File size: 4,837 Bytes
82d1b2a | 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 | {
"best_metric": 0.9132375276225795,
"best_model_checkpoint": "./save_models/stsb/roberta-base_lr1e-05_run0/checkpoint-2916",
"epoch": 10.0,
"eval_steps": 500,
"global_step": 3240,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_averaged_scores": 0.8719844165680126,
"eval_loss": 0.5549536347389221,
"eval_pearson": 0.8792634862673233,
"eval_runtime": 1.0963,
"eval_samples_per_second": 524.504,
"eval_spearmanr": 0.8647053468687018,
"eval_steps_per_second": 32.838,
"step": 324
},
{
"epoch": 1.54,
"learning_rate": 8.998357963875205e-06,
"loss": 1.9846,
"step": 500
},
{
"epoch": 2.0,
"eval_averaged_scores": 0.8945047640614983,
"eval_loss": 0.603453516960144,
"eval_pearson": 0.9005924807835378,
"eval_runtime": 0.704,
"eval_samples_per_second": 816.784,
"eval_spearmanr": 0.8884170473394587,
"eval_steps_per_second": 51.138,
"step": 648
},
{
"epoch": 3.0,
"eval_averaged_scores": 0.9062316400464019,
"eval_loss": 0.4641549587249756,
"eval_pearson": 0.9128021174279124,
"eval_runtime": 0.7081,
"eval_samples_per_second": 811.986,
"eval_spearmanr": 0.8996611626648913,
"eval_steps_per_second": 50.837,
"step": 972
},
{
"epoch": 3.09,
"learning_rate": 7.35632183908046e-06,
"loss": 0.3739,
"step": 1000
},
{
"epoch": 4.0,
"eval_averaged_scores": 0.9065076507852758,
"eval_loss": 0.4377610683441162,
"eval_pearson": 0.9127118914783907,
"eval_runtime": 0.6286,
"eval_samples_per_second": 914.771,
"eval_spearmanr": 0.9003034100921611,
"eval_steps_per_second": 57.273,
"step": 1296
},
{
"epoch": 4.63,
"learning_rate": 5.7142857142857145e-06,
"loss": 0.2485,
"step": 1500
},
{
"epoch": 5.0,
"eval_averaged_scores": 0.908379700337028,
"eval_loss": 0.4117390811443329,
"eval_pearson": 0.9141856508223978,
"eval_runtime": 0.6332,
"eval_samples_per_second": 908.107,
"eval_spearmanr": 0.9025737498516583,
"eval_steps_per_second": 56.855,
"step": 1620
},
{
"epoch": 6.0,
"eval_averaged_scores": 0.9116822332416219,
"eval_loss": 0.4102296233177185,
"eval_pearson": 0.9173376535815415,
"eval_runtime": 0.617,
"eval_samples_per_second": 931.917,
"eval_spearmanr": 0.9060268129017023,
"eval_steps_per_second": 58.346,
"step": 1944
},
{
"epoch": 6.17,
"learning_rate": 4.072249589490969e-06,
"loss": 0.1894,
"step": 2000
},
{
"epoch": 7.0,
"eval_averaged_scores": 0.9117323593371983,
"eval_loss": 0.402465283870697,
"eval_pearson": 0.9170297139907337,
"eval_runtime": 0.6389,
"eval_samples_per_second": 899.99,
"eval_spearmanr": 0.9064350046836629,
"eval_steps_per_second": 56.347,
"step": 2268
},
{
"epoch": 7.72,
"learning_rate": 2.4302134646962236e-06,
"loss": 0.1519,
"step": 2500
},
{
"epoch": 8.0,
"eval_averaged_scores": 0.9119600828390606,
"eval_loss": 0.4155682921409607,
"eval_pearson": 0.9177323566058198,
"eval_runtime": 0.6403,
"eval_samples_per_second": 898.065,
"eval_spearmanr": 0.9061878090723013,
"eval_steps_per_second": 56.227,
"step": 2592
},
{
"epoch": 9.0,
"eval_averaged_scores": 0.9132375276225795,
"eval_loss": 0.39730867743492126,
"eval_pearson": 0.9183296123362426,
"eval_runtime": 0.6124,
"eval_samples_per_second": 938.861,
"eval_spearmanr": 0.9081454429089164,
"eval_steps_per_second": 58.781,
"step": 2916
},
{
"epoch": 9.26,
"learning_rate": 7.881773399014779e-07,
"loss": 0.1262,
"step": 3000
},
{
"epoch": 10.0,
"eval_averaged_scores": 0.9126844528170279,
"eval_loss": 0.41949743032455444,
"eval_pearson": 0.9177749306754028,
"eval_runtime": 0.6141,
"eval_samples_per_second": 936.342,
"eval_spearmanr": 0.907593974958653,
"eval_steps_per_second": 58.623,
"step": 3240
},
{
"epoch": 10.0,
"step": 3240,
"total_flos": 1693845460370892.0,
"train_loss": 0.4830472233854694,
"train_runtime": 291.8592,
"train_samples_per_second": 177.277,
"train_steps_per_second": 11.101
}
],
"logging_steps": 500,
"max_steps": 3240,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 1693845460370892.0,
"trial_name": null,
"trial_params": null
}
|