File size: 3,521 Bytes
3047c05 |
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 |
{
"best_metric": 0.39891308546066284,
"best_model_checkpoint": "distilbert_add_GLUE_Experiment_logit_kd_qnli_256/checkpoint-1230",
"epoch": 8.0,
"global_step": 3280,
"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": 0.4156,
"step": 410
},
{
"epoch": 1.0,
"eval_accuracy": 0.5053999633900788,
"eval_loss": 0.4111415147781372,
"eval_runtime": 5.3768,
"eval_samples_per_second": 1016.031,
"eval_steps_per_second": 4.092,
"step": 410
},
{
"epoch": 2.0,
"learning_rate": 4.8e-05,
"loss": 0.4078,
"step": 820
},
{
"epoch": 2.0,
"eval_accuracy": 0.5799011532125206,
"eval_loss": 0.4018184542655945,
"eval_runtime": 5.3514,
"eval_samples_per_second": 1020.846,
"eval_steps_per_second": 4.111,
"step": 820
},
{
"epoch": 3.0,
"learning_rate": 4.7e-05,
"loss": 0.3962,
"step": 1230
},
{
"epoch": 3.0,
"eval_accuracy": 0.5874061870766978,
"eval_loss": 0.39891308546066284,
"eval_runtime": 5.3383,
"eval_samples_per_second": 1023.358,
"eval_steps_per_second": 4.121,
"step": 1230
},
{
"epoch": 4.0,
"learning_rate": 4.600000000000001e-05,
"loss": 0.3899,
"step": 1640
},
{
"epoch": 4.0,
"eval_accuracy": 0.5866739886509243,
"eval_loss": 0.40177708864212036,
"eval_runtime": 5.3395,
"eval_samples_per_second": 1023.138,
"eval_steps_per_second": 4.12,
"step": 1640
},
{
"epoch": 5.0,
"learning_rate": 4.5e-05,
"loss": 0.3851,
"step": 2050
},
{
"epoch": 5.0,
"eval_accuracy": 0.5799011532125206,
"eval_loss": 0.4032135009765625,
"eval_runtime": 5.3369,
"eval_samples_per_second": 1023.624,
"eval_steps_per_second": 4.122,
"step": 2050
},
{
"epoch": 6.0,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.3802,
"step": 2460
},
{
"epoch": 6.0,
"eval_accuracy": 0.5727622185612301,
"eval_loss": 0.4117971658706665,
"eval_runtime": 5.4272,
"eval_samples_per_second": 1006.599,
"eval_steps_per_second": 4.054,
"step": 2460
},
{
"epoch": 7.0,
"learning_rate": 4.3e-05,
"loss": 0.3762,
"step": 2870
},
{
"epoch": 7.0,
"eval_accuracy": 0.5718469705290133,
"eval_loss": 0.4092874228954315,
"eval_runtime": 5.3443,
"eval_samples_per_second": 1022.211,
"eval_steps_per_second": 4.117,
"step": 2870
},
{
"epoch": 8.0,
"learning_rate": 4.2e-05,
"loss": 0.3717,
"step": 3280
},
{
"epoch": 8.0,
"eval_accuracy": 0.5736774665934469,
"eval_loss": 0.40997278690338135,
"eval_runtime": 5.339,
"eval_samples_per_second": 1023.223,
"eval_steps_per_second": 4.121,
"step": 3280
},
{
"epoch": 8.0,
"step": 3280,
"total_flos": 1.3806149824413696e+16,
"train_loss": 0.39033554356272626,
"train_runtime": 1120.6278,
"train_samples_per_second": 4673.407,
"train_steps_per_second": 18.293
}
],
"max_steps": 20500,
"num_train_epochs": 50,
"total_flos": 1.3806149824413696e+16,
"trial_name": null,
"trial_params": null
}
|