File size: 6,336 Bytes
965c27f |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 |
{
"best_metric": 0.7884615384615384,
"best_model_checkpoint": "/home/ubuntu/utah/babylm-24/src/evaluation/results/finetune/DebertaV2-Base-10M_babylm-A/boolq/checkpoint-4716",
"epoch": 7.0,
"eval_steps": 500,
"global_step": 8253,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.42408821034775235,
"grad_norm": 4.898578643798828,
"learning_rate": 9.787955894826124e-06,
"loss": 0.669,
"step": 500
},
{
"epoch": 0.8481764206955047,
"grad_norm": 2.427595615386963,
"learning_rate": 9.575911789652248e-06,
"loss": 0.6535,
"step": 1000
},
{
"epoch": 1.0,
"eval_accuracy": 0.6513761281967163,
"eval_f1": 0.7812739831158864,
"eval_loss": 0.6350241899490356,
"eval_mcc": 0.1190648771022687,
"eval_runtime": 2.7173,
"eval_samples_per_second": 601.699,
"eval_steps_per_second": 75.442,
"step": 1179
},
{
"epoch": 1.272264631043257,
"grad_norm": 3.5514039993286133,
"learning_rate": 9.363867684478373e-06,
"loss": 0.6279,
"step": 1500
},
{
"epoch": 1.6963528413910094,
"grad_norm": 6.262450218200684,
"learning_rate": 9.151823579304497e-06,
"loss": 0.6019,
"step": 2000
},
{
"epoch": 2.0,
"eval_accuracy": 0.6446483135223389,
"eval_f1": 0.7172749391727494,
"eval_loss": 0.6267324090003967,
"eval_mcc": 0.23986158954968526,
"eval_runtime": 2.7281,
"eval_samples_per_second": 599.313,
"eval_steps_per_second": 75.143,
"step": 2358
},
{
"epoch": 2.1204410517387617,
"grad_norm": 10.400861740112305,
"learning_rate": 8.93977947413062e-06,
"loss": 0.5841,
"step": 2500
},
{
"epoch": 2.544529262086514,
"grad_norm": 6.1930718421936035,
"learning_rate": 8.727735368956744e-06,
"loss": 0.5239,
"step": 3000
},
{
"epoch": 2.9686174724342664,
"grad_norm": 9.404278755187988,
"learning_rate": 8.515691263782867e-06,
"loss": 0.5263,
"step": 3500
},
{
"epoch": 3.0,
"eval_accuracy": 0.6709480285644531,
"eval_f1": 0.738581146744412,
"eval_loss": 0.6594865322113037,
"eval_mcc": 0.2953818504855689,
"eval_runtime": 2.7221,
"eval_samples_per_second": 600.629,
"eval_steps_per_second": 75.308,
"step": 3537
},
{
"epoch": 3.392705682782019,
"grad_norm": 8.5890474319458,
"learning_rate": 8.303647158608991e-06,
"loss": 0.4231,
"step": 4000
},
{
"epoch": 3.816793893129771,
"grad_norm": 19.422046661376953,
"learning_rate": 8.091603053435115e-06,
"loss": 0.4158,
"step": 4500
},
{
"epoch": 4.0,
"eval_accuracy": 0.7039755582809448,
"eval_f1": 0.7884615384615384,
"eval_loss": 0.7751796245574951,
"eval_mcc": 0.3197717100660696,
"eval_runtime": 2.7784,
"eval_samples_per_second": 588.466,
"eval_steps_per_second": 73.783,
"step": 4716
},
{
"epoch": 4.2408821034775235,
"grad_norm": 26.661087036132812,
"learning_rate": 7.879558948261238e-06,
"loss": 0.3625,
"step": 5000
},
{
"epoch": 4.664970313825275,
"grad_norm": 7.987252235412598,
"learning_rate": 7.667514843087362e-06,
"loss": 0.3286,
"step": 5500
},
{
"epoch": 5.0,
"eval_accuracy": 0.6856269240379333,
"eval_f1": 0.7485322896281801,
"eval_loss": 1.1917099952697754,
"eval_mcc": 0.3306542824781416,
"eval_runtime": 2.7099,
"eval_samples_per_second": 603.332,
"eval_steps_per_second": 75.647,
"step": 5895
},
{
"epoch": 5.089058524173028,
"grad_norm": 18.63119125366211,
"learning_rate": 7.455470737913486e-06,
"loss": 0.3092,
"step": 6000
},
{
"epoch": 5.51314673452078,
"grad_norm": 19.191608428955078,
"learning_rate": 7.2434266327396106e-06,
"loss": 0.2618,
"step": 6500
},
{
"epoch": 5.937234944868533,
"grad_norm": 2.243471145629883,
"learning_rate": 7.031382527565734e-06,
"loss": 0.2755,
"step": 7000
},
{
"epoch": 6.0,
"eval_accuracy": 0.6764525771141052,
"eval_f1": 0.7428293631502187,
"eval_loss": 1.446665644645691,
"eval_mcc": 0.3074619968336629,
"eval_runtime": 2.7032,
"eval_samples_per_second": 604.829,
"eval_steps_per_second": 75.835,
"step": 7074
},
{
"epoch": 6.361323155216285,
"grad_norm": 37.863040924072266,
"learning_rate": 6.819338422391858e-06,
"loss": 0.2147,
"step": 7500
},
{
"epoch": 6.785411365564038,
"grad_norm": 12.277471542358398,
"learning_rate": 6.607294317217981e-06,
"loss": 0.2273,
"step": 8000
},
{
"epoch": 7.0,
"eval_accuracy": 0.6709480285644531,
"eval_f1": 0.7307307307307307,
"eval_loss": 1.8949030637741089,
"eval_mcc": 0.31265280298270903,
"eval_runtime": 2.7263,
"eval_samples_per_second": 599.708,
"eval_steps_per_second": 75.193,
"step": 8253
},
{
"epoch": 7.0,
"step": 8253,
"total_flos": 3893201765612544.0,
"train_loss": 0.43125597612793976,
"train_runtime": 554.1638,
"train_samples_per_second": 340.224,
"train_steps_per_second": 42.551
}
],
"logging_steps": 500,
"max_steps": 23580,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 3,
"early_stopping_threshold": 0.001
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3893201765612544.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}
|