File size: 5,607 Bytes
f034bed |
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 |
{
"best_metric": 0.8986041101202016,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-4515",
"epoch": 9.0,
"eval_steps": 500,
"global_step": 5805,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 0.770919680595398,
"learning_rate": 0.00045575725544182215,
"loss": 0.2361,
"step": 645
},
{
"epoch": 1.0,
"eval_accuracy": 0.8898797983714618,
"eval_f1": 0.003508771929824561,
"eval_loss": 0.22947192192077637,
"eval_mcc": 0.039546160983878816,
"eval_precision": 1.0,
"eval_recall": 0.0017574692442882249,
"eval_runtime": 9.9701,
"eval_samples_per_second": 517.345,
"eval_steps_per_second": 16.249,
"step": 645
},
{
"epoch": 2.0,
"grad_norm": 0.8797195553779602,
"learning_rate": 0.00040511756039273084,
"loss": 0.2287,
"step": 1290
},
{
"epoch": 2.0,
"eval_accuracy": 0.8896859247770453,
"eval_f1": 0.0,
"eval_loss": 0.22863532602787018,
"eval_mcc": 0.0,
"eval_precision": 0.0,
"eval_recall": 0.0,
"eval_runtime": 10.133,
"eval_samples_per_second": 509.028,
"eval_steps_per_second": 15.987,
"step": 1290
},
{
"epoch": 3.0,
"grad_norm": 0.5287452340126038,
"learning_rate": 0.0003544778653436394,
"loss": 0.2263,
"step": 1935
},
{
"epoch": 3.0,
"eval_accuracy": 0.8896859247770453,
"eval_f1": 0.0,
"eval_loss": 0.2284112125635147,
"eval_mcc": 0.0,
"eval_precision": 0.0,
"eval_recall": 0.0,
"eval_runtime": 9.9193,
"eval_samples_per_second": 519.998,
"eval_steps_per_second": 16.332,
"step": 1935
},
{
"epoch": 4.0,
"grad_norm": 1.02663254737854,
"learning_rate": 0.0003038381702945481,
"loss": 0.2233,
"step": 2580
},
{
"epoch": 4.0,
"eval_accuracy": 0.8966653741760372,
"eval_f1": 0.19607843137254902,
"eval_loss": 0.2262517362833023,
"eval_mcc": 0.25274955080099837,
"eval_precision": 0.6914893617021277,
"eval_recall": 0.11423550087873462,
"eval_runtime": 9.9602,
"eval_samples_per_second": 517.859,
"eval_steps_per_second": 16.265,
"step": 2580
},
{
"epoch": 5.0,
"grad_norm": 0.33138540387153625,
"learning_rate": 0.00025319847524545675,
"loss": 0.2197,
"step": 3225
},
{
"epoch": 5.0,
"eval_accuracy": 0.8970531213648701,
"eval_f1": 0.18683001531393567,
"eval_loss": 0.21906551718711853,
"eval_mcc": 0.25294386512776135,
"eval_precision": 0.7261904761904762,
"eval_recall": 0.10720562390158173,
"eval_runtime": 9.9303,
"eval_samples_per_second": 519.421,
"eval_steps_per_second": 16.314,
"step": 3225
},
{
"epoch": 6.0,
"grad_norm": 0.3962567448616028,
"learning_rate": 0.00020255878019636542,
"loss": 0.2188,
"step": 3870
},
{
"epoch": 6.0,
"eval_accuracy": 0.8968592477704537,
"eval_f1": 0.1501597444089457,
"eval_loss": 0.21888957917690277,
"eval_mcc": 0.24100417515941616,
"eval_precision": 0.8245614035087719,
"eval_recall": 0.08260105448154657,
"eval_runtime": 9.9381,
"eval_samples_per_second": 519.011,
"eval_steps_per_second": 16.301,
"step": 3870
},
{
"epoch": 7.0,
"grad_norm": 0.816288948059082,
"learning_rate": 0.00015191908514727406,
"loss": 0.217,
"step": 4515
},
{
"epoch": 7.0,
"eval_accuracy": 0.8986041101202016,
"eval_f1": 0.20877458396369136,
"eval_loss": 0.2174820899963379,
"eval_mcc": 0.27516569645731026,
"eval_precision": 0.75,
"eval_recall": 0.12126537785588752,
"eval_runtime": 9.926,
"eval_samples_per_second": 519.645,
"eval_steps_per_second": 16.321,
"step": 4515
},
{
"epoch": 8.0,
"grad_norm": 0.9780616760253906,
"learning_rate": 0.00010127939009818271,
"loss": 0.2152,
"step": 5160
},
{
"epoch": 8.0,
"eval_accuracy": 0.8972469949592865,
"eval_f1": 0.16927899686520376,
"eval_loss": 0.2163967788219452,
"eval_mcc": 0.2498815158419147,
"eval_precision": 0.782608695652174,
"eval_recall": 0.09490333919156414,
"eval_runtime": 9.9496,
"eval_samples_per_second": 518.41,
"eval_steps_per_second": 16.282,
"step": 5160
},
{
"epoch": 9.0,
"grad_norm": 0.3984989523887634,
"learning_rate": 5.0639695049091355e-05,
"loss": 0.2142,
"step": 5805
},
{
"epoch": 9.0,
"eval_accuracy": 0.8986041101202016,
"eval_f1": 0.22288261515601784,
"eval_loss": 0.21662580966949463,
"eval_mcc": 0.2797000424158355,
"eval_precision": 0.7211538461538461,
"eval_recall": 0.13181019332161686,
"eval_runtime": 9.9343,
"eval_samples_per_second": 519.211,
"eval_steps_per_second": 16.307,
"step": 5805
}
],
"logging_steps": 500,
"max_steps": 6450,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 14282482793400.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"alpha": 0.6185480031675171,
"learning_rate": 0.0005063969504909135,
"num_train_epochs": 10,
"temperature": 26
}
}
|