{"current_steps": 5, "total_steps": 40000, "loss": 15.8073, "lr": 4.999999876629946e-05, "epoch": 0.00016004097048844505, "percentage": 0.01, "elapsed_time": "0:00:05", "remaining_time": "11:10:14", "throughput": 1403.49, "total_tokens": 7056} {"current_steps": 10, "total_steps": 40000, "loss": 14.0983, "lr": 4.999999375439123e-05, "epoch": 0.0003200819409768901, "percentage": 0.03, "elapsed_time": "0:00:06", "remaining_time": "7:31:29", "throughput": 2059.65, "total_tokens": 13952} {"current_steps": 15, "total_steps": 40000, "loss": 15.4996, "lr": 4.9999984887169785e-05, "epoch": 0.0004801229114653351, "percentage": 0.04, "elapsed_time": "0:00:08", "remaining_time": "6:18:47", "throughput": 2458.32, "total_tokens": 20960} {"current_steps": 20, "total_steps": 40000, "loss": 16.9627, "lr": 4.9999972164636506e-05, "epoch": 0.0006401638819537802, "percentage": 0.05, "elapsed_time": "0:00:10", "remaining_time": "5:42:23", "throughput": 2721.5, "total_tokens": 27968} {"current_steps": 25, "total_steps": 40000, "loss": 15.2224, "lr": 4.999995558679334e-05, "epoch": 0.0008002048524422252, "percentage": 0.06, "elapsed_time": "0:00:12", "remaining_time": "5:20:02", "throughput": 2897.77, "total_tokens": 34800} {"current_steps": 30, "total_steps": 40000, "loss": 17.4422, "lr": 4.999993515364287e-05, "epoch": 0.0009602458229306702, "percentage": 0.07, "elapsed_time": "0:00:13", "remaining_time": "5:05:22", "throughput": 3062.12, "total_tokens": 42112} {"current_steps": 35, "total_steps": 40000, "loss": 14.5495, "lr": 4.999991086518822e-05, "epoch": 0.0011202867934191152, "percentage": 0.09, "elapsed_time": "0:00:15", "remaining_time": "4:55:01", "throughput": 3169.54, "total_tokens": 49136} {"current_steps": 40, "total_steps": 40000, "loss": 14.9526, "lr": 4.999988272143315e-05, "epoch": 0.0012803277639075604, "percentage": 0.1, "elapsed_time": "0:00:17", "remaining_time": "4:47:07", "throughput": 3251.11, "total_tokens": 56064} {"current_steps": 45, "total_steps": 40000, "loss": 16.9271, "lr": 4.999985072238199e-05, "epoch": 0.0014403687343960054, "percentage": 0.11, "elapsed_time": "0:00:18", "remaining_time": "4:40:57", "throughput": 3321.2, "total_tokens": 63056} {"current_steps": 50, "total_steps": 40000, "loss": 16.1943, "lr": 4.999981486803969e-05, "epoch": 0.0016004097048844504, "percentage": 0.12, "elapsed_time": "0:00:20", "remaining_time": "4:35:59", "throughput": 3358.17, "total_tokens": 69600} {"current_steps": 55, "total_steps": 40000, "loss": 11.9455, "lr": 4.999977515841176e-05, "epoch": 0.0017604506753728954, "percentage": 0.14, "elapsed_time": "0:00:22", "remaining_time": "4:31:51", "throughput": 3406.08, "total_tokens": 76496} {"current_steps": 60, "total_steps": 40000, "loss": 13.9099, "lr": 4.9999731593504344e-05, "epoch": 0.0019204916458613404, "percentage": 0.15, "elapsed_time": "0:00:24", "remaining_time": "4:28:29", "throughput": 3447.13, "total_tokens": 83424} {"current_steps": 65, "total_steps": 40000, "loss": 11.8623, "lr": 4.999968417332415e-05, "epoch": 0.0020805326163497854, "percentage": 0.16, "elapsed_time": "0:00:25", "remaining_time": "4:25:39", "throughput": 3482.67, "total_tokens": 90352} {"current_steps": 70, "total_steps": 40000, "loss": 11.0303, "lr": 4.999963289787848e-05, "epoch": 0.0022405735868382304, "percentage": 0.18, "elapsed_time": "0:00:27", "remaining_time": "4:23:09", "throughput": 3528.23, "total_tokens": 97664} {"current_steps": 75, "total_steps": 40000, "loss": 9.3144, "lr": 4.999957776717526e-05, "epoch": 0.002400614557326676, "percentage": 0.19, "elapsed_time": "0:00:29", "remaining_time": "4:21:03", "throughput": 3546.56, "total_tokens": 104352} {"current_steps": 80, "total_steps": 40000, "loss": 9.2038, "lr": 4.9999518781222984e-05, "epoch": 0.002560655527815121, "percentage": 0.2, "elapsed_time": "0:00:31", "remaining_time": "4:19:20", "throughput": 3564.36, "total_tokens": 111152} {"current_steps": 85, "total_steps": 40000, "loss": 8.644, "lr": 4.9999455940030746e-05, "epoch": 0.002720696498303566, "percentage": 0.21, "elapsed_time": "0:00:32", "remaining_time": "4:17:41", "throughput": 3600.39, "total_tokens": 118544} {"current_steps": 90, "total_steps": 40000, "loss": 9.5396, "lr": 4.999938924360824e-05, "epoch": 0.002880737468792011, "percentage": 0.22, "elapsed_time": "0:00:34", "remaining_time": "4:16:11", "throughput": 3622.41, "total_tokens": 125568} {"current_steps": 95, "total_steps": 40000, "loss": 8.131, "lr": 4.999931869196575e-05, "epoch": 0.003040778439280456, "percentage": 0.24, "elapsed_time": "0:00:36", "remaining_time": "4:14:51", "throughput": 3644.09, "total_tokens": 132656} {"current_steps": 100, "total_steps": 40000, "loss": 8.1072, "lr": 4.999924428511416e-05, "epoch": 0.003200819409768901, "percentage": 0.25, "elapsed_time": "0:00:38", "remaining_time": "4:13:38", "throughput": 3662.14, "total_tokens": 139680} {"current_steps": 105, "total_steps": 40000, "loss": 6.8283, "lr": 4.999916602306494e-05, "epoch": 0.003360860380257346, "percentage": 0.26, "elapsed_time": "0:00:39", "remaining_time": "4:12:32", "throughput": 3681.84, "total_tokens": 146832} {"current_steps": 110, "total_steps": 40000, "loss": 6.1304, "lr": 4.999908390583016e-05, "epoch": 0.003520901350745791, "percentage": 0.27, "elapsed_time": "0:00:41", "remaining_time": "4:11:34", "throughput": 3694.04, "total_tokens": 153760} {"current_steps": 115, "total_steps": 40000, "loss": 7.4639, "lr": 4.999899793342247e-05, "epoch": 0.003680942321234236, "percentage": 0.29, "elapsed_time": "0:00:43", "remaining_time": "4:10:38", "throughput": 3709.9, "total_tokens": 160864} {"current_steps": 120, "total_steps": 40000, "loss": 8.8824, "lr": 4.999890810585516e-05, "epoch": 0.003840983291722681, "percentage": 0.3, "elapsed_time": "0:00:45", "remaining_time": "4:09:50", "throughput": 3715.92, "total_tokens": 167616} {"current_steps": 125, "total_steps": 40000, "loss": 7.8986, "lr": 4.999881442314206e-05, "epoch": 0.004001024262211126, "percentage": 0.31, "elapsed_time": "0:00:46", "remaining_time": "4:09:03", "throughput": 3721.55, "total_tokens": 174336} {"current_steps": 130, "total_steps": 40000, "loss": 6.6778, "lr": 4.9998716885297617e-05, "epoch": 0.004161065232699571, "percentage": 0.33, "elapsed_time": "0:00:48", "remaining_time": "4:08:19", "throughput": 3730.09, "total_tokens": 181216} {"current_steps": 135, "total_steps": 40000, "loss": 7.1049, "lr": 4.999861549233688e-05, "epoch": 0.004321106203188016, "percentage": 0.34, "elapsed_time": "0:00:50", "remaining_time": "4:07:38", "throughput": 3737.87, "total_tokens": 188080} {"current_steps": 140, "total_steps": 40000, "loss": 6.8969, "lr": 4.999851024427548e-05, "epoch": 0.004481147173676461, "percentage": 0.35, "elapsed_time": "0:00:52", "remaining_time": "4:06:59", "throughput": 3739.39, "total_tokens": 194640} {"current_steps": 145, "total_steps": 40000, "loss": 6.7604, "lr": 4.999840114112965e-05, "epoch": 0.004641188144164906, "percentage": 0.36, "elapsed_time": "0:00:53", "remaining_time": "4:06:24", "throughput": 3737.4, "total_tokens": 201024} {"current_steps": 150, "total_steps": 40000, "loss": 7.3739, "lr": 4.999828818291621e-05, "epoch": 0.004801229114653352, "percentage": 0.38, "elapsed_time": "0:00:55", "remaining_time": "4:05:50", "throughput": 3744.55, "total_tokens": 207904} {"current_steps": 155, "total_steps": 40000, "loss": 6.5427, "lr": 4.999817136965259e-05, "epoch": 0.004961270085141797, "percentage": 0.39, "elapsed_time": "0:00:57", "remaining_time": "4:05:17", "throughput": 3744.76, "total_tokens": 214400} {"current_steps": 160, "total_steps": 40000, "loss": 5.3109, "lr": 4.9998050701356794e-05, "epoch": 0.005121311055630242, "percentage": 0.4, "elapsed_time": "0:00:58", "remaining_time": "4:04:47", "throughput": 3745.19, "total_tokens": 220912} {"current_steps": 165, "total_steps": 40000, "loss": 6.4278, "lr": 4.999792617804744e-05, "epoch": 0.005281352026118687, "percentage": 0.41, "elapsed_time": "0:01:00", "remaining_time": "4:04:23", "throughput": 3753.37, "total_tokens": 227968} {"current_steps": 170, "total_steps": 40000, "loss": 5.0922, "lr": 4.9997797799743724e-05, "epoch": 0.005441392996607132, "percentage": 0.43, "elapsed_time": "0:01:02", "remaining_time": "4:03:57", "throughput": 3759.45, "total_tokens": 234864} {"current_steps": 175, "total_steps": 40000, "loss": 4.9773, "lr": 4.999766556646545e-05, "epoch": 0.005601433967095577, "percentage": 0.44, "elapsed_time": "0:01:04", "remaining_time": "4:03:30", "throughput": 3770.6, "total_tokens": 242080} {"current_steps": 180, "total_steps": 40000, "loss": 5.017, "lr": 4.9997529478232996e-05, "epoch": 0.005761474937584022, "percentage": 0.45, "elapsed_time": "0:01:05", "remaining_time": "4:03:06", "throughput": 3776.97, "total_tokens": 249040} {"current_steps": 185, "total_steps": 40000, "loss": 4.421, "lr": 4.9997389535067365e-05, "epoch": 0.005921515908072467, "percentage": 0.46, "elapsed_time": "0:01:07", "remaining_time": "4:02:43", "throughput": 3784.29, "total_tokens": 256080} {"current_steps": 190, "total_steps": 40000, "loss": 4.2633, "lr": 4.999724573699012e-05, "epoch": 0.006081556878560912, "percentage": 0.47, "elapsed_time": "0:01:09", "remaining_time": "4:02:21", "throughput": 3793.68, "total_tokens": 263296} {"current_steps": 195, "total_steps": 40000, "loss": 5.0942, "lr": 4.9997098084023457e-05, "epoch": 0.006241597849049357, "percentage": 0.49, "elapsed_time": "0:01:11", "remaining_time": "4:02:00", "throughput": 3800.06, "total_tokens": 270320} {"current_steps": 200, "total_steps": 40000, "loss": 2.8233, "lr": 4.999694657619013e-05, "epoch": 0.006401638819537802, "percentage": 0.5, "elapsed_time": "0:01:12", "remaining_time": "4:01:40", "throughput": 3805.0, "total_tokens": 277264} {"current_steps": 200, "total_steps": 40000, "eval_loss": 4.07581901550293, "epoch": 0.006401638819537802, "percentage": 0.5, "elapsed_time": "0:06:59", "remaining_time": "23:12:04", "throughput": 660.59, "total_tokens": 277264} {"current_steps": 205, "total_steps": 40000, "loss": 3.4348, "lr": 4.999679121351352e-05, "epoch": 0.006561679790026247, "percentage": 0.51, "elapsed_time": "0:07:03", "remaining_time": "22:48:58", "throughput": 670.96, "total_tokens": 283904} {"current_steps": 210, "total_steps": 40000, "loss": 3.3381, "lr": 4.9996631996017565e-05, "epoch": 0.006721720760514692, "percentage": 0.53, "elapsed_time": "0:07:04", "remaining_time": "22:21:46", "throughput": 684.94, "total_tokens": 291024} {"current_steps": 215, "total_steps": 40000, "loss": 2.9486, "lr": 4.9996468923726835e-05, "epoch": 0.006881761731003137, "percentage": 0.54, "elapsed_time": "0:07:06", "remaining_time": "21:55:48", "throughput": 698.1, "total_tokens": 297840} {"current_steps": 220, "total_steps": 40000, "loss": 3.6695, "lr": 4.999630199666647e-05, "epoch": 0.007041802701491582, "percentage": 0.55, "elapsed_time": "0:07:08", "remaining_time": "21:30:59", "throughput": 710.66, "total_tokens": 304432} {"current_steps": 225, "total_steps": 40000, "loss": 2.8671, "lr": 4.999613121486222e-05, "epoch": 0.007201843671980027, "percentage": 0.56, "elapsed_time": "0:07:10", "remaining_time": "21:07:14", "throughput": 723.79, "total_tokens": 311312} {"current_steps": 230, "total_steps": 40000, "loss": 3.0195, "lr": 4.999595657834041e-05, "epoch": 0.007361884642468472, "percentage": 0.57, "elapsed_time": "0:07:11", "remaining_time": "20:44:32", "throughput": 736.62, "total_tokens": 318112} {"current_steps": 235, "total_steps": 40000, "loss": 3.1515, "lr": 4.999577808712798e-05, "epoch": 0.007521925612956917, "percentage": 0.59, "elapsed_time": "0:07:13", "remaining_time": "20:22:47", "throughput": 749.44, "total_tokens": 324944} {"current_steps": 240, "total_steps": 40000, "loss": 3.136, "lr": 4.999559574125244e-05, "epoch": 0.007681966583445362, "percentage": 0.6, "elapsed_time": "0:07:15", "remaining_time": "20:01:59", "throughput": 761.69, "total_tokens": 331584} {"current_steps": 245, "total_steps": 40000, "loss": 2.5772, "lr": 4.9995409540741934e-05, "epoch": 0.007842007553933807, "percentage": 0.61, "elapsed_time": "0:07:17", "remaining_time": "19:42:00", "throughput": 774.92, "total_tokens": 338688} {"current_steps": 250, "total_steps": 40000, "loss": 2.1309, "lr": 4.999521948562516e-05, "epoch": 0.008002048524422252, "percentage": 0.62, "elapsed_time": "0:07:18", "remaining_time": "19:22:49", "throughput": 786.95, "total_tokens": 345312} {"current_steps": 255, "total_steps": 40000, "loss": 2.4527, "lr": 4.999502557593143e-05, "epoch": 0.008162089494910697, "percentage": 0.64, "elapsed_time": "0:07:20", "remaining_time": "19:04:22", "throughput": 799.47, "total_tokens": 352192} {"current_steps": 260, "total_steps": 40000, "loss": 2.4101, "lr": 4.999482781169066e-05, "epoch": 0.008322130465399142, "percentage": 0.65, "elapsed_time": "0:07:22", "remaining_time": "18:46:38", "throughput": 811.24, "total_tokens": 358784} {"current_steps": 265, "total_steps": 40000, "loss": 2.6069, "lr": 4.9994626192933324e-05, "epoch": 0.008482171435887587, "percentage": 0.66, "elapsed_time": "0:07:23", "remaining_time": "18:29:34", "throughput": 823.36, "total_tokens": 365568} {"current_steps": 270, "total_steps": 40000, "loss": 3.3534, "lr": 4.999442071969054e-05, "epoch": 0.008642212406376032, "percentage": 0.68, "elapsed_time": "0:07:25", "remaining_time": "18:13:08", "throughput": 835.52, "total_tokens": 372416} {"current_steps": 275, "total_steps": 40000, "loss": 1.9377, "lr": 4.999421139199397e-05, "epoch": 0.008802253376864477, "percentage": 0.69, "elapsed_time": "0:07:27", "remaining_time": "17:57:17", "throughput": 848.02, "total_tokens": 379456} {"current_steps": 280, "total_steps": 40000, "loss": 2.3777, "lr": 4.999399820987592e-05, "epoch": 0.008962294347352922, "percentage": 0.7, "elapsed_time": "0:07:29", "remaining_time": "17:42:02", "throughput": 859.63, "total_tokens": 386144} {"current_steps": 285, "total_steps": 40000, "loss": 2.4771, "lr": 4.999378117336924e-05, "epoch": 0.009122335317841367, "percentage": 0.71, "elapsed_time": "0:07:30", "remaining_time": "17:27:19", "throughput": 871.52, "total_tokens": 393008} {"current_steps": 290, "total_steps": 40000, "loss": 1.9243, "lr": 4.9993560282507415e-05, "epoch": 0.009282376288329812, "percentage": 0.73, "elapsed_time": "0:07:32", "remaining_time": "17:13:06", "throughput": 883.06, "total_tokens": 399744} {"current_steps": 295, "total_steps": 40000, "loss": 1.9918, "lr": 4.9993335537324495e-05, "epoch": 0.009442417258818258, "percentage": 0.74, "elapsed_time": "0:07:34", "remaining_time": "16:59:20", "throughput": 894.73, "total_tokens": 406576} {"current_steps": 300, "total_steps": 40000, "loss": 1.881, "lr": 4.999310693785516e-05, "epoch": 0.009602458229306703, "percentage": 0.75, "elapsed_time": "0:07:36", "remaining_time": "16:46:03", "throughput": 905.85, "total_tokens": 413200} {"current_steps": 305, "total_steps": 40000, "loss": 2.2119, "lr": 4.9992874484134653e-05, "epoch": 0.009762499199795148, "percentage": 0.76, "elapsed_time": "0:07:37", "remaining_time": "16:33:11", "throughput": 917.34, "total_tokens": 420032} {"current_steps": 310, "total_steps": 40000, "loss": 2.3348, "lr": 4.999263817619882e-05, "epoch": 0.009922540170283593, "percentage": 0.78, "elapsed_time": "0:07:39", "remaining_time": "16:20:45", "throughput": 928.82, "total_tokens": 426896} {"current_steps": 315, "total_steps": 40000, "loss": 1.6311, "lr": 4.9992398014084105e-05, "epoch": 0.010082581140772038, "percentage": 0.79, "elapsed_time": "0:07:41", "remaining_time": "16:08:41", "throughput": 939.52, "total_tokens": 433440} {"current_steps": 320, "total_steps": 40000, "loss": 2.2815, "lr": 4.999215399782754e-05, "epoch": 0.010242622111260483, "percentage": 0.8, "elapsed_time": "0:07:43", "remaining_time": "15:57:01", "throughput": 950.02, "total_tokens": 439936} {"current_steps": 325, "total_steps": 40000, "loss": 2.2862, "lr": 4.999190612746675e-05, "epoch": 0.010402663081748928, "percentage": 0.81, "elapsed_time": "0:07:44", "remaining_time": "15:45:44", "throughput": 961.13, "total_tokens": 446752} {"current_steps": 330, "total_steps": 40000, "loss": 1.9627, "lr": 4.999165440303998e-05, "epoch": 0.010562704052237373, "percentage": 0.83, "elapsed_time": "0:07:46", "remaining_time": "15:34:45", "throughput": 971.4, "total_tokens": 453216} {"current_steps": 335, "total_steps": 40000, "loss": 1.7508, "lr": 4.999139882458603e-05, "epoch": 0.010722745022725818, "percentage": 0.84, "elapsed_time": "0:07:48", "remaining_time": "15:24:06", "throughput": 981.51, "total_tokens": 459632} {"current_steps": 340, "total_steps": 40000, "loss": 1.7253, "lr": 4.9991139392144314e-05, "epoch": 0.010882785993214263, "percentage": 0.85, "elapsed_time": "0:07:50", "remaining_time": "15:13:46", "throughput": 992.4, "total_tokens": 466448} {"current_steps": 345, "total_steps": 40000, "loss": 1.425, "lr": 4.999087610575485e-05, "epoch": 0.011042826963702708, "percentage": 0.86, "elapsed_time": "0:07:51", "remaining_time": "15:03:44", "throughput": 1002.75, "total_tokens": 473056} {"current_steps": 350, "total_steps": 40000, "loss": 1.5573, "lr": 4.999060896545824e-05, "epoch": 0.011202867934191153, "percentage": 0.88, "elapsed_time": "0:07:53", "remaining_time": "14:53:59", "throughput": 1013.92, "total_tokens": 480080} {"current_steps": 355, "total_steps": 40000, "loss": 2.1659, "lr": 4.999033797129568e-05, "epoch": 0.011362908904679598, "percentage": 0.89, "elapsed_time": "0:07:55", "remaining_time": "14:44:30", "throughput": 1025.18, "total_tokens": 487184} {"current_steps": 360, "total_steps": 40000, "loss": 1.7505, "lr": 4.999006312330894e-05, "epoch": 0.011522949875168043, "percentage": 0.9, "elapsed_time": "0:07:56", "remaining_time": "14:35:18", "throughput": 1036.17, "total_tokens": 494208} {"current_steps": 365, "total_steps": 40000, "loss": 1.6393, "lr": 4.998978442154043e-05, "epoch": 0.011682990845656488, "percentage": 0.91, "elapsed_time": "0:07:58", "remaining_time": "14:26:21", "throughput": 1046.84, "total_tokens": 501120} {"current_steps": 370, "total_steps": 40000, "loss": 1.6823, "lr": 4.9989501866033125e-05, "epoch": 0.011843031816144933, "percentage": 0.92, "elapsed_time": "0:08:00", "remaining_time": "14:17:39", "throughput": 1056.35, "total_tokens": 507520} {"current_steps": 375, "total_steps": 40000, "loss": 1.63, "lr": 4.998921545683059e-05, "epoch": 0.012003072786633378, "percentage": 0.94, "elapsed_time": "0:08:02", "remaining_time": "14:09:11", "throughput": 1066.97, "total_tokens": 514480} {"current_steps": 380, "total_steps": 40000, "loss": 1.5192, "lr": 4.9988925193976996e-05, "epoch": 0.012163113757121823, "percentage": 0.95, "elapsed_time": "0:08:03", "remaining_time": "14:00:55", "throughput": 1076.97, "total_tokens": 521168} {"current_steps": 385, "total_steps": 40000, "loss": 1.4496, "lr": 4.998863107751711e-05, "epoch": 0.012323154727610268, "percentage": 0.96, "elapsed_time": "0:08:05", "remaining_time": "13:52:51", "throughput": 1087.33, "total_tokens": 528064} {"current_steps": 390, "total_steps": 40000, "loss": 1.6921, "lr": 4.998833310749629e-05, "epoch": 0.012483195698098713, "percentage": 0.97, "elapsed_time": "0:08:07", "remaining_time": "13:45:00", "throughput": 1096.99, "total_tokens": 534656} {"current_steps": 395, "total_steps": 40000, "loss": 1.3612, "lr": 4.998803128396047e-05, "epoch": 0.012643236668587158, "percentage": 0.99, "elapsed_time": "0:08:09", "remaining_time": "13:37:21", "throughput": 1108.28, "total_tokens": 542080} {"current_steps": 400, "total_steps": 40000, "loss": 1.6949, "lr": 4.9987725606956215e-05, "epoch": 0.012803277639075603, "percentage": 1.0, "elapsed_time": "0:08:10", "remaining_time": "13:29:53", "throughput": 1118.43, "total_tokens": 548976} {"current_steps": 400, "total_steps": 40000, "eval_loss": 1.6426799297332764, "epoch": 0.012803277639075603, "percentage": 1.0, "elapsed_time": "0:13:58", "remaining_time": "23:03:37", "throughput": 654.66, "total_tokens": 548976} {"current_steps": 405, "total_steps": 40000, "loss": 1.5581, "lr": 4.998741607653066e-05, "epoch": 0.012963318609564048, "percentage": 1.01, "elapsed_time": "0:14:02", "remaining_time": "22:52:13", "throughput": 659.89, "total_tokens": 555728} {"current_steps": 410, "total_steps": 40000, "loss": 1.2506, "lr": 4.9987102692731523e-05, "epoch": 0.013123359580052493, "percentage": 1.03, "elapsed_time": "0:14:03", "remaining_time": "22:38:06", "throughput": 666.8, "total_tokens": 562704} {"current_steps": 415, "total_steps": 40000, "loss": 1.4979, "lr": 4.9986785455607157e-05, "epoch": 0.013283400550540938, "percentage": 1.04, "elapsed_time": "0:14:05", "remaining_time": "22:24:20", "throughput": 673.53, "total_tokens": 569552} {"current_steps": 420, "total_steps": 40000, "loss": 1.3954, "lr": 4.9986464365206456e-05, "epoch": 0.013443441521029383, "percentage": 1.05, "elapsed_time": "0:14:07", "remaining_time": "22:10:53", "throughput": 680.16, "total_tokens": 576336} {"current_steps": 425, "total_steps": 40000, "loss": 1.9262, "lr": 4.9986139421578956e-05, "epoch": 0.013603482491517828, "percentage": 1.06, "elapsed_time": "0:14:09", "remaining_time": "21:57:45", "throughput": 686.51, "total_tokens": 582912} {"current_steps": 430, "total_steps": 40000, "loss": 1.2745, "lr": 4.998581062477477e-05, "epoch": 0.013763523462006273, "percentage": 1.07, "elapsed_time": "0:14:10", "remaining_time": "21:44:56", "throughput": 693.27, "total_tokens": 589856} {"current_steps": 435, "total_steps": 40000, "loss": 1.0926, "lr": 4.998547797484458e-05, "epoch": 0.013923564432494718, "percentage": 1.09, "elapsed_time": "0:14:12", "remaining_time": "21:32:23", "throughput": 699.9, "total_tokens": 596704} {"current_steps": 440, "total_steps": 40000, "loss": 1.4237, "lr": 4.9985141471839706e-05, "epoch": 0.014083605402983163, "percentage": 1.1, "elapsed_time": "0:14:14", "remaining_time": "21:20:08", "throughput": 706.45, "total_tokens": 603520} {"current_steps": 445, "total_steps": 40000, "loss": 1.4373, "lr": 4.998480111581203e-05, "epoch": 0.014243646373471608, "percentage": 1.11, "elapsed_time": "0:14:16", "remaining_time": "21:08:11", "throughput": 713.03, "total_tokens": 610384} {"current_steps": 450, "total_steps": 40000, "loss": 1.4921, "lr": 4.998445690681405e-05, "epoch": 0.014403687343960053, "percentage": 1.12, "elapsed_time": "0:14:17", "remaining_time": "20:56:28", "throughput": 719.2, "total_tokens": 616912} {"current_steps": 455, "total_steps": 40000, "loss": 1.7408, "lr": 4.9984108844898834e-05, "epoch": 0.014563728314448498, "percentage": 1.14, "elapsed_time": "0:14:19", "remaining_time": "20:45:01", "throughput": 725.89, "total_tokens": 623904} {"current_steps": 460, "total_steps": 40000, "loss": 1.4856, "lr": 4.9983756930120076e-05, "epoch": 0.014723769284936943, "percentage": 1.15, "elapsed_time": "0:14:21", "remaining_time": "20:33:49", "throughput": 732.93, "total_tokens": 631232} {"current_steps": 465, "total_steps": 40000, "loss": 1.4744, "lr": 4.9983401162532025e-05, "epoch": 0.014883810255425388, "percentage": 1.16, "elapsed_time": "0:14:22", "remaining_time": "20:22:51", "throughput": 739.99, "total_tokens": 638592} {"current_steps": 470, "total_steps": 40000, "loss": 1.299, "lr": 4.998304154218955e-05, "epoch": 0.015043851225913833, "percentage": 1.18, "elapsed_time": "0:14:24", "remaining_time": "20:12:07", "throughput": 746.83, "total_tokens": 645792} {"current_steps": 475, "total_steps": 40000, "loss": 1.0605, "lr": 4.998267806914812e-05, "epoch": 0.015203892196402278, "percentage": 1.19, "elapsed_time": "0:14:26", "remaining_time": "20:01:36", "throughput": 754.06, "total_tokens": 653344} {"current_steps": 480, "total_steps": 40000, "loss": 1.8531, "lr": 4.998231074346378e-05, "epoch": 0.015363933166890723, "percentage": 1.2, "elapsed_time": "0:14:28", "remaining_time": "19:51:19", "throughput": 759.94, "total_tokens": 659760} {"current_steps": 485, "total_steps": 40000, "loss": 1.0612, "lr": 4.998193956519317e-05, "epoch": 0.015523974137379168, "percentage": 1.21, "elapsed_time": "0:14:29", "remaining_time": "19:41:15", "throughput": 766.15, "total_tokens": 666480} {"current_steps": 490, "total_steps": 40000, "loss": 1.387, "lr": 4.9981564534393545e-05, "epoch": 0.015684015107867613, "percentage": 1.23, "elapsed_time": "0:14:31", "remaining_time": "19:31:23", "throughput": 772.28, "total_tokens": 673152} {"current_steps": 495, "total_steps": 40000, "loss": 1.1292, "lr": 4.998118565112272e-05, "epoch": 0.01584405607835606, "percentage": 1.24, "elapsed_time": "0:14:33", "remaining_time": "19:21:42", "throughput": 778.51, "total_tokens": 679936} {"current_steps": 500, "total_steps": 40000, "loss": 1.3022, "lr": 4.998080291543914e-05, "epoch": 0.016004097048844503, "percentage": 1.25, "elapsed_time": "0:14:35", "remaining_time": "19:12:13", "throughput": 784.56, "total_tokens": 686576} {"current_steps": 505, "total_steps": 40000, "loss": 1.7466, "lr": 4.9980416327401826e-05, "epoch": 0.01616413801933295, "percentage": 1.26, "elapsed_time": "0:14:36", "remaining_time": "19:02:56", "throughput": 790.78, "total_tokens": 693392} {"current_steps": 510, "total_steps": 40000, "loss": 1.005, "lr": 4.998002588707038e-05, "epoch": 0.016324178989821393, "percentage": 1.27, "elapsed_time": "0:14:38", "remaining_time": "18:53:49", "throughput": 797.56, "total_tokens": 700720} {"current_steps": 515, "total_steps": 40000, "loss": 1.4077, "lr": 4.997963159450503e-05, "epoch": 0.01648421996030984, "percentage": 1.29, "elapsed_time": "0:14:40", "remaining_time": "18:44:53", "throughput": 804.33, "total_tokens": 708064} {"current_steps": 520, "total_steps": 40000, "loss": 1.5913, "lr": 4.9979233449766575e-05, "epoch": 0.016644260930798283, "percentage": 1.3, "elapsed_time": "0:14:42", "remaining_time": "18:36:07", "throughput": 811.31, "total_tokens": 715616} {"current_steps": 525, "total_steps": 40000, "loss": 1.2452, "lr": 4.997883145291641e-05, "epoch": 0.01680430190128673, "percentage": 1.31, "elapsed_time": "0:14:43", "remaining_time": "18:27:31", "throughput": 817.35, "total_tokens": 722352} {"current_steps": 530, "total_steps": 40000, "loss": 1.3922, "lr": 4.9978425604016536e-05, "epoch": 0.016964342871775173, "percentage": 1.32, "elapsed_time": "0:14:45", "remaining_time": "18:19:06", "throughput": 823.7, "total_tokens": 729408} {"current_steps": 535, "total_steps": 40000, "loss": 1.6123, "lr": 4.9978015903129536e-05, "epoch": 0.01712438384226362, "percentage": 1.34, "elapsed_time": "0:14:47", "remaining_time": "18:10:49", "throughput": 830.07, "total_tokens": 736480} {"current_steps": 540, "total_steps": 40000, "loss": 1.3945, "lr": 4.997760235031859e-05, "epoch": 0.017284424812752063, "percentage": 1.35, "elapsed_time": "0:14:48", "remaining_time": "18:02:41", "throughput": 836.1, "total_tokens": 743280} {"current_steps": 545, "total_steps": 40000, "loss": 1.1716, "lr": 4.9977184945647473e-05, "epoch": 0.01744446578324051, "percentage": 1.36, "elapsed_time": "0:14:50", "remaining_time": "17:54:43", "throughput": 842.16, "total_tokens": 750128} {"current_steps": 550, "total_steps": 40000, "loss": 1.5389, "lr": 4.997676368918055e-05, "epoch": 0.017604506753728953, "percentage": 1.38, "elapsed_time": "0:14:52", "remaining_time": "17:46:52", "throughput": 848.4, "total_tokens": 757152} {"current_steps": 555, "total_steps": 40000, "loss": 1.4058, "lr": 4.9976338580982794e-05, "epoch": 0.0177645477242174, "percentage": 1.39, "elapsed_time": "0:14:54", "remaining_time": "17:39:11", "throughput": 854.02, "total_tokens": 763648} {"current_steps": 560, "total_steps": 40000, "loss": 1.3518, "lr": 4.9975909621119755e-05, "epoch": 0.017924588694705843, "percentage": 1.4, "elapsed_time": "0:14:55", "remaining_time": "17:31:37", "throughput": 860.5, "total_tokens": 770928} {"current_steps": 565, "total_steps": 40000, "loss": 1.5465, "lr": 4.997547680965758e-05, "epoch": 0.01808462966519429, "percentage": 1.41, "elapsed_time": "0:14:57", "remaining_time": "17:24:12", "throughput": 866.86, "total_tokens": 778128} {"current_steps": 570, "total_steps": 40000, "loss": 1.338, "lr": 4.997504014666302e-05, "epoch": 0.018244670635682733, "percentage": 1.43, "elapsed_time": "0:14:59", "remaining_time": "17:16:54", "throughput": 872.67, "total_tokens": 784848} {"current_steps": 575, "total_steps": 40000, "loss": 1.1269, "lr": 4.997459963220342e-05, "epoch": 0.01840471160617118, "percentage": 1.44, "elapsed_time": "0:15:01", "remaining_time": "17:09:44", "throughput": 878.63, "total_tokens": 791744} {"current_steps": 580, "total_steps": 40000, "loss": 1.4166, "lr": 4.997415526634671e-05, "epoch": 0.018564752576659623, "percentage": 1.45, "elapsed_time": "0:15:02", "remaining_time": "17:02:42", "throughput": 884.58, "total_tokens": 798640} {"current_steps": 585, "total_steps": 40000, "loss": 1.325, "lr": 4.99737070491614e-05, "epoch": 0.01872479354714807, "percentage": 1.46, "elapsed_time": "0:15:04", "remaining_time": "16:55:46", "throughput": 890.85, "total_tokens": 805840} {"current_steps": 590, "total_steps": 40000, "loss": 1.0425, "lr": 4.997325498071663e-05, "epoch": 0.018884834517636517, "percentage": 1.47, "elapsed_time": "0:15:06", "remaining_time": "16:48:57", "throughput": 896.57, "total_tokens": 812560} {"current_steps": 595, "total_steps": 40000, "loss": 1.4546, "lr": 4.997279906108211e-05, "epoch": 0.01904487548812496, "percentage": 1.49, "elapsed_time": "0:15:08", "remaining_time": "16:42:16", "throughput": 902.63, "total_tokens": 819616} {"current_steps": 600, "total_steps": 40000, "loss": 1.4877, "lr": 4.9972339290328155e-05, "epoch": 0.019204916458613407, "percentage": 1.5, "elapsed_time": "0:15:09", "remaining_time": "16:35:40", "throughput": 907.95, "total_tokens": 826016} {"current_steps": 600, "total_steps": 40000, "eval_loss": 1.322749137878418, "epoch": 0.019204916458613407, "percentage": 1.5, "elapsed_time": "0:20:58", "remaining_time": "22:56:52", "throughput": 656.58, "total_tokens": 826016} {"current_steps": 605, "total_steps": 40000, "loss": 1.2122, "lr": 4.9971875668525646e-05, "epoch": 0.01936495742910185, "percentage": 1.51, "elapsed_time": "0:21:01", "remaining_time": "22:48:57", "throughput": 660.17, "total_tokens": 832736} {"current_steps": 610, "total_steps": 40000, "loss": 1.347, "lr": 4.997140819574609e-05, "epoch": 0.019524998399590297, "percentage": 1.52, "elapsed_time": "0:21:03", "remaining_time": "22:39:25", "throughput": 665.25, "total_tokens": 840304} {"current_steps": 615, "total_steps": 40000, "loss": 1.0804, "lr": 4.997093687206159e-05, "epoch": 0.01968503937007874, "percentage": 1.54, "elapsed_time": "0:21:04", "remaining_time": "22:30:03", "throughput": 669.46, "total_tokens": 846784} {"current_steps": 620, "total_steps": 40000, "loss": 1.2516, "lr": 4.997046169754482e-05, "epoch": 0.019845080340567187, "percentage": 1.55, "elapsed_time": "0:21:06", "remaining_time": "22:20:49", "throughput": 673.88, "total_tokens": 853536} {"current_steps": 625, "total_steps": 40000, "loss": 1.3086, "lr": 4.996998267226905e-05, "epoch": 0.02000512131105563, "percentage": 1.56, "elapsed_time": "0:21:08", "remaining_time": "22:11:45", "throughput": 678.29, "total_tokens": 860304} {"current_steps": 630, "total_steps": 40000, "loss": 1.2913, "lr": 4.996949979630817e-05, "epoch": 0.020165162281544077, "percentage": 1.57, "elapsed_time": "0:21:10", "remaining_time": "22:02:49", "throughput": 682.71, "total_tokens": 867088} {"current_steps": 635, "total_steps": 40000, "loss": 0.9854, "lr": 4.996901306973663e-05, "epoch": 0.02032520325203252, "percentage": 1.59, "elapsed_time": "0:21:11", "remaining_time": "21:54:02", "throughput": 686.89, "total_tokens": 873600} {"current_steps": 640, "total_steps": 40000, "loss": 1.1794, "lr": 4.996852249262949e-05, "epoch": 0.020485244222520967, "percentage": 1.6, "elapsed_time": "0:21:13", "remaining_time": "21:45:23", "throughput": 691.55, "total_tokens": 880720} {"current_steps": 645, "total_steps": 40000, "loss": 1.4952, "lr": 4.996802806506241e-05, "epoch": 0.02064528519300941, "percentage": 1.61, "elapsed_time": "0:21:15", "remaining_time": "21:36:52", "throughput": 696.12, "total_tokens": 887760} {"current_steps": 650, "total_steps": 40000, "loss": 0.8562, "lr": 4.996752978711164e-05, "epoch": 0.020805326163497857, "percentage": 1.62, "elapsed_time": "0:21:17", "remaining_time": "21:28:29", "throughput": 700.69, "total_tokens": 894800} {"current_steps": 655, "total_steps": 40000, "loss": 1.2553, "lr": 4.996702765885401e-05, "epoch": 0.0209653671339863, "percentage": 1.64, "elapsed_time": "0:21:18", "remaining_time": "21:20:13", "throughput": 705.26, "total_tokens": 901856} {"current_steps": 660, "total_steps": 40000, "loss": 0.9647, "lr": 4.9966521680366964e-05, "epoch": 0.021125408104474747, "percentage": 1.65, "elapsed_time": "0:21:20", "remaining_time": "21:12:05", "throughput": 709.29, "total_tokens": 908240} {"current_steps": 665, "total_steps": 40000, "loss": 1.2859, "lr": 4.9966011851728524e-05, "epoch": 0.02128544907496319, "percentage": 1.66, "elapsed_time": "0:21:22", "remaining_time": "21:04:04", "throughput": 713.85, "total_tokens": 915312} {"current_steps": 670, "total_steps": 40000, "loss": 1.3215, "lr": 4.996549817301731e-05, "epoch": 0.021445490045451637, "percentage": 1.68, "elapsed_time": "0:21:23", "remaining_time": "20:56:10", "throughput": 718.35, "total_tokens": 922336} {"current_steps": 675, "total_steps": 40000, "loss": 1.3489, "lr": 4.9964980644312544e-05, "epoch": 0.02160553101594008, "percentage": 1.69, "elapsed_time": "0:21:25", "remaining_time": "20:48:23", "throughput": 722.66, "total_tokens": 929120} {"current_steps": 680, "total_steps": 40000, "loss": 1.4993, "lr": 4.996445926569403e-05, "epoch": 0.021765571986428527, "percentage": 1.7, "elapsed_time": "0:21:27", "remaining_time": "20:40:43", "throughput": 726.99, "total_tokens": 935952} {"current_steps": 685, "total_steps": 40000, "loss": 0.9173, "lr": 4.996393403724218e-05, "epoch": 0.02192561295691697, "percentage": 1.71, "elapsed_time": "0:21:29", "remaining_time": "20:33:10", "throughput": 731.18, "total_tokens": 942608} {"current_steps": 690, "total_steps": 40000, "loss": 1.3786, "lr": 4.9963404959037985e-05, "epoch": 0.022085653927405417, "percentage": 1.73, "elapsed_time": "0:21:30", "remaining_time": "20:25:44", "throughput": 735.97, "total_tokens": 950080} {"current_steps": 695, "total_steps": 40000, "loss": 1.2705, "lr": 4.996287203116303e-05, "epoch": 0.02224569489789386, "percentage": 1.74, "elapsed_time": "0:21:32", "remaining_time": "20:18:24", "throughput": 740.27, "total_tokens": 956912} {"current_steps": 700, "total_steps": 40000, "loss": 1.3206, "lr": 4.996233525369951e-05, "epoch": 0.022405735868382307, "percentage": 1.75, "elapsed_time": "0:21:34", "remaining_time": "20:11:10", "throughput": 744.21, "total_tokens": 963296} {"current_steps": 705, "total_steps": 40000, "loss": 1.3208, "lr": 4.99617946267302e-05, "epoch": 0.02256577683887075, "percentage": 1.76, "elapsed_time": "0:21:36", "remaining_time": "20:04:02", "throughput": 748.19, "total_tokens": 969744} {"current_steps": 710, "total_steps": 40000, "loss": 1.1084, "lr": 4.996125015033846e-05, "epoch": 0.022725817809359197, "percentage": 1.77, "elapsed_time": "0:21:37", "remaining_time": "19:57:00", "throughput": 752.41, "total_tokens": 976512} {"current_steps": 715, "total_steps": 40000, "loss": 1.549, "lr": 4.996070182460827e-05, "epoch": 0.02288585877984764, "percentage": 1.79, "elapsed_time": "0:21:39", "remaining_time": "19:50:04", "throughput": 757.0, "total_tokens": 983792} {"current_steps": 720, "total_steps": 40000, "loss": 0.9447, "lr": 4.996014964962418e-05, "epoch": 0.023045899750336087, "percentage": 1.8, "elapsed_time": "0:21:41", "remaining_time": "19:43:14", "throughput": 761.36, "total_tokens": 990784} {"current_steps": 725, "total_steps": 40000, "loss": 1.1206, "lr": 4.9959593625471344e-05, "epoch": 0.02320594072082453, "percentage": 1.81, "elapsed_time": "0:21:43", "remaining_time": "19:36:30", "throughput": 765.84, "total_tokens": 997936} {"current_steps": 730, "total_steps": 40000, "loss": 1.3934, "lr": 4.995903375223552e-05, "epoch": 0.023365981691312977, "percentage": 1.82, "elapsed_time": "0:21:44", "remaining_time": "19:29:51", "throughput": 770.1, "total_tokens": 1004832} {"current_steps": 735, "total_steps": 40000, "loss": 1.0783, "lr": 4.995847003000302e-05, "epoch": 0.02352602266180142, "percentage": 1.84, "elapsed_time": "0:21:46", "remaining_time": "19:23:18", "throughput": 774.36, "total_tokens": 1011744} {"current_steps": 740, "total_steps": 40000, "loss": 1.1087, "lr": 4.9957902458860804e-05, "epoch": 0.023686063632289867, "percentage": 1.85, "elapsed_time": "0:21:48", "remaining_time": "19:16:50", "throughput": 778.27, "total_tokens": 1018208} {"current_steps": 745, "total_steps": 40000, "loss": 1.2584, "lr": 4.995733103889639e-05, "epoch": 0.02384610460277831, "percentage": 1.86, "elapsed_time": "0:21:50", "remaining_time": "19:10:26", "throughput": 782.4, "total_tokens": 1024960} {"current_steps": 750, "total_steps": 40000, "loss": 1.6266, "lr": 4.99567557701979e-05, "epoch": 0.024006145573266757, "percentage": 1.88, "elapsed_time": "0:21:51", "remaining_time": "19:04:08", "throughput": 786.62, "total_tokens": 1031856} {"current_steps": 755, "total_steps": 40000, "loss": 1.465, "lr": 4.995617665285403e-05, "epoch": 0.0241661865437552, "percentage": 1.89, "elapsed_time": "0:21:53", "remaining_time": "18:57:55", "throughput": 790.76, "total_tokens": 1038656} {"current_steps": 760, "total_steps": 40000, "loss": 0.8611, "lr": 4.99555936869541e-05, "epoch": 0.024326227514243647, "percentage": 1.9, "elapsed_time": "0:21:55", "remaining_time": "18:51:47", "throughput": 795.03, "total_tokens": 1045648} {"current_steps": 765, "total_steps": 40000, "loss": 1.4581, "lr": 4.995500687258803e-05, "epoch": 0.02448626848473209, "percentage": 1.91, "elapsed_time": "0:21:56", "remaining_time": "18:45:43", "throughput": 799.35, "total_tokens": 1052720} {"current_steps": 770, "total_steps": 40000, "loss": 1.3272, "lr": 4.995441620984628e-05, "epoch": 0.024646309455220537, "percentage": 1.93, "elapsed_time": "0:21:58", "remaining_time": "18:39:45", "throughput": 803.33, "total_tokens": 1059360} {"current_steps": 775, "total_steps": 40000, "loss": 1.5654, "lr": 4.995382169881996e-05, "epoch": 0.02480635042570898, "percentage": 1.94, "elapsed_time": "0:22:00", "remaining_time": "18:33:51", "throughput": 807.07, "total_tokens": 1065696} {"current_steps": 780, "total_steps": 40000, "loss": 1.2737, "lr": 4.9953223339600755e-05, "epoch": 0.024966391396197427, "percentage": 1.95, "elapsed_time": "0:22:02", "remaining_time": "18:28:02", "throughput": 811.2, "total_tokens": 1072560} {"current_steps": 785, "total_steps": 40000, "loss": 0.964, "lr": 4.995262113228091e-05, "epoch": 0.025126432366685873, "percentage": 1.96, "elapsed_time": "0:22:03", "remaining_time": "18:22:16", "throughput": 815.18, "total_tokens": 1079232} {"current_steps": 790, "total_steps": 40000, "loss": 1.419, "lr": 4.995201507695332e-05, "epoch": 0.025286473337174317, "percentage": 1.98, "elapsed_time": "0:22:05", "remaining_time": "18:16:35", "throughput": 819.22, "total_tokens": 1086000} {"current_steps": 795, "total_steps": 40000, "loss": 1.1916, "lr": 4.995140517371144e-05, "epoch": 0.025446514307662763, "percentage": 1.99, "elapsed_time": "0:22:07", "remaining_time": "18:10:59", "throughput": 823.29, "total_tokens": 1092816} {"current_steps": 800, "total_steps": 40000, "loss": 1.3337, "lr": 4.995079142264932e-05, "epoch": 0.025606555278151207, "percentage": 2.0, "elapsed_time": "0:22:09", "remaining_time": "18:05:26", "throughput": 827.6, "total_tokens": 1099968} {"current_steps": 800, "total_steps": 40000, "eval_loss": 1.2205781936645508, "epoch": 0.025606555278151207, "percentage": 2.0, "elapsed_time": "0:27:56", "remaining_time": "22:49:24", "throughput": 655.98, "total_tokens": 1099968} {"current_steps": 805, "total_steps": 40000, "loss": 1.4324, "lr": 4.995017382386162e-05, "epoch": 0.025766596248639653, "percentage": 2.01, "elapsed_time": "0:28:00", "remaining_time": "22:43:25", "throughput": 658.93, "total_tokens": 1107088} {"current_steps": 810, "total_steps": 40000, "loss": 0.8714, "lr": 4.994955237744356e-05, "epoch": 0.025926637219128097, "percentage": 2.02, "elapsed_time": "0:28:01", "remaining_time": "22:36:13", "throughput": 662.45, "total_tokens": 1114160} {"current_steps": 815, "total_steps": 40000, "loss": 1.2628, "lr": 4.994892708349101e-05, "epoch": 0.026086678189616543, "percentage": 2.04, "elapsed_time": "0:28:03", "remaining_time": "22:29:07", "throughput": 665.7, "total_tokens": 1120784} {"current_steps": 820, "total_steps": 40000, "loss": 1.1351, "lr": 4.994829794210035e-05, "epoch": 0.026246719160104987, "percentage": 2.05, "elapsed_time": "0:28:05", "remaining_time": "22:22:06", "throughput": 668.84, "total_tokens": 1127232} {"current_steps": 825, "total_steps": 40000, "loss": 1.007, "lr": 4.994766495336864e-05, "epoch": 0.026406760130593433, "percentage": 2.06, "elapsed_time": "0:28:07", "remaining_time": "22:15:10", "throughput": 672.42, "total_tokens": 1134416} {"current_steps": 830, "total_steps": 40000, "loss": 0.8153, "lr": 4.994702811739348e-05, "epoch": 0.026566801101081877, "percentage": 2.08, "elapsed_time": "0:28:08", "remaining_time": "22:08:19", "throughput": 675.91, "total_tokens": 1141488} {"current_steps": 835, "total_steps": 40000, "loss": 0.9723, "lr": 4.994638743427308e-05, "epoch": 0.026726842071570323, "percentage": 2.09, "elapsed_time": "0:28:10", "remaining_time": "22:01:33", "throughput": 679.43, "total_tokens": 1148608} {"current_steps": 840, "total_steps": 40000, "loss": 1.452, "lr": 4.994574290410624e-05, "epoch": 0.026886883042058767, "percentage": 2.1, "elapsed_time": "0:28:12", "remaining_time": "21:54:52", "throughput": 682.81, "total_tokens": 1155504} {"current_steps": 845, "total_steps": 40000, "loss": 1.1103, "lr": 4.9945094526992364e-05, "epoch": 0.027046924012547213, "percentage": 2.11, "elapsed_time": "0:28:14", "remaining_time": "21:48:15", "throughput": 686.02, "total_tokens": 1162128} {"current_steps": 850, "total_steps": 40000, "loss": 1.1044, "lr": 4.994444230303142e-05, "epoch": 0.027206964983035656, "percentage": 2.12, "elapsed_time": "0:28:15", "remaining_time": "21:41:44", "throughput": 689.42, "total_tokens": 1169088} {"current_steps": 855, "total_steps": 40000, "loss": 1.4213, "lr": 4.994378623232402e-05, "epoch": 0.027367005953524103, "percentage": 2.14, "elapsed_time": "0:28:17", "remaining_time": "21:35:16", "throughput": 692.7, "total_tokens": 1175840} {"current_steps": 860, "total_steps": 40000, "loss": 1.1944, "lr": 4.99431263149713e-05, "epoch": 0.027527046924012546, "percentage": 2.15, "elapsed_time": "0:28:19", "remaining_time": "21:28:53", "throughput": 695.98, "total_tokens": 1182624} {"current_steps": 865, "total_steps": 40000, "loss": 1.5011, "lr": 4.9942462551075056e-05, "epoch": 0.027687087894500993, "percentage": 2.16, "elapsed_time": "0:28:20", "remaining_time": "21:22:35", "throughput": 699.32, "total_tokens": 1189504} {"current_steps": 870, "total_steps": 40000, "loss": 1.2137, "lr": 4.994179494073764e-05, "epoch": 0.027847128864989436, "percentage": 2.17, "elapsed_time": "0:28:22", "remaining_time": "21:16:21", "throughput": 702.69, "total_tokens": 1196448} {"current_steps": 875, "total_steps": 40000, "loss": 1.1347, "lr": 4.9941123484062e-05, "epoch": 0.028007169835477883, "percentage": 2.19, "elapsed_time": "0:28:24", "remaining_time": "21:10:11", "throughput": 706.04, "total_tokens": 1203376} {"current_steps": 880, "total_steps": 40000, "loss": 1.2748, "lr": 4.99404481811517e-05, "epoch": 0.028167210805966326, "percentage": 2.2, "elapsed_time": "0:28:26", "remaining_time": "21:04:05", "throughput": 709.16, "total_tokens": 1209936} {"current_steps": 885, "total_steps": 40000, "loss": 0.9779, "lr": 4.9939769032110864e-05, "epoch": 0.028327251776454773, "percentage": 2.21, "elapsed_time": "0:28:27", "remaining_time": "20:58:04", "throughput": 712.29, "total_tokens": 1216496} {"current_steps": 890, "total_steps": 40000, "loss": 1.099, "lr": 4.993908603704423e-05, "epoch": 0.028487292746943216, "percentage": 2.23, "elapsed_time": "0:28:29", "remaining_time": "20:52:06", "throughput": 715.32, "total_tokens": 1222928} {"current_steps": 895, "total_steps": 40000, "loss": 1.2695, "lr": 4.9938399196057126e-05, "epoch": 0.028647333717431663, "percentage": 2.24, "elapsed_time": "0:28:31", "remaining_time": "20:46:13", "throughput": 718.62, "total_tokens": 1229808} {"current_steps": 900, "total_steps": 40000, "loss": 0.8704, "lr": 4.993770850925547e-05, "epoch": 0.028807374687920106, "percentage": 2.25, "elapsed_time": "0:28:33", "remaining_time": "20:40:23", "throughput": 721.91, "total_tokens": 1236688} {"current_steps": 905, "total_steps": 40000, "loss": 1.1344, "lr": 4.993701397674577e-05, "epoch": 0.028967415658408553, "percentage": 2.26, "elapsed_time": "0:28:34", "remaining_time": "20:34:38", "throughput": 725.14, "total_tokens": 1243472} {"current_steps": 910, "total_steps": 40000, "loss": 1.0555, "lr": 4.993631559863515e-05, "epoch": 0.029127456628896996, "percentage": 2.27, "elapsed_time": "0:28:36", "remaining_time": "20:28:56", "throughput": 728.55, "total_tokens": 1250592} {"current_steps": 915, "total_steps": 40000, "loss": 1.0344, "lr": 4.9935613375031283e-05, "epoch": 0.029287497599385443, "percentage": 2.29, "elapsed_time": "0:28:38", "remaining_time": "20:23:17", "throughput": 731.63, "total_tokens": 1257152} {"current_steps": 920, "total_steps": 40000, "loss": 1.1411, "lr": 4.993490730604248e-05, "epoch": 0.029447538569873886, "percentage": 2.3, "elapsed_time": "0:28:40", "remaining_time": "20:17:43", "throughput": 734.87, "total_tokens": 1263984} {"current_steps": 925, "total_steps": 40000, "loss": 1.2989, "lr": 4.993419739177761e-05, "epoch": 0.029607579540362333, "percentage": 2.31, "elapsed_time": "0:28:41", "remaining_time": "20:12:12", "throughput": 738.33, "total_tokens": 1271216} {"current_steps": 930, "total_steps": 40000, "loss": 1.0564, "lr": 4.9933483632346164e-05, "epoch": 0.029767620510850776, "percentage": 2.33, "elapsed_time": "0:28:43", "remaining_time": "20:06:44", "throughput": 741.64, "total_tokens": 1278208} {"current_steps": 935, "total_steps": 40000, "loss": 1.1524, "lr": 4.993276602785821e-05, "epoch": 0.029927661481339223, "percentage": 2.34, "elapsed_time": "0:28:45", "remaining_time": "20:01:20", "throughput": 744.73, "total_tokens": 1284816} {"current_steps": 940, "total_steps": 40000, "loss": 1.3674, "lr": 4.993204457842441e-05, "epoch": 0.030087702451827666, "percentage": 2.35, "elapsed_time": "0:28:46", "remaining_time": "19:56:00", "throughput": 747.73, "total_tokens": 1291296} {"current_steps": 945, "total_steps": 40000, "loss": 1.6892, "lr": 4.993131928415602e-05, "epoch": 0.030247743422316113, "percentage": 2.36, "elapsed_time": "0:28:48", "remaining_time": "19:50:43", "throughput": 750.68, "total_tokens": 1297696} {"current_steps": 950, "total_steps": 40000, "loss": 0.972, "lr": 4.993059014516489e-05, "epoch": 0.030407784392804556, "percentage": 2.38, "elapsed_time": "0:28:50", "remaining_time": "19:45:29", "throughput": 753.8, "total_tokens": 1304384} {"current_steps": 955, "total_steps": 40000, "loss": 1.317, "lr": 4.9929857161563464e-05, "epoch": 0.030567825363293003, "percentage": 2.39, "elapsed_time": "0:28:52", "remaining_time": "19:40:18", "throughput": 757.54, "total_tokens": 1312176} {"current_steps": 960, "total_steps": 40000, "loss": 0.9696, "lr": 4.992912033346477e-05, "epoch": 0.030727866333781446, "percentage": 2.4, "elapsed_time": "0:28:53", "remaining_time": "19:35:11", "throughput": 760.84, "total_tokens": 1319216} {"current_steps": 965, "total_steps": 40000, "loss": 0.9472, "lr": 4.992837966098245e-05, "epoch": 0.030887907304269893, "percentage": 2.41, "elapsed_time": "0:28:55", "remaining_time": "19:30:07", "throughput": 764.2, "total_tokens": 1326368} {"current_steps": 970, "total_steps": 40000, "loss": 1.3939, "lr": 4.992763514423071e-05, "epoch": 0.031047948274758336, "percentage": 2.43, "elapsed_time": "0:28:57", "remaining_time": "19:25:06", "throughput": 767.4, "total_tokens": 1333248} {"current_steps": 975, "total_steps": 40000, "loss": 1.2407, "lr": 4.992688678332437e-05, "epoch": 0.031207989245246783, "percentage": 2.44, "elapsed_time": "0:28:59", "remaining_time": "19:20:08", "throughput": 770.54, "total_tokens": 1340032} {"current_steps": 980, "total_steps": 40000, "loss": 1.1083, "lr": 4.992613457837884e-05, "epoch": 0.031368030215735226, "percentage": 2.45, "elapsed_time": "0:29:00", "remaining_time": "19:15:13", "throughput": 773.58, "total_tokens": 1346672} {"current_steps": 985, "total_steps": 40000, "loss": 1.0793, "lr": 4.992537852951011e-05, "epoch": 0.03152807118622367, "percentage": 2.46, "elapsed_time": "0:29:02", "remaining_time": "19:10:21", "throughput": 776.82, "total_tokens": 1353664} {"current_steps": 990, "total_steps": 40000, "loss": 0.9967, "lr": 4.9924618636834785e-05, "epoch": 0.03168811215671212, "percentage": 2.48, "elapsed_time": "0:29:04", "remaining_time": "19:05:32", "throughput": 780.25, "total_tokens": 1360992} {"current_steps": 995, "total_steps": 40000, "loss": 1.3929, "lr": 4.9923854900470046e-05, "epoch": 0.03184815312720057, "percentage": 2.49, "elapsed_time": "0:29:06", "remaining_time": "19:00:46", "throughput": 783.29, "total_tokens": 1367648} {"current_steps": 1000, "total_steps": 40000, "loss": 1.2957, "lr": 4.992308732053367e-05, "epoch": 0.032008194097689006, "percentage": 2.5, "elapsed_time": "0:29:07", "remaining_time": "18:56:02", "throughput": 786.53, "total_tokens": 1374672} {"current_steps": 1000, "total_steps": 40000, "eval_loss": 1.148005723953247, "epoch": 0.032008194097689006, "percentage": 2.5, "elapsed_time": "0:34:55", "remaining_time": "22:42:22", "throughput": 655.87, "total_tokens": 1374672} {"current_steps": 1005, "total_steps": 40000, "loss": 0.9381, "lr": 4.992231589714402e-05, "epoch": 0.03216823506817745, "percentage": 2.51, "elapsed_time": "0:34:59", "remaining_time": "22:37:34", "throughput": 658.09, "total_tokens": 1381504} {"current_steps": 1010, "total_steps": 40000, "loss": 0.9645, "lr": 4.992154063042007e-05, "epoch": 0.0323282760386659, "percentage": 2.53, "elapsed_time": "0:35:01", "remaining_time": "22:31:47", "throughput": 660.84, "total_tokens": 1388448} {"current_steps": 1015, "total_steps": 40000, "loss": 0.6509, "lr": 4.992076152048136e-05, "epoch": 0.03248831700915435, "percentage": 2.54, "elapsed_time": "0:35:02", "remaining_time": "22:26:04", "throughput": 663.41, "total_tokens": 1394992} {"current_steps": 1020, "total_steps": 40000, "loss": 1.3882, "lr": 4.991997856744807e-05, "epoch": 0.032648357979642786, "percentage": 2.55, "elapsed_time": "0:35:04", "remaining_time": "22:20:24", "throughput": 666.06, "total_tokens": 1401712} {"current_steps": 1025, "total_steps": 40000, "loss": 1.225, "lr": 4.9919191771440905e-05, "epoch": 0.03280839895013123, "percentage": 2.56, "elapsed_time": "0:35:06", "remaining_time": "22:14:47", "throughput": 668.63, "total_tokens": 1408288} {"current_steps": 1030, "total_steps": 40000, "loss": 1.1423, "lr": 4.991840113258122e-05, "epoch": 0.03296843992061968, "percentage": 2.57, "elapsed_time": "0:35:07", "remaining_time": "22:09:14", "throughput": 671.37, "total_tokens": 1415216} {"current_steps": 1035, "total_steps": 40000, "loss": 1.2859, "lr": 4.9917606650990933e-05, "epoch": 0.03312848089110813, "percentage": 2.59, "elapsed_time": "0:35:09", "remaining_time": "22:03:44", "throughput": 674.16, "total_tokens": 1422272} {"current_steps": 1040, "total_steps": 40000, "loss": 1.3868, "lr": 4.9916808326792566e-05, "epoch": 0.033288521861596566, "percentage": 2.6, "elapsed_time": "0:35:11", "remaining_time": "21:58:17", "throughput": 677.04, "total_tokens": 1429520} {"current_steps": 1045, "total_steps": 40000, "loss": 1.2422, "lr": 4.9916006160109235e-05, "epoch": 0.03344856283208501, "percentage": 2.61, "elapsed_time": "0:35:13", "remaining_time": "21:52:53", "throughput": 679.63, "total_tokens": 1436160} {"current_steps": 1050, "total_steps": 40000, "loss": 1.3802, "lr": 4.991520015106464e-05, "epoch": 0.03360860380257346, "percentage": 2.62, "elapsed_time": "0:35:14", "remaining_time": "21:47:32", "throughput": 682.36, "total_tokens": 1443120} {"current_steps": 1055, "total_steps": 40000, "loss": 1.1933, "lr": 4.991439029978308e-05, "epoch": 0.03376864477306191, "percentage": 2.64, "elapsed_time": "0:35:16", "remaining_time": "21:42:14", "throughput": 685.01, "total_tokens": 1449904} {"current_steps": 1060, "total_steps": 40000, "loss": 1.7153, "lr": 4.9913576606389434e-05, "epoch": 0.033928685743550346, "percentage": 2.65, "elapsed_time": "0:35:18", "remaining_time": "21:36:59", "throughput": 687.53, "total_tokens": 1456432} {"current_steps": 1065, "total_steps": 40000, "loss": 0.9681, "lr": 4.991275907100919e-05, "epoch": 0.03408872671403879, "percentage": 2.66, "elapsed_time": "0:35:20", "remaining_time": "21:31:47", "throughput": 690.16, "total_tokens": 1463200} {"current_steps": 1070, "total_steps": 40000, "loss": 1.0195, "lr": 4.9911937693768434e-05, "epoch": 0.03424876768452724, "percentage": 2.67, "elapsed_time": "0:35:21", "remaining_time": "21:26:38", "throughput": 692.83, "total_tokens": 1470064} {"current_steps": 1075, "total_steps": 40000, "loss": 1.1034, "lr": 4.991111247479382e-05, "epoch": 0.03440880865501569, "percentage": 2.69, "elapsed_time": "0:35:23", "remaining_time": "21:21:32", "throughput": 695.68, "total_tokens": 1477312} {"current_steps": 1080, "total_steps": 40000, "loss": 0.8957, "lr": 4.9910283414212605e-05, "epoch": 0.034568849625504126, "percentage": 2.7, "elapsed_time": "0:35:25", "remaining_time": "21:16:29", "throughput": 698.34, "total_tokens": 1484176} {"current_steps": 1085, "total_steps": 40000, "loss": 1.2903, "lr": 4.990945051215265e-05, "epoch": 0.03472889059599257, "percentage": 2.71, "elapsed_time": "0:35:27", "remaining_time": "21:11:28", "throughput": 701.02, "total_tokens": 1491088} {"current_steps": 1090, "total_steps": 40000, "loss": 0.8703, "lr": 4.99086137687424e-05, "epoch": 0.03488893156648102, "percentage": 2.73, "elapsed_time": "0:35:28", "remaining_time": "21:06:30", "throughput": 703.58, "total_tokens": 1497760} {"current_steps": 1095, "total_steps": 40000, "loss": 0.8066, "lr": 4.9907773184110874e-05, "epoch": 0.03504897253696947, "percentage": 2.74, "elapsed_time": "0:35:30", "remaining_time": "21:01:36", "throughput": 706.25, "total_tokens": 1504672} {"current_steps": 1100, "total_steps": 40000, "loss": 0.9148, "lr": 4.9906928758387715e-05, "epoch": 0.035209013507457906, "percentage": 2.75, "elapsed_time": "0:35:32", "remaining_time": "20:56:43", "throughput": 709.11, "total_tokens": 1511984} {"current_steps": 1105, "total_steps": 40000, "loss": 1.2105, "lr": 4.9906080491703146e-05, "epoch": 0.03536905447794635, "percentage": 2.76, "elapsed_time": "0:35:33", "remaining_time": "20:51:53", "throughput": 711.78, "total_tokens": 1518912} {"current_steps": 1110, "total_steps": 40000, "loss": 1.019, "lr": 4.990522838418797e-05, "epoch": 0.0355290954484348, "percentage": 2.77, "elapsed_time": "0:35:35", "remaining_time": "20:47:06", "throughput": 714.27, "total_tokens": 1525472} {"current_steps": 1115, "total_steps": 40000, "loss": 1.3062, "lr": 4.9904372435973604e-05, "epoch": 0.03568913641892325, "percentage": 2.79, "elapsed_time": "0:35:37", "remaining_time": "20:42:21", "throughput": 716.74, "total_tokens": 1531984} {"current_steps": 1120, "total_steps": 40000, "loss": 1.2492, "lr": 4.990351264719203e-05, "epoch": 0.035849177389411686, "percentage": 2.8, "elapsed_time": "0:35:39", "remaining_time": "20:37:39", "throughput": 719.58, "total_tokens": 1539296} {"current_steps": 1125, "total_steps": 40000, "loss": 1.1632, "lr": 4.990264901797586e-05, "epoch": 0.03600921835990013, "percentage": 2.81, "elapsed_time": "0:35:40", "remaining_time": "20:32:59", "throughput": 722.18, "total_tokens": 1546112} {"current_steps": 1130, "total_steps": 40000, "loss": 1.154, "lr": 4.990178154845826e-05, "epoch": 0.03616925933038858, "percentage": 2.83, "elapsed_time": "0:35:42", "remaining_time": "20:28:22", "throughput": 724.83, "total_tokens": 1553040} {"current_steps": 1135, "total_steps": 40000, "loss": 1.0206, "lr": 4.9900910238773014e-05, "epoch": 0.03632930030087703, "percentage": 2.84, "elapsed_time": "0:35:44", "remaining_time": "20:23:47", "throughput": 727.26, "total_tokens": 1559504} {"current_steps": 1140, "total_steps": 40000, "loss": 1.1805, "lr": 4.990003508905448e-05, "epoch": 0.036489341271365466, "percentage": 2.85, "elapsed_time": "0:35:46", "remaining_time": "20:19:15", "throughput": 729.87, "total_tokens": 1566384} {"current_steps": 1145, "total_steps": 40000, "loss": 1.4606, "lr": 4.989915609943763e-05, "epoch": 0.03664938224185391, "percentage": 2.86, "elapsed_time": "0:35:47", "remaining_time": "20:14:45", "throughput": 732.4, "total_tokens": 1573072} {"current_steps": 1150, "total_steps": 40000, "loss": 0.9304, "lr": 4.9898273270058e-05, "epoch": 0.03680942321234236, "percentage": 2.88, "elapsed_time": "0:35:49", "remaining_time": "20:10:18", "throughput": 735.03, "total_tokens": 1580000} {"current_steps": 1155, "total_steps": 40000, "loss": 1.0865, "lr": 4.989738660105174e-05, "epoch": 0.03696946418283081, "percentage": 2.89, "elapsed_time": "0:35:51", "remaining_time": "20:05:52", "throughput": 737.52, "total_tokens": 1586624} {"current_steps": 1160, "total_steps": 40000, "loss": 1.0314, "lr": 4.989649609255559e-05, "epoch": 0.037129505153319246, "percentage": 2.9, "elapsed_time": "0:35:53", "remaining_time": "20:01:29", "throughput": 740.21, "total_tokens": 1593696} {"current_steps": 1165, "total_steps": 40000, "loss": 1.0892, "lr": 4.989560174470687e-05, "epoch": 0.03728954612380769, "percentage": 2.91, "elapsed_time": "0:35:54", "remaining_time": "19:57:08", "throughput": 742.72, "total_tokens": 1600384} {"current_steps": 1170, "total_steps": 40000, "loss": 1.0696, "lr": 4.989470355764351e-05, "epoch": 0.03744958709429614, "percentage": 2.93, "elapsed_time": "0:35:56", "remaining_time": "19:52:50", "throughput": 745.15, "total_tokens": 1606912} {"current_steps": 1175, "total_steps": 40000, "loss": 1.256, "lr": 4.9893801531504e-05, "epoch": 0.03760962806478459, "percentage": 2.94, "elapsed_time": "0:35:58", "remaining_time": "19:48:33", "throughput": 747.72, "total_tokens": 1613760} {"current_steps": 1180, "total_steps": 40000, "loss": 0.9569, "lr": 4.9892895666427475e-05, "epoch": 0.03776966903527303, "percentage": 2.95, "elapsed_time": "0:35:59", "remaining_time": "19:44:19", "throughput": 750.36, "total_tokens": 1620768} {"current_steps": 1185, "total_steps": 40000, "loss": 1.1083, "lr": 4.9891985962553606e-05, "epoch": 0.03792971000576147, "percentage": 2.96, "elapsed_time": "0:36:01", "remaining_time": "19:40:07", "throughput": 752.89, "total_tokens": 1627536} {"current_steps": 1190, "total_steps": 40000, "loss": 0.9708, "lr": 4.989107242002269e-05, "epoch": 0.03808975097624992, "percentage": 2.97, "elapsed_time": "0:36:03", "remaining_time": "19:35:57", "throughput": 755.48, "total_tokens": 1634432} {"current_steps": 1195, "total_steps": 40000, "loss": 1.1674, "lr": 4.989015503897561e-05, "epoch": 0.038249791946738367, "percentage": 2.99, "elapsed_time": "0:36:05", "remaining_time": "19:31:49", "throughput": 758.04, "total_tokens": 1641296} {"current_steps": 1200, "total_steps": 40000, "loss": 1.0295, "lr": 4.988923381955383e-05, "epoch": 0.03840983291722681, "percentage": 3.0, "elapsed_time": "0:36:06", "remaining_time": "19:27:43", "throughput": 760.5, "total_tokens": 1647936} {"current_steps": 1200, "total_steps": 40000, "eval_loss": 1.100285530090332, "epoch": 0.03840983291722681, "percentage": 3.0, "elapsed_time": "0:41:54", "remaining_time": "22:34:58", "throughput": 655.4, "total_tokens": 1647936} {"current_steps": 1205, "total_steps": 40000, "loss": 1.0094, "lr": 4.988830876189942e-05, "epoch": 0.03856987388771525, "percentage": 3.01, "elapsed_time": "0:41:57", "remaining_time": "22:30:56", "throughput": 657.32, "total_tokens": 1654928} {"current_steps": 1210, "total_steps": 40000, "loss": 1.024, "lr": 4.988737986615503e-05, "epoch": 0.0387299148582037, "percentage": 3.02, "elapsed_time": "0:41:59", "remaining_time": "22:26:07", "throughput": 659.55, "total_tokens": 1661696} {"current_steps": 1215, "total_steps": 40000, "loss": 1.0728, "lr": 4.988644713246391e-05, "epoch": 0.038889955828692147, "percentage": 3.04, "elapsed_time": "0:42:01", "remaining_time": "22:21:20", "throughput": 661.82, "total_tokens": 1668576} {"current_steps": 1220, "total_steps": 40000, "loss": 1.3698, "lr": 4.988551056096991e-05, "epoch": 0.03904999679918059, "percentage": 3.05, "elapsed_time": "0:42:02", "remaining_time": "22:16:35", "throughput": 664.08, "total_tokens": 1675408} {"current_steps": 1225, "total_steps": 40000, "loss": 1.4525, "lr": 4.988457015181743e-05, "epoch": 0.03921003776966903, "percentage": 3.06, "elapsed_time": "0:42:04", "remaining_time": "22:11:52", "throughput": 666.35, "total_tokens": 1682304} {"current_steps": 1230, "total_steps": 40000, "loss": 0.9736, "lr": 4.988362590515153e-05, "epoch": 0.03937007874015748, "percentage": 3.08, "elapsed_time": "0:42:06", "remaining_time": "22:07:12", "throughput": 668.61, "total_tokens": 1689152} {"current_steps": 1235, "total_steps": 40000, "loss": 0.9143, "lr": 4.9882677821117805e-05, "epoch": 0.039530119710645927, "percentage": 3.09, "elapsed_time": "0:42:08", "remaining_time": "22:02:34", "throughput": 670.89, "total_tokens": 1696096} {"current_steps": 1240, "total_steps": 40000, "loss": 1.0735, "lr": 4.988172589986246e-05, "epoch": 0.03969016068113437, "percentage": 3.1, "elapsed_time": "0:42:09", "remaining_time": "21:57:58", "throughput": 673.09, "total_tokens": 1702816} {"current_steps": 1245, "total_steps": 40000, "loss": 0.7331, "lr": 4.9880770141532304e-05, "epoch": 0.03985020165162281, "percentage": 3.11, "elapsed_time": "0:42:11", "remaining_time": "21:53:24", "throughput": 675.3, "total_tokens": 1709568} {"current_steps": 1250, "total_steps": 40000, "loss": 1.3487, "lr": 4.987981054627472e-05, "epoch": 0.04001024262211126, "percentage": 3.12, "elapsed_time": "0:42:13", "remaining_time": "21:48:52", "throughput": 677.52, "total_tokens": 1716368} {"current_steps": 1255, "total_steps": 40000, "loss": 1.0613, "lr": 4.987884711423769e-05, "epoch": 0.040170283592599706, "percentage": 3.14, "elapsed_time": "0:42:15", "remaining_time": "21:44:23", "throughput": 679.72, "total_tokens": 1723136} {"current_steps": 1260, "total_steps": 40000, "loss": 0.8177, "lr": 4.9877879845569784e-05, "epoch": 0.04033032456308815, "percentage": 3.15, "elapsed_time": "0:42:16", "remaining_time": "21:39:56", "throughput": 682.02, "total_tokens": 1730144} {"current_steps": 1265, "total_steps": 40000, "loss": 0.984, "lr": 4.9876908740420175e-05, "epoch": 0.04049036553357659, "percentage": 3.16, "elapsed_time": "0:42:18", "remaining_time": "21:35:31", "throughput": 684.28, "total_tokens": 1737072} {"current_steps": 1270, "total_steps": 40000, "loss": 0.8867, "lr": 4.987593379893861e-05, "epoch": 0.04065040650406504, "percentage": 3.17, "elapsed_time": "0:42:20", "remaining_time": "21:31:07", "throughput": 686.44, "total_tokens": 1743728} {"current_steps": 1275, "total_steps": 40000, "loss": 0.8755, "lr": 4.987495502127545e-05, "epoch": 0.040810447474553486, "percentage": 3.19, "elapsed_time": "0:42:21", "remaining_time": "21:26:46", "throughput": 688.66, "total_tokens": 1750560} {"current_steps": 1280, "total_steps": 40000, "loss": 1.0743, "lr": 4.987397240758162e-05, "epoch": 0.04097048844504193, "percentage": 3.2, "elapsed_time": "0:42:23", "remaining_time": "21:22:27", "throughput": 690.82, "total_tokens": 1757248} {"current_steps": 1285, "total_steps": 40000, "loss": 0.9948, "lr": 4.9872985958008664e-05, "epoch": 0.04113052941553037, "percentage": 3.21, "elapsed_time": "0:42:25", "remaining_time": "21:18:10", "throughput": 693.13, "total_tokens": 1764336} {"current_steps": 1290, "total_steps": 40000, "loss": 0.9297, "lr": 4.987199567270871e-05, "epoch": 0.04129057038601882, "percentage": 3.23, "elapsed_time": "0:42:27", "remaining_time": "21:13:55", "throughput": 695.39, "total_tokens": 1771296} {"current_steps": 1295, "total_steps": 40000, "loss": 1.1475, "lr": 4.9871001551834444e-05, "epoch": 0.041450611356507266, "percentage": 3.24, "elapsed_time": "0:42:28", "remaining_time": "21:09:42", "throughput": 697.61, "total_tokens": 1778144} {"current_steps": 1300, "total_steps": 40000, "loss": 0.8187, "lr": 4.98700035955392e-05, "epoch": 0.04161065232699571, "percentage": 3.25, "elapsed_time": "0:42:30", "remaining_time": "21:05:31", "throughput": 699.75, "total_tokens": 1784832} {"current_steps": 1305, "total_steps": 40000, "loss": 1.2508, "lr": 4.986900180397686e-05, "epoch": 0.04177069329748415, "percentage": 3.26, "elapsed_time": "0:42:32", "remaining_time": "21:01:22", "throughput": 701.98, "total_tokens": 1791744} {"current_steps": 1310, "total_steps": 40000, "loss": 1.3186, "lr": 4.9867996177301926e-05, "epoch": 0.0419307342679726, "percentage": 3.28, "elapsed_time": "0:42:34", "remaining_time": "20:57:14", "throughput": 704.05, "total_tokens": 1798224} {"current_steps": 1315, "total_steps": 40000, "loss": 1.2641, "lr": 4.9866986715669464e-05, "epoch": 0.042090775238461046, "percentage": 3.29, "elapsed_time": "0:42:35", "remaining_time": "20:53:09", "throughput": 706.28, "total_tokens": 1805168} {"current_steps": 1320, "total_steps": 40000, "loss": 1.1425, "lr": 4.9865973419235155e-05, "epoch": 0.04225081620894949, "percentage": 3.3, "elapsed_time": "0:42:37", "remaining_time": "20:49:05", "throughput": 708.72, "total_tokens": 1812624} {"current_steps": 1325, "total_steps": 40000, "loss": 1.0581, "lr": 4.986495628815526e-05, "epoch": 0.04241085717943793, "percentage": 3.31, "elapsed_time": "0:42:39", "remaining_time": "20:45:03", "throughput": 710.94, "total_tokens": 1819520} {"current_steps": 1330, "total_steps": 40000, "loss": 0.9247, "lr": 4.986393532258663e-05, "epoch": 0.04257089814992638, "percentage": 3.33, "elapsed_time": "0:42:41", "remaining_time": "20:41:03", "throughput": 713.05, "total_tokens": 1826176} {"current_steps": 1335, "total_steps": 40000, "loss": 1.0536, "lr": 4.986291052268671e-05, "epoch": 0.042730939120414826, "percentage": 3.34, "elapsed_time": "0:42:42", "remaining_time": "20:37:05", "throughput": 715.36, "total_tokens": 1833312} {"current_steps": 1340, "total_steps": 40000, "loss": 0.7642, "lr": 4.986188188861355e-05, "epoch": 0.04289098009090327, "percentage": 3.35, "elapsed_time": "0:42:44", "remaining_time": "20:33:08", "throughput": 717.4, "total_tokens": 1839808} {"current_steps": 1345, "total_steps": 40000, "loss": 1.0767, "lr": 4.9860849420525766e-05, "epoch": 0.04305102106139171, "percentage": 3.36, "elapsed_time": "0:42:46", "remaining_time": "20:29:14", "throughput": 719.53, "total_tokens": 1846512} {"current_steps": 1350, "total_steps": 40000, "loss": 0.8629, "lr": 4.9859813118582575e-05, "epoch": 0.04321106203188016, "percentage": 3.38, "elapsed_time": "0:42:48", "remaining_time": "20:25:21", "throughput": 721.84, "total_tokens": 1853696} {"current_steps": 1355, "total_steps": 40000, "loss": 0.8665, "lr": 4.98587729829438e-05, "epoch": 0.043371103002368606, "percentage": 3.39, "elapsed_time": "0:42:49", "remaining_time": "20:21:29", "throughput": 723.95, "total_tokens": 1860352} {"current_steps": 1360, "total_steps": 40000, "loss": 1.0375, "lr": 4.985772901376983e-05, "epoch": 0.04353114397285705, "percentage": 3.4, "elapsed_time": "0:42:51", "remaining_time": "20:17:39", "throughput": 726.05, "total_tokens": 1867008} {"current_steps": 1365, "total_steps": 40000, "loss": 0.9008, "lr": 4.9856681211221666e-05, "epoch": 0.0436911849433455, "percentage": 3.41, "elapsed_time": "0:42:53", "remaining_time": "20:13:51", "throughput": 728.12, "total_tokens": 1873600} {"current_steps": 1370, "total_steps": 40000, "loss": 0.9841, "lr": 4.985562957546089e-05, "epoch": 0.04385122591383394, "percentage": 3.43, "elapsed_time": "0:42:54", "remaining_time": "20:10:05", "throughput": 730.31, "total_tokens": 1880512} {"current_steps": 1375, "total_steps": 40000, "loss": 1.0112, "lr": 4.9854574106649686e-05, "epoch": 0.044011266884322386, "percentage": 3.44, "elapsed_time": "0:42:56", "remaining_time": "20:06:20", "throughput": 732.41, "total_tokens": 1887168} {"current_steps": 1380, "total_steps": 40000, "loss": 0.7898, "lr": 4.985351480495081e-05, "epoch": 0.04417130785481083, "percentage": 3.45, "elapsed_time": "0:42:58", "remaining_time": "20:02:37", "throughput": 734.7, "total_tokens": 1894336} {"current_steps": 1385, "total_steps": 40000, "loss": 1.1293, "lr": 4.985245167052762e-05, "epoch": 0.04433134882529928, "percentage": 3.46, "elapsed_time": "0:43:00", "remaining_time": "19:58:56", "throughput": 736.83, "total_tokens": 1901120} {"current_steps": 1390, "total_steps": 40000, "loss": 1.1227, "lr": 4.9851384703544066e-05, "epoch": 0.04449138979578772, "percentage": 3.48, "elapsed_time": "0:43:01", "remaining_time": "19:55:16", "throughput": 738.96, "total_tokens": 1907904} {"current_steps": 1395, "total_steps": 40000, "loss": 1.1394, "lr": 4.985031390416469e-05, "epoch": 0.044651430766276166, "percentage": 3.49, "elapsed_time": "0:43:03", "remaining_time": "19:51:38", "throughput": 741.14, "total_tokens": 1914816} {"current_steps": 1400, "total_steps": 40000, "loss": 1.0462, "lr": 4.984923927255461e-05, "epoch": 0.04481147173676461, "percentage": 3.5, "elapsed_time": "0:43:05", "remaining_time": "19:48:01", "throughput": 743.29, "total_tokens": 1921648} {"current_steps": 1400, "total_steps": 40000, "eval_loss": 1.0607013702392578, "epoch": 0.04481147173676461, "percentage": 3.5, "elapsed_time": "0:48:53", "remaining_time": "22:27:51", "throughput": 655.14, "total_tokens": 1921648} {"current_steps": 1405, "total_steps": 40000, "loss": 0.8579, "lr": 4.984816080887958e-05, "epoch": 0.04497151270725306, "percentage": 3.51, "elapsed_time": "0:48:56", "remaining_time": "22:24:24", "throughput": 656.69, "total_tokens": 1928352} {"current_steps": 1410, "total_steps": 40000, "loss": 1.1832, "lr": 4.9847078513305875e-05, "epoch": 0.0451315536777415, "percentage": 3.52, "elapsed_time": "0:48:58", "remaining_time": "22:20:15", "throughput": 658.64, "total_tokens": 1935232} {"current_steps": 1415, "total_steps": 40000, "loss": 0.8176, "lr": 4.984599238600043e-05, "epoch": 0.045291594648229946, "percentage": 3.54, "elapsed_time": "0:48:59", "remaining_time": "22:16:08", "throughput": 660.46, "total_tokens": 1941728} {"current_steps": 1420, "total_steps": 40000, "loss": 0.9429, "lr": 4.9844902427130716e-05, "epoch": 0.04545163561871839, "percentage": 3.55, "elapsed_time": "0:49:01", "remaining_time": "22:12:02", "throughput": 662.3, "total_tokens": 1948272} {"current_steps": 1425, "total_steps": 40000, "loss": 0.9779, "lr": 4.984380863686482e-05, "epoch": 0.04561167658920684, "percentage": 3.56, "elapsed_time": "0:49:03", "remaining_time": "22:07:59", "throughput": 664.12, "total_tokens": 1954784} {"current_steps": 1430, "total_steps": 40000, "loss": 0.8687, "lr": 4.984271101537143e-05, "epoch": 0.04577171755969528, "percentage": 3.57, "elapsed_time": "0:49:05", "remaining_time": "22:03:57", "throughput": 666.11, "total_tokens": 1961808} {"current_steps": 1435, "total_steps": 40000, "loss": 1.0402, "lr": 4.9841609562819816e-05, "epoch": 0.045931758530183726, "percentage": 3.59, "elapsed_time": "0:49:06", "remaining_time": "21:59:56", "throughput": 667.92, "total_tokens": 1968304} {"current_steps": 1440, "total_steps": 40000, "loss": 1.0266, "lr": 4.984050427937983e-05, "epoch": 0.04609179950067217, "percentage": 3.6, "elapsed_time": "0:49:08", "remaining_time": "21:55:57", "throughput": 669.81, "total_tokens": 1975024} {"current_steps": 1445, "total_steps": 40000, "loss": 0.9971, "lr": 4.983939516522191e-05, "epoch": 0.04625184047116062, "percentage": 3.61, "elapsed_time": "0:49:10", "remaining_time": "21:52:00", "throughput": 671.85, "total_tokens": 1982192} {"current_steps": 1450, "total_steps": 40000, "loss": 1.0107, "lr": 4.983828222051711e-05, "epoch": 0.04641188144164906, "percentage": 3.62, "elapsed_time": "0:49:12", "remaining_time": "21:48:05", "throughput": 673.81, "total_tokens": 1989168} {"current_steps": 1455, "total_steps": 40000, "loss": 0.9461, "lr": 4.983716544543705e-05, "epoch": 0.046571922412137506, "percentage": 3.64, "elapsed_time": "0:49:13", "remaining_time": "21:44:11", "throughput": 675.67, "total_tokens": 1995824} {"current_steps": 1460, "total_steps": 40000, "loss": 0.7877, "lr": 4.983604484015395e-05, "epoch": 0.04673196338262595, "percentage": 3.65, "elapsed_time": "0:49:15", "remaining_time": "21:40:19", "throughput": 677.57, "total_tokens": 2002608} {"current_steps": 1465, "total_steps": 40000, "loss": 1.2153, "lr": 4.983492040484064e-05, "epoch": 0.0468920043531144, "percentage": 3.66, "elapsed_time": "0:49:17", "remaining_time": "21:36:28", "throughput": 679.48, "total_tokens": 2009424} {"current_steps": 1470, "total_steps": 40000, "loss": 0.7993, "lr": 4.98337921396705e-05, "epoch": 0.04705204532360284, "percentage": 3.67, "elapsed_time": "0:49:19", "remaining_time": "21:32:39", "throughput": 681.29, "total_tokens": 2015968} {"current_steps": 1475, "total_steps": 40000, "loss": 0.886, "lr": 4.983266004481753e-05, "epoch": 0.047212086294091286, "percentage": 3.69, "elapsed_time": "0:49:20", "remaining_time": "21:28:51", "throughput": 683.23, "total_tokens": 2022896} {"current_steps": 1480, "total_steps": 40000, "loss": 1.2504, "lr": 4.9831524120456316e-05, "epoch": 0.04737212726457973, "percentage": 3.7, "elapsed_time": "0:49:22", "remaining_time": "21:25:05", "throughput": 685.25, "total_tokens": 2030080} {"current_steps": 1485, "total_steps": 40000, "loss": 1.0367, "lr": 4.9830384366762026e-05, "epoch": 0.04753216823506818, "percentage": 3.71, "elapsed_time": "0:49:24", "remaining_time": "21:21:20", "throughput": 687.06, "total_tokens": 2036608} {"current_steps": 1490, "total_steps": 40000, "loss": 0.8528, "lr": 4.9829240783910436e-05, "epoch": 0.04769220920555662, "percentage": 3.72, "elapsed_time": "0:49:25", "remaining_time": "21:17:37", "throughput": 688.9, "total_tokens": 2043264} {"current_steps": 1495, "total_steps": 40000, "loss": 1.0476, "lr": 4.982809337207789e-05, "epoch": 0.047852250176045066, "percentage": 3.74, "elapsed_time": "0:49:27", "remaining_time": "21:13:56", "throughput": 690.77, "total_tokens": 2050000} {"current_steps": 1500, "total_steps": 40000, "loss": 0.8952, "lr": 4.9826942131441337e-05, "epoch": 0.04801229114653351, "percentage": 3.75, "elapsed_time": "0:49:29", "remaining_time": "21:10:15", "throughput": 692.65, "total_tokens": 2056784} {"current_steps": 1505, "total_steps": 40000, "loss": 0.954, "lr": 4.9825787062178315e-05, "epoch": 0.04817233211702196, "percentage": 3.76, "elapsed_time": "0:49:31", "remaining_time": "21:06:37", "throughput": 694.68, "total_tokens": 2064032} {"current_steps": 1510, "total_steps": 40000, "loss": 0.9541, "lr": 4.9824628164466945e-05, "epoch": 0.0483323730875104, "percentage": 3.77, "elapsed_time": "0:49:32", "remaining_time": "21:03:00", "throughput": 696.48, "total_tokens": 2070576} {"current_steps": 1515, "total_steps": 40000, "loss": 1.3575, "lr": 4.982346543848595e-05, "epoch": 0.048492414057998846, "percentage": 3.79, "elapsed_time": "0:49:34", "remaining_time": "20:59:24", "throughput": 698.25, "total_tokens": 2077056} {"current_steps": 1520, "total_steps": 40000, "loss": 0.7896, "lr": 4.9822298884414626e-05, "epoch": 0.04865245502848729, "percentage": 3.8, "elapsed_time": "0:49:36", "remaining_time": "20:55:49", "throughput": 700.0, "total_tokens": 2083472} {"current_steps": 1525, "total_steps": 40000, "loss": 1.1508, "lr": 4.982112850243288e-05, "epoch": 0.04881249599897574, "percentage": 3.81, "elapsed_time": "0:49:38", "remaining_time": "20:52:16", "throughput": 702.12, "total_tokens": 2091008} {"current_steps": 1530, "total_steps": 40000, "loss": 1.1531, "lr": 4.98199542927212e-05, "epoch": 0.04897253696946418, "percentage": 3.82, "elapsed_time": "0:49:39", "remaining_time": "20:48:45", "throughput": 703.87, "total_tokens": 2097456} {"current_steps": 1535, "total_steps": 40000, "loss": 0.9007, "lr": 4.981877625546066e-05, "epoch": 0.049132577939952626, "percentage": 3.84, "elapsed_time": "0:49:41", "remaining_time": "20:45:15", "throughput": 705.81, "total_tokens": 2104448} {"current_steps": 1540, "total_steps": 40000, "loss": 1.1142, "lr": 4.981759439083293e-05, "epoch": 0.04929261891044107, "percentage": 3.85, "elapsed_time": "0:49:43", "remaining_time": "20:41:46", "throughput": 707.54, "total_tokens": 2110832} {"current_steps": 1545, "total_steps": 40000, "loss": 1.0017, "lr": 4.981640869902027e-05, "epoch": 0.04945265988092952, "percentage": 3.86, "elapsed_time": "0:49:45", "remaining_time": "20:38:18", "throughput": 709.39, "total_tokens": 2117584} {"current_steps": 1550, "total_steps": 40000, "loss": 0.6692, "lr": 4.9815219180205517e-05, "epoch": 0.04961270085141796, "percentage": 3.88, "elapsed_time": "0:49:46", "remaining_time": "20:34:52", "throughput": 711.22, "total_tokens": 2124288} {"current_steps": 1555, "total_steps": 40000, "loss": 0.8952, "lr": 4.9814025834572126e-05, "epoch": 0.049772741821906406, "percentage": 3.89, "elapsed_time": "0:49:48", "remaining_time": "20:31:34", "throughput": 713.11, "total_tokens": 2131376} {"current_steps": 1560, "total_steps": 40000, "loss": 0.9866, "lr": 4.981282866230411e-05, "epoch": 0.04993278279239485, "percentage": 3.9, "elapsed_time": "0:49:50", "remaining_time": "20:28:11", "throughput": 714.97, "total_tokens": 2138192} {"current_steps": 1565, "total_steps": 40000, "loss": 0.9164, "lr": 4.981162766358611e-05, "epoch": 0.0500928237628833, "percentage": 3.91, "elapsed_time": "0:49:52", "remaining_time": "20:24:48", "throughput": 716.83, "total_tokens": 2144992} {"current_steps": 1570, "total_steps": 40000, "loss": 0.9074, "lr": 4.9810422838603316e-05, "epoch": 0.05025286473337175, "percentage": 3.92, "elapsed_time": "0:49:54", "remaining_time": "20:21:27", "throughput": 718.69, "total_tokens": 2151792} {"current_steps": 1575, "total_steps": 40000, "loss": 0.813, "lr": 4.9809214187541533e-05, "epoch": 0.050412905703860186, "percentage": 3.94, "elapsed_time": "0:49:55", "remaining_time": "20:18:07", "throughput": 720.69, "total_tokens": 2159040} {"current_steps": 1580, "total_steps": 40000, "loss": 1.291, "lr": 4.980800171058715e-05, "epoch": 0.05057294667434863, "percentage": 3.95, "elapsed_time": "0:49:57", "remaining_time": "20:14:49", "throughput": 722.61, "total_tokens": 2166032} {"current_steps": 1585, "total_steps": 40000, "loss": 0.9681, "lr": 4.980678540792715e-05, "epoch": 0.05073298764483708, "percentage": 3.96, "elapsed_time": "0:49:59", "remaining_time": "20:11:31", "throughput": 724.49, "total_tokens": 2172944} {"current_steps": 1590, "total_steps": 40000, "loss": 0.9095, "lr": 4.980556527974909e-05, "epoch": 0.050893028615325527, "percentage": 3.98, "elapsed_time": "0:50:00", "remaining_time": "20:08:15", "throughput": 726.61, "total_tokens": 2180560} {"current_steps": 1595, "total_steps": 40000, "loss": 1.2774, "lr": 4.980434132624114e-05, "epoch": 0.051053069585813966, "percentage": 3.99, "elapsed_time": "0:50:02", "remaining_time": "20:05:00", "throughput": 728.54, "total_tokens": 2187616} {"current_steps": 1600, "total_steps": 40000, "loss": 0.8464, "lr": 4.980311354759205e-05, "epoch": 0.05121311055630241, "percentage": 4.0, "elapsed_time": "0:50:04", "remaining_time": "20:01:47", "throughput": 730.39, "total_tokens": 2194448} {"current_steps": 1600, "total_steps": 40000, "eval_loss": 1.0352177619934082, "epoch": 0.05121311055630241, "percentage": 4.0, "elapsed_time": "0:55:52", "remaining_time": "22:20:48", "throughput": 654.66, "total_tokens": 2194448} {"current_steps": 1605, "total_steps": 40000, "loss": 0.8405, "lr": 4.980188194399116e-05, "epoch": 0.05137315152679086, "percentage": 4.01, "elapsed_time": "0:55:55", "remaining_time": "22:17:45", "throughput": 656.08, "total_tokens": 2201312} {"current_steps": 1610, "total_steps": 40000, "loss": 1.0519, "lr": 4.9800646515628384e-05, "epoch": 0.051533192497279307, "percentage": 4.03, "elapsed_time": "0:55:57", "remaining_time": "22:14:06", "throughput": 657.88, "total_tokens": 2208496} {"current_steps": 1615, "total_steps": 40000, "loss": 1.2335, "lr": 4.979940726269426e-05, "epoch": 0.051693233467767746, "percentage": 4.04, "elapsed_time": "0:55:58", "remaining_time": "22:10:29", "throughput": 659.55, "total_tokens": 2215248} {"current_steps": 1620, "total_steps": 40000, "loss": 1.2203, "lr": 4.979816418537988e-05, "epoch": 0.05185327443825619, "percentage": 4.05, "elapsed_time": "0:56:00", "remaining_time": "22:06:54", "throughput": 661.24, "total_tokens": 2222080} {"current_steps": 1625, "total_steps": 40000, "loss": 1.0114, "lr": 4.979691728387696e-05, "epoch": 0.05201331540874464, "percentage": 4.06, "elapsed_time": "0:56:02", "remaining_time": "22:03:20", "throughput": 662.89, "total_tokens": 2228784} {"current_steps": 1630, "total_steps": 40000, "loss": 1.3576, "lr": 4.979566655837776e-05, "epoch": 0.052173356379233086, "percentage": 4.08, "elapsed_time": "0:56:03", "remaining_time": "21:59:47", "throughput": 664.65, "total_tokens": 2235856} {"current_steps": 1635, "total_steps": 40000, "loss": 1.0597, "lr": 4.9794412009075184e-05, "epoch": 0.052333397349721526, "percentage": 4.09, "elapsed_time": "0:56:05", "remaining_time": "21:56:15", "throughput": 666.3, "total_tokens": 2242560} {"current_steps": 1640, "total_steps": 40000, "loss": 0.7664, "lr": 4.979315363616269e-05, "epoch": 0.05249343832020997, "percentage": 4.1, "elapsed_time": "0:56:07", "remaining_time": "21:52:45", "throughput": 668.02, "total_tokens": 2249504} {"current_steps": 1645, "total_steps": 40000, "loss": 1.0344, "lr": 4.979189143983434e-05, "epoch": 0.05265347929069842, "percentage": 4.11, "elapsed_time": "0:56:09", "remaining_time": "21:49:15", "throughput": 669.66, "total_tokens": 2256192} {"current_steps": 1650, "total_steps": 40000, "loss": 1.298, "lr": 4.979062542028478e-05, "epoch": 0.052813520261186866, "percentage": 4.12, "elapsed_time": "0:56:10", "remaining_time": "21:45:47", "throughput": 671.32, "total_tokens": 2262960} {"current_steps": 1655, "total_steps": 40000, "loss": 1.2807, "lr": 4.978935557770923e-05, "epoch": 0.052973561231675306, "percentage": 4.14, "elapsed_time": "0:56:12", "remaining_time": "21:42:21", "throughput": 673.1, "total_tokens": 2270128} {"current_steps": 1660, "total_steps": 40000, "loss": 0.8639, "lr": 4.978808191230353e-05, "epoch": 0.05313360220216375, "percentage": 4.15, "elapsed_time": "0:56:14", "remaining_time": "21:38:55", "throughput": 674.79, "total_tokens": 2276976} {"current_steps": 1665, "total_steps": 40000, "loss": 1.0496, "lr": 4.9786804424264085e-05, "epoch": 0.0532936431726522, "percentage": 4.16, "elapsed_time": "0:56:16", "remaining_time": "21:35:31", "throughput": 676.57, "total_tokens": 2284192} {"current_steps": 1670, "total_steps": 40000, "loss": 1.0751, "lr": 4.978552311378792e-05, "epoch": 0.053453684143140646, "percentage": 4.17, "elapsed_time": "0:56:17", "remaining_time": "21:32:08", "throughput": 678.19, "total_tokens": 2290832} {"current_steps": 1675, "total_steps": 40000, "loss": 1.1678, "lr": 4.978423798107261e-05, "epoch": 0.053613725113629086, "percentage": 4.19, "elapsed_time": "0:56:19", "remaining_time": "21:28:46", "throughput": 679.91, "total_tokens": 2297824} {"current_steps": 1680, "total_steps": 40000, "loss": 0.9801, "lr": 4.978294902631635e-05, "epoch": 0.05377376608411753, "percentage": 4.2, "elapsed_time": "0:56:21", "remaining_time": "21:25:26", "throughput": 681.64, "total_tokens": 2304848} {"current_steps": 1685, "total_steps": 40000, "loss": 1.1634, "lr": 4.9781656249717914e-05, "epoch": 0.05393380705460598, "percentage": 4.21, "elapsed_time": "0:56:23", "remaining_time": "21:22:07", "throughput": 683.43, "total_tokens": 2312080} {"current_steps": 1690, "total_steps": 40000, "loss": 1.0891, "lr": 4.9780359651476645e-05, "epoch": 0.054093848025094426, "percentage": 4.23, "elapsed_time": "0:56:24", "remaining_time": "21:18:49", "throughput": 685.07, "total_tokens": 2318848} {"current_steps": 1695, "total_steps": 40000, "loss": 0.9883, "lr": 4.977905923179251e-05, "epoch": 0.054253888995582866, "percentage": 4.24, "elapsed_time": "0:56:26", "remaining_time": "21:15:31", "throughput": 686.76, "total_tokens": 2325760} {"current_steps": 1700, "total_steps": 40000, "loss": 1.2033, "lr": 4.977775499086606e-05, "epoch": 0.05441392996607131, "percentage": 4.25, "elapsed_time": "0:56:28", "remaining_time": "21:12:16", "throughput": 688.67, "total_tokens": 2333408} {"current_steps": 1705, "total_steps": 40000, "loss": 1.0514, "lr": 4.97764469288984e-05, "epoch": 0.05457397093655976, "percentage": 4.26, "elapsed_time": "0:56:30", "remaining_time": "21:09:01", "throughput": 690.39, "total_tokens": 2340448} {"current_steps": 1710, "total_steps": 40000, "loss": 1.1112, "lr": 4.977513504609127e-05, "epoch": 0.054734011907048206, "percentage": 4.28, "elapsed_time": "0:56:31", "remaining_time": "21:05:47", "throughput": 692.17, "total_tokens": 2347696} {"current_steps": 1715, "total_steps": 40000, "loss": 1.2526, "lr": 4.9773819342646965e-05, "epoch": 0.054894052877536646, "percentage": 4.29, "elapsed_time": "0:56:33", "remaining_time": "21:02:35", "throughput": 693.87, "total_tokens": 2354656} {"current_steps": 1720, "total_steps": 40000, "loss": 0.972, "lr": 4.97724998187684e-05, "epoch": 0.05505409384802509, "percentage": 4.3, "elapsed_time": "0:56:35", "remaining_time": "20:59:23", "throughput": 695.75, "total_tokens": 2362224} {"current_steps": 1725, "total_steps": 40000, "loss": 1.0237, "lr": 4.9771176474659045e-05, "epoch": 0.05521413481851354, "percentage": 4.31, "elapsed_time": "0:56:36", "remaining_time": "20:56:13", "throughput": 697.35, "total_tokens": 2368896} {"current_steps": 1730, "total_steps": 40000, "loss": 0.9054, "lr": 4.976984931052299e-05, "epoch": 0.055374175789001986, "percentage": 4.32, "elapsed_time": "0:56:38", "remaining_time": "20:53:04", "throughput": 699.05, "total_tokens": 2375872} {"current_steps": 1735, "total_steps": 40000, "loss": 1.1627, "lr": 4.976851832656489e-05, "epoch": 0.055534216759490426, "percentage": 4.34, "elapsed_time": "0:56:40", "remaining_time": "20:49:56", "throughput": 700.74, "total_tokens": 2382832} {"current_steps": 1740, "total_steps": 40000, "loss": 0.9842, "lr": 4.9767183522990004e-05, "epoch": 0.05569425772997887, "percentage": 4.35, "elapsed_time": "0:56:42", "remaining_time": "20:46:49", "throughput": 702.39, "total_tokens": 2389648} {"current_steps": 1745, "total_steps": 40000, "loss": 1.2813, "lr": 4.9765844900004176e-05, "epoch": 0.05585429870046732, "percentage": 4.36, "elapsed_time": "0:56:43", "remaining_time": "20:43:42", "throughput": 704.14, "total_tokens": 2396832} {"current_steps": 1750, "total_steps": 40000, "loss": 1.0396, "lr": 4.9764502457813834e-05, "epoch": 0.056014339670955766, "percentage": 4.38, "elapsed_time": "0:56:45", "remaining_time": "20:40:38", "throughput": 705.73, "total_tokens": 2403488} {"current_steps": 1755, "total_steps": 40000, "loss": 1.1494, "lr": 4.9763156196626005e-05, "epoch": 0.05617438064144421, "percentage": 4.39, "elapsed_time": "0:56:47", "remaining_time": "20:37:34", "throughput": 707.4, "total_tokens": 2410384} {"current_steps": 1760, "total_steps": 40000, "loss": 0.8587, "lr": 4.97618061166483e-05, "epoch": 0.05633442161193265, "percentage": 4.4, "elapsed_time": "0:56:49", "remaining_time": "20:34:31", "throughput": 709.03, "total_tokens": 2417168} {"current_steps": 1765, "total_steps": 40000, "loss": 0.8734, "lr": 4.9760452218088915e-05, "epoch": 0.0564944625824211, "percentage": 4.41, "elapsed_time": "0:56:50", "remaining_time": "20:31:29", "throughput": 710.57, "total_tokens": 2423664} {"current_steps": 1770, "total_steps": 40000, "loss": 0.7594, "lr": 4.975909450115663e-05, "epoch": 0.056654503552909546, "percentage": 4.42, "elapsed_time": "0:56:52", "remaining_time": "20:28:28", "throughput": 712.25, "total_tokens": 2430640} {"current_steps": 1775, "total_steps": 40000, "loss": 1.1877, "lr": 4.975773296606084e-05, "epoch": 0.05681454452339799, "percentage": 4.44, "elapsed_time": "0:56:54", "remaining_time": "20:25:28", "throughput": 713.9, "total_tokens": 2437504} {"current_steps": 1780, "total_steps": 40000, "loss": 1.1289, "lr": 4.97563676130115e-05, "epoch": 0.05697458549388643, "percentage": 4.45, "elapsed_time": "0:56:56", "remaining_time": "20:22:29", "throughput": 715.69, "total_tokens": 2444848} {"current_steps": 1785, "total_steps": 40000, "loss": 1.0241, "lr": 4.9754998442219166e-05, "epoch": 0.05713462646437488, "percentage": 4.46, "elapsed_time": "0:56:57", "remaining_time": "20:19:31", "throughput": 717.33, "total_tokens": 2451712} {"current_steps": 1790, "total_steps": 40000, "loss": 0.9972, "lr": 4.9753625453894984e-05, "epoch": 0.057294667434863326, "percentage": 4.47, "elapsed_time": "0:56:59", "remaining_time": "20:16:35", "throughput": 719.01, "total_tokens": 2458704} {"current_steps": 1795, "total_steps": 40000, "loss": 0.9265, "lr": 4.975224864825068e-05, "epoch": 0.05745470840535177, "percentage": 4.49, "elapsed_time": "0:57:01", "remaining_time": "20:13:39", "throughput": 720.51, "total_tokens": 2465088} {"current_steps": 1800, "total_steps": 40000, "loss": 0.8272, "lr": 4.9750868025498576e-05, "epoch": 0.05761474937584021, "percentage": 4.5, "elapsed_time": "0:57:03", "remaining_time": "20:10:44", "throughput": 722.18, "total_tokens": 2472048} {"current_steps": 1800, "total_steps": 40000, "eval_loss": 1.0095940828323364, "epoch": 0.05761474937584021, "percentage": 4.5, "elapsed_time": "1:02:50", "remaining_time": "22:13:45", "throughput": 655.57, "total_tokens": 2472048} {"current_steps": 1805, "total_steps": 40000, "loss": 0.7257, "lr": 4.974948358585158e-05, "epoch": 0.05777479034632866, "percentage": 4.51, "elapsed_time": "1:02:54", "remaining_time": "22:11:06", "throughput": 656.71, "total_tokens": 2478640} {"current_steps": 1810, "total_steps": 40000, "loss": 1.2526, "lr": 4.9748095329523205e-05, "epoch": 0.057934831316817106, "percentage": 4.52, "elapsed_time": "1:02:56", "remaining_time": "22:07:52", "throughput": 658.24, "total_tokens": 2485520} {"current_steps": 1815, "total_steps": 40000, "loss": 1.2334, "lr": 4.974670325672752e-05, "epoch": 0.05809487228730555, "percentage": 4.54, "elapsed_time": "1:02:57", "remaining_time": "22:04:38", "throughput": 659.75, "total_tokens": 2492400} {"current_steps": 1820, "total_steps": 40000, "loss": 1.1512, "lr": 4.974530736767921e-05, "epoch": 0.05825491325779399, "percentage": 4.55, "elapsed_time": "1:02:59", "remaining_time": "22:01:26", "throughput": 661.23, "total_tokens": 2499136} {"current_steps": 1825, "total_steps": 40000, "loss": 0.9482, "lr": 4.9743907662593524e-05, "epoch": 0.05841495422828244, "percentage": 4.56, "elapsed_time": "1:03:01", "remaining_time": "21:58:15", "throughput": 662.65, "total_tokens": 2505632} {"current_steps": 1830, "total_steps": 40000, "loss": 0.7797, "lr": 4.974250414168633e-05, "epoch": 0.058574995198770886, "percentage": 4.58, "elapsed_time": "1:03:02", "remaining_time": "21:55:05", "throughput": 664.2, "total_tokens": 2512672} {"current_steps": 1835, "total_steps": 40000, "loss": 1.0673, "lr": 4.974109680517407e-05, "epoch": 0.05873503616925933, "percentage": 4.59, "elapsed_time": "1:03:04", "remaining_time": "21:51:56", "throughput": 665.72, "total_tokens": 2519568} {"current_steps": 1840, "total_steps": 40000, "loss": 1.0215, "lr": 4.973968565327376e-05, "epoch": 0.05889507713974777, "percentage": 4.6, "elapsed_time": "1:03:06", "remaining_time": "21:48:48", "throughput": 667.23, "total_tokens": 2526448} {"current_steps": 1845, "total_steps": 40000, "loss": 1.0656, "lr": 4.973827068620303e-05, "epoch": 0.05905511811023622, "percentage": 4.61, "elapsed_time": "1:03:08", "remaining_time": "21:45:40", "throughput": 668.84, "total_tokens": 2533696} {"current_steps": 1850, "total_steps": 40000, "loss": 0.8512, "lr": 4.973685190418008e-05, "epoch": 0.059215159080724666, "percentage": 4.62, "elapsed_time": "1:03:09", "remaining_time": "21:42:34", "throughput": 670.32, "total_tokens": 2540464} {"current_steps": 1855, "total_steps": 40000, "loss": 1.1045, "lr": 4.97354293074237e-05, "epoch": 0.05937520005121311, "percentage": 4.64, "elapsed_time": "1:03:11", "remaining_time": "21:39:29", "throughput": 671.7, "total_tokens": 2546880} {"current_steps": 1860, "total_steps": 40000, "loss": 0.7817, "lr": 4.9734002896153276e-05, "epoch": 0.05953524102170155, "percentage": 4.65, "elapsed_time": "1:03:13", "remaining_time": "21:36:25", "throughput": 673.23, "total_tokens": 2553824} {"current_steps": 1865, "total_steps": 40000, "loss": 0.9062, "lr": 4.973257267058877e-05, "epoch": 0.05969528199219, "percentage": 4.66, "elapsed_time": "1:03:15", "remaining_time": "21:33:22", "throughput": 674.61, "total_tokens": 2560240} {"current_steps": 1870, "total_steps": 40000, "loss": 0.9026, "lr": 4.973113863095076e-05, "epoch": 0.059855322962678446, "percentage": 4.67, "elapsed_time": "1:03:16", "remaining_time": "21:30:20", "throughput": 676.26, "total_tokens": 2567680} {"current_steps": 1875, "total_steps": 40000, "loss": 1.2013, "lr": 4.9729700777460384e-05, "epoch": 0.06001536393316689, "percentage": 4.69, "elapsed_time": "1:03:18", "remaining_time": "21:27:18", "throughput": 677.71, "total_tokens": 2574352} {"current_steps": 1880, "total_steps": 40000, "loss": 1.1526, "lr": 4.972825911033937e-05, "epoch": 0.06017540490365533, "percentage": 4.7, "elapsed_time": "1:03:20", "remaining_time": "21:24:18", "throughput": 679.32, "total_tokens": 2581648} {"current_steps": 1885, "total_steps": 40000, "loss": 1.0968, "lr": 4.9726813629810056e-05, "epoch": 0.06033544587414378, "percentage": 4.71, "elapsed_time": "1:03:22", "remaining_time": "21:21:19", "throughput": 680.78, "total_tokens": 2588384} {"current_steps": 1890, "total_steps": 40000, "loss": 1.2758, "lr": 4.9725364336095326e-05, "epoch": 0.060495486844632226, "percentage": 4.72, "elapsed_time": "1:03:23", "remaining_time": "21:18:20", "throughput": 682.21, "total_tokens": 2595024} {"current_steps": 1895, "total_steps": 40000, "loss": 0.7694, "lr": 4.972391122941871e-05, "epoch": 0.06065552781512067, "percentage": 4.74, "elapsed_time": "1:03:25", "remaining_time": "21:15:23", "throughput": 683.56, "total_tokens": 2601360} {"current_steps": 1900, "total_steps": 40000, "loss": 1.0567, "lr": 4.972245431000428e-05, "epoch": 0.06081556878560911, "percentage": 4.75, "elapsed_time": "1:03:27", "remaining_time": "21:12:26", "throughput": 685.14, "total_tokens": 2608544} {"current_steps": 1905, "total_steps": 40000, "loss": 0.9534, "lr": 4.972099357807671e-05, "epoch": 0.06097560975609756, "percentage": 4.76, "elapsed_time": "1:03:29", "remaining_time": "21:09:31", "throughput": 686.58, "total_tokens": 2615216} {"current_steps": 1910, "total_steps": 40000, "loss": 0.7915, "lr": 4.971952903386127e-05, "epoch": 0.061135650726586006, "percentage": 4.78, "elapsed_time": "1:03:30", "remaining_time": "21:06:36", "throughput": 688.02, "total_tokens": 2621904} {"current_steps": 1915, "total_steps": 40000, "loss": 0.9869, "lr": 4.971806067758381e-05, "epoch": 0.06129569169707445, "percentage": 4.79, "elapsed_time": "1:03:32", "remaining_time": "21:03:43", "throughput": 689.53, "total_tokens": 2628896} {"current_steps": 1920, "total_steps": 40000, "loss": 1.0045, "lr": 4.971658850947076e-05, "epoch": 0.06145573266756289, "percentage": 4.8, "elapsed_time": "1:03:34", "remaining_time": "21:00:50", "throughput": 690.97, "total_tokens": 2635568} {"current_steps": 1925, "total_steps": 40000, "loss": 1.0993, "lr": 4.9715112529749165e-05, "epoch": 0.06161577363805134, "percentage": 4.81, "elapsed_time": "1:03:36", "remaining_time": "20:57:58", "throughput": 692.34, "total_tokens": 2642016} {"current_steps": 1930, "total_steps": 40000, "loss": 0.8925, "lr": 4.9713632738646624e-05, "epoch": 0.061775814608539786, "percentage": 4.83, "elapsed_time": "1:03:37", "remaining_time": "20:55:07", "throughput": 693.84, "total_tokens": 2648944} {"current_steps": 1935, "total_steps": 40000, "loss": 1.2891, "lr": 4.971214913639134e-05, "epoch": 0.06193585557902823, "percentage": 4.84, "elapsed_time": "1:03:39", "remaining_time": "20:52:17", "throughput": 695.38, "total_tokens": 2656016} {"current_steps": 1940, "total_steps": 40000, "loss": 0.9128, "lr": 4.9710661723212104e-05, "epoch": 0.06209589654951667, "percentage": 4.85, "elapsed_time": "1:03:41", "remaining_time": "20:49:27", "throughput": 696.89, "total_tokens": 2662992} {"current_steps": 1945, "total_steps": 40000, "loss": 0.9889, "lr": 4.9709170499338295e-05, "epoch": 0.06225593752000512, "percentage": 4.86, "elapsed_time": "1:03:43", "remaining_time": "20:46:39", "throughput": 698.35, "total_tokens": 2669776} {"current_steps": 1950, "total_steps": 40000, "loss": 1.0617, "lr": 4.9707675464999895e-05, "epoch": 0.062415978490493566, "percentage": 4.88, "elapsed_time": "1:03:44", "remaining_time": "20:43:51", "throughput": 699.83, "total_tokens": 2676656} {"current_steps": 1955, "total_steps": 40000, "loss": 0.9246, "lr": 4.970617662042743e-05, "epoch": 0.06257601946098201, "percentage": 4.89, "elapsed_time": "1:03:46", "remaining_time": "20:41:04", "throughput": 701.31, "total_tokens": 2683552} {"current_steps": 1960, "total_steps": 40000, "loss": 1.1437, "lr": 4.970467396585206e-05, "epoch": 0.06273606043147045, "percentage": 4.9, "elapsed_time": "1:03:48", "remaining_time": "20:38:18", "throughput": 702.78, "total_tokens": 2690400} {"current_steps": 1965, "total_steps": 40000, "loss": 0.8466, "lr": 4.97031675015055e-05, "epoch": 0.0628961014019589, "percentage": 4.91, "elapsed_time": "1:03:49", "remaining_time": "20:35:33", "throughput": 704.17, "total_tokens": 2696960} {"current_steps": 1970, "total_steps": 40000, "loss": 0.9096, "lr": 4.9701657227620075e-05, "epoch": 0.06305614237244735, "percentage": 4.92, "elapsed_time": "1:03:51", "remaining_time": "20:32:50", "throughput": 706.0, "total_tokens": 2705200} {"current_steps": 1975, "total_steps": 40000, "loss": 0.9231, "lr": 4.9700143144428685e-05, "epoch": 0.06321618334293579, "percentage": 4.94, "elapsed_time": "1:03:53", "remaining_time": "20:30:06", "throughput": 707.53, "total_tokens": 2712304} {"current_steps": 1980, "total_steps": 40000, "loss": 1.1706, "lr": 4.969862525216482e-05, "epoch": 0.06337622431342424, "percentage": 4.95, "elapsed_time": "1:03:55", "remaining_time": "20:27:23", "throughput": 708.99, "total_tokens": 2719136} {"current_steps": 1985, "total_steps": 40000, "loss": 0.8656, "lr": 4.9697103551062556e-05, "epoch": 0.06353626528391268, "percentage": 4.96, "elapsed_time": "1:03:56", "remaining_time": "20:24:41", "throughput": 710.52, "total_tokens": 2726208} {"current_steps": 1990, "total_steps": 40000, "loss": 0.9974, "lr": 4.9695578041356565e-05, "epoch": 0.06369630625440113, "percentage": 4.98, "elapsed_time": "1:03:58", "remaining_time": "20:22:00", "throughput": 712.05, "total_tokens": 2733312} {"current_steps": 1995, "total_steps": 40000, "loss": 0.8783, "lr": 4.969404872328209e-05, "epoch": 0.06385634722488957, "percentage": 4.99, "elapsed_time": "1:04:00", "remaining_time": "20:19:20", "throughput": 713.47, "total_tokens": 2740032} {"current_steps": 2000, "total_steps": 40000, "loss": 1.1763, "lr": 4.969251559707498e-05, "epoch": 0.06401638819537801, "percentage": 5.0, "elapsed_time": "1:04:02", "remaining_time": "20:16:40", "throughput": 714.9, "total_tokens": 2746752} {"current_steps": 2000, "total_steps": 40000, "eval_loss": 0.9864804744720459, "epoch": 0.06401638819537801, "percentage": 5.0, "elapsed_time": "1:09:50", "remaining_time": "22:06:53", "throughput": 655.52, "total_tokens": 2746752} {"current_steps": 2005, "total_steps": 40000, "loss": 1.1539, "lr": 4.9690978662971674e-05, "epoch": 0.06417642916586647, "percentage": 5.01, "elapsed_time": "1:09:53", "remaining_time": "22:04:27", "throughput": 656.7, "total_tokens": 2753872} {"current_steps": 2010, "total_steps": 40000, "loss": 1.1204, "lr": 4.968943792120916e-05, "epoch": 0.0643364701363549, "percentage": 5.03, "elapsed_time": "1:09:55", "remaining_time": "22:01:32", "throughput": 658.03, "total_tokens": 2760624} {"current_steps": 2015, "total_steps": 40000, "loss": 0.8563, "lr": 4.9687893372025046e-05, "epoch": 0.06449651110684335, "percentage": 5.04, "elapsed_time": "1:09:57", "remaining_time": "21:58:38", "throughput": 659.3, "total_tokens": 2767104} {"current_steps": 2020, "total_steps": 40000, "loss": 0.6645, "lr": 4.9686345015657535e-05, "epoch": 0.0646565520773318, "percentage": 5.05, "elapsed_time": "1:09:58", "remaining_time": "21:55:44", "throughput": 660.62, "total_tokens": 2773776} {"current_steps": 2025, "total_steps": 40000, "loss": 0.7894, "lr": 4.968479285234538e-05, "epoch": 0.06481659304782024, "percentage": 5.06, "elapsed_time": "1:10:00", "remaining_time": "21:52:52", "throughput": 662.01, "total_tokens": 2780768} {"current_steps": 2030, "total_steps": 40000, "loss": 1.1591, "lr": 4.9683236882327974e-05, "epoch": 0.0649766340183087, "percentage": 5.08, "elapsed_time": "1:10:02", "remaining_time": "21:50:00", "throughput": 663.35, "total_tokens": 2787568} {"current_steps": 2035, "total_steps": 40000, "loss": 0.9077, "lr": 4.968167710584526e-05, "epoch": 0.06513667498879713, "percentage": 5.09, "elapsed_time": "1:10:03", "remaining_time": "21:47:09", "throughput": 664.69, "total_tokens": 2794320} {"current_steps": 2040, "total_steps": 40000, "loss": 0.9714, "lr": 4.968011352313775e-05, "epoch": 0.06529671595928557, "percentage": 5.1, "elapsed_time": "1:10:05", "remaining_time": "21:44:18", "throughput": 665.98, "total_tokens": 2800912} {"current_steps": 2045, "total_steps": 40000, "loss": 1.0718, "lr": 4.967854613444659e-05, "epoch": 0.06545675692977403, "percentage": 5.11, "elapsed_time": "1:10:07", "remaining_time": "21:41:29", "throughput": 667.37, "total_tokens": 2807920} {"current_steps": 2050, "total_steps": 40000, "loss": 0.9229, "lr": 4.967697494001349e-05, "epoch": 0.06561679790026247, "percentage": 5.12, "elapsed_time": "1:10:09", "remaining_time": "21:38:40", "throughput": 668.86, "total_tokens": 2815360} {"current_steps": 2055, "total_steps": 40000, "loss": 1.0156, "lr": 4.9675399940080736e-05, "epoch": 0.0657768388707509, "percentage": 5.14, "elapsed_time": "1:10:10", "remaining_time": "21:35:53", "throughput": 670.22, "total_tokens": 2822240} {"current_steps": 2060, "total_steps": 40000, "loss": 1.1071, "lr": 4.9673821134891226e-05, "epoch": 0.06593687984123936, "percentage": 5.15, "elapsed_time": "1:10:12", "remaining_time": "21:33:06", "throughput": 671.64, "total_tokens": 2829360} {"current_steps": 2065, "total_steps": 40000, "loss": 0.8973, "lr": 4.967223852468842e-05, "epoch": 0.0660969208117278, "percentage": 5.16, "elapsed_time": "1:10:14", "remaining_time": "21:30:19", "throughput": 672.89, "total_tokens": 2835824} {"current_steps": 2070, "total_steps": 40000, "loss": 0.9965, "lr": 4.967065210971639e-05, "epoch": 0.06625696178221625, "percentage": 5.17, "elapsed_time": "1:10:16", "remaining_time": "21:27:34", "throughput": 674.18, "total_tokens": 2842416} {"current_steps": 2075, "total_steps": 40000, "loss": 1.0242, "lr": 4.966906189021977e-05, "epoch": 0.06641700275270469, "percentage": 5.19, "elapsed_time": "1:10:17", "remaining_time": "21:24:50", "throughput": 675.55, "total_tokens": 2849360} {"current_steps": 2080, "total_steps": 40000, "loss": 0.9658, "lr": 4.966746786644379e-05, "epoch": 0.06657704372319313, "percentage": 5.2, "elapsed_time": "1:10:19", "remaining_time": "21:22:06", "throughput": 676.95, "total_tokens": 2856464} {"current_steps": 2085, "total_steps": 40000, "loss": 0.9598, "lr": 4.966587003863429e-05, "epoch": 0.06673708469368159, "percentage": 5.21, "elapsed_time": "1:10:21", "remaining_time": "21:19:23", "throughput": 678.32, "total_tokens": 2863408} {"current_steps": 2090, "total_steps": 40000, "loss": 0.9579, "lr": 4.966426840703765e-05, "epoch": 0.06689712566417003, "percentage": 5.22, "elapsed_time": "1:10:23", "remaining_time": "21:16:40", "throughput": 679.76, "total_tokens": 2870656} {"current_steps": 2095, "total_steps": 40000, "loss": 1.1555, "lr": 4.9662662971900875e-05, "epoch": 0.06705716663465847, "percentage": 5.24, "elapsed_time": "1:10:24", "remaining_time": "21:13:59", "throughput": 680.97, "total_tokens": 2876960} {"current_steps": 2100, "total_steps": 40000, "loss": 0.6682, "lr": 4.9661053733471534e-05, "epoch": 0.06721720760514692, "percentage": 5.25, "elapsed_time": "1:10:26", "remaining_time": "21:11:18", "throughput": 682.34, "total_tokens": 2883904} {"current_steps": 2105, "total_steps": 40000, "loss": 1.1917, "lr": 4.965944069199781e-05, "epoch": 0.06737724857563536, "percentage": 5.26, "elapsed_time": "1:10:28", "remaining_time": "21:08:38", "throughput": 683.63, "total_tokens": 2890560} {"current_steps": 2110, "total_steps": 40000, "loss": 0.6018, "lr": 4.965782384772842e-05, "epoch": 0.06753728954612381, "percentage": 5.27, "elapsed_time": "1:10:29", "remaining_time": "21:05:59", "throughput": 685.0, "total_tokens": 2897536} {"current_steps": 2115, "total_steps": 40000, "loss": 1.0833, "lr": 4.9656203200912734e-05, "epoch": 0.06769733051661225, "percentage": 5.29, "elapsed_time": "1:10:31", "remaining_time": "21:03:21", "throughput": 686.42, "total_tokens": 2904736} {"current_steps": 2120, "total_steps": 40000, "loss": 0.8028, "lr": 4.965457875180067e-05, "epoch": 0.06785737148710069, "percentage": 5.3, "elapsed_time": "1:10:33", "remaining_time": "21:00:43", "throughput": 687.73, "total_tokens": 2911488} {"current_steps": 2125, "total_steps": 40000, "loss": 1.2045, "lr": 4.9652950500642724e-05, "epoch": 0.06801741245758915, "percentage": 5.31, "elapsed_time": "1:10:35", "remaining_time": "20:58:06", "throughput": 689.12, "total_tokens": 2918592} {"current_steps": 2130, "total_steps": 40000, "loss": 1.0976, "lr": 4.965131844769001e-05, "epoch": 0.06817745342807759, "percentage": 5.33, "elapsed_time": "1:10:36", "remaining_time": "20:55:30", "throughput": 690.44, "total_tokens": 2925360} {"current_steps": 2135, "total_steps": 40000, "loss": 0.6585, "lr": 4.96496825931942e-05, "epoch": 0.06833749439856603, "percentage": 5.34, "elapsed_time": "1:10:38", "remaining_time": "20:52:54", "throughput": 691.82, "total_tokens": 2932400} {"current_steps": 2140, "total_steps": 40000, "loss": 1.0162, "lr": 4.9648042937407566e-05, "epoch": 0.06849753536905448, "percentage": 5.35, "elapsed_time": "1:10:40", "remaining_time": "20:50:19", "throughput": 693.17, "total_tokens": 2939344} {"current_steps": 2145, "total_steps": 40000, "loss": 0.7426, "lr": 4.964639948058297e-05, "epoch": 0.06865757633954292, "percentage": 5.36, "elapsed_time": "1:10:42", "remaining_time": "20:47:45", "throughput": 694.46, "total_tokens": 2945984} {"current_steps": 2150, "total_steps": 40000, "loss": 0.9153, "lr": 4.9644752222973846e-05, "epoch": 0.06881761731003137, "percentage": 5.38, "elapsed_time": "1:10:43", "remaining_time": "20:45:11", "throughput": 695.76, "total_tokens": 2952704} {"current_steps": 2155, "total_steps": 40000, "loss": 1.1538, "lr": 4.964310116483422e-05, "epoch": 0.06897765828051981, "percentage": 5.39, "elapsed_time": "1:10:45", "remaining_time": "20:42:39", "throughput": 697.06, "total_tokens": 2959472} {"current_steps": 2160, "total_steps": 40000, "loss": 0.7179, "lr": 4.964144630641872e-05, "epoch": 0.06913769925100825, "percentage": 5.4, "elapsed_time": "1:10:47", "remaining_time": "20:40:07", "throughput": 698.33, "total_tokens": 2966064} {"current_steps": 2165, "total_steps": 40000, "loss": 0.9516, "lr": 4.9639787647982525e-05, "epoch": 0.0692977402214967, "percentage": 5.41, "elapsed_time": "1:10:49", "remaining_time": "20:37:36", "throughput": 699.69, "total_tokens": 2973040} {"current_steps": 2170, "total_steps": 40000, "loss": 0.743, "lr": 4.963812518978143e-05, "epoch": 0.06945778119198515, "percentage": 5.42, "elapsed_time": "1:10:50", "remaining_time": "20:35:05", "throughput": 700.98, "total_tokens": 2979760} {"current_steps": 2175, "total_steps": 40000, "loss": 0.9826, "lr": 4.963645893207182e-05, "epoch": 0.0696178221624736, "percentage": 5.44, "elapsed_time": "1:10:52", "remaining_time": "20:32:35", "throughput": 702.35, "total_tokens": 2986784} {"current_steps": 2180, "total_steps": 40000, "loss": 1.0624, "lr": 4.963478887511063e-05, "epoch": 0.06977786313296204, "percentage": 5.45, "elapsed_time": "1:10:54", "remaining_time": "20:30:06", "throughput": 703.62, "total_tokens": 2993392} {"current_steps": 2185, "total_steps": 40000, "loss": 0.7915, "lr": 4.963311501915542e-05, "epoch": 0.06993790410345048, "percentage": 5.46, "elapsed_time": "1:10:56", "remaining_time": "20:27:37", "throughput": 704.91, "total_tokens": 3000112} {"current_steps": 2190, "total_steps": 40000, "loss": 0.8475, "lr": 4.963143736446432e-05, "epoch": 0.07009794507393893, "percentage": 5.47, "elapsed_time": "1:10:57", "remaining_time": "20:25:09", "throughput": 706.13, "total_tokens": 3006544} {"current_steps": 2195, "total_steps": 40000, "loss": 1.0364, "lr": 4.962975591129603e-05, "epoch": 0.07025798604442737, "percentage": 5.49, "elapsed_time": "1:10:59", "remaining_time": "20:22:42", "throughput": 707.38, "total_tokens": 3013072} {"current_steps": 2200, "total_steps": 40000, "loss": 1.3931, "lr": 4.962807065990986e-05, "epoch": 0.07041802701491581, "percentage": 5.5, "elapsed_time": "1:11:01", "remaining_time": "20:20:15", "throughput": 708.75, "total_tokens": 3020144} {"current_steps": 2200, "total_steps": 40000, "eval_loss": 0.96968013048172, "epoch": 0.07041802701491581, "percentage": 5.5, "elapsed_time": "1:16:49", "remaining_time": "21:59:58", "throughput": 655.21, "total_tokens": 3020144} {"current_steps": 2205, "total_steps": 40000, "loss": 0.9711, "lr": 4.9626381610565714e-05, "epoch": 0.07057806798540427, "percentage": 5.51, "elapsed_time": "1:16:53", "remaining_time": "21:57:57", "throughput": 656.14, "total_tokens": 3027072} {"current_steps": 2210, "total_steps": 40000, "loss": 0.9703, "lr": 4.9624688763524043e-05, "epoch": 0.0707381089558927, "percentage": 5.53, "elapsed_time": "1:16:55", "remaining_time": "21:55:17", "throughput": 657.35, "total_tokens": 3033808} {"current_steps": 2215, "total_steps": 40000, "loss": 0.8034, "lr": 4.962299211904591e-05, "epoch": 0.07089814992638116, "percentage": 5.54, "elapsed_time": "1:16:56", "remaining_time": "21:52:38", "throughput": 