File size: 13,347 Bytes
0e66ada |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.004518344478583047,
"global_step": 25,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.5308924913406372,
"learning_rate": 4.2857142857142855e-06,
"loss": 1.8408,
"step": 1,
"teacher_loss": 1.9863686561584473
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.7996352910995483,
"learning_rate": 8.571428571428571e-06,
"loss": 1.9171,
"step": 2,
"teacher_loss": 2.0412771701812744
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.7973085641860962,
"learning_rate": 1.2857142857142857e-05,
"loss": 2.0705,
"step": 3,
"teacher_loss": 2.2119908332824707
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.9594857692718506,
"learning_rate": 1.7142857142857142e-05,
"loss": 1.8092,
"step": 4,
"teacher_loss": 1.9035913944244385
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 1.0630263090133667,
"learning_rate": 2.1428571428571428e-05,
"loss": 1.7453,
"step": 5,
"teacher_loss": 1.821063756942749
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.7821776866912842,
"learning_rate": 2.5714285714285714e-05,
"loss": 1.8497,
"step": 6,
"teacher_loss": 1.9682769775390625
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.8524608612060547,
"learning_rate": 3e-05,
"loss": 1.4181,
"step": 7,
"teacher_loss": 1.480897307395935
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.6336731314659119,
"learning_rate": 2.977211629518312e-05,
"loss": 1.948,
"step": 8,
"teacher_loss": 2.094085693359375
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.6002183556556702,
"learning_rate": 2.9095389311788626e-05,
"loss": 1.6932,
"step": 9,
"teacher_loss": 1.8146612644195557
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.5702627301216125,
"learning_rate": 2.7990381056766583e-05,
"loss": 1.2117,
"step": 10,
"teacher_loss": 1.2829853296279907
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.8245307207107544,
"learning_rate": 2.649066664678467e-05,
"loss": 1.353,
"step": 11,
"teacher_loss": 1.4116955995559692
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.4113720655441284,
"learning_rate": 2.464181414529809e-05,
"loss": 1.4131,
"step": 12,
"teacher_loss": 1.524428129196167
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.5899919867515564,
"learning_rate": 2.25e-05,
"loss": 1.748,
"step": 13,
"teacher_loss": 1.876697301864624
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.7763683199882507,
"learning_rate": 2.0130302149885033e-05,
"loss": 1.2634,
"step": 14,
"teacher_loss": 1.317491054534912
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 1.256364107131958,
"learning_rate": 1.760472266500396e-05,
"loss": 1.8216,
"step": 15,
"teacher_loss": 1.884453296661377
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.630717396736145,
"learning_rate": 1.5e-05,
"loss": 1.052,
"step": 16,
"teacher_loss": 1.0988600254058838
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 2.1178719997406006,
"learning_rate": 1.2395277334996045e-05,
"loss": 1.768,
"step": 17,
"teacher_loss": 1.729122519493103
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.33149364590644836,
"learning_rate": 9.86969785011497e-06,
"loss": 1.0413,
"step": 18,
"teacher_loss": 1.1201426982879639
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 1.1079105138778687,
"learning_rate": 7.500000000000004e-06,
"loss": 1.718,
"step": 19,
"teacher_loss": 1.7857446670532227
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 1.143695592880249,
"learning_rate": 5.3581858547019095e-06,
"loss": 1.0575,
"step": 20,
"teacher_loss": 1.047965407371521
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.5923559665679932,
"learning_rate": 3.5093333532153316e-06,
"loss": 0.9105,
"step": 21,
"teacher_loss": 0.9459026455879211
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.4449232816696167,
"learning_rate": 2.0096189432334194e-06,
"loss": 0.9125,
"step": 22,
"teacher_loss": 0.9643977284431458
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 1.3087965250015259,
"learning_rate": 9.046106882113753e-07,
"loss": 1.5437,
"step": 23,
"teacher_loss": 1.5698204040527344
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 1.0976316928863525,
"learning_rate": 2.278837048168797e-07,
"loss": 1.6757,
"step": 24,
"teacher_loss": 1.7399156093597412
},
{
"compression/statistics/magnitude_sparsity/sparsity_level_for_model": 0.7019828954219413,
"compression/statistics/magnitude_sparsity/sparsity_level_for_sparsified_layers": 0.8999995714352454,
"compression/statistics/magnitude_sparsity/target_sparsity_level": 0.0,
"compression_loss": 0.0,
"epoch": 0.0,
"label_loss": 0.7453712224960327,
"learning_rate": 0.0,
"loss": 1.3899,
"step": 25,
"teacher_loss": 1.4615265130996704
},
{
"epoch": 0.0,
"step": 25,
"total_flos": 78389685043200.0,
"train_loss": 1.526875147819519,
"train_runtime": 69.4951,
"train_samples_per_second": 5.756,
"train_steps_per_second": 0.36
}
],
"max_steps": 25,
"num_train_epochs": 1,
"total_flos": 78389685043200.0,
"trial_name": null,
"trial_params": null
}
|