File size: 3,377 Bytes
fe45bf9 25380e9 fe45bf9 25380e9 fe45bf9 5a19fb2 3f0151b c678ad5 7f3e895 ff82bd9 72e8a1c 90c44f1 da732ea 8a8df84 25380e9 fe45bf9 25380e9 fe45bf9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.913978494623656,
"eval_steps": 200,
"global_step": 2200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.54,
"learning_rate": 0.0002,
"loss": 0.1582,
"step": 200
},
{
"epoch": 0.54,
"eval_runtime": 113.8373,
"eval_samples_per_second": 2.75,
"eval_steps_per_second": 0.176,
"step": 200
},
{
"epoch": 1.08,
"learning_rate": 0.0002,
"loss": 0.077,
"step": 400
},
{
"epoch": 1.08,
"eval_runtime": 113.8308,
"eval_samples_per_second": 2.75,
"eval_steps_per_second": 0.176,
"step": 400
},
{
"epoch": 1.61,
"learning_rate": 0.0002,
"loss": 0.0598,
"step": 600
},
{
"epoch": 1.61,
"eval_runtime": 113.7433,
"eval_samples_per_second": 2.752,
"eval_steps_per_second": 0.176,
"step": 600
},
{
"epoch": 2.15,
"learning_rate": 0.0002,
"loss": 0.0552,
"step": 800
},
{
"epoch": 2.15,
"eval_runtime": 113.7453,
"eval_samples_per_second": 2.752,
"eval_steps_per_second": 0.176,
"step": 800
},
{
"epoch": 2.69,
"learning_rate": 0.0002,
"loss": 0.0418,
"step": 1000
},
{
"epoch": 2.69,
"eval_runtime": 113.7299,
"eval_samples_per_second": 2.752,
"eval_steps_per_second": 0.176,
"step": 1000
},
{
"epoch": 3.23,
"learning_rate": 0.0002,
"loss": 0.0396,
"step": 1200
},
{
"epoch": 3.23,
"eval_runtime": 113.7472,
"eval_samples_per_second": 2.752,
"eval_steps_per_second": 0.176,
"step": 1200
},
{
"epoch": 3.76,
"learning_rate": 0.0002,
"loss": 0.0333,
"step": 1400
},
{
"epoch": 3.76,
"eval_runtime": 113.6577,
"eval_samples_per_second": 2.754,
"eval_steps_per_second": 0.176,
"step": 1400
},
{
"epoch": 4.3,
"learning_rate": 0.0002,
"loss": 0.0303,
"step": 1600
},
{
"epoch": 4.3,
"eval_runtime": 113.7892,
"eval_samples_per_second": 2.751,
"eval_steps_per_second": 0.176,
"step": 1600
},
{
"epoch": 4.84,
"learning_rate": 0.0002,
"loss": 0.028,
"step": 1800
},
{
"epoch": 4.84,
"eval_runtime": 113.8547,
"eval_samples_per_second": 2.749,
"eval_steps_per_second": 0.176,
"step": 1800
},
{
"epoch": 5.38,
"learning_rate": 0.0002,
"loss": 0.0255,
"step": 2000
},
{
"epoch": 5.38,
"eval_runtime": 113.7853,
"eval_samples_per_second": 2.751,
"eval_steps_per_second": 0.176,
"step": 2000
},
{
"epoch": 5.91,
"learning_rate": 0.0002,
"loss": 0.0259,
"step": 2200
},
{
"epoch": 5.91,
"eval_runtime": 113.6789,
"eval_samples_per_second": 2.753,
"eval_steps_per_second": 0.176,
"step": 2200
}
],
"logging_steps": 200,
"max_steps": 2232,
"num_train_epochs": 6,
"save_steps": 200,
"total_flos": 1.048086317730816e+18,
"trial_name": null,
"trial_params": null
}
|