| "loss": 0.7662, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0004217330185864961, | |
| "loss": 0.7295, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00041941504225513447, | |
| "loss": 0.7412, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0004170918084788675, | |
| "loss": 0.7122, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0004147634466255721, | |
| "loss": 0.7375, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0004124300863486793, | |
| "loss": 0.7056, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00041009185757995433, | |
| "loss": 0.7127, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00040774889052226133, | |
| "loss": 0.699, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0004054013156423135, | |
| "loss": 0.7063, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00040304926366340746, | |
| "loss": 0.7145, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00040069286555814465, | |
| "loss": 0.7283, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00039833225254113795, | |
| "loss": 0.7117, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.000395967556061705, | |
| "loss": 0.6506, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00039359890779654843, | |
| "loss": 0.7239, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.000391226439642424, | |
| "loss": 0.7084, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0003888502837087955, | |
| "loss": 0.6888, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0003864705723104786, | |
| "loss": 0.6919, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00038408743796027284, | |
| "loss": 0.7193, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00038170101336158275, | |
| "loss": 0.6699, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0003793114314010282, | |
| "loss": 0.6661, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00037691882514104546, | |
| "loss": 0.7258, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00037452332781247636, | |
| "loss": 0.678, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00037212507280715056, | |
| "loss": 0.7179, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 0.7194330096244812, | |
| "eval_runtime": 47.2733, | |
| "eval_samples_per_second": 2.115, | |
| "eval_steps_per_second": 0.529, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0003697241936704573, | |
| "loss": 0.6818, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00036732082409390886, | |
| "loss": 0.6697, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00036491509790769616, | |
| "loss": 0.7394, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0003625071490732366, | |
| "loss": 0.6873, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0003600971116757144, | |
| "loss": 0.7043, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0003576851199166141, | |
| "loss": 0.6955, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00035527130810624776, | |
| "loss": 0.7175, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00035285581065627595, | |
| "loss": 0.7508, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.000350438762072223, | |
| "loss": 0.6486, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00034802029694598705, | |
| "loss": 0.6568, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0003456005499483456, | |
| "loss": 0.7239, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00034317965582145686, | |
| "loss": 0.7016, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00034075774937135557, | |
| "loss": 0.687, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00033833496546044746, | |
| "loss": 0.6799, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00033591143899999905, | |
| "loss": 0.6837, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00033348730494262534, | |
| "loss": 0.7378, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0003310626982747749, | |
| "loss": 0.6542, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0003286377540092133, | |
| "loss": 0.6899, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00032621260717750515, | |
| "loss": 0.6803, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0003237873928224948, | |
| "loss": 0.6789, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00032136224599078677, | |
| "loss": 0.7018, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0003189373017252252, | |
| "loss": 0.6739, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0003165126950573747, | |
| "loss": 0.6385, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0003140885610000009, | |
| "loss": 0.6665, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00031166503453955246, | |
| "loss": 0.6987, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 0.7022287249565125, | |
| "eval_runtime": 47.2534, | |
| "eval_samples_per_second": 2.116, | |
| "eval_steps_per_second": 0.529, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00030924225062864435, | |
| "loss": 0.6822, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00030682034417854327, | |
| "loss": 0.6643, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0003043994500516544, | |
| "loss": 0.6735, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0003019797030540131, | |
| "loss": 0.6723, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002995612379277771, | |
| "loss": 0.6638, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.000297144189343724, | |
| "loss": 0.6975, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00029472869189375227, | |
| "loss": 0.7059, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00029231488008338595, | |
| "loss": 0.7657, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002899028883242856, | |
| "loss": 0.707, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00028749285092676344, | |
| "loss": 0.6707, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00028508490209230386, | |
| "loss": 0.7009, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00028267917590609116, | |
| "loss": 0.6248, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0002802758063295427, | |
| "loss": 0.6933, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00027787492719284936, | |
| "loss": 0.6744, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002754766721875236, | |
| "loss": 0.6926, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002730811748589547, | |
| "loss": 0.725, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002706885685989718, | |
| "loss": 0.73, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0002682989866384173, | |
| "loss": 0.6588, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002659125620397272, | |
| "loss": 0.6382, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002635294276895214, | |
| "loss": 0.6902, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00026114971629120453, | |
| "loss": 0.6632, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.000258773560357576, | |
| "loss": 0.6414, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002564010922034516, | |
| "loss": 0.6523, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00025403244393829504, | |
| "loss": 0.7573, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.000251667747458862, | |
| "loss": 0.7295, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.7042359709739685, | |
| "eval_runtime": 47.2541, | |
| "eval_samples_per_second": 2.116, | |
| "eval_steps_per_second": 0.529, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002493071344418553, | |
| "loss": 0.7289, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00024695073633659246, | |
| "loss": 0.6323, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00024459868435768646, | |
| "loss": 0.6575, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00024225110947773856, | |
| "loss": 0.7192, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00023990814242004572, | |
| "loss": 0.6669, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00023756991365132073, | |
| "loss": 0.6991, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.000235236553374428, | |
| "loss": 0.63, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00023290819152113257, | |
| "loss": 0.7387, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00023058495774486555, | |
| "loss": 0.6548, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00022826698141350396, | |
| "loss": 0.6401, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00022595439160216711, | |
| "loss": 0.6642, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0002236473170860295, | |
| "loss": 0.7435, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00022134588633314936, | |
| "loss": 0.6788, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00021905022749731565, | |
| "loss": 0.7188, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00021676046841091133, | |
| "loss": 0.6899, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0002144767365777955, | |
| "loss": 0.6762, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0002121991591662034, | |
| "loss": 0.6592, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00020992786300166473, | |
| "loss": 0.6636, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00020766297455994203, | |
| "loss": 0.6471, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00020540461995998728, | |
| "loss": 0.6782, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00020315292495691971, | |
| "loss": 0.6857, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00020090801493502278, | |
| "loss": 0.6337, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0001986700149007624, | |
| "loss": 0.6529, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0001964390494758258, | |
| "loss": 0.6749, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00019421524289018252, | |
| "loss": 0.6614, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 0.704497754573822, | |
| "eval_runtime": 47.2368, | |
| "eval_samples_per_second": 2.117, | |
| "eval_steps_per_second": 0.529, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0001919987189751662, | |
| "loss": 0.6318, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00018978960115657945, | |
| "loss": 0.6396, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00018758801244782072, | |
| "loss": 0.6918, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0001853940754430346, | |
| "loss": 0.7145, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00018320791231028527, | |
| "loss": 0.7019, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00018102964478475318, | |
| "loss": 0.7036, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0001788593941619569, | |
| "loss": 0.6391, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00017669728129099881, | |
| "loss": 0.6977, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00017454342656783464, | |
| "loss": 0.6911, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.000172397949928571, | |
| "loss": 0.731, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00017026097084278557, | |
| "loss": 0.675, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00016813260830687474, | |
| "loss": 0.6953, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00016601298083742793, | |
| "loss": 0.6629, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00016390220646462695, | |
| "loss": 0.6865, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00016180040272567491, | |
| "loss": 0.6926, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00015970768665825037, | |
| "loss": 0.7088, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00015762417479399005, | |
| "loss": 0.6628, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0001555499831520006, | |
| "loss": 0.6601, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00015348522723239726, | |
| "loss": 0.6605, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00015143002200987304, | |
| "loss": 0.6514, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00014938448192729616, | |
| "loss": 0.6739, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00014734872088933713, | |
| "loss": 0.6996, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00014532285225612613, | |
| "loss": 0.6322, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00014330698883694115, | |
| "loss": 0.6382, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00014130124288392538, | |
| "loss": 0.6661, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 0.7015612721443176, | |
| "eval_runtime": 47.2358, | |
| "eval_samples_per_second": 2.117, | |
| "eval_steps_per_second": 0.529, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 430, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "total_flos": 7.322913306456883e+17, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |