Llama2_Instruction_Finetuning_Experiments
/
llama2_7b_r128_alpha256
/checkpoint-375
/trainer_state.json
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9273570324574961, | |
| "eval_steps": 500, | |
| "global_step": 375, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0003, | |
| "loss": 1.8153, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0003, | |
| "loss": 1.6303, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0003, | |
| "loss": 1.6116, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0003, | |
| "loss": 1.5673, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0003, | |
| "loss": 1.3609, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0003, | |
| "loss": 1.2827, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0003, | |
| "loss": 1.2007, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0003, | |
| "loss": 1.2038, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0003, | |
| "loss": 1.1573, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0003, | |
| "loss": 1.1077, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0003, | |
| "loss": 1.1129, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0003, | |
| "loss": 1.0797, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0003, | |
| "loss": 1.0305, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0003, | |
| "loss": 1.0469, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0003, | |
| "loss": 1.0351, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0003, | |
| "loss": 1.0119, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9768, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9678, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9907, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9969, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9745, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0003, | |
| "loss": 1.0067, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0003, | |
| "loss": 1.0026, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0003, | |
| "loss": 0.937, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9162, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9208, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0003, | |
| "loss": 1.0024, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9405, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9414, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0003, | |
| "loss": 0.924, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9499, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9758, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9483, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9765, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9296, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9615, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9371, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9342, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9395, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9117, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9577, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9343, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9315, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9275, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9142, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9574, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9248, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9282, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9278, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9587, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9042, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9162, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9155, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9131, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9314, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9258, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9748, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9132, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9031, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9271, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9225, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9248, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0003, | |
| "loss": 0.913, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0003, | |
| "loss": 0.921, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9299, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9168, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9288, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9768, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8997, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9332, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9379, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8703, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9297, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9281, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9322, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9189, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9278, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9233, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9099, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9093, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8735, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9276, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9176, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9127, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9034, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9285, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9089, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9359, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9224, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9255, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8984, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9243, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9479, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9087, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9082, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9111, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9198, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9003, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9436, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9247, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9321, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8737, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8939, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9224, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9087, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9321, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9249, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0003, | |
| "loss": 0.931, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9023, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9048, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9294, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0003, | |
| "loss": 0.939, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0003, | |
| "loss": 0.914, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8886, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8595, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9124, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8725, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9174, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9099, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9251, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9098, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9041, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9296, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9245, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9325, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8948, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9074, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9054, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8945, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9638, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9422, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8736, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8873, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9207, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9085, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8885, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9462, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9142, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9153, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9204, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9303, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8852, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8807, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9085, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0003, | |
| "loss": 0.936, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0003, | |
| "loss": 0.89, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9454, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8845, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0003, | |
| "loss": 0.905, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0003, | |
| "loss": 0.886, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9232, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9008, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9368, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8981, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9086, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8679, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8847, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9136, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8911, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9089, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9584, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8901, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8887, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8815, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9104, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9366, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9329, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9283, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9019, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9251, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0003, | |
| "loss": 0.881, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9219, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9161, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9045, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9106, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9343, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9335, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9001, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9114, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8635, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0003, | |
| "loss": 0.898, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9244, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9454, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9444, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9183, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9052, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9078, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9344, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0003, | |
| "loss": 0.936, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8871, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9122, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9266, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9344, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9168, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9011, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9285, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8675, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9066, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8729, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0003, | |
| "loss": 0.899, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8819, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9093, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9326, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9375, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9048, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9385, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9015, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8879, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8989, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8649, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9171, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8951, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9582, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9014, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0003, | |
| "loss": 0.913, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0003, | |
| "loss": 0.898, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8973, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8746, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8895, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9355, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9043, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9501, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8954, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0003, | |
| "loss": 0.91, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9041, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9141, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8926, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9198, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8994, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9233, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9209, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8951, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9018, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8744, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8921, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9141, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9265, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9085, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9565, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8861, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9017, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9037, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8947, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9079, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9136, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9256, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9018, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9024, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8416, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9122, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0003, | |
| "loss": 0.915, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9133, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0003, | |
| "loss": 0.902, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9033, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9169, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8778, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8905, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9083, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8625, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8845, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0003, | |
| "loss": 0.947, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8956, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9204, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8618, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8927, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8632, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0003, | |
| "loss": 0.895, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9135, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9397, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8725, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8758, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8726, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9122, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9045, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0003, | |
| "loss": 0.901, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8736, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0003, | |
| "loss": 0.913, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0003, | |
| "loss": 0.925, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8933, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8922, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9029, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8923, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8756, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8957, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8951, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8998, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9223, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8788, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0003, | |
| "loss": 0.894, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8458, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8828, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8931, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8776, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9021, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8766, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9076, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8823, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9169, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9123, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8913, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8747, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9071, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8822, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8901, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9107, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8925, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9175, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9198, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9085, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8926, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8668, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0003, | |
| "loss": 0.901, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9114, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8967, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9047, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9374, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8948, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8571, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8603, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9127, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0003, | |
| "loss": 0.919, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9331, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8877, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9005, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8946, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9126, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8858, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8704, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8849, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8807, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9322, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8798, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9058, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8785, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9141, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8699, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9035, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8962, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0003, | |
| "loss": 0.908, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8827, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8985, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9063, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9144, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9015, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9156, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8971, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9007, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0003, | |
| "loss": 0.897, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8954, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8898, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8751, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8929, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9048, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9133, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8999, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9438, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8856, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8827, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8717, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9428, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8884, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8663, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8873, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9045, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0003, | |
| "loss": 0.894, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8886, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9134, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0003, | |
| "loss": 0.9284, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8973, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8974, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8653, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8805, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8917, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0003, | |
| "loss": 0.8791, | |
| "step": 375 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 404, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "total_flos": 4.234518435117957e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |