| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.99758337361044, | |
| "global_step": 516, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0003999073369028083, | |
| "loss": 4.4497, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00039962943347572903, | |
| "loss": 3.7433, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00039916654723268495, | |
| "loss": 3.4124, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0003985191070984053, | |
| "loss": 3.3596, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.000397687713010971, | |
| "loss": 3.2361, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00039667313536589325, | |
| "loss": 3.2741, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0003954763143022415, | |
| "loss": 3.1754, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00039409835883148103, | |
| "loss": 3.1644, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00039254054580982917, | |
| "loss": 3.158, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00039080431875508013, | |
| "loss": 3.1109, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00038889128650899707, | |
| "loss": 3.1248, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0003868032217465096, | |
| "loss": 3.01, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00038454205933309793, | |
| "loss": 3.1002, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0003821098945318869, | |
| "loss": 3.001, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0003795089810621101, | |
| "loss": 3.0187, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00037674172901074385, | |
| "loss": 2.9759, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0003738107025992461, | |
| "loss": 2.8984, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0003707186178074693, | |
| "loss": 2.9715, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0003674683398569492, | |
| "loss": 3.0181, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0003640628805559022, | |
| "loss": 3.0082, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00036050539550839015, | |
| "loss": 2.9286, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.0003567991811902403, | |
| "loss": 2.9238, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0003529476718944283, | |
| "loss": 2.9692, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0003489544365487564, | |
| "loss": 2.9091, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.000344823175408774, | |
| "loss": 2.8245, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.8029613494873047, | |
| "eval_runtime": 57.7962, | |
| "eval_samples_per_second": 33.013, | |
| "eval_steps_per_second": 4.135, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00034055771662900637, | |
| "loss": 3.0457, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00033616201271566845, | |
| "loss": 2.5236, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.0003316401368641496, | |
| "loss": 2.6179, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0003269962791846651, | |
| "loss": 2.5468, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00032223474281956987, | |
| "loss": 2.6191, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0003173599399559337, | |
| "loss": 2.639, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0003123763877370721, | |
| "loss": 2.6327, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00030728870407682117, | |
| "loss": 2.6121, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0003021016033804358, | |
| "loss": 2.465, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0002968198921760758, | |
| "loss": 2.619, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0002914484646609277, | |
| "loss": 2.5499, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0002859922981660906, | |
| "loss": 2.5248, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002804564485444265, | |
| "loss": 2.6074, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00027484604548565065, | |
| "loss": 2.5412, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.0002691662877630023, | |
| "loss": 2.5677, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.0002634224384159003, | |
| "loss": 2.5344, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00025761981987304755, | |
| "loss": 2.5655, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.00025176380902050413, | |
| "loss": 2.5598, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00024585983221929805, | |
| "loss": 2.5926, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00023991336027719059, | |
| "loss": 2.4798, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00023392990337925694, | |
| "loss": 2.4976, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.000227915005981978, | |
| "loss": 2.5969, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00022187424167557492, | |
| "loss": 2.5677, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.000215813208019348, | |
| "loss": 2.6221, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00020973752135480505, | |
| "loss": 2.5241, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.000203652811601385, | |
| "loss": 2.521, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.634265899658203, | |
| "eval_runtime": 57.8082, | |
| "eval_samples_per_second": 33.006, | |
| "eval_steps_per_second": 4.134, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.0001975647170396005, | |
| "loss": 2.5802, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 0.00019147887908643253, | |
| "loss": 2.2447, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.0001854009370678185, | |
| "loss": 2.2409, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.00017933652299307847, | |
| "loss": 2.2383, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.00017329125633612044, | |
| "loss": 2.2028, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.00016727073882826242, | |
| "loss": 2.1655, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00016128054926749404, | |
| "loss": 2.2198, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.00015532623834899002, | |
| "loss": 2.2186, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.00014941332352166385, | |
| "loss": 2.2225, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.00014354728387552882, | |
| "loss": 2.2135, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.00013773355506460367, | |
| "loss": 2.1537, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.00013197752427006679, | |
| "loss": 2.2074, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.00012628452520832765, | |
| "loss": 2.1916, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 0.00012065983318864011, | |
| "loss": 2.2548, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.00011510866022483702, | |
| "loss": 2.2211, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.00010963615020571705, | |
| "loss": 2.1348, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.00010424737412855825, | |
| "loss": 2.2425, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 9.894732540017415e-05, | |
| "loss": 2.207, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 9.374091520986936e-05, | |
| "loss": 2.1436, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 8.863296797857865e-05, | |
| "loss": 2.1318, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 8.362821688840947e-05, | |
| "loss": 2.193, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 7.873129949672862e-05, | |
| "loss": 2.1751, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 7.394675343885826e-05, | |
| "loss": 2.2015, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 6.927901222336221e-05, | |
| "loss": 2.1469, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 6.473240112381944e-05, | |
| "loss": 2.1919, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 6.0311133170892234e-05, | |
| "loss": 2.2074, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.5594911575317383, | |
| "eval_runtime": 57.8697, | |
| "eval_samples_per_second": 32.971, | |
| "eval_steps_per_second": 4.13, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 5.601930524840086e-05, | |
| "loss": 2.1884, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 5.186089429702436e-05, | |
| "loss": 2.0386, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 4.783975362914439e-05, | |
| "loss": 2.0487, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 4.395960935824621e-05, | |
| "loss": 1.8492, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 4.022405694618658e-05, | |
| "loss": 2.0609, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 3.663655787152791e-05, | |
| "loss": 1.9626, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 3.320043642202444e-05, | |
| "loss": 1.9572, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 2.9918876614234493e-05, | |
| "loss": 1.9518, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 2.679491924311226e-05, | |
| "loss": 2.0956, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 2.3831459064312743e-05, | |
| "loss": 1.997, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 2.1031242111821635e-05, | |
| "loss": 1.965, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 1.8396863153395216e-05, | |
| "loss": 2.0042, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 1.593076328616814e-05, | |
| "loss": 2.009, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 1.3635227674657147e-05, | |
| "loss": 1.9708, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 1.1512383433257112e-05, | |
| "loss": 1.9904, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 9.564197655190609e-06, | |
| "loss": 1.9272, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 7.792475589738679e-06, | |
| "loss": 1.9683, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 6.198858969440747e-06, | |
| "loss": 1.9925, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 4.784824488814588e-06, | |
| "loss": 1.969, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 3.5516824360052546e-06, | |
| "loss": 1.9914, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 2.500575478631717e-06, | |
| "loss": 1.867, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 1.6324776049554401e-06, | |
| "loss": 2.0106, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 9.481932213528443e-07, | |
| "loss": 1.9669, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 4.483564069273527e-07, | |
| "loss": 1.9383, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 1.334303259521219e-07, | |
| "loss": 1.9087, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 3.7067986876637704e-09, | |
| "loss": 2.0145, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.555163860321045, | |
| "eval_runtime": 57.8174, | |
| "eval_samples_per_second": 33.0, | |
| "eval_steps_per_second": 4.134, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 516, | |
| "total_flos": 3.457207135056691e+16, | |
| "train_loss": 2.476019163464391, | |
| "train_runtime": 8176.7734, | |
| "train_samples_per_second": 8.095, | |
| "train_steps_per_second": 0.063 | |
| } | |
| ], | |
| "max_steps": 516, | |
| "num_train_epochs": 4, | |
| "total_flos": 3.457207135056691e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |