File size: 4,286 Bytes
57eb330 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 12.0,
"eval_steps": 500,
"global_step": 2544,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 0.00019900471698113207,
"loss": 6.1329,
"step": 212
},
{
"epoch": 1.0,
"eval_loss": 5.14426851272583,
"eval_runtime": 3.8194,
"eval_samples_per_second": 176.991,
"eval_steps_per_second": 22.255,
"step": 212
},
{
"epoch": 2.0,
"learning_rate": 0.00019800471698113207,
"loss": 4.6548,
"step": 424
},
{
"epoch": 2.0,
"eval_loss": 3.559998035430908,
"eval_runtime": 3.8713,
"eval_samples_per_second": 174.616,
"eval_steps_per_second": 21.956,
"step": 424
},
{
"epoch": 3.0,
"learning_rate": 0.00019700471698113207,
"loss": 3.2979,
"step": 636
},
{
"epoch": 3.0,
"eval_loss": 2.3220388889312744,
"eval_runtime": 3.7585,
"eval_samples_per_second": 179.86,
"eval_steps_per_second": 22.616,
"step": 636
},
{
"epoch": 4.0,
"learning_rate": 0.00019600471698113207,
"loss": 2.2394,
"step": 848
},
{
"epoch": 4.0,
"eval_loss": 1.5198729038238525,
"eval_runtime": 3.8733,
"eval_samples_per_second": 174.529,
"eval_steps_per_second": 21.945,
"step": 848
},
{
"epoch": 5.0,
"learning_rate": 0.00019500471698113208,
"loss": 1.5436,
"step": 1060
},
{
"epoch": 5.0,
"eval_loss": 1.0844509601593018,
"eval_runtime": 3.7882,
"eval_samples_per_second": 178.45,
"eval_steps_per_second": 22.438,
"step": 1060
},
{
"epoch": 6.0,
"learning_rate": 0.0001940047169811321,
"loss": 1.1087,
"step": 1272
},
{
"epoch": 6.0,
"eval_loss": 0.8275050520896912,
"eval_runtime": 3.8596,
"eval_samples_per_second": 175.146,
"eval_steps_per_second": 22.023,
"step": 1272
},
{
"epoch": 7.0,
"learning_rate": 0.00019300943396226416,
"loss": 0.8094,
"step": 1484
},
{
"epoch": 7.0,
"eval_loss": 0.6410268545150757,
"eval_runtime": 3.826,
"eval_samples_per_second": 176.686,
"eval_steps_per_second": 22.216,
"step": 1484
},
{
"epoch": 8.0,
"learning_rate": 0.00019200943396226417,
"loss": 0.5999,
"step": 1696
},
{
"epoch": 8.0,
"eval_loss": 0.5242534279823303,
"eval_runtime": 3.7888,
"eval_samples_per_second": 178.42,
"eval_steps_per_second": 22.434,
"step": 1696
},
{
"epoch": 9.0,
"learning_rate": 0.00019100943396226417,
"loss": 0.4333,
"step": 1908
},
{
"epoch": 9.0,
"eval_loss": 0.4525991678237915,
"eval_runtime": 3.7762,
"eval_samples_per_second": 179.014,
"eval_steps_per_second": 22.509,
"step": 1908
},
{
"epoch": 10.0,
"learning_rate": 0.00019000943396226417,
"loss": 0.3096,
"step": 2120
},
{
"epoch": 10.0,
"eval_loss": 0.3988202214241028,
"eval_runtime": 3.3771,
"eval_samples_per_second": 200.169,
"eval_steps_per_second": 25.169,
"step": 2120
},
{
"epoch": 11.0,
"learning_rate": 0.00018900943396226415,
"loss": 0.225,
"step": 2332
},
{
"epoch": 11.0,
"eval_loss": 0.37283995747566223,
"eval_runtime": 3.3836,
"eval_samples_per_second": 199.788,
"eval_steps_per_second": 25.121,
"step": 2332
},
{
"epoch": 12.0,
"learning_rate": 0.00018800943396226415,
"loss": 0.1484,
"step": 2544
},
{
"epoch": 12.0,
"eval_loss": 0.36433306336402893,
"eval_runtime": 3.9173,
"eval_samples_per_second": 172.567,
"eval_steps_per_second": 21.698,
"step": 2544
}
],
"logging_steps": 500,
"max_steps": 42400,
"num_train_epochs": 200,
"save_steps": 500,
"total_flos": 3419356374609576.0,
"trial_name": null,
"trial_params": null
}
|