| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 550, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.090909090909091e-06, | |
| "loss": 2.3833, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 2.4676, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 7.272727272727273e-05, | |
| "loss": 2.2207, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00010909090909090909, | |
| "loss": 2.1377, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00014545454545454546, | |
| "loss": 1.9925, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 1.9958, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00021818181818181818, | |
| "loss": 1.8572, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002545454545454545, | |
| "loss": 1.9631, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002909090909090909, | |
| "loss": 1.8855, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00032727272727272726, | |
| "loss": 1.8563, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00036363636363636367, | |
| "loss": 1.77, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0004, | |
| "loss": 1.8378, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00043636363636363637, | |
| "loss": 1.9476, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0004727272727272727, | |
| "loss": 1.8713, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "gpt4_scores": 0.5359999999999999, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "std": 0.0580868315541483, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.8388524055480957, | |
| "eval_runtime": 4.9686, | |
| "eval_samples_per_second": 4.629, | |
| "eval_steps_per_second": 1.208, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0004999949650182266, | |
| "loss": 1.7168, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0004998741355957963, | |
| "loss": 1.6773, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0004995922759815339, | |
| "loss": 1.6162, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0004991495678185201, | |
| "loss": 1.5625, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0004985462964079136, | |
| "loss": 1.4995, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0004977828505250904, | |
| "loss": 1.4863, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0004968597221690986, | |
| "loss": 1.4958, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0004957775062455933, | |
| "loss": 1.6001, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0004945369001834514, | |
| "loss": 1.5667, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0004931387034853173, | |
| "loss": 1.4828, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0004915838172123671, | |
| "loss": 1.4508, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0004898732434036243, | |
| "loss": 1.4932, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0004880080844302004, | |
| "loss": 1.4789, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0004859895422848767, | |
| "loss": 1.3297, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.00048381891780748665, | |
| "loss": 1.0117, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0004814976098465951, | |
| "loss": 0.7652, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.0004790271143580174, | |
| "loss": 0.8033, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.0004764090234407577, | |
| "loss": 0.6905, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0004736450243109884, | |
| "loss": 0.7312, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.00047073689821473173, | |
| "loss": 0.761, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.00046768651927994433, | |
| "loss": 0.6884, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.0004644958533087443, | |
| "loss": 0.623, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.0004611669565105596, | |
| "loss": 0.7938, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.00045770197417701366, | |
| "loss": 0.7256, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.00045410313929940244, | |
| "loss": 0.8236, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.00045037277112965383, | |
| "loss": 0.9053, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.0004465132736856969, | |
| "loss": 0.8822, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.00044252713420220394, | |
| "loss": 0.847, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.00043841692152770415, | |
| "loss": 0.3486, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 0.00043418528446910123, | |
| "loss": 0.3387, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 0.0004298349500846628, | |
| "loss": 0.3827, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 0.00042536872192658034, | |
| "loss": 0.3494, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 0.00042078947823423365, | |
| "loss": 0.3773, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 0.0004161001700793231, | |
| "loss": 0.327, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 0.00041130381946406574, | |
| "loss": 0.4188, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 0.0004064035173736804, | |
| "loss": 0.3763, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 0.00040140242178441667, | |
| "loss": 0.3837, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 0.0003963037556284129, | |
| "loss": 0.4003, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 0.0003911108047166924, | |
| "loss": 0.32, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 0.00038582691562163827, | |
| "loss": 0.3738, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.0003804554935203115, | |
| "loss": 0.3584, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.000375, | |
| "loss": 0.3469, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 0.0003694639508274158, | |
| "loss": 0.1782, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 0.0003638509136829758, | |
| "loss": 0.1614, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 0.00035816450586162706, | |
| "loss": 0.2127, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 0.00035240839194169884, | |
| "loss": 0.173, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 0.00034658628142328216, | |
| "loss": 0.1831, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 0.00034070192633766023, | |
| "loss": 0.2235, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 0.0003347591188293301, | |
| "loss": 0.1765, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 0.00032876168871217323, | |
| "loss": 0.1828, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 0.00032271350100134975, | |
| "loss": 0.1773, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.0003166184534225087, | |
| "loss": 0.1496, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 0.0003104804738999169, | |
| "loss": 0.176, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 0.00030430351802512693, | |
| "loss": 0.1545, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 0.00029809156650781527, | |
| "loss": 0.1631, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "gpt4_scores": 0.6274, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "std": 0.04891773502524415, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.9787437915802, | |
| "eval_runtime": 4.9451, | |
| "eval_samples_per_second": 4.651, | |
| "eval_steps_per_second": 1.213, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 0.0002918486226104327, | |
| "loss": 0.123, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 0.00028557870956832135, | |
| "loss": 0.1251, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 0.0002792858679969596, | |
| "loss": 0.0895, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 0.0002729741532880069, | |
| "loss": 0.0952, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 0.000266647632995826, | |
| "loss": 0.0914, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 0.00026031038421616684, | |
| "loss": 0.1204, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 0.000253966490958702, | |
