| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.942528735632184, | |
| "eval_steps": 22, | |
| "global_step": 261, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 19.59183260405101, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.3985, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 1.5676738023757935, | |
| "eval_runtime": 3.9227, | |
| "eval_samples_per_second": 4.844, | |
| "eval_steps_per_second": 1.275, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 25.857640141956836, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.6073, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 19.53747244629775, | |
| "learning_rate": 6e-06, | |
| "loss": 1.5784, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 32.1611390841105, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.4924, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 25.68491589990429, | |
| "learning_rate": 1e-05, | |
| "loss": 1.5215, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 21.800722806654328, | |
| "learning_rate": 1.2e-05, | |
| "loss": 1.5508, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 17.19812526688047, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 1.205, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 33.24510948526866, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.6376, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 14.986129451187, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.454, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 17.517194747344856, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6559, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 18.22606604955052, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 1.5816, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 26.577328122239592, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.7884, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 17.563463503652706, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 1.4405, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 19.98739837372538, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 1.7512, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 16.25364292099236, | |
| "learning_rate": 3e-05, | |
| "loss": 1.7037, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 22.328347783615648, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 1.5476, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 20.71265405702363, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 1.8108, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 22.425069186679085, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.6751, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 18.646553829771403, | |
| "learning_rate": 3.8e-05, | |
| "loss": 1.7696, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 16.74801305116847, | |
| "learning_rate": 4e-05, | |
| "loss": 1.7699, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 30.99364381661585, | |
| "learning_rate": 4.2e-05, | |
| "loss": 2.1827, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 19.761245037191404, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 1.4776, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.856759786605835, | |
| "eval_runtime": 1.4309, | |
| "eval_samples_per_second": 13.279, | |
| "eval_steps_per_second": 3.494, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 27.821861354666428, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 1.8677, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 22.80354998875929, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.7424, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 19.920321630615994, | |
| "learning_rate": 5e-05, | |
| "loss": 1.769, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 23.82621534355921, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 1.8615, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 27.63826215875828, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 1.7164, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 30.810269474286084, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 1.8922, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 23.279443617002265, | |
| "learning_rate": 5.8e-05, | |
| "loss": 1.8507, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 18.091756285883704, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6537, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 23.292568819411724, | |
| "learning_rate": 6.2e-05, | |
| "loss": 1.9125, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 52.21913805211888, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 1.8456, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 30.771918199992527, | |
| "learning_rate": 6.6e-05, | |
| "loss": 1.9398, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 40.19880102087157, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 2.3763, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 28.33779955799431, | |
| "learning_rate": 7e-05, | |
| "loss": 2.0815, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 54.379783823327905, | |
| "learning_rate": 7.2e-05, | |
| "loss": 2.1032, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 662.6041427579516, | |
| "learning_rate": 7.4e-05, | |
| "loss": 3.5917, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 4011.501090614335, | |
| "learning_rate": 7.6e-05, | |
| "loss": 7.3933, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 753.5816146908044, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 15.8371, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 291.86609997137384, | |
| "learning_rate": 8e-05, | |
| "loss": 9.0249, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 922.0326051718562, | |
| "learning_rate": 8.2e-05, | |
| "loss": 9.8922, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 115.68135873083658, | |
| "learning_rate": 8.4e-05, | |
| "loss": 8.2719, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 693.1702757980898, | |
| "learning_rate": 8.6e-05, | |
| "loss": 24.1699, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 219.78828591396768, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 10.1246, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 8.758976936340332, | |
| "eval_runtime": 1.3819, | |
| "eval_samples_per_second": 13.749, | |
| "eval_steps_per_second": 3.618, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 101.32256273283853, | |
| "learning_rate": 9e-05, | |
| "loss": 9.1756, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 11.958039992364316, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 7.7273, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 3232.8188937829473, | |
| "learning_rate": 9.4e-05, | |
| "loss": 8.7486, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 34.97640980952823, | |
| "learning_rate": 9.6e-05, | |
| "loss": 8.0394, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 28.785233378323184, | |
| "learning_rate": 9.8e-05, | |
| "loss": 7.6241, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 734.1733446536996, | |
| "learning_rate": 0.0001, | |
| "loss": 7.7813, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 59.66290191764372, | |
| "learning_rate": 0.00010200000000000001, | |
| "loss": 7.6734, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 18.23606863385719, | |
| "learning_rate": 0.00010400000000000001, | |
| "loss": 7.8783, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 15.152500341579357, | |
| "learning_rate": 0.00010600000000000002, | |
| "loss": 7.6016, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 25.1062172290986, | |
| "learning_rate": 0.00010800000000000001, | |
| "loss": 7.7206, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 30.75760910048317, | |
| "learning_rate": 0.00011000000000000002, | |
| "loss": 7.7526, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 18.354297835205724, | |
| "learning_rate": 0.00011200000000000001, | |
| "loss": 7.5551, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 32.48061320811231, | |
| "learning_rate": 0.00011399999999999999, | |
| "loss": 7.6922, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 26.624723764338736, | |
| "learning_rate": 0.000116, | |
| "loss": 7.5791, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 13.92226298912218, | |
| "learning_rate": 0.000118, | |
| "loss": 7.3692, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 15.428105634893914, | |
| "learning_rate": 0.00012, | |
| "loss": 7.564, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 23.02235056392551, | |
| "learning_rate": 0.000122, | |
| "loss": 7.3948, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 16.470374126805776, | |
| "learning_rate": 0.000124, | |
| "loss": 7.4646, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 19.574553557429, | |
| "learning_rate": 0.000126, | |
| "loss": 7.3902, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 25.549182808604662, | |
| "learning_rate": 0.00012800000000000002, | |
| "loss": 7.5461, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 618.1147749407063, | |
| "learning_rate": 0.00013000000000000002, | |
| "loss": 8.157, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 66.0610660913446, | |
| "learning_rate": 0.000132, | |
| "loss": 8.1284, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 8.004860877990723, | |
| "eval_runtime": 1.3748, | |
| "eval_samples_per_second": 13.82, | |
| "eval_steps_per_second": 3.637, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 41.635960690924975, | |
| "learning_rate": 0.000134, | |
| "loss": 8.0602, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 16.679869546723175, | |
| "learning_rate": 0.00013600000000000003, | |
| "loss": 7.8268, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 33.70142265056291, | |