658.61, "total_tokens": 3040752} {"current_steps": 2220, "total_steps": 40000, "loss": 0.8434, "lr": 4.962129167739296e-05, "epoch": 0.0710581908968696, "percentage": 5.55, "elapsed_time": "1:16:58", "remaining_time": "21:50:00", "throughput": 659.87, "total_tokens": 3047696} {"current_steps": 2225, "total_steps": 40000, "loss": 0.9836, "lr": 4.961958743882742e-05, "epoch": 0.07121823186735804, "percentage": 5.56, "elapsed_time": "1:17:00", "remaining_time": "21:47:23", "throughput": 661.12, "total_tokens": 3054656} {"current_steps": 2230, "total_steps": 40000, "loss": 0.8219, "lr": 4.961787940361211e-05, "epoch": 0.0713782728378465, "percentage": 5.58, "elapsed_time": "1:17:02", "remaining_time": "21:44:46", "throughput": 662.44, "total_tokens": 3061904} {"current_steps": 2235, "total_steps": 40000, "loss": 1.1908, "lr": 4.961616757201043e-05, "epoch": 0.07153831380833493, "percentage": 5.59, "elapsed_time": "1:17:03", "remaining_time": "21:42:10", "throughput": 663.66, "total_tokens": 3068704} {"current_steps": 2240, "total_steps": 40000, "loss": 1.1186, "lr": 4.961445194428637e-05, "epoch": 0.07169835477882337, "percentage": 5.6, "elapsed_time": "1:17:05", "remaining_time": "21:39:34", "throughput": 664.84, "total_tokens": 3075280} {"current_steps": 2245, "total_steps": 40000, "loss": 0.8481, "lr": 4.9612732520704486e-05, "epoch": 0.07185839574931183, "percentage": 5.61, "elapsed_time": "1:17:07", "remaining_time": "21:37:00", "throughput": 666.12, "total_tokens": 3082384} {"current_steps": 2250, "total_steps": 40000, "loss": 0.8196, "lr": 4.961100930152994e-05, "epoch": 0.07201843671980027, "percentage": 5.62, "elapsed_time": "1:17:09", "remaining_time": "21:34:26", "throughput": 667.27, "total_tokens": 3088848} {"current_steps": 2255, "total_steps": 40000, "loss": 0.9935, "lr": 4.960928228702849e-05, "epoch": 0.07217847769028872, "percentage": 5.64, "elapsed_time": "1:17:10", "remaining_time": "21:31:52", "throughput": 668.48, "total_tokens": 3095648} {"current_steps": 2260, "total_steps": 40000, "loss": 0.7882, "lr": 4.960755147746645e-05, "epoch": 0.07233851866077716, "percentage": 5.65, "elapsed_time": "1:17:12", "remaining_time": "21:29:20", "throughput": 669.72, "total_tokens": 3102528} {"current_steps": 2265, "total_steps": 40000, "loss": 0.7148, "lr": 4.9605816873110736e-05, "epoch": 0.0724985596312656, "percentage": 5.66, "elapsed_time": "1:17:14", "remaining_time": "21:26:47", "throughput": 670.86, "total_tokens": 3108976} {"current_steps": 2270, "total_steps": 40000, "loss": 1.0737, "lr": 4.960407847422883e-05, "epoch": 0.07265860060175405, "percentage": 5.67, "elapsed_time": "1:17:16", "remaining_time": "21:24:16", "throughput": 672.09, "total_tokens": 3115872} {"current_steps": 2275, "total_steps": 40000, "loss": 0.9878, "lr": 4.960233628108885e-05, "epoch": 0.07281864157224249, "percentage": 5.69, "elapsed_time": "1:17:17", "remaining_time": "21:21:46", "throughput": 673.28, "total_tokens": 3122528} {"current_steps": 2280, "total_steps": 40000, "loss": 0.9798, "lr": 4.960059029395942e-05, "epoch": 0.07297868254273093, "percentage": 5.7, "elapsed_time": "1:17:19", "remaining_time": "21:19:15", "throughput": 674.69, "total_tokens": 3130256} {"current_steps": 2285, "total_steps": 40000, "loss": 1.0889, "lr": 4.959884051310983e-05, "epoch": 0.07313872351321939, "percentage": 5.71, "elapsed_time": "1:17:21", "remaining_time": "21:16:46", "throughput": 675.96, "total_tokens": 3137312} {"current_steps": 2290, "total_steps": 40000, "loss": 0.9349, "lr": 4.959708693880991e-05, "epoch": 0.07329876448370783, "percentage": 5.73, "elapsed_time": "1:17:23", "remaining_time": "21:14:17", "throughput": 677.19, "total_tokens": 3144192} {"current_steps": 2295, "total_steps": 40000, "loss": 1.353, "lr": 4.9595329571330074e-05, "epoch": 0.07345880545419628, "percentage": 5.74, "elapsed_time": "1:17:24", "remaining_time": "21:11:49", "throughput": 678.47, "total_tokens": 3151296} {"current_steps": 2300, "total_steps": 40000, "loss": 0.8311, "lr": 4.9593568410941326e-05, "epoch": 0.07361884642468472, "percentage": 5.75, "elapsed_time": "1:17:26", "remaining_time": "21:09:21", "throughput": 679.74, "total_tokens": 3158384} {"current_steps": 2305, "total_steps": 40000, "loss": 0.7476, "lr": 4.959180345791528e-05, "epoch": 0.07377888739517316, "percentage": 5.76, "elapsed_time": "1:17:28", "remaining_time": "21:06:54", "throughput": 680.94, "total_tokens": 3165136} {"current_steps": 2310, "total_steps": 40000, "loss": 1.1197, "lr": 4.9590034712524086e-05, "epoch": 0.07393892836566161, "percentage": 5.78, "elapsed_time": "1:17:29", "remaining_time": "21:04:28", "throughput": 682.26, "total_tokens": 3172464} {"current_steps": 2315, "total_steps": 40000, "loss": 0.8969, "lr": 4.958826217504053e-05, "epoch": 0.07409896933615005, "percentage": 5.79, "elapsed_time": "1:17:31", "remaining_time": "21:02:03", "throughput": 683.51, "total_tokens": 3179472} {"current_steps": 2320, "total_steps": 40000, "loss": 0.8612, "lr": 4.958648584573795e-05, "epoch": 0.07425901030663849, "percentage": 5.8, "elapsed_time": "1:17:33", "remaining_time": "20:59:38", "throughput": 684.77, "total_tokens": 3186512} {"current_steps": 2325, "total_steps": 40000, "loss": 0.7577, "lr": 4.958470572489028e-05, "epoch": 0.07441905127712695, "percentage": 5.81, "elapsed_time": "1:17:35", "remaining_time": "20:57:13", "throughput": 686.0, "total_tokens": 3193440} {"current_steps": 2330, "total_steps": 40000, "loss": 1.079, "lr": 4.958292181277203e-05, "epoch": 0.07457909224761539, "percentage": 5.83, "elapsed_time": "1:17:36", "remaining_time": "20:54:49", "throughput": 687.26, "total_tokens": 3200480} {"current_steps": 2335, "total_steps": 40000, "loss": 0.8628, "lr": 4.958113410965832e-05, "epoch": 0.07473913321810384, "percentage": 5.84, "elapsed_time": "1:17:38", "remaining_time": "20:52:26", "throughput": 688.41, "total_tokens": 3207024} {"current_steps": 2340, "total_steps": 40000, "loss": 0.9489, "lr": 4.957934261582481e-05, "epoch": 0.07489917418859228, "percentage": 5.85, "elapsed_time": "1:17:40", "remaining_time": "20:50:03", "throughput": 689.55, "total_tokens": 3213536} {"current_steps": 2345, "total_steps": 40000, "loss": 1.0519, "lr": 4.95775473315478e-05, "epoch": 0.07505921515908072, "percentage": 5.86, "elapsed_time": "1:17:42", "remaining_time": "20:47:41", "throughput": 690.72, "total_tokens": 3220192} {"current_steps": 2350, "total_steps": 40000, "loss": 1.057, "lr": 4.9575748257104124e-05, "epoch": 0.07521925612956917, "percentage": 5.88, "elapsed_time": "1:17:43", "remaining_time": "20:45:20", "throughput": 691.94, "total_tokens": 3227088} {"current_steps": 2355, "total_steps": 40000, "loss": 0.7726, "lr": 4.9573945392771224e-05, "epoch": 0.07537929710005761, "percentage": 5.89, "elapsed_time": "1:17:45", "remaining_time": "20:42:59", "throughput": 693.12, "total_tokens": 3233824} {"current_steps": 2360, "total_steps": 40000, "loss": 0.7727, "lr": 4.9572138738827134e-05, "epoch": 0.07553933807054607, "percentage": 5.9, "elapsed_time": "1:17:47", "remaining_time": "20:40:39", "throughput": 694.35, "total_tokens": 3240736} {"current_steps": 2365, "total_steps": 40000, "loss": 0.899, "lr": 4.957032829555046e-05, "epoch": 0.0756993790410345, "percentage": 5.91, "elapsed_time": "1:17:49", "remaining_time": "20:38:19", "throughput": 695.52, "total_tokens": 3247392} {"current_steps": 2370, "total_steps": 40000, "loss": 0.727, "lr": 4.956851406322039e-05, "epoch": 0.07585942001152295, "percentage": 5.92, "elapsed_time": "1:17:50", "remaining_time": "20:36:00", "throughput": 696.71, "total_tokens": 3254160} {"current_steps": 2375, "total_steps": 40000, "loss": 0.8888, "lr": 4.9566696042116704e-05, "epoch": 0.0760194609820114, "percentage": 5.94, "elapsed_time": "1:17:52", "remaining_time": "20:33:42", "throughput": 697.86, "total_tokens": 3260736} {"current_steps": 2380, "total_steps": 40000, "loss": 0.8369, "lr": 4.9564874232519766e-05, "epoch": 0.07617950195249984, "percentage": 5.95, "elapsed_time": "1:17:54", "remaining_time": "20:31:25", "throughput": 699.28, "total_tokens": 3268624} {"current_steps": 2385, "total_steps": 40000, "loss": 1.0143, "lr": 4.9563048634710516e-05, "epoch": 0.07633954292298828, "percentage": 5.96, "elapsed_time": "1:17:56", "remaining_time": "20:29:07", "throughput": 700.6, "total_tokens": 3276048} {"current_steps": 2390, "total_steps": 40000, "loss": 0.8996, "lr": 4.956121924897049e-05, "epoch": 0.07649958389347673, "percentage": 5.97, "elapsed_time": "1:17:57", "remaining_time": "20:26:51", "throughput": 701.81, "total_tokens": 3282912} {"current_steps": 2395, "total_steps": 40000, "loss": 0.8172, "lr": 4.955938607558181e-05, "epoch": 0.07665962486396517, "percentage": 5.99, "elapsed_time": "1:17:59", "remaining_time": "20:24:34", "throughput": 703.09, "total_tokens": 3290112} {"current_steps": 2400, "total_steps": 40000, "loss": 1.2572, "lr": 4.955754911482715e-05, "epoch": 0.07681966583445363, "percentage": 6.0, "elapsed_time": "1:18:01", "remaining_time": "20:22:19", "throughput": 704.22, "total_tokens": 3296624} {"current_steps": 2400, "total_steps": 40000, "eval_loss": 0.9547861814498901, "epoch": 0.07681966583445363, "percentage": 6.0, "elapsed_time": "1:23:49", "remaining_time": "21:53:12", "throughput": 655.48, "total_tokens": 3296624} {"current_steps": 2405, "total_steps": 40000, "loss": 1.3303, "lr": 4.9555708366989804e-05, "epoch": 0.07697970680494207, "percentage": 6.01, "elapsed_time": "1:23:53", "remaining_time": "21:51:18", "throughput": 656.29, "total_tokens": 3303216} {"current_steps": 2410, "total_steps": 40000, "loss": 0.7683, "lr": 4.9553863832353655e-05, "epoch": 0.0771397477754305, "percentage": 6.02, "elapsed_time": "1:23:54", "remaining_time": "21:48:51", "throughput": 657.4, "total_tokens": 3309952} {"current_steps": 2415, "total_steps": 40000, "loss": 0.7909, "lr": 4.955201551120313e-05, "epoch": 0.07729978874591896, "percentage": 6.04, "elapsed_time": "1:23:56", "remaining_time": "21:46:25", "throughput": 658.51, "total_tokens": 3316688} {"current_steps": 2420, "total_steps": 40000, "loss": 0.8238, "lr": 4.955016340382328e-05, "epoch": 0.0774598297164074, "percentage": 6.05, "elapsed_time": "1:23:58", "remaining_time": "21:44:00", "throughput": 659.7, "total_tokens": 3323840} {"current_steps": 2425, "total_steps": 40000, "loss": 0.9905, "lr": 4.954830751049972e-05, "epoch": 0.07761987068689584, "percentage": 6.06, "elapsed_time": "1:24:00", "remaining_time": "21:41:35", "throughput": 660.87, "total_tokens": 3330864} {"current_steps": 2430, "total_steps": 40000, "loss": 0.9926, "lr": 4.954644783151864e-05, "epoch": 0.07777991165738429, "percentage": 6.08, "elapsed_time": "1:24:01", "remaining_time": "21:39:11", "throughput": 661.96, "total_tokens": 3337520} {"current_steps": 2435, "total_steps": 40000, "loss": 0.849, "lr": 4.954458436716684e-05, "epoch": 0.07793995262787273, "percentage": 6.09, "elapsed_time": "1:24:03", "remaining_time": "21:36:48", "throughput": 663.2, "total_tokens": 3344896} {"current_steps": 2440, "total_steps": 40000, "loss": 0.8325, "lr": 4.954271711773168e-05, "epoch": 0.07809999359836119, "percentage": 6.1, "elapsed_time": "1:24:05", "remaining_time": "21:34:25", "throughput": 664.29, "total_tokens": 3351584} {"current_steps": 2445, "total_steps": 40000, "loss": 0.8302, "lr": 4.9540846083501115e-05, "epoch": 0.07826003456884963, "percentage": 6.11, "elapsed_time": "1:24:07", "remaining_time": "21:32:02", "throughput": 665.44, "total_tokens": 3358528} {"current_steps": 2450, "total_steps": 40000, "loss": 1.0373, "lr": 4.953897126476369e-05, "epoch": 0.07842007553933807, "percentage": 6.12, "elapsed_time": "1:24:08", "remaining_time": "21:29:40", "throughput": 666.49, "total_tokens": 3364960} {"current_steps": 2455, "total_steps": 40000, "loss": 1.1599, "lr": 4.9537092661808514e-05, "epoch": 0.07858011650982652, "percentage": 6.14, "elapsed_time": "1:24:10", "remaining_time": "21:27:19", "throughput": 667.63, "total_tokens": 3371904} {"current_steps": 2460, "total_steps": 40000, "loss": 1.1655, "lr": 4.9535210274925306e-05, "epoch": 0.07874015748031496, "percentage": 6.15, "elapsed_time": "1:24:12", "remaining_time": "21:24:58", "throughput": 668.81, "total_tokens": 3379008} {"current_steps": 2465, "total_steps": 40000, "loss": 0.9996, "lr": 4.953332410440435e-05, "epoch": 0.0789001984508034, "percentage": 6.16, "elapsed_time": "1:24:14", "remaining_time": "21:22:38", "throughput": 669.95, "total_tokens": 3385952} {"current_steps": 2470, "total_steps": 40000, "loss": 1.0641, "lr": 4.9531434150536496e-05, "epoch": 0.07906023942129185, "percentage": 6.17, "elapsed_time": "1:24:15", "remaining_time": "21:20:19", "throughput": 671.11, "total_tokens": 3392960} {"current_steps": 2475, "total_steps": 40000, "loss": 0.9314, "lr": 4.952954041361322e-05, "epoch": 0.07922028039178029, "percentage": 6.19, "elapsed_time": "1:24:17", "remaining_time": "21:17:59", "throughput": 672.28, "total_tokens": 3400048} {"current_steps": 2480, "total_steps": 40000, "loss": 0.7825, "lr": 4.952764289392655e-05, "epoch": 0.07938032136226875, "percentage": 6.2, "elapsed_time": "1:24:19", "remaining_time": "21:15:41", "throughput": 673.34, "total_tokens": 3406576} {"current_steps": 2485, "total_steps": 40000, "loss": 0.7968, "lr": 4.952574159176912e-05, "epoch": 0.07954036233275719, "percentage": 6.21, "elapsed_time": "1:24:20", "remaining_time": "21:13:23", "throughput": 674.42, "total_tokens": 3413232} {"current_steps": 2490, "total_steps": 40000, "loss": 1.2348, "lr": 4.952383650743413e-05, "epoch": 0.07970040330324563, "percentage": 6.22, "elapsed_time": "1:24:22", "remaining_time": "21:11:05", "throughput": 675.61, "total_tokens": 3420400} {"current_steps": 2495, "total_steps": 40000, "loss": 0.9151, "lr": 4.952192764121536e-05, "epoch": 0.07986044427373408, "percentage": 6.24, "elapsed_time": "1:24:24", "remaining_time": "21:08:49", "throughput": 676.81, "total_tokens": 3427680} {"current_steps": 2500, "total_steps": 40000, "loss": 1.0864, "lr": 4.9520014993407185e-05, "epoch": 0.08002048524422252, "percentage": 6.25, "elapsed_time": "1:24:26", "remaining_time": "21:06:32", "throughput": 677.91, "total_tokens": 3434400} {"current_steps": 2505, "total_steps": 40000, "loss": 0.7307, "lr": 4.951809856430456e-05, "epoch": 0.08018052621471096, "percentage": 6.26, "elapsed_time": "1:24:27", "remaining_time": "21:04:17", "throughput": 679.02, "total_tokens": 3441200} {"current_steps": 2510, "total_steps": 40000, "loss": 0.9894, "lr": 4.951617835420303e-05, "epoch": 0.08034056718519941, "percentage": 6.28, "elapsed_time": "1:24:29", "remaining_time": "21:02:01", "throughput": 680.14, "total_tokens": 3448096} {"current_steps": 2515, "total_steps": 40000, "loss": 1.0341, "lr": 4.951425436339869e-05, "epoch": 0.08050060815568785, "percentage": 6.29, "elapsed_time": "1:24:31", "remaining_time": "20:59:47", "throughput": 681.24, "total_tokens": 3454832} {"current_steps": 2520, "total_steps": 40000, "loss": 0.905, "lr": 4.9512326592188274e-05, "epoch": 0.0806606491261763, "percentage": 6.3, "elapsed_time": "1:24:33", "remaining_time": "20:57:32", "throughput": 682.32, "total_tokens": 3461504} {"current_steps": 2525, "total_steps": 40000, "loss": 0.9116, "lr": 4.9510395040869054e-05, "epoch": 0.08082069009666475, "percentage": 6.31, "elapsed_time": "1:24:34", "remaining_time": "20:55:19", "throughput": 683.41, "total_tokens": 3468208} {"current_steps": 2530, "total_steps": 40000, "loss": 1.0398, "lr": 4.9508459709738905e-05, "epoch": 0.08098073106715319, "percentage": 6.33, "elapsed_time": "1:24:36", "remaining_time": "20:53:06", "throughput": 684.51, "total_tokens": 3474992} {"current_steps": 2535, "total_steps": 40000, "loss": 0.8753, "lr": 4.950652059909627e-05, "epoch": 0.08114077203764164, "percentage": 6.34, "elapsed_time": "1:24:38", "remaining_time": "20:50:53", "throughput": 685.76, "total_tokens": 3482528} {"current_steps": 2540, "total_steps": 40000, "loss": 0.9763, "lr": 4.95045777092402e-05, "epoch": 0.08130081300813008, "percentage": 6.35, "elapsed_time": "1:24:40", "remaining_time": "20:48:41", "throughput": 686.83, "total_tokens": 3489168} {"current_steps": 2545, "total_steps": 40000, "loss": 1.0828, "lr": 4.950263104047031e-05, "epoch": 0.08146085397861853, "percentage": 6.36, "elapsed_time": "1:24:41", "remaining_time": "20:46:29", "throughput": 687.91, "total_tokens": 3495824} {"current_steps": 2550, "total_steps": 40000, "loss": 0.9105, "lr": 4.9500680593086775e-05, "epoch": 0.08162089494910697, "percentage": 6.38, "elapsed_time": "1:24:43", "remaining_time": "20:44:18", "throughput": 688.97, "total_tokens": 3502448} {"current_steps": 2555, "total_steps": 40000, "loss": 0.7644, "lr": 4.94987263673904e-05, "epoch": 0.08178093591959541, "percentage": 6.39, "elapsed_time": "1:24:45", "remaining_time": "20:42:08", "throughput": 690.04, "total_tokens": 3509072} {"current_steps": 2560, "total_steps": 40000, "loss": 0.9954, "lr": 4.949676836368256e-05, "epoch": 0.08194097689008387, "percentage": 6.4, "elapsed_time": "1:24:47", "remaining_time": "20:39:58", "throughput": 691.2, "total_tokens": 3516160} {"current_steps": 2565, "total_steps": 40000, "loss": 0.9339, "lr": 4.949480658226518e-05, "epoch": 0.0821010178605723, "percentage": 6.41, "elapsed_time": "1:24:48", "remaining_time": "20:37:48", "throughput": 692.25, "total_tokens": 3522704} {"current_steps": 2570, "total_steps": 40000, "loss": 0.75, "lr": 4.949284102344082e-05, "epoch": 0.08226105883106075, "percentage": 6.42, "elapsed_time": "1:24:50", "remaining_time": "20:35:39", "throughput": 693.42, "total_tokens": 3529856} {"current_steps": 2575, "total_steps": 40000, "loss": 1.2447, "lr": 4.9490871687512565e-05, "epoch": 0.0824210998015492, "percentage": 6.44, "elapsed_time": "1:24:52", "remaining_time": "20:33:30", "throughput": 694.57, "total_tokens": 3536912} {"current_steps": 2580, "total_steps": 40000, "loss": 0.9485, "lr": 4.948889857478413e-05, "epoch": 0.08258114077203764, "percentage": 6.45, "elapsed_time": "1:24:53", "remaining_time": "20:31:22", "throughput": 695.82, "total_tokens": 3544480} {"current_steps": 2585, "total_steps": 40000, "loss": 0.7467, "lr": 4.948692168555978e-05, "epoch": 0.0827411817425261, "percentage": 6.46, "elapsed_time": "1:24:55", "remaining_time": "20:29:14", "throughput": 696.92, "total_tokens": 3551280} {"current_steps": 2590, "total_steps": 40000, "loss": 0.7975, "lr": 4.94849410201444e-05, "epoch": 0.08290122271301453, "percentage": 6.48, "elapsed_time": "1:24:57", "remaining_time": "20:27:07", "throughput": 698.05, "total_tokens": 3558288} {"current_steps": 2595, "total_steps": 40000, "loss": 0.9947, "lr": 4.948295657884341e-05, "epoch": 0.08306126368350297, "percentage": 6.49, "elapsed_time": "1:24:59", "remaining_time": "20:25:00", "throughput": 699.13, "total_tokens": 3564992} {"current_steps": 2600, "total_steps": 40000, "loss": 1.0349, "lr": 4.9480968361962835e-05, "epoch": 0.08322130465399143, "percentage": 6.5, "elapsed_time": "1:25:00", "remaining_time": "20:22:54", "throughput": 700.23, "total_tokens": 3571808} {"current_steps": 2600, "total_steps": 40000, "eval_loss": 0.9399411082267761, "epoch": 0.08322130465399143, "percentage": 6.5, "elapsed_time": "1:30:49", "remaining_time": "21:46:30", "throughput": 655.43, "total_tokens": 3571808} {"current_steps": 2605, "total_steps": 40000, "loss": 0.7752, "lr": 4.9478976369809305e-05, "epoch": 0.08338134562447987, "percentage": 6.51, "elapsed_time": "1:30:52", "remaining_time": "21:44:37", "throughput": 656.28, "total_tokens": 3578656} {"current_steps": 2610, "total_steps": 40000, "loss": 0.8184, "lr": 4.947698060268999e-05, "epoch": 0.0835413865949683, "percentage": 6.53, "elapsed_time": "1:30:54", "remaining_time": "21:42:22", "throughput": 657.37, "total_tokens": 3585776} {"current_steps": 2615, "total_steps": 40000, "loss": 0.8855, "lr": 4.9474981060912665e-05, "epoch": 0.08370142756545676, "percentage": 6.54, "elapsed_time": "1:30:56", "remaining_time": "21:40:07", "throughput": 658.49, "total_tokens": 3592992} {"current_steps": 2620, "total_steps": 40000, "loss": 0.8317, "lr": 4.94729777447857e-05, "epoch": 0.0838614685359452, "percentage": 6.55, "elapsed_time": "1:30:58", "remaining_time": "21:37:52", "throughput": 659.54, "total_tokens": 3599904} {"current_steps": 2625, "total_steps": 40000, "loss": 0.8269, "lr": 4.947097065461801e-05, "epoch": 0.08402150950643365, "percentage": 6.56, "elapsed_time": "1:30:59", "remaining_time": "21:35:38", "throughput": 660.65, "total_tokens": 3607088} {"current_steps": 2630, "total_steps": 40000, "loss": 0.861, "lr": 4.9468959790719125e-05, "epoch": 0.08418155047692209, "percentage": 6.58, "elapsed_time": "1:31:01", "remaining_time": "21:33:25", "throughput": 661.71, "total_tokens": 3614016} {"current_steps": 2635, "total_steps": 40000, "loss": 0.8164, "lr": 4.9466945153399146e-05, "epoch": 0.08434159144741053, "percentage": 6.59, "elapsed_time": "1:31:03", "remaining_time": "21:31:12", "throughput": 662.69, "total_tokens": 3620544} {"current_steps": 2640, "total_steps": 40000, "loss": 1.0427, "lr": 4.9464926742968755e-05, "epoch": 0.08450163241789899, "percentage": 6.6, "elapsed_time": "1:31:05", "remaining_time": "21:28:59", "throughput": 663.86, "total_tokens": 3628080} {"current_steps": 2645, "total_steps": 40000, "loss": 0.8634, "lr": 4.946290455973921e-05, "epoch": 0.08466167338838743, "percentage": 6.61, "elapsed_time": "1:31:06", "remaining_time": "21:26:47", "throughput": 664.96, "total_tokens": 3635264} {"current_steps": 2650, "total_steps": 40000, "loss": 0.9844, "lr": 4.9460878604022365e-05, "epoch": 0.08482171435887587, "percentage": 6.62, "elapsed_time": "1:31:08", "remaining_time": "21:24:36", "throughput": 666.04, "total_tokens": 3642304} {"current_steps": 2655, "total_steps": 40000, "loss": 0.7988, "lr": 4.945884887613065e-05, "epoch": 0.08498175532936432, "percentage": 6.64, "elapsed_time": "1:31:10", "remaining_time": "21:22:24", "throughput": 667.02, "total_tokens": 3648832} {"current_steps": 2660, "total_steps": 40000, "loss": 0.9386, "lr": 4.9456815376377055e-05, "epoch": 0.08514179629985276, "percentage": 6.65, "elapsed_time": "1:31:12", "remaining_time": "21:20:14", "throughput": 668.04, "total_tokens": 3655568} {"current_steps": 2665, "total_steps": 40000, "loss": 0.7271, "lr": 4.9454778105075195e-05, "epoch": 0.08530183727034121, "percentage": 6.66, "elapsed_time": "1:31:13", "remaining_time": "21:18:04", "throughput": 669.01, "total_tokens": 3662032} {"current_steps": 2670, "total_steps": 40000, "loss": 1.0593, "lr": 4.945273706253924e-05, "epoch": 0.08546187824082965, "percentage": 6.68, "elapsed_time": "1:31:15", "remaining_time": "21:15:54", "throughput": 670.09, "total_tokens": 3669088} {"current_steps": 2675, "total_steps": 40000, "loss": 0.7904, "lr": 4.9450692249083925e-05, "epoch": 0.08562191921131809, "percentage": 6.69, "elapsed_time": "1:31:17", "remaining_time": "21:13:45", "throughput": 671.19, "total_tokens": 3676272} {"current_steps": 2680, "total_steps": 40000, "loss": 0.8746, "lr": 4.9448643665024605e-05, "epoch": 0.08578196018180655, "percentage": 6.7, "elapsed_time": "1:31:18", "remaining_time": "21:11:37", "throughput": 672.24, "total_tokens": 3683184} {"current_steps": 2685, "total_steps": 40000, "loss": 0.7485, "lr": 4.944659131067719e-05, "epoch": 0.08594200115229499, "percentage": 6.71, "elapsed_time": "1:31:20", "remaining_time": "21:09:28", "throughput": 673.24, "total_tokens": 3689872} {"current_steps": 2690, "total_steps": 40000, "loss": 0.8139, "lr": 4.944453518635818e-05, "epoch": 0.08610204212278343, "percentage": 6.73, "elapsed_time": "1:31:22", "remaining_time": "21:07:21", "throughput": 674.23, "total_tokens": 3696432} {"current_steps": 2695, "total_steps": 40000, "loss": 0.9207, "lr": 4.944247529238465e-05, "epoch": 0.08626208309327188, "percentage": 6.74, "elapsed_time": "1:31:24", "remaining_time": "21:05:13", "throughput": 675.33, "total_tokens": 3703648} {"current_steps": 2700, "total_steps": 40000, "loss": 1.0584, "lr": 4.944041162907427e-05, "epoch": 0.08642212406376032, "percentage": 6.75, "elapsed_time": "1:31:25", "remaining_time": "21:03:07", "throughput": 676.32, "total_tokens": 3710256} {"current_steps": 2705, "total_steps": 40000, "loss": 0.9122, "lr": 4.943834419674529e-05, "epoch": 0.08658216503424877, "percentage": 6.76, "elapsed_time": "1:31:27", "remaining_time": "21:01:00", "throughput": 677.34, "total_tokens": 3716992} {"current_steps": 2710, "total_steps": 40000, "loss": 0.885, "lr": 4.9436272995716506e-05, "epoch": 0.08674220600473721, "percentage": 6.78, "elapsed_time": "1:31:29", "remaining_time": "20:58:54", "throughput": 678.33, "total_tokens": 3723648} {"current_steps": 2715, "total_steps": 40000, "loss": 0.7945, "lr": 4.943419802630735e-05, "epoch": 0.08690224697522565, "percentage": 6.79, "elapsed_time": "1:31:31", "remaining_time": "20:56:49", "throughput": 679.32, "total_tokens": 3730240} {"current_steps": 2720, "total_steps": 40000, "loss": 0.7786, "lr": 4.94321192888378e-05, "epoch": 0.0870622879457141, "percentage": 6.8, "elapsed_time": "1:31:32", "remaining_time": "20:54:44", "throughput": 680.42, "total_tokens": 3737456} {"current_steps": 2725, "total_steps": 40000, "loss": 0.7358, "lr": 4.943003678362842e-05, "epoch": 0.08722232891620255, "percentage": 6.81, "elapsed_time": "1:31:34", "remaining_time": "20:52:40", "throughput": 681.49, "total_tokens": 3744528} {"current_steps": 2730, "total_steps": 40000, "loss": 0.8948, "lr": 4.942795051100036e-05, "epoch": 0.087382369886691, "percentage": 6.83, "elapsed_time": "1:31:36", "remaining_time": "20:50:36", "throughput": 682.58, "total_tokens": 3751696} {"current_steps": 2735, "total_steps": 40000, "loss": 0.9678, "lr": 4.942586047127536e-05, "epoch": 0.08754241085717944, "percentage": 6.84, "elapsed_time": "1:31:38", "remaining_time": "20:48:32", "throughput": 683.54, "total_tokens": 3758176} {"current_steps": 2740, "total_steps": 40000, "loss": 1.0743, "lr": 4.942376666477571e-05, "epoch": 0.08770245182766788, "percentage": 6.85, "elapsed_time": "1:31:39", "remaining_time": "20:46:29", "throughput": 684.67, "total_tokens": 3765568} {"current_steps": 2745, "total_steps": 40000, "loss": 0.8422, "lr": 4.9421669091824304e-05, "epoch": 0.08786249279815633, "percentage": 6.86, "elapsed_time": "1:31:41", "remaining_time": "20:44:26", "throughput": 685.64, "total_tokens": 3772064} {"current_steps": 2750, "total_steps": 40000, "loss": 0.6264, "lr": 4.9419567752744634e-05, "epoch": 0.08802253376864477, "percentage": 6.88, "elapsed_time": "1:31:43", "remaining_time": "20:42:24", "throughput": 686.72, "total_tokens": 3779232} {"current_steps": 2755, "total_steps": 40000, "loss": 0.9092, "lr": 4.941746264786074e-05, "epoch": 0.08818257473913321, "percentage": 6.89, "elapsed_time": "1:31:45", "remaining_time": "20:40:22", "throughput": 687.69, "total_tokens": 3785728} {"current_steps": 2760, "total_steps": 40000, "loss": 0.7735, "lr": 4.9415353777497254e-05, "epoch": 0.08834261570962167, "percentage": 6.9, "elapsed_time": "1:31:46", "remaining_time": "20:38:21", "throughput": 688.7, "total_tokens": 3792528} {"current_steps": 2765, "total_steps": 40000, "loss": 0.677, "lr": 4.9413241141979394e-05, "epoch": 0.0885026566801101, "percentage": 6.91, "elapsed_time": "1:31:48", "remaining_time": "20:36:20", "throughput": 689.73, "total_tokens": 3799376} {"current_steps": 2770, "total_steps": 40000, "loss": 0.8898, "lr": 4.9411124741632956e-05, "epoch": 0.08866269765059856, "percentage": 6.93, "elapsed_time": "1:31:50", "remaining_time": "20:34:19", "throughput": 690.74, "total_tokens": 3806128} {"current_steps": 2775, "total_steps": 40000, "loss": 0.9704, "lr": 4.940900457678431e-05, "epoch": 0.088822738621087, "percentage": 6.94, "elapsed_time": "1:31:51", "remaining_time": "20:32:19", "throughput": 691.75, "total_tokens": 3812896} {"current_steps": 2780, "total_steps": 40000, "loss": 0.8426, "lr": 4.9406880647760425e-05, "epoch": 0.08898277959157544, "percentage": 6.95, "elapsed_time": "1:31:53", "remaining_time": "20:30:20", "throughput": 692.76, "total_tokens": 3819648} {"current_steps": 2785, "total_steps": 40000, "loss": 1.2064, "lr": 4.9404752954888824e-05, "epoch": 0.08914282056206389, "percentage": 6.96, "elapsed_time": "1:31:55", "remaining_time": "20:28:20", "throughput": 693.75, "total_tokens": 3826352} {"current_steps": 2790, "total_steps": 40000, "loss": 0.8038, "lr": 4.940262149849762e-05, "epoch": 0.08930286153255233, "percentage": 6.98, "elapsed_time": "1:31:57", "remaining_time": "20:26:21", "throughput": 694.8, "total_tokens": 3833312} {"current_steps": 2795, "total_steps": 40000, "loss": 1.1054, "lr": 4.9400486278915526e-05, "epoch": 0.08946290250304077, "percentage": 6.99, "elapsed_time": "1:31:58", "remaining_time": "20:24:23", "throughput": 695.86, "total_tokens": 3840384} {"current_steps": 2800, "total_steps": 40000, "loss": 1.1218, "lr": 4.939834729647181e-05, "epoch": 0.08962294347352923, "percentage": 7.0, "elapsed_time": "1:32:00", "remaining_time": "20:22:25", "throughput": 696.87, "total_tokens": 3847184} {"current_steps": 2800, "total_steps": 40000, "eval_loss": 0.931298017501831, "epoch": 0.08962294347352923, "percentage": 7.0, "elapsed_time": "1:37:48", "remaining_time": "21:39:24", "throughput": 655.59, "total_tokens": 3847184} {"current_steps": 2805, "total_steps": 40000, "loss": 0.7985, "lr": 4.9396204551496326e-05, "epoch": 0.08978298444401767, "percentage": 7.01, "elapsed_time": "1:37:51", "remaining_time": "21:37:39", "throughput": 656.36, "total_tokens": 3853904} {"current_steps": 2810, "total_steps": 40000, "loss": 1.1067, "lr": 4.939405804431952e-05, "epoch": 0.08994302541450612, "percentage": 7.03, "elapsed_time": "1:37:53", "remaining_time": "21:35:34", "throughput": 657.34, "total_tokens": 3860832} {"current_steps": 2815, "total_steps": 40000, "loss": 0.9148, "lr": 4.9391907775272414e-05, "epoch": 0.09010306638499456, "percentage": 7.04, "elapsed_time": "1:37:55", "remaining_time": "21:33:28", "throughput": 658.28, "total_tokens": 3867488} {"current_steps": 2820, "total_steps": 40000, "loss": 0.8541, "lr": 4.9389753744686604e-05, "epoch": 0.090263107355483, "percentage": 7.05, "elapsed_time": "1:37:56", "remaining_time": "21:31:23", "throughput": 659.27, "total_tokens": 3874480} {"current_steps": 2825, "total_steps": 40000, "loss": 1.0059, "lr": 4.938759595289426e-05, "epoch": 0.09042314832597145, "percentage": 7.06, "elapsed_time": "1:37:58", "remaining_time": "21:29:18", "throughput": 660.23, "total_tokens": 3881248} {"current_steps": 2830, "total_steps": 40000, "loss": 1.219, "lr": 4.938543440022815e-05, "epoch": 0.09058318929645989, "percentage": 7.07, "elapsed_time": "1:38:00", "remaining_time": "21:27:14", "throughput": 661.26, "total_tokens": 3888464} {"current_steps": 2835, "total_steps": 40000, "loss": 0.9997, "lr": 4.938326908702161e-05, "epoch": 0.09074323026694833, "percentage": 7.09, "elapsed_time": "1:38:02", "remaining_time": "21:25:10", "throughput": 662.23, "total_tokens": 3895296} {"current_steps": 2840, "total_steps": 40000, "loss": 1.0494, "lr": 4.9381100013608554e-05, "epoch": 0.09090327123743679, "percentage": 7.1, "elapsed_time": "1:38:03", "remaining_time": "21:23:07", "throughput": 663.17, "total_tokens": 3901968} {"current_steps": 2845, "total_steps": 40000, "loss": 0.9164, "lr": 4.9378927180323485e-05, "epoch": 0.09106331220792523, "percentage": 7.11, "elapsed_time": "1:38:05", "remaining_time": "21:21:04", "throughput": 664.14, "total_tokens": 3908864} {"current_steps": 2850, "total_steps": 40000, "loss": 0.8869, "lr": 4.937675058750148e-05, "epoch": 0.09122335317841368, "percentage": 7.12, "elapsed_time": "1:38:07", "remaining_time": "21:19:01", "throughput": 665.08, "total_tokens": 3915536} {"current_steps": 2855, "total_steps": 40000, "loss": 0.8249, "lr": 4.937457023547819e-05, "epoch": 0.09138339414890212, "percentage": 7.14, "elapsed_time": "1:38:09", "remaining_time": "21:16:59", "throughput": 666.06, "total_tokens": 3922464} {"current_steps": 2860, "total_steps": 40000, "loss": 0.8407, "lr": 4.9372386124589876e-05, "epoch": 0.09154343511939056, "percentage": 7.15, "elapsed_time": "1:38:10", "remaining_time": "21:14:57", "throughput": 666.97, "total_tokens": 3928992} {"current_steps": 2865, "total_steps": 40000, "loss": 0.8102, "lr": 4.937019825517333e-05, "epoch": 0.09170347608987901, "percentage": 7.16, "elapsed_time": "1:38:12", "remaining_time": "21:12:56", "throughput": 667.99, "total_tokens": 3936112} {"current_steps": 2870, "total_steps": 40000, "loss": 0.8657, "lr": 4.9368006627565954e-05, "epoch": 0.09186351706036745, "percentage": 7.17, "elapsed_time": "1:38:14", "remaining_time": "21:10:55", "throughput": 668.93, "total_tokens": 3942848} {"current_steps": 2875, "total_steps": 40000, "loss": 0.8793, "lr": 4.936581124210573e-05, "epoch": 0.09202355803085589, "percentage": 7.19, "elapsed_time": "1:38:15", "remaining_time": "21:08:55", "throughput": 669.92, "total_tokens": 3949856} {"current_steps": 2880, "total_steps": 40000, "loss": 1.094, "lr": 4.9363612099131216e-05, "epoch": 0.09218359900134435, "percentage": 7.2, "elapsed_time": "1:38:17", "remaining_time": "21:06:54", "throughput": 670.81, "total_tokens": 3956240} {"current_steps": 2885, "total_steps": 40000, "loss": 1.0411, "lr": 4.936140919898155e-05, "epoch": 0.09234363997183279, "percentage": 7.21, "elapsed_time": "1:38:19", "remaining_time": "21:04:55", "throughput": 671.83, "total_tokens": 3963440} {"current_steps": 2890, "total_steps": 40000, "loss": 1.0066, "lr": 4.9359202541996426e-05, "epoch": 0.09250368094232124, "percentage": 7.22, "elapsed_time": "1:38:21", "remaining_time": "21:02:56", "throughput": 672.75, "total_tokens": 3970000} {"current_steps": 2895, "total_steps": 40000, "loss": 1.0129, "lr": 4.935699212851616e-05, "epoch": 0.09266372191280968, "percentage": 7.24, "elapsed_time": "1:38:22", "remaining_time": "21:00:57", "throughput": 673.69, "total_tokens": 3976720} {"current_steps": 2900, "total_steps": 40000, "loss": 0.8462, "lr": 4.935477795888162e-05, "epoch": 0.09282376288329812, "percentage": 7.25, "elapsed_time": "1:38:24", "remaining_time": "20:58:58", "throughput": 674.6, "total_tokens": 3983280} {"current_steps": 2905, "total_steps": 40000, "loss": 1.0003, "lr": 4.935256003343426e-05, "epoch": 0.09298380385378657, "percentage": 7.26, "elapsed_time": "1:38:26", "remaining_time": "20:57:00", "throughput": 675.56, "total_tokens": 3990096} {"current_steps": 2910, "total_steps": 40000, "loss": 0.9597, "lr": 4.93503383525161e-05, "epoch": 0.09314384482427501, "percentage": 7.27, "elapsed_time": "1:38:28", "remaining_time": "20:55:03", "throughput": 676.55, "total_tokens": 3997152} {"current_steps": 2915, "total_steps": 40000, "loss": 0.7734, "lr": 4.934811291646977e-05, "epoch": 0.09330388579476345, "percentage": 7.29, "elapsed_time": "1:38:29", "remaining_time": "20:53:05", "throughput": 677.48, "total_tokens": 4003792} {"current_steps": 2920, "total_steps": 40000, "loss": 1.0885, "lr": 4.934588372563845e-05, "epoch": 0.0934639267652519, "percentage": 7.3, "elapsed_time": "1:38:31", "remaining_time": "20:51:09", "throughput": 678.45, "total_tokens": 4010704} {"current_steps": 2925, "total_steps": 40000, "loss": 0.9166, "lr": 4.93436507803659e-05, "epoch": 0.09362396773574035, "percentage": 7.31, "elapsed_time": "1:38:33", "remaining_time": "20:49:12", "throughput": 679.36, "total_tokens": 4017264} {"current_steps": 2930, "total_steps": 40000, "loss": 0.9256, "lr": 4.934141408099649e-05, "epoch": 0.0937840087062288, "percentage": 7.32, "elapsed_time": "1:38:35", "remaining_time": "20:47:16", "throughput": 680.28, "total_tokens": 4023920} {"current_steps": 2935, "total_steps": 40000, "loss": 0.9598, "lr": 4.9339173627875135e-05, "epoch": 0.09394404967671724, "percentage": 7.34, "elapsed_time": "1:38:36", "remaining_time": "20:45:20", "throughput": 681.23, "total_tokens": 4030720} {"current_steps": 2940, "total_steps": 40000, "loss": 0.8475, "lr": 4.9336929421347335e-05, "epoch": 0.09410409064720568, "percentage": 7.35, "elapsed_time": "1:38:38", "remaining_time": "20:43:25", "throughput": 682.16, "total_tokens": 4037376} {"current_steps": 2945, "total_steps": 40000, "loss": 0.8816, "lr": 4.933468146175918e-05, "epoch": 0.09426413161769413, "percentage": 7.36, "elapsed_time": "1:38:40", "remaining_time": "20:41:30", "throughput": 683.14, "total_tokens": 4044352} {"current_steps": 2950, "total_steps": 40000, "loss": 0.8737, "lr": 4.933242974945734e-05, "epoch": 0.09442417258818257, "percentage": 7.38, "elapsed_time": "1:38:41", "remaining_time": "20:39:36", "throughput": 684.11, "total_tokens": 4051264} {"current_steps": 2955, "total_steps": 40000, "loss": 1.0623, "lr": 4.933017428478906e-05, "epoch": 0.09458421355867103, "percentage": 7.39, "elapsed_time": "1:38:43", "remaining_time": "20:37:41", "throughput": 685.05, "total_tokens": 4058032} {"current_steps": 2960, "total_steps": 40000, "loss": 1.0079, "lr": 4.932791506810214e-05, "epoch": 0.09474425452915947, "percentage": 7.4, "elapsed_time": "1:38:45", "remaining_time": "20:35:48", "throughput": 685.98, "total_tokens": 4064768} {"current_steps": 2965, "total_steps": 40000, "loss": 0.9029, "lr": 4.932565209974499e-05, "epoch": 0.0949042954996479, "percentage": 7.41, "elapsed_time": "1:38:47", "remaining_time": "20:33:55", "throughput": 686.96, "total_tokens": 4071728} {"current_steps": 2970, "total_steps": 40000, "loss": 0.7039, "lr": 4.93233853800666e-05, "epoch": 0.09506433647013636, "percentage": 7.42, "elapsed_time": "1:38:48", "remaining_time": "20:32:02", "throughput": 687.89, "total_tokens": 4078464} {"current_steps": 2975, "total_steps": 40000, "loss": 0.9092, "lr": 4.932111490941651e-05, "epoch": 0.0952243774406248, "percentage": 7.44, "elapsed_time": "1:38:50", "remaining_time": "20:30:09", "throughput": 688.9, "total_tokens": 4085632} {"current_steps": 2980, "total_steps": 40000, "loss": 0.9257, "lr": 4.9318840688144876e-05, "epoch": 0.09538441841111324, "percentage": 7.45, "elapsed_time": "1:38:52", "remaining_time": "20:28:17", "throughput": 689.92, "total_tokens": 4092912} {"current_steps": 2985, "total_steps": 40000, "loss": 0.9017, "lr": 4.9316562716602387e-05, "epoch": 0.09554445938160169, "percentage": 7.46, "elapsed_time": "1:38:54", "remaining_time": "20:26:25", "throughput": 690.98, "total_tokens": 4100384} {"current_steps": 2990, "total_steps": 40000, "loss": 1.18, "lr": 4.9314280995140346e-05, "epoch": 0.09570450035209013, "percentage": 7.47, "elapsed_time": "1:38:55", "remaining_time": "20:24:33", "throughput": 691.96, "total_tokens": 4107376} {"current_steps": 2995, "total_steps": 40000, "loss": 0.9294, "lr": 4.931199552411063e-05, "epoch": 0.09586454132257859, "percentage": 7.49, "elapsed_time": "1:38:57", "remaining_time": "20:22:42", "throughput": 692.86, "total_tokens": 4113936} {"current_steps": 3000, "total_steps": 40000, "loss": 0.8946, "lr": 4.930970630386568e-05, "epoch": 0.09602458229306703, "percentage": 7.5, "elapsed_time": "1:38:59", "remaining_time": "20:20:51", "throughput": 693.85, "total_tokens": 4121024} {"current_steps": 3000, "total_steps": 40000, "eval_loss": 0.9184989333152771, "epoch": 0.09602458229306703, "percentage": 7.5, "elapsed_time": "1:44:47", "remaining_time": "21:32:21", "throughput": 655.47, "total_tokens": 4121024} {"current_steps": 3005, "total_steps": 40000, "loss": 0.935, "lr": 4.9307413334758524e-05, "epoch": 0.09618462326355547, "percentage": 7.51, "elapsed_time": "1:44:50", "remaining_time": "21:30:43", "throughput": 656.21, "total_tokens": 4127872} {"current_steps": 3010, "total_steps": 40000, "loss": 0.7282, "lr": 4.930511661714276e-05, "epoch": 0.09634466423404392, "percentage": 7.52, "elapsed_time": "1:44:52", "remaining_time": "21:28:45", "throughput": 657.09, "total_tokens": 4134560} {"current_steps": 3015, "total_steps": 40000, "loss": 0.8473, "lr": 4.9302816151372576e-05, "epoch": 0.09650470520453236, "percentage": 7.54, "elapsed_time": "1:44:53", "remaining_time": "21:26:48", "throughput": 658.07, "total_tokens": 4141904} {"current_steps": 3020, "total_steps": 40000, "loss": 0.9067, "lr": 4.930051193780274e-05, "epoch": 0.0966647461750208, "percentage": 7.55, "elapsed_time": "1:44:55", "remaining_time": "21:24:51", "throughput": 658.96, "total_tokens": 4148640} {"current_steps": 3025, "total_steps": 40000, "loss": 1.0321, "lr": 4.929820397678858e-05, "epoch": 0.09682478714550925, "percentage": 7.56, "elapsed_time": "1:44:57", "remaining_time": "21:22:54", "throughput": 659.85, "total_tokens": 4155392} {"current_steps": 3030, "total_steps": 40000, "loss": 0.8868, "lr": 4.9295892268686015e-05, "epoch": 0.09698482811599769, "percentage": 7.58, "elapsed_time": "1:44:59", "remaining_time": "21:20:58", "throughput": 660.77, "total_tokens": 4162288} {"current_steps": 3035, "total_steps": 40000, "loss": 0.6965, "lr": 4.9293576813851536e-05, "epoch": 0.09714486908648615, "percentage": 7.59, "elapsed_time": "1:45:00", "remaining_time": "21:19:02", "throughput": 661.71, "total_tokens": 4169408} {"current_steps": 3040, "total_steps": 40000, "loss": 0.9579, "lr": 4.929125761264223e-05, "epoch": 0.09730491005697459, "percentage": 7.6, "elapsed_time": "1:45:02", "remaining_time": "21:17:07", "throughput": 662.6, "total_tokens": 4176128} {"current_steps": 3045, "total_steps": 40000, "loss": 0.721, "lr": 4.928893466541573e-05, "epoch": 0.09746495102746303, "percentage": 7.61, "elapsed_time": "1:45:04", "remaining_time": "21:15:11", "throughput": 663.5, "total_tokens": 4182960} {"current_steps": 3050, "total_steps": 40000, "loss": 1.2568, "lr": 4.928660797253027e-05, "epoch": 0.09762499199795148, "percentage": 7.62, "elapsed_time": "1:45:06", "remaining_time": "21:13:17", "throughput": 664.37, "total_tokens": 4189584} {"current_steps": 3055, "total_steps": 40000, "loss": 1.1028, "lr": 4.928427753434467e-05, "epoch": 0.09778503296843992, "percentage": 7.64, "elapsed_time": "1:45:07", "remaining_time": "21:11:22", "throughput": 665.22, "total_tokens": 4196144} {"current_steps": 3060, "total_steps": 40000, "loss": 0.832, "lr": 4.9281943351218286e-05, "epoch": 0.09794507393892836, "percentage": 7.65, "elapsed_time": "1:45:09", "remaining_time": "21:09:28", "throughput": 666.17, "total_tokens": 4203264} {"current_steps": 3065, "total_steps": 40000, "loss": 0.7812, "lr": 4.9279605423511095e-05, "epoch": 0.09810511490941681, "percentage": 7.66, "elapsed_time": "1:45:11", "remaining_time": "21:07:35", "throughput": 667.06, "total_tokens": 4210048} {"current_steps": 3070, "total_steps": 40000, "loss": 1.0966, "lr": 4.927726375158363e-05, "epoch": 0.09826515587990525, "percentage": 7.67, "elapsed_time": "1:45:13", "remaining_time": "21:05:41", "throughput": 667.89, "total_tokens": 4216448} {"current_steps": 3075, "total_steps": 40000, "loss": 0.7551, "lr": 4.9274918335797004e-05, "epoch": 0.0984251968503937, "percentage": 7.69, "elapsed_time": "1:45:14", "remaining_time": "21:03:48", "throughput": 668.79, "total_tokens": 4223296} {"current_steps": 3080, "total_steps": 40000, "loss": 0.9545, "lr": 4.927256917651292e-05, "epoch": 0.09858523782088215, "percentage": 7.7, "elapsed_time": "1:45:16", "remaining_time": "21:01:56", "throughput": 669.71, "total_tokens": 4230256} {"current_steps": 3085, "total_steps": 40000, "loss": 0.7668, "lr": 4.927021627409364e-05, "epoch": 0.09874527879137059, "percentage": 7.71, "elapsed_time": "1:45:18", "remaining_time": "21:00:04", "throughput": 670.59, "total_tokens": 4236976} {"current_steps": 3090, "total_steps": 40000, "loss": 0.8968, "lr": 4.9267859628902005e-05, "epoch": 0.09890531976185904, "percentage": 7.72, "elapsed_time": "1:45:20", "remaining_time": "20:58:12", "throughput": 671.45, "total_tokens": 4243584} {"current_steps": 3095, "total_steps": 40000, "loss": 0.977, "lr": 4.9265499241301454e-05, "epoch": 0.09906536073234748, "percentage": 7.74, "elapsed_time": "1:45:21", "remaining_time": "20:56:20", "throughput": 672.34, "total_tokens": 4250352} {"current_steps": 3100, "total_steps": 40000, "loss": 0.8912, "lr": 4.926313511165598e-05, "epoch": 0.09922540170283592, "percentage": 7.75, "elapsed_time": "1:45:23", "remaining_time": "20:54:29", "throughput": 673.22, "total_tokens": 4257072} {"current_steps": 3105, "total_steps": 40000, "loss": 0.8962, "lr": 4.926076724033016e-05, "epoch": 0.09938544267332437, "percentage": 7.76, "elapsed_time": "1:45:25", "remaining_time": "20:52:39", "throughput": 674.19, "total_tokens": 4264416} {"current_steps": 3110, "total_steps": 40000, "loss": 1.0908, "lr": 4.9258395627689146e-05, "epoch": 0.09954548364381281, "percentage": 7.78, "elapsed_time": "1:45:26", "remaining_time": "20:50:48", "throughput": 675.07, "total_tokens": 4271104} {"current_steps": 3115, "total_steps": 40000, "loss": 0.9256, "lr": 4.925602027409868e-05, "epoch": 0.09970552461430127, "percentage": 7.79, "elapsed_time": "1:45:28", "remaining_time": "20:48:58", "throughput": 676.02, "total_tokens": 4278352} {"current_steps": 3120, "total_steps": 40000, "loss": 0.8779, "lr": 4.925364117992507e-05, "epoch": 0.0998655655847897, "percentage": 7.8, "elapsed_time": "1:45:30", "remaining_time": "20:47:08", "throughput": 676.9, "total_tokens": 4285056} {"current_steps": 3125, "total_steps": 40000, "loss": 1.0313, "lr": 4.92512583455352e-05, "epoch": 0.10002560655527815, "percentage": 7.81, "elapsed_time": "1:45:32", "remaining_time": "20:45:19", "throughput": 677.82, "total_tokens": 4292096} {"current_steps": 3130, "total_steps": 40000, "loss": 0.9259, "lr": 4.9248871771296536e-05, "epoch": 0.1001856475257666, "percentage": 7.83, "elapsed_time": "1:45:33", "remaining_time": "20:43:30", "throughput": 678.72, "total_tokens": 4298960} {"current_steps": 3135, "total_steps": 40000, "loss": 0.828, "lr": 4.924648145757711e-05, "epoch": 0.10034568849625504, "percentage": 7.84, "elapsed_time": "1:45:35", "remaining_time": "20:41:41", "throughput": 679.58, "total_tokens": 4305600} {"current_steps": 3140, "total_steps": 40000, "loss": 0.8562, "lr": 4.924408740474554e-05, "epoch": 0.1005057294667435, "percentage": 7.85, "elapsed_time": "1:45:37", "remaining_time": "20:39:53", "throughput": 680.54, "total_tokens": 4312832} {"current_steps": 3145, "total_steps": 40000, "loss": 0.8644, "lr": 4.924168961317103e-05, "epoch": 0.10066577043723193, "percentage": 7.86, "elapsed_time": "1:45:39", "remaining_time": "20:38:05", "throughput": 681.45, "total_tokens": 4319776} {"current_steps": 3150, "total_steps": 40000, "loss": 0.5942, "lr": 4.9239288083223334e-05, "epoch": 0.10082581140772037, "percentage": 7.88, "elapsed_time": "1:45:40", "remaining_time": "20:36:17", "throughput": 682.4, "total_tokens": 4326992} {"current_steps": 3155, "total_steps": 40000, "loss": 0.7024, "lr": 4.9236882815272803e-05, "epoch": 0.10098585237820883, "percentage": 7.89, "elapsed_time": "1:45:42", "remaining_time": "20:34:30", "throughput": 683.34, "total_tokens": 4334160} {"current_steps": 3160, "total_steps": 40000, "loss": 0.9249, "lr": 4.9234473809690365e-05, "epoch": 0.10114589334869727, "percentage": 7.9, "elapsed_time": "1:45:44", "remaining_time": "20:32:43", "throughput": 684.25, "total_tokens": 4341104} {"current_steps": 3165, "total_steps": 40000, "loss": 0.972, "lr": 4.923206106684752e-05, "epoch": 0.1013059343191857, "percentage": 7.91, "elapsed_time": "1:45:46", "remaining_time": "20:30:56", "throughput": 685.18, "total_tokens": 4348192} {"current_steps": 3170, "total_steps": 40000, "loss": 0.7586, "lr": 4.922964458711634e-05, "epoch": 0.10146597528967416, "percentage": 7.92, "elapsed_time": "1:45:47", "remaining_time": "20:29:10", "throughput": 686.07, "total_tokens": 4355024} {"current_steps": 3175, "total_steps": 40000, "loss": 0.9569, "lr": 4.9227224370869474e-05, "epoch": 0.1016260162601626, "percentage": 7.94, "elapsed_time": "1:45:49", "remaining_time": "20:27:24", "throughput": 686.94, "total_tokens": 4361744} {"current_steps": 3180, "total_steps": 40000, "loss": 0.6612, "lr": 4.9224800418480155e-05, "epoch": 0.10178605723065105, "percentage": 7.95, "elapsed_time": "1:45:51", "remaining_time": "20:25:38", "throughput": 687.9, "total_tokens": 4369024} {"current_steps": 3185, "total_steps": 40000, "loss": 1.0744, "lr": 4.9222372730322176e-05, "epoch": 0.10194609820113949, "percentage": 7.96, "elapsed_time": "1:45:52", "remaining_time": "20:23:53", "throughput": 688.84, "total_tokens": 4376224} {"current_steps": 3190, "total_steps": 40000, "loss": 0.9832, "lr": 4.921994130676993e-05, "epoch": 0.10210613917162793, "percentage": 7.98, "elapsed_time": "1:45:54", "remaining_time": "20:22:08", "throughput": 689.76, "total_tokens": 4383248} {"current_steps": 3195, "total_steps": 40000, "loss": 0.9932, "lr": 4.9217506148198366e-05, "epoch": 0.10226618014211639, "percentage": 7.99, "elapsed_time": "1:45:56", "remaining_time": "20:20:23", "throughput": 690.64, "total_tokens": 4390032} {"current_steps": 3200, "total_steps": 40000, "loss": 0.7198, "lr": 4.921506725498302e-05, "epoch": 0.10242622111260483, "percentage": 8.0, "elapsed_time": "1:45:58", "remaining_time": "20:18:39", "throughput": 691.53, "total_tokens": 4396880} {"current_steps": 3200, "total_steps": 40000, "eval_loss": 0.9093787670135498, "epoch": 0.10242622111260483, "percentage": 8.0, "elapsed_time": "1:51:46", "remaining_time": "21:25:19", "throughput": 655.66, "total_tokens": 4396880} {"current_steps": 3205, "total_steps": 40000, "loss": 0.7087, "lr": 4.9212624627499994e-05, "epoch": 0.10258626208309327, "percentage": 8.01, "elapsed_time": "1:51:49", "remaining_time": "21:23:47", "throughput": 656.33, "total_tokens": 4403616} {"current_steps": 3210, "total_steps": 40000, "loss": 0.915, "lr": 4.921017826612597e-05, "epoch": 0.10274630305358172, "percentage": 8.03, "elapsed_time": "1:51:51", "remaining_time": "21:21:57", "throughput": 657.19, "total_tokens": 4410528} {"current_steps": 3215, "total_steps": 40000, "loss": 0.8877, "lr": 4.9207728171238223e-05, "epoch": 0.10290634402407016, "percentage": 8.04, "elapsed_time": "1:51:52", "remaining_time": "21:20:07", "throughput": 658.1, "total_tokens": 4417792} {"current_steps": 3220, "total_steps": 40000, "loss": 0.742, "lr": 4.920527434321458e-05, "epoch": 0.10306638499455861, "percentage": 8.05, "elapsed_time": "1:51:54", "remaining_time": "21:18:17", "throughput": 658.97, "total_tokens": 4424752} {"current_steps": 3225, "total_steps": 40000, "loss": 1.0539, "lr": 4.920281678243345e-05, "epoch": 0.10322642596504705, "percentage": 8.06, "elapsed_time": "1:51:56", "remaining_time": "21:16:27", "throughput": 659.79, "total_tokens": 4431408} {"current_steps": 3230, "total_steps": 40000, "loss": 0.9647, "lr": 4.920035548927381e-05, "epoch": 0.10338646693553549, "percentage": 8.08, "elapsed_time": "1:51:58", "remaining_time": "21:14:41", "throughput": 660.61, "total_tokens": 4438240} {"current_steps": 3235, "total_steps": 40000, "loss": 0.917, "lr": 4.919789046411525e-05, "epoch": 0.10354650790602395, "percentage": 8.09, "elapsed_time": "1:52:00", "remaining_time": "21:12:52", "throughput": 661.45, "total_tokens": 4445056} {"current_steps": 3240, "total_steps": 40000, "loss": 0.7663, "lr": 4.919542170733787e-05, "epoch": 0.10370654887651239, "percentage": 8.1, "elapsed_time": "1:52:01", "remaining_time": "21:11:04", "throughput": 662.29, "total_tokens": 4451808} {"current_steps": 3245, "total_steps": 40000, "loss": 0.8936, "lr": 4.919294921932242e-05, "epoch": 0.10386658984700083, "percentage": 8.11, "elapsed_time": "1:52:03", "remaining_time": "21:09:15", "throughput": 663.16, "total_tokens": 4458784} {"current_steps": 3250, "total_steps": 40000, "loss": 0.9842, "lr": 4.919047300045016e-05, "epoch": 0.10402663081748928, "percentage": 8.12, "elapsed_time": "1:52:05", "remaining_time": "21:07:27", "throughput": 664.01, "total_tokens": 4465648} {"current_steps": 3255, "total_steps": 40000, "loss": 1.0174, "lr": 4.918799305110299e-05, "epoch": 0.10418667178797772, "percentage": 8.14, "elapsed_time": "1:52:07", "remaining_time": "21:05:40", "throughput": 664.83, "total_tokens": 4472352} {"current_steps": 3260, "total_steps": 40000, "loss": 0.8626, "lr": 4.918550937166331e-05, "epoch": 0.10434671275846617, "percentage": 8.15, "elapsed_time": "1:52:08", "remaining_time": "21:03:52", "throughput": 665.68, "total_tokens": 4479200} {"current_steps": 3265, "total_steps": 40000, "loss": 1.0783, "lr": 4.918302196251415e-05, "epoch": 0.10450675372895461, "percentage": 8.16, "elapsed_time": "1:52:10", "remaining_time": "21:02:06", "throughput": 666.5, "total_tokens": 4485904} {"current_steps": 3270, "total_steps": 40000, "loss": 0.8366, "lr": 4.91805308240391e-05, "epoch": 0.10466679469944305, "percentage": 8.18, "elapsed_time": "1:52:12", "remaining_time": "21:00:19", "throughput": 667.33, "total_tokens": 4492608} {"current_steps": 3275, "total_steps": 40000, "loss": 0.9436, "lr": 4.9178035956622326e-05, "epoch": 0.1048268356699315, "percentage": 8.19, "elapsed_time": "1:52:13", "remaining_time": "20:58:33", "throughput": 668.17, "total_tokens": 4499424} {"current_steps": 3280, "total_steps": 40000, "loss": 1.3028, "lr": 4.917553736064857e-05, "epoch": 0.10498687664041995, "percentage": 8.2, "elapsed_time": "1:52:15", "remaining_time": "20:56:47", "throughput": 669.01, "total_tokens": 4506288} {"current_steps": 3285, "total_steps": 40000, "loss": 0.9867, "lr": 4.917303503650314e-05, "epoch": 0.10514691761090839, "percentage": 8.21, "elapsed_time": "1:52:17", "remaining_time": "20:55:01", "throughput": 669.79, "total_tokens": 4512672} {"current_steps": 3290, "total_steps": 40000, "loss": 0.7933, "lr": 4.917052898457194e-05, "epoch": 0.10530695858139684, "percentage": 8.22, "elapsed_time": "1:52:19", "remaining_time": "20:53:16", "throughput": 670.61, "total_tokens": 4519376} {"current_steps": 3295, "total_steps": 40000, "loss": 0.7983, "lr": 4.916801920524141e-05, "epoch": 0.10546699955188528, "percentage": 8.24, "elapsed_time": "1:52:20", "remaining_time": "20:51:31", "throughput": 671.47, "total_tokens": 4526352} {"current_steps": 3300, "total_steps": 40000, "loss": 0.843, "lr": 4.916550569889862e-05, "epoch": 0.10562704052237373, "percentage": 8.25, "elapsed_time": "1:52:22", "remaining_time": "20:49:46", "throughput": 672.33, "total_tokens": 4533264} {"current_steps": 3305, "total_steps": 40000, "loss": 0.9656, "lr": 4.916298846593116e-05, "epoch": 0.10578708149286217, "percentage": 8.26, "elapsed_time": "1:52:24", "remaining_time": "20:48:02", "throughput": 673.15, "total_tokens": 4540016} {"current_steps": 3310, "total_steps": 40000, "loss": 0.9305, "lr": 4.916046750672722e-05, "epoch": 0.10594712246335061, "percentage": 8.28, "elapsed_time": "1:52:26", "remaining_time": "20:46:18", "throughput": 673.95, "total_tokens": 4546544} {"current_steps": 3315, "total_steps": 40000, "loss": 0.6697, "lr": 4.915794282167559e-05, "epoch": 0.10610716343383907, "percentage": 8.29, "elapsed_time": "1:52:27", "remaining_time": "20:44:34", "throughput": 674.81, "total_tokens": 4553520} {"current_steps": 3320, "total_steps": 40000, "loss": 0.9853, "lr": 4.915541441116558e-05, "epoch": 0.1062672044043275, "percentage": 8.3, "elapsed_time": "1:52:29", "remaining_time": "20:42:50", "throughput": 675.72, "total_tokens": 4560832} {"current_steps": 3325, "total_steps": 40000, "loss": 0.7885, "lr": 4.915288227558711e-05, "epoch": 0.10642724537481596, "percentage": 8.31, "elapsed_time": "1:52:31", "remaining_time": "20:41:07", "throughput": 676.58, "total_tokens": 4567824} {"current_steps": 3330, "total_steps": 40000, "loss": 0.9094, "lr": 4.915034641533066e-05, "epoch": 0.1065872863453044, "percentage": 8.33, "elapsed_time": "1:52:33", "remaining_time": "20:39:25", "throughput": 677.41, "total_tokens": 4574608} {"current_steps": 3335, "total_steps": 40000, "loss": 0.7965, "lr": 4.914780683078731e-05, "epoch": 0.10674732731579284, "percentage": 8.34, "elapsed_time": "1:52:34", "remaining_time": "20:37:42", "throughput": 678.23, "total_tokens": 4581296} {"current_steps": 3340, "total_steps": 40000, "loss": 1.1506, "lr": 4.9145263522348695e-05, "epoch": 0.10690736828628129, "percentage": 8.35, "elapsed_time": "1:52:36", "remaining_time": "20:36:00", "throughput": 679.09, "total_tokens": 4588320} {"current_steps": 3345, "total_steps": 40000, "loss": 0.8604, "lr": 4.9142716490407e-05, "epoch": 0.10706740925676973, "percentage": 8.36, "elapsed_time": "1:52:38", "remaining_time": "20:34:18", "throughput": 679.97, "total_tokens": 4595408} {"current_steps": 3350, "total_steps": 40000, "loss": 0.94, "lr": 4.914016573535504e-05, "epoch": 0.10722745022725817, "percentage": 8.38, "elapsed_time": "1:52:40", "remaining_time": "20:32:36", "throughput": 680.91, "total_tokens": 4602992} {"current_steps": 3355, "total_steps": 40000, "loss": 0.6553, "lr": 4.9137611257586154e-05, "epoch": 0.10738749119774663, "percentage": 8.39, "elapsed_time": "1:52:41", "remaining_time": "20:30:55", "throughput": 681.72, "total_tokens": 4609648} {"current_steps": 3360, "total_steps": 40000, "loss": 1.0028, "lr": 4.9135053057494274e-05, "epoch": 0.10754753216823507, "percentage": 8.4, "elapsed_time": "1:52:43", "remaining_time": "20:29:14", "throughput": 682.55, "total_tokens": 4616432} {"current_steps": 3365, "total_steps": 40000, "loss": 0.8312, "lr": 4.913249113547392e-05, "epoch": 0.10770757313872352, "percentage": 8.41, "elapsed_time": "1:52:45", "remaining_time": "20:27:33", "throughput": 683.37, "total_tokens": 4623168} {"current_steps": 3370, "total_steps": 40000, "loss": 1.0836, "lr": 4.912992549192016e-05, "epoch": 0.10786761410921196, "percentage": 8.43, "elapsed_time": "1:52:46", "remaining_time": "20:25:53", "throughput": 684.21, "total_tokens": 4630064} {"current_steps": 3375, "total_steps": 40000, "loss": 1.0141, "lr": 4.9127356127228665e-05, "epoch": 0.1080276550797004, "percentage": 8.44, "elapsed_time": "1:52:48", "remaining_time": "20:24:13", "throughput": 685.06, "total_tokens": 4637008} {"current_steps": 3380, "total_steps": 40000, "loss": 0.9802, "lr": 4.912478304179564e-05, "epoch": 0.10818769605018885, "percentage": 8.45, "elapsed_time": "1:52:50", "remaining_time": "20:22:33", "throughput": 685.89, "total_tokens": 4643792} {"current_steps": 3385, "total_steps": 40000, "loss": 0.8776, "lr": 4.9122206236017896e-05, "epoch": 0.10834773702067729, "percentage": 8.46, "elapsed_time": "1:52:52", "remaining_time": "20:20:53", "throughput": 686.7, "total_tokens": 4650464} {"current_steps": 3390, "total_steps": 40000, "loss": 0.9412, "lr": 4.911962571029282e-05, "epoch": 0.10850777799116573, "percentage": 8.48, "elapsed_time": "1:52:53", "remaining_time": "20:19:14", "throughput": 687.53, "total_tokens": 4657248} {"current_steps": 3395, "total_steps": 40000, "loss": 1.0543, "lr": 4.9117041465018353e-05, "epoch": 0.10866781896165419, "percentage": 8.49, "elapsed_time": "1:52:55", "remaining_time": "20:17:35", "throughput": 688.3, "total_tokens": 4663696} {"current_steps": 3400, "total_steps": 40000, "loss": 0.8046, "lr": 4.911445350059302e-05, "epoch": 0.10882785993214263, "percentage": 8.5, "elapsed_time": "1:52:57", "remaining_time": "20:15:56", "throughput": 689.23, "total_tokens": 4671152} {"current_steps": 3400, "total_steps": 40000, "eval_loss": 0.9013528227806091, "epoch": 0.10882785993214263, "percentage": 8.5, "elapsed_time": "1:58:44", "remaining_time": "21:18:11", "throughput": 655.66, "total_tokens": 4671152} {"current_steps": 3405, "total_steps": 40000, "loss": 0.722, "lr": 4.9111861817415905e-05, "epoch": 0.10898790090263108, "percentage": 8.51, "elapsed_time": "1:58:47", "remaining_time": "21:16:45", "throughput": 656.28, "total_tokens": 4677840} {"current_steps": 3410, "total_steps": 40000, "loss": 0.8458, "lr": 4.91092664158867e-05, "epoch": 0.10914794187311952, "percentage": 8.53, "elapsed_time": "1:58:49", "remaining_time": "21:15:01", "throughput": 657.04, "total_tokens": 4684432} {"current_steps": 3415, "total_steps": 40000, "loss": 1.0482, "lr": 4.910666729640563e-05, "epoch": 0.10930798284360796, "percentage": 8.54, "elapsed_time": "1:58:51", "remaining_time": "21:13:17", "throughput": 657.88, "total_tokens": 4691552} {"current_steps": 3420, "total_steps": 40000, "loss": 0.8885, "lr": 4.910406445937353e-05, "epoch": 0.10946802381409641, "percentage": 8.55, "elapsed_time": "1:58:53", "remaining_time": "21:11:34", "throughput": 658.7, "total_tokens": 4698528} {"current_steps": 3425, "total_steps": 40000, "loss": 0.7279, "lr": 4.9101457905191774e-05, "epoch": 0.10962806478458485, "percentage": 8.56, "elapsed_time": "1:58:54", "remaining_time": "21:09:51", "throughput": 659.55, "total_tokens": 4705728} {"current_steps": 3430, "total_steps": 40000, "loss": 0.9934, "lr": 4.909884763426233e-05, "epoch": 0.10978810575507329, "percentage": 8.58, "elapsed_time": "1:58:56", "remaining_time": "21:08:08", "throughput": 660.3, "total_tokens": 4712240} {"current_steps": 3435, "total_steps": 40000, "loss": 1.0438, "lr": 4.9096233646987736e-05, "epoch": 0.10994814672556175, "percentage": 8.59, "elapsed_time": "1:58:58", "remaining_time": "21:06:25", "throughput": 661.22, "total_tokens": 4720000} {"current_steps": 3440, "total_steps": 40000, "loss": 1.1385, "lr": 4.9093615943771104e-05, "epoch": 0.11010818769605019, "percentage": 8.6, "elapsed_time": "1:59:00", "remaining_time": "21:04:43", "throughput": 662.13, "total_tokens": 4727648} {"current_steps": 3445, "total_steps": 40000, "loss": 1.1014, "lr": 4.909099452501611e-05, "epoch": 0.11026822866653864, "percentage": 8.61, "elapsed_time": "1:59:01", "remaining_time": "21:03:01", "throughput": 662.88, "total_tokens": 4734128} {"current_steps": 3450, "total_steps": 40000, "loss": 0.6886, "lr": 4.908836939112702e-05, "epoch": 0.11042826963702708, "percentage": 8.62, "elapsed_time": "1:59:03", "remaining_time": "21:01:19", "throughput": 663.69, "total_tokens": 4741088} {"current_steps": 3455, "total_steps": 40000, "loss": 0.9042, "lr": 4.908574054250865e-05, "epoch": 0.11058831060751552, "percentage": 8.64, "elapsed_time": "1:59:05", "remaining_time": "20:59:38", "throughput": 664.51, "total_tokens": 4748064} {"current_steps": 3460, "total_steps": 40000, "loss": 1.0196, "lr": 4.9083107979566414e-05, "epoch": 0.11074835157800397, "percentage": 8.65, "elapsed_time": "1:59:06", "remaining_time": "20:57:57", "throughput": 665.33, "total_tokens": 4755104} {"current_steps": 3465, "total_steps": 40000, "loss": 0.9116, "lr": 4.908047170270628e-05, "epoch": 0.11090839254849241, "percentage": 8.66, "elapsed_time": "1:59:08", "remaining_time": "20:56:16", "throughput": 666.17, "total_tokens": 4762240} {"current_steps": 3470, "total_steps": 40000, "loss": 0.8064, "lr": 4.9077831712334784e-05, "epoch": 0.11106843351898085, "percentage": 8.67, "elapsed_time": "1:59:10", "remaining_time": "20:54:35", "throughput": 666.91, "total_tokens": 4768672} {"current_steps": 3475, "total_steps": 40000, "loss": 0.8636, "lr": 4.907518800885907e-05, "epoch": 0.1112284744894693, "percentage": 8.69, "elapsed_time": "1:59:12", "remaining_time": "20:52:55", "throughput": 667.69, "total_tokens": 4775456} {"current_steps": 3480, "total_steps": 40000, "loss": 0.9449, "lr": 4.907254059268681e-05, "epoch": 0.11138851545995775, "percentage": 8.7, "elapsed_time": "1:59:13", "remaining_time": "20:51:14", "throughput": 668.52, "total_tokens": 4782512} {"current_steps": 3485, "total_steps": 40000, "loss": 0.8111, "lr": 4.906988946422628e-05, "epoch": 0.1115485564304462, "percentage": 8.71, "elapsed_time": "1:59:15", "remaining_time": "20:49:35", "throughput": 669.31, "total_tokens": 4789376} {"current_steps": 3490, "total_steps": 40000, "loss": 0.9847, "lr": 4.9067234623886315e-05, "epoch": 0.11170859740093464, "percentage": 8.72, "elapsed_time": "1:59:17", "remaining_time": "20:47:55", "throughput": 670.12, "total_tokens": 4796336} {"current_steps": 3495, "total_steps": 40000, "loss": 0.6551, "lr": 4.9064576072076316e-05, "epoch": 0.11186863837142308, "percentage": 8.74, "elapsed_time": "1:59:19", "remaining_time": "20:46:16", "throughput": 670.92, "total_tokens": 4803168} {"current_steps": 3500, "total_steps": 40000, "loss": 0.7381, "lr": 4.906191380920628e-05, "epoch": 0.11202867934191153, "percentage": 8.75, "elapsed_time": "1:59:20", "remaining_time": "20:44:37", "throughput": 671.76, "total_tokens": 4810368} {"current_steps": 3505, "total_steps": 40000, "loss": 0.8903, "lr": 4.905924783568675e-05, "epoch": 0.11218872031239997, "percentage": 8.76, "elapsed_time": "1:59:22", "remaining_time": "20:42:58", "throughput": 672.62, "total_tokens": 4817712} {"current_steps": 3510, "total_steps": 40000, "loss": 0.8179, "lr": 4.905657815192886e-05, "epoch": 0.11234876128288843, "percentage": 8.77, "elapsed_time": "1:59:24", "remaining_time": "20:41:20", "throughput": 673.43, "total_tokens": 4824640} {"current_steps": 3515, "total_steps": 40000, "loss": 1.0275, "lr": 4.90539047583443e-05, "epoch": 0.11250880225337687, "percentage": 8.79, "elapsed_time": "1:59:26", "remaining_time": "20:39:42", "throughput": 674.22, "total_tokens": 4831520} {"current_steps": 3520, "total_steps": 40000, "loss": 0.9896, "lr": 4.905122765534534e-05, "epoch": 0.1126688432238653, "percentage": 8.8, "elapsed_time": "1:59:27", "remaining_time": "20:38:04", "throughput": 674.97, "total_tokens": 4838064} {"current_steps": 3525, "total_steps": 40000, "loss": 1.1795, "lr": 4.9048546843344846e-05, "epoch": 0.11282888419435376, "percentage": 8.81, "elapsed_time": "1:59:29", "remaining_time": "20:36:26", "throughput": 675.89, "total_tokens": 4845824} {"current_steps": 3530, "total_steps": 40000, "loss": 0.6702, "lr": 4.9045862322756206e-05, "epoch": 0.1129889251648422, "percentage": 8.82, "elapsed_time": "1:59:31", "remaining_time": "20:34:49", "throughput": 676.69, "total_tokens": 4852768} {"current_steps": 3535, "total_steps": 40000, "loss": 0.7645, "lr": 4.904317409399342e-05, "epoch": 0.11314896613533064, "percentage": 8.84, "elapsed_time": "1:59:33", "remaining_time": "20:33:12", "throughput": 677.5, "total_tokens": 4859728} {"current_steps": 3540, "total_steps": 40000, "loss": 0.7791, "lr": 4.904048215747104e-05, "epoch": 0.11330900710581909, "percentage": 8.85, "elapsed_time": "1:59:34", "remaining_time": "20:31:35", "throughput": 678.25, "total_tokens": 4866256} {"current_steps": 3545, "total_steps": 40000, "loss": 1.3028, "lr": 4.90377865136042e-05, "epoch": 0.11346904807630753, "percentage": 8.86, "elapsed_time": "1:59:36", "remaining_time": "20:30:02", "throughput": 679.49, "total_tokens": 4876560} {"current_steps": 3550, "total_steps": 40000, "loss": 0.7118, "lr": 4.90350871628086e-05, "epoch": 0.11362908904679599, "percentage": 8.88, "elapsed_time": "1:59:38", "remaining_time": "20:28:26", "throughput": 680.25, "total_tokens": 4883216} {"current_steps": 3555, "total_steps": 40000, "loss": 0.7357, "lr": 4.903238410550052e-05, "epoch": 0.11378913001728443, "percentage": 8.89, "elapsed_time": "1:59:40", "remaining_time": "20:26:50", "throughput": 681.07, "total_tokens": 4890224} {"current_steps": 3560, "total_steps": 40000, "loss": 0.8895, "lr": 4.90296773420968e-05, "epoch": 0.11394917098777287, "percentage": 8.9, "elapsed_time": "1:59:41", "remaining_time": "20:25:14", "throughput": 681.84, "total_tokens": 4896944} {"current_steps": 3565, "total_steps": 40000, "loss": 0.9929, "lr": 4.902696687301486e-05, "epoch": 0.11410921195826132, "percentage": 8.91, "elapsed_time": "1:59:43", "remaining_time": "20:23:39", "throughput": 682.64, "total_tokens": 4903920} {"current_steps": 3570, "total_steps": 40000, "loss": 0.9503, "lr": 4.902425269867268e-05, "epoch": 0.11426925292874976, "percentage": 8.92, "elapsed_time": "1:59:45", "remaining_time": "20:22:04", "throughput": 683.4, "total_tokens": 4910560} {"current_steps": 3575, "total_steps": 40000, "loss": 0.7131, "lr": 4.902153481948883e-05, "epoch": 0.1144292938992382, "percentage": 8.94, "elapsed_time": "1:59:47", "remaining_time": "20:20:29", "throughput": 684.17, "total_tokens": 4917296} {"current_steps": 3580, "total_steps": 40000, "loss": 0.7431, "lr": 4.901881323588244e-05, "epoch": 0.11458933486972665, "percentage": 8.95, "elapsed_time": "1:59:48", "remaining_time": "20:18:54", "throughput": 684.93, "total_tokens": 4923920} {"current_steps": 3585, "total_steps": 40000, "loss": 0.95, "lr": 4.90160879482732e-05, "epoch": 0.11474937584021509, "percentage": 8.96, "elapsed_time": "1:59:50", "remaining_time": "20:17:19", "throughput": 685.7, "total_tokens": 4930672} {"current_steps": 3590, "total_steps": 40000, "loss": 0.7724, "lr": 4.9013358957081405e-05, "epoch": 0.11490941681070355, "percentage": 8.97, "elapsed_time": "1:59:52", "remaining_time": "20:15:45", "throughput": 686.49, "total_tokens": 4937536} {"current_steps": 3595, "total_steps": 40000, "loss": 0.8166, "lr": 4.901062626272789e-05, "epoch": 0.11506945778119199, "percentage": 8.99, "elapsed_time": "1:59:54", "remaining_time": "20:14:11", "throughput": 687.25, "total_tokens": 4944144} {"current_steps": 3600, "total_steps": 40000, "loss": 0.8053, "lr": 4.900788986563406e-05, "epoch": 0.11522949875168043, "percentage": 9.0, "elapsed_time": "1:59:55", "remaining_time": "20:12:38", "throughput": 688.01, "total_tokens": 4950800} {"current_steps": 3600, "total_steps": 40000, "eval_loss": 0.8916367292404175, "epoch": 0.11522949875168043, "percentage": 9.0, "elapsed_time": "2:05:43", "remaining_time": "21:11:12", "throughput": 656.31, "total_tokens": 4950800} {"current_steps": 3605, "total_steps": 40000, "loss": 0.7725, "lr": 4.9005149766221915e-05, "epoch": 0.11538953972216888, "percentage": 9.01, "elapsed_time": "2:05:46", "remaining_time": "21:09:50", "throughput": 656.95, "total_tokens": 4957856} {"current_steps": 3610, "total_steps": 40000, "loss": 0.7755, "lr": 4.9002405964914e-05, "epoch": 0.11554958069265732, "percentage": 9.03, "elapsed_time": "2:05:48", "remaining_time": "21:08:12", "throughput": 657.76, "total_tokens": 4965168} {"current_steps": 3615, "total_steps": 40000, "loss": 0.6717, "lr": 4.899965846213346e-05, "epoch": 0.11570962166314576, "percentage": 9.04, "elapsed_time": "2:05:50", "remaining_time": "21:06:33", "throughput": 658.51, "total_tokens": 4971968} {"current_steps": 3620, "total_steps": 40000, "loss": 1.0066, "lr": 4.899690725830399e-05, "epoch": 0.11586966263363421, "percentage": 9.05, "elapsed_time": "2:05:52", "remaining_time": "21:04:55", "throughput": 659.31, "total_tokens": 4979104} {"current_steps": 3625, "total_steps": 40000, "loss": 0.5667, "lr": 4.899415235384985e-05, "epoch": 0.11602970360412265, "percentage": 9.06, "elapsed_time": "2:05:53", "remaining_time": "21:03:18", "throughput": 660.09, "total_tokens": 4986144} {"current_steps": 3630, "total_steps": 40000, "loss": 0.6283, "lr": 4.899139374919589e-05, "epoch": 0.1161897445746111, "percentage": 9.07, "elapsed_time": "2:05:55", "remaining_time": "21:01:40", "throughput": 660.81, "total_tokens": 4992752} {"current_steps": 3635, "total_steps": 40000, "loss": 0.8048, "lr": 4.898863144476752e-05, "epoch": 0.11634978554509955, "percentage": 9.09, "elapsed_time": "2:05:57", "remaining_time": "21:00:03", "throughput": 661.64, "total_tokens": 5000144} {"current_steps": 3640, "total_steps": 40000, "loss": 0.8228, "lr": 4.898586544099072e-05, "epoch": 0.11650982651558799, "percentage": 9.1, "elapsed_time": "2:05:58", "remaining_time": "20:58:26", "throughput": 662.39, "total_tokens": 5006992} {"current_steps": 3645, "total_steps": 40000, "loss": 0.8403, "lr": 4.898309573829204e-05, "epoch": 0.11666986748607644, "percentage": 9.11, "elapsed_time": "2:06:00", "remaining_time": "20:56:50", "throughput": 663.12, "total_tokens": 5013696} {"current_steps": 3650, "total_steps": 40000, "loss": 0.842, "lr": 4.898032233709862e-05, "epoch": 0.11682990845656488, "percentage": 9.12, "elapsed_time": "2:06:02", "remaining_time": "20:55:13", "throughput": 663.93, "total_tokens": 5020912} {"current_steps": 3655, "total_steps": 40000, "loss": 0.8412, "lr": 4.8977545237838123e-05, "epoch": 0.11698994942705332, "percentage": 9.14, "elapsed_time": "2:06:04", "remaining_time": "20:53:37", "throughput": 664.64, "total_tokens": 5027488} {"current_steps": 3660, "total_steps": 40000, "loss": 0.8129, "lr": 4.8974764440938836e-05, "epoch": 0.11714999039754177, "percentage": 9.15, "elapsed_time": "2:06:05", "remaining_time": "20:52:01", "throughput": 665.37, "total_tokens": 5034160} {"current_steps": 3665, "total_steps": 40000, "loss": 0.8181, "lr": 4.897197994682959e-05, "epoch": 0.11731003136803021, "percentage": 9.16, "elapsed_time": "2:06:07", "remaining_time": "20:50:26", "throughput": 666.15, "total_tokens": 5041168} {"current_steps": 3670, "total_steps": 40000, "loss": 0.6965, "lr": 4.8969191755939786e-05, "epoch": 0.11747007233851867, "percentage": 9.18, "elapsed_time": "2:06:09", "remaining_time": "20:48:50", "throughput": 666.95, "total_tokens": 5048432} {"current_steps": 3675, "total_steps": 40000, "loss": 0.9113, "lr": 4.8966399868699396e-05, "epoch": 0.1176301133090071, "percentage": 9.19, "elapsed_time": "2:06:11", "remaining_time": "20:47:15", "throughput": 667.74, "total_tokens": 5055552} {"current_steps": 3680, "total_steps": 40000, "loss": 0.7002, "lr": 4.8963604285538965e-05, "epoch": 0.11779015427949555, "percentage": 9.2, "elapsed_time": "2:06:12", "remaining_time": "20:45:41", "throughput": 668.53, "total_tokens": 5062704} {"current_steps": 3685, "total_steps": 40000, "loss": 0.7378, "lr": 4.8960805006889604e-05, "epoch": 0.117950195249984, "percentage": 9.21, "elapsed_time": "2:06:14", "remaining_time": "20:44:06", "throughput": 669.41, "total_tokens": 5070528} {"current_steps": 3690, "total_steps": 40000, "loss": 0.759, "lr": 4.8958002033183004e-05, "epoch": 0.11811023622047244, "percentage": 9.22, "elapsed_time": "2:06:16", "remaining_time": "20:42:32", "throughput": 670.18, "total_tokens": 