| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 2085, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00014354066985645933, | |
| "loss": 4.6999, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00028708133971291867, | |
| "loss": 4.0234, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00043062200956937803, | |
| "loss": 3.84, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0005741626794258373, | |
| "loss": 3.7458, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0007177033492822966, | |
| "loss": 3.6694, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0008612440191387561, | |
| "loss": 3.6173, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.000999999298909658, | |
| "loss": 3.5916, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0009993264033223551, | |
| "loss": 3.5461, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0009973935099776767, | |
| "loss": 3.5042, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0009942054963290549, | |
| "loss": 3.4956, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0009897704069942402, | |
| "loss": 3.5649, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0009840994334555549, | |
| "loss": 3.5746, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0009772068858193608, | |
| "loss": 3.5424, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.000969110156706009, | |
| "loss": 3.567, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0009598296773613879, | |
| "loss": 3.4753, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0009493888661008194, | |
| "loss": 3.4324, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0009378140692153992, | |
| "loss": 3.4661, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0009251344944898958, | |
| "loss": 3.4081, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0009113821374999736, | |
| "loss": 3.3848, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0008965917008747158, | |
| "loss": 3.3552, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.000880800506728183, | |
| "loss": 3.3352, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0008640484024809779, | |
| "loss": 3.2935, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0008463776603094606, | |
| "loss": 3.2754, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.0008278328704763516, | |
| "loss": 3.2657, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0008084608288118838, | |
| "loss": 3.256, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0007883104186294383, | |
| "loss": 3.2201, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0007674324873736347, | |
| "loss": 3.1941, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.0007458797183121429, | |
| "loss": 3.1856, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0007237064975949886, | |
| "loss": 3.1649, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0007009687770168125, | |
| "loss": 3.155, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0006777239328283909, | |
| "loss": 3.1357, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0006540306209536906, | |
| "loss": 3.1309, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0006299486289778033, | |
| "loss": 3.1091, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0006055387252792498, | |
| "loss": 3.0958, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.0005808625056873581, | |
| "loss": 3.0813, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.0005559822380516539, | |
| "loss": 3.0854, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0005309607051154799, | |
| "loss": 3.068, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.0005058610460903332, | |
| "loss": 3.0664, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00048074659733069516, | |
| "loss": 3.0627, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00045568073251138903, | |
| "loss": 3.0376, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.0004307267027107653, | |
| "loss": 3.0274, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00040594747680324574, | |
| "loss": 3.0212, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0003814055825639795, | |
| "loss": 3.0101, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.000357162948886567, | |
| "loss": 3.0076, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 0.00033328074951199845, | |
| "loss": 3.0129, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 0.0003098192486631408, | |
| "loss": 2.9902, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.00028683764897429804, | |
| "loss": 2.9819, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 0.0002643939420995788, | |
| "loss": 2.9891, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.00024254476237704588, | |
| "loss": 2.9702, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.00022134524391790916, | |
| "loss": 2.972, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.00020084888148138487, | |
| "loss": 2.9733, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.00018110739548628618, | |
| "loss": 2.9688, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 0.0001621706014999767, | |
| "loss": 2.9629, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.00014408628453401574, | |
| "loss": 2.9609, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 0.00012690007846369856, | |
| "loss": 2.9461, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 0.00011065535087576234, | |
| "loss": 2.9493, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 9.539309363483478e-05, | |
| "loss": 2.9417, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 8.115181944476685e-05, | |
| "loss": 2.9459, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 6.796746466586756e-05, | |
| "loss": 2.9273, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 5.58732986332719e-05, | |
| "loss": 2.9397, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 4.4899839705266174e-05, | |
| "loss": 2.943, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 3.507477825341493e-05, | |
| "loss": 2.9381, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 2.642290678881504e-05, | |
| "loss": 2.9509, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 1.8966057400797153e-05, | |
| "loss": 2.9437, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 1.272304666594032e-05, | |
| "loss": 2.9374, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 7.709628166416128e-06, | |
| "loss": 2.9508, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.93845273747806e-06, | |
| "loss": 2.9407, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.4190365444071153e-06, | |
| "loss": 2.949, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 1.5773706946742295e-07, | |
| "loss": 2.9544, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 2085, | |
| "total_flos": 1.731497869485015e+17, | |
| "train_loss": 3.211610127181458, | |
| "train_runtime": 4482.5265, | |
| "train_samples_per_second": 74.379, | |
| "train_steps_per_second": 0.465 | |
| } | |
| ], | |
| "logging_steps": 30, | |
| "max_steps": 2085, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 5000, | |
| "total_flos": 1.731497869485015e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |