File size: 5,756 Bytes
51c54b3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 | {
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 1000,
"global_step": 11562,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0001729804532087874,
"grad_norm": 7.4878644943237305,
"learning_rate": 0.0,
"loss": 3.5397,
"step": 1
},
{
"epoch": 0.1729804532087874,
"grad_norm": 5.6725382804870605,
"learning_rate": 3.452689846047397e-06,
"loss": 3.1143,
"step": 1000
},
{
"epoch": 0.1729804532087874,
"eval_cosine_accuracy": 0.9447891712188721,
"eval_loss": 1.529471516609192,
"eval_runtime": 20.6972,
"eval_samples_per_second": 459.435,
"eval_steps_per_second": 3.624,
"step": 1000
},
{
"epoch": 0.3459609064175748,
"grad_norm": 5.92240047454834,
"learning_rate": 6.912298910223145e-06,
"loss": 2.5164,
"step": 2000
},
{
"epoch": 0.3459609064175748,
"eval_cosine_accuracy": 0.9559364914894104,
"eval_loss": 1.4076837301254272,
"eval_runtime": 20.5209,
"eval_samples_per_second": 463.381,
"eval_steps_per_second": 3.655,
"step": 2000
},
{
"epoch": 0.5189413596263622,
"grad_norm": 6.010852336883545,
"learning_rate": 1.0371907974398893e-05,
"loss": 2.2667,
"step": 3000
},
{
"epoch": 0.5189413596263622,
"eval_cosine_accuracy": 0.9617204666137695,
"eval_loss": 1.3271853923797607,
"eval_runtime": 20.4455,
"eval_samples_per_second": 465.091,
"eval_steps_per_second": 3.668,
"step": 3000
},
{
"epoch": 0.6919218128351496,
"grad_norm": 5.722408771514893,
"learning_rate": 1.3831517038574642e-05,
"loss": 2.0664,
"step": 4000
},
{
"epoch": 0.6919218128351496,
"eval_cosine_accuracy": 0.9661373496055603,
"eval_loss": 1.262633204460144,
"eval_runtime": 20.4097,
"eval_samples_per_second": 465.906,
"eval_steps_per_second": 3.675,
"step": 4000
},
{
"epoch": 0.864902266043937,
"grad_norm": 5.409216403961182,
"learning_rate": 1.729112610275039e-05,
"loss": 1.9159,
"step": 5000
},
{
"epoch": 0.864902266043937,
"eval_cosine_accuracy": 0.9705542325973511,
"eval_loss": 1.195585012435913,
"eval_runtime": 20.7661,
"eval_samples_per_second": 457.91,
"eval_steps_per_second": 3.612,
"step": 5000
},
{
"epoch": 1.0378827192527245,
"grad_norm": 5.540963172912598,
"learning_rate": 1.9813181110534513e-05,
"loss": 1.7788,
"step": 6000
},
{
"epoch": 1.0378827192527245,
"eval_cosine_accuracy": 0.9710800051689148,
"eval_loss": 1.1745668649673462,
"eval_runtime": 21.9748,
"eval_samples_per_second": 432.723,
"eval_steps_per_second": 3.413,
"step": 6000
},
{
"epoch": 1.2108631724615118,
"grad_norm": 5.699978828430176,
"learning_rate": 1.8948278844490574e-05,
"loss": 1.6737,
"step": 7000
},
{
"epoch": 1.2108631724615118,
"eval_cosine_accuracy": 0.9727626442909241,
"eval_loss": 1.1350425481796265,
"eval_runtime": 20.6263,
"eval_samples_per_second": 461.014,
"eval_steps_per_second": 3.636,
"step": 7000
},
{
"epoch": 1.3838436256702993,
"grad_norm": 6.418245792388916,
"learning_rate": 1.8083376578446638e-05,
"loss": 1.5966,
"step": 8000
},
{
"epoch": 1.3838436256702993,
"eval_cosine_accuracy": 0.9716058373451233,
"eval_loss": 1.122388482093811,
"eval_runtime": 20.6692,
"eval_samples_per_second": 460.056,
"eval_steps_per_second": 3.629,
"step": 8000
},
{
"epoch": 1.5568240788790866,
"grad_norm": 5.495181083679199,
"learning_rate": 1.72184743124027e-05,
"loss": 1.535,
"step": 9000
},
{
"epoch": 1.5568240788790866,
"eval_cosine_accuracy": 0.9738143086433411,
"eval_loss": 1.0911048650741577,
"eval_runtime": 20.6637,
"eval_samples_per_second": 460.179,
"eval_steps_per_second": 3.63,
"step": 9000
},
{
"epoch": 1.729804532087874,
"grad_norm": 5.562320709228516,
"learning_rate": 1.6354436948624807e-05,
"loss": 1.4752,
"step": 10000
},
{
"epoch": 1.729804532087874,
"eval_cosine_accuracy": 0.9746555685997009,
"eval_loss": 1.0861026048660278,
"eval_runtime": 20.6157,
"eval_samples_per_second": 461.249,
"eval_steps_per_second": 3.638,
"step": 10000
},
{
"epoch": 1.9027849852966616,
"grad_norm": 5.75679349899292,
"learning_rate": 1.5489534682580868e-05,
"loss": 1.4419,
"step": 11000
},
{
"epoch": 1.9027849852966616,
"eval_cosine_accuracy": 0.9758123755455017,
"eval_loss": 1.0716735124588013,
"eval_runtime": 21.2666,
"eval_samples_per_second": 447.132,
"eval_steps_per_second": 3.527,
"step": 11000
}
],
"logging_steps": 1000,
"max_steps": 28905,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|