File size: 4,526 Bytes
3dfb65e | 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 | {
"best_metric": 0.8596623807901907,
"best_model_checkpoint": "./save_models/mrpc/roberta-base_lr5e-05_run0/checkpoint-1449",
"epoch": 10.0,
"eval_steps": 500,
"global_step": 2070,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.8010899182561307,
"eval_averaged_scores": 0.8262068735883505,
"eval_f1": 0.8513238289205703,
"eval_loss": 0.4088594615459442,
"eval_runtime": 0.8357,
"eval_samples_per_second": 439.143,
"eval_steps_per_second": 27.521,
"step": 207
},
{
"epoch": 2.0,
"eval_accuracy": 0.7602179836512262,
"eval_averaged_scores": 0.781009892726514,
"eval_f1": 0.8018018018018018,
"eval_loss": 0.4726070165634155,
"eval_runtime": 0.4955,
"eval_samples_per_second": 740.675,
"eval_steps_per_second": 46.418,
"step": 414
},
{
"epoch": 2.42,
"learning_rate": 4.0359897172236504e-05,
"loss": 0.4481,
"step": 500
},
{
"epoch": 3.0,
"eval_accuracy": 0.8283378746594006,
"eval_averaged_scores": 0.8527654285577706,
"eval_f1": 0.8771929824561405,
"eval_loss": 0.46944934129714966,
"eval_runtime": 0.4861,
"eval_samples_per_second": 754.978,
"eval_steps_per_second": 47.315,
"step": 621
},
{
"epoch": 4.0,
"eval_accuracy": 0.8365122615803815,
"eval_averaged_scores": 0.8587323212663813,
"eval_f1": 0.880952380952381,
"eval_loss": 0.716332197189331,
"eval_runtime": 0.4857,
"eval_samples_per_second": 755.614,
"eval_steps_per_second": 47.355,
"step": 828
},
{
"epoch": 4.83,
"learning_rate": 2.750642673521851e-05,
"loss": 0.2017,
"step": 1000
},
{
"epoch": 5.0,
"eval_accuracy": 0.8283378746594006,
"eval_averaged_scores": 0.8510426848246903,
"eval_f1": 0.87374749498998,
"eval_loss": 0.9263336658477783,
"eval_runtime": 0.4853,
"eval_samples_per_second": 756.307,
"eval_steps_per_second": 47.398,
"step": 1035
},
{
"epoch": 6.0,
"eval_accuracy": 0.8283378746594006,
"eval_averaged_scores": 0.8510426848246903,
"eval_f1": 0.87374749498998,
"eval_loss": 1.0142543315887451,
"eval_runtime": 0.4866,
"eval_samples_per_second": 754.169,
"eval_steps_per_second": 47.264,
"step": 1242
},
{
"epoch": 7.0,
"eval_accuracy": 0.8365122615803815,
"eval_averaged_scores": 0.8596623807901907,
"eval_f1": 0.8828125,
"eval_loss": 1.0171551704406738,
"eval_runtime": 0.4871,
"eval_samples_per_second": 753.373,
"eval_steps_per_second": 47.214,
"step": 1449
},
{
"epoch": 7.25,
"learning_rate": 1.4652956298200515e-05,
"loss": 0.0593,
"step": 1500
},
{
"epoch": 8.0,
"eval_accuracy": 0.8337874659400545,
"eval_averaged_scores": 0.8557714884810492,
"eval_f1": 0.8777555110220441,
"eval_loss": 1.0489568710327148,
"eval_runtime": 0.4847,
"eval_samples_per_second": 757.236,
"eval_steps_per_second": 47.456,
"step": 1656
},
{
"epoch": 9.0,
"eval_accuracy": 0.8337874659400545,
"eval_averaged_scores": 0.8569723184317168,
"eval_f1": 0.8801571709233792,
"eval_loss": 1.2099965810775757,
"eval_runtime": 0.4891,
"eval_samples_per_second": 750.402,
"eval_steps_per_second": 47.028,
"step": 1863
},
{
"epoch": 9.66,
"learning_rate": 1.7994858611825194e-06,
"loss": 0.0183,
"step": 2000
},
{
"epoch": 10.0,
"eval_accuracy": 0.8310626702997275,
"eval_averaged_scores": 0.8542665130154764,
"eval_f1": 0.8774703557312253,
"eval_loss": 1.2079670429229736,
"eval_runtime": 0.4843,
"eval_samples_per_second": 757.767,
"eval_steps_per_second": 47.489,
"step": 2070
},
{
"epoch": 10.0,
"step": 2070,
"total_flos": 1295111753354040.0,
"train_loss": 0.17568344080523737,
"train_runtime": 279.1119,
"train_samples_per_second": 118.268,
"train_steps_per_second": 7.416
}
],
"logging_steps": 500,
"max_steps": 2070,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 1295111753354040.0,
"trial_name": null,
"trial_params": null
}
|