File size: 5,210 Bytes
c13e1d3 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 |
{
"best_metric": 0.25090140104293823,
"best_model_checkpoint": "/data/jcanete/all_results/mldoc/albeto_large/epochs_3_bs_16_lr_5e-6/checkpoint-1700",
"epoch": 3.0,
"global_step": 1776,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.17,
"eval_accuracy": 0.28299999237060547,
"eval_loss": 1.2837506532669067,
"eval_runtime": 8.1555,
"eval_samples_per_second": 122.617,
"eval_steps_per_second": 7.725,
"step": 100
},
{
"epoch": 0.34,
"eval_accuracy": 0.531000018119812,
"eval_loss": 1.1732338666915894,
"eval_runtime": 8.1951,
"eval_samples_per_second": 122.024,
"eval_steps_per_second": 7.688,
"step": 200
},
{
"epoch": 0.51,
"eval_accuracy": 0.5540000200271606,
"eval_loss": 0.9090207815170288,
"eval_runtime": 8.1405,
"eval_samples_per_second": 122.843,
"eval_steps_per_second": 7.739,
"step": 300
},
{
"epoch": 0.68,
"eval_accuracy": 0.5619999766349792,
"eval_loss": 0.8500489592552185,
"eval_runtime": 8.4022,
"eval_samples_per_second": 119.017,
"eval_steps_per_second": 7.498,
"step": 400
},
{
"epoch": 0.84,
"learning_rate": 3.603603603603604e-06,
"loss": 0.2667,
"step": 500
},
{
"epoch": 0.84,
"eval_accuracy": 0.6660000085830688,
"eval_loss": 0.7123118042945862,
"eval_runtime": 8.0822,
"eval_samples_per_second": 123.728,
"eval_steps_per_second": 7.795,
"step": 500
},
{
"epoch": 1.01,
"eval_accuracy": 0.7820000052452087,
"eval_loss": 0.6517438888549805,
"eval_runtime": 8.9908,
"eval_samples_per_second": 111.225,
"eval_steps_per_second": 7.007,
"step": 600
},
{
"epoch": 1.18,
"eval_accuracy": 0.8230000138282776,
"eval_loss": 0.5667398571968079,
"eval_runtime": 8.2149,
"eval_samples_per_second": 121.73,
"eval_steps_per_second": 7.669,
"step": 700
},
{
"epoch": 1.35,
"eval_accuracy": 0.8650000095367432,
"eval_loss": 0.47660863399505615,
"eval_runtime": 8.0853,
"eval_samples_per_second": 123.682,
"eval_steps_per_second": 7.792,
"step": 800
},
{
"epoch": 1.52,
"eval_accuracy": 0.8799999952316284,
"eval_loss": 0.38954979181289673,
"eval_runtime": 8.0289,
"eval_samples_per_second": 124.55,
"eval_steps_per_second": 7.847,
"step": 900
},
{
"epoch": 1.69,
"learning_rate": 2.195945945945946e-06,
"loss": 0.1264,
"step": 1000
},
{
"epoch": 1.69,
"eval_accuracy": 0.8420000076293945,
"eval_loss": 0.5382915139198303,
"eval_runtime": 8.0917,
"eval_samples_per_second": 123.584,
"eval_steps_per_second": 7.786,
"step": 1000
},
{
"epoch": 1.86,
"eval_accuracy": 0.9100000262260437,
"eval_loss": 0.36202001571655273,
"eval_runtime": 7.986,
"eval_samples_per_second": 125.219,
"eval_steps_per_second": 7.889,
"step": 1100
},
{
"epoch": 2.03,
"eval_accuracy": 0.9240000247955322,
"eval_loss": 0.3379409909248352,
"eval_runtime": 8.6218,
"eval_samples_per_second": 115.985,
"eval_steps_per_second": 7.307,
"step": 1200
},
{
"epoch": 2.2,
"eval_accuracy": 0.9279999732971191,
"eval_loss": 0.29248443245887756,
"eval_runtime": 8.2615,
"eval_samples_per_second": 121.044,
"eval_steps_per_second": 7.626,
"step": 1300
},
{
"epoch": 2.36,
"eval_accuracy": 0.9240000247955322,
"eval_loss": 0.28705379366874695,
"eval_runtime": 8.1584,
"eval_samples_per_second": 122.573,
"eval_steps_per_second": 7.722,
"step": 1400
},
{
"epoch": 2.53,
"learning_rate": 7.882882882882883e-07,
"loss": 0.0676,
"step": 1500
},
{
"epoch": 2.53,
"eval_accuracy": 0.9279999732971191,
"eval_loss": 0.2619408965110779,
"eval_runtime": 7.9492,
"eval_samples_per_second": 125.798,
"eval_steps_per_second": 7.925,
"step": 1500
},
{
"epoch": 2.7,
"eval_accuracy": 0.9279999732971191,
"eval_loss": 0.26721176505088806,
"eval_runtime": 7.9627,
"eval_samples_per_second": 125.585,
"eval_steps_per_second": 7.912,
"step": 1600
},
{
"epoch": 2.87,
"eval_accuracy": 0.9319999814033508,
"eval_loss": 0.25090140104293823,
"eval_runtime": 8.0714,
"eval_samples_per_second": 123.894,
"eval_steps_per_second": 7.805,
"step": 1700
},
{
"epoch": 3.0,
"step": 1776,
"total_flos": 982359617226624.0,
"train_loss": 0.13927180917413384,
"train_runtime": 1029.288,
"train_samples_per_second": 27.567,
"train_steps_per_second": 1.725
}
],
"max_steps": 1776,
"num_train_epochs": 3,
"total_flos": 982359617226624.0,
"trial_name": null,
"trial_params": null
}
|