| { | |
| "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": 2.7431, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 2.8776, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 7.272727272727273e-05, | |
| "loss": 2.634, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00010909090909090909, | |
| "loss": 2.5152, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00014545454545454546, | |
| "loss": 2.3073, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 2.2473, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00021818181818181818, | |
| "loss": 2.1606, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002545454545454545, | |
| "loss": 2.1845, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002909090909090909, | |
| "loss": 2.0583, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00032727272727272726, | |
| "loss": 2.0335, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00036363636363636367, | |
| "loss": 1.924, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0004, | |
| "loss": 1.9703, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00043636363636363637, | |
| "loss": 1.9575, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0004727272727272727, | |
| "loss": 2.0255, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.0004999949650182266, | |
| "loss": 1.9794, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0004998741355957963, | |
| "loss": 1.789, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0004995922759815339, | |
| "loss": 1.7866, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0004991495678185201, | |
| "loss": 1.7061, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0004985462964079136, | |
| "loss": 1.6782, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0004977828505250904, | |
| "loss": 1.5574, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.0004968597221690986, | |
| "loss": 1.5883, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0004957775062455933, | |
| "loss": 1.7155, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0004945369001834514, | |
| "loss": 1.6924, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0004931387034853173, | |
| "loss": 1.6414, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0004915838172123671, | |
| "loss": 1.6989, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0004898732434036243, | |
| "loss": 1.7026, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0004880080844302004, | |
| "loss": 1.538, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.0004859895422848767, | |
| "loss": 1.5902, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "pls_score": 62.8, | |
| "std": 4.561052510112109, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.0346944332122803, | |
| "eval_runtime": 4.9191, | |
| "eval_samples_per_second": 4.676, | |
| "eval_steps_per_second": 1.22, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.00048381891780748665, | |
| "loss": 1.5041, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0004814976098465951, | |
| "loss": 0.9413, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.0004790271143580174, | |
| "loss": 0.9638, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.0004764090234407577, | |
| "loss": 0.8674, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0004736450243109884, | |
| "loss": 0.8621, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.00047073689821473173, | |
| "loss": 0.86, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.00046768651927994433, | |
| "loss": 0.7993, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.0004644958533087443, | |
| "loss": 0.7921, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.0004611669565105596, | |
| "loss": 0.9535, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.00045770197417701366, | |
| "loss": 0.823, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.00045410313929940244, | |
| "loss": 0.8705, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.00045037277112965383, | |
| "loss": 0.9627, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.0004465132736856969, | |
| "loss": 1.0076, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.00044252713420220394, | |
| "loss": 0.9706, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.00043841692152770415, | |
| "loss": 0.4535, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 0.00043418528446910123, | |
| "loss": 0.3861, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 0.0004298349500846628, | |
| "loss": 0.4925, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 0.00042536872192658034, | |
| "loss": 0.4753, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 0.00042078947823423365, | |
| "loss": 0.4131, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 0.0004161001700793231, | |
| "loss": 0.3977, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 0.00041130381946406574, | |
| "loss": 0.4816, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 0.0004064035173736804, | |
| "loss": 0.4944, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 0.00040140242178441667, | |
| "loss": 0.4889, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 0.0003963037556284129, | |
| "loss": 0.449, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 0.0003911108047166924, | |
| "loss": 0.5103, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 0.00038582691562163827, | |
| "loss": 0.4971, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.0003804554935203115, | |
| "loss": 0.4087, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 0.000375, | |
| "loss": 0.4146, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "pls_score": 63.6, | |
| "std": 4.067038234391212, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.783196449279785, | |
| "eval_runtime": 4.9791, | |
| "eval_samples_per_second": 4.619, | |
| "eval_steps_per_second": 1.205, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 0.0003694639508274158, | |
| "loss": 0.2699, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 0.0003638509136829758, | |
| "loss": 0.24, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 0.00035816450586162706, | |
| "loss": 0.2368, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 0.00035240839194169884, | |
| "loss": 0.1893, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 0.00034658628142328216, | |
| "loss": 0.2246, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 0.00034070192633766023, | |
| "loss": 0.3669, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 0.0003347591188293301, | |
| "loss": 0.2311, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 0.00032876168871217323, | |
| "loss": 0.213, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 0.00032271350100134975, | |
| "loss": 0.2392, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 0.0003166184534225087, | |
| "loss": 0.2525, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 0.0003104804738999169, | |
| "loss": 0.2326, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 0.00030430351802512693, | |
| "loss": 0.2374, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 0.00029809156650781527, | |
| "loss": 0.2193, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "pls_score": 62.0, | |
| "std": 3.676955262170047, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 3.024041175842285, | |
| "eval_runtime": 4.9575, | |
| "eval_samples_per_second": 4.639, | |
| "eval_steps_per_second": 1.21, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 0.0002918486226104327, | |
| "loss": 0.2179, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 0.00028557870956832135, | |
| "loss": 0.1443, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 0.0002792858679969596, | |
| "loss": 0.1345, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 0.0002729741532880069, | |
| "loss": 0.1421, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 0.000266647632995826, | |
| "loss": 0.1247, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 0.00026031038421616684, | |
| "loss": 0.1541, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 0.000253966490958702, | |
| "loss": 0.1539, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 0.00024762004151510585, | |
