|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 10.0, |
|
"eval_steps": 500, |
|
"global_step": 280, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0, |
|
"loss": 1.4847, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 6.309297535714573e-05, |
|
"loss": 1.2044, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0001, |
|
"loss": 1.1772, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.00012618595071429146, |
|
"loss": 1.1318, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.0001464973520717927, |
|
"loss": 1.0803, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.00016309297535714573, |
|
"loss": 1.0287, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.00017712437491614223, |
|
"loss": 0.9974, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.0001892789260714372, |
|
"loss": 0.958, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.0002, |
|
"loss": 0.9355, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.0002, |
|
"loss": 0.9544, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.0002, |
|
"loss": 0.8867, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 0.0002, |
|
"loss": 0.8466, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.0002, |
|
"loss": 0.8225, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7851, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7768, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7356, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6515, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7061, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6145, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 0.0002, |
|
"loss": 0.6616, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 0.0002, |
|
"loss": 0.523, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 0.0002, |
|
"loss": 0.4883, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 0.0002, |
|
"loss": 0.452, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 0.0002, |
|
"loss": 0.3769, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 0.0002, |
|
"loss": 0.4295, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 0.0002, |
|
"loss": 0.3565, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.0002, |
|
"loss": 0.4003, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.0002, |
|
"loss": 0.3266, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.2492515742778778, |
|
"eval_runtime": 55.0422, |
|
"eval_samples_per_second": 15.752, |
|
"eval_steps_per_second": 0.509, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.232, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 0.0002, |
|
"loss": 0.2445, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.2248, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 0.0002, |
|
"loss": 0.1929, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 0.0002, |
|
"loss": 0.2116, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 1.21, |
|
"learning_rate": 0.0002, |
|
"loss": 0.1934, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 0.0002, |
|
"loss": 0.2355, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 0.0002, |
|
"loss": 0.1541, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 0.0002, |
|
"loss": 0.1533, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0981, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 0.0002, |
|
"loss": 0.106, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 0.0002, |
|
"loss": 0.1764, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 0.0002, |
|
"loss": 0.1153, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 0.0002, |
|
"loss": 0.1043, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 0.0002, |
|
"loss": 0.1349, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 0.0002, |
|
"loss": 0.1331, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0688, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0732, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0936, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 0.0002, |
|
"loss": 0.1128, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 0.0002, |
|
"loss": 0.1004, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0567, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 0.0002, |
|
"loss": 0.1314, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0496, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"learning_rate": 0.0002, |
|
"loss": 0.1106, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 1.93, |
|
"learning_rate": 0.0002, |
|
"loss": 0.1594, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 0.0002, |
|
"loss": 0.1061, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0401, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.04567016288638115, |
|
"eval_runtime": 55.1162, |
|
"eval_samples_per_second": 15.73, |
|
"eval_steps_per_second": 0.508, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0377, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 2.07, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0321, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 2.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0318, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0449, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 2.18, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0209, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 2.21, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0389, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 2.25, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0246, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 2.29, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0221, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0326, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 2.36, |
|
"learning_rate": 0.0002, |
|
"loss": 0.03, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 2.39, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0145, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 2.43, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0309, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 2.46, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0397, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0283, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0229, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 2.57, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0211, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0135, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0377, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 2.68, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0333, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 2.71, |
|
"learning_rate": 0.0002, |
|
"loss": 0.022, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 2.75, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0132, |
|
"step": 77 |
|
}, |
|
{ |
|
"epoch": 2.79, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0258, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 2.82, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0312, |
|
"step": 79 |
|
}, |
|
{ |
|
"epoch": 2.86, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0261, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 2.89, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0217, |
|
"step": 81 |
|
}, |
|
{ |
|
"epoch": 2.93, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0286, |
|
"step": 82 |
|
}, |
|
{ |
|
"epoch": 2.96, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0341, |
|
"step": 83 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0097, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 0.015407511964440346, |
|
"eval_runtime": 55.2224, |
|
"eval_samples_per_second": 15.7, |
|
"eval_steps_per_second": 0.507, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 3.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0076, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 3.07, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0137, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 3.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.009, |
|
"step": 87 |
|
}, |
|
{ |
|
"epoch": 3.14, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0083, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 3.18, |
|
"learning_rate": 0.0002, |
|
"loss": 0.011, |
|
"step": 89 |
|
}, |
|
{ |
|
"epoch": 3.21, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0092, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 3.25, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0108, |
|
"step": 91 |
|
}, |
|
{ |
|
"epoch": 3.29, |
|
"learning_rate": 0.0002, |
|
"loss": 0.007, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 3.32, |
|
"learning_rate": 0.0002, |
|
"loss": 0.008, |
|
"step": 93 |
|
}, |
|
{ |
|
"epoch": 3.36, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0063, |
|
"step": 94 |
|
}, |
|
{ |
|
"epoch": 3.39, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0117, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 3.43, |
|
"learning_rate": 0.0002, |
|
"loss": 0.015, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 3.46, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0117, |
|
"step": 97 |
|
}, |
|
{ |
|
"epoch": 3.5, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0102, |
|
"step": 98 |
|
}, |
|
{ |
|
"epoch": 3.54, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0113, |
|
"step": 99 |
|
}, |
|
{ |
|
"epoch": 3.57, |
|
"learning_rate": 0.0002, |
|
"loss": 0.006, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 3.61, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0157, |
|
"step": 101 |
|
}, |
|
{ |
|
"epoch": 3.64, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0109, |
|
"step": 102 |
|
}, |
|
{ |
|
"epoch": 3.68, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0157, |
|
"step": 103 |
|
}, |
|
{ |
|
"epoch": 3.71, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0097, |
|
"step": 104 |
|
}, |
|
{ |
|
"epoch": 3.75, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0159, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 3.79, |
|
"learning_rate": 0.0002, |
|
"loss": 0.012, |
|
"step": 106 |
|
}, |
|
{ |
|
"epoch": 3.82, |
|
"learning_rate": 0.0002, |
|
"loss": 0.009, |
|
"step": 107 |
|
}, |
|
{ |
|
"epoch": 3.86, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0076, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 3.89, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0098, |
|
"step": 109 |
|
}, |
|
{ |
|
"epoch": 3.93, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0204, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 3.96, |
|
"learning_rate": 0.0002, |
|
"loss": 0.005, |
|
"step": 111 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0111, |
|
"step": 112 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_loss": 0.009237131103873253, |
|
"eval_runtime": 55.2594, |
|
"eval_samples_per_second": 15.69, |
|
"eval_steps_per_second": 0.507, |
|
"step": 112 |
|
}, |
|
{ |
|
"epoch": 4.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0108, |
|
"step": 113 |
|
}, |
|
{ |
|
"epoch": 4.07, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0056, |
|
"step": 114 |
|
}, |
|
{ |
|
"epoch": 4.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0056, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 4.14, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0067, |
|
"step": 116 |
|
}, |
|
{ |
|
"epoch": 4.18, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0054, |
|
"step": 117 |
|
}, |
|
{ |
|
"epoch": 4.21, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0102, |
|
"step": 118 |
|
}, |
|
{ |
|
"epoch": 4.25, |
|
"learning_rate": 0.0002, |
|
"loss": 0.012, |
|
"step": 119 |
|
}, |
|
{ |
|
"epoch": 4.29, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0109, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 4.32, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0092, |
|
"step": 121 |
|
}, |
|
{ |
|
"epoch": 4.36, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0062, |
|
"step": 122 |
|
}, |
|
{ |
|
"epoch": 4.39, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0063, |
|
"step": 123 |
|
}, |
|
{ |
|
"epoch": 4.43, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0051, |
|
"step": 124 |
|
}, |
|
{ |
|
"epoch": 4.46, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0044, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 4.5, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0058, |
|
"step": 126 |
|
}, |
|
{ |
|
"epoch": 4.54, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0045, |
|
"step": 127 |
|
}, |
|
{ |
|
"epoch": 4.57, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0048, |
|
"step": 128 |
|
}, |
|
{ |
|
"epoch": 4.61, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0061, |
|
"step": 129 |
|
}, |
|
{ |
|
"epoch": 4.64, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0034, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 4.68, |
|
"learning_rate": 0.0002, |
|
"loss": 0.004, |
|
"step": 131 |
|
}, |
|
{ |
|
"epoch": 4.71, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0039, |
|
"step": 132 |
|
}, |
|
{ |
|
"epoch": 4.75, |
|
"learning_rate": 0.0002, |
|
"loss": 0.007, |
|
"step": 133 |
|
}, |
|
{ |
|
"epoch": 4.79, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0041, |
|
"step": 134 |
|
}, |
|
{ |
|
"epoch": 4.82, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0086, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 4.86, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0056, |
|
"step": 136 |
|
}, |
|
{ |
|
"epoch": 4.89, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0085, |
|
"step": 137 |
|
}, |
|
{ |
|
"epoch": 4.93, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0099, |
|
"step": 138 |
|
}, |
|
{ |
|
"epoch": 4.96, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0031, |
|
"step": 139 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0042, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_loss": 0.006931006908416748, |
|
"eval_runtime": 55.2933, |
|
"eval_samples_per_second": 15.68, |
|
"eval_steps_per_second": 0.506, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 5.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0072, |
|
"step": 141 |
|
}, |
|
{ |
|
"epoch": 5.07, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0048, |
|
"step": 142 |
|
}, |
|
{ |
|
"epoch": 5.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0074, |
|
"step": 143 |
|
}, |
|
{ |
|
"epoch": 5.14, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0086, |
|
"step": 144 |
|
}, |
|
{ |
|
"epoch": 5.18, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0078, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 5.21, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0043, |
|
"step": 146 |
|
}, |
|
{ |
|
"epoch": 5.25, |
|
"learning_rate": 0.0002, |
|
"loss": 0.005, |
|
"step": 147 |
|
}, |
|
{ |
|
"epoch": 5.29, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0057, |
|
"step": 148 |
|
}, |
|
{ |
|
"epoch": 5.32, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0083, |
|
"step": 149 |
|
}, |
|
{ |
|
"epoch": 5.36, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0069, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 5.39, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0039, |
|
"step": 151 |
|
}, |
|
{ |
|
"epoch": 5.43, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0058, |
|
"step": 152 |
|
}, |
|
{ |
|
"epoch": 5.46, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0058, |
|
"step": 153 |
|
}, |
|
{ |
|
"epoch": 5.5, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0101, |
|
"step": 154 |
|
}, |
|
{ |
|
"epoch": 5.54, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0038, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 5.57, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0085, |
|
"step": 156 |
|
}, |
|
{ |
|
"epoch": 5.61, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0052, |
|
"step": 157 |
|
}, |
|
{ |
|
"epoch": 5.64, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0045, |
|
"step": 158 |
|
}, |
|
{ |
|
"epoch": 5.68, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0128, |
|
"step": 159 |
|
}, |
|
{ |
|
"epoch": 5.71, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0043, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 5.75, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0033, |
|
"step": 161 |
|
}, |
|
{ |
|
"epoch": 5.79, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0026, |
|
"step": 162 |
|
}, |
|
{ |
|
"epoch": 5.82, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0027, |
|
"step": 163 |
|
}, |
|
{ |
|
"epoch": 5.86, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0159, |
|
"step": 164 |
|
}, |
|
{ |
|
"epoch": 5.89, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0037, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 5.93, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0057, |
|
"step": 166 |
|
}, |
|
{ |
|
"epoch": 5.96, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0079, |
|
"step": 167 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0049, |
|
"step": 168 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_loss": 0.005192028358578682, |
|
"eval_runtime": 55.2474, |
|
"eval_samples_per_second": 15.693, |
|
"eval_steps_per_second": 0.507, |
|
"step": 168 |
|
}, |
|
{ |
|
"epoch": 6.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0025, |
|
"step": 169 |
|
}, |
|
{ |
|
"epoch": 6.07, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0062, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 6.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0025, |
|
"step": 171 |
|
}, |
|
{ |
|
"epoch": 6.14, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0077, |
|
"step": 172 |
|
}, |
|
{ |
|
"epoch": 6.18, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0027, |
|
"step": 173 |
|
}, |
|
{ |
|
"epoch": 6.21, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0067, |
|
"step": 174 |
|
}, |
|
{ |
|
"epoch": 6.25, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0032, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 6.29, |
|
"learning_rate": 0.0002, |
|
"loss": 0.006, |
|
"step": 176 |
|
}, |
|
{ |
|
"epoch": 6.32, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0072, |
|
"step": 177 |
|
}, |
|
{ |
|
"epoch": 6.36, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0101, |
|
"step": 178 |
|
}, |
|
{ |
|
"epoch": 6.39, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0078, |
|
"step": 179 |
|
}, |
|
{ |
|
"epoch": 6.43, |
|
"learning_rate": 0.0002, |
|
"loss": 0.003, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 6.46, |
|
"learning_rate": 0.0002, |
|
"loss": 0.006, |
|
"step": 181 |
|
}, |
|
{ |
|
"epoch": 6.5, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0056, |
|
"step": 182 |
|
}, |
|
{ |
|
"epoch": 6.54, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0053, |
|
"step": 183 |
|
}, |
|
{ |
|
"epoch": 6.57, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0098, |
|
"step": 184 |
|
}, |
|
{ |
|
"epoch": 6.61, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0052, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 6.64, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0045, |
|
"step": 186 |
|
}, |
|
{ |
|
"epoch": 6.68, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0082, |
|
"step": 187 |
|
}, |
|
{ |
|
"epoch": 6.71, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0042, |
|
"step": 188 |
|
}, |
|
{ |
|
"epoch": 6.75, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0043, |
|
"step": 189 |
|
}, |
|
{ |
|
"epoch": 6.79, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0062, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 6.82, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0069, |
|
"step": 191 |
|
}, |
|
{ |
|
"epoch": 6.86, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0047, |
|
"step": 192 |
|
}, |
|
{ |
|
"epoch": 6.89, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0044, |
|
"step": 193 |
|
}, |
|
{ |
|
"epoch": 6.93, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0046, |
|
"step": 194 |
|
}, |
|
{ |
|
"epoch": 6.96, |
|
"learning_rate": 0.0002, |
|
"loss": 0.003, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0022, |
|
"step": 196 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_loss": 0.0039033088833093643, |
|
"eval_runtime": 55.2409, |
|
"eval_samples_per_second": 15.695, |
|
"eval_steps_per_second": 0.507, |
|
"step": 196 |
|
}, |
|
{ |
|
"epoch": 7.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0047, |
|
"step": 197 |
|
}, |
|
{ |
|
"epoch": 7.07, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0064, |
|
"step": 198 |
|
}, |
|
{ |
|
"epoch": 7.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0044, |
|
"step": 199 |
|
}, |
|
{ |
|
"epoch": 7.14, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0051, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 7.18, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0026, |
|
"step": 201 |
|
}, |
|
{ |
|
"epoch": 7.21, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0042, |
|
"step": 202 |
|
}, |
|
{ |
|
"epoch": 7.25, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0034, |
|
"step": 203 |
|
}, |
|
{ |
|
"epoch": 7.29, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0012, |
|
"step": 204 |
|
}, |
|
{ |
|
"epoch": 7.32, |
|
"learning_rate": 0.0002, |
|
"loss": 0.002, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 7.36, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0061, |
|
"step": 206 |
|
}, |
|
{ |
|
"epoch": 7.39, |
|
"learning_rate": 0.0002, |
|
"loss": 0.005, |
|
"step": 207 |
|
}, |
|
{ |
|
"epoch": 7.43, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0065, |
|
"step": 208 |
|
}, |
|
{ |
|
"epoch": 7.46, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0019, |
|
"step": 209 |
|
}, |
|
{ |
|
"epoch": 7.5, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0027, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 7.54, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0037, |
|
"step": 211 |
|
}, |
|
{ |
|
"epoch": 7.57, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0052, |
|
"step": 212 |
|
}, |
|
{ |
|
"epoch": 7.61, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0029, |
|
"step": 213 |
|
}, |
|
{ |
|
"epoch": 7.64, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0025, |
|
"step": 214 |
|
}, |
|
{ |
|
"epoch": 7.68, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0019, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 7.71, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0038, |
|
"step": 216 |
|
}, |
|
{ |
|
"epoch": 7.75, |
|
"learning_rate": 0.0002, |
|
"loss": 0.004, |
|
"step": 217 |
|
}, |
|
{ |
|
"epoch": 7.79, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0033, |
|
"step": 218 |
|
}, |
|
{ |
|
"epoch": 7.82, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0066, |
|
"step": 219 |
|
}, |
|
{ |
|
"epoch": 7.86, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0047, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 7.89, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0032, |
|
"step": 221 |
|
}, |
|
{ |
|
"epoch": 7.93, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0065, |
|
"step": 222 |
|
}, |
|
{ |
|
"epoch": 7.96, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0025, |
|
"step": 223 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"learning_rate": 0.0002, |
|
"loss": 0.002, |
|
"step": 224 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_loss": 0.005082768388092518, |
|
"eval_runtime": 55.2726, |
|
"eval_samples_per_second": 15.686, |
|
"eval_steps_per_second": 0.507, |
|
"step": 224 |
|
}, |
|
{ |
|
"epoch": 8.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0051, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 8.07, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0087, |
|
"step": 226 |
|
}, |
|
{ |
|
"epoch": 8.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0025, |
|
"step": 227 |
|
}, |
|
{ |
|
"epoch": 8.14, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0046, |
|
"step": 228 |
|
}, |
|
{ |
|
"epoch": 8.18, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0023, |
|
"step": 229 |
|
}, |
|
{ |
|
"epoch": 8.21, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0033, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 8.25, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0024, |
|
"step": 231 |
|
}, |
|
{ |
|
"epoch": 8.29, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0048, |
|
"step": 232 |
|
}, |
|
{ |
|
"epoch": 8.32, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0036, |
|
"step": 233 |
|
}, |
|
{ |
|
"epoch": 8.36, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0025, |
|
"step": 234 |
|
}, |
|
{ |
|
"epoch": 8.39, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0028, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 8.43, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0027, |
|
"step": 236 |
|
}, |
|
{ |
|
"epoch": 8.46, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0034, |
|
"step": 237 |
|
}, |
|
{ |
|
"epoch": 8.5, |
|
"learning_rate": 0.0002, |
|
"loss": 0.002, |
|
"step": 238 |
|
}, |
|
{ |
|
"epoch": 8.54, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0035, |
|
"step": 239 |
|
}, |
|
{ |
|
"epoch": 8.57, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0076, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 8.61, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0042, |
|
"step": 241 |
|
}, |
|
{ |
|
"epoch": 8.64, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0035, |
|
"step": 242 |
|
}, |
|
{ |
|
"epoch": 8.68, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0044, |
|
"step": 243 |
|
}, |
|
{ |
|
"epoch": 8.71, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0054, |
|
"step": 244 |
|
}, |
|
{ |
|
"epoch": 8.75, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0025, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 8.79, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0013, |
|
"step": 246 |
|
}, |
|
{ |
|
"epoch": 8.82, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0025, |
|
"step": 247 |
|
}, |
|
{ |
|
"epoch": 8.86, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0013, |
|
"step": 248 |
|
}, |
|
{ |
|
"epoch": 8.89, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0015, |
|
"step": 249 |
|
}, |
|
{ |
|
"epoch": 8.93, |
|
"learning_rate": 0.0002, |
|
"loss": 0.002, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 8.96, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0025, |
|
"step": 251 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0015, |
|
"step": 252 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_loss": 0.004076390527188778, |
|
"eval_runtime": 55.2102, |
|
"eval_samples_per_second": 15.704, |
|
"eval_steps_per_second": 0.507, |
|
"step": 252 |
|
}, |
|
{ |
|
"epoch": 9.04, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0015, |
|
"step": 253 |
|
}, |
|
{ |
|
"epoch": 9.07, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0029, |
|
"step": 254 |
|
}, |
|
{ |
|
"epoch": 9.11, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0014, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 9.14, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0018, |
|
"step": 256 |
|
}, |
|
{ |
|
"epoch": 9.18, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0061, |
|
"step": 257 |
|
}, |
|
{ |
|
"epoch": 9.21, |
|
"learning_rate": 0.0002, |
|
"loss": 0.003, |
|
"step": 258 |
|
}, |
|
{ |
|
"epoch": 9.25, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0016, |
|
"step": 259 |
|
}, |
|
{ |
|
"epoch": 9.29, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0014, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 9.32, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0034, |
|
"step": 261 |
|
}, |
|
{ |
|
"epoch": 9.36, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0008, |
|
"step": 262 |
|
}, |
|
{ |
|
"epoch": 9.39, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0049, |
|
"step": 263 |
|
}, |
|
{ |
|
"epoch": 9.43, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0012, |
|
"step": 264 |
|
}, |
|
{ |
|
"epoch": 9.46, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0012, |
|
"step": 265 |
|
}, |
|
{ |
|
"epoch": 9.5, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0012, |
|
"step": 266 |
|
}, |
|
{ |
|
"epoch": 9.54, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0021, |
|
"step": 267 |
|
}, |
|
{ |
|
"epoch": 9.57, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0065, |
|
"step": 268 |
|
}, |
|
{ |
|
"epoch": 9.61, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0007, |
|
"step": 269 |
|
}, |
|
{ |
|
"epoch": 9.64, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0032, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 9.68, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0014, |
|
"step": 271 |
|
}, |
|
{ |
|
"epoch": 9.71, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0035, |
|
"step": 272 |
|
}, |
|
{ |
|
"epoch": 9.75, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0015, |
|
"step": 273 |
|
}, |
|
{ |
|
"epoch": 9.79, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0012, |
|
"step": 274 |
|
}, |
|
{ |
|
"epoch": 9.82, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0016, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 9.86, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0021, |
|
"step": 276 |
|
}, |
|
{ |
|
"epoch": 9.89, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0023, |
|
"step": 277 |
|
}, |
|
{ |
|
"epoch": 9.93, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0044, |
|
"step": 278 |
|
}, |
|
{ |
|
"epoch": 9.96, |
|
"learning_rate": 0.0002, |
|
"loss": 0.001, |
|
"step": 279 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 0.0002, |
|
"loss": 0.0015, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"eval_loss": 0.0016192951006814837, |
|
"eval_runtime": 55.2675, |
|
"eval_samples_per_second": 15.687, |
|
"eval_steps_per_second": 0.507, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"step": 280, |
|
"total_flos": 8.284116092306063e+17, |
|
"train_loss": 0.09805020090986676, |
|
"train_runtime": 3259.3787, |
|
"train_samples_per_second": 2.66, |
|
"train_steps_per_second": 0.086 |
|
} |
|
], |
|
"logging_steps": 1.0, |
|
"max_steps": 280, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 10, |
|
"save_steps": 50000, |
|
"total_flos": 8.284116092306063e+17, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|