Upload RuShuffleControl/trainer_state.json with huggingface_hub
Browse files
RuShuffleControl/trainer_state.json
ADDED
|
@@ -0,0 +1,430 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 13.038,
|
| 5 |
+
"global_step": 3000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 2e-06,
|
| 13 |
+
"loss": 11.0098,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 9.999999999999999e-05,
|
| 19 |
+
"loss": 8.5348,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.03,
|
| 24 |
+
"learning_rate": 0.00019999999999999998,
|
| 25 |
+
"loss": 6.0584,
|
| 26 |
+
"step": 100
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.05,
|
| 30 |
+
"learning_rate": 0.0003,
|
| 31 |
+
"loss": 5.5248,
|
| 32 |
+
"step": 150
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.07,
|
| 36 |
+
"learning_rate": 0.00039999999999999996,
|
| 37 |
+
"loss": 5.0954,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.01,
|
| 42 |
+
"learning_rate": 0.0005,
|
| 43 |
+
"loss": 4.8186,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.03,
|
| 48 |
+
"learning_rate": 0.0006,
|
| 49 |
+
"loss": 4.6442,
|
| 50 |
+
"step": 300
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.04,
|
| 54 |
+
"learning_rate": 0.0005888888888888889,
|
| 55 |
+
"loss": 4.4369,
|
| 56 |
+
"step": 350
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.06,
|
| 60 |
+
"learning_rate": 0.0005777777777777776,
|
| 61 |
+
"loss": 4.1967,
|
| 62 |
+
"step": 400
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.0,
|
| 66 |
+
"learning_rate": 0.0005666666666666666,
|
| 67 |
+
"loss": 4.0663,
|
| 68 |
+
"step": 450
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.02,
|
| 72 |
+
"learning_rate": 0.0005555555555555556,
|
| 73 |
+
"loss": 3.9725,
|
| 74 |
+
"step": 500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.04,
|
| 78 |
+
"learning_rate": 0.0005444444444444444,
|
| 79 |
+
"loss": 3.9152,
|
| 80 |
+
"step": 550
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.05,
|
| 84 |
+
"learning_rate": 0.0005333333333333333,
|
| 85 |
+
"loss": 3.8671,
|
| 86 |
+
"step": 600
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.07,
|
| 90 |
+
"learning_rate": 0.0005222222222222222,
|
| 91 |
+
"loss": 3.8332,
|
| 92 |
+
"step": 650
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.01,
|
| 96 |
+
"learning_rate": 0.0005111111111111111,
|
| 97 |
+
"loss": 3.8044,
|
| 98 |
+
"step": 700
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 3.03,
|
| 102 |
+
"learning_rate": 0.0005,
|
| 103 |
+
"loss": 3.7774,
|
| 104 |
+
"step": 750
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 3.04,
|
| 108 |
+
"learning_rate": 0.0004888888888888889,
|
| 109 |
+
"loss": 3.7509,
|
| 110 |
+
"step": 800
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.06,
|
| 114 |
+
"learning_rate": 0.0004777777777777777,
|
| 115 |
+
"loss": 3.7289,
|
| 116 |
+
"step": 850
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 4.0,
|
| 120 |
+
"learning_rate": 0.0004666666666666666,
|
| 121 |
+
"loss": 3.7133,
|
| 122 |
+
"step": 900
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 4.02,
|
| 126 |
+
"learning_rate": 0.00045555555555555556,
|
| 127 |
+
"loss": 3.6884,
|
| 128 |
+
"step": 950
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.04,
|
| 132 |
+
"learning_rate": 0.00044444444444444436,
|
| 133 |
+
"loss": 3.6722,
|
| 134 |
+
"step": 1000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 4.04,
|
| 138 |
+
"eval_loss": 4.149817943572998,
|
| 139 |
+
"eval_runtime": 95.0109,
|
| 140 |
+
"eval_samples_per_second": 131.711,
|
| 141 |
+
"eval_steps_per_second": 8.241,
|
| 142 |
+
"step": 1000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 4.04,
|
| 146 |
+
"eval_/home/s2678328/mission-impossible-language-models/training/babylm_dataset.py_loss": 4.149817943572998,
|
| 147 |
+
"eval_/home/s2678328/mission-impossible-language-models/training/babylm_dataset.py_ppl": 63.42245278186028,
|
| 148 |
+
"eval_/home/s2678328/mission-impossible-language-models/training/babylm_dataset.py_runtime": 95.0109,
|
| 149 |
+
"eval_/home/s2678328/mission-impossible-language-models/training/babylm_dataset.py_samples_per_second": 131.711,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 4.05,
|
| 154 |
+
"learning_rate": 0.0004333333333333333,
|
| 155 |
+
"loss": 3.6561,
|
| 156 |
+
"step": 1050
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 4.07,
|
| 160 |
+
"learning_rate": 0.0004222222222222222,
|
| 161 |
+
"loss": 3.6445,
|
| 162 |
+
"step": 1100
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 5.01,
|
| 166 |
+
"learning_rate": 0.0004111111111111111,
|
| 167 |
+
"loss": 3.6333,
|
| 168 |
+
"step": 1150
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 5.03,
|
| 172 |
+
"learning_rate": 0.00039999999999999996,
|
| 173 |
+
"loss": 3.6214,
|
| 174 |
+
"step": 1200
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 5.05,
|
| 178 |
+
"learning_rate": 0.00038888888888888887,
|
| 179 |
+
"loss": 3.6075,
|
| 180 |
+
"step": 1250
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 5.06,
|
| 184 |
+
"learning_rate": 0.00037777777777777777,
|
| 185 |
+
"loss": 3.5992,
|
| 186 |
+
"step": 1300
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 6.01,
|
| 190 |
+
"learning_rate": 0.00036666666666666667,
|
| 191 |
+
"loss": 3.5956,
|
| 192 |
+
"step": 1350
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 6.02,
|
| 196 |
+
"learning_rate": 0.0003555555555555555,
|
| 197 |
+
"loss": 3.5829,
|
| 198 |
+
"step": 1400
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 6.04,
|
| 202 |
+
"learning_rate": 0.0003444444444444444,
|
| 203 |
+
"loss": 3.5736,
|
| 204 |
+
"step": 1450
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 6.06,
|
| 208 |
+
"learning_rate": 0.0003333333333333333,
|
| 209 |
+
"loss": 3.566,
|
| 210 |
+
"step": 1500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 6.07,
|
| 214 |
+
"learning_rate": 0.0003222222222222222,
|
| 215 |
+
"loss": 3.5615,
|
| 216 |
+
"step": 1550
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 7.02,
|
| 220 |
+
"learning_rate": 0.00031111111111111107,
|
| 221 |
+
"loss": 3.5553,
|
| 222 |
+
"step": 1600
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 7.03,
|
| 226 |
+
"learning_rate": 0.0003,
|
| 227 |
+
"loss": 3.5475,
|
| 228 |
+
"step": 1650
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 7.05,
|
| 232 |
+
"learning_rate": 0.0002888888888888888,
|
| 233 |
+
"loss": 3.54,
|
| 234 |
+
"step": 1700
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 7.07,
|
| 238 |
+
"learning_rate": 0.0002777777777777778,
|
| 239 |
+
"loss": 3.5355,
|
| 240 |
+
"step": 1750
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 8.01,
|
| 244 |
+
"learning_rate": 0.0002666666666666666,
|
| 245 |
+
"loss": 3.5329,
|
| 246 |
+
"step": 1800
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 8.02,
|
| 250 |
+
"learning_rate": 0.00025555555555555553,
|
| 251 |
+
"loss": 3.5247,
|
| 252 |
+
"step": 1850
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 8.04,
|
| 256 |
+
"learning_rate": 0.00024444444444444443,
|
| 257 |
+
"loss": 3.5188,
|
| 258 |
+
"step": 1900
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 8.06,
|
| 262 |
+
"learning_rate": 0.0002333333333333333,
|
| 263 |
+
"loss": 3.5129,
|
| 264 |
+
"step": 1950
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 9.0,
|
| 268 |
+
"learning_rate": 0.00022222222222222218,
|
| 269 |
+
"loss": 3.5148,
|
| 270 |
+
"step": 2000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 9.0,
|
| 274 |
+
"eval_loss": 4.061845302581787,
|
| 275 |
+
"eval_runtime": 95.5917,
|
| 276 |
+
"eval_samples_per_second": 130.911,
|
| 277 |
+
"eval_steps_per_second": 8.191,
|
| 278 |
+
"step": 2000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 9.0,
|
| 282 |
+
"eval_/home/s2678328/mission-impossible-language-models/training/babylm_dataset.py_loss": 4.061845302581787,
|
| 283 |
+
"eval_/home/s2678328/mission-impossible-language-models/training/babylm_dataset.py_ppl": 58.081389990982125,
|
| 284 |
+
"eval_/home/s2678328/mission-impossible-language-models/training/babylm_dataset.py_runtime": 95.5917,
|
| 285 |
+
"eval_/home/s2678328/mission-impossible-language-models/training/babylm_dataset.py_samples_per_second": 130.911,
|
| 286 |
+
"step": 2000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 9.02,
|
| 290 |
+
"learning_rate": 0.0002111111111111111,
|
| 291 |
+
"loss": 3.5045,
|
| 292 |
+
"step": 2050
