File size: 4,916 Bytes
472dab5 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 |
{
"best_metric": 0.4542507827281952,
"best_model_checkpoint": "mobilebert_add_GLUE_Experiment_sst2_128/checkpoint-3689",
"epoch": 12.0,
"global_step": 6324,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 4.9e-05,
"loss": 0.6677,
"step": 527
},
{
"epoch": 1.0,
"eval_accuracy": 0.5756880733944955,
"eval_loss": 0.677055299282074,
"eval_runtime": 1.7061,
"eval_samples_per_second": 511.104,
"eval_steps_per_second": 4.103,
"step": 527
},
{
"epoch": 2.0,
"learning_rate": 4.8e-05,
"loss": 0.5966,
"step": 1054
},
{
"epoch": 2.0,
"eval_accuracy": 0.5424311926605505,
"eval_loss": 0.7135030627250671,
"eval_runtime": 1.5325,
"eval_samples_per_second": 569.001,
"eval_steps_per_second": 4.568,
"step": 1054
},
{
"epoch": 3.0,
"learning_rate": 4.7e-05,
"loss": 0.5714,
"step": 1581
},
{
"epoch": 3.0,
"eval_accuracy": 0.555045871559633,
"eval_loss": 0.7271105647087097,
"eval_runtime": 1.5765,
"eval_samples_per_second": 553.131,
"eval_steps_per_second": 4.44,
"step": 1581
},
{
"epoch": 4.0,
"learning_rate": 4.600000000000001e-05,
"loss": 0.5573,
"step": 2108
},
{
"epoch": 4.0,
"eval_accuracy": 0.5619266055045872,
"eval_loss": 0.6891608238220215,
"eval_runtime": 1.5223,
"eval_samples_per_second": 572.828,
"eval_steps_per_second": 4.598,
"step": 2108
},
{
"epoch": 5.0,
"learning_rate": 4.5e-05,
"loss": 0.501,
"step": 2635
},
{
"epoch": 5.0,
"eval_accuracy": 0.7798165137614679,
"eval_loss": 0.45462021231651306,
"eval_runtime": 1.5903,
"eval_samples_per_second": 548.34,
"eval_steps_per_second": 4.402,
"step": 2635
},
{
"epoch": 6.0,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.2856,
"step": 3162
},
{
"epoch": 6.0,
"eval_accuracy": 0.805045871559633,
"eval_loss": 0.46127501130104065,
"eval_runtime": 1.5321,
"eval_samples_per_second": 569.164,
"eval_steps_per_second": 4.569,
"step": 3162
},
{
"epoch": 7.0,
"learning_rate": 4.3e-05,
"loss": 0.2288,
"step": 3689
},
{
"epoch": 7.0,
"eval_accuracy": 0.7981651376146789,
"eval_loss": 0.4542507827281952,
"eval_runtime": 1.5229,
"eval_samples_per_second": 572.609,
"eval_steps_per_second": 4.597,
"step": 3689
},
{
"epoch": 8.0,
"learning_rate": 4.2e-05,
"loss": 0.2027,
"step": 4216
},
{
"epoch": 8.0,
"eval_accuracy": 0.7993119266055045,
"eval_loss": 0.4661611020565033,
"eval_runtime": 1.5648,
"eval_samples_per_second": 557.264,
"eval_steps_per_second": 4.473,
"step": 4216
},
{
"epoch": 9.0,
"learning_rate": 4.1e-05,
"loss": 0.1883,
"step": 4743
},
{
"epoch": 9.0,
"eval_accuracy": 0.8038990825688074,
"eval_loss": 0.516830563545227,
"eval_runtime": 1.5219,
"eval_samples_per_second": 572.954,
"eval_steps_per_second": 4.599,
"step": 4743
},
{
"epoch": 10.0,
"learning_rate": 4e-05,
"loss": 0.1779,
"step": 5270
},
{
"epoch": 10.0,
"eval_accuracy": 0.7855504587155964,
"eval_loss": 0.5748016834259033,
"eval_runtime": 1.5164,
"eval_samples_per_second": 575.045,
"eval_steps_per_second": 4.616,
"step": 5270
},
{
"epoch": 11.0,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.1691,
"step": 5797
},
{
"epoch": 11.0,
"eval_accuracy": 0.8027522935779816,
"eval_loss": 0.5195825099945068,
"eval_runtime": 1.5266,
"eval_samples_per_second": 571.211,
"eval_steps_per_second": 4.585,
"step": 5797
},
{
"epoch": 12.0,
"learning_rate": 3.8e-05,
"loss": 0.1596,
"step": 6324
},
{
"epoch": 12.0,
"eval_accuracy": 0.7947247706422018,
"eval_loss": 0.5943012237548828,
"eval_runtime": 1.5592,
"eval_samples_per_second": 559.25,
"eval_steps_per_second": 4.489,
"step": 6324
},
{
"epoch": 12.0,
"step": 6324,
"total_flos": 1.9293579893538816e+16,
"train_loss": 0.3588200110110356,
"train_runtime": 4204.4171,
"train_samples_per_second": 800.931,
"train_steps_per_second": 6.267
}
],
"max_steps": 26350,
"num_train_epochs": 50,
"total_flos": 1.9293579893538816e+16,
"trial_name": null,
"trial_params": null
}
|