File size: 5,716 Bytes
c9cbdc2 |
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 |
{
"best_metric": 0.6829745596868885,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-1536",
"epoch": 9.0,
"eval_steps": 500,
"global_step": 1728,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 0.896482527256012,
"learning_rate": 2.4429947101690063e-05,
"loss": 0.3642,
"step": 192
},
{
"epoch": 1.0,
"eval_accuracy": 0.525440313111546,
"eval_f1": 0.14762741652021089,
"eval_loss": 0.33992624282836914,
"eval_mcc": 0.1099564814603399,
"eval_precision": 0.7241379310344828,
"eval_recall": 0.0821917808219178,
"eval_runtime": 66.5832,
"eval_samples_per_second": 15.349,
"eval_steps_per_second": 0.481,
"step": 192
},
{
"epoch": 2.0,
"grad_norm": 3.451338529586792,
"learning_rate": 2.1376203713978805e-05,
"loss": 0.3285,
"step": 384
},
{
"epoch": 2.0,
"eval_accuracy": 0.5753424657534246,
"eval_f1": 0.31761006289308175,
"eval_loss": 0.31206491589546204,
"eval_mcc": 0.2299532209711479,
"eval_precision": 0.808,
"eval_recall": 0.19765166340508805,
"eval_runtime": 66.7282,
"eval_samples_per_second": 15.316,
"eval_steps_per_second": 0.48,
"step": 384
},
{
"epoch": 3.0,
"grad_norm": 1.4082952737808228,
"learning_rate": 1.8322460326267547e-05,
"loss": 0.314,
"step": 576
},
{
"epoch": 3.0,
"eval_accuracy": 0.6526418786692759,
"eval_f1": 0.5310435931307793,
"eval_loss": 0.30446648597717285,
"eval_mcc": 0.3570476542530334,
"eval_precision": 0.8170731707317073,
"eval_recall": 0.3933463796477495,
"eval_runtime": 66.749,
"eval_samples_per_second": 15.311,
"eval_steps_per_second": 0.479,
"step": 576
},
{
"epoch": 4.0,
"grad_norm": 2.84216570854187,
"learning_rate": 1.526871693855629e-05,
"loss": 0.3104,
"step": 768
},
{
"epoch": 4.0,
"eval_accuracy": 0.6193737769080235,
"eval_f1": 0.44028776978417267,
"eval_loss": 0.303169846534729,
"eval_mcc": 0.3106911694942452,
"eval_precision": 0.8315217391304348,
"eval_recall": 0.299412915851272,
"eval_runtime": 66.7305,
"eval_samples_per_second": 15.315,
"eval_steps_per_second": 0.48,
"step": 768
},
{
"epoch": 5.0,
"grad_norm": 1.591246485710144,
"learning_rate": 1.2214973550845031e-05,
"loss": 0.3085,
"step": 960
},
{
"epoch": 5.0,
"eval_accuracy": 0.62720156555773,
"eval_f1": 0.4715672676837725,
"eval_loss": 0.301248162984848,
"eval_mcc": 0.31481519810966196,
"eval_precision": 0.8095238095238095,
"eval_recall": 0.33268101761252444,
"eval_runtime": 66.7765,
"eval_samples_per_second": 15.305,
"eval_steps_per_second": 0.479,
"step": 960
},
{
"epoch": 6.0,
"grad_norm": 2.543092966079712,
"learning_rate": 9.161230163133773e-06,
"loss": 0.3072,
"step": 1152
},
{
"epoch": 6.0,
"eval_accuracy": 0.6663405088062623,
"eval_f1": 0.5721455457967377,
"eval_loss": 0.3020024299621582,
"eval_mcc": 0.3705330895438953,
"eval_precision": 0.7972027972027972,
"eval_recall": 0.4461839530332681,
"eval_runtime": 66.3804,
"eval_samples_per_second": 15.396,
"eval_steps_per_second": 0.482,
"step": 1152
},
{
"epoch": 7.0,
"grad_norm": 1.1360045671463013,
"learning_rate": 6.107486775422516e-06,
"loss": 0.3054,
"step": 1344
},
{
"epoch": 7.0,
"eval_accuracy": 0.6761252446183953,
"eval_f1": 0.5867665418227216,
"eval_loss": 0.3013523519039154,
"eval_mcc": 0.39067710929989413,
"eval_precision": 0.8103448275862069,
"eval_recall": 0.4598825831702544,
"eval_runtime": 66.3545,
"eval_samples_per_second": 15.402,
"eval_steps_per_second": 0.482,
"step": 1344
},
{
"epoch": 8.0,
"grad_norm": 1.4480931758880615,
"learning_rate": 3.053743387711258e-06,
"loss": 0.3049,
"step": 1536
},
{
"epoch": 8.0,
"eval_accuracy": 0.6829745596868885,
"eval_f1": 0.6029411764705882,
"eval_loss": 0.3014501929283142,
"eval_mcc": 0.39988223338971185,
"eval_precision": 0.8065573770491803,
"eval_recall": 0.48140900195694714,
"eval_runtime": 66.4924,
"eval_samples_per_second": 15.37,
"eval_steps_per_second": 0.481,
"step": 1536
},
{
"epoch": 9.0,
"grad_norm": 1.073256015777588,
"learning_rate": 0.0,
"loss": 0.3037,
"step": 1728
},
{
"epoch": 9.0,
"eval_accuracy": 0.6663405088062623,
"eval_f1": 0.5678073510773131,
"eval_loss": 0.30004358291625977,
"eval_mcc": 0.37380065293537335,
"eval_precision": 0.8057553956834532,
"eval_recall": 0.4383561643835616,
"eval_runtime": 66.6207,
"eval_samples_per_second": 15.341,
"eval_steps_per_second": 0.48,
"step": 1728
}
],
"logging_steps": 500,
"max_steps": 1728,
"num_input_tokens_seen": 0,
"num_train_epochs": 9,
"save_steps": 500,
"total_flos": 2121256775520.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": {
"alpha": 0.4423735218743273,
"learning_rate": 2.748369048940132e-05,
"num_train_epochs": 9,
"per_device_train_batch_size": 16,
"temperature": 18
}
}
|