File size: 4,258 Bytes
4c021c1 |
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 |
{
"best_metric": 0.4527376592159271,
"best_model_checkpoint": "hBERTv1_new_pretrain_w_init_48_qnli/checkpoint-4095",
"epoch": 10.0,
"global_step": 8190,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 3.9200000000000004e-05,
"loss": 0.615,
"step": 819
},
{
"epoch": 1.0,
"eval_accuracy": 0.7040087863811093,
"eval_loss": 0.5774398446083069,
"eval_runtime": 10.067,
"eval_samples_per_second": 542.663,
"eval_steps_per_second": 4.271,
"step": 819
},
{
"epoch": 2.0,
"learning_rate": 3.8400000000000005e-05,
"loss": 0.5092,
"step": 1638
},
{
"epoch": 2.0,
"eval_accuracy": 0.7818048691195314,
"eval_loss": 0.4735040068626404,
"eval_runtime": 10.1673,
"eval_samples_per_second": 537.309,
"eval_steps_per_second": 4.229,
"step": 1638
},
{
"epoch": 3.0,
"learning_rate": 3.76e-05,
"loss": 0.4554,
"step": 2457
},
{
"epoch": 3.0,
"eval_accuracy": 0.7861980596741717,
"eval_loss": 0.466993510723114,
"eval_runtime": 10.0759,
"eval_samples_per_second": 542.183,
"eval_steps_per_second": 4.268,
"step": 2457
},
{
"epoch": 4.0,
"learning_rate": 3.680000000000001e-05,
"loss": 0.4041,
"step": 3276
},
{
"epoch": 4.0,
"eval_accuracy": 0.7807065714808713,
"eval_loss": 0.4881279766559601,
"eval_runtime": 10.0028,
"eval_samples_per_second": 546.149,
"eval_steps_per_second": 4.299,
"step": 3276
},
{
"epoch": 5.0,
"learning_rate": 3.6e-05,
"loss": 0.3567,
"step": 4095
},
{
"epoch": 5.0,
"eval_accuracy": 0.7935200439319056,
"eval_loss": 0.4527376592159271,
"eval_runtime": 10.0559,
"eval_samples_per_second": 543.261,
"eval_steps_per_second": 4.276,
"step": 4095
},
{
"epoch": 6.0,
"learning_rate": 3.52e-05,
"loss": 0.3218,
"step": 4914
},
{
"epoch": 6.0,
"eval_accuracy": 0.7819879187259747,
"eval_loss": 0.5325487852096558,
"eval_runtime": 10.0427,
"eval_samples_per_second": 543.975,
"eval_steps_per_second": 4.282,
"step": 4914
},
{
"epoch": 7.0,
"learning_rate": 3.44e-05,
"loss": 0.2864,
"step": 5733
},
{
"epoch": 7.0,
"eval_accuracy": 0.7829031667581915,
"eval_loss": 0.5454465746879578,
"eval_runtime": 10.0511,
"eval_samples_per_second": 543.525,
"eval_steps_per_second": 4.278,
"step": 5733
},
{
"epoch": 8.0,
"learning_rate": 3.3600000000000004e-05,
"loss": 0.2482,
"step": 6552
},
{
"epoch": 8.0,
"eval_accuracy": 0.7700896943071572,
"eval_loss": 0.5525962114334106,
"eval_runtime": 10.0206,
"eval_samples_per_second": 545.178,
"eval_steps_per_second": 4.291,
"step": 6552
},
{
"epoch": 9.0,
"learning_rate": 3.28e-05,
"loss": 0.2146,
"step": 7371
},
{
"epoch": 9.0,
"eval_accuracy": 0.7834523155775215,
"eval_loss": 0.5931808948516846,
"eval_runtime": 10.0523,
"eval_samples_per_second": 543.455,
"eval_steps_per_second": 4.278,
"step": 7371
},
{
"epoch": 10.0,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.1825,
"step": 8190
},
{
"epoch": 10.0,
"eval_accuracy": 0.7752150832875709,
"eval_loss": 0.6240017414093018,
"eval_runtime": 10.0826,
"eval_samples_per_second": 541.827,
"eval_steps_per_second": 4.265,
"step": 8190
},
{
"epoch": 10.0,
"step": 8190,
"total_flos": 1.5512100096966656e+17,
"train_loss": 0.35937960372011885,
"train_runtime": 5750.0945,
"train_samples_per_second": 910.794,
"train_steps_per_second": 7.122
}
],
"max_steps": 40950,
"num_train_epochs": 50,
"total_flos": 1.5512100096966656e+17,
"trial_name": null,
"trial_params": null
}
|