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 9.03,
|
| 296 |
+
"learning_rate": 0.00019999999999999998,
|
| 297 |
+
"loss": 3.5013,
|
| 298 |
+
"step": 2100
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 9.05,
|
| 302 |
+
"learning_rate": 0.00018888888888888888,
|
| 303 |
+
"loss": 3.4959,
|
| 304 |
+
"step": 2150
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 9.07,
|
| 308 |
+
"learning_rate": 0.00017777777777777776,
|
| 309 |
+
"loss": 3.4938,
|
| 310 |
+
"step": 2200
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 10.01,
|
| 314 |
+
"learning_rate": 0.00016666666666666666,
|
| 315 |
+
"loss": 3.4916,
|
| 316 |
+
"step": 2250
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 10.03,
|
| 320 |
+
"learning_rate": 0.00015555555555555554,
|
| 321 |
+
"loss": 3.4859,
|
| 322 |
+
"step": 2300
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 10.04,
|
| 326 |
+
"learning_rate": 0.0001444444444444444,
|
| 327 |
+
"loss": 3.4813,
|
| 328 |
+
"step": 2350
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 10.06,
|
| 332 |
+
"learning_rate": 0.0001333333333333333,
|
| 333 |
+
"loss": 3.4765,
|
| 334 |
+
"step": 2400
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 11.0,
|
| 338 |
+
"learning_rate": 0.00012222222222222221,
|
| 339 |
+
"loss": 3.4802,
|
| 340 |
+
"step": 2450
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 11.02,
|
| 344 |
+
"learning_rate": 0.00011111111111111109,
|
| 345 |
+
"loss": 3.4708,
|
| 346 |
+
"step": 2500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 11.04,
|
| 350 |
+
"learning_rate": 9.999999999999999e-05,
|
| 351 |
+
"loss": 3.4683,
|
| 352 |
+
"step": 2550
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 11.05,
|
| 356 |
+
"learning_rate": 8.888888888888888e-05,
|
| 357 |
+
"loss": 3.4653,
|
| 358 |
+
"step": 2600
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 11.07,
|
| 362 |
+
"learning_rate": 7.777777777777777e-05,
|
| 363 |
+
"loss": 3.4637,
|
| 364 |
+
"step": 2650
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 12.01,
|
| 368 |
+
"learning_rate": 6.666666666666666e-05,
|
| 369 |
+
"loss": 3.4623,
|
| 370 |
+
"step": 2700
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 12.03,
|
| 374 |
+
"learning_rate": 5.5555555555555545e-05,
|
| 375 |
+
"loss": 3.4586,
|
| 376 |
+
"step": 2750
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 12.05,
|
| 380 |
+
"learning_rate": 4.444444444444444e-05,
|
| 381 |
+
"loss": 3.4533,
|
| 382 |
+
"step": 2800
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 12.06,
|
| 386 |
+
"learning_rate": 3.333333333333333e-05,
|
| 387 |
+
"loss": 3.4516,
|
| 388 |
+
"step": 2850
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 13.0,
|
| 392 |
+
"learning_rate": 2.222222222222222e-05,
|
| 393 |
+
"loss": 3.455,
|
| 394 |
+
"step": 2900
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 13.02,
|
| 398 |
+
"learning_rate": 1.111111111111111e-05,
|
| 399 |
+
"loss": 3.4478,
|
| 400 |
+
"step": 2950
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 13.04,
|
| 404 |
+
"learning_rate": 0.0,
|
| 405 |
+
"loss": 3.4458,
|
| 406 |
+
"step": 3000
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 13.04,
|
| 410 |
+
"eval_loss": 4.029599189758301,
|
| 411 |
+
"eval_runtime": 94.0962,
|
| 412 |
+
"eval_samples_per_second": 132.991,
|
| 413 |
+
"eval_steps_per_second": 8.321,
|
| 414 |
+
"step": 3000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 13.04,
|
| 418 |
+
"eval_/home/s2678328/mission-impossible-language-models/training/babylm_dataset.py_loss": 4.029599189758301,
|
| 419 |
+
"eval_/home/s2678328/mission-impossible-language-models/training/babylm_dataset.py_ppl": 56.23836581621429,
|
| 420 |
+
"eval_/home/s2678328/mission-impossible-language-models/training/babylm_dataset.py_runtime": 94.0962,
|
| 421 |
+
"eval_/home/s2678328/mission-impossible-language-models/training/babylm_dataset.py_samples_per_second": 132.991,
|
| 422 |
+
"step": 3000
|
| 423 |
+
}
|
| 424 |
+
],
|
| 425 |
+
"max_steps": 3000,
|
| 426 |
+
"num_train_epochs": 9223372036854775807,
|
| 427 |
+
"total_flos": 1.3382077680451584e+17,
|
| 428 |
+
"trial_name": null,
|
| 429 |
+
"trial_params": null
|
| 430 |
+
}
|