File size: 5,545 Bytes
af73dae | 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": 0.5893135666847229,
"best_model_checkpoint": "tiny_bert_km_10_v1_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": 0.7777377963066101,
"learning_rate": 4.9e-05,
"loss": 0.6324,
"step": 15
},
{
"epoch": 1.0,
"eval_accuracy": 0.7107843137254902,
"eval_combined_score": 0.7665367351759982,
"eval_f1": 0.822289156626506,
"eval_loss": 0.6063352227210999,
"eval_runtime": 0.1334,
"eval_samples_per_second": 3057.75,
"eval_steps_per_second": 14.989,
"step": 15
},
{
"epoch": 2.0,
"grad_norm": 1.288647174835205,
"learning_rate": 4.8e-05,
"loss": 0.596,
"step": 30
},
{
"epoch": 2.0,
"eval_accuracy": 0.7034313725490197,
"eval_combined_score": 0.7612822034643454,
"eval_f1": 0.8191330343796711,
"eval_loss": 0.5933586359024048,
"eval_runtime": 0.1309,
"eval_samples_per_second": 3116.868,
"eval_steps_per_second": 15.279,
"step": 30
},
{
"epoch": 3.0,
"grad_norm": 1.0193438529968262,
"learning_rate": 4.7e-05,
"loss": 0.5663,
"step": 45
},
{
"epoch": 3.0,
"eval_accuracy": 0.7083333333333334,
"eval_combined_score": 0.7641515380736259,
"eval_f1": 0.8199697428139183,
"eval_loss": 0.5923270583152771,
"eval_runtime": 0.1384,
"eval_samples_per_second": 2947.473,
"eval_steps_per_second": 14.448,
"step": 45
},
{
"epoch": 4.0,
"grad_norm": 1.2852709293365479,
"learning_rate": 4.600000000000001e-05,
"loss": 0.5449,
"step": 60
},
{
"epoch": 4.0,
"eval_accuracy": 0.7009803921568627,
"eval_combined_score": 0.7521030993042378,
"eval_f1": 0.8032258064516129,
"eval_loss": 0.5893135666847229,
"eval_runtime": 0.1389,
"eval_samples_per_second": 2937.399,
"eval_steps_per_second": 14.399,
"step": 60
},
{
"epoch": 5.0,
"grad_norm": 1.8828601837158203,
"learning_rate": 4.5e-05,
"loss": 0.4957,
"step": 75
},
{
"epoch": 5.0,
"eval_accuracy": 0.6568627450980392,
"eval_combined_score": 0.7034313725490196,
"eval_f1": 0.75,
"eval_loss": 0.630436897277832,
"eval_runtime": 0.1304,
"eval_samples_per_second": 3128.67,
"eval_steps_per_second": 15.337,
"step": 75
},
{
"epoch": 6.0,
"grad_norm": 1.855084776878357,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.4356,
"step": 90
},
{
"epoch": 6.0,
"eval_accuracy": 0.6936274509803921,
"eval_combined_score": 0.7403401309416441,
"eval_f1": 0.787052810902896,
"eval_loss": 0.6516110301017761,
"eval_runtime": 0.1294,
"eval_samples_per_second": 3153.752,
"eval_steps_per_second": 15.46,
"step": 90
},
{
"epoch": 7.0,
"grad_norm": 2.397104501724243,
"learning_rate": 4.3e-05,
"loss": 0.3509,
"step": 105
},
{
"epoch": 7.0,
"eval_accuracy": 0.6887254901960784,
"eval_combined_score": 0.7397498950156669,
"eval_f1": 0.7907742998352554,
"eval_loss": 0.7439402341842651,
"eval_runtime": 0.1343,
"eval_samples_per_second": 3037.258,
"eval_steps_per_second": 14.889,
"step": 105
},
{
"epoch": 8.0,
"grad_norm": 2.2138803005218506,
"learning_rate": 4.2e-05,
"loss": 0.2548,
"step": 120
},
{
"epoch": 8.0,
"eval_accuracy": 0.6617647058823529,
"eval_combined_score": 0.7085419274092616,
"eval_f1": 0.7553191489361702,
"eval_loss": 0.8599588871002197,
"eval_runtime": 0.1419,
"eval_samples_per_second": 2876.022,
"eval_steps_per_second": 14.098,
"step": 120
},
{
"epoch": 9.0,
"grad_norm": 2.5679445266723633,
"learning_rate": 4.1e-05,
"loss": 0.1693,
"step": 135
},
{
"epoch": 9.0,
"eval_accuracy": 0.6225490196078431,
"eval_combined_score": 0.668681917211329,
"eval_f1": 0.7148148148148148,
"eval_loss": 1.095586895942688,
"eval_runtime": 0.1285,
"eval_samples_per_second": 3174.615,
"eval_steps_per_second": 15.562,
"step": 135
},
{
"epoch": 9.0,
"step": 135,
"total_flos": 865692760633344.0,
"train_loss": 0.44955003173262986,
"train_runtime": 25.8086,
"train_samples_per_second": 7106.171,
"train_steps_per_second": 29.06
}
],
"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
}
|