5077552} {"current_steps": 3695, "total_steps": 40000, "loss": 0.9307, "lr": 4.8955195364851414e-05, "epoch": 0.11827027719096088, "percentage": 9.24, "elapsed_time": "2:06:18", "remaining_time": "20:40:58", "throughput": 670.98, "total_tokens": 5084768} {"current_steps": 3700, "total_steps": 40000, "loss": 0.8179, "lr": 4.895238500232766e-05, "epoch": 0.11843031816144933, "percentage": 9.25, "elapsed_time": "2:06:19", "remaining_time": "20:39:24", "throughput": 671.72, "total_tokens": 5091536} {"current_steps": 3705, "total_steps": 40000, "loss": 0.8827, "lr": 4.8949570946045143e-05, "epoch": 0.11859035913193777, "percentage": 9.26, "elapsed_time": "2:06:21", "remaining_time": "20:37:50", "throughput": 672.44, "total_tokens": 5098112} {"current_steps": 3710, "total_steps": 40000, "loss": 0.7308, "lr": 4.89467531964378e-05, "epoch": 0.11875040010242623, "percentage": 9.28, "elapsed_time": "2:06:23", "remaining_time": "20:36:17", "throughput": 673.13, "total_tokens": 5104528} {"current_steps": 3715, "total_steps": 40000, "loss": 0.8074, "lr": 4.894393175394019e-05, "epoch": 0.11891044107291467, "percentage": 9.29, "elapsed_time": "2:06:25", "remaining_time": "20:34:44", "throughput": 673.9, "total_tokens": 5111568} {"current_steps": 3720, "total_steps": 40000, "loss": 0.7544, "lr": 4.8941106618987406e-05, "epoch": 0.1190704820434031, "percentage": 9.3, "elapsed_time": "2:06:26", "remaining_time": "20:33:11", "throughput": 674.64, "total_tokens": 5118336} {"current_steps": 3725, "total_steps": 40000, "loss": 0.9505, "lr": 4.893827779201512e-05, "epoch": 0.11923052301389156, "percentage": 9.31, "elapsed_time": "2:06:28", "remaining_time": "20:31:38", "throughput": 675.42, "total_tokens": 5125392} {"current_steps": 3730, "total_steps": 40000, "loss": 0.8345, "lr": 4.893544527345957e-05, "epoch": 0.11939056398438, "percentage": 9.32, "elapsed_time": "2:06:30", "remaining_time": "20:30:06", "throughput": 676.12, "total_tokens": 5131920} {"current_steps": 3735, "total_steps": 40000, "loss": 0.7901, "lr": 4.8932609063757563e-05, "epoch": 0.11955060495486845, "percentage": 9.34, "elapsed_time": "2:06:31", "remaining_time": "20:28:34", "throughput": 676.88, "total_tokens": 5138880} {"current_steps": 3740, "total_steps": 40000, "loss": 0.8062, "lr": 4.8929769163346484e-05, "epoch": 0.11971064592535689, "percentage": 9.35, "elapsed_time": "2:06:33", "remaining_time": "20:27:02", "throughput": 677.64, "total_tokens": 5145808} {"current_steps": 3745, "total_steps": 40000, "loss": 0.7704, "lr": 4.892692557266429e-05, "epoch": 0.11987068689584533, "percentage": 9.36, "elapsed_time": "2:06:35", "remaining_time": "20:25:30", "throughput": 678.39, "total_tokens": 5152672} {"current_steps": 3750, "total_steps": 40000, "loss": 0.9338, "lr": 4.8924078292149464e-05, "epoch": 0.12003072786633379, "percentage": 9.38, "elapsed_time": "2:06:37", "remaining_time": "20:23:59", "throughput": 679.18, "total_tokens": 5159824} {"current_steps": 3755, "total_steps": 40000, "loss": 1.0256, "lr": 4.892122732224114e-05, "epoch": 0.12019076883682223, "percentage": 9.39, "elapsed_time": "2:06:38", "remaining_time": "20:22:28", "throughput": 679.93, "total_tokens": 5166752} {"current_steps": 3760, "total_steps": 40000, "loss": 0.9671, "lr": 4.8918372663378944e-05, "epoch": 0.12035080980731067, "percentage": 9.4, "elapsed_time": "2:06:40", "remaining_time": "20:20:57", "throughput": 680.7, "total_tokens": 5173744} {"current_steps": 3765, "total_steps": 40000, "loss": 0.8658, "lr": 4.89155143160031e-05, "epoch": 0.12051085077779912, "percentage": 9.41, "elapsed_time": "2:06:42", "remaining_time": "20:19:26", "throughput": 681.5, "total_tokens": 5181040} {"current_steps": 3770, "total_steps": 40000, "loss": 0.7242, "lr": 4.891265228055441e-05, "epoch": 0.12067089174828756, "percentage": 9.43, "elapsed_time": "2:06:44", "remaining_time": "20:17:56", "throughput": 682.21, "total_tokens": 5187584} {"current_steps": 3775, "total_steps": 40000, "loss": 0.7682, "lr": 4.890978655747424e-05, "epoch": 0.12083093271877601, "percentage": 9.44, "elapsed_time": "2:06:45", "remaining_time": "20:16:26", "throughput": 682.97, "total_tokens": 5194544} {"current_steps": 3780, "total_steps": 40000, "loss": 0.8335, "lr": 4.89069171472045e-05, "epoch": 0.12099097368926445, "percentage": 9.45, "elapsed_time": "2:06:47", "remaining_time": "20:14:56", "throughput": 683.71, "total_tokens": 5201408} {"current_steps": 3785, "total_steps": 40000, "loss": 0.8728, "lr": 4.890404405018772e-05, "epoch": 0.12115101465975289, "percentage": 9.46, "elapsed_time": "2:06:49", "remaining_time": "20:13:26", "throughput": 684.43, "total_tokens": 5208064} {"current_steps": 3790, "total_steps": 40000, "loss": 0.6685, "lr": 4.8901167266866934e-05, "epoch": 0.12131105563024135, "percentage": 9.47, "elapsed_time": "2:06:51", "remaining_time": "20:11:56", "throughput": 685.15, "total_tokens": 5214752} {"current_steps": 3795, "total_steps": 40000, "loss": 0.8474, "lr": 4.88982867976858e-05, "epoch": 0.12147109660072979, "percentage": 9.49, "elapsed_time": "2:06:52", "remaining_time": "20:10:27", "throughput": 685.89, "total_tokens": 5221536} {"current_steps": 3800, "total_steps": 40000, "loss": 0.9251, "lr": 4.889540264308852e-05, "epoch": 0.12163113757121823, "percentage": 9.5, "elapsed_time": "2:06:54", "remaining_time": "20:08:58", "throughput": 686.65, "total_tokens": 5228512} {"current_steps": 3800, "total_steps": 40000, "eval_loss": 0.8845858573913574, "epoch": 0.12163113757121823, "percentage": 9.5, "elapsed_time": "2:12:42", "remaining_time": "21:04:12", "throughput": 656.65, "total_tokens": 5228512} {"current_steps": 3805, "total_steps": 40000, "loss": 0.8965, "lr": 4.889251480351986e-05, "epoch": 0.12179117854170668, "percentage": 9.51, "elapsed_time": "2:12:46", "remaining_time": "21:02:56", "throughput": 657.21, "total_tokens": 5235344} {"current_steps": 3810, "total_steps": 40000, "loss": 0.8052, "lr": 4.888962327942517e-05, "epoch": 0.12195121951219512, "percentage": 9.53, "elapsed_time": "2:12:47", "remaining_time": "21:01:23", "throughput": 657.92, "total_tokens": 5242176} {"current_steps": 3815, "total_steps": 40000, "loss": 0.9975, "lr": 4.8886728071250356e-05, "epoch": 0.12211126048268357, "percentage": 9.54, "elapsed_time": "2:12:49", "remaining_time": "20:59:50", "throughput": 658.64, "total_tokens": 5248992} {"current_steps": 3820, "total_steps": 40000, "loss": 0.9224, "lr": 4.8883829179441884e-05, "epoch": 0.12227130145317201, "percentage": 9.55, "elapsed_time": "2:12:51", "remaining_time": "20:58:17", "throughput": 659.38, "total_tokens": 5256080} {"current_steps": 3825, "total_steps": 40000, "loss": 0.9228, "lr": 4.888092660444682e-05, "epoch": 0.12243134242366045, "percentage": 9.56, "elapsed_time": "2:12:52", "remaining_time": "20:56:44", "throughput": 660.07, "total_tokens": 5262688} {"current_steps": 3830, "total_steps": 40000, "loss": 0.7779, "lr": 4.887802034671276e-05, "epoch": 0.1225913833941489, "percentage": 9.57, "elapsed_time": "2:12:54", "remaining_time": "20:55:12", "throughput": 660.79, "total_tokens": 5269616} {"current_steps": 3835, "total_steps": 40000, "loss": 0.8161, "lr": 4.88751104066879e-05, "epoch": 0.12275142436463735, "percentage": 9.59, "elapsed_time": "2:12:56", "remaining_time": "20:53:39", "throughput": 661.61, "total_tokens": 5277264} {"current_steps": 3840, "total_steps": 40000, "loss": 1.1299, "lr": 4.887219678482098e-05, "epoch": 0.12291146533512579, "percentage": 9.6, "elapsed_time": "2:12:58", "remaining_time": "20:52:07", "throughput": 662.3, "total_tokens": 5283952} {"current_steps": 3845, "total_steps": 40000, "loss": 0.7445, "lr": 4.8869279481561316e-05, "epoch": 0.12307150630561424, "percentage": 9.61, "elapsed_time": "2:12:59", "remaining_time": "20:50:36", "throughput": 663.03, "total_tokens": 5290928} {"current_steps": 3850, "total_steps": 40000, "loss": 1.0298, "lr": 4.88663584973588e-05, "epoch": 0.12323154727610268, "percentage": 9.62, "elapsed_time": "2:13:01", "remaining_time": "20:49:04", "throughput": 663.72, "total_tokens": 5297584} {"current_steps": 3855, "total_steps": 40000, "loss": 0.7825, "lr": 4.8863433832663874e-05, "epoch": 0.12339158824659113, "percentage": 9.64, "elapsed_time": "2:13:03", "remaining_time": "20:47:33", "throughput": 664.41, "total_tokens": 5304208} {"current_steps": 3860, "total_steps": 40000, "loss": 0.9372, "lr": 4.886050548792757e-05, "epoch": 0.12355162921707957, "percentage": 9.65, "elapsed_time": "2:13:05", "remaining_time": "20:46:02", "throughput": 665.1, "total_tokens": 5310880} {"current_steps": 3865, "total_steps": 40000, "loss": 0.6366, "lr": 4.8857573463601465e-05, "epoch": 0.12371167018756801, "percentage": 9.66, "elapsed_time": "2:13:06", "remaining_time": "20:44:31", "throughput": 665.79, "total_tokens": 5317600} {"current_steps": 3870, "total_steps": 40000, "loss": 0.8951, "lr": 4.885463776013772e-05, "epoch": 0.12387171115805647, "percentage": 9.68, "elapsed_time": "2:13:08", "remaining_time": "20:43:00", "throughput": 666.55, "total_tokens": 5324800} {"current_steps": 3875, "total_steps": 40000, "loss": 0.8476, "lr": 4.8851698377989056e-05, "epoch": 0.1240317521285449, "percentage": 9.69, "elapsed_time": "2:13:10", "remaining_time": "20:41:30", "throughput": 667.24, "total_tokens": 5331472} {"current_steps": 3880, "total_steps": 40000, "loss": 0.6941, "lr": 4.884875531760876e-05, "epoch": 0.12419179309903335, "percentage": 9.7, "elapsed_time": "2:13:12", "remaining_time": "20:40:00", "throughput": 667.88, "total_tokens": 5337744} {"current_steps": 3885, "total_steps": 40000, "loss": 0.687, "lr": 4.88458085794507e-05, "epoch": 0.1243518340695218, "percentage": 9.71, "elapsed_time": "2:13:13", "remaining_time": "20:38:30", "throughput": 668.59, "total_tokens": 5344624} {"current_steps": 3890, "total_steps": 40000, "loss": 0.9308, "lr": 4.884285816396929e-05, "epoch": 0.12451187504001024, "percentage": 9.72, "elapsed_time": "2:13:15", "remaining_time": "20:37:01", "throughput": 669.3, "total_tokens": 5351472} {"current_steps": 3895, "total_steps": 40000, "loss": 0.8448, "lr": 4.8839904071619526e-05, "epoch": 0.12467191601049869, "percentage": 9.74, "elapsed_time": "2:13:17", "remaining_time": "20:35:31", "throughput": 670.03, "total_tokens": 5358400} {"current_steps": 3900, "total_steps": 40000, "loss": 0.9308, "lr": 4.8836946302856955e-05, "epoch": 0.12483195698098713, "percentage": 9.75, "elapsed_time": "2:13:19", "remaining_time": "20:34:02", "throughput": 670.76, "total_tokens": 5365472} {"current_steps": 3905, "total_steps": 40000, "loss": 0.8008, "lr": 4.8833984858137715e-05, "epoch": 0.12499199795147557, "percentage": 9.76, "elapsed_time": "2:13:20", "remaining_time": "20:32:33", "throughput": 671.49, "total_tokens": 5372464} {"current_steps": 3910, "total_steps": 40000, "loss": 0.7473, "lr": 4.8831019737918494e-05, "epoch": 0.12515203892196403, "percentage": 9.78, "elapsed_time": "2:13:22", "remaining_time": "20:31:04", "throughput": 672.27, "total_tokens": 5379840} {"current_steps": 3915, "total_steps": 40000, "loss": 0.8134, "lr": 4.882805094265655e-05, "epoch": 0.12531207989245247, "percentage": 9.79, "elapsed_time": "2:13:24", "remaining_time": "20:29:36", "throughput": 673.01, "total_tokens": 5386976} {"current_steps": 3920, "total_steps": 40000, "loss": 1.2527, "lr": 4.8825078472809706e-05, "epoch": 0.1254721208629409, "percentage": 9.8, "elapsed_time": "2:13:25", "remaining_time": "20:28:07", "throughput": 673.71, "total_tokens": 5393712} {"current_steps": 3925, "total_steps": 40000, "loss": 0.7978, "lr": 4.882210232883635e-05, "epoch": 0.12563216183342935, "percentage": 9.81, "elapsed_time": "2:13:27", "remaining_time": "20:26:39", "throughput": 674.41, "total_tokens": 5400528} {"current_steps": 3930, "total_steps": 40000, "loss": 0.828, "lr": 4.881912251119546e-05, "epoch": 0.1257922028039178, "percentage": 9.83, "elapsed_time": "2:13:29", "remaining_time": "20:25:11", "throughput": 675.1, "total_tokens": 5407216} {"current_steps": 3935, "total_steps": 40000, "loss": 0.889, "lr": 4.881613902034654e-05, "epoch": 0.12595224377440625, "percentage": 9.84, "elapsed_time": "2:13:31", "remaining_time": "20:23:44", "throughput": 675.85, "total_tokens": 5414368} {"current_steps": 3940, "total_steps": 40000, "loss": 0.7245, "lr": 4.88131518567497e-05, "epoch": 0.1261122847448947, "percentage": 9.85, "elapsed_time": "2:13:32", "remaining_time": "20:22:16", "throughput": 676.59, "total_tokens": 5421504} {"current_steps": 3945, "total_steps": 40000, "loss": 0.8327, "lr": 4.881016102086558e-05, "epoch": 0.12627232571538313, "percentage": 9.86, "elapsed_time": "2:13:34", "remaining_time": "20:20:49", "throughput": 677.26, "total_tokens": 5428016} {"current_steps": 3950, "total_steps": 40000, "loss": 1.1151, "lr": 4.8807166513155425e-05, "epoch": 0.12643236668587157, "percentage": 9.88, "elapsed_time": "2:13:36", "remaining_time": "20:19:22", "throughput": 678.04, "total_tokens": 5435440} {"current_steps": 3955, "total_steps": 40000, "loss": 0.9986, "lr": 4.8804168334081004e-05, "epoch": 0.12659240765636004, "percentage": 9.89, "elapsed_time": "2:13:38", "remaining_time": "20:17:55", "throughput": 678.76, "total_tokens": 5442384} {"current_steps": 3960, "total_steps": 40000, "loss": 1.0531, "lr": 4.880116648410468e-05, "epoch": 0.12675244862684848, "percentage": 9.9, "elapsed_time": "2:13:39", "remaining_time": "20:16:29", "throughput": 679.46, "total_tokens": 5449200} {"current_steps": 3965, "total_steps": 40000, "loss": 0.7538, "lr": 4.879816096368939e-05, "epoch": 0.12691248959733692, "percentage": 9.91, "elapsed_time": "2:13:41", "remaining_time": "20:15:02", "throughput": 680.17, "total_tokens": 5456064} {"current_steps": 3970, "total_steps": 40000, "loss": 0.9162, "lr": 4.879515177329861e-05, "epoch": 0.12707253056782536, "percentage": 9.93, "elapsed_time": "2:13:43", "remaining_time": "20:13:36", "throughput": 680.91, "total_tokens": 5463200} {"current_steps": 3975, "total_steps": 40000, "loss": 0.8534, "lr": 4.8792138913396394e-05, "epoch": 0.1272325715383138, "percentage": 9.94, "elapsed_time": "2:13:45", "remaining_time": "20:12:10", "throughput": 681.65, "total_tokens": 5470304} {"current_steps": 3980, "total_steps": 40000, "loss": 0.7387, "lr": 4.8789122384447374e-05, "epoch": 0.12739261250880227, "percentage": 9.95, "elapsed_time": "2:13:46", "remaining_time": "20:10:45", "throughput": 682.35, "total_tokens": 5477152} {"current_steps": 3985, "total_steps": 40000, "loss": 0.7187, "lr": 4.878610218691673e-05, "epoch": 0.1275526534792907, "percentage": 9.96, "elapsed_time": "2:13:48", "remaining_time": "20:09:19", "throughput": 683.06, "total_tokens": 5483984} {"current_steps": 3990, "total_steps": 40000, "loss": 0.8574, "lr": 4.87830783212702e-05, "epoch": 0.12771269444977915, "percentage": 9.98, "elapsed_time": "2:13:50", "remaining_time": "20:07:54", "throughput": 683.79, "total_tokens": 5491024} {"current_steps": 3995, "total_steps": 40000, "loss": 0.8151, "lr": 4.878005078797413e-05, "epoch": 0.12787273542026759, "percentage": 9.99, "elapsed_time": "2:13:52", "remaining_time": "20:06:29", "throughput": 684.5, "total_tokens": 5497968} {"current_steps": 4000, "total_steps": 40000, "loss": 0.845, "lr": 4.877701958749539e-05, "epoch": 0.12803277639075603, "percentage": 10.0, "elapsed_time": "2:13:53", "remaining_time": "20:05:04", "throughput": 685.18, "total_tokens": 5504608} {"current_steps": 4000, "total_steps": 40000, "eval_loss": 0.8784042000770569, "epoch": 0.12803277639075603, "percentage": 10.0, "elapsed_time": "2:19:42", "remaining_time": "20:57:20", "throughput": 656.69, "total_tokens": 5504608} {"current_steps": 4005, "total_steps": 40000, "loss": 0.8079, "lr": 4.877398472030142e-05, "epoch": 0.12819281736124447, "percentage": 10.01, "elapsed_time": "2:19:45", "remaining_time": "20:56:06", "throughput": 657.25, "total_tokens": 5511520} {"current_steps": 4010, "total_steps": 40000, "loss": 0.9785, "lr": 4.877094618686024e-05, "epoch": 0.12835285833173293, "percentage": 10.03, "elapsed_time": "2:19:47", "remaining_time": "20:54:38", "throughput": 657.9, "total_tokens": 5518112} {"current_steps": 4015, "total_steps": 40000, "loss": 0.7926, "lr": 4.876790398764045e-05, "epoch": 0.12851289930222137, "percentage": 10.04, "elapsed_time": "2:19:49", "remaining_time": "20:53:09", "throughput": 658.55, "total_tokens": 5524720} {"current_steps": 4020, "total_steps": 40000, "loss": 0.7666, "lr": 4.8764858123111167e-05, "epoch": 0.1286729402727098, "percentage": 10.05, "elapsed_time": "2:19:50", "remaining_time": "20:51:40", "throughput": 659.28, "total_tokens": 5531968} {"current_steps": 4025, "total_steps": 40000, "loss": 0.8722, "lr": 4.876180859374212e-05, "epoch": 0.12883298124319825, "percentage": 10.06, "elapsed_time": "2:19:52", "remaining_time": "20:50:12", "throughput": 659.93, "total_tokens": 5538544} {"current_steps": 4030, "total_steps": 40000, "loss": 1.0191, "lr": 4.875875540000357e-05, "epoch": 0.1289930222136867, "percentage": 10.08, "elapsed_time": "2:19:54", "remaining_time": "20:48:44", "throughput": 660.6, "total_tokens": 5545328} {"current_steps": 4035, "total_steps": 40000, "loss": 0.997, "lr": 4.8755698542366376e-05, "epoch": 0.12915306318417516, "percentage": 10.09, "elapsed_time": "2:19:56", "remaining_time": "20:47:16", "throughput": 661.25, "total_tokens": 5551936} {"current_steps": 4040, "total_steps": 40000, "loss": 1.1144, "lr": 4.875263802130193e-05, "epoch": 0.1293131041546636, "percentage": 10.1, "elapsed_time": "2:19:57", "remaining_time": "20:45:49", "throughput": 661.86, "total_tokens": 5558224} {"current_steps": 4045, "total_steps": 40000, "loss": 0.6703, "lr": 4.8749573837282207e-05, "epoch": 0.12947314512515204, "percentage": 10.11, "elapsed_time": "2:19:59", "remaining_time": "20:44:22", "throughput": 662.51, "total_tokens": 5564832} {"current_steps": 4050, "total_steps": 40000, "loss": 0.8639, "lr": 4.874650599077974e-05, "epoch": 0.12963318609564048, "percentage": 10.12, "elapsed_time": "2:20:01", "remaining_time": "20:42:54", "throughput": 663.12, "total_tokens": 5571120} {"current_steps": 4055, "total_steps": 40000, "loss": 0.8918, "lr": 4.874343448226764e-05, "epoch": 0.12979322706612892, "percentage": 10.14, "elapsed_time": "2:20:03", "remaining_time": "20:41:27", "throughput": 663.81, "total_tokens": 5578032} {"current_steps": 4060, "total_steps": 40000, "loss": 0.7083, "lr": 4.874035931221955e-05, "epoch": 0.1299532680366174, "percentage": 10.15, "elapsed_time": "2:20:04", "remaining_time": "20:40:01", "throughput": 664.45, "total_tokens": 5584576} {"current_steps": 4065, "total_steps": 40000, "loss": 0.6888, "lr": 4.8737280481109724e-05, "epoch": 0.13011330900710583, "percentage": 10.16, "elapsed_time": "2:20:06", "remaining_time": "20:38:34", "throughput": 665.18, "total_tokens": 5591872} {"current_steps": 4070, "total_steps": 40000, "loss": 0.9813, "lr": 4.873419798941294e-05, "epoch": 0.13027334997759427, "percentage": 10.17, "elapsed_time": "2:20:08", "remaining_time": "20:37:08", "throughput": 665.82, "total_tokens": 5598416} {"current_steps": 4075, "total_steps": 40000, "loss": 0.8623, "lr": 4.873111183760458e-05, "epoch": 0.1304333909480827, "percentage": 10.19, "elapsed_time": "2:20:10", "remaining_time": "20:35:42", "throughput": 666.54, "total_tokens": 5605600} {"current_steps": 4080, "total_steps": 40000, "loss": 0.9068, "lr": 4.8728022026160537e-05, "epoch": 0.13059343191857115, "percentage": 10.2, "elapsed_time": "2:20:11", "remaining_time": "20:34:16", "throughput": 667.19, "total_tokens": 5612272} {"current_steps": 4085, "total_steps": 40000, "loss": 0.7387, "lr": 4.872492855555732e-05, "epoch": 0.13075347288905959, "percentage": 10.21, "elapsed_time": "2:20:13", "remaining_time": "20:32:50", "throughput": 667.83, "total_tokens": 5618800} {"current_steps": 4090, "total_steps": 40000, "loss": 0.7618, "lr": 4.8721831426271956e-05, "epoch": 0.13091351385954805, "percentage": 10.22, "elapsed_time": "2:20:15", "remaining_time": "20:31:25", "throughput": 668.51, "total_tokens": 5625664} {"current_steps": 4095, "total_steps": 40000, "loss": 0.7235, "lr": 4.87187306387821e-05, "epoch": 0.1310735548300365, "percentage": 10.24, "elapsed_time": "2:20:16", "remaining_time": "20:30:00", "throughput": 669.19, "total_tokens": 5632560} {"current_steps": 4100, "total_steps": 40000, "loss": 0.9428, "lr": 4.87156261935659e-05, "epoch": 0.13123359580052493, "percentage": 10.25, "elapsed_time": "2:20:18", "remaining_time": "20:28:34", "throughput": 669.9, "total_tokens": 5639696} {"current_steps": 4105, "total_steps": 40000, "loss": 0.8804, "lr": 4.871251809110211e-05, "epoch": 0.13139363677101337, "percentage": 10.26, "elapsed_time": "2:20:20", "remaining_time": "20:27:10", "throughput": 670.54, "total_tokens": 5646208} {"current_steps": 4110, "total_steps": 40000, "loss": 0.8157, "lr": 4.8709406331870044e-05, "epoch": 0.1315536777415018, "percentage": 10.27, "elapsed_time": "2:20:22", "remaining_time": "20:25:45", "throughput": 671.24, "total_tokens": 5653312} {"current_steps": 4115, "total_steps": 40000, "loss": 0.6156, "lr": 4.8706290916349574e-05, "epoch": 0.13171371871199028, "percentage": 10.29, "elapsed_time": "2:20:23", "remaining_time": "20:24:20", "throughput": 671.88, "total_tokens": 5659888} {"current_steps": 4120, "total_steps": 40000, "loss": 0.9026, "lr": 4.8703171845021134e-05, "epoch": 0.13187375968247872, "percentage": 10.3, "elapsed_time": "2:20:25", "remaining_time": "20:22:56", "throughput": 672.54, "total_tokens": 5666592} {"current_steps": 4125, "total_steps": 40000, "loss": 1.0574, "lr": 4.870004911836572e-05, "epoch": 0.13203380065296716, "percentage": 10.31, "elapsed_time": "2:20:27", "remaining_time": "20:21:32", "throughput": 673.25, "total_tokens": 5673728} {"current_steps": 4130, "total_steps": 40000, "loss": 0.738, "lr": 4.869692273686489e-05, "epoch": 0.1321938416234556, "percentage": 10.32, "elapsed_time": "2:20:29", "remaining_time": "20:20:08", "throughput": 673.93, "total_tokens": 5680656} {"current_steps": 4135, "total_steps": 40000, "loss": 0.7531, "lr": 4.869379270100079e-05, "epoch": 0.13235388259394404, "percentage": 10.34, "elapsed_time": "2:20:30", "remaining_time": "20:18:45", "throughput": 674.66, "total_tokens": 5687920} {"current_steps": 4140, "total_steps": 40000, "loss": 0.8506, "lr": 4.86906590112561e-05, "epoch": 0.1325139235644325, "percentage": 10.35, "elapsed_time": "2:20:32", "remaining_time": "20:17:21", "throughput": 675.35, "total_tokens": 5694912} {"current_steps": 4145, "total_steps": 40000, "loss": 0.8261, "lr": 4.8687521668114064e-05, "epoch": 0.13267396453492095, "percentage": 10.36, "elapsed_time": "2:20:34", "remaining_time": "20:15:58", "throughput": 676.03, "total_tokens": 5701840} {"current_steps": 4150, "total_steps": 40000, "loss": 0.8989, "lr": 4.868438067205853e-05, "epoch": 0.13283400550540939, "percentage": 10.38, "elapsed_time": "2:20:36", "remaining_time": "20:14:35", "throughput": 676.7, "total_tokens": 5708640} {"current_steps": 4155, "total_steps": 40000, "loss": 0.7757, "lr": 4.8681236023573844e-05, "epoch": 0.13299404647589783, "percentage": 10.39, "elapsed_time": "2:20:37", "remaining_time": "20:13:12", "throughput": 677.39, "total_tokens": 5715632} {"current_steps": 4160, "total_steps": 40000, "loss": 1.043, "lr": 4.867808772314497e-05, "epoch": 0.13315408744638627, "percentage": 10.4, "elapsed_time": "2:20:39", "remaining_time": "20:11:49", "throughput": 678.02, "total_tokens": 5722176} {"current_steps": 4165, "total_steps": 40000, "loss": 0.7849, "lr": 4.867493577125741e-05, "epoch": 0.13331412841687473, "percentage": 10.41, "elapsed_time": "2:20:41", "remaining_time": "20:10:27", "throughput": 678.65, "total_tokens": 5728672} {"current_steps": 4170, "total_steps": 40000, "loss": 0.7708, "lr": 4.867178016839725e-05, "epoch": 0.13347416938736317, "percentage": 10.42, "elapsed_time": "2:20:42", "remaining_time": "20:09:04", "throughput": 679.36, "total_tokens": 5735840} {"current_steps": 4175, "total_steps": 40000, "loss": 0.655, "lr": 4.8668620915051094e-05, "epoch": 0.1336342103578516, "percentage": 10.44, "elapsed_time": "2:20:44", "remaining_time": "20:07:42", "throughput": 680.0, "total_tokens": 5742400} {"current_steps": 4180, "total_steps": 40000, "loss": 0.8023, "lr": 4.866545801170616e-05, "epoch": 0.13379425132834005, "percentage": 10.45, "elapsed_time": "2:20:46", "remaining_time": "20:06:20", "throughput": 680.67, "total_tokens": 5749264} {"current_steps": 4185, "total_steps": 40000, "loss": 0.825, "lr": 4.86622914588502e-05, "epoch": 0.1339542922988285, "percentage": 10.46, "elapsed_time": "2:20:48", "remaining_time": "20:04:59", "throughput": 681.42, "total_tokens": 5756752} {"current_steps": 4190, "total_steps": 40000, "loss": 0.7105, "lr": 4.865912125697154e-05, "epoch": 0.13411433326931693, "percentage": 10.47, "elapsed_time": "2:20:49", "remaining_time": "20:03:37", "throughput": 682.11, "total_tokens": 5763760} {"current_steps": 4195, "total_steps": 40000, "loss": 0.8922, "lr": 4.865594740655907e-05, "epoch": 0.1342743742398054, "percentage": 10.49, "elapsed_time": "2:20:51", "remaining_time": "20:02:16", "throughput": 682.81, "total_tokens": 5770880} {"current_steps": 4200, "total_steps": 40000, "loss": 0.9929, "lr": 4.865276990810222e-05, "epoch": 0.13443441521029384, "percentage": 10.5, "elapsed_time": "2:20:53", "remaining_time": "20:00:55", "throughput": 683.53, "total_tokens": 5778176} {"current_steps": 4200, "total_steps": 40000, "eval_loss": 0.8733596801757812, "epoch": 0.13443441521029384, "percentage": 10.5, "elapsed_time": "2:26:41", "remaining_time": "20:50:22", "throughput": 656.5, "total_tokens": 5778176} {"current_steps": 4205, "total_steps": 40000, "loss": 0.8782, "lr": 4.8649588762091016e-05, "epoch": 0.13459445618078228, "percentage": 10.51, "elapsed_time": "2:26:44", "remaining_time": "20:49:10", "throughput": 657.01, "total_tokens": 5784832} {"current_steps": 4210, "total_steps": 40000, "loss": 0.8492, "lr": 4.8646403969016016e-05, "epoch": 0.13475449715127072, "percentage": 10.53, "elapsed_time": "2:26:46", "remaining_time": "20:47:45", "throughput": 657.68, "total_tokens": 5791904} {"current_steps": 4215, "total_steps": 40000, "loss": 1.0597, "lr": 4.864321552936838e-05, "epoch": 0.13491453812175916, "percentage": 10.54, "elapsed_time": "2:26:48", "remaining_time": "20:46:21", "throughput": 658.3, "total_tokens": 5798512} {"current_steps": 4220, "total_steps": 40000, "loss": 0.7353, "lr": 4.864002344363978e-05, "epoch": 0.13507457909224763, "percentage": 10.55, "elapsed_time": "2:26:49", "remaining_time": "20:44:57", "throughput": 658.98, "total_tokens": 5805616} {"current_steps": 4225, "total_steps": 40000, "loss": 0.9595, "lr": 4.863682771232248e-05, "epoch": 0.13523462006273607, "percentage": 10.56, "elapsed_time": "2:26:51", "remaining_time": "20:43:32", "throughput": 659.64, "total_tokens": 5812544} {"current_steps": 4230, "total_steps": 40000, "loss": 0.7798, "lr": 4.8633628335909324e-05, "epoch": 0.1353946610332245, "percentage": 10.57, "elapsed_time": "2:26:53", "remaining_time": "20:42:09", "throughput": 660.32, "total_tokens": 5819744} {"current_steps": 4235, "total_steps": 40000, "loss": 0.7301, "lr": 4.8630425314893676e-05, "epoch": 0.13555470200371295, "percentage": 10.59, "elapsed_time": "2:26:55", "remaining_time": "20:40:45", "throughput": 661.01, "total_tokens": 5826960} {"current_steps": 4240, "total_steps": 40000, "loss": 0.9816, "lr": 4.862721864976948e-05, "epoch": 0.13571474297420139, "percentage": 10.6, "elapsed_time": "2:26:56", "remaining_time": "20:39:21", "throughput": 661.67, "total_tokens": 5833872} {"current_steps": 4245, "total_steps": 40000, "loss": 0.9218, "lr": 4.862400834103125e-05, "epoch": 0.13587478394468985, "percentage": 10.61, "elapsed_time": "2:26:58", "remaining_time": "20:37:58", "throughput": 662.34, "total_tokens": 5840944} {"current_steps": 4250, "total_steps": 40000, "loss": 1.0081, "lr": 4.862079438917406e-05, "epoch": 0.1360348249151783, "percentage": 10.62, "elapsed_time": "2:27:00", "remaining_time": "20:36:35", "throughput": 663.0, "total_tokens": 5847952} {"current_steps": 4255, "total_steps": 40000, "loss": 0.9187, "lr": 4.8617576794693536e-05, "epoch": 0.13619486588566673, "percentage": 10.64, "elapsed_time": "2:27:02", "remaining_time": "20:35:12", "throughput": 663.64, "total_tokens": 5854704} {"current_steps": 4260, "total_steps": 40000, "loss": 0.8899, "lr": 4.8614355558085875e-05, "epoch": 0.13635490685615517, "percentage": 10.65, "elapsed_time": "2:27:03", "remaining_time": "20:33:49", "throughput": 664.36, "total_tokens": 5862240} {"current_steps": 4265, "total_steps": 40000, "loss": 0.7575, "lr": 4.861113067984783e-05, "epoch": 0.1365149478266436, "percentage": 10.66, "elapsed_time": "2:27:05", "remaining_time": "20:32:26", "throughput": 664.99, "total_tokens": 5868960} {"current_steps": 4270, "total_steps": 40000, "loss": 0.9181, "lr": 4.860790216047671e-05, "epoch": 0.13667498879713205, "percentage": 10.67, "elapsed_time": "2:27:07", "remaining_time": "20:31:04", "throughput": 665.6, "total_tokens": 5875472} {"current_steps": 4275, "total_steps": 40000, "loss": 0.8256, "lr": 4.860467000047041e-05, "epoch": 0.13683502976762052, "percentage": 10.69, "elapsed_time": "2:27:09", "remaining_time": "20:29:42", "throughput": 666.19, "total_tokens": 5881888} {"current_steps": 4280, "total_steps": 40000, "loss": 0.7659, "lr": 4.860143420032737e-05, "epoch": 0.13699507073810896, "percentage": 10.7, "elapsed_time": "2:27:10", "remaining_time": "20:28:20", "throughput": 666.86, "total_tokens": 5888960} {"current_steps": 4285, "total_steps": 40000, "loss": 0.746, "lr": 4.859819476054657e-05, "epoch": 0.1371551117085974, "percentage": 10.71, "elapsed_time": "2:27:12", "remaining_time": "20:26:58", "throughput": 667.5, "total_tokens": 5895696} {"current_steps": 4290, "total_steps": 40000, "loss": 0.8201, "lr": 4.859495168162758e-05, "epoch": 0.13731515267908584, "percentage": 10.72, "elapsed_time": "2:27:14", "remaining_time": "20:25:36", "throughput": 668.17, "total_tokens": 5902832} {"current_steps": 4295, "total_steps": 40000, "loss": 1.1408, "lr": 4.859170496407054e-05, "epoch": 0.13747519364957428, "percentage": 10.74, "elapsed_time": "2:27:16", "remaining_time": "20:24:15", "throughput": 668.85, "total_tokens": 5909984} {"current_steps": 4300, "total_steps": 40000, "loss": 0.7438, "lr": 4.8588454608376114e-05, "epoch": 0.13763523462006275, "percentage": 10.75, "elapsed_time": "2:27:17", "remaining_time": "20:22:54", "throughput": 669.47, "total_tokens": 5916624} {"current_steps": 4305, "total_steps": 40000, "loss": 0.8828, "lr": 4.8585200615045555e-05, "epoch": 0.1377952755905512, "percentage": 10.76, "elapsed_time": "2:27:19", "remaining_time": "20:21:32", "throughput": 670.15, "total_tokens": 5923760} {"current_steps": 4310, "total_steps": 40000, "loss": 0.8484, "lr": 4.8581942984580674e-05, "epoch": 0.13795531656103963, "percentage": 10.78, "elapsed_time": "2:27:21", "remaining_time": "20:20:12", "throughput": 670.8, "total_tokens": 5930736} {"current_steps": 4315, "total_steps": 40000, "loss": 1.032, "lr": 4.857868171748384e-05, "epoch": 0.13811535753152807, "percentage": 10.79, "elapsed_time": "2:27:22", "remaining_time": "20:18:51", "throughput": 671.46, "total_tokens": 5937696} {"current_steps": 4320, "total_steps": 40000, "loss": 0.7396, "lr": 4.8575416814257976e-05, "epoch": 0.1382753985020165, "percentage": 10.8, "elapsed_time": "2:27:24", "remaining_time": "20:17:30", "throughput": 672.13, "total_tokens": 5944768} {"current_steps": 4325, "total_steps": 40000, "loss": 0.8064, "lr": 4.857214827540657e-05, "epoch": 0.13843543947250497, "percentage": 10.81, "elapsed_time": "2:27:26", "remaining_time": "20:16:10", "throughput": 672.84, "total_tokens": 5952208} {"current_steps": 4330, "total_steps": 40000, "loss": 0.9058, "lr": 4.856887610143367e-05, "epoch": 0.1385954804429934, "percentage": 10.82, "elapsed_time": "2:27:28", "remaining_time": "20:14:50", "throughput": 673.53, "total_tokens": 5959488} {"current_steps": 4335, "total_steps": 40000, "loss": 0.8633, "lr": 4.8565600292843896e-05, "epoch": 0.13875552141348185, "percentage": 10.84, "elapsed_time": "2:27:29", "remaining_time": "20:13:30", "throughput": 674.14, "total_tokens": 5966080} {"current_steps": 4340, "total_steps": 40000, "loss": 0.7478, "lr": 4.856232085014241e-05, "epoch": 0.1389155623839703, "percentage": 10.85, "elapsed_time": "2:27:31", "remaining_time": "20:12:10", "throughput": 674.81, "total_tokens": 5973184} {"current_steps": 4345, "total_steps": 40000, "loss": 0.9498, "lr": 4.855903777383495e-05, "epoch": 0.13907560335445873, "percentage": 10.86, "elapsed_time": "2:27:33", "remaining_time": "20:10:50", "throughput": 675.43, "total_tokens": 5979872} {"current_steps": 4350, "total_steps": 40000, "loss": 0.6895, "lr": 4.85557510644278e-05, "epoch": 0.1392356443249472, "percentage": 10.88, "elapsed_time": "2:27:35", "remaining_time": "20:09:31", "throughput": 676.07, "total_tokens": 5986704} {"current_steps": 4355, "total_steps": 40000, "loss": 1.0616, "lr": 4.855246072242782e-05, "epoch": 0.13939568529543564, "percentage": 10.89, "elapsed_time": "2:27:36", "remaining_time": "20:08:12", "throughput": 676.73, "total_tokens": 5993728} {"current_steps": 4360, "total_steps": 40000, "loss": 0.6038, "lr": 4.8549166748342414e-05, "epoch": 0.13955572626592408, "percentage": 10.9, "elapsed_time": "2:27:38", "remaining_time": "20:06:52", "throughput": 677.37, "total_tokens": 6000544} {"current_steps": 4365, "total_steps": 40000, "loss": 0.7672, "lr": 4.8545869142679556e-05, "epoch": 0.13971576723641252, "percentage": 10.91, "elapsed_time": "2:27:40", "remaining_time": "20:05:33", "throughput": 678.03, "total_tokens": 6007552} {"current_steps": 4370, "total_steps": 40000, "loss": 0.6756, "lr": 4.8542567905947776e-05, "epoch": 0.13987580820690096, "percentage": 10.93, "elapsed_time": "2:27:42", "remaining_time": "20:04:15", "throughput": 678.78, "total_tokens": 6015424} {"current_steps": 4375, "total_steps": 40000, "loss": 0.8362, "lr": 4.853926303865618e-05, "epoch": 0.1400358491773894, "percentage": 10.94, "elapsed_time": "2:27:43", "remaining_time": "20:02:56", "throughput": 679.42, "total_tokens": 6022224} {"current_steps": 4380, "total_steps": 40000, "loss": 0.7903, "lr": 4.853595454131441e-05, "epoch": 0.14019589014787787, "percentage": 10.95, "elapsed_time": "2:27:45", "remaining_time": "20:01:38", "throughput": 680.04, "total_tokens": 6028880} {"current_steps": 4385, "total_steps": 40000, "loss": 0.9272, "lr": 4.8532642414432674e-05, "epoch": 0.1403559311183663, "percentage": 10.96, "elapsed_time": "2:27:47", "remaining_time": "20:00:20", "throughput": 680.69, "total_tokens": 6035872} {"current_steps": 4390, "total_steps": 40000, "loss": 0.5703, "lr": 4.8529326658521754e-05, "epoch": 0.14051597208885475, "percentage": 10.97, "elapsed_time": "2:27:49", "remaining_time": "19:59:01", "throughput": 681.3, "total_tokens": 6042480} {"current_steps": 4395, "total_steps": 40000, "loss": 1.1923, "lr": 4.8526007274092965e-05, "epoch": 0.14067601305934319, "percentage": 10.99, "elapsed_time": "2:27:50", "remaining_time": "19:57:44", "throughput": 681.92, "total_tokens": 6049104} {"current_steps": 4400, "total_steps": 40000, "loss": 0.7947, "lr": 4.852268426165822e-05, "epoch": 0.14083605402983163, "percentage": 11.0, "elapsed_time": "2:27:52", "remaining_time": "19:56:26", "throughput": 682.53, "total_tokens": 6055712} {"current_steps": 4400, "total_steps": 40000, "eval_loss": 0.8656924962997437, "epoch": 0.14083605402983163, "percentage": 11.0, "elapsed_time": "2:33:40", "remaining_time": "20:43:20", "throughput": 656.78, "total_tokens": 6055712} {"current_steps": 4405, "total_steps": 40000, "loss": 0.7677, "lr": 4.851935762172995e-05, "epoch": 0.1409960950003201, "percentage": 11.01, "elapsed_time": "2:33:44", "remaining_time": "20:42:23", "throughput": 657.21, "total_tokens": 6062800} {"current_steps": 4410, "total_steps": 40000, "loss": 0.7917, "lr": 4.8516027354821175e-05, "epoch": 0.14115613597080853, "percentage": 11.03, "elapsed_time": "2:33:46", "remaining_time": "20:41:02", "throughput": 657.84, "total_tokens": 6069744} {"current_steps": 4415, "total_steps": 40000, "loss": 0.9337, "lr": 4.851269346144546e-05, "epoch": 0.14131617694129697, "percentage": 11.04, "elapsed_time": "2:33:48", "remaining_time": "20:39:41", "throughput": 658.5, "total_tokens": 6076928} {"current_steps": 4420, "total_steps": 40000, "loss": 0.8603, "lr": 4.850935594211693e-05, "epoch": 0.1414762179117854, "percentage": 11.05, "elapsed_time": "2:33:50", "remaining_time": "20:38:21", "throughput": 659.18, "total_tokens": 6084400} {"current_steps": 4425, "total_steps": 40000, "loss": 1.0639, "lr": 4.850601479735029e-05, "epoch": 0.14163625888227385, "percentage": 11.06, "elapsed_time": "2:33:51", "remaining_time": "20:37:00", "throughput": 