| "learning_rate": 0.000138, | |
| "loss": 8.1206, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 43.29315748881759, | |
| "learning_rate": 0.00014, | |
| "loss": 7.7882, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 28.3799834727588, | |
| "learning_rate": 0.000142, | |
| "loss": 7.5454, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 30.911781055251613, | |
| "learning_rate": 0.000144, | |
| "loss": 7.7616, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 56.741836296758365, | |
| "learning_rate": 0.000146, | |
| "loss": 8.1145, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 13.967249574234195, | |
| "learning_rate": 0.000148, | |
| "loss": 7.6758, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 42.28071588262047, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 7.5507, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 27.40577229308579, | |
| "learning_rate": 0.000152, | |
| "loss": 7.6852, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 21.422615778584905, | |
| "learning_rate": 0.000154, | |
| "loss": 7.6071, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 28.22569647336005, | |
| "learning_rate": 0.00015600000000000002, | |
| "loss": 7.5556, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 20.075502929468385, | |
| "learning_rate": 0.00015800000000000002, | |
| "loss": 7.529, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 14.896626626967638, | |
| "learning_rate": 0.00016, | |
| "loss": 7.5352, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 16.98565517398293, | |
| "learning_rate": 0.000162, | |
| "loss": 7.5734, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 17.76803489316823, | |
| "learning_rate": 0.000164, | |
| "loss": 7.591, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 15.601674972992182, | |
| "learning_rate": 0.000166, | |
| "loss": 7.4251, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 21.36580777081032, | |
| "learning_rate": 0.000168, | |
| "loss": 7.728, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 19.73380900316605, | |
| "learning_rate": 0.00017, | |
| "loss": 7.3548, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 16.40313028374367, | |
| "learning_rate": 0.000172, | |
| "loss": 7.3652, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 11.846265862818466, | |
| "learning_rate": 0.000174, | |
| "loss": 7.4363, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 11.82176337757903, | |
| "learning_rate": 0.00017600000000000002, | |
| "loss": 7.3967, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 7.461406707763672, | |
| "eval_runtime": 1.3867, | |
| "eval_samples_per_second": 13.702, | |
| "eval_steps_per_second": 3.606, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 14.25806078550941, | |
| "learning_rate": 0.00017800000000000002, | |
| "loss": 7.3814, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 10.077089336320658, | |
| "learning_rate": 0.00018, | |
| "loss": 7.2599, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 15.159363102480643, | |
| "learning_rate": 0.000182, | |
| "loss": 7.5719, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 14.678683877513562, | |
| "learning_rate": 0.00018400000000000003, | |
| "loss": 7.4794, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 16.396549401486602, | |
| "learning_rate": 0.00018600000000000002, | |
| "loss": 7.6211, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 15.078668930441678, | |
| "learning_rate": 0.000188, | |
| "loss": 7.3625, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 13.546080322892589, | |
| "learning_rate": 0.00019, | |
| "loss": 7.3016, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 18.231949750348118, | |
| "learning_rate": 0.000192, | |
| "loss": 7.386, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 12.444086372431334, | |
| "learning_rate": 0.000194, | |
| "loss": 7.5534, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 9.994459143045797, | |
| "learning_rate": 0.000196, | |
| "loss": 7.4254, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 14.889247706503676, | |
| "learning_rate": 0.00019800000000000002, | |
| "loss": 7.3938, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 19.194847464605004, | |
| "learning_rate": 0.0002, | |
| "loss": 7.3875, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 19.234057674068023, | |
| "learning_rate": 0.00019998096274980728, | |
| "loss": 7.348, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 10.248320279074052, | |
| "learning_rate": 0.000199923858247567, | |
| "loss": 7.2365, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 15.579201434411983, | |
| "learning_rate": 0.00019982870823553308, | |
| "loss": 7.2351, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 10.951732160571428, | |
| "learning_rate": 0.00019969554894159723, | |
| "loss": 7.4413, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 12.034336556190219, | |
| "learning_rate": 0.00019952443106549533, | |
| "loss": 7.4256, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 11.555864069154051, | |
| "learning_rate": 0.00019931541975950378, | |
| "loss": 7.0947, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 8.079125584036722, | |
| "learning_rate": 0.00019906859460363307, | |
| "loss": 7.3727, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 10.901301706963714, | |
| "learning_rate": 0.00019878404957532814, | |
| "loss": 7.2419, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 9.771076993744128, | |
| "learning_rate": 0.0001984618930136869, | |
| "loss": 7.2896, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 11.395240298688034, | |
| "learning_rate": 0.00019810224757821064, | |
| "loss": 7.2567, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 7.299312591552734, | |
| "eval_runtime": 1.381, | |
| "eval_samples_per_second": 13.758, | |
| "eval_steps_per_second": 3.621, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 11.839939762683946, | |
| "learning_rate": 0.00019770525020210204, | |
| "loss": 7.3145, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 13.454044820108352, | |
| "learning_rate": 0.0001972710520401287, | |
| "loss": 7.3279, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 10.349510041217494, | |
| "learning_rate": 0.0001967998184110713, | |
| "loss": 7.0995, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 11.299695940906268, | |
| "learning_rate": 0.00019629172873477995, | |
| "loss": 7.1545, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 10.300523126150598, | |
| "learning_rate": 0.00019574697646386027, | |
| "loss": 7.2619, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 12.280692750358627, | |
| "learning_rate": 0.0001951657690100178, | |
| "loss": 7.4703, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 11.308344462386193, | |
| "learning_rate": 0.0001945483276650868, | |
| "loss": 7.2927, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 9.46182612207882, | |
| "learning_rate": 0.0001938948875167745, | |
| "loss": 7.1097, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 8.495214573764272, | |
| "learning_rate": 0.00019320569735915271, | |
| "loss": 7.2199, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 10.888318204738358, | |
| "learning_rate": 0.00019248101959793066, | |
| "loss": 7.4214, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 15.655909856272627, | |
| "learning_rate": 0.00019172113015054532, | |
| "loss": 7.4141, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 14.348570302527095, | |
| "learning_rate": 0.00019092631834110723, | |
| "loss": 7.2034, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 11.216620878113865, | |
| "learning_rate": 0.0001900968867902419, | |
| "loss": 7.1925, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 15.214529842718143, | |
| "learning_rate": 0.00018923315129986835, | |
| "loss": 7.204, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 24.933551829531577, | |
| "learning_rate": 0.00018833544073295917, | |
| "loss": 7.5231, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 12.291980045440198, | |
| "learning_rate": 0.00018740409688832764, | |
| "loss": 7.2323, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 19.503396545387695, | |
| "learning_rate": 0.00018643947437048944, | |
| "loss": 7.3214, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 13.982404823681808, | |
| "learning_rate": 0.00018544194045464886, | |
| "loss": 7.4008, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 13.775851829485163, | |
| "learning_rate": 0.00018441187494686053, | |
| "loss": 7.2854, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 16.44073199273777, | |
| "learning_rate": 0.0001833496700394202, | |
| "loss": 7.4218, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 21.66328419423237, | |
| "learning_rate": 0.00018225573016153945, | |
| "loss": 7.3589, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 14.027278482513156, | |
| "learning_rate": 0.00018113047182536127, | |
| "loss": 7.3329, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 7.374873161315918, | |
| "eval_runtime": 1.3815, | |
| "eval_samples_per_second": 13.753, | |
| "eval_steps_per_second": 3.619, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 10.89412121909016, | |
| "learning_rate": 0.00017997432346737524, | |
| "loss": 7.3277, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 18.182727305484867, | |
| "learning_rate": 0.00017878772528529232, | |
| "loss": 7.3505, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 18.738647279231998, | |
| "learning_rate": 0.000177571129070442, | |
| "loss": 7.4395, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 8.544634593385059, | |
| "learning_rate": 0.00017632499803575474, | |