| "loss": 0.1004, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 0.00024762004151510585, | |
| "loss": 0.1251, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 0.00024127512582437484, | |
| "loss": 0.0999, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 0.00023493583283708543, | |
| "loss": 0.0932, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 0.00022860624788029015, | |
| "loss": 0.0786, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 0.00022229045002474727, | |
| "loss": 0.0984, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 0.000215992509456184, | |
| "loss": 0.0769, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 0.000209716484852284, | |
| "loss": 0.0765, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "gpt4_scores": 0.5669999999999998, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "std": 0.05915420526048846, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 3.0907390117645264, | |
| "eval_runtime": 4.9453, | |
| "eval_samples_per_second": 4.651, | |
| "eval_steps_per_second": 1.213, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 0.0002034664207670925, | |
| "loss": 0.0632, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 0.0001972463450245226, | |
| "loss": 0.0566, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 0.00019106026612264316, | |
| "loss": 0.054, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 0.00018491217065042198, | |
| "loss": 0.0482, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 0.00017880602071858692, | |
| "loss": 0.0482, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 0.00017274575140626317, | |
| "loss": 0.0575, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 0.00016673526822502983, | |
| "loss": 0.0506, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 0.00016077844460203207, | |
| "loss": 0.0536, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 0.00015487911938376925, | |
| "loss": 0.0503, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 0.00014904109436216883, | |
| "loss": 0.0507, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 0.00014326813182453956, | |
| "loss": 0.0572, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 0.0001375639521289836, | |
| "loss": 0.0575, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 0.00013193223130682935, | |
| "loss": 0.0546, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "learning_rate": 0.00012637659869363084, | |
| "loss": 0.0489, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "gpt4_scores": 0.5259999999999999, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "std": 0.05718811065247741, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 3.2638301849365234, | |
| "eval_runtime": 4.9708, | |
| "eval_samples_per_second": 4.627, | |
| "eval_steps_per_second": 1.207, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 0.00012090063459025954, | |
| "loss": 0.0396, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 0.0001155078679555969, | |
| "loss": 0.0441, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 0.00011020177413231333, | |
| "loss": 0.0413, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 0.00010498577260720049, | |
| "loss": 0.0436, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 9.986322480749927e-05, | |
| "loss": 0.0532, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 9.483743193464408e-05, | |
| "loss": 0.0375, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 8.991163283681945e-05, | |
| "loss": 0.0431, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 8.508900192169963e-05, | |
| "loss": 0.0449, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 8.037264711071699e-05, | |
| "loss": 0.0502, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 7.576560783617667e-05, | |
| "loss": 0.038, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 7.127085308250913e-05, | |
| "loss": 0.0483, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 6.689127947292231e-05, | |
| "loss": 0.0411, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 6.262970940268654e-05, | |
| "loss": 0.0529, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 5.848888922025553e-05, | |
| "loss": 0.0559, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "gpt4_scores": 0.574, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "std": 0.056200355870759375, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 3.374971389770508, | |
| "eval_runtime": 4.9393, | |
| "eval_samples_per_second": 4.657, | |
| "eval_steps_per_second": 1.215, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 5.4471487457395216e-05, | |
| "loss": 0.0389, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 5.058009310946118e-05, | |
| "loss": 0.0445, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 4.6817213966933034e-05, | |
| "loss": 0.0467, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 4.318527499928074e-05, | |
| "loss": 0.0357, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 3.968661679220467e-05, | |
| "loss": 0.0469, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 3.632349403925664e-05, | |
| "loss": 0.0503, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 3.309807408881269e-05, | |
| "loss": 0.0419, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 3.0012435547336736e-05, | |
| "loss": 0.0437, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 2.7068566939831645e-05, | |
| "loss": 0.0388, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 2.4268365428344735e-05, | |
| "loss": 0.0379, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 2.1613635589349755e-05, | |
| "loss": 0.0442, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 1.9106088250797264e-05, | |
| "loss": 0.0529, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 1.674733938957873e-05, | |
| "loss": 0.0424, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "gpt4_scores": 0.586, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "std": 0.05261254603229158, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 3.401412010192871, | |
| "eval_runtime": 4.9704, | |
| "eval_samples_per_second": 4.627, | |
| "eval_steps_per_second": 1.207, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 1.4538909090118846e-05, | |
| "loss": 0.0488, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 1.2482220564763668e-05, | |
| "loss": 0.0406, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 1.0578599236598707e-05, | |
| "loss": 0.0387, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 8.829271885286095e-06, | |
| "loss": 0.0413, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 7.235365856472442e-06, | |
| "loss": 0.0512, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 5.797908335276214e-06, | |
| "loss": 0.0451, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 4.517825684323323e-06, | |
| "loss": 0.0385, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 3.3959428467570664e-06, | |
| "loss": 0.0377, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 2.4329828146074094e-06, | |
| "loss": 0.0434, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 1.6295661628624448e-06, | |
| "loss": 0.0442, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 9.862106495415469e-07, | |
| "loss": 0.0418, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 5.033308820289185e-07, | |
| "loss": 0.0457, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 1.8123804988159908e-07, | |
| "loss": 0.0428, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "learning_rate": 2.0139724285161975e-08, | |
| "loss": 0.0449, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 550, | |
| "total_flos": 1.879358707856179e+16, | |
| "train_loss": 0.0, | |
| "train_runtime": 16.9739, | |
| "train_samples_per_second": 127.843, | |
| "train_steps_per_second": 32.403 | |
| } | |
| ], | |
| "logging_steps": 4, | |
| "max_steps": 550, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 55, | |
| "total_flos": 1.879358707856179e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |