File size: 8,461 Bytes
2bfe524 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 |
{
"best_global_step": 1500,
"best_metric": 0.7817611579593701,
"best_model_checkpoint": "./results/run-3/checkpoint-1500",
"epoch": 4.0,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.2,
"grad_norm": 0.3840266466140747,
"learning_rate": 5.623773985869002e-05,
"loss": 0.4015,
"step": 100
},
{
"epoch": 0.4,
"grad_norm": 36.44963455200195,
"learning_rate": 6.805455705058522e-05,
"loss": 0.0,
"step": 200
},
{
"epoch": 0.6,
"grad_norm": 0.6683640480041504,
"learning_rate": 6.718217457333122e-05,
"loss": 0.0,
"step": 300
},
{
"epoch": 0.8,
"grad_norm": 0.7861915230751038,
"learning_rate": 6.630979209607721e-05,
"loss": 0.1644,
"step": 400
},
{
"epoch": 1.0,
"grad_norm": 2.053349256515503,
"learning_rate": 6.54374096188232e-05,
"loss": 0.0025,
"step": 500
},
{
"epoch": 1.0,
"eval_economic_inequality_accuracy": 0.7770780856423174,
"eval_economic_inequality_f1": 0.6795991195482776,
"eval_economic_policy_benefits_accuracy": 0.8215488215488216,
"eval_economic_policy_benefits_f1": 0.7410643713786043,
"eval_ethnic_boundaries_accuracy": 0.946078431372549,
"eval_ethnic_boundaries_f1": 0.9198646713093299,
"eval_language_policy_accuracy": 0.6764705882352942,
"eval_language_policy_f1": 0.545923632610939,
"eval_loss": NaN,
"eval_mother_tongue_education_accuracy": 0.7777777777777778,
"eval_mother_tongue_education_f1": 0.6805555555555556,
"eval_overall_accuracy": 0.8064020197505432,
"eval_overall_f1": 0.7222001215424422,
"eval_religion_ethnic_identity_accuracy": 0.839458413926499,
"eval_religion_ethnic_identity_f1": 0.7661933788519465,
"eval_runtime": 4.4769,
"eval_samples_per_second": 893.468,
"eval_steps_per_second": 55.842,
"step": 500
},
{
"epoch": 1.2,
"grad_norm": 4.278098106384277,
"learning_rate": 6.456502714156919e-05,
"loss": 0.003,
"step": 600
},
{
"epoch": 1.4,
"grad_norm": 2.1036500930786133,
"learning_rate": 6.369264466431519e-05,
"loss": 0.0604,
"step": 700
},
{
"epoch": 1.6,
"grad_norm": 1.2531561851501465,
"learning_rate": 6.282026218706118e-05,
"loss": 0.0,
"step": 800
},
{
"epoch": 1.8,
"grad_norm": 1.4897408485412598,
"learning_rate": 6.194787970980717e-05,
"loss": 0.0114,
"step": 900
},
{
"epoch": 2.0,
"grad_norm": 1.9127349853515625,
"learning_rate": 6.107549723255315e-05,
"loss": 25991.0925,
"step": 1000
},
{
"epoch": 2.0,
"eval_economic_inequality_accuracy": 0.8224181360201511,
"eval_economic_inequality_f1": 0.7973444391161673,
"eval_economic_policy_benefits_accuracy": 0.8215488215488216,
"eval_economic_policy_benefits_f1": 0.7410643713786043,
"eval_ethnic_boundaries_accuracy": 0.9330065359477124,
"eval_ethnic_boundaries_f1": 0.9306378882302275,
"eval_language_policy_accuracy": 0.6764705882352942,
"eval_language_policy_f1": 0.545923632610939,
"eval_loss": NaN,
"eval_mother_tongue_education_accuracy": 0.7777777777777778,
"eval_mother_tongue_education_f1": 0.6805555555555556,
"eval_overall_accuracy": 0.8117800455760427,
"eval_overall_f1": 0.7478535187845178,
"eval_religion_ethnic_identity_accuracy": 0.839458413926499,
"eval_religion_ethnic_identity_f1": 0.7915952258156131,
"eval_runtime": 4.4757,
"eval_samples_per_second": 893.725,
"eval_steps_per_second": 55.858,
"step": 1000
},
{
"epoch": 2.2,
"grad_norm": 0.9552398324012756,
"learning_rate": 6.020311475529915e-05,
"loss": 0.0,
"step": 1100
},
{
"epoch": 2.4,
"grad_norm": 1.114319920539856,
"learning_rate": 5.9330732278045136e-05,
"loss": 0.0009,
"step": 1200
},
{
"epoch": 2.6,
"grad_norm": 0.16842737793922424,
"learning_rate": 5.845834980079113e-05,
"loss": 0.0,
"step": 1300
},
{
"epoch": 2.8,
"grad_norm": 1.0355138778686523,
"learning_rate": 5.758596732353712e-05,
"loss": 0.0638,
"step": 1400
},
{
"epoch": 3.0,
"grad_norm": 0.5731643438339233,
"learning_rate": 5.6713584846283115e-05,
"loss": 0.0,
"step": 1500
},
{
"epoch": 3.0,
"eval_economic_inequality_accuracy": 0.8224181360201511,
"eval_economic_inequality_f1": 0.7938100421450593,
"eval_economic_policy_benefits_accuracy": 0.8383838383838383,
"eval_economic_policy_benefits_f1": 0.8108014554114583,
"eval_ethnic_boundaries_accuracy": 0.9395424836601307,
"eval_ethnic_boundaries_f1": 0.9340440546398507,
"eval_language_policy_accuracy": 0.6764705882352942,
"eval_language_policy_f1": 0.6109373423468875,
"eval_loss": NaN,
"eval_mother_tongue_education_accuracy": 0.7777777777777778,
"eval_mother_tongue_education_f1": 0.7407407407407408,
"eval_overall_accuracy": 0.8150304610083521,
"eval_overall_f1": 0.7817611579593701,
"eval_religion_ethnic_identity_accuracy": 0.8355899419729207,
"eval_religion_ethnic_identity_f1": 0.8002333124722241,
"eval_runtime": 4.4858,
"eval_samples_per_second": 891.71,
"eval_steps_per_second": 55.732,
"step": 1500
},
{
"epoch": 3.2,
"grad_norm": 0.58502596616745,
"learning_rate": 5.58412023690291e-05,
"loss": 0.0013,
"step": 1600
},
{
"epoch": 3.4,
"grad_norm": 12.144497871398926,
"learning_rate": 5.49688198917751e-05,
"loss": 0.0,
"step": 1700
},
{
"epoch": 3.6,
"grad_norm": 0.9917765259742737,
"learning_rate": 5.4096437414521086e-05,
"loss": 0.1593,
"step": 1800
},
{
"epoch": 3.8,
"grad_norm": 0.2664477825164795,
"learning_rate": 5.3224054937267074e-05,
"loss": 0.0082,
"step": 1900
},
{
"epoch": 4.0,
"grad_norm": 0.33486196398735046,
"learning_rate": 5.235167246001307e-05,
"loss": 0.0,
"step": 2000
},
{
"epoch": 4.0,
"eval_economic_inequality_accuracy": 0.783375314861461,
"eval_economic_inequality_f1": 0.7832095348608167,
"eval_economic_policy_benefits_accuracy": 0.7845117845117845,
"eval_economic_policy_benefits_f1": 0.7745310880322321,
"eval_ethnic_boundaries_accuracy": 0.9101307189542484,
"eval_ethnic_boundaries_f1": 0.9195608338612992,
"eval_language_policy_accuracy": 0.6176470588235294,
"eval_language_policy_f1": 0.5673853251707923,
"eval_loss": NaN,
"eval_mother_tongue_education_accuracy": 0.7777777777777778,
"eval_mother_tongue_education_f1": 0.7407407407407408,
"eval_overall_accuracy": 0.780003176208314,
"eval_overall_f1": 0.7667330042293844,
"eval_religion_ethnic_identity_accuracy": 0.8065764023210832,
"eval_religion_ethnic_identity_f1": 0.8149705027104255,
"eval_runtime": 4.4762,
"eval_samples_per_second": 893.625,
"eval_steps_per_second": 55.852,
"step": 2000
}
],
"logging_steps": 100,
"max_steps": 8000,
"num_input_tokens_seen": 0,
"num_train_epochs": 16,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 2,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 1
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.6841526607872e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": {
"gradient_accumulation_steps": 4,
"learning_rate": 6.873501538284335e-05,
"num_train_epochs": 16,
"per_device_train_batch_size": 8,
"warmup_steps": 121,
"weight_decay": 0.08748775333302956
}
}
|