File size: 11,420 Bytes
5aa6f84 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 |
{
"best_metric": 0.042461033910512924,
"best_model_checkpoint": "./teapotllm/checkpoint-876",
"epoch": 8.0,
"eval_steps": 500,
"global_step": 1752,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"em_boolean": 0.5294117647058824,
"em_chat": 0.03783783783783784,
"em_extraction": 0.5333333333333333,
"em_qa": 0.5333333333333333,
"em_summarization": 0.0,
"em_unanswerable": 0.0,
"epoch": 1.0,
"mean_em": 0.12075471698113208,
"mean_similarity": 0.6624939311014594,
"mean_word_count_diff": 11.958490566037735,
"similarity_boolean": 0.649950959993636,
"similarity_chat": 0.6068178282194846,
"similarity_extraction": 0.8274670541286469,
"similarity_qa": 0.8895131280024846,
"similarity_summarization": 0.7897715005609725,
"similarity_unanswerable": 0.8186558306217193,
"word_count_diff_boolean": 2.764705882352941,
"word_count_diff_chat": 11.275675675675675,
"word_count_diff_extraction": 1.8666666666666667,
"word_count_diff_qa": 2.7333333333333334,
"word_count_diff_summarization": 50.05555555555556,
"word_count_diff_unanswerable": 4.4
},
{
"epoch": 1.0,
"grad_norm": 0.29226627945899963,
"learning_rate": 1.314e-05,
"loss": 0.0548,
"step": 219
},
{
"epoch": 1.0,
"eval_loss": 0.04732182249426842,
"eval_runtime": 17.2425,
"eval_samples_per_second": 15.369,
"eval_steps_per_second": 1.972,
"step": 219
},
{
"em_boolean": 0.7058823529411765,
"em_chat": 0.05405405405405406,
"em_extraction": 0.4,
"em_qa": 0.4,
"em_summarization": 0.0,
"em_unanswerable": 0.0,
"epoch": 2.0,
"mean_em": 0.12830188679245283,
"mean_similarity": 0.6936857629426808,
"mean_word_count_diff": 11.475471698113207,
"similarity_boolean": 0.7671171505661571,
"similarity_chat": 0.6481531772158435,
"similarity_extraction": 0.7221033732096355,
"similarity_qa": 0.8645438591639201,
"similarity_summarization": 0.824706514676412,
"similarity_unanswerable": 0.8155314723650614,
"word_count_diff_boolean": 2.7058823529411766,
"word_count_diff_chat": 10.556756756756757,
"word_count_diff_extraction": 2.933333333333333,
"word_count_diff_qa": 3.2,
"word_count_diff_summarization": 50.166666666666664,
"word_count_diff_unanswerable": 3.1333333333333333
},
{
"epoch": 2.0,
"grad_norm": 0.30153563618659973,
"learning_rate": 2.628e-05,
"loss": 0.0445,
"step": 438
},
{
"epoch": 2.0,
"eval_loss": 0.04412226751446724,
"eval_runtime": 17.2255,
"eval_samples_per_second": 15.384,
"eval_steps_per_second": 1.974,
"step": 438
},
{
"em_boolean": 0.5882352941176471,
"em_chat": 0.05945945945945946,
"em_extraction": 0.4666666666666667,
"em_qa": 0.5333333333333333,
"em_summarization": 0.0,
"em_unanswerable": 0.0,
"epoch": 3.0,
"mean_em": 0.13584905660377358,
"mean_similarity": 0.7036299928109039,
"mean_word_count_diff": 11.230188679245282,
"similarity_boolean": 0.702288385699777,
"similarity_chat": 0.6661249467549292,
"similarity_extraction": 0.7363929619391759,
"similarity_qa": 0.9095388889312744,
"similarity_summarization": 0.7749250100718604,
"similarity_unanswerable": 0.8434868295987447,
"word_count_diff_boolean": 1.8823529411764706,
"word_count_diff_chat": 10.41081081081081,
"word_count_diff_extraction": 1.4,
"word_count_diff_qa": 2.8666666666666667,
"word_count_diff_summarization": 50.111111111111114,
"word_count_diff_unanswerable": 3.466666666666667
},
{
"epoch": 3.0,
"grad_norm": 0.4190770983695984,
"learning_rate": 2.9365689308796065e-05,
"loss": 0.0366,
"step": 657
},
{
"epoch": 3.0,
"eval_loss": 0.04255302622914314,
"eval_runtime": 17.2484,
"eval_samples_per_second": 15.364,
"eval_steps_per_second": 1.971,
"step": 657
},
{
"em_boolean": 0.8823529411764706,
"em_chat": 0.05405405405405406,
"em_extraction": 0.6666666666666666,
"em_qa": 0.3333333333333333,
"em_summarization": 0.0,
"em_unanswerable": 0.0,
"epoch": 4.0,
"mean_em": 0.1509433962264151,
"mean_similarity": 0.7214625703522338,
"mean_word_count_diff": 11.275471698113208,
"similarity_boolean": 0.9250823608325685,
"similarity_chat": 0.6629158062407294,
"similarity_extraction": 0.9287973960240682,
"similarity_qa": 0.8280642042557399,
"similarity_summarization": 0.7930781609482236,
"similarity_unanswerable": 0.8128950635592143,
"word_count_diff_boolean": 0.5882352941176471,
"word_count_diff_chat": 10.556756756756757,
"word_count_diff_extraction": 0.4666666666666667,
"word_count_diff_qa": 3.2,
"word_count_diff_summarization": 50.27777777777778,
"word_count_diff_unanswerable": 4.333333333333333
},
{
"epoch": 4.0,
"grad_norm": 0.34906384348869324,
"learning_rate": 2.6482696742411827e-05,
"loss": 0.0301,
"step": 876
},
{
"epoch": 4.0,
"eval_loss": 0.042461033910512924,
"eval_runtime": 17.2294,
"eval_samples_per_second": 15.381,
"eval_steps_per_second": 1.973,
"step": 876
},
{
"em_boolean": 0.8823529411764706,
"em_chat": 0.07027027027027027,
"em_extraction": 0.4,
"em_qa": 0.6,
"em_summarization": 0.0,
"em_unanswerable": 0.0,
"epoch": 5.0,
"mean_em": 0.16226415094339622,
"mean_similarity": 0.7417481038367973,
"mean_word_count_diff": 10.89811320754717,
"similarity_boolean": 0.9421353953726151,
"similarity_chat": 0.6902955391922513,
"similarity_extraction": 0.7581887672344844,
"similarity_qa": 0.9694860418637593,
"similarity_summarization": 0.795685844288932,
"similarity_unanswerable": 0.840320247411728,
"word_count_diff_boolean": 0.0,
"word_count_diff_chat": 10.04864864864865,
"word_count_diff_extraction": 2.066666666666667,
"word_count_diff_qa": 2.3333333333333335,
"word_count_diff_summarization": 50.111111111111114,
"word_count_diff_unanswerable": 4.066666666666666
},
{
"epoch": 5.0,
"grad_norm": 0.2575681209564209,
"learning_rate": 2.17227572135781e-05,
"loss": 0.0252,
"step": 1095
},
{
"epoch": 5.0,
"eval_loss": 0.043407145887613297,
"eval_runtime": 17.2466,
"eval_samples_per_second": 15.365,
"eval_steps_per_second": 1.971,
"step": 1095
},
{
"em_boolean": 0.8235294117647058,
"em_chat": 0.04864864864864865,
"em_extraction": 0.4666666666666667,
"em_qa": 0.3333333333333333,
"em_summarization": 0.0,
"em_unanswerable": 0.0,
"epoch": 6.0,
"mean_em": 0.1320754716981132,
"mean_similarity": 0.712902327184126,
"mean_word_count_diff": 11.09433962264151,
"similarity_boolean": 0.8407609323587488,
"similarity_chat": 0.6657742724023961,
"similarity_extraction": 0.8315838446219762,
"similarity_qa": 0.8299160649379095,
"similarity_summarization": 0.7715526024500529,
"similarity_unanswerable": 0.8431663314501444,
"word_count_diff_boolean": 1.2352941176470589,
"word_count_diff_chat": 10.183783783783785,
"word_count_diff_extraction": 1.5333333333333334,
"word_count_diff_qa": 3.2,
"word_count_diff_summarization": 50.22222222222222,
"word_count_diff_unanswerable": 4.0
},
{
"epoch": 6.0,
"grad_norm": 0.08031666278839111,
"learning_rate": 1.586392436600814e-05,
"loss": 0.0221,
"step": 1314
},
{
"epoch": 6.0,
"eval_loss": 0.04415750876069069,
"eval_runtime": 17.2236,
"eval_samples_per_second": 15.386,
"eval_steps_per_second": 1.974,
"step": 1314
},
{
"em_boolean": 0.8823529411764706,
"em_chat": 0.07567567567567568,
"em_extraction": 0.4,
"em_qa": 0.4,
"em_summarization": 0.0,
"em_unanswerable": 0.0,
"epoch": 7.0,
"mean_em": 0.15471698113207547,
"mean_similarity": 0.7240072643349194,
"mean_word_count_diff": 11.026415094339622,
"similarity_boolean": 0.8786488135947901,
"similarity_chat": 0.6825028176545291,
"similarity_extraction": 0.7764622618754705,
"similarity_qa": 0.8644786556561788,
"similarity_summarization": 0.7805107865068648,
"similarity_unanswerable": 0.7999044020970663,
"word_count_diff_boolean": 1.1764705882352942,
"word_count_diff_chat": 10.151351351351352,
"word_count_diff_extraction": 1.5333333333333334,
"word_count_diff_qa": 3.1333333333333333,
"word_count_diff_summarization": 50.388888888888886,
"word_count_diff_unanswerable": 3.1333333333333333
},
{
"epoch": 7.0,
"grad_norm": 0.21582281589508057,
"learning_rate": 9.863875543572635e-06,
"loss": 0.0193,
"step": 1533
},
{
"epoch": 7.0,
"eval_loss": 0.0449073351919651,
"eval_runtime": 17.225,
"eval_samples_per_second": 15.385,
"eval_steps_per_second": 1.974,
"step": 1533
},
{
"em_boolean": 0.8823529411764706,
"em_chat": 0.05945945945945946,
"em_extraction": 0.6,
"em_qa": 0.3333333333333333,
"em_summarization": 0.0,
"em_unanswerable": 0.0,
"epoch": 8.0,
"mean_em": 0.1509433962264151,
"mean_similarity": 0.7287208422667013,
"mean_word_count_diff": 11.075471698113208,
"similarity_boolean": 0.9135467927245533,
"similarity_chat": 0.6845327336139776,
"similarity_extraction": 0.8388477871815364,
"similarity_qa": 0.8482021888097128,
"similarity_summarization": 0.7841283877690634,
"similarity_unanswerable": 0.7681407590707143,
"word_count_diff_boolean": 0.7647058823529411,
"word_count_diff_chat": 10.254054054054054,
"word_count_diff_extraction": 1.7333333333333334,
"word_count_diff_qa": 3.466666666666667,
"word_count_diff_summarization": 49.888888888888886,
"word_count_diff_unanswerable": 3.2666666666666666
},
{
"epoch": 8.0,
"grad_norm": 0.22318905591964722,
"learning_rate": 4.703371073261941e-06,
"loss": 0.0176,
"step": 1752
},
{
"epoch": 8.0,
"eval_loss": 0.04609951004385948,
"eval_runtime": 17.2261,
"eval_samples_per_second": 15.384,
"eval_steps_per_second": 1.974,
"step": 1752
}
],
"logging_steps": 500,
"max_steps": 2190,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"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": 1.6096499368722432e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|