| "loss": 0.1498, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 0.00024127512582437484, | |
| "loss": 0.1678, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 0.00023493583283708543, | |
| "loss": 0.2514, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 0.00022860624788029015, | |
| "loss": 0.1418, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 0.00022229045002474727, | |
| "loss": 0.1455, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 0.000215992509456184, | |
| "loss": 0.1259, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 0.000209716484852284, | |
| "loss": 0.1547, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "pls_score": 60.8, | |
| "std": 4.155382052230576, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 3.2443737983703613, | |
| "eval_runtime": 4.9618, | |
| "eval_samples_per_second": 4.635, | |
| "eval_steps_per_second": 1.209, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 0.0002034664207670925, | |
| "loss": 0.1248, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 0.0001972463450245226, | |
| "loss": 0.1031, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 0.00019106026612264316, | |
| "loss": 0.1077, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 0.00018491217065042198, | |
| "loss": 0.1014, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 0.00017880602071858692, | |
| "loss": 0.1129, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 0.00017274575140626317, | |
| "loss": 0.1099, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "learning_rate": 0.00016673526822502983, | |
| "loss": 0.1073, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 0.00016077844460203207, | |
| "loss": 0.1967, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 0.00015487911938376925, | |
| "loss": 0.1046, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 6.69, | |
| "learning_rate": 0.00014904109436216883, | |
| "loss": 0.1225, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 0.00014326813182453956, | |
| "loss": 0.1107, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 6.84, | |
| "learning_rate": 0.0001375639521289836, | |
| "loss": 0.106, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 0.00013193223130682935, | |
| "loss": 0.1025, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "learning_rate": 0.00012637659869363084, | |
| "loss": 0.1096, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "pls_score": 59.183673469387756, | |
| "std": 4.240153693923696, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 3.395291566848755, | |
| "eval_runtime": 4.9577, | |
| "eval_samples_per_second": 4.639, | |
| "eval_steps_per_second": 1.21, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 0.00012090063459025954, | |
| "loss": 0.0881, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 0.0001155078679555969, | |
| "loss": 0.0862, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 0.00011020177413231333, | |
| "loss": 0.1033, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 0.00010498577260720049, | |
| "loss": 0.0953, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.35, | |
| "learning_rate": 9.986322480749927e-05, | |
| "loss": 0.0981, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 7.42, | |
| "learning_rate": 9.483743193464408e-05, | |
| "loss": 0.1042, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 8.991163283681945e-05, | |
| "loss": 0.0992, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 8.508900192169963e-05, | |
| "loss": 0.0904, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 8.037264711071699e-05, | |
| "loss": 0.1085, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 7.576560783617667e-05, | |
| "loss": 0.0924, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "learning_rate": 7.127085308250913e-05, | |
| "loss": 0.213, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 6.689127947292231e-05, | |
| "loss": 0.0925, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "learning_rate": 6.262970940268654e-05, | |
| "loss": 0.1037, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 5.848888922025553e-05, | |
| "loss": 0.1053, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "pls_score": 58.0, | |
| "std": 3.7629775444453557, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 3.4806602001190186, | |
| "eval_runtime": 4.9487, | |
| "eval_samples_per_second": 4.648, | |
| "eval_steps_per_second": 1.212, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 5.4471487457395216e-05, | |
| "loss": 0.0906, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 5.058009310946118e-05, | |
| "loss": 0.1902, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 4.6817213966933034e-05, | |
| "loss": 0.093, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 4.318527499928074e-05, | |
| "loss": 0.0911, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 3.968661679220467e-05, | |
| "loss": 0.0958, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 3.632349403925664e-05, | |
| "loss": 0.0956, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 3.309807408881269e-05, | |
| "loss": 0.094, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 3.0012435547336736e-05, | |
| "loss": 0.097, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 2.7068566939831645e-05, | |
| "loss": 0.0919, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 2.4268365428344735e-05, | |
| "loss": 0.0937, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 2.1613635589349755e-05, | |
| "loss": 0.1222, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 1.9106088250797264e-05, | |
| "loss": 0.0907, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 1.674733938957873e-05, | |
| "loss": 0.0969, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "pls_score": 55.2, | |
| "std": 4.022337628792492, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 3.5086076259613037, | |
| "eval_runtime": 4.9635, | |
| "eval_samples_per_second": 4.634, | |
| "eval_steps_per_second": 1.209, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 1.4538909090118846e-05, | |
| "loss": 0.0869, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 1.2482220564763668e-05, | |
| "loss": 0.1033, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 1.0578599236598707e-05, | |
| "loss": 0.105, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 9.24, | |
| "learning_rate": 8.829271885286095e-06, | |
| "loss": 0.0989, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "learning_rate": 7.235365856472442e-06, | |
| "loss": 0.0901, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 5.797908335276214e-06, | |
| "loss": 0.0912, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 4.517825684323323e-06, | |
| "loss": 0.0857, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 3.3959428467570664e-06, | |
| "loss": 0.112, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 2.4329828146074094e-06, | |
| "loss": 0.0845, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 1.6295661628624448e-06, | |
| "loss": 0.0966, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 9.862106495415469e-07, | |
| "loss": 0.0973, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 5.033308820289185e-07, | |
| "loss": 0.0894, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 1.8123804988159908e-07, | |
| "loss": 0.0867, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "learning_rate": 2.0139724285161975e-08, | |
| "loss": 0.1768, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "pls_score": 57.95918367346939, | |
| "std": 4.172255118366954, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 3.5129005908966064, | |
| "eval_runtime": 4.9489, | |
| "eval_samples_per_second": 4.648, | |
| "eval_steps_per_second": 1.212, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 550, | |
| "total_flos": 1.8757245462528e+16, | |
| "train_loss": 0.1272620278596878, | |
| "train_runtime": 22126.0761, | |
| "train_samples_per_second": 0.098, | |
| "train_steps_per_second": 0.025 | |
| } | |
| ], | |
| "logging_steps": 4, | |
| "max_steps": 550, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 55, | |
| "total_flos": 1.8757245462528e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |