File size: 3,499 Bytes
23fec4b |
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": 0.6930947303771973,
"best_model_checkpoint": "mobilebert_add_GLUE_Experiment_qnli_128/checkpoint-2457",
"epoch": 8.0,
"global_step": 6552,
"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": 0.6933,
"step": 819
},
{
"epoch": 1.0,
"eval_accuracy": 0.4946000366099213,
"eval_loss": 0.6931872367858887,
"eval_runtime": 9.484,
"eval_samples_per_second": 576.021,
"eval_steps_per_second": 4.534,
"step": 819
},
{
"epoch": 2.0,
"learning_rate": 4.8e-05,
"loss": 0.6932,
"step": 1638
},
{
"epoch": 2.0,
"eval_accuracy": 0.4946000366099213,
"eval_loss": 0.6932188868522644,
"eval_runtime": 9.4261,
"eval_samples_per_second": 579.563,
"eval_steps_per_second": 4.562,
"step": 1638
},
{
"epoch": 3.0,
"learning_rate": 4.7e-05,
"loss": 0.6932,
"step": 2457
},
{
"epoch": 3.0,
"eval_accuracy": 0.5053999633900788,
"eval_loss": 0.6930947303771973,
"eval_runtime": 9.4523,
"eval_samples_per_second": 577.956,
"eval_steps_per_second": 4.549,
"step": 2457
},
{
"epoch": 4.0,
"learning_rate": 4.600000000000001e-05,
"loss": 0.6932,
"step": 3276
},
{
"epoch": 4.0,
"eval_accuracy": 0.4946000366099213,
"eval_loss": 0.6932775974273682,
"eval_runtime": 9.6547,
"eval_samples_per_second": 565.836,
"eval_steps_per_second": 4.454,
"step": 3276
},
{
"epoch": 5.0,
"learning_rate": 4.5e-05,
"loss": 0.6932,
"step": 4095
},
{
"epoch": 5.0,
"eval_accuracy": 0.5053999633900788,
"eval_loss": 0.6931426525115967,
"eval_runtime": 9.4692,
"eval_samples_per_second": 576.924,
"eval_steps_per_second": 4.541,
"step": 4095
},
{
"epoch": 6.0,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.6932,
"step": 4914
},
{
"epoch": 6.0,
"eval_accuracy": 0.5053999633900788,
"eval_loss": 0.6931297779083252,
"eval_runtime": 9.4468,
"eval_samples_per_second": 578.291,
"eval_steps_per_second": 4.552,
"step": 4914
},
{
"epoch": 7.0,
"learning_rate": 4.3e-05,
"loss": 0.6932,
"step": 5733
},
{
"epoch": 7.0,
"eval_accuracy": 0.5053999633900788,
"eval_loss": 0.6931160688400269,
"eval_runtime": 9.568,
"eval_samples_per_second": 570.963,
"eval_steps_per_second": 4.494,
"step": 5733
},
{
"epoch": 8.0,
"learning_rate": 4.2e-05,
"loss": 0.6932,
"step": 6552
},
{
"epoch": 8.0,
"eval_accuracy": 0.5053999633900788,
"eval_loss": 0.6931292414665222,
"eval_runtime": 9.4706,
"eval_samples_per_second": 576.838,
"eval_steps_per_second": 4.54,
"step": 6552
},
{
"epoch": 8.0,
"step": 6552,
"total_flos": 2.0003934735171584e+16,
"train_loss": 0.6931800702552655,
"train_runtime": 4355.0892,
"train_samples_per_second": 1202.536,
"train_steps_per_second": 9.403
}
],
"max_steps": 40950,
"num_train_epochs": 50,
"total_flos": 2.0003934735171584e+16,
"trial_name": null,
"trial_params": null
}
|