File size: 4,141 Bytes
31d07cc |
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": 0.3441176414489746,
"best_model_checkpoint": "distilbert_sa_GLUE_Experiment_logit_kd_wnli_96/checkpoint-15",
"epoch": 10.0,
"global_step": 30,
"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": 0.348,
"step": 3
},
{
"epoch": 1.0,
"eval_accuracy": 0.5633802816901409,
"eval_loss": 0.345082551240921,
"eval_runtime": 0.113,
"eval_samples_per_second": 628.265,
"eval_steps_per_second": 8.849,
"step": 3
},
{
"epoch": 2.0,
"learning_rate": 4.8e-05,
"loss": 0.3477,
"step": 6
},
{
"epoch": 2.0,
"eval_accuracy": 0.5633802816901409,
"eval_loss": 0.3447287976741791,
"eval_runtime": 0.1177,
"eval_samples_per_second": 603.052,
"eval_steps_per_second": 8.494,
"step": 6
},
{
"epoch": 3.0,
"learning_rate": 4.7e-05,
"loss": 0.3467,
"step": 9
},
{
"epoch": 3.0,
"eval_accuracy": 0.5633802816901409,
"eval_loss": 0.3444860577583313,
"eval_runtime": 0.1121,
"eval_samples_per_second": 633.302,
"eval_steps_per_second": 8.92,
"step": 9
},
{
"epoch": 4.0,
"learning_rate": 4.600000000000001e-05,
"loss": 0.3473,
"step": 12
},
{
"epoch": 4.0,
"eval_accuracy": 0.5633802816901409,
"eval_loss": 0.34416645765304565,
"eval_runtime": 0.1108,
"eval_samples_per_second": 641.052,
"eval_steps_per_second": 9.029,
"step": 12
},
{
"epoch": 5.0,
"learning_rate": 4.5e-05,
"loss": 0.3474,
"step": 15
},
{
"epoch": 5.0,
"eval_accuracy": 0.5633802816901409,
"eval_loss": 0.3441176414489746,
"eval_runtime": 0.1102,
"eval_samples_per_second": 644.292,
"eval_steps_per_second": 9.075,
"step": 15
},
{
"epoch": 6.0,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.3476,
"step": 18
},
{
"epoch": 6.0,
"eval_accuracy": 0.5633802816901409,
"eval_loss": 0.34430181980133057,
"eval_runtime": 0.1109,
"eval_samples_per_second": 640.012,
"eval_steps_per_second": 9.014,
"step": 18
},
{
"epoch": 7.0,
"learning_rate": 4.3e-05,
"loss": 0.3477,
"step": 21
},
{
"epoch": 7.0,
"eval_accuracy": 0.5633802816901409,
"eval_loss": 0.3445564806461334,
"eval_runtime": 0.1111,
"eval_samples_per_second": 638.78,
"eval_steps_per_second": 8.997,
"step": 21
},
{
"epoch": 8.0,
"learning_rate": 4.2e-05,
"loss": 0.347,
"step": 24
},
{
"epoch": 8.0,
"eval_accuracy": 0.5633802816901409,
"eval_loss": 0.3449000120162964,
"eval_runtime": 0.111,
"eval_samples_per_second": 639.483,
"eval_steps_per_second": 9.007,
"step": 24
},
{
"epoch": 9.0,
"learning_rate": 4.1e-05,
"loss": 0.3477,
"step": 27
},
{
"epoch": 9.0,
"eval_accuracy": 0.5633802816901409,
"eval_loss": 0.34510910511016846,
"eval_runtime": 0.1348,
"eval_samples_per_second": 526.598,
"eval_steps_per_second": 7.417,
"step": 27
},
{
"epoch": 10.0,
"learning_rate": 4e-05,
"loss": 0.3472,
"step": 30
},
{
"epoch": 10.0,
"eval_accuracy": 0.5633802816901409,
"eval_loss": 0.3452550768852234,
"eval_runtime": 0.1099,
"eval_samples_per_second": 645.899,
"eval_steps_per_second": 9.097,
"step": 30
},
{
"epoch": 10.0,
"step": 30,
"total_flos": 36999717191680.0,
"train_loss": 0.34743192195892336,
"train_runtime": 34.4199,
"train_samples_per_second": 922.431,
"train_steps_per_second": 4.358
}
],
"max_steps": 150,
"num_train_epochs": 50,
"total_flos": 36999717191680.0,
"trial_name": null,
"trial_params": null
}
|