| "loss": 7.3132, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 23.787945119488832, | |
| "learning_rate": 0.00017504980663939613, | |
| "loss": 7.3635, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 15.988837162794528, | |
| "learning_rate": 0.00017374604040411935, | |
| "loss": 7.298, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 8.594141503866256, | |
| "learning_rate": 0.00017241419573240462, | |
| "loss": 7.2263, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 10.834111660116264, | |
| "learning_rate": 0.00017105477971745666, | |
| "loss": 7.2234, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 20.898663112099943, | |
| "learning_rate": 0.00016966830995013133, | |
| "loss": 7.4312, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 9.882602517532073, | |
| "learning_rate": 0.00016825531432186543, | |
| "loss": 7.3389, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 7.435249821686469, | |
| "learning_rate": 0.00016681633082368498, | |
| "loss": 7.2015, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 13.215068331486576, | |
| "learning_rate": 0.0001653519073413675, | |
| "loss": 7.1425, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 11.754841557793458, | |
| "learning_rate": 0.00016386260144683745, | |
| "loss": 7.3101, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 7.674786980372276, | |
| "learning_rate": 0.00016234898018587337, | |
| "loss": 7.1703, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 8.30389279917059, | |
| "learning_rate": 0.00016081161986220807, | |
| "loss": 7.2516, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 14.325137493545546, | |
| "learning_rate": 0.00015925110581810394, | |
| "loss": 7.3326, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 9.943124774719692, | |
| "learning_rate": 0.00015766803221148673, | |
| "loss": 7.5501, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 11.710815673357324, | |
| "learning_rate": 0.00015606300178972287, | |
| "loss": 7.3344, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 8.287278539768234, | |
| "learning_rate": 0.00015443662566012645, | |
| "loss": 7.2426, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 8.045767995001754, | |
| "learning_rate": 0.00015278952305728324, | |
| "loss": 7.2319, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 16.213767636990735, | |
| "learning_rate": 0.00015112232110728015, | |
| "loss": 7.2226, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 10.115986520778595, | |
| "learning_rate": 0.00014943565458893, | |
| "loss": 7.0671, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 7.336472511291504, | |
| "eval_runtime": 1.3763, | |
| "eval_samples_per_second": 13.806, | |
| "eval_steps_per_second": 3.633, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 7.370162670560762, | |
| "learning_rate": 0.00014773016569208283, | |
| "loss": 7.2456, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 14.854609514494987, | |
| "learning_rate": 0.00014600650377311522, | |
| "loss": 7.0447, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 9.984605765623492, | |
| "learning_rate": 0.0001442653251076912, | |
| "loss": 7.1948, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 11.053561117527067, | |
| "learning_rate": 0.00014250729264088843, | |
| "loss": 7.1485, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 11.604464862126479, | |
| "learning_rate": 0.00014073307573478526, | |
| "loss": 7.4198, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 8.62267592810566, | |
| "learning_rate": 0.00013894334991360448, | |
| "loss": 7.3045, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 10.961255591651343, | |
| "learning_rate": 0.00013713879660651068, | |
| "loss": 6.9983, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 11.12104950103157, | |
| "learning_rate": 0.0001353201028881598, | |
| "loss": 7.1046, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 8.807345567053673, | |
| "learning_rate": 0.00013348796121709862, | |
| "loss": 7.3378, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 10.666053356976384, | |
| "learning_rate": 0.00013164306917211476, | |
| "loss": 7.0008, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 7.835224761952429, | |
| "learning_rate": 0.000129786129186637, | |
| "loss": 6.9881, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 19.4062633667929, | |
| "learning_rate": 0.00012791784828128724, | |
| "loss": 7.2579, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 10.113263144537674, | |
| "learning_rate": 0.00012603893779468604, | |
| "loss": 7.3091, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 10.870503515462726, | |
| "learning_rate": 0.0001241501131126138, | |
| "loss": 7.4527, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 8.533887294828766, | |
| "learning_rate": 0.00012225209339563145, | |
| "loss": 7.2855, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 13.486746604884923, | |
| "learning_rate": 0.0001203456013052634, | |
| "loss": 7.2705, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 10.69251762526038, | |
| "learning_rate": 0.00011843136272884794, | |
| "loss": 7.0932, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 9.124923914761991, | |
| "learning_rate": 0.00011651010650315923, | |
| "loss": 7.3754, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 13.481473855966252, | |
| "learning_rate": 0.00011458256413690633, | |
| "loss": 7.3104, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 13.187202052506544, | |
| "learning_rate": 0.00011264946953221496, | |
| "loss": 7.3614, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 13.527193725705766, | |
| "learning_rate": 0.00011071155870519777, | |
| "loss": 7.2734, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "grad_norm": 8.023369511183457, | |
| "learning_rate": 0.00010876956950572006, | |
| "loss": 7.4786, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 7.319369316101074, | |
| "eval_runtime": 1.3976, | |
| "eval_samples_per_second": 13.595, | |
| "eval_steps_per_second": 3.578, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 11.41077205951204, | |
| "learning_rate": 0.0001068242413364671, | |
| "loss": 7.2116, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "grad_norm": 9.551865991569315, | |
| "learning_rate": 0.00010487631487142017, | |
| "loss": 7.2411, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 11.576046488111642, | |
| "learning_rate": 0.00010292653177384876, | |
| "loss": 7.4401, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "grad_norm": 9.356673167513755, | |
| "learning_rate": 0.00010097563441392581, | |
| "loss": 7.3184, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 12.119641565241189, | |
| "learning_rate": 9.90243655860742e-05, | |
| "loss": 7.2285, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 11.06643382673938, | |
| "learning_rate": 9.707346822615128e-05, | |
| "loss": 7.1729, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 9.198991504624212, | |
| "learning_rate": 9.512368512857984e-05, | |
| "loss": 7.2619, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "grad_norm": 14.240944645441582, | |
| "learning_rate": 9.317575866353292e-05, | |
| "loss": 7.5778, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "grad_norm": 8.473455381717486, | |
| "learning_rate": 9.123043049427995e-05, | |
| "loss": 7.2432, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 12.027303786674432, | |
| "learning_rate": 8.928844129480227e-05, | |
| "loss": 7.4036, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "grad_norm": 10.45148339945213, | |
| "learning_rate": 8.735053046778506e-05, | |
| "loss": 7.2052, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 12.816375890508084, | |
| "learning_rate": 8.541743586309365e-05, | |
| "loss": 7.1882, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "grad_norm": 12.872264386256504, | |
| "learning_rate": 8.348989349684076e-05, | |
| "loss": 7.1129, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "grad_norm": 8.712185045895534, | |
| "learning_rate": 8.156863727115211e-05, | |
| "loss": 7.3354, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "grad_norm": 7.169962044034168, | |
| "learning_rate": 7.965439869473664e-05, | |
| "loss": 7.1493, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 9.20643667535514, | |
| "learning_rate": 7.774790660436858e-05, | |
| "loss": 7.1867, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 9.71231661001151, | |
| "learning_rate": 7.584988688738622e-05, | |
| "loss": 7.1941, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "grad_norm": 9.869652181292283, | |
| "learning_rate": 7.396106220531398e-05, | |
| "loss": 7.2606, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "grad_norm": 7.820315914553451, | |
| "learning_rate": 7.208215171871277e-05, | |
| "loss": 7.1575, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 8.668852408202328, | |
| "learning_rate": 7.021387081336301e-05, | |
| "loss": 7.3339, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "grad_norm": 6.97843034949997, | |
| "learning_rate": 6.835693082788525e-05, | |
| "loss": 7.307, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "grad_norm": 16.571225038227503, | |
| "learning_rate": 6.651203878290139e-05, | |
| "loss": 7.3548, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_loss": 7.309223175048828, | |
| "eval_runtime": 1.3716, | |
| "eval_samples_per_second": 13.852, | |
| "eval_steps_per_second": 3.645, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "grad_norm": 14.645439276497052, | |
| "learning_rate": 6.46798971118402e-05, | |
| "loss": 7.1198, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 11.180148474401758, | |
| "learning_rate": 6.286120339348935e-05, | |
| "loss": 7.383, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 8.297433608048966, | |
| "learning_rate": 6.105665008639557e-05, | |
| "loss": 7.0708, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "grad_norm": 7.35350265603106, | |
| "learning_rate": 5.926692426521474e-05, | |
| "loss": 7.2686, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "grad_norm": 10.931447125375616, | |
| "learning_rate": 5.749270735911158e-05, | |
| "loss": 7.0715, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "grad_norm": 12.580996736421003, | |
| "learning_rate": 5.573467489230879e-05, | |
| "loss": 7.3576, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "grad_norm": 12.648533406639174, | |
| "learning_rate": 5.399349622688479e-05, | |
| "loss": 7.3546, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "grad_norm": 8.448979459452485, | |
| "learning_rate": 5.226983430791722e-05, | |
| "loss": 7.0968, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 14.75106031841705, | |
| "learning_rate": 5.0564345411070025e-05, | |
| "loss": 7.2726, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "grad_norm": 7.623885276483663, | |
| "learning_rate": 4.8877678892719866e-05, | |
| "loss": 7.2646, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "grad_norm": 11.112819218207525, | |
| "learning_rate": 4.721047694271676e-05, | |
| "loss": 7.1452, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "grad_norm": 15.00591466641024, | |
| "learning_rate": 4.556337433987359e-05, | |
| "loss": 6.9634, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "grad_norm": 9.000881151933429, | |
| "learning_rate": 4.393699821027716e-05, | |
| "loss": 7.2109, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "grad_norm": 8.677018023760695, | |
| "learning_rate": 4.2331967788513295e-05, | |
| "loss": 7.1976, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "grad_norm": 7.021254016561991, | |
| "learning_rate": 4.074889418189608e-05, | |
| "loss": 7.2308, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 14.097624320239541, | |
| "learning_rate": 3.9188380137791936e-05, | |
| "loss": 7.2678, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "grad_norm": 7.660009091922155, | |
| "learning_rate": 3.7651019814126654e-05, | |
| "loss": 7.2609, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "grad_norm": 6.879429170747529, | |
| "learning_rate": 3.613739855316257e-05, | |
| "loss": 7.1545, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "grad_norm": 9.342549224552343, | |
| "learning_rate": 3.46480926586325e-05, | |
| "loss": 7.122, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "grad_norm": 9.584840694689616, | |
| "learning_rate": 3.3183669176315045e-05, | |
| "loss": 7.2049, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "grad_norm": 14.37215919620074, | |
| "learning_rate": 3.174468567813461e-05, | |
| "loss": 7.4374, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "grad_norm": 6.257502820833114, | |
| "learning_rate": 3.033169004986873e-05, | |
| "loss": 7.1782, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "eval_loss": 7.296360492706299, | |
| "eval_runtime": 1.3751, | |
| "eval_samples_per_second": 13.818, | |
| "eval_steps_per_second": 3.636, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "grad_norm": 7.202404193022492, | |
| "learning_rate": 2.894522028254334e-05, | |
| "loss": 7.1248, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "grad_norm": 11.03004064225623, | |
| "learning_rate": 2.7585804267595384e-05, | |
| "loss": 7.4726, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "grad_norm": 10.208828744090669, | |
| "learning_rate": 2.6253959595880673e-05, | |
| "loss": 7.1886, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "grad_norm": 7.194649499092706, | |
| "learning_rate": 2.495019336060387e-05, | |
| "loss": 7.2576, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "grad_norm": 15.063508439238962, | |
| "learning_rate": 2.367500196424529e-05, | |
| "loss": 6.924, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "grad_norm": 9.528135297299904, | |
| "learning_rate": 2.242887092955801e-05, | |
| "loss": 7.1941, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "grad_norm": 7.719290154588222, | |
| "learning_rate": 2.121227471470768e-05, | |
| "loss": 7.3391, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 7.714834107984481, | |
| "learning_rate": 2.002567653262479e-05, | |
| "loss": 7.1969, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "grad_norm": 8.228923346547797, | |
| "learning_rate": 1.8869528174638752e-05, | |
| "loss": 7.1543, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "grad_norm": 6.001756411009184, | |
| "learning_rate": 1.774426983846058e-05, | |
| "loss": 7.2465, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "grad_norm": 10.434576481704424, | |
| "learning_rate": 1.6650329960579792e-05, | |
| "loss": 7.2623, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "grad_norm": 8.095148267701724, | |
| "learning_rate": 1.5588125053139468e-05, | |
| "loss": 7.1761, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "grad_norm": 9.145578669056132, | |
| "learning_rate": 1.4558059545351143e-05, | |
| "loss": 7.1295, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "grad_norm": 7.413949304325555, | |
| "learning_rate": 1.3560525629510568e-05, | |
| "loss": 7.1572, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 8.238266895583749, | |
| "learning_rate": 1.259590311167238e-05, | |
| "loss": 7.2317, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "grad_norm": 7.150286325977236, | |
| "learning_rate": 1.166455926704082e-05, | |
| "loss": 7.3381, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "grad_norm": 10.918607427652104, | |
| "learning_rate": 1.0766848700131648e-05, | |
| "loss": 7.3925, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "grad_norm": 6.6969446531973285, | |
| "learning_rate": 9.903113209758096e-06, | |
| "loss": 7.2799, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "grad_norm": 13.477825461653845, | |
| "learning_rate": 9.073681658892775e-06, | |
| "loss": 6.901, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "grad_norm": 6.783585528560174, | |
| "learning_rate": 8.278869849454718e-06, | |
| "loss": 7.2819, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "grad_norm": 9.548057270672551, | |
| "learning_rate": 7.5189804020693536e-06, | |
| "loss": 7.1192, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "grad_norm": 7.742180355619181, | |
| "learning_rate": 6.794302640847294e-06, | |
| "loss": 7.2729, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_loss": 7.292217254638672, | |
| "eval_runtime": 1.3839, | |
| "eval_samples_per_second": 13.729, | |
| "eval_steps_per_second": 3.613, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "grad_norm": 10.845656873156827, | |
| "learning_rate": 6.1051124832254944e-06, | |
| "loss": 6.9693, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "grad_norm": 10.323147542445835, | |
| "learning_rate": 5.451672334913216e-06, | |
| "loss": 7.3785, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "grad_norm": 10.41796325752105, | |
| "learning_rate": 4.834230989982213e-06, | |
| "loss": 7.3632, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "grad_norm": 6.590462249149956, | |
| "learning_rate": 4.253023536139733e-06, | |
| "loss": 7.279, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "grad_norm": 9.637387713657647, | |
| "learning_rate": 3.7082712652200867e-06, | |
| "loss": 7.2857, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "grad_norm": 5.983998578137723, | |
| "learning_rate": 3.2001815889286856e-06, | |
| "loss": 7.2269, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 6.750577266168699, | |
| "learning_rate": 2.728947959871353e-06, | |
| "loss": 7.2672, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "grad_norm": 8.828265865856226, | |
| "learning_rate": 2.294749797897955e-06, | |
| "loss": 7.1355, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "grad_norm": 8.092540989425222, | |
| "learning_rate": 1.8977524217893783e-06, | |
| "loss": 7.079, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "grad_norm": 14.298932570519032, | |
| "learning_rate": 1.5381069863131037e-06, | |
| "loss": 7.1462, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "grad_norm": 6.9722905081773465, | |
| "learning_rate": 1.2159504246718522e-06, | |
| "loss": 7.1766, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "grad_norm": 8.429744971276516, | |
| "learning_rate": 9.314053963669245e-07, | |
| "loss": 7.3844, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "grad_norm": 7.0927677230675386, | |
| "learning_rate": 6.845802404962243e-07, | |
| "loss": 7.3318, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "grad_norm": 6.6033524293092265, | |
| "learning_rate": 4.7556893450466653e-07, | |
| "loss": 7.1159, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "grad_norm": 9.59870072155561, | |
| "learning_rate": 3.044510584027771e-07, | |
| "loss": 7.3733, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "grad_norm": 7.255692976305313, | |
| "learning_rate": 1.7129176446692984e-07, | |
| "loss": 7.2345, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "grad_norm": 7.239401601436061, | |
| "learning_rate": 7.614175243301213e-08, | |
| "loss": 7.2672, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "grad_norm": 6.342843427851908, | |
| "learning_rate": 1.9037250192732726e-08, | |
| "loss": 7.2741, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "grad_norm": 8.76817744282957, | |
| "learning_rate": 0.0, | |
| "loss": 7.2543, | |
| "step": 261 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 261, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 87, | |
| "total_flos": 1.8244065215014502e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |