| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9989382410192886, | |
| "eval_steps": 20, | |
| "global_step": 706, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 3.9795, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 3.2944, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.2e-05, | |
| "loss": 4.0746, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 4.1905, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2e-05, | |
| "loss": 4.4667, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.4e-05, | |
| "loss": 4.8488, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 4.1473, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 3.7834, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.6e-05, | |
| "loss": 3.2778, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4e-05, | |
| "loss": 3.1975, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 2.7504, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.8e-05, | |
| "loss": 2.5047, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 2.3366, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 2.1348, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6171, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 1.2901, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 1.1358, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.9456, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 7.6e-05, | |
| "loss": 0.8864, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8756, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.7110548615455627, | |
| "eval_runtime": 29.5129, | |
| "eval_samples_per_second": 55.196, | |
| "eval_steps_per_second": 55.196, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.8825, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.822, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 0.8001, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.8978, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8214, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00010400000000000001, | |
| "loss": 0.8012, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00010800000000000001, | |
| "loss": 0.9169, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00011200000000000001, | |
| "loss": 0.8436, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.000116, | |
| "loss": 0.738, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00012, | |
| "loss": 0.8238, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.000124, | |
| "loss": 0.85, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00012800000000000002, | |
| "loss": 0.8292, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.000132, | |
| "loss": 0.8739, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00013600000000000003, | |
| "loss": 0.8456, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00014, | |
| "loss": 0.7558, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.000144, | |
| "loss": 0.6982, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.000148, | |
| "loss": 0.7985, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.000152, | |
| "loss": 0.7995, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00015600000000000002, | |
| "loss": 0.5988, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00016, | |
| "loss": 0.9058, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 0.6764179468154907, | |
| "eval_runtime": 29.6679, | |
| "eval_samples_per_second": 54.908, | |
| "eval_steps_per_second": 54.908, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.000164, | |
| "loss": 0.8351, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.000168, | |
| "loss": 0.8182, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.000172, | |
| "loss": 0.8694, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00017600000000000002, | |
| "loss": 0.7743, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018, | |
| "loss": 0.7448, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00018400000000000003, | |
| "loss": 0.8416, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.000188, | |
| "loss": 0.7496, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.000192, | |
| "loss": 0.7353, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.000196, | |
| "loss": 0.9026, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8415, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00020400000000000003, | |
| "loss": 0.7606, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00020800000000000001, | |
| "loss": 0.743, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00021200000000000003, | |
| "loss": 0.7478, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00021600000000000002, | |
| "loss": 0.6924, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00022000000000000003, | |
| "loss": 0.9163, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00022400000000000002, | |
| "loss": 0.7332, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00022799999999999999, | |
| "loss": 0.7678, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.000232, | |
| "loss": 0.7561, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.000236, | |
| "loss": 0.8494, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00024, | |
| "loss": 0.7526, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 0.6668684482574463, | |
| "eval_runtime": 29.5308, | |
| "eval_samples_per_second": 55.163, | |
| "eval_steps_per_second": 55.163, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.000244, | |
| "loss": 0.7944, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.000248, | |
| "loss": 0.7107, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.000252, | |
| "loss": 0.7443, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00025600000000000004, | |
| "loss": 0.7802, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00026000000000000003, | |
| "loss": 0.6785, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.000264, | |
| "loss": 0.7853, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.000268, | |
| "loss": 0.8059, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00027200000000000005, | |
| "loss": 0.6702, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.000276, | |
| "loss": 0.7784, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00028, | |
| "loss": 0.7447, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.000284, | |
| "loss": 0.6466, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.000288, | |
| "loss": 0.6549, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.000292, | |
| "loss": 0.6841, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.000296, | |
| "loss": 0.6441, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00030000000000000003, | |
| "loss": 0.6777, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.000304, | |
| "loss": 0.7301, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.000308, | |
| "loss": 0.692, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00031200000000000005, | |
| "loss": 0.7697, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00031600000000000004, | |
| "loss": 0.6374, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00032, | |
| "loss": 0.6926, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 0.6363404989242554, | |
| "eval_runtime": 29.5123, | |
| "eval_samples_per_second": 55.197, | |
| "eval_steps_per_second": 55.197, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.000324, | |
| "loss": 0.7258, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.000328, | |
| "loss": 0.6556, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.000332, | |
| "loss": 0.6122, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.000336, | |
| "loss": 0.6915, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00034, | |
| "loss": 0.7711, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.000344, | |
| "loss": 0.6637, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.000348, | |
| "loss": 0.635, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00035200000000000005, | |
| "loss": 0.648, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00035600000000000003, | |
| "loss": 0.6904, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00036, | |
| "loss": 0.7026, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.000364, | |
| "loss": 0.6285, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00036800000000000005, | |
| "loss": 0.6239, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00037200000000000004, | |
| "loss": 0.6897, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.000376, | |
| "loss": 0.6162, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00038, | |
| "loss": 0.6414, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.000384, | |
| "loss": 0.637, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.000388, | |
| "loss": 0.7453, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.000392, | |
| "loss": 0.6462, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00039600000000000003, | |
| "loss": 0.6717, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0004, | |
| "loss": 0.6731, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 0.6186901926994324, | |
| "eval_runtime": 29.5468, | |
| "eval_samples_per_second": 55.133, | |
| "eval_steps_per_second": 55.133, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00039999731246874025, | |
| "loss": 0.6801, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0003999892499471893, | |
| "loss": 0.6285, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00039997581265202993, | |
| "loss": 0.6436, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0003999570009443936, | |
| "loss": 0.7124, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00039993281532985087, | |
| "loss": 0.6157, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00039990325645839766, | |
| "loss": 0.6532, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0003998683251244379, | |
| "loss": 0.6072, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0003998280222667621, | |
| "loss": 0.6871, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00039978234896852216, | |
| "loss": 0.6139, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0003997313064572023, | |
| "loss": 0.7056, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0003996748961045859, | |
| "loss": 0.5983, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0003996131194267189, | |
| "loss": 0.5374, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00039954597808386874, | |
| "loss": 0.6804, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00039947347388048, | |
| "loss": 0.6254, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00039939560876512585, | |
| "loss": 0.7221, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0003993123848304556, | |
| "loss": 0.6417, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0003992238043131386, | |
| "loss": 0.4836, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0003991298695938038, | |
| "loss": 0.6186, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0003990305831969761, | |
| "loss": 0.6362, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00039892594779100866, | |
| "loss": 0.647, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 0.6162068843841553, | |
| "eval_runtime": 29.5244, | |
| "eval_samples_per_second": 55.175, | |
| "eval_steps_per_second": 55.175, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0003988159661880105, | |
| "loss": 0.5818, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0003987006413437718, | |
| "loss": 0.6267, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00039857997635768365, | |
| "loss": 0.5502, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00039845397447265535, | |
| "loss": 0.6438, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00039832263907502684, | |
| "loss": 0.6472, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0003981859736944781, | |
| "loss": 0.6834, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00039804398200393395, | |
| "loss": 0.6091, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0003978966678194653, | |
| "loss": 0.58, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00039774403510018714, | |
| "loss": 0.5988, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0003975860879481514, | |
| "loss": 0.6177, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00039742283060823706, | |
| "loss": 0.5535, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0003972542674680364, | |
| "loss": 0.7208, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0003970804030577363, | |
| "loss": 0.626, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0003969012420499972, | |
| "loss": 0.5747, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00039671678925982723, | |
| "loss": 0.5567, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00039652704964445275, | |
| "loss": 0.6814, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00039633202830318526, | |
| "loss": 0.5917, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0003961317304772842, | |
| "loss": 0.5793, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00039592616154981633, | |
| "loss": 0.6533, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00039571532704551083, | |
| "loss": 0.6219, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 0.6040534377098083, | |
| "eval_runtime": 29.5629, | |
| "eval_samples_per_second": 55.103, | |
| "eval_steps_per_second": 55.103, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0003954992326306109, | |
| "loss": 0.5167, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00039527788411272143, | |
| "loss": 0.6516, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00039505128744065314, | |
| "loss": 0.607, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0003948194487042623, | |
| "loss": 0.6482, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0003945823741342875, | |
| "loss": 0.6133, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0003943400701021819, | |
| "loss": 0.5582, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00039409254311994216, | |
| "loss": 0.5985, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00039383979983993327, | |
| "loss": 0.5648, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0003935818470547098, | |
| "loss": 0.5884, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00039331869169683363, | |
| "loss": 0.5948, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0003930503408386871, | |
| "loss": 0.5532, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00039277680169228364, | |
| "loss": 0.6034, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0003924980816090731, | |
| "loss": 0.6522, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0003922141880797449, | |
| "loss": 0.6142, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0003919251287340265, | |
| "loss": 0.5816, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.000391630911340478, | |
| "loss": 0.5686, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00039133154380628394, | |
| "loss": 0.6053, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0003910270341770404, | |
| "loss": 0.7025, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00039071739063653875, | |
| "loss": 0.5625, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00039040262150654597, | |
| "loss": 0.5781, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 0.593679666519165, | |
| "eval_runtime": 29.5229, | |
| "eval_samples_per_second": 55.178, | |
| "eval_steps_per_second": 55.178, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00039008273524658094, | |
| "loss": 0.603, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0003897577404536867, | |
| "loss": 0.5789, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00038942764586220006, | |
| "loss": 0.6881, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00038909246034351624, | |
| "loss": 0.6034, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00038875219290585093, | |
| "loss": 0.5881, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0003884068526939978, | |
| "loss": 0.6318, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00038805644898908307, | |
| "loss": 0.5383, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0003877009912083159, | |
| "loss": 0.5284, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00038734048890473507, | |
| "loss": 0.5723, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00038697495176695274, | |
| "loss": 0.6311, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00038660438961889387, | |
| "loss": 0.6043, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00038622881241953195, | |
| "loss": 0.5023, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0003858482302626216, | |
| "loss": 0.566, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0003854626533764273, | |
| "loss": 0.5677, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00038507209212344833, | |
| "loss": 0.6342, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00038467655700014054, | |
| "loss": 0.6095, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0003842760586366339, | |
| "loss": 0.6715, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00038387060779644725, | |
| "loss": 0.5173, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00038346021537619866, | |
| "loss": 0.6155, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0003830448924053126, | |
| "loss": 0.6346, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.6006138324737549, | |
| "eval_runtime": 29.5105, | |
| "eval_samples_per_second": 55.201, | |
| "eval_steps_per_second": 55.201, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00038262465004572377, | |
| "loss": 0.7549, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.000382199499591577, | |
| "loss": 0.5214, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00038176945246892367, | |
| "loss": 0.5625, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0003813345202354145, | |
| "loss": 0.5267, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0003808947145799894, | |
| "loss": 0.6413, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0003804500473225627, | |
| "loss": 0.4987, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00038000053041370603, | |
| "loss": 0.6235, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0003795461759343268, | |
| "loss": 0.5331, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0003790869960953437, | |
| "loss": 0.6096, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0003786230032373583, | |
| "loss": 0.5872, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00037815420983032397, | |
| "loss": 0.6665, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0003776806284732098, | |
| "loss": 0.7373, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00037720227189366295, | |
| "loss": 0.5193, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00037671915294766606, | |
| "loss": 0.5335, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00037623128461919175, | |
| "loss": 0.5148, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00037573868001985377, | |
| "loss": 0.5961, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0003752413523885549, | |
| "loss": 0.5421, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00037473931509113056, | |
| "loss": 0.6177, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0003742325816199901, | |
| "loss": 0.6656, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00037372116559375397, | |
| "loss": 0.7663, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 0.5926464200019836, | |
| "eval_runtime": 29.5066, | |
| "eval_samples_per_second": 55.208, | |
| "eval_steps_per_second": 55.208, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00037320508075688776, | |
| "loss": 0.6667, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00037268434097933274, | |
| "loss": 0.587, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0003721589602561332, | |
| "loss": 0.5747, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0003716289527070604, | |
| "loss": 0.557, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0003710943325762328, | |
| "loss": 0.5724, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00037055511423173356, | |
| "loss": 0.6036, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0003700113121652243, | |
| "loss": 0.6007, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0003694629409915555, | |
| "loss": 0.6895, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00036891001544837393, | |
| "loss": 0.6642, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0003683525503957263, | |
| "loss": 0.7124, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00036779056081566024, | |
| "loss": 0.52, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00036722406181182143, | |
| "loss": 0.6133, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0003666530686090475, | |
| "loss": 0.5487, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0003660775965529595, | |
| "loss": 0.5686, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0003654976611095487, | |
| "loss": 0.4951, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0003649132778647615, | |
| "loss": 0.5794, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00036432446252408014, | |
| "loss": 0.4965, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0003637312309121011, | |
| "loss": 0.6146, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00036313359897210935, | |
| "loss": 0.5697, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00036253158276565006, | |
| "loss": 0.5864, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 0.5865967273712158, | |
| "eval_runtime": 29.5042, | |
| "eval_samples_per_second": 55.212, | |
| "eval_steps_per_second": 55.212, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.000361925198472097, | |
| "loss": 0.4863, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00036131446238821767, | |
| "loss": 0.5185, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00036069939092773514, | |
| "loss": 0.5846, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0003600800006208872, | |
| "loss": 0.5416, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00035945630811398205, | |
| "loss": 0.5783, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0003588283301689507, | |
| "loss": 0.7388, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0003581960836628968, | |
| "loss": 0.7164, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0003575595855876427, | |
| "loss": 0.5729, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0003569188530492732, | |
| "loss": 0.5475, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0003562739032676756, | |
| "loss": 0.6107, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00035562475357607694, | |
| "loss": 0.5441, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.000354971421420578, | |
| "loss": 0.6148, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0003543139243596847, | |
| "loss": 0.5864, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00035365228006383614, | |
| "loss": 0.5044, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00035298650631492956, | |
| "loss": 0.4947, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0003523166210058426, | |
| "loss": 0.5524, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0003516426421399523, | |
| "loss": 0.5434, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00035096458783065145, | |
| "loss": 0.6695, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0003502824763008615, | |
| "loss": 0.6813, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00034959632588254304, | |
| "loss": 0.5943, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.5755711793899536, | |
| "eval_runtime": 29.5, | |
| "eval_samples_per_second": 55.22, | |
| "eval_steps_per_second": 55.22, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.000348906155016203, | |
| "loss": 0.5239, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0003482119822503994, | |
| "loss": 0.5347, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.000347513826241242, | |
| "loss": 0.5513, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0003468117057518921, | |
| "loss": 0.6988, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.000346105639652057, | |
| "loss": 0.5591, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00034539564691748407, | |
| "loss": 0.5305, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00034468174662944995, | |
| "loss": 0.5492, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0003439639579742481, | |
| "loss": 0.5907, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00034324230024267285, | |
| "loss": 0.5596, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00034251679282950144, | |
| "loss": 0.6163, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00034178745523297233, | |
| "loss": 0.7016, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0003410543070542615, | |
| "loss": 0.734, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00034031736799695537, | |
| "loss": 0.6601, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0003395766578665215, | |
| "loss": 0.5738, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00033883219656977615, | |
| "loss": 0.5691, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0003380840041143494, | |
| "loss": 0.4958, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0003373321006081474, | |
| "loss": 0.4613, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00033657650625881183, | |
| "loss": 0.5939, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0003358172413731772, | |
| "loss": 0.6093, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00033505432635672457, | |
| "loss": 0.5029, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 0.5733422040939331, | |
| "eval_runtime": 29.5698, | |
| "eval_samples_per_second": 55.09, | |
| "eval_steps_per_second": 55.09, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0003342877817130334, | |
| "loss": 0.6983, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.00033351762804323073, | |
| "loss": 0.5567, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0003327438860454372, | |
| "loss": 0.5081, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00033196657651421066, | |
| "loss": 0.5475, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.000331185720339988, | |
| "loss": 0.5527, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0003304013385085229, | |
| "loss": 0.5244, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0003296134521003222, | |
| "loss": 0.6156, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0003288220822900796, | |
| "loss": 0.5203, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00032802725034610593, | |
| "loss": 0.5844, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0003272289776297583, | |
| "loss": 0.6262, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0003264272855948653, | |
| "loss": 0.552, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0003256221957871512, | |
| "loss": 0.5817, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0003248137298436561, | |
| "loss": 0.4906, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00032400190949215507, | |
| "loss": 0.4638, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0003231867565505737, | |
| "loss": 0.532, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0003223682929264022, | |
| "loss": 0.572, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0003215465406161064, | |
| "loss": 0.6238, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0003207215217045363, | |
| "loss": 0.5751, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0003198932583643332, | |
| "loss": 0.5688, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0003190617728553332, | |
| "loss": 0.5482, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 0.5711647272109985, | |
| "eval_runtime": 29.618, | |
| "eval_samples_per_second": 55.0, | |
| "eval_steps_per_second": 55.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0003182270875239694, | |
| "loss": 0.6118, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0003173892248026708, | |
| "loss": 0.5704, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0003165482072092602, | |
| "loss": 0.6117, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00031570405734634814, | |
| "loss": 0.5798, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0003148567979007261, | |
| "loss": 0.5585, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00031400645164275653, | |
| "loss": 0.6552, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.000313153041425761, | |
| "loss": 0.5421, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0003122965901854058, | |
| "loss": 0.497, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0003114371209390857, | |
| "loss": 0.5207, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00031057465678530543, | |
| "loss": 0.5028, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0003097092209030588, | |
| "loss": 0.4905, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0003088408365512055, | |
| "loss": 0.6156, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00030796952706784646, | |
| "loss": 0.5414, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0003070953158696967, | |
| "loss": 0.4219, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00030621822645145506, | |
| "loss": 0.6778, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.000305338282385174, | |
| "loss": 0.5173, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00030445550731962546, | |
| "loss": 0.5959, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0003035699249796651, | |
| "loss": 0.6535, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0003026815591655953, | |
| "loss": 0.6306, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00030179043375252486, | |
| "loss": 0.5413, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 0.5820406675338745, | |
| "eval_runtime": 29.5338, | |
| "eval_samples_per_second": 55.157, | |
| "eval_steps_per_second": 55.157, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.000300896572689728, | |
| "loss": 0.5046, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00030000000000000003, | |
| "loss": 0.6131, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00029910073977901236, | |
| "loss": 0.4598, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00029819881619466443, | |
| "loss": 0.5017, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00029729425348643467, | |
| "loss": 0.6571, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00029638707596472855, | |
| "loss": 0.577, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00029547730801022544, | |
| "loss": 0.5014, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00029456497407322365, | |
| "loss": 0.4571, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0002936500986729829, | |
| "loss": 0.5818, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0002927327063970655, | |
| "loss": 0.5138, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00029181282190067574, | |
| "loss": 0.5927, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00029089046990599685, | |
| "loss": 0.5297, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0002899656752015272, | |
| "loss": 0.5693, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0002890384626414134, | |
| "loss": 0.5579, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.000288108857144783, | |
| "loss": 0.6165, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00028717688369507425, | |
| "loss": 0.4311, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00028624256733936486, | |
| "loss": 0.5919, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0002853059331876991, | |
| "loss": 0.6499, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0002843670064124125, | |
| "loss": 0.5486, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0002834258122474556, | |
| "loss": 0.657, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 0.5696084499359131, | |
| "eval_runtime": 29.5183, | |
| "eval_samples_per_second": 55.186, | |
| "eval_steps_per_second": 55.186, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0002824823759877159, | |
| "loss": 0.6218, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00028153672298833775, | |
| "loss": 0.4651, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0002805888786640412, | |
| "loss": 0.5388, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00027963886848843863, | |
| "loss": 0.4579, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00027868671799335053, | |
| "loss": 0.6092, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00027773245276811905, | |
| "loss": 0.711, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00027677609845892055, | |
| "loss": 0.6601, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002758176807680759, | |
| "loss": 0.4271, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00027485722545336023, | |
| "loss": 0.5561, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00027389475832731035, | |
| "loss": 0.4772, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00027293030525653105, | |
| "loss": 0.56, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0002719638921610002, | |
| "loss": 0.5905, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0002709955450133718, | |
| "loss": 0.4981, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0002700252898382781, | |
| "loss": 0.5701, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0002690531527116304, | |
| "loss": 0.4725, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.00026807915975991765, | |
| "loss": 0.5022, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.000267103337159505, | |
| "loss": 0.4953, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002661257111359299, | |
| "loss": 0.5762, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.0002651463079631973, | |
| "loss": 0.6713, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00026416515396307353, | |
| "loss": 0.506, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.5838707685470581, | |
| "eval_runtime": 29.495, | |
| "eval_samples_per_second": 55.23, | |
| "eval_steps_per_second": 55.23, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0002631822755043793, | |
| "loss": 0.5368, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00026219769900228014, | |
| "loss": 0.5509, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0002612114509175775, | |
| "loss": 0.5365, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0002602235577559969, | |
| "loss": 0.6527, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0002592340460674759, | |
| "loss": 0.4975, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00025824294244545045, | |
| "loss": 0.6552, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.00025725027352614015, | |
| "loss": 0.5523, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00025625606598783256, | |
| "loss": 0.6078, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002552603465501661, | |
| "loss": 0.4592, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0002542631419734118, | |
| "loss": 0.587, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00025326447905775446, | |
| "loss": 0.5689, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00025226438464257217, | |
| "loss": 0.4961, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00025126288560571483, | |
| "loss": 0.4735, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00025026000886278223, | |
| "loss": 0.5387, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00024925578136640033, | |
| "loss": 0.5427, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0002482502301054969, | |
| "loss": 0.5362, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0002472433821045765, | |
| "loss": 0.5619, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.000246235264422994, | |
| "loss": 0.4473, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0002452259041542269, | |
| "loss": 0.4934, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0002442153284251484, | |
| "loss": 0.4804, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 0.5803248882293701, | |
| "eval_runtime": 29.5222, | |
| "eval_samples_per_second": 55.179, | |
| "eval_steps_per_second": 55.179, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00024320356439529674, | |
| "loss": 0.5928, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00024219063925614664, | |
| "loss": 0.5542, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00024117658023037791, | |
| "loss": 0.4748, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0002401614145711437, | |
| "loss": 0.4946, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.00023914516956133862, | |
| "loss": 0.4455, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0002381278725128649, | |
| "loss": 0.4165, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0002371095507658987, | |
| "loss": 0.4976, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00023609023168815526, | |
| "loss": 0.4858, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00023506994267415358, | |
| "loss": 0.5761, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00023404871114447975, | |
| "loss": 0.46, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00023302656454505033, | |
| "loss": 0.3988, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00023200353034637483, | |
| "loss": 0.6341, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00023097963604281697, | |
| "loss": 0.4849, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00022995490915185633, | |
| "loss": 0.4287, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00022892937721334842, | |
| "loss": 0.3591, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 0.00022790306778878465, | |
| "loss": 0.454, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00022687600846055164, | |
| "loss": 0.4785, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002258482268311898, | |
| "loss": 0.4696, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.00022481975052265188, | |
| "loss": 0.4635, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0002237906071755601, | |
| "loss": 0.5095, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "eval_loss": 0.5974432229995728, | |
| "eval_runtime": 29.5049, | |
| "eval_samples_per_second": 55.211, | |
| "eval_steps_per_second": 55.211, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00022276082444846353, | |
| "loss": 0.4766, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0002217304300170949, | |
| "loss": 0.5072, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.00022069945157362675, | |
| "loss": 0.5265, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00021966791682592697, | |
| "loss": 0.4095, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00021863585349681436, | |
| "loss": 0.3976, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00021760328932331349, | |
| "loss": 0.4774, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00021657025205590923, | |
| "loss": 0.3426, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0002155367694578013, | |
| "loss": 0.4508, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00021450286930415735, | |
| "loss": 0.5369, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0002134685793813673, | |
| "loss": 0.4261, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00021243392748629614, | |
| "loss": 0.5256, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.00021139894142553693, | |
| "loss": 0.3956, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 0.0002103636490146637, | |
| "loss": 0.4001, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00020932807807748352, | |
| "loss": 0.6379, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0002082922564452891, | |
| "loss": 0.4611, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00020725621195611052, | |
| "loss": 0.5071, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0002062199724539674, | |
| "loss": 0.4864, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00020518356578812022, | |
| "loss": 0.4323, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00020414701981232215, | |
| "loss": 0.5897, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.0002031103623840702, | |
| "loss": 0.4404, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_loss": 0.574560284614563, | |
| "eval_runtime": 29.5518, | |
| "eval_samples_per_second": 55.124, | |
| "eval_steps_per_second": 55.124, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0002020736213638569, | |
| "loss": 0.4287, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0002010368246144213, | |
| "loss": 0.5213, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0002, | |
| "loss": 0.405, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00019896317538557878, | |
| "loss": 0.4283, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0001979263786361431, | |
| "loss": 0.4649, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00019688963761592981, | |
| "loss": 0.6243, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00019585298018767798, | |
| "loss": 0.4704, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00019481643421187978, | |
| "loss": 0.4266, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00019378002754603265, | |
| "loss": 0.4229, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00019274378804388952, | |
| "loss": 0.3718, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00019170774355471094, | |
| "loss": 0.4005, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0001906719219225165, | |
| "loss": 0.4458, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00018963635098533633, | |
| "loss": 0.4691, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00018860105857446306, | |
| "loss": 0.5098, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.0001875660725137039, | |
| "loss": 0.4538, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00018653142061863273, | |
| "loss": 0.5558, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00018549713069584276, | |
| "loss": 0.6011, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00018446323054219875, | |
| "loss": 0.3524, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00018342974794409079, | |
| "loss": 0.5304, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00018239671067668661, | |
| "loss": 0.3869, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 0.5739707350730896, | |
| "eval_runtime": 29.5087, | |
| "eval_samples_per_second": 55.204, | |
| "eval_steps_per_second": 55.204, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.0001813641465031857, | |
| "loss": 0.4354, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00018033208317407308, | |
| "loss": 0.4195, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0001793005484263733, | |
| "loss": 0.6035, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00017826956998290508, | |
| "loss": 0.4244, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00017723917555153654, | |
| "loss": 0.4614, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00017620939282444003, | |
| "loss": 0.4522, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00017518024947734814, | |
| "loss": 0.459, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00017415177316881022, | |
| "loss": 0.4259, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00017312399153944846, | |
| "loss": 0.4132, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00017209693221121542, | |
| "loss": 0.402, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00017107062278665165, | |
| "loss": 0.4812, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00017004509084814372, | |
| "loss": 0.3626, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00016902036395718305, | |
| "loss": 0.4885, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00016799646965362524, | |
| "loss": 0.5113, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00016697343545494974, | |
| "loss": 0.5277, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00016595128885552027, | |
| "loss": 0.5086, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00016493005732584647, | |
| "loss": 0.3616, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00016390976831184476, | |
| "loss": 0.599, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00016289044923410134, | |
| "loss": 0.3622, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00016187212748713519, | |
| "loss": 0.4129, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 0.5777345895767212, | |
| "eval_runtime": 29.5678, | |
| "eval_samples_per_second": 55.094, | |
| "eval_steps_per_second": 55.094, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00016085483043866143, | |
| "loss": 0.3741, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00015983858542885634, | |
| "loss": 0.508, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00015882341976962216, | |
| "loss": 0.4585, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0001578093607438534, | |
| "loss": 0.4852, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00015679643560470336, | |
| "loss": 0.5091, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00015578467157485165, | |
| "loss": 0.5604, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0001547740958457731, | |
| "loss": 0.5011, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00015376473557700613, | |
| "loss": 0.5016, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0001527566178954235, | |
| "loss": 0.4144, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00015174976989450314, | |
| "loss": 0.4511, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00015074421863359974, | |
| "loss": 0.4535, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0001497399911372178, | |
| "loss": 0.4065, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0001487371143942852, | |
| "loss": 0.6148, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00014773561535742793, | |
| "loss": 0.5625, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00014673552094224553, | |
| "loss": 0.3462, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00014573685802658824, | |
| "loss": 0.5958, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00014473965344983397, | |
| "loss": 0.4676, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00014374393401216746, | |
| "loss": 0.5282, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0001427497264738599, | |
| "loss": 0.4669, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.00014175705755454962, | |
| "loss": 0.4209, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 0.5824912786483765, | |
| "eval_runtime": 29.5128, | |
| "eval_samples_per_second": 55.196, | |
| "eval_steps_per_second": 55.196, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00014076595393252412, | |
| "loss": 0.5164, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00013977644224400312, | |
| "loss": 0.4663, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00013878854908242256, | |
| "loss": 0.4182, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00013780230099771988, | |
| "loss": 0.525, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0001368177244956208, | |
| "loss": 0.4229, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0001358348460369265, | |
| "loss": 0.5392, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00013485369203680283, | |
| "loss": 0.436, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00013387428886407014, | |
| "loss": 0.4743, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00013289666284049503, | |
| "loss": 0.4443, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0001319208402400824, | |
| "loss": 0.4095, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00013094684728836962, | |
| "loss": 0.4275, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00012997471016172187, | |
| "loss": 0.5256, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0001290044549866283, | |
| "loss": 0.5106, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0001280361078389998, | |
| "loss": 0.5659, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.000127069694743469, | |
| "loss": 0.5246, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00012610524167268975, | |
| "loss": 0.4125, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0001251427745466398, | |
| "loss": 0.647, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00012418231923192415, | |
| "loss": 0.4888, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00012322390154107952, | |
| "loss": 0.4619, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00012226754723188097, | |
| "loss": 0.4014, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 0.5741853713989258, | |
| "eval_runtime": 29.4992, | |
| "eval_samples_per_second": 55.222, | |
| "eval_steps_per_second": 55.222, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.00012131328200664955, | |
| "loss": 0.3622, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0001203611315115615, | |
| "loss": 0.4422, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.00011941112133595882, | |
| "loss": 0.5294, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.00011846327701166226, | |
| "loss": 0.583, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.00011751762401228414, | |
| "loss": 0.4461, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00011657418775254436, | |
| "loss": 0.427, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00011563299358758757, | |
| "loss": 0.5413, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.000114694066812301, | |
| "loss": 0.4541, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.00011375743266063508, | |
| "loss": 0.5347, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00011282311630492579, | |
| "loss": 0.5056, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00011189114285521705, | |
| "loss": 0.5073, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0001109615373585866, | |
| "loss": 0.4864, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00011003432479847284, | |
| "loss": 0.5461, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00010910953009400323, | |
| "loss": 0.4275, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00010818717809932435, | |
| "loss": 0.4805, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0001072672936029345, | |
| "loss": 0.4679, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.0001063499013270172, | |
| "loss": 0.3686, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00010543502592677646, | |
| "loss": 0.5115, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00010452269198977456, | |
| "loss": 0.3532, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00010361292403527154, | |
| "loss": 0.3333, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 0.5851367712020874, | |
| "eval_runtime": 29.5774, | |
| "eval_samples_per_second": 55.076, | |
| "eval_steps_per_second": 55.076, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00010270574651356541, | |
| "loss": 0.4008, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00010180118380533559, | |
| "loss": 0.5154, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00010089926022098767, | |
| "loss": 0.4936, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.00010000000000000005, | |
| "loss": 0.3771, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 9.910342731027206e-05, | |
| "loss": 0.4883, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 9.820956624747513e-05, | |
| "loss": 0.4783, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 9.731844083440478e-05, | |
| "loss": 0.3825, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 9.643007502033493e-05, | |
| "loss": 0.4128, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 9.554449268037464e-05, | |
| "loss": 0.3869, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 9.466171761482602e-05, | |
| "loss": 0.4742, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 9.378177354854498e-05, | |
| "loss": 0.4733, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 9.290468413030342e-05, | |
| "loss": 0.4182, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 9.203047293215349e-05, | |
| "loss": 0.3875, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 9.115916344879451e-05, | |
| "loss": 0.4561, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 9.029077909694128e-05, | |
| "loss": 0.4582, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.942534321469463e-05, | |
| "loss": 0.3878, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 8.856287906091434e-05, | |
| "loss": 0.4842, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.770340981459424e-05, | |
| "loss": 0.4127, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.684695857423906e-05, | |
| "loss": 0.343, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 8.599354835724347e-05, | |
| "loss": 0.5041, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 0.5797593593597412, | |
| "eval_runtime": 29.4998, | |
| "eval_samples_per_second": 55.221, | |
| "eval_steps_per_second": 55.221, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.514320209927392e-05, | |
| "loss": 0.4945, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.429594265365193e-05, | |
| "loss": 0.4627, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.345179279073982e-05, | |
| "loss": 0.4855, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 8.261077519732914e-05, | |
| "loss": 0.4253, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 8.177291247603068e-05, | |
| "loss": 0.5328, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 8.093822714466686e-05, | |
| "loss": 0.5276, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 8.01067416356668e-05, | |
| "loss": 0.5293, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 7.927847829546374e-05, | |
| "loss": 0.5709, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.845345938389372e-05, | |
| "loss": 0.3874, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.763170707359781e-05, | |
| "loss": 0.6164, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.68132434494263e-05, | |
| "loss": 0.4348, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.5998090507845e-05, | |
| "loss": 0.4215, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.518627015634392e-05, | |
| "loss": 0.4744, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.437780421284883e-05, | |
| "loss": 0.4775, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.357271440513473e-05, | |
| "loss": 0.5049, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 7.277102237024178e-05, | |
| "loss": 0.4757, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 7.197274965389413e-05, | |
| "loss": 0.4429, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 7.117791770992047e-05, | |
| "loss": 0.4628, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 7.038654789967776e-05, | |
| "loss": 0.5186, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 6.959866149147716e-05, | |
| "loss": 0.5528, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 0.5631201267242432, | |
| "eval_runtime": 29.5533, | |
| "eval_samples_per_second": 55.121, | |
| "eval_steps_per_second": 55.121, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 6.881427966001202e-05, | |
| "loss": 0.4201, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 6.803342348578938e-05, | |
| "loss": 0.3929, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 6.72561139545629e-05, | |
| "loss": 0.5163, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 6.648237195676928e-05, | |
| "loss": 0.4811, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 6.571221828696664e-05, | |
| "loss": 0.5658, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 6.494567364327549e-05, | |
| "loss": 0.5507, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 6.418275862682286e-05, | |
| "loss": 0.4629, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 6.342349374118817e-05, | |
| "loss": 0.4757, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 6.266789939185265e-05, | |
| "loss": 0.3063, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 6.191599588565067e-05, | |
| "loss": 0.3894, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 6.116780343022393e-05, | |
| "loss": 0.4114, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 6.042334213347856e-05, | |
| "loss": 0.399, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 5.9682632003044695e-05, | |
| "loss": 0.4437, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 5.8945692945738596e-05, | |
| "loss": 0.4709, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 5.821254476702767e-05, | |
| "loss": 0.4779, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 5.748320717049862e-05, | |
| "loss": 0.4662, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 5.6757699757327257e-05, | |
| "loss": 0.4706, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 5.603604202575199e-05, | |
| "loss": 0.5546, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 5.531825337055005e-05, | |
| "loss": 0.4415, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 5.460435308251597e-05, | |
| "loss": 0.4372, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 0.5746860504150391, | |
| "eval_runtime": 29.5006, | |
| "eval_samples_per_second": 55.219, | |
| "eval_steps_per_second": 55.219, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 5.3894360347943016e-05, | |
| "loss": 0.4186, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 5.318829424810796e-05, | |
| "loss": 0.4436, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 5.2486173758758e-05, | |
| "loss": 0.3979, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 5.178801774960065e-05, | |
| "loss": 0.3732, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 5.109384498379699e-05, | |
| "loss": 0.3469, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 5.040367411745701e-05, | |
| "loss": 0.4271, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.971752369913856e-05, | |
| "loss": 0.4189, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.903541216934864e-05, | |
| "loss": 0.5201, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.835735786004774e-05, | |
| "loss": 0.4036, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 4.768337899415749e-05, | |
| "loss": 0.5698, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.7013493685070484e-05, | |
| "loss": 0.4032, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.634771993616389e-05, | |
| "loss": 0.4928, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 4.568607564031535e-05, | |
| "loss": 0.3489, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.502857857942204e-05, | |
| "loss": 0.506, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.4375246423923125e-05, | |
| "loss": 0.3895, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.3726096732324415e-05, | |
| "loss": 0.4829, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.3081146950726804e-05, | |
| "loss": 0.4555, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.2440414412357376e-05, | |
| "loss": 0.5311, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.1803916337103275e-05, | |
| "loss": 0.398, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 4.11716698310493e-05, | |
| "loss": 0.3901, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 0.5625116229057312, | |
| "eval_runtime": 29.4983, | |
| "eval_samples_per_second": 55.224, | |
| "eval_steps_per_second": 55.224, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 4.054369188601796e-05, | |
| "loss": 0.3709, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 3.991999937911282e-05, | |
| "loss": 0.3773, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 3.930060907226485e-05, | |
| "loss": 0.502, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 3.8685537611782355e-05, | |
| "loss": 0.5624, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 3.807480152790302e-05, | |
| "loss": 0.5273, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 3.7468417234349976e-05, | |
| "loss": 0.3771, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 3.686640102789067e-05, | |
| "loss": 0.3751, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 3.6268769087898956e-05, | |
| "loss": 0.4526, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 3.567553747591988e-05, | |
| "loss": 0.335, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 3.508672213523854e-05, | |
| "loss": 0.4781, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 3.4502338890451315e-05, | |
| "loss": 0.3673, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 3.39224034470405e-05, | |
| "loss": 0.4073, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 3.3346931390952464e-05, | |
| "loss": 0.4014, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 3.277593818817863e-05, | |
| "loss": 0.4375, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 3.2209439184339804e-05, | |
| "loss": 0.4856, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 3.164744960427373e-05, | |
| "loss": 0.5534, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 3.1089984551626106e-05, | |
| "loss": 0.3766, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 3.053705900844452e-05, | |
| "loss": 0.541, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.9988687834775707e-05, | |
| "loss": 0.3937, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.9444885768266427e-05, | |
| "loss": 0.5271, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 0.5745556950569153, | |
| "eval_runtime": 29.5072, | |
| "eval_samples_per_second": 55.207, | |
| "eval_steps_per_second": 55.207, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.8905667423767256e-05, | |
| "loss": 0.4961, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.8371047292939645e-05, | |
| "loss": 0.306, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.7841039743866848e-05, | |
| "loss": 0.4234, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.7315659020667307e-05, | |
| "loss": 0.4259, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.679491924311226e-05, | |
| "loss": 0.5458, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.6278834406246054e-05, | |
| "loss": 0.4212, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.576741838000991e-05, | |
| "loss": 0.445, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.526068490886946e-05, | |
| "loss": 0.4042, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.4758647611445152e-05, | |
| "loss": 0.4857, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.4261319980146292e-05, | |
| "loss": 0.4402, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.3768715380808316e-05, | |
| "loss": 0.4056, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.3280847052333976e-05, | |
| "loss": 0.4577, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.279772810633707e-05, | |
| "loss": 0.3902, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.2319371526790223e-05, | |
| "loss": 0.4658, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.1845790169676074e-05, | |
| "loss": 0.3919, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.137699676264171e-05, | |
| "loss": 0.4294, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.091300390465638e-05, | |
| "loss": 0.3718, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.0453824065673222e-05, | |
| "loss": 0.5159, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 1.9999469586293996e-05, | |
| "loss": 0.4383, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1.9549952677437354e-05, | |
| "loss": 0.4283, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 0.566196084022522, | |
| "eval_runtime": 29.5086, | |
| "eval_samples_per_second": 55.204, | |
| "eval_steps_per_second": 55.204, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1.9105285420010598e-05, | |
| "loss": 0.3683, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1.8665479764585503e-05, | |
| "loss": 0.424, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1.8230547531076403e-05, | |
| "loss": 0.4972, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 1.7800500408423028e-05, | |
| "loss": 0.3295, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 1.7375349954276233e-05, | |
| "loss": 0.4563, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 1.695510759468746e-05, | |
| "loss": 0.3215, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.653978462380139e-05, | |
| "loss": 0.5377, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.6129392203552717e-05, | |
| "loss": 0.5608, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.5723941363366102e-05, | |
| "loss": 0.4279, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.5323442999859505e-05, | |
| "loss": 0.4503, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.4927907876551716e-05, | |
| "loss": 0.3723, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.4537346623572757e-05, | |
| "loss": 0.4459, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 1.415176973737844e-05, | |
| "loss": 0.5126, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.3771187580468115e-05, | |
| "loss": 0.4712, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.3395610381106171e-05, | |
| "loss": 0.4301, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.3025048233047266e-05, | |
| "loss": 0.4497, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.2659511095264997e-05, | |
| "loss": 0.6653, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.2299008791684174e-05, | |
| "loss": 0.4751, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.1943551010916887e-05, | |
| "loss": 0.4593, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.1593147306002183e-05, | |
| "loss": 0.4336, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 0.5652015209197998, | |
| "eval_runtime": 29.5541, | |
| "eval_samples_per_second": 55.119, | |
| "eval_steps_per_second": 55.119, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 1.1247807094149098e-05, | |
| "loss": 0.3976, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.0907539656483745e-05, | |
| "loss": 0.4607, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.0572354137799978e-05, | |
| "loss": 0.3328, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 1.0242259546313327e-05, | |
| "loss": 0.3834, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 9.91726475341912e-06, | |
| "loss": 0.3841, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 9.597378493454013e-06, | |
| "loss": 0.4061, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 9.282609363461281e-06, | |
| "loss": 0.5084, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 8.972965822959678e-06, | |
| "loss": 0.4186, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 8.668456193716057e-06, | |
| "loss": 0.4335, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 8.369088659522018e-06, | |
| "loss": 0.4099, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 8.074871265973572e-06, | |
| "loss": 0.4574, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 7.785811920255093e-06, | |
| "loss": 0.3767, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 7.501918390926932e-06, | |
| "loss": 0.4218, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 7.223198307716428e-06, | |
| "loss": 0.4847, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 6.949659161312871e-06, | |
| "loss": 0.3806, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 6.6813083031664005e-06, | |
| "loss": 0.467, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 6.418152945290224e-06, | |
| "loss": 0.4087, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 6.1602001600667755e-06, | |
| "loss": 0.5307, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 5.907456880057871e-06, | |
| "loss": 0.3665, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 5.659929897818095e-06, | |
| "loss": 0.3534, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 0.5697055459022522, | |
| "eval_runtime": 29.5456, | |
| "eval_samples_per_second": 55.135, | |
| "eval_steps_per_second": 55.135, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 5.417625865712506e-06, | |
| "loss": 0.4096, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 5.180551295737734e-06, | |
| "loss": 0.3822, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 4.9487125593469244e-06, | |
| "loss": 0.4499, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 4.7221158872786e-06, | |
| "loss": 0.4191, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 4.500767369389158e-06, | |
| "loss": 0.4676, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 4.284672954489177e-06, | |
| "loss": 0.379, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 4.073838450183654e-06, | |
| "loss": 0.4382, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.8682695227158174e-06, | |
| "loss": 0.3908, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.667971696814787e-06, | |
| "loss": 0.4563, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.4729503555472663e-06, | |
| "loss": 0.4164, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.2832107401727928e-06, | |
| "loss": 0.361, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.0987579500028062e-06, | |
| "loss": 0.4599, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.919596942263736e-06, | |
| "loss": 0.4045, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.7457325319636408e-06, | |
| "loss": 0.4345, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.5771693917629345e-06, | |
| "loss": 0.5191, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.4139120518486657e-06, | |
| "loss": 0.444, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.2559648998128792e-06, | |
| "loss": 0.4587, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 2.1033321805346896e-06, | |
| "loss": 0.4841, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.9560179960661283e-06, | |
| "loss": 0.3539, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.8140263055219209e-06, | |
| "loss": 0.4728, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 0.5713478922843933, | |
| "eval_runtime": 29.5401, | |
| "eval_samples_per_second": 55.145, | |
| "eval_steps_per_second": 55.145, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.6773609249731703e-06, | |
| "loss": 0.5651, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.5460255273447077e-06, | |
| "loss": 0.5959, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.4200236423163704e-06, | |
| "loss": 0.5015, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.2993586562282112e-06, | |
| "loss": 0.5174, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.1840338119894822e-06, | |
| "loss": 0.3708, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.0740522089913941e-06, | |
| "loss": 0.4129, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 9.694168030239148e-07, | |
| "loss": 0.4747, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 8.701304061962789e-07, | |
| "loss": 0.3967, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 7.761956868614473e-07, | |
| "loss": 0.3929, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 6.876151695443867e-07, | |
| "loss": 0.4657, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 6.043912348741465e-07, | |
| "loss": 0.4274, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 5.265261195200211e-07, | |
| "loss": 0.5102, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 4.5402191613130864e-07, | |
| "loss": 0.4686, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 3.8688057328113425e-07, | |
| "loss": 0.397, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 3.251038954140917e-07, | |
| "loss": 0.4532, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.6869354279770444e-07, | |
| "loss": 0.3698, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.1765103147783905e-07, | |
| "loss": 0.4519, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.7197773323791577e-07, | |
| "loss": 0.4861, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.3167487556213775e-07, | |
| "loss": 0.5166, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 9.67435416023843e-08, | |
| "loss": 0.5159, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 0.5703364014625549, | |
| "eval_runtime": 29.5151, | |
| "eval_samples_per_second": 55.192, | |
| "eval_steps_per_second": 55.192, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 6.718467014918962e-08, | |
| "loss": 0.3659, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 4.299905560642969e-08, | |
| "loss": 0.4171, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 2.418734797009492e-08, | |
| "loss": 0.3435, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.075005281070407e-08, | |
| "loss": 0.5624, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 2.6875312597374193e-09, | |
| "loss": 0.4061, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.3871, | |
| "step": 706 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 706, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 1.8453659621743657e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |