File size: 5,547 Bytes
fd606ef | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 | {
"best_global_step": 60,
"best_metric": 0.5812366008758545,
"best_model_checkpoint": "tiny_bert_km_50_v2_mrpc/checkpoint-60",
"epoch": 9.0,
"eval_steps": 500,
"global_step": 135,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 0.7363313436508179,
"learning_rate": 4.9e-05,
"loss": 0.632,
"step": 15
},
{
"epoch": 1.0,
"eval_accuracy": 0.7034313725490197,
"eval_combined_score": 0.7601876983773843,
"eval_f1": 0.8169440242057489,
"eval_loss": 0.5975198149681091,
"eval_runtime": 0.1327,
"eval_samples_per_second": 3075.467,
"eval_steps_per_second": 15.076,
"step": 15
},
{
"epoch": 2.0,
"grad_norm": 1.268504023551941,
"learning_rate": 4.8e-05,
"loss": 0.5917,
"step": 30
},
{
"epoch": 2.0,
"eval_accuracy": 0.7132352941176471,
"eval_combined_score": 0.7691737008704828,
"eval_f1": 0.8251121076233184,
"eval_loss": 0.5832136273384094,
"eval_runtime": 0.1486,
"eval_samples_per_second": 2746.391,
"eval_steps_per_second": 13.463,
"step": 30
},
{
"epoch": 3.0,
"grad_norm": 1.0295687913894653,
"learning_rate": 4.7e-05,
"loss": 0.5638,
"step": 45
},
{
"epoch": 3.0,
"eval_accuracy": 0.7034313725490197,
"eval_combined_score": 0.7607382426654873,
"eval_f1": 0.8180451127819549,
"eval_loss": 0.5895337462425232,
"eval_runtime": 0.1302,
"eval_samples_per_second": 3134.825,
"eval_steps_per_second": 15.367,
"step": 45
},
{
"epoch": 4.0,
"grad_norm": 1.3483902215957642,
"learning_rate": 4.600000000000001e-05,
"loss": 0.5417,
"step": 60
},
{
"epoch": 4.0,
"eval_accuracy": 0.7181372549019608,
"eval_combined_score": 0.7696440551337176,
"eval_f1": 0.8211508553654744,
"eval_loss": 0.5812366008758545,
"eval_runtime": 0.1387,
"eval_samples_per_second": 2941.894,
"eval_steps_per_second": 14.421,
"step": 60
},
{
"epoch": 5.0,
"grad_norm": 1.3638129234313965,
"learning_rate": 4.5e-05,
"loss": 0.5019,
"step": 75
},
{
"epoch": 5.0,
"eval_accuracy": 0.7009803921568627,
"eval_combined_score": 0.7524194565285921,
"eval_f1": 0.8038585209003215,
"eval_loss": 0.5993048548698425,
"eval_runtime": 0.1529,
"eval_samples_per_second": 2667.691,
"eval_steps_per_second": 13.077,
"step": 75
},
{
"epoch": 6.0,
"grad_norm": 1.534933090209961,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.4343,
"step": 90
},
{
"epoch": 6.0,
"eval_accuracy": 0.678921568627451,
"eval_combined_score": 0.7301118694556287,
"eval_f1": 0.7813021702838063,
"eval_loss": 0.620622456073761,
"eval_runtime": 0.1423,
"eval_samples_per_second": 2867.218,
"eval_steps_per_second": 14.055,
"step": 90
},
{
"epoch": 7.0,
"grad_norm": 2.426776885986328,
"learning_rate": 4.3e-05,
"loss": 0.3592,
"step": 105
},
{
"epoch": 7.0,
"eval_accuracy": 0.7083333333333334,
"eval_combined_score": 0.754501675041876,
"eval_f1": 0.8006700167504187,
"eval_loss": 0.6731041669845581,
"eval_runtime": 0.1344,
"eval_samples_per_second": 3035.9,
"eval_steps_per_second": 14.882,
"step": 105
},
{
"epoch": 8.0,
"grad_norm": 2.3238067626953125,
"learning_rate": 4.2e-05,
"loss": 0.2533,
"step": 120
},
{
"epoch": 8.0,
"eval_accuracy": 0.7009803921568627,
"eval_combined_score": 0.7508169934640523,
"eval_f1": 0.8006535947712419,
"eval_loss": 0.7867075800895691,
"eval_runtime": 0.1325,
"eval_samples_per_second": 3079.546,
"eval_steps_per_second": 15.096,
"step": 120
},
{
"epoch": 9.0,
"grad_norm": 2.622627019882202,
"learning_rate": 4.1e-05,
"loss": 0.1831,
"step": 135
},
{
"epoch": 9.0,
"eval_accuracy": 0.7034313725490197,
"eval_combined_score": 0.7517156862745098,
"eval_f1": 0.8,
"eval_loss": 0.8554521203041077,
"eval_runtime": 0.1556,
"eval_samples_per_second": 2622.352,
"eval_steps_per_second": 12.855,
"step": 135
},
{
"epoch": 9.0,
"step": 135,
"total_flos": 865692760633344.0,
"train_loss": 0.45122435004622846,
"train_runtime": 25.3703,
"train_samples_per_second": 7228.916,
"train_steps_per_second": 29.562
}
],
"logging_steps": 1,
"max_steps": 750,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 5
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 865692760633344.0,
"train_batch_size": 256,
"trial_name": null,
"trial_params": null
}
|