File size: 5,122 Bytes
b74afca |
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 |
{
"best_metric": 0.7207920792079208,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-23/checkpoint-2376",
"epoch": 8.0,
"eval_steps": 500,
"global_step": 2376,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 1.666294813156128,
"learning_rate": 0.00034226276676608983,
"loss": 0.688,
"step": 297
},
{
"epoch": 1.0,
"eval_accuracy": 0.5900990099009901,
"eval_f1": 0.5389755011135857,
"eval_loss": 0.6901505589485168,
"eval_mcc": 0.18426952240167496,
"eval_precision": 0.6142131979695431,
"eval_recall": 0.4801587301587302,
"eval_runtime": 0.9313,
"eval_samples_per_second": 542.229,
"eval_steps_per_second": 17.18,
"step": 297
},
{
"epoch": 2.0,
"grad_norm": 1.4357942342758179,
"learning_rate": 0.00029336808579950554,
"loss": 0.6503,
"step": 594
},
{
"epoch": 2.0,
"eval_accuracy": 0.6237623762376238,
"eval_f1": 0.6895424836601307,
"eval_loss": 0.641117513179779,
"eval_mcc": 0.27448731892832257,
"eval_precision": 0.5861111111111111,
"eval_recall": 0.8373015873015873,
"eval_runtime": 0.9311,
"eval_samples_per_second": 542.381,
"eval_steps_per_second": 17.184,
"step": 594
},
{
"epoch": 3.0,
"grad_norm": 2.663438081741333,
"learning_rate": 0.0002444734048329213,
"loss": 0.6219,
"step": 891
},
{
"epoch": 3.0,
"eval_accuracy": 0.6455445544554456,
"eval_f1": 0.7098865478119936,
"eval_loss": 0.6294957995414734,
"eval_mcc": 0.32613098301912463,
"eval_precision": 0.6,
"eval_recall": 0.8690476190476191,
"eval_runtime": 0.9408,
"eval_samples_per_second": 536.754,
"eval_steps_per_second": 17.006,
"step": 891
},
{
"epoch": 4.0,
"grad_norm": 1.565063238143921,
"learning_rate": 0.00019557872386633703,
"loss": 0.5927,
"step": 1188
},
{
"epoch": 4.0,
"eval_accuracy": 0.700990099009901,
"eval_f1": 0.7392055267702936,
"eval_loss": 0.59776771068573,
"eval_mcc": 0.42132165499205354,
"eval_precision": 0.654434250764526,
"eval_recall": 0.8492063492063492,
"eval_runtime": 0.9309,
"eval_samples_per_second": 542.515,
"eval_steps_per_second": 17.189,
"step": 1188
},
{
"epoch": 5.0,
"grad_norm": 5.263581275939941,
"learning_rate": 0.00014668404289975277,
"loss": 0.5661,
"step": 1485
},
{
"epoch": 5.0,
"eval_accuracy": 0.7188118811881188,
"eval_f1": 0.7455197132616487,
"eval_loss": 0.560869574546814,
"eval_mcc": 0.44822084848200644,
"eval_precision": 0.6797385620915033,
"eval_recall": 0.8253968253968254,
"eval_runtime": 0.9261,
"eval_samples_per_second": 545.289,
"eval_steps_per_second": 17.276,
"step": 1485
},
{
"epoch": 6.0,
"grad_norm": 4.6163554191589355,
"learning_rate": 9.778936193316852e-05,
"loss": 0.5531,
"step": 1782
},
{
"epoch": 6.0,
"eval_accuracy": 0.7128712871287128,
"eval_f1": 0.7415329768270944,
"eval_loss": 0.5461980104446411,
"eval_mcc": 0.4372741452666515,
"eval_precision": 0.6731391585760518,
"eval_recall": 0.8253968253968254,
"eval_runtime": 0.9305,
"eval_samples_per_second": 542.701,
"eval_steps_per_second": 17.194,
"step": 1782
},
{
"epoch": 7.0,
"grad_norm": 2.3622937202453613,
"learning_rate": 4.889468096658426e-05,
"loss": 0.5399,
"step": 2079
},
{
"epoch": 7.0,
"eval_accuracy": 0.7148514851485148,
"eval_f1": 0.7464788732394366,
"eval_loss": 0.5450253486633301,
"eval_mcc": 0.44448710523745394,
"eval_precision": 0.6708860759493671,
"eval_recall": 0.8412698412698413,
"eval_runtime": 0.9357,
"eval_samples_per_second": 539.724,
"eval_steps_per_second": 17.1,
"step": 2079
},
{
"epoch": 8.0,
"grad_norm": 3.19594407081604,
"learning_rate": 0.0,
"loss": 0.5312,
"step": 2376
},
{
"epoch": 8.0,
"eval_accuracy": 0.7207920792079208,
"eval_f1": 0.7486631016042781,
"eval_loss": 0.5413804054260254,
"eval_mcc": 0.45352789496190093,
"eval_precision": 0.6796116504854369,
"eval_recall": 0.8333333333333334,
"eval_runtime": 0.9335,
"eval_samples_per_second": 540.958,
"eval_steps_per_second": 17.139,
"step": 2376
}
],
"logging_steps": 500,
"max_steps": 2376,
"num_input_tokens_seen": 0,
"num_train_epochs": 8,
"save_steps": 500,
"total_flos": 5845610127840.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"alpha": 0.9955244977733414,
"learning_rate": 0.00039115744773267407,
"num_train_epochs": 8,
"temperature": 44
}
}
|