File size: 4,235 Bytes
486c2fc |
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 |
{
"best_metric": 1.1504948139190674,
"best_model_checkpoint": "mobilebert_add_GLUE_Experiment_logit_kd_stsb_128/checkpoint-135",
"epoch": 8.0,
"global_step": 360,
"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": 2.524,
"step": 45
},
{
"epoch": 1.0,
"eval_combined_score": -0.01736734231487362,
"eval_loss": 1.360716700553894,
"eval_pearson": -0.00663663554659777,
"eval_runtime": 2.4294,
"eval_samples_per_second": 617.427,
"eval_spearmanr": -0.02809804908314947,
"eval_steps_per_second": 4.939,
"step": 45
},
{
"epoch": 2.0,
"learning_rate": 4.8e-05,
"loss": 1.0877,
"step": 90
},
{
"epoch": 2.0,
"eval_combined_score": 0.04715345879740872,
"eval_loss": 1.1729449033737183,
"eval_pearson": 0.04463194868937297,
"eval_runtime": 2.4375,
"eval_samples_per_second": 615.373,
"eval_spearmanr": 0.049674968905444455,
"eval_steps_per_second": 4.923,
"step": 90
},
{
"epoch": 3.0,
"learning_rate": 4.7e-05,
"loss": 1.0648,
"step": 135
},
{
"epoch": 3.0,
"eval_combined_score": 0.04421394291851102,
"eval_loss": 1.1504948139190674,
"eval_pearson": 0.04698914731414176,
"eval_runtime": 2.44,
"eval_samples_per_second": 614.756,
"eval_spearmanr": 0.041438738522880283,
"eval_steps_per_second": 4.918,
"step": 135
},
{
"epoch": 4.0,
"learning_rate": 4.600000000000001e-05,
"loss": 1.0737,
"step": 180
},
{
"epoch": 4.0,
"eval_combined_score": 0.046832979635148,
"eval_loss": 1.1564427614212036,
"eval_pearson": 0.04721941129058438,
"eval_runtime": 2.4235,
"eval_samples_per_second": 618.935,
"eval_spearmanr": 0.04644654797971162,
"eval_steps_per_second": 4.951,
"step": 180
},
{
"epoch": 5.0,
"learning_rate": 4.5e-05,
"loss": 1.0445,
"step": 225
},
{
"epoch": 5.0,
"eval_combined_score": 0.05520806466844213,
"eval_loss": 1.1971248388290405,
"eval_pearson": 0.052931152302893685,
"eval_runtime": 2.4387,
"eval_samples_per_second": 615.085,
"eval_spearmanr": 0.057484977033990574,
"eval_steps_per_second": 4.921,
"step": 225
},
{
"epoch": 6.0,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.0296,
"step": 270
},
{
"epoch": 6.0,
"eval_combined_score": 0.06521746724840925,
"eval_loss": 1.172328233718872,
"eval_pearson": 0.05777555561817145,
"eval_runtime": 2.424,
"eval_samples_per_second": 618.82,
"eval_spearmanr": 0.07265937887864705,
"eval_steps_per_second": 4.951,
"step": 270
},
{
"epoch": 7.0,
"learning_rate": 4.3e-05,
"loss": 1.026,
"step": 315
},
{
"epoch": 7.0,
"eval_combined_score": 0.06137059081122272,
"eval_loss": 1.2734508514404297,
"eval_pearson": 0.062103519281422596,
"eval_runtime": 2.4342,
"eval_samples_per_second": 616.228,
"eval_spearmanr": 0.06063766234102283,
"eval_steps_per_second": 4.93,
"step": 315
},
{
"epoch": 8.0,
"learning_rate": 4.2e-05,
"loss": 1.0216,
"step": 360
},
{
"epoch": 8.0,
"eval_combined_score": 0.06830693724297929,
"eval_loss": 1.221414566040039,
"eval_pearson": 0.06657556927592724,
"eval_runtime": 2.4254,
"eval_samples_per_second": 618.464,
"eval_spearmanr": 0.07003830521003132,
"eval_steps_per_second": 4.948,
"step": 360
},
{
"epoch": 8.0,
"step": 360,
"total_flos": 1097941280358400.0,
"train_loss": 1.2339968151516385,
"train_runtime": 263.7899,
"train_samples_per_second": 1089.693,
"train_steps_per_second": 8.53
}
],
"max_steps": 2250,
"num_train_epochs": 50,
"total_flos": 1097941280358400.0,
"trial_name": null,
"trial_params": null
}
|