File size: 5,636 Bytes
90a72b2 | 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": 92,
"best_metric": 2.3479087352752686,
"best_model_checkpoint": "tiny_bert_km_5_v2_stsb/checkpoint-92",
"epoch": 9.0,
"eval_steps": 500,
"global_step": 207,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 3.2017595767974854,
"learning_rate": 4.9e-05,
"loss": 2.7925,
"step": 23
},
{
"epoch": 1.0,
"eval_combined_score": 0.11189326293514337,
"eval_loss": 2.3609859943389893,
"eval_pearson": 0.11928981153434301,
"eval_runtime": 0.4356,
"eval_samples_per_second": 3443.807,
"eval_spearmanr": 0.10449671433594372,
"eval_steps_per_second": 13.775,
"step": 23
},
{
"epoch": 2.0,
"grad_norm": 3.0342791080474854,
"learning_rate": 4.8e-05,
"loss": 2.0233,
"step": 46
},
{
"epoch": 2.0,
"eval_combined_score": 0.10503262884435496,
"eval_loss": 2.7264516353607178,
"eval_pearson": 0.10536681667826245,
"eval_runtime": 0.4819,
"eval_samples_per_second": 3112.724,
"eval_spearmanr": 0.10469844101044747,
"eval_steps_per_second": 12.451,
"step": 46
},
{
"epoch": 3.0,
"grad_norm": 3.3021488189697266,
"learning_rate": 4.7e-05,
"loss": 1.9375,
"step": 69
},
{
"epoch": 3.0,
"eval_combined_score": 0.15795839329801392,
"eval_loss": 2.3723838329315186,
"eval_pearson": 0.16413878451371774,
"eval_runtime": 0.5006,
"eval_samples_per_second": 2996.464,
"eval_spearmanr": 0.15177800208231013,
"eval_steps_per_second": 11.986,
"step": 69
},
{
"epoch": 4.0,
"grad_norm": 12.65180778503418,
"learning_rate": 4.600000000000001e-05,
"loss": 1.8081,
"step": 92
},
{
"epoch": 4.0,
"eval_combined_score": 0.21473410605933732,
"eval_loss": 2.3479087352752686,
"eval_pearson": 0.22084416872448345,
"eval_runtime": 0.4472,
"eval_samples_per_second": 3353.842,
"eval_spearmanr": 0.2086240433941912,
"eval_steps_per_second": 13.415,
"step": 92
},
{
"epoch": 5.0,
"grad_norm": 14.563904762268066,
"learning_rate": 4.5e-05,
"loss": 1.593,
"step": 115
},
{
"epoch": 5.0,
"eval_combined_score": 0.2341727272115602,
"eval_loss": 2.5032310485839844,
"eval_pearson": 0.23463414846011482,
"eval_runtime": 0.4639,
"eval_samples_per_second": 3233.596,
"eval_spearmanr": 0.2337113059630056,
"eval_steps_per_second": 12.934,
"step": 115
},
{
"epoch": 6.0,
"grad_norm": 16.085830688476562,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.4271,
"step": 138
},
{
"epoch": 6.0,
"eval_combined_score": 0.2668894994914338,
"eval_loss": 2.3829503059387207,
"eval_pearson": 0.2663211377699541,
"eval_runtime": 0.461,
"eval_samples_per_second": 3253.99,
"eval_spearmanr": 0.26745786121291354,
"eval_steps_per_second": 13.016,
"step": 138
},
{
"epoch": 7.0,
"grad_norm": 17.25328826904297,
"learning_rate": 4.3e-05,
"loss": 1.2196,
"step": 161
},
{
"epoch": 7.0,
"eval_combined_score": 0.3036982340745887,
"eval_loss": 2.367271900177002,
"eval_pearson": 0.3016266607369947,
"eval_runtime": 0.4595,
"eval_samples_per_second": 3264.444,
"eval_spearmanr": 0.3057698074121827,
"eval_steps_per_second": 13.058,
"step": 161
},
{
"epoch": 8.0,
"grad_norm": 19.59164810180664,
"learning_rate": 4.2e-05,
"loss": 1.0511,
"step": 184
},
{
"epoch": 8.0,
"eval_combined_score": 0.29420108006699475,
"eval_loss": 2.502896785736084,
"eval_pearson": 0.2914824122831241,
"eval_runtime": 0.5124,
"eval_samples_per_second": 2927.296,
"eval_spearmanr": 0.2969197478508654,
"eval_steps_per_second": 11.709,
"step": 184
},
{
"epoch": 9.0,
"grad_norm": 13.128865242004395,
"learning_rate": 4.1e-05,
"loss": 0.9721,
"step": 207
},
{
"epoch": 9.0,
"eval_combined_score": 0.29443550792517503,
"eval_loss": 2.524557113647461,
"eval_pearson": 0.2911705345450899,
"eval_runtime": 0.4558,
"eval_samples_per_second": 3290.86,
"eval_spearmanr": 0.29770048130526017,
"eval_steps_per_second": 13.163,
"step": 207
},
{
"epoch": 9.0,
"step": 207,
"total_flos": 1356793384840704.0,
"train_loss": 1.6471541676544337,
"train_runtime": 37.5069,
"train_samples_per_second": 7663.93,
"train_steps_per_second": 30.661
}
],
"logging_steps": 1,
"max_steps": 1150,
"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": 1356793384840704.0,
"train_batch_size": 256,
"trial_name": null,
"trial_params": null
}
|