659.81, "total_tokens": 6091328} {"current_steps": 4430, "total_steps": 40000, "loss": 0.8138, "lr": 4.850267002766076e-05, "epoch": 0.14179629985276232, "percentage": 11.07, "elapsed_time": "2:33:53", "remaining_time": "20:35:40", "throughput": 660.41, "total_tokens": 6098032} {"current_steps": 4435, "total_steps": 40000, "loss": 0.8093, "lr": 4.849932163356417e-05, "epoch": 0.14195634082325076, "percentage": 11.09, "elapsed_time": "2:33:55", "remaining_time": "20:34:20", "throughput": 661.03, "total_tokens": 6104832} {"current_steps": 4440, "total_steps": 40000, "loss": 0.9706, "lr": 4.8495969615576864e-05, "epoch": 0.1421163817937392, "percentage": 11.1, "elapsed_time": "2:33:57", "remaining_time": "20:33:00", "throughput": 661.61, "total_tokens": 6111392} {"current_steps": 4445, "total_steps": 40000, "loss": 0.9007, "lr": 4.849261397421577e-05, "epoch": 0.14227642276422764, "percentage": 11.11, "elapsed_time": "2:33:58", "remaining_time": "20:31:40", "throughput": 662.19, "total_tokens": 6117872} {"current_steps": 4450, "total_steps": 40000, "loss": 0.9025, "lr": 4.848925470999839e-05, "epoch": 0.14243646373471608, "percentage": 11.12, "elapsed_time": "2:34:00", "remaining_time": "20:30:21", "throughput": 662.79, "total_tokens": 6124624} {"current_steps": 4455, "total_steps": 40000, "loss": 0.7744, "lr": 4.848589182344273e-05, "epoch": 0.14259650470520452, "percentage": 11.14, "elapsed_time": "2:34:02", "remaining_time": "20:29:01", "throughput": 663.42, "total_tokens": 6131568} {"current_steps": 4460, "total_steps": 40000, "loss": 0.8967, "lr": 4.848252531506742e-05, "epoch": 0.142756545675693, "percentage": 11.15, "elapsed_time": "2:34:04", "remaining_time": "20:27:42", "throughput": 664.08, "total_tokens": 6138784} {"current_steps": 4465, "total_steps": 40000, "loss": 0.889, "lr": 4.847915518539161e-05, "epoch": 0.14291658664618143, "percentage": 11.16, "elapsed_time": "2:34:05", "remaining_time": "20:26:23", "throughput": 664.72, "total_tokens": 6145904} {"current_steps": 4470, "total_steps": 40000, "loss": 0.6855, "lr": 4.847578143493501e-05, "epoch": 0.14307662761666987, "percentage": 11.18, "elapsed_time": "2:34:07", "remaining_time": "20:25:04", "throughput": 665.35, "total_tokens": 6152848} {"current_steps": 4475, "total_steps": 40000, "loss": 0.631, "lr": 4.847240406421789e-05, "epoch": 0.1432366685871583, "percentage": 11.19, "elapsed_time": "2:34:09", "remaining_time": "20:23:45", "throughput": 665.95, "total_tokens": 6159568} {"current_steps": 4480, "total_steps": 40000, "loss": 0.6209, "lr": 4.84690230737611e-05, "epoch": 0.14339670955764675, "percentage": 11.2, "elapsed_time": "2:34:11", "remaining_time": "20:22:27", "throughput": 666.57, "total_tokens": 6166448} {"current_steps": 4485, "total_steps": 40000, "loss": 0.6206, "lr": 4.846563846408602e-05, "epoch": 0.1435567505281352, "percentage": 11.21, "elapsed_time": "2:34:12", "remaining_time": "20:21:08", "throughput": 667.14, "total_tokens": 6172832} {"current_steps": 4490, "total_steps": 40000, "loss": 0.7517, "lr": 4.84622502357146e-05, "epoch": 0.14371679149862365, "percentage": 11.22, "elapsed_time": "2:34:14", "remaining_time": "20:19:50", "throughput": 667.8, "total_tokens": 6180176} {"current_steps": 4495, "total_steps": 40000, "loss": 0.9926, "lr": 4.8458858389169345e-05, "epoch": 0.1438768324691121, "percentage": 11.24, "elapsed_time": "2:34:16", "remaining_time": "20:18:32", "throughput": 668.43, "total_tokens": 6187168} {"current_steps": 4500, "total_steps": 40000, "loss": 0.8817, "lr": 4.8455462924973334e-05, "epoch": 0.14403687343960053, "percentage": 11.25, "elapsed_time": "2:34:17", "remaining_time": "20:17:15", "throughput": 669.15, "total_tokens": 6194928} {"current_steps": 4505, "total_steps": 40000, "loss": 0.9438, "lr": 4.845206384365018e-05, "epoch": 0.14419691441008897, "percentage": 11.26, "elapsed_time": "2:34:19", "remaining_time": "20:15:57", "throughput": 669.75, "total_tokens": 6201648} {"current_steps": 4510, "total_steps": 40000, "loss": 0.8829, "lr": 4.844866114572405e-05, "epoch": 0.14435695538057744, "percentage": 11.28, "elapsed_time": "2:34:21", "remaining_time": "20:14:39", "throughput": 670.33, "total_tokens": 6208224} {"current_steps": 4515, "total_steps": 40000, "loss": 0.769, "lr": 4.8445254831719706e-05, "epoch": 0.14451699635106588, "percentage": 11.29, "elapsed_time": "2:34:23", "remaining_time": "20:13:22", "throughput": 670.93, "total_tokens": 6214928} {"current_steps": 4520, "total_steps": 40000, "loss": 0.9026, "lr": 4.8441844902162434e-05, "epoch": 0.14467703732155432, "percentage": 11.3, "elapsed_time": "2:34:24", "remaining_time": "20:12:05", "throughput": 671.54, "total_tokens": 6221744} {"current_steps": 4525, "total_steps": 40000, "loss": 0.7213, "lr": 4.843843135757809e-05, "epoch": 0.14483707829204276, "percentage": 11.31, "elapsed_time": "2:34:26", "remaining_time": "20:10:48", "throughput": 672.18, "total_tokens": 6228880} {"current_steps": 4530, "total_steps": 40000, "loss": 0.8587, "lr": 4.843501419849308e-05, "epoch": 0.1449971192625312, "percentage": 11.33, "elapsed_time": "2:34:28", "remaining_time": "20:09:31", "throughput": 672.78, "total_tokens": 6235616} {"current_steps": 4535, "total_steps": 40000, "loss": 0.7512, "lr": 4.8431593425434386e-05, "epoch": 0.14515716023301967, "percentage": 11.34, "elapsed_time": "2:34:30", "remaining_time": "20:08:15", "throughput": 673.44, "total_tokens": 6242848} {"current_steps": 4540, "total_steps": 40000, "loss": 0.7907, "lr": 4.8428169038929526e-05, "epoch": 0.1453172012035081, "percentage": 11.35, "elapsed_time": "2:34:31", "remaining_time": "20:06:58", "throughput": 674.04, "total_tokens": 6249616} {"current_steps": 4545, "total_steps": 40000, "loss": 1.0095, "lr": 4.8424741039506575e-05, "epoch": 0.14547724217399655, "percentage": 11.36, "elapsed_time": "2:34:33", "remaining_time": "20:05:42", "throughput": 674.64, "total_tokens": 6256352} {"current_steps": 4550, "total_steps": 40000, "loss": 0.6424, "lr": 4.842130942769419e-05, "epoch": 0.14563728314448499, "percentage": 11.38, "elapsed_time": "2:34:35", "remaining_time": "20:04:25", "throughput": 675.25, "total_tokens": 6263120} {"current_steps": 4555, "total_steps": 40000, "loss": 0.7982, "lr": 4.841787420402156e-05, "epoch": 0.14579732411497343, "percentage": 11.39, "elapsed_time": "2:34:37", "remaining_time": "20:03:09", "throughput": 675.84, "total_tokens": 6269840} {"current_steps": 4560, "total_steps": 40000, "loss": 0.9969, "lr": 4.841443536901844e-05, "epoch": 0.14595736508546187, "percentage": 11.4, "elapsed_time": "2:34:38", "remaining_time": "20:01:54", "throughput": 676.46, "total_tokens": 6276720} {"current_steps": 4565, "total_steps": 40000, "loss": 0.6933, "lr": 4.841099292321514e-05, "epoch": 0.14611740605595033, "percentage": 11.41, "elapsed_time": "2:34:40", "remaining_time": "20:00:38", "throughput": 677.05, "total_tokens": 6283408} {"current_steps": 4570, "total_steps": 40000, "loss": 0.8394, "lr": 4.8407546867142525e-05, "epoch": 0.14627744702643877, "percentage": 11.43, "elapsed_time": "2:34:42", "remaining_time": "19:59:22", "throughput": 677.65, "total_tokens": 6290112} {"current_steps": 4575, "total_steps": 40000, "loss": 0.8454, "lr": 4.840409720133203e-05, "epoch": 0.1464374879969272, "percentage": 11.44, "elapsed_time": "2:34:43", "remaining_time": "19:58:07", "throughput": 678.27, "total_tokens": 6297088} {"current_steps": 4580, "total_steps": 40000, "loss": 0.8853, "lr": 4.8400643926315634e-05, "epoch": 0.14659752896741565, "percentage": 11.45, "elapsed_time": "2:34:45", "remaining_time": "19:56:52", "throughput": 678.91, "total_tokens": 6304144} {"current_steps": 4585, "total_steps": 40000, "loss": 0.8482, "lr": 4.839718704262587e-05, "epoch": 0.1467575699379041, "percentage": 11.46, "elapsed_time": "2:34:47", "remaining_time": "19:55:37", "throughput": 679.52, "total_tokens": 6311040} {"current_steps": 4590, "total_steps": 40000, "loss": 0.8043, "lr": 4.839372655079585e-05, "epoch": 0.14691761090839256, "percentage": 11.47, "elapsed_time": "2:34:49", "remaining_time": "19:54:22", "throughput": 680.14, "total_tokens": 6317920} {"current_steps": 4595, "total_steps": 40000, "loss": 0.9102, "lr": 4.83902624513592e-05, "epoch": 0.147077651878881, "percentage": 11.49, "elapsed_time": "2:34:50", "remaining_time": "19:53:07", "throughput": 680.72, "total_tokens": 6324544} {"current_steps": 4600, "total_steps": 40000, "loss": 0.6828, "lr": 4.838679474485014e-05, "epoch": 0.14723769284936944, "percentage": 11.5, "elapsed_time": "2:34:52", "remaining_time": "19:51:53", "throughput": 681.36, "total_tokens": 6331680} {"current_steps": 4600, "total_steps": 40000, "eval_loss": 0.8624129295349121, "epoch": 0.14723769284936944, "percentage": 11.5, "elapsed_time": "2:40:40", "remaining_time": "20:36:31", "throughput": 656.77, "total_tokens": 6331680} {"current_steps": 4605, "total_steps": 40000, "loss": 0.7821, "lr": 4.838332343180343e-05, "epoch": 0.14739773381985788, "percentage": 11.51, "elapsed_time": "2:40:44", "remaining_time": "20:35:26", "throughput": 657.22, "total_tokens": 6338304} {"current_steps": 4610, "total_steps": 40000, "loss": 0.8997, "lr": 4.83798485127544e-05, "epoch": 0.14755777479034632, "percentage": 11.53, "elapsed_time": "2:40:45", "remaining_time": "20:34:09", "throughput": 657.84, "total_tokens": 6345456} {"current_steps": 4615, "total_steps": 40000, "loss": 0.9236, "lr": 4.837636998823892e-05, "epoch": 0.1477178157608348, "percentage": 11.54, "elapsed_time": "2:40:47", "remaining_time": "20:32:52", "throughput": 658.4, "total_tokens": 6351984} {"current_steps": 4620, "total_steps": 40000, "loss": 0.79, "lr": 4.8372887858793414e-05, "epoch": 0.14787785673132323, "percentage": 11.55, "elapsed_time": "2:40:49", "remaining_time": "20:31:34", "throughput": 659.0, "total_tokens": 6358944} {"current_steps": 4625, "total_steps": 40000, "loss": 0.999, "lr": 4.836940212495489e-05, "epoch": 0.14803789770181167, "percentage": 11.56, "elapsed_time": "2:40:51", "remaining_time": "20:30:17", "throughput": 659.6, "total_tokens": 6365840} {"current_steps": 4630, "total_steps": 40000, "loss": 1.0105, "lr": 4.836591278726087e-05, "epoch": 0.1481979386723001, "percentage": 11.58, "elapsed_time": "2:40:52", "remaining_time": "20:29:00", "throughput": 660.24, "total_tokens": 6373168} {"current_steps": 4635, "total_steps": 40000, "loss": 0.8722, "lr": 4.836241984624947e-05, "epoch": 0.14835797964278855, "percentage": 11.59, "elapsed_time": "2:40:54", "remaining_time": "20:27:44", "throughput": 660.79, "total_tokens": 6379632} {"current_steps": 4640, "total_steps": 40000, "loss": 0.6899, "lr": 4.8358923302459336e-05, "epoch": 0.14851802061327699, "percentage": 11.6, "elapsed_time": "2:40:56", "remaining_time": "20:26:27", "throughput": 661.36, "total_tokens": 6386272} {"current_steps": 4645, "total_steps": 40000, "loss": 0.961, "lr": 4.835542315642968e-05, "epoch": 0.14867806158376545, "percentage": 11.61, "elapsed_time": "2:40:58", "remaining_time": "20:25:11", "throughput": 661.97, "total_tokens": 6393280} {"current_steps": 4650, "total_steps": 40000, "loss": 0.7305, "lr": 4.8351919408700274e-05, "epoch": 0.1488381025542539, "percentage": 11.62, "elapsed_time": "2:40:59", "remaining_time": "20:23:54", "throughput": 662.55, "total_tokens": 6400032} {"current_steps": 4655, "total_steps": 40000, "loss": 0.7505, "lr": 4.834841205981144e-05, "epoch": 0.14899814352474233, "percentage": 11.64, "elapsed_time": "2:41:01", "remaining_time": "20:22:38", "throughput": 663.1, "total_tokens": 6406496} {"current_steps": 4660, "total_steps": 40000, "loss": 0.993, "lr": 4.8344901110304054e-05, "epoch": 0.14915818449523077, "percentage": 11.65, "elapsed_time": "2:41:03", "remaining_time": "20:21:23", "throughput": 663.74, "total_tokens": 6413856} {"current_steps": 4665, "total_steps": 40000, "loss": 0.7513, "lr": 4.8341386560719534e-05, "epoch": 0.1493182254657192, "percentage": 11.66, "elapsed_time": "2:41:04", "remaining_time": "20:20:07", "throughput": 664.28, "total_tokens": 6420256} {"current_steps": 4670, "total_steps": 40000, "loss": 0.9508, "lr": 4.833786841159989e-05, "epoch": 0.14947826643620768, "percentage": 11.68, "elapsed_time": "2:41:06", "remaining_time": "20:18:51", "throughput": 664.86, "total_tokens": 6426960} {"current_steps": 4675, "total_steps": 40000, "loss": 0.6614, "lr": 4.833434666348765e-05, "epoch": 0.14963830740669612, "percentage": 11.69, "elapsed_time": "2:41:08", "remaining_time": "20:17:36", "throughput": 665.47, "total_tokens": 6434048} {"current_steps": 4680, "total_steps": 40000, "loss": 0.8768, "lr": 4.833082131692592e-05, "epoch": 0.14979834837718456, "percentage": 11.7, "elapsed_time": "2:41:10", "remaining_time": "20:16:20", "throughput": 666.04, "total_tokens": 6440736} {"current_steps": 4685, "total_steps": 40000, "loss": 0.9303, "lr": 4.832729237245835e-05, "epoch": 0.149958389347673, "percentage": 11.71, "elapsed_time": "2:41:11", "remaining_time": "20:15:05", "throughput": 666.61, "total_tokens": 6447344} {"current_steps": 4690, "total_steps": 40000, "loss": 0.8442, "lr": 4.8323759830629145e-05, "epoch": 0.15011843031816144, "percentage": 11.72, "elapsed_time": "2:41:13", "remaining_time": "20:13:50", "throughput": 667.19, "total_tokens": 6454112} {"current_steps": 4695, "total_steps": 40000, "loss": 0.7878, "lr": 4.8320223691983066e-05, "epoch": 0.1502784712886499, "percentage": 11.74, "elapsed_time": "2:41:15", "remaining_time": "20:12:36", "throughput": 667.82, "total_tokens": 6461424} {"current_steps": 4700, "total_steps": 40000, "loss": 0.5774, "lr": 4.831668395706544e-05, "epoch": 0.15043851225913835, "percentage": 11.75, "elapsed_time": "2:41:17", "remaining_time": "20:11:21", "throughput": 668.37, "total_tokens": 6467872} {"current_steps": 4705, "total_steps": 40000, "loss": 0.7662, "lr": 4.8313140626422125e-05, "epoch": 0.15059855322962679, "percentage": 11.76, "elapsed_time": "2:41:18", "remaining_time": "20:10:06", "throughput": 668.93, "total_tokens": 6474512} {"current_steps": 4710, "total_steps": 40000, "loss": 1.0087, "lr": 4.830959370059956e-05, "epoch": 0.15075859420011523, "percentage": 11.77, "elapsed_time": "2:41:20", "remaining_time": "20:08:52", "throughput": 669.51, "total_tokens": 6481248} {"current_steps": 4715, "total_steps": 40000, "loss": 1.1352, "lr": 4.830604318014472e-05, "epoch": 0.15091863517060367, "percentage": 11.79, "elapsed_time": "2:41:22", "remaining_time": "20:07:38", "throughput": 670.08, "total_tokens": 6487920} {"current_steps": 4720, "total_steps": 40000, "loss": 0.9177, "lr": 4.830248906560514e-05, "epoch": 0.15107867614109213, "percentage": 11.8, "elapsed_time": "2:41:24", "remaining_time": "20:06:24", "throughput": 670.7, "total_tokens": 6495056} {"current_steps": 4725, "total_steps": 40000, "loss": 1.03, "lr": 4.829893135752891e-05, "epoch": 0.15123871711158057, "percentage": 11.81, "elapsed_time": "2:41:25", "remaining_time": "20:05:10", "throughput": 671.34, "total_tokens": 6502448} {"current_steps": 4730, "total_steps": 40000, "loss": 0.7146, "lr": 4.829537005646466e-05, "epoch": 0.151398758082069, "percentage": 11.82, "elapsed_time": "2:41:27", "remaining_time": "20:03:56", "throughput": 671.92, "total_tokens": 6509280} {"current_steps": 4735, "total_steps": 40000, "loss": 0.9262, "lr": 4.8291805162961615e-05, "epoch": 0.15155879905255745, "percentage": 11.84, "elapsed_time": "2:41:29", "remaining_time": "20:02:43", "throughput": 672.52, "total_tokens": 6516224} {"current_steps": 4740, "total_steps": 40000, "loss": 0.8502, "lr": 4.82882366775695e-05, "epoch": 0.1517188400230459, "percentage": 11.85, "elapsed_time": "2:41:31", "remaining_time": "20:01:29", "throughput": 673.09, "total_tokens": 6522912} {"current_steps": 4745, "total_steps": 40000, "loss": 0.7779, "lr": 4.828466460083864e-05, "epoch": 0.15187888099353433, "percentage": 11.86, "elapsed_time": "2:41:32", "remaining_time": "20:00:16", "throughput": 673.67, "total_tokens": 6529680} {"current_steps": 4750, "total_steps": 40000, "loss": 0.8414, "lr": 4.8281088933319877e-05, "epoch": 0.1520389219640228, "percentage": 11.88, "elapsed_time": "2:41:34", "remaining_time": "19:59:03", "throughput": 674.23, "total_tokens": 6536352} {"current_steps": 4755, "total_steps": 40000, "loss": 0.7238, "lr": 4.827750967556464e-05, "epoch": 0.15219896293451124, "percentage": 11.89, "elapsed_time": "2:41:36", "remaining_time": "19:57:50", "throughput": 674.8, "total_tokens": 6543056} {"current_steps": 4760, "total_steps": 40000, "loss": 0.8284, "lr": 4.827392682812488e-05, "epoch": 0.15235900390499968, "percentage": 11.9, "elapsed_time": "2:41:37", "remaining_time": "19:56:37", "throughput": 675.35, "total_tokens": 6549504} {"current_steps": 4765, "total_steps": 40000, "loss": 0.7989, "lr": 4.827034039155312e-05, "epoch": 0.15251904487548812, "percentage": 11.91, "elapsed_time": "2:41:39", "remaining_time": "19:55:24", "throughput": 675.94, "total_tokens": 6556384} {"current_steps": 4770, "total_steps": 40000, "loss": 0.8988, "lr": 4.8266750366402445e-05, "epoch": 0.15267908584597656, "percentage": 11.92, "elapsed_time": "2:41:41", "remaining_time": "19:54:12", "throughput": 676.5, "total_tokens": 6563024} {"current_steps": 4775, "total_steps": 40000, "loss": 0.9974, "lr": 4.8263156753226476e-05, "epoch": 0.15283912681646503, "percentage": 11.94, "elapsed_time": "2:41:43", "remaining_time": "19:52:59", "throughput": 677.07, "total_tokens": 6569712} {"current_steps": 4780, "total_steps": 40000, "loss": 1.0199, "lr": 4.8259559552579394e-05, "epoch": 0.15299916778695347, "percentage": 11.95, "elapsed_time": "2:41:44", "remaining_time": "19:51:47", "throughput": 677.66, "total_tokens": 6576576} {"current_steps": 4785, "total_steps": 40000, "loss": 0.8065, "lr": 4.825595876501593e-05, "epoch": 0.1531592087574419, "percentage": 11.96, "elapsed_time": "2:41:46", "remaining_time": "19:50:35", "throughput": 678.27, "total_tokens": 6583696} {"current_steps": 4790, "total_steps": 40000, "loss": 0.8789, "lr": 4.825235439109137e-05, "epoch": 0.15331924972793035, "percentage": 11.97, "elapsed_time": "2:41:48", "remaining_time": "19:49:23", "throughput": 678.86, "total_tokens": 6590608} {"current_steps": 4795, "total_steps": 40000, "loss": 0.9812, "lr": 4.824874643136156e-05, "epoch": 0.15347929069841879, "percentage": 11.99, "elapsed_time": "2:41:50", "remaining_time": "19:48:11", "throughput": 679.48, "total_tokens": 6597776} {"current_steps": 4800, "total_steps": 40000, "loss": 0.7723, "lr": 4.824513488638288e-05, "epoch": 0.15363933166890725, "percentage": 12.0, "elapsed_time": "2:41:51", "remaining_time": "19:47:00", "throughput": 680.05, "total_tokens": 6604544} {"current_steps": 4800, "total_steps": 40000, "eval_loss": 0.8568878173828125, "epoch": 0.15363933166890725, "percentage": 12.0, "elapsed_time": "2:47:40", "remaining_time": "20:29:33", "throughput": 656.51, "total_tokens": 6604544} {"current_steps": 4805, "total_steps": 40000, "loss": 0.7645, "lr": 4.8241519756712293e-05, "epoch": 0.1537993726393957, "percentage": 12.01, "elapsed_time": "2:47:43", "remaining_time": "20:28:31", "throughput": 656.98, "total_tokens": 6611472} {"current_steps": 4810, "total_steps": 40000, "loss": 0.923, "lr": 4.8237901042907285e-05, "epoch": 0.15395941360988413, "percentage": 12.03, "elapsed_time": "2:47:45", "remaining_time": "20:27:16", "throughput": 657.6, "total_tokens": 6618912} {"current_steps": 4815, "total_steps": 40000, "loss": 0.8927, "lr": 4.823427874552591e-05, "epoch": 0.15411945458037257, "percentage": 12.04, "elapsed_time": "2:47:46", "remaining_time": "20:26:02", "throughput": 658.17, "total_tokens": 6625712} {"current_steps": 4820, "total_steps": 40000, "loss": 0.755, "lr": 4.823065286512677e-05, "epoch": 0.154279495550861, "percentage": 12.05, "elapsed_time": "2:47:48", "remaining_time": "20:24:48", "throughput": 658.72, "total_tokens": 6632432} {"current_steps": 4825, "total_steps": 40000, "loss": 0.7029, "lr": 4.8227023402269025e-05, "epoch": 0.15443953652134945, "percentage": 12.06, "elapsed_time": "2:47:50", "remaining_time": "20:23:34", "throughput": 659.3, "total_tokens": 6639392} {"current_steps": 4830, "total_steps": 40000, "loss": 0.9038, "lr": 4.822339035751239e-05, "epoch": 0.15459957749183792, "percentage": 12.07, "elapsed_time": "2:47:52", "remaining_time": "20:22:20", "throughput": 659.86, "total_tokens": 6646224} {"current_steps": 4835, "total_steps": 40000, "loss": 0.8319, "lr": 4.8219753731417104e-05, "epoch": 0.15475961846232636, "percentage": 12.09, "elapsed_time": "2:47:53", "remaining_time": "20:21:07", "throughput": 660.43, "total_tokens": 6653040} {"current_steps": 4840, "total_steps": 40000, "loss": 1.0931, "lr": 4.821611352454401e-05, "epoch": 0.1549196594328148, "percentage": 12.1, "elapsed_time": "2:47:55", "remaining_time": "20:19:53", "throughput": 661.0, "total_tokens": 6659968} {"current_steps": 4845, "total_steps": 40000, "loss": 0.9482, "lr": 4.8212469737454444e-05, "epoch": 0.15507970040330324, "percentage": 12.11, "elapsed_time": "2:47:57", "remaining_time": "20:18:40", "throughput": 661.58, "total_tokens": 6666912} {"current_steps": 4850, "total_steps": 40000, "loss": 0.8192, "lr": 4.820882237071035e-05, "epoch": 0.15523974137379168, "percentage": 12.12, "elapsed_time": "2:47:59", "remaining_time": "20:17:27", "throughput": 662.13, "total_tokens": 6673632} {"current_steps": 4855, "total_steps": 40000, "loss": 0.9225, "lr": 4.820517142487417e-05, "epoch": 0.15539978234428015, "percentage": 12.14, "elapsed_time": "2:48:00", "remaining_time": "20:16:14", "throughput": 662.73, "total_tokens": 6680832} {"current_steps": 4860, "total_steps": 40000, "loss": 0.7874, "lr": 4.8201516900508956e-05, "epoch": 0.15555982331476859, "percentage": 12.15, "elapsed_time": "2:48:02", "remaining_time": "20:15:01", "throughput": 663.27, "total_tokens": 6687440} {"current_steps": 4865, "total_steps": 40000, "loss": 0.6685, "lr": 4.819785879817827e-05, "epoch": 0.15571986428525703, "percentage": 12.16, "elapsed_time": "2:48:04", "remaining_time": "20:13:50", "throughput": 663.81, "total_tokens": 6694208} {"current_steps": 4870, "total_steps": 40000, "loss": 0.7123, "lr": 4.8194197118446226e-05, "epoch": 0.15587990525574547, "percentage": 12.17, "elapsed_time": "2:48:06", "remaining_time": "20:12:37", "throughput": 664.39, "total_tokens": 6701168} {"current_steps": 4875, "total_steps": 40000, "loss": 1.0736, "lr": 4.819053186187752e-05, "epoch": 0.1560399462262339, "percentage": 12.19, "elapsed_time": "2:48:07", "remaining_time": "20:11:25", "throughput": 664.93, "total_tokens": 6707808} {"current_steps": 4880, "total_steps": 40000, "loss": 0.8582, "lr": 4.818686302903736e-05, "epoch": 0.15619998719672237, "percentage": 12.2, "elapsed_time": "2:48:09", "remaining_time": "20:10:12", "throughput": 665.47, "total_tokens": 6714400} {"current_steps": 4885, "total_steps": 40000, "loss": 0.8875, "lr": 4.818319062049154e-05, "epoch": 0.1563600281672108, "percentage": 12.21, "elapsed_time": "2:48:11", "remaining_time": "20:09:00", "throughput": 666.07, "total_tokens": 6721632} {"current_steps": 4890, "total_steps": 40000, "loss": 0.9745, "lr": 4.817951463680639e-05, "epoch": 0.15652006913769925, "percentage": 12.22, "elapsed_time": "2:48:13", "remaining_time": "20:07:48", "throughput": 666.73, "total_tokens": 6729392} {"current_steps": 4895, "total_steps": 40000, "loss": 0.6707, "lr": 4.817583507854879e-05, "epoch": 0.1566801101081877, "percentage": 12.24, "elapsed_time": "2:48:14", "remaining_time": "20:06:36", "throughput": 667.3, "total_tokens": 6736320} {"current_steps": 4900, "total_steps": 40000, "loss": 1.0845, "lr": 4.817215194628617e-05, "epoch": 0.15684015107867613, "percentage": 12.25, "elapsed_time": "2:48:16", "remaining_time": "20:05:25", "throughput": 667.91, "total_tokens": 6743664} {"current_steps": 4905, "total_steps": 40000, "loss": 0.9167, "lr": 4.816846524058653e-05, "epoch": 0.1570001920491646, "percentage": 12.26, "elapsed_time": "2:48:18", "remaining_time": "20:04:13", "throughput": 668.49, "total_tokens": 6750672} {"current_steps": 4910, "total_steps": 40000, "loss": 1.355, "lr": 4.816477496201839e-05, "epoch": 0.15716023301965304, "percentage": 12.28, "elapsed_time": "2:48:20", "remaining_time": "20:03:01", "throughput": 669.05, "total_tokens": 6757488} {"current_steps": 4915, "total_steps": 40000, "loss": 0.944, "lr": 4.8161081111150845e-05, "epoch": 0.15732027399014148, "percentage": 12.29, "elapsed_time": "2:48:21", "remaining_time": "20:01:50", "throughput": 669.6, "total_tokens": 6764224} {"current_steps": 4920, "total_steps": 40000, "loss": 0.9804, "lr": 4.815738368855354e-05, "epoch": 0.15748031496062992, "percentage": 12.3, "elapsed_time": "2:48:23", "remaining_time": "20:00:39", "throughput": 670.16, "total_tokens": 6770976} {"current_steps": 4925, "total_steps": 40000, "loss": 0.7283, "lr": 4.815368269479664e-05, "epoch": 0.15764035593111836, "percentage": 12.31, "elapsed_time": "2:48:25", "remaining_time": "19:59:28", "throughput": 670.71, "total_tokens": 6777776} {"current_steps": 4930, "total_steps": 40000, "loss": 0.7818, "lr": 4.814997813045092e-05, "epoch": 0.1578003969016068, "percentage": 12.32, "elapsed_time": "2:48:27", "remaining_time": "19:58:17", "throughput": 671.31, "total_tokens": 6784944} {"current_steps": 4935, "total_steps": 40000, "loss": 0.8683, "lr": 4.814626999608764e-05, "epoch": 0.15796043787209527, "percentage": 12.34, "elapsed_time": "2:48:28", "remaining_time": "19:57:06", "throughput": 671.88, "total_tokens": 6791856} {"current_steps": 4940, "total_steps": 40000, "loss": 0.869, "lr": 4.814255829227865e-05, "epoch": 0.1581204788425837, "percentage": 12.35, "elapsed_time": "2:48:30", "remaining_time": "19:55:56", "throughput": 672.41, "total_tokens": 6798400} {"current_steps": 4945, "total_steps": 40000, "loss": 0.865, "lr": 4.813884301959635e-05, "epoch": 0.15828051981307215, "percentage": 12.36, "elapsed_time": "2:48:32", "remaining_time": "19:54:45", "throughput": 673.0, "total_tokens": 6805552} {"current_steps": 4950, "total_steps": 40000, "loss": 0.8632, "lr": 4.813512417861368e-05, "epoch": 0.15844056078356059, "percentage": 12.38, "elapsed_time": "2:48:34", "remaining_time": "19:53:35", "throughput": 673.59, "total_tokens": 6812720} {"current_steps": 4955, "total_steps": 40000, "loss": 0.7936, "lr": 4.813140176990411e-05, "epoch": 0.15860060175404903, "percentage": 12.39, "elapsed_time": "2:48:35", "remaining_time": "19:52:25", "throughput": 674.15, "total_tokens": 6819568} {"current_steps": 4960, "total_steps": 40000, "loss": 1.0182, "lr": 4.8127675794041714e-05, "epoch": 0.1587606427245375, "percentage": 12.4, "elapsed_time": "2:48:37", "remaining_time": "19:51:15", "throughput": 674.7, "total_tokens": 6826256} {"current_steps": 4965, "total_steps": 40000, "loss": 0.9624, "lr": 4.812394625160107e-05, "epoch": 0.15892068369502593, "percentage": 12.41, "elapsed_time": "2:48:39", "remaining_time": "19:50:05", "throughput": 675.31, "total_tokens": 6833568} {"current_steps": 4970, "total_steps": 40000, "loss": 1.0264, "lr": 4.812021314315732e-05, "epoch": 0.15908072466551437, "percentage": 12.43, "elapsed_time": "2:48:40", "remaining_time": "19:48:55", "throughput": 675.85, "total_tokens": 6840208} {"current_steps": 4975, "total_steps": 40000, "loss": 0.8686, "lr": 4.811647646928616e-05, "epoch": 0.1592407656360028, "percentage": 12.44, "elapsed_time": "2:48:42", "remaining_time": "19:47:45", "throughput": 676.44, "total_tokens": 6847408} {"current_steps": 4980, "total_steps": 40000, "loss": 0.788, "lr": 4.8112736230563814e-05, "epoch": 0.15940080660649125, "percentage": 12.45, "elapsed_time": "2:48:44", "remaining_time": "19:46:36", "throughput": 677.03, "total_tokens": 6854496} {"current_steps": 4985, "total_steps": 40000, "loss": 1.0458, "lr": 4.81089924275671e-05, "epoch": 0.15956084757697972, "percentage": 12.46, "elapsed_time": "2:48:46", "remaining_time": "19:45:26", "throughput": 677.59, "total_tokens": 6861392} {"current_steps": 4990, "total_steps": 40000, "loss": 0.7865, "lr": 4.810524506087335e-05, "epoch": 0.15972088854746816, "percentage": 12.47, "elapsed_time": "2:48:47", "remaining_time": "19:44:17", "throughput": 678.16, "total_tokens": 6868368} {"current_steps": 4995, "total_steps": 40000, "loss": 0.7855, "lr": 4.810149413106044e-05, "epoch": 0.1598809295179566, "percentage": 12.49, "elapsed_time": "2:48:49", "remaining_time": "19:43:08", "throughput": 678.76, "total_tokens": 6875584} {"current_steps": 5000, "total_steps": 40000, "loss": 0.8328, "lr": 4.809773963870684e-05, "epoch": 0.16004097048844504, "percentage": 12.5, "elapsed_time": "2:48:51", "remaining_time": "19:41:59", "throughput": 679.3, "total_tokens": 6882256} {"current_steps": 5000, "total_steps": 40000, "eval_loss": 0.8511151075363159, "epoch": 0.16004097048844504, "percentage": 12.5, "elapsed_time": "2:54:38", "remaining_time": "20:22:32", "throughput": 656.77, "total_tokens": 6882256} {"current_steps": 5005, "total_steps": 40000, "loss": 0.8456, "lr": 4.809398158439151e-05, "epoch": 0.16020101145893348, "percentage": 12.51, "elapsed_time": "2:54:42", "remaining_time": "20:21:32", "throughput": 657.25, "total_tokens": 6889504} {"current_steps": 5010, "total_steps": 40000, "loss": 0.8506, "lr": 4.8090219968694005e-05, "epoch": 0.16036105242942192, "percentage": 12.53, "elapsed_time": "2:54:44", "remaining_time": "20:20:21", "throughput": 657.82, "total_tokens": 6896608} {"current_steps": 5015, "total_steps": 40000, "loss": 0.7971, "lr": 4.808645479219442e-05, "epoch": 0.1605210933999104, "percentage": 12.54, "elapsed_time": "2:54:45", "remaining_time": "20:19:09", "throughput": 658.34, "total_tokens": 6903216} {"current_steps": 5020, "total_steps": 40000, "loss": 0.8286, "lr": 4.8082686055473375e-05, "epoch": 0.16068113437039883, "percentage": 12.55, "elapsed_time": "2:54:47", "remaining_time": "20:17:58", "throughput": 658.96, "total_tokens": 6910912} {"current_steps": 5025, "total_steps": 40000, "loss": 0.8279, "lr": 4.8078913759112066e-05, "epoch": 0.16084117534088727, "percentage": 12.56, "elapsed_time": "2:54:49", "remaining_time": "20:16:47", "throughput": 659.49, "total_tokens": 6917616} {"current_steps": 5030, "total_steps": 40000, "loss": 0.9667, "lr": 4.807513790369223e-05, "epoch": 0.1610012163113757, "percentage": 12.57, "elapsed_time": "2:54:51", "remaining_time": "20:15:36", "throughput": 660.05, "total_tokens": 6924624} {"current_steps": 5035, "total_steps": 40000, "loss": 0.788, "lr": 4.8071358489796145e-05, "epoch": 0.16116125728186415, "percentage": 12.59, "elapsed_time": "2:54:52", "remaining_time": "20:14:25", "throughput": 660.6, "total_tokens": 6931520} {"current_steps": 5040, "total_steps": 40000, "loss": 0.7501, "lr": 4.806757551800665e-05, "epoch": 0.1613212982523526, "percentage": 12.6, "elapsed_time": "2:54:54", "remaining_time": "20:13:15", "throughput": 661.15, "total_tokens": 6938480} {"current_steps": 5045, "total_steps": 40000, "loss": 0.6543, "lr": 4.806378898890713e-05, "epoch": 0.16148133922284105, "percentage": 12.61, "elapsed_time": "2:54:56", "remaining_time": "20:12:04", "throughput": 661.65, "total_tokens": 6944880} {"current_steps": 5050, "total_steps": 40000, "loss": 1.0486, "lr": 4.80599989030815e-05, "epoch": 0.1616413801933295, "percentage": 12.62, "elapsed_time": "2:54:57", "remaining_time": "20:10:54", "throughput": 662.21, "total_tokens": 6951840} {"current_steps": 5055, "total_steps": 40000, "loss": 0.7422, "lr": 4.805620526111426e-05, "epoch": 0.16180142116381793, "percentage": 12.64, "elapsed_time": "2:54:59", "remaining_time": "20:09:44", "throughput": 662.76, "total_tokens": 6958832} {"current_steps": 5060, "total_steps": 40000, "loss": 0.9145, "lr": 4.805240806359042e-05, "epoch": 0.16196146213430637, "percentage": 12.65, "elapsed_time": "2:55:01", "remaining_time": "20:08:33", "throughput": 663.31, "total_tokens": 6965744} {"current_steps": 5065, "total_steps": 40000, "loss": 0.702, "lr": 4.804860731109557e-05, "epoch": 0.16212150310479484, "percentage": 12.66, "elapsed_time": "2:55:03", "remaining_time": "20:07:23", "throughput": 663.85, "total_tokens": 6972528} {"current_steps": 5070, "total_steps": 40000, "loss": 0.8768, "lr": 4.804480300421581e-05, "epoch": 0.16228154407528328, "percentage": 12.68, "elapsed_time": "2:55:04", "remaining_time": "20:06:14", "throughput": 664.4, "total_tokens": 6979520} {"current_steps": 5075, "total_steps": 40000, "loss": 1.0074, "lr": 4.804099514353784e-05, "epoch": 0.16244158504577172, "percentage": 12.69, "elapsed_time": "2:55:06", "remaining_time": "20:05:04", "throughput": 664.97, "total_tokens": 6986624} {"current_steps": 5080, "total_steps": 40000, "loss": 0.7882, "lr": 4.8037183729648867e-05, "epoch": 0.16260162601626016, "percentage": 12.7, "elapsed_time": "2:55:08", "remaining_time": "20:03:54", "throughput": 665.52, "total_tokens": 6993584} {"current_steps": 5085, "total_steps": 40000, "loss": 0.7349, "lr": 4.803336876313666e-05, "epoch": 0.1627616669867486, "percentage": 12.71, "elapsed_time": "2:55:10", "remaining_time": "20:02:45", "throughput": 666.08, "total_tokens": 7000544} {"current_steps": 5090, "total_steps": 40000, "loss": 0.6919, "lr": 4.802955024458953e-05, "epoch": 0.16292170795723707, "percentage": 12.72, "elapsed_time": "2:55:11", "remaining_time": "20:01:36", "throughput": 666.63, "total_tokens": 7007536} {"current_steps": 5095, "total_steps": 40000, "loss": 0.6435, "lr": 4.802572817459634e-05, "epoch": 0.1630817489277255, "percentage": 12.74, "elapsed_time": "2:55:13", "remaining_time": "20:00:26", "throughput": 667.13, "total_tokens": 7013952} {"current_steps": 5100, "total_steps": 40000, "loss": 0.8549, "lr": 4.802190255374651e-05, "epoch": 0.16324178989821395, "percentage": 12.75, "elapsed_time": "2:55:15", "remaining_time": "19:59:18", "throughput": 667.7, "total_tokens": 7021152} {"current_steps": 5105, "total_steps": 40000, "loss": 0.8673, "lr": 4.801807338263e-05, "epoch": 0.16340183086870239, "percentage": 12.76, "elapsed_time": "2:55:17", "remaining_time": "19:58:09", "throughput": 668.22, "total_tokens": 7027760} {"current_steps": 5110, "total_steps": 40000, "loss": 1.0388, "lr": 4.8014240661837306e-05, "epoch": 0.16356187183919083, "percentage": 12.78, "elapsed_time": "2:55:18", "remaining_time": "19:57:00", "throughput": 668.8, "total_tokens": 7034976} {"current_steps": 5115, "total_steps": 40000, "loss": 0.7505, "lr": 4.80104043919595e-05, "epoch": 0.16372191280967927, "percentage": 12.79, "elapsed_time": "2:55:20", "remaining_time": "19:55:51", "throughput": 669.33, "total_tokens": 7041728} {"current_steps": 5120, "total_steps": 40000, "loss": 0.8937, "lr": 4.800656457358815e-05, "epoch": 0.16388195378016773, "percentage": 12.8, "elapsed_time": "2:55:22", "remaining_time": "19:54:43", "throughput": 669.87, "total_tokens": 7048560} {"current_steps": 5125, "total_steps": 40000, "loss": 0.6859, "lr": 4.800272120731544e-05, "epoch": 0.16404199475065617, "percentage": 12.81, "elapsed_time": "2:55:24", "remaining_time": "19:53:34", "throughput": 670.38, "total_tokens": 7055040} {"current_steps": 5130, "total_steps": 40000, "loss": 0.7403, "lr": 4.799887429373404e-05, "epoch": 0.1642020357211446, "percentage": 12.83, "elapsed_time": "2:55:25", "remaining_time": "19:52:26", "throughput": 670.95, "total_tokens": 7062272} {"current_steps": 5135, "total_steps": 40000, "loss": 0.7343, "lr": 4.79950238334372e-05, "epoch": 0.16436207669163305, "percentage": 12.84, "elapsed_time": "2:55:27", "remaining_time": "19:51:18", "throughput": 671.54, "total_tokens": 7069584} {"current_steps": 5140, "total_steps": 40000, "loss": 0.7611, "lr": 4.799116982701872e-05, "epoch": 0.1645221176621215, "percentage": 12.85, "elapsed_time": "2:55:29", "remaining_time": "19:50:10", "throughput": 672.07, "total_tokens": 7076352} {"current_steps": 5145, "total_steps": 40000, "loss": 1.0674, "lr": 4.7987312275072926e-05, "epoch": 0.16468215863260996, "percentage": 12.86, "elapsed_time": "2:55:30", "remaining_time": "19:49:02", "throughput": 672.6, "total_tokens": 7083168} {"current_steps": 5150, "total_steps": 40000, "loss": 0.6582, "lr": 4.79834511781947e-05, "epoch": 0.1648421996030984, "percentage": 12.88, "elapsed_time": "2:55:32", "remaining_time": "19:47:54", "throughput": 673.17, "total_tokens": 7090320} {"current_steps": 5155, "total_steps": 40000, "loss": 0.7608, "lr": 4.797958653697947e-05, "epoch": 0.16500224057358684, "percentage": 12.89, "elapsed_time": "2:55:34", "remaining_time": "19:46:47", "throughput": 673.73, "total_tokens": 7097408} {"current_steps": 5160, "total_steps": 40000, "loss": 0.6512, "lr": 4.7975718352023225e-05, "epoch": 0.16516228154407528, "percentage": 12.9, "elapsed_time": "2:55:36", "remaining_time": "19:45:39", "throughput": 674.27, "total_tokens": 7104272} {"current_steps": 5165, "total_steps": 40000, "loss": 0.7313, "lr": 4.7971846623922476e-05, "epoch": 0.16532232251456372, "percentage": 12.91, "elapsed_time": "2:55:37", "remaining_time": "19:44:32", "throughput": 674.85, "total_tokens": 7111552} {"current_steps": 5170, "total_steps": 40000, "loss": 0.6152, "lr": 4.7967971353274294e-05, "epoch": 0.1654823634850522, "percentage": 12.93, "elapsed_time": "2:55:39", "remaining_time": "19:43:24", "throughput": 675.4, "total_tokens": 7118464} {"current_steps": 5175, "total_steps": 40000, "loss": 0.7646, "lr": 4.79640925406763e-05, "epoch": 0.16564240445554063, "percentage": 12.94, "elapsed_time": "2:55:41", "remaining_time": "19:42:17", "throughput": 675.92, "total_tokens": 7125072} {"current_steps": 5180, "total_steps": 40000, "loss": 1.0681, "lr": 4.796021018672664e-05, "epoch": 0.16580244542602907, "percentage": 12.95, "elapsed_time": "2:55:43", "remaining_time": "19:41:10", "throughput": 676.42, "total_tokens": 7131584} {"current_steps": 5185, "total_steps": 40000, "loss": 0.8001, "lr": 4.795632429202405e-05, "epoch": 0.1659624863965175, "percentage": 12.96, "elapsed_time": "2:55:44", "remaining_time": "19:40:03", "throughput": 676.96, "total_tokens": 7138448} {"current_steps": 5190, "total_steps": 40000, "loss": 0.7384, "lr": 4.795243485716775e-05, "epoch": 0.16612252736700595, "percentage": 12.97, "elapsed_time": "2:55:46", "remaining_time": "19:38:57", "throughput": 677.47, "total_tokens": 7145024} {"current_steps": 5195, "total_steps": 40000, "loss": 0.7874, "lr": 4.794854188275757e-05, "epoch": 0.16628256833749439, "percentage": 12.99, "elapsed_time": "2:55:48", "remaining_time": "19:37:50", "throughput": 678.03, "total_tokens": 7152064} {"current_steps": 5200, "total_steps": 40000, "loss": 0.8425, "lr": 4.794464536939384e-05, "epoch": 0.16644260930798285, "percentage": 13.0, "elapsed_time": "2:55:50", "remaining_time": "19:36:44", "throughput": 678.58, "total_tokens": 7159072} {"current_steps": 5200, "total_steps": 40000, "eval_loss": 0.8481181859970093, "epoch": 0.16644260930798285, "percentage": 13.0, "elapsed_time": "3:01:37", "remaining_time": "20:15:30", "throughput": 656.94, "total_tokens": 7159072} {"current_steps": 5205, "total_steps": 40000, "loss": 0.8196, "lr": 4.794074531767745e-05, "epoch": 0.1666026502784713, "percentage": 13.01, "elapsed_time": "3:01:40", "remaining_time": "20:14:31", "throughput": 657.37, "total_tokens": 7165856} {"current_steps": 5210, "total_steps": 40000, "loss": 0.8705, "lr": 4.7936841728209834e-05, "epoch": 0.16676269124895973, "percentage": 13.03, "elapsed_time": "3:01:42", "remaining_time": "20:13:22", "throughput": 657.9, "total_tokens": 7172848} {"current_steps": 5215, "total_steps": 40000, "loss": 1.1306, "lr": 4.7932934601593e-05, "epoch": 0.16692273221944817, "percentage": 13.04, "elapsed_time": "3:01:44", "remaining_time": "20:12:13", "throughput": 658.42, "total_tokens": 7179600} {"current_steps": 5220, "total_steps": 40000, "loss": 0.7407, "lr": 4.792902393842943e-05, "epoch": 0.1670827731899366, "percentage": 13.05, "elapsed_time": "3:01:46", "remaining_time": "20:11:05", "throughput": 658.94, "total_tokens": 7186480} {"current_steps": 5225, "total_steps": 40000, "loss": 0.7296, "lr": 4.792510973932225e-05, "epoch": 0.16724281416042508, "percentage": 13.06, "elapsed_time": "3:01:47", "remaining_time": "20:09:57", "throughput": 659.48, "total_tokens": 7193456} {"current_steps": 5230, "total_steps": 40000, "loss": 0.9386, "lr": 4.7921192004875036e-05, "epoch": 0.16740285513091352, "percentage": 13.08, "elapsed_time": "3:01:49", "remaining_time": "20:08:48", "throughput": 660.04, "total_tokens": 7200704} {"current_steps": 5235, "total_steps": 40000, "loss": 0.6616, "lr": 4.791727073569198e-05, "epoch": 0.16756289610140196, "percentage": 13.09, "elapsed_time": "3:01:51", "remaining_time": "20:07:40", "throughput": 660.52, "total_tokens": 7207152} {"current_steps": 5240, "total_steps": 40000, "loss": 1.0482, "lr": 4.7913345932377775e-05, "epoch": 0.1677229370718904, "percentage": 13.1, "elapsed_time": "3:01:53", "remaining_time": "20:06:32", "throughput": 661.07, "total_tokens": 7214304} {"current_steps": 5245, "total_steps": 40000, "loss": 0.8502, "lr": 4.790941759553769e-05, "epoch": 0.16788297804237884, "percentage": 13.11, "elapsed_time": "3:01:54", "remaining_time": "20:05:24", "throughput": 661.58, "total_tokens": 7221008} {"current_steps": 5250, "total_steps": 40000, "loss": 0.8305, "lr": 4.79054857257775e-05, "epoch": 0.1680430190128673, "percentage": 13.12, "elapsed_time": "3:01:56", "remaining_time": "20:04:16", "throughput": 662.07, "total_tokens": 7227504} {"current_steps": 5255, "total_steps": 40000, "loss": 0.7248, "lr": 4.790155032370357e-05, "epoch": 0.16820305998335575, "percentage": 13.14, "elapsed_time": "3:01:58", "remaining_time": "20:03:09", "throughput": 662.57, "total_tokens": 7234064} {"current_steps": 5260, "total_steps": 40000, "loss": 0.9652, "lr": 4.789761138992278e-05, "epoch": 0.16836310095384419, "percentage": 13.15, "elapsed_time": "3:01:59", "remaining_time": "20:02:01", "throughput": 663.08, "total_tokens": 7240848} {"current_steps": 5265, "total_steps": 40000, "loss": 1.0621, "lr": 4.7893668925042565e-05, "epoch": 0.16852314192433263, "percentage": 13.16, "elapsed_time": "3:02:01", "remaining_time": "20:00:54", "throughput": 663.61, "total_tokens": 7247744} {"current_steps": 5270, "total_steps": 40000, "loss": 1.0717, "lr": 4.78897229296709e-05, "epoch": 0.16868318289482107, "percentage": 13.18, "elapsed_time": "3:02:03", "remaining_time": "19:59:47", "throughput": 664.13, "total_tokens": 7254544} {"current_steps": 5275, "total_steps": 40000, "loss": 0.8558, "lr": 4.7885773404416315e-05, "epoch": 0.16884322386530953, "percentage": 13.19, "elapsed_time": "3:02:05", "remaining_time": "19:58:39", "throughput": 664.69, "total_tokens": 7261904} {"current_steps": 5280, "total_steps": 40000, "loss": 0.6206, "lr": 4.788182034988786e-05, "epoch": 0.16900326483579797, "percentage": 13.2, "elapsed_time": "3:02:06", "remaining_time": "19:57:32", "throughput": 665.23, "total_tokens": 7268896} {"current_steps": 5285, "total_steps": 40000, "loss": 0.7856, "lr": 4.787786376669516e-05, "epoch": 0.1691633058062864, "percentage": 13.21, "elapsed_time": "3:02:08", "remaining_time": "19:56:25", "throughput": 665.74, "total_tokens": 7275648} {"current_steps": 5290, "total_steps": 40000, "loss": 0.8955, "lr": 4.787390365544837e-05, "epoch": 0.16932334677677485, "percentage": 13.23, "elapsed_time": "3:02:10", "remaining_time": "19:55:19", "throughput": 666.26, "total_tokens": 7282512} {"current_steps": 5295, "total_steps": 40000, "loss": 0.9506, "lr": 4.786994001675818e-05, "epoch": 0.1694833877472633, "percentage": 13.24, "elapsed_time": "3:02:12", "remaining_time": "19:54:12", "throughput": 666.76, "total_tokens": 7289120} {"current_steps": 5300, "total_steps": 40000, "loss": 1.0985, "lr": 4.786597285123584e-05, "epoch": 0.16964342871775173, "percentage": 13.25, "elapsed_time": "3:02:13", "remaining_time": "19:53:05", "throughput": 667.29, "total_tokens": 7296112} {"current_steps": 5305, "total_steps": 40000, "loss": 1.0194, "lr": 4.7862002159493135e-05, "epoch": 0.1698034696882402, "percentage": 13.26, "elapsed_time": "3:02:15", "remaining_time": "19:51:59", "throughput": 667.79, "total_tokens": 7302720} {"current_steps": 5310, "total_steps": 40000, "loss": 0.9523, "lr": 4.785802794214239e-05, "epoch": 0.16996351065872864, "percentage": 13.28, "elapsed_time": "3:02:17", "remaining_time": "19:50:53", "throughput": 668.34, "total_tokens": 7309920} {"current_steps": 5315, "total_steps": 40000, "loss": 0.9135, "lr": 4.7854050199796495e-05, "epoch": 0.17012355162921708, "percentage": 13.29, "elapsed_time": "3:02:19", "remaining_time": "19:49:47", "throughput": 668.89, "total_tokens": 7317008} {"current_steps": 5320, "total_steps": 40000, "loss": 0.7916, "lr": 4.7850068933068845e-05, "epoch": 0.17028359259970552, "percentage": 13.3, "elapsed_time": "3:02:20", "remaining_time": "19:48:40", "throughput": 669.4, "total_tokens": 7323824} {"current_steps": 5325, "total_steps": 40000, "loss": 0.8504, "lr": 4.7846084142573425e-05, "epoch": 0.17044363357019396, "percentage": 13.31, "elapsed_time": "3:02:22", "remaining_time": "19:47:35", "throughput": 669.92, "total_tokens": 7330592} {"current_steps": 5330, "total_steps": 40000, "loss": 0.5728, "lr": 4.7842095828924725e-05, "epoch": 0.17060367454068243, "percentage": 13.33, "elapsed_time": "3:02:24", "remaining_time": "19:46:29", "throughput": 670.44, "total_tokens": 7337488} {"current_steps": 5335, "total_steps": 40000, "loss": 1.2981, "lr": 4.783810399273779e-05, "epoch": 0.17076371551117087, "percentage": 13.34, "elapsed_time": "3:02:26", "remaining_time": "19:45:23", "throughput": 670.98, "total_tokens": 7344592} {"current_steps": 5340, "total_steps": 40000, "loss": 1.3536, "lr": 4.7834108634628226e-05, "epoch": 0.1709237564816593, "percentage": 13.35, "elapsed_time": "3:02:27", "remaining_time": "19:44:17", "throughput": 671.48, "total_tokens": 7351184} {"current_steps": 5345, "total_steps": 40000, "loss": 0.8288, "lr": 4.783010975521216e-05, "epoch": 0.17108379745214775, "percentage": 13.36, "elapsed_time": "3:02:29", "remaining_time": "19:43:12", "throughput": 671.99, "total_tokens": 7357984} {"current_steps": 5350, "total_steps": 40000, "loss": 1.0396, "lr": 4.782610735510626e-05, "epoch": 0.17124383842263619, "percentage": 13.38, "elapsed_time": "3:02:31", "remaining_time": "19:42:07", "throughput": 672.51, "total_tokens": 7364816} {"current_steps": 5355, "total_steps": 40000, "loss": 0.8326, "lr": 4.782210143492776e-05, "epoch": 0.17140387939312465, "percentage": 13.39, "elapsed_time": "3:02:32", "remaining_time": "19:41:01", "throughput": 673.05, "total_tokens": 7371904} {"current_steps": 5360, "total_steps": 40000, "loss": 0.9038, "lr": 4.781809199529442e-05, "epoch": 0.1715639203636131, "percentage": 13.4, "elapsed_time": "3:02:34", "remaining_time": "19:39:56", "throughput": 673.53, "total_tokens": 7378368} {"current_steps": 5365, "total_steps": 40000, "loss": 0.9667, "lr": 4.781407903682454e-05, "epoch": 0.17172396133410153, "percentage": 13.41, "elapsed_time": "3:02:36", "remaining_time": "19:38:51", "throughput": 674.06, "total_tokens": 7385296} {"current_steps": 5370, "total_steps": 40000, "loss": 0.9116, "lr": 4.781006256013698e-05, "epoch": 0.17188400230458997, "percentage": 13.43, "elapsed_time": "3:02:38", "remaining_time": "19:37:47", "throughput": 674.58, "total_tokens": 7392160} {"current_steps": 5375, "total_steps": 40000, "loss": 0.6621, "lr": 4.7806042565851115e-05, "epoch": 0.1720440432750784, "percentage": 13.44, "elapsed_time": "3:02:39", "remaining_time": "19:36:42", "throughput": 675.08, "total_tokens": 7398864} {"current_steps": 5380, "total_steps": 40000, "loss": 0.7731, "lr": 4.7802019054586895e-05, "epoch": 0.17220408424556685, "percentage": 13.45, "elapsed_time": "3:02:41", "remaining_time": "19:35:37", "throughput": 675.59, "total_tokens": 7405536} {"current_steps": 5385, "total_steps": 40000, "loss": 0.773, "lr": 4.779799202696479e-05, "epoch": 0.17236412521605532, "percentage": 13.46, "elapsed_time": "3:02:43", "remaining_time": "19:34:33", "throughput": 676.09, "total_tokens": 7412288} {"current_steps": 5390, "total_steps": 40000, "loss": 0.795, "lr": 4.779396148360581e-05, "epoch": 0.17252416618654376, "percentage": 13.48, "elapsed_time": "3:02:45", "remaining_time": "19:33:28", "throughput": 676.65, "total_tokens": 7419536} {"current_steps": 5395, "total_steps": 40000, "loss": 0.9271, "lr": 4.7789927425131517e-05, "epoch": 0.1726842071570322, "percentage": 13.49, "elapsed_time": "3:02:46", "remaining_time": "19:32:24", "throughput": 677.19, "total_tokens": 7426672} {"current_steps": 5400, "total_steps": 40000, "loss": 0.7358, "lr": 4.778588985216403e-05, "epoch": 0.17284424812752064, "percentage": 13.5, "elapsed_time": "3:02:48", "remaining_time": "19:31:20", "throughput": 677.67, "total_tokens": 7433136} {"current_steps": 5400, "total_steps": 40000, "eval_loss": 0.8421432375907898, "epoch": 0.17284424812752064, "percentage": 13.5, "elapsed_time": "3:08:36", "remaining_time": "20:08:27", "throughput": 656.85, "total_tokens": 7433136} {"current_steps": 5405, "total_steps": 40000, "loss": 0.7623, "lr": 4.778184876532598e-05, "epoch": 0.17300428909800908, "percentage": 13.51, "elapsed_time": "3:08:39", "remaining_time": "20:07:31", "throughput": 657.26, "total_tokens": 7439920} {"current_steps": 5410, "total_steps": 40000, "loss": 0.7162, "lr": 4.7777804165240556e-05, "epoch": 0.17316433006849755, "percentage": 13.53, "elapsed_time": "3:08:41", "remaining_time": "20:06:25", "throughput": 657.73, "total_tokens": 7446432} {"current_steps": 5415, "total_steps": 40000, "loss": 0.8556, "lr": 4.7773756052531485e-05, "epoch": 0.17332437103898599, "percentage": 13.54, "elapsed_time": "3:08:43", "remaining_time": "20:05:19", "throughput": 658.27, "total_tokens": 7453632} {"current_steps": 5420, "total_steps": 40000, "loss": 0.5983, "lr": 4.7769704427823035e-05, "epoch": 0.17348441200947443, "percentage": 13.55, "elapsed_time": "3:08:44", "remaining_time": "20:04:13", "throughput": 658.74, "total_tokens": 7460160} {"current_steps": 5425, "total_steps": 40000, "loss": 0.6103, "lr": 4.776564929174003e-05, "epoch": 0.17364445297996287, "percentage": 13.56, "elapsed_time": "3:08:46", "remaining_time": "20:03:07", "throughput": 659.24, "total_tokens": 7466928} {"current_steps": 5430, "total_steps": 40000, "loss": 1.2223, "lr": 4.7761590644907806e-05, "epoch": 0.1738044939504513, "percentage": 13.58, "elapsed_time": "3:08:48", "remaining_time": "20:02:01", "throughput": 659.74, "total_tokens": 7473680} {"current_steps": 5435, "total_steps": 40000, "loss": 0.7723, "lr": 4.7757528487952263e-05, "epoch": 0.17396453492093977, "percentage": 13.59, "elapsed_time": "3:08:50", "remaining_time": "20:00:55", "throughput": 660.26, "total_tokens": 7480784} {"current_steps": 5440, "total_steps": 40000, "loss": 0.8385, "lr": 4.7753462821499836e-05, "epoch": 0.1741245758914282, "percentage": 13.6, "elapsed_time": "3:08:51", "remaining_time": "19:59:50", "throughput": 660.76, "total_tokens": 7487552} {"current_steps": 5445, "total_steps": 40000, "loss": 0.7096, "lr": 4.774939364617751e-05, "epoch": 0.17428461686191665, "percentage": 13.61, "elapsed_time": "3:08:53", "remaining_time": "19:58:44", "throughput": 661.25, "total_tokens": 7494240} {"current_steps": 5450, "total_steps": 40000, "loss": 1.0214, "lr": 4.7745320962612795e-05, "epoch": 0.1744446578324051, "percentage": 13.63, "elapsed_time": "3:08:55", "remaining_time": "19:57:39", "throughput": 661.76, "total_tokens": 7501216} {"current_steps": 5455, "total_steps": 40000, "loss": 0.7459, "lr": 4.7741244771433756e-05, "epoch": 0.17460469880289353, "percentage": 13.64, "elapsed_time": "3:08:56", "remaining_time": "19:56:33", "throughput": 662.26, "total_tokens": 7508064} {"current_steps": 5460, "total_steps": 40000, "loss": 0.7902, "lr": 4.7737165073268985e-05, "epoch": 0.174764739773382, "percentage": 13.65, "elapsed_time": "3:08:58", "remaining_time": "19:55:28", "throughput": 662.78, "total_tokens": 7515104} {"current_steps": 5465, "total_steps": 40000, "loss": 0.651, "lr": 4.7733081868747626e-05, "epoch": 0.17492478074387044, "percentage": 13.66, "elapsed_time": "3:09:00", "remaining_time": "19:54:23", "throughput": 663.29, "total_tokens": 7522016} {"current_steps": 5470, "total_steps": 40000, "loss": 0.9947, "lr": 4.772899515849936e-05, "epoch": 0.17508482171435888, "percentage": 13.68, "elapsed_time": "3:09:02", "remaining_time": "19:53:18", "throughput": 663.8, "total_tokens": 7528928} {"current_steps": 5475, "total_steps": 40000, "loss": 1.0114, "lr": 4.7724904943154414e-05, "epoch": 0.17524486268484732, "percentage": 13.69, "elapsed_time": "3:09:03", "remaining_time": "19:52:14", "throughput": 664.31, "total_tokens": 7535888} {"current_steps": 5480, "total_steps": 40000, "loss": 1.0416, "lr": 4.772081122334354e-05, "epoch": 0.17540490365533576, "percentage": 13.7, "elapsed_time": "3:09:05", "remaining_time": "19:51:09", "throughput": 664.83, "total_tokens": 7542960} {"current_steps": 5485, "total_steps": 40000, "loss": 0.9306, "lr": 4.771671399969806e-05, "epoch": 0.1755649446258242, "percentage": 13.71, "elapsed_time": "3:09:07", "remaining_time": "19:50:04", "throughput": 665.34, "total_tokens": 7549888} {"current_steps": 5490, "total_steps": 40000, "loss": 0.7453, "lr": 4.7712613272849794e-05, "epoch": 0.17572498559631267, "percentage": 13.73, "elapsed_time": "3:09:09", "remaining_time": "19:49:00", "throughput": 665.88, "total_tokens": 7557200} {"current_steps": 5495, "total_steps": 40000, "loss": 0.6821, "lr": 4.770850904343114e-05, "epoch": 0.1758850265668011, "percentage": 13.74, "elapsed_time": "3:09:10", "remaining_time": "19:47:55", "throughput": 666.41, "total_tokens": 7564336} {"current_steps": 5500, "total_steps": 40000, "loss": 0.8122, "lr": 4.770440131207502e-05, "epoch": 0.17604506753728955, "percentage": 13.75, "elapsed_time": "3:09:12", "remaining_time": "19:46:51", "throughput": 666.91, "total_tokens": 7571184} {"current_steps": 5505, "total_steps": 40000, "loss": 0.8697, "lr": 4.7700290079414896e-05, "epoch": 0.17620510850777799, "percentage": 13.76, "elapsed_time": "3:09:14", "remaining_time": "19:45:47", "throughput": 667.42, "total_tokens": 7578048} {"current_steps": 5510, "total_steps": 40000, "loss": 0.6653, "lr": 4.769617534608477e-05, "epoch": 0.17636514947826643, "percentage": 13.78, "elapsed_time": "3:09:16", "remaining_time": "19:44:43", "throughput": 667.91, "total_tokens": 7584864} {"current_steps": 5515, "total_steps": 40000, "loss": 0.7491, "lr": 4.7692057112719193e-05, "epoch": 0.1765251904487549, "percentage": 13.79, "elapsed_time": "3:09:17", "remaining_time": "19:43:39", "throughput": 668.44, "total_tokens": 7592016} {"current_steps": 5520, "total_steps": 40000, "loss": 0.6852, "lr": 4.7687935379953234e-05, "epoch": 0.17668523141924333, "percentage": 13.8, "elapsed_time": "3:09:19", "remaining_time": "19:42:35", "throughput": 668.92, "total_tokens": 7598624} {"current_steps": 5525, "total_steps": 40000, "loss": 0.7889, "lr": 4.7683810148422534e-05, "epoch": 0.17684527238973177, "percentage": 13.81, "elapsed_time": "3:09:21", "remaining_time": "19:41:32", "throughput": 669.44, "total_tokens": 7605648} {"current_steps": 5530, "total_steps": 40000, "loss": 0.8831, "lr": 4.767968141876324e-05, "epoch": 0.1770053133602202, "percentage": 13.83, "elapsed_time": "3:09:22", "remaining_time": "19:40:28", "throughput": 669.95, "total_tokens": 7612608} {"current_steps": 5535, "total_steps": 40000, "loss": 0.8026, "lr": 4.767554919161207e-05, "epoch": 0.17716535433070865, "percentage": 13.84, "elapsed_time": "3:09:24", "remaining_time": "19:39:25", "throughput": 670.43, "total_tokens": 7619264} {"current_steps": 5540, "total_steps": 40000, "loss": 0.7099, "lr": 4.767141346760624e-05, "epoch": 0.17732539530119712, "percentage": 13.85, "elapsed_time": "3:09:26", "remaining_time": "19:38:21", "throughput": 670.92, "total_tokens": 7625936} {"current_steps": 5545, "total_steps": 40000, "loss": 0.922, "lr": 4.766727424738356e-05, "epoch": 0.17748543627168556, "percentage": 13.86, "elapsed_time": "3:09:28", "remaining_time": "19:37:18", "throughput": 671.44, "total_tokens": 7633008} {"current_steps": 5550, "total_steps": 40000, "loss": 0.812, "lr": 4.7663131531582325e-05, "epoch": 0.177645477242174, "percentage": 13.88, "elapsed_time": "3:09:29", "remaining_time": "19:36:15", "throughput": 671.91, "total_tokens": 7639568} {"current_steps": 5555, "total_steps": 40000, "loss": 0.8751, "lr": 4.765898532084142e-05, "epoch": 0.17780551821266244, "percentage": 13.89, "elapsed_time": "3:09:31", "remaining_time": "19:35:12", "throughput": 672.4, "total_tokens": 7646304} {"current_steps": 5560, "total_steps": 40000, "loss": 0.7798, "lr": 4.765483561580022e-05, "epoch": 0.17796555918315088, "percentage": 13.9, "elapsed_time": "3:09:33", "remaining_time": "19:34:09", "throughput": 672.9, "total_tokens": 7653152} {"current_steps": 5565, "total_steps": 40000, "loss": 0.5996, "lr": 4.7650682417098666e-05, "epoch": 0.17812560015363932, "percentage": 13.91, "elapsed_time": "3:09:35", "remaining_time": "19:33:06", "throughput": 673.43, "total_tokens": 7660320} {"current_steps": 5570, "total_steps": 40000, "loss": 0.8652, "lr": 4.7646525725377244e-05, "epoch": 0.17828564112412779, "percentage": 13.93, "elapsed_time": "3:09:36", "remaining_time": "19:32:04", "throughput": 673.88, "total_tokens": 7666672} {"current_steps": 5575, "total_steps": 40000, "loss": 0.8952, "lr": 4.764236554127696e-05, "epoch": 0.17844568209461623, "percentage": 13.94, "elapsed_time": "3:09:38", "remaining_time": "19:31:01", "throughput": 674.41, "total_tokens": 7673840} {"current_steps": 5580, "total_steps": 40000, "loss": 0.6966, "lr": 4.7638201865439356e-05, "epoch": 0.17860572306510467, "percentage": 13.95, "elapsed_time": "3:09:40", "remaining_time": "19:29:59", "throughput": 674.9, "total_tokens": 7680544} {"current_steps": 5585, "total_steps": 40000, "loss": 0.8882, "lr": 4.7634034698506545e-05, "epoch": 0.1787657640355931, "percentage": 13.96, "elapsed_time": "3:09:42", "remaining_time": "19:28:56", "throughput": 675.4, "total_tokens": 7687488} {"current_steps": 5590, "total_steps": 40000, "loss": 1.0576, "lr": 4.762986404112115e-05, "epoch": 0.17892580500608155, "percentage": 13.98, "elapsed_time": "3:09:43", "remaining_time": "19:27:54", "throughput": 675.89, "total_tokens": 7694160} {"current_steps": 5595, "total_steps": 40000, "loss": 0.6286, "lr": 4.762568989392633e-05, "epoch": 0.17908584597657, "percentage": 13.99, "elapsed_time": "3:09:45", "remaining_time": "19:26:52", "throughput": 676.39, "total_tokens": 7701120} {"current_steps": 5600, "total_steps": 40000, "loss": 0.9727, "lr": 4.76215122575658e-05, "epoch": 0.17924588694705845, "percentage": 14.0, "elapsed_time": "3:09:47", "remaining_time": "19:25:50", "throughput": 676.87, "total_tokens": 7707776} {"current_steps": 5600, "total_steps": 40000, "eval_loss": 0.8378154039382935, "epoch": 0.17924588694705845, "percentage": 14.0, "elapsed_time": "3:15:35", "remaining_time": "20:01:28", "throughput": 656.8, "total_tokens": 7707776} {"current_steps": 5605, "total_steps": 40000, "loss": 0.9152, "lr": 4.7617331132683795e-05, "epoch": 0.1794059279175469, "percentage": 14.01, "elapsed_time": "3:15:38", "remaining_time": "20:00:34", "throughput": 657.17, "total_tokens": 7714304} {"current_steps": 5610, "total_steps": 40000, "loss": 0.8206, "lr": 4.7613146519925105e-05, "epoch": 0.17956596888803533, "percentage": 14.03, "elapsed_time": "3:15:40", "remaining_time": "19:59:30", "throughput": 657.65, "total_tokens": 7721120} {"current_steps": 5615, "total_steps": 40000, "loss": 0.7291, "lr": 4.7608958419935045e-05, "epoch": 0.17972600985852377, "percentage": 14.04, "elapsed_time": "3:15:42", "remaining_time": "19:58:26", "throughput": 658.16, "total_tokens": 7728240} {"current_steps": 5620, "total_steps": 40000, "loss": 0.7853, "lr": 4.760476683335948e-05, "epoch": 0.17988605082901224, "percentage": 14.05, "elapsed_time": "3:15:43", "remaining_time": "19:57:22", "throughput": 658.63, "total_tokens": 7734864} {"current_steps": 5625, "total_steps": 40000, "loss": 0.7926, "lr": 4.760057176084479e-05, "epoch": 0.18004609179950068, "percentage": 14.06, "elapsed_time": "3:15:45", "remaining_time": "19:56:18", "throughput": 659.09, "total_tokens": 7741472} {"current_steps": 5630, "total_steps": 40000, "loss": 0.7177, "lr": 4.759637320303793e-05, "epoch": 0.18020613276998912, "percentage": 14.07, "elapsed_time": "3:15:47", "remaining_time": "19:55:15", "throughput": 659.56, "total_tokens": 7748064} {"current_steps": 5635, "total_steps": 40000, "loss": 0.941, "lr": 4.759217116058635e-05, "epoch": 0.18036617374047756, "percentage": 14.09, "elapsed_time": "3:15:49", "remaining_time": "19:54:11", "throughput": 660.03, "total_tokens": 7754784} {"current_steps": 5640, "total_steps": 40000, "loss": 0.8357, "lr": 4.758796563413807e-05, "epoch": 0.180526214710966, "percentage": 14.1, "elapsed_time": "3:15:50", "remaining_time": "19:53:08", "throughput": 660.56, "total_tokens": 7762080} {"current_steps": 5645, "total_steps": 40000, "loss": 0.8324, "lr": 4.758375662434163e-05, "epoch": 0.18068625568145444, "percentage": 14.11, "elapsed_time": "3:15:52", "remaining_time": "19:52:05", "throughput": 661.04, "total_tokens": 7768944} {"current_steps": 5650, "total_steps": 40000, "loss": 1.1608, "lr": 4.7579544131846114e-05, "epoch": 0.1808462966519429, "percentage": 14.12, "elapsed_time": "3:15:54", "remaining_time": "19:51:01", "throughput": 661.55, "total_tokens": 7776080} {"current_steps": 5655, "total_steps": 40000, "loss": 0.6852, "lr": 4.757532815730114e-05, "epoch": 0.18100633762243135, "percentage": 14.14, "elapsed_time": "3:15:56", "remaining_time": "19:49:58", "throughput": 662.05, "total_tokens": 7783024} {"current_steps": 5660, "total_steps": 40000, "loss": 0.5888, "lr": 4.7571108701356865e-05, "epoch": 0.18116637859291979, "percentage": 14.15, "elapsed_time": "3:15:57", "remaining_time": "19:48:55", "throughput": 662.51, "total_tokens": 7789680} {"current_steps": 5665, "total_steps": 40000, "loss": 0.7788, "lr": 4.756688576466398e-05, "epoch": 0.18132641956340823, "percentage": 14.16, "elapsed_time": "3:15:59", "remaining_time": "19:47:53", "throughput": 663.01, "total_tokens": 7796656} {"current_steps": 5670, "total_steps": 40000, "loss": 0.6315, "lr": 4.756265934787372e-05, "epoch": 0.18148646053389667, "percentage": 14.17, "elapsed_time": "3:16:01", "remaining_time": "19:46:50", "throughput": 663.53, "total_tokens": 7803968} {"current_steps": 5675, "total_steps": 40000, "loss": 0.9268, "lr": 4.755842945163785e-05, "epoch": 0.18164650150438513, "percentage": 14.19, "elapsed_time": "3:16:02", "remaining_time": "19:45:47", "throughput": 664.08, "total_tokens": 7811536} {"current_steps": 5680, "total_steps": 40000, "loss": 0.8759, "lr": 4.755419607660867e-05, "epoch": 0.18180654247487357, "percentage": 14.2, "elapsed_time": "3:16:04", "remaining_time": "19:44:45", "throughput": 664.58, "total_tokens": 7818656} {"current_steps": 5685, "total_steps": 40000, "loss": 1.0003, "lr": 4.7549959223439016e-05, "epoch": 0.181966583445362, "percentage": 14.21, "elapsed_time": "3:16:06", "remaining_time": "19:43:43", "throughput": 665.05, "total_tokens": 7825328} {"current_steps": 5690, "total_steps": 40000, "loss": 0.9524, "lr": 4.754571889278228e-05, "epoch": 0.18212662441585045, "percentage": 14.22, "elapsed_time": "3:16:08", "remaining_time": "19:42:40", "throughput": 665.55, "total_tokens": 7832288} {"current_steps": 5695, "total_steps": 40000, "loss": 0.7792, "lr": 4.754147508529235e-05, "epoch": 0.1822866653863389, "percentage": 14.24, "elapsed_time": "3:16:09", "remaining_time": "19:41:38", "throughput": 666.01, "total_tokens": 7838832} {"current_steps": 5700, "total_steps": 40000, "loss": 0.7062, "lr": 4.75372278016237e-05, "epoch": 0.18244670635682736, "percentage": 14.25, "elapsed_time": "3:16:11", "remaining_time": "19:40:36", "throughput": 666.5, "total_tokens": 7845840} {"current_steps": 5705, "total_steps": 40000, "loss": 0.6663, "lr": 4.753297704243129e-05, "epoch": 0.1826067473273158, "percentage": 14.26, "elapsed_time": "3:16:13", "remaining_time": "19:39:34", "throughput": 666.98, "total_tokens": 7852592} {"current_steps": 5710, "total_steps": 40000, "loss": 0.7282, "lr": 4.752872280837066e-05, "epoch": 0.18276678829780424, "percentage": 14.27, "elapsed_time": "3:16:15", "remaining_time": "19:38:32", "throughput": 667.5, "total_tokens": 7859856} {"current_steps": 5715, "total_steps": 40000, "loss": 0.7708, "lr": 4.752446510009786e-05, "epoch": 0.18292682926829268, "percentage": 14.29, "elapsed_time": "3:16:16", "remaining_time": "19:37:30", "throughput": 668.02, "total_tokens": 7867136} {"current_steps": 5720, "total_steps": 40000, "loss": 0.9108, "lr": 4.7520203918269476e-05, "epoch": 0.18308687023878112, "percentage": 14.3, "elapsed_time": "3:16:18", "remaining_time": "19:36:29", "throughput": 668.52, "total_tokens": 7874240} {"current_steps": 5725, "total_steps": 40000, "loss": 0.8569, "lr": 4.751593926354265e-05, "epoch": 0.1832469112092696, "percentage": 14.31, "elapsed_time": "3:16:20", "remaining_time": "19:35:27", "throughput": 669.01, "total_tokens": 7881200} {"current_steps": 5730, "total_steps": 40000, "loss": 0.8277, "lr": 4.751167113657503e-05, "epoch": 0.18340695217975803, "percentage": 14.32, "elapsed_time": "3:16:22", "remaining_time": "19:34:26", "throughput": 669.51, "total_tokens": 7888192} {"current_steps": 5735, "total_steps": 40000, "loss": 0.5771, "lr": 4.7507399538024834e-05, "epoch": 0.18356699315024647, "percentage": 14.34, "elapsed_time": "3:16:23", "remaining_time": "19:33:24", "throughput": 669.98, "total_tokens": 7894912} {"current_steps": 5740, "total_steps": 40000, "loss": 0.8289, "lr": 4.750312446855077e-05, "epoch": 0.1837270341207349, "percentage": 14.35, "elapsed_time": "3:16:25", "remaining_time": "19:32:23", "throughput": 670.49, "total_tokens": 7902048} {"current_steps": 5745, "total_steps": 40000, "loss": 0.8102, "lr": 4.749884592881212e-05, "epoch": 0.18388707509122335, "percentage": 14.36, "elapsed_time": "3:16:27", "remaining_time": "19:31:22", "throughput": 670.95, "total_tokens": 7908720} {"current_steps": 5750, "total_steps": 40000, "loss": 0.7836, "lr": 4.74945639194687e-05, "epoch": 0.18404711606171179, "percentage": 14.37, "elapsed_time": "3:16:29", "remaining_time": "19:30:21", "throughput": 671.43, "total_tokens": 7915488} {"current_steps": 5755, "total_steps": 40000, "loss": 0.7162, "lr": 4.749027844118083e-05, "epoch": 0.18420715703220025, "percentage": 14.39, "elapsed_time": "3:16:30", "remaining_time": "19:29:20", "throughput": 671.91, "total_tokens": 7922384} {"current_steps": 5760, "total_steps": 40000, "loss": 1.0238, "lr": 4.7485989494609395e-05, "epoch": 0.1843671980026887, "percentage": 14.4, "elapsed_time": "3:16:32", "remaining_time": "19:28:19", "throughput": 672.41, "total_tokens": 7929424} {"current_steps": 5765, "total_steps": 40000, "loss": 0.8184, "lr": 4.748169708041581e-05, "epoch": 0.18452723897317713, "percentage": 14.41, "elapsed_time": "3:16:34", "remaining_time": "19:27:19", "throughput": 672.9, "total_tokens": 7936352} {"current_steps": 5770, "total_steps": 40000, "loss": 0.8332, "lr": 4.7477401199262004e-05, "epoch": 0.18468727994366557, "percentage": 14.42, "elapsed_time": "3:16:35", "remaining_time": "19:26:18", "throughput": 673.39, "total_tokens": 7943264} {"current_steps": 5775, "total_steps": 40000, "loss": 0.7034, "lr": 4.747310185181048e-05, "epoch": 0.184847320914154, "percentage": 14.44, "elapsed_time": "3:16:37", "remaining_time": "19:25:17", "throughput": 673.9, "total_tokens": 7950480} {"current_steps": 5780, "total_steps": 40000, "loss": 0.9192, "lr": 4.746879903872422e-05, "epoch": 0.18500736188464248, "percentage": 14.45, "elapsed_time": "3:16:39", "remaining_time": "19:24:17", "throughput": 674.4, "total_tokens": 7957488} {"current_steps": 5785, "total_steps": 40000, "loss": 0.773, "lr": 4.746449276066679e-05, "epoch": 0.18516740285513092, "percentage": 14.46, "elapsed_time": "3:16:41", "remaining_time": "19:23:17", "throughput": 674.88, "total_tokens": 7964352} {"current_steps": 5790, "total_steps": 40000, "loss": 0.6683, "lr": 4.746018301830227e-05, "epoch": 0.18532744382561936, "percentage": 14.47, "elapsed_time": "3:16:42", "remaining_time": "19:22:17", "throughput": 675.35, "total_tokens": 7971136} {"current_steps": 5795, "total_steps": 40000, "loss": 0.8203, "lr": 4.7455869812295275e-05, "epoch": 0.1854874847961078, "percentage": 14.49, "elapsed_time": "3:16:44", "remaining_time": "19:21:17", "throughput": 675.87, "total_tokens": 7978432} {"current_steps": 5800, "total_steps": 40000, "loss": 0.6727, "lr": 4.7451553143310964e-05, "epoch": 0.18564752576659624, "percentage": 14.5, "elapsed_time": "3:16:46", "remaining_time": "19:20:17", "throughput": 676.37, "total_tokens": 7985472} {"current_steps": 5800, "total_steps": 40000, "eval_loss": 0.8367400765419006, "epoch": 0.18564752576659624, "percentage": 14.5, "elapsed_time": "3:22:34", "remaining_time": "19:54:31", "throughput": 656.98, "total_tokens": 7985472} {"current_steps": 5805, "total_steps": 40000, "loss": 0.8271, "lr": 4.744723301201501e-05, "epoch": 0.1858075667370847, "percentage": 14.51, "elapsed_time": "3:22:38", "remaining_time": "19:53:38", "throughput": 657.35, "total_tokens": 7992160} {"current_steps": 5810, "total_steps": 40000, "loss": 0.8709, "lr": 4.744290941907364e-05, "epoch": 0.18596760770757315, "percentage": 14.52, "elapsed_time": "3:22:39", "remaining_time": "19:52:36", "throughput": 657.89, "total_tokens": 7999776} {"current_steps": 5815, "total_steps": 40000, "loss": 0.8588, "lr": 4.7438582365153594e-05, "epoch": 0.18612764867806159, "percentage": 14.54, "elapsed_time": "3:22:41", "remaining_time": "19:51:34", "throughput": 658.37, "total_tokens": 8006816} {"current_steps": 5820, "total_steps": 40000, "loss": 0.8248, "lr": 4.743425185092217e-05, "epoch": 0.18628768964855003, "percentage": 14.55, "elapsed_time": "3:22:43", "remaining_time": "19:50:33", "throughput": 658.84, "total_tokens": 8013632} {"current_steps": 5825, "total_steps": 40000, "loss": 1.0099, "lr": 4.742991787704719e-05, "epoch": 0.18644773061903847, "percentage": 14.56, "elapsed_time": "3:22:45", "remaining_time": "19:49:31", "throughput": 659.32, "total_tokens": 8020672} {"current_steps": 5830, "total_steps": 40000, "loss": 0.6036, "lr": 4.7425580444196994e-05, "epoch": 0.1866077715895269, "percentage": 14.57, "elapsed_time": "3:22:46", "remaining_time": "19:48:30", "throughput": 659.78, "total_tokens": 8027376} {"current_steps": 5835, "total_steps": 40000, "loss": 0.6589, "lr": 4.742123955304048e-05, "epoch": 0.18676781256001537, "percentage": 14.59, "elapsed_time": "3:22:48", "remaining_time": "19:47:28", "throughput": 660.29, "total_tokens": 8034704} {"current_steps": 5840, "total_steps": 40000, "loss": 0.6655, "lr": 4.741689520424706e-05, "epoch": 0.1869278535305038, "percentage": 14.6, "elapsed_time": "3:22:50", "remaining_time": "19:46:27", "throughput": 660.74, "total_tokens": 8041392} {"current_steps": 5845, "total_steps": 40000, "loss": 1.0244, "lr": 4.741254739848669e-05, "epoch": 0.18708789450099225, "percentage": 14.61, "elapsed_time": "3:22:51", "remaining_time": "19:45:26", "throughput": 661.22, "total_tokens": 8048400} {"current_steps": 5850, "total_steps": 40000, "loss": 0.8189, "lr": 4.740819613642987e-05, "epoch": 0.1872479354714807, "percentage": 14.62, "elapsed_time": "3:22:53", "remaining_time": "19:44:25", "throughput": 661.74, "total_tokens": 8055808} {"current_steps": 5855, "total_steps": 40000, "loss": 0.8418, "lr": 4.74038414187476e-05, "epoch": 0.18740797644196913, "percentage": 14.64, "elapsed_time": "3:22:55", "remaining_time": "19:43:24", "throughput": 662.19, "total_tokens": 8062480} {"current_steps": 5860, "total_steps": 40000, "loss": 0.627, "lr": 4.739948324611144e-05, "epoch": 0.1875680174124576, "percentage": 14.65, "elapsed_time": "3:22:57", "remaining_time": "19:42:23", "throughput": 662.66, "total_tokens": 8069376} {"current_steps": 5865, "total_steps": 40000, "loss": 0.7128, "lr": 4.7395121619193465e-05, "epoch": 0.18772805838294604, "percentage": 14.66, "elapsed_time": "3:22:58", "remaining_time": "19:41:22", "throughput": 663.12, "total_tokens": 8076096} {"current_steps": 5870, "total_steps": 40000, "loss": 0.9497, "lr": 4.7390756538666313e-05, "epoch": 0.18788809935343448, "percentage": 14.67, "elapsed_time": "3:23:00", "remaining_time": "19:40:22", "throughput": 663.58, "total_tokens": 8082912} {"current_steps": 5875, "total_steps": 40000, "loss": 0.7735, "lr": 4.738638800520311e-05, "epoch": 0.18804814032392292, "percentage": 14.69, "elapsed_time": "3:23:02", "remaining_time": "19:39:21", "throughput": 664.04, "total_tokens": 8089568} {"current_steps": 5880, "total_steps": 40000, "loss": 0.5363, "lr": 4.738201601947757e-05, "epoch": 0.18820818129441136, "percentage": 14.7, "elapsed_time": "3:23:04", "remaining_time": "19:38:21", "throughput": 664.5, "total_tokens": 8096416} {"current_steps": 5885, "total_steps": 40000, "loss": 0.9523, "lr": 4.7377640582163876e-05, "epoch": 0.18836822226489983, "percentage": 14.71, "elapsed_time": "3:23:05", "remaining_time": "19:37:20", "throughput": 664.96, "total_tokens": 8103088} {"current_steps": 5890, "total_steps": 40000, "loss": 0.7168, "lr": 4.7373261693936786e-05, "epoch": 0.18852826323538827, "percentage": 14.72, "elapsed_time": "3:23:07", "remaining_time": "19:36:20", "throughput": 665.39, "total_tokens": 8109520} {"current_steps": 5895, "total_steps": 40000, "loss": 0.7956, "lr": 4.7368879355471595e-05, "epoch": 0.1886883042058767, "percentage": 14.74, "elapsed_time": "3:23:09", "remaining_time": "19:35:20", "throughput": 665.84, "total_tokens": 8116176} {"current_steps": 5900, "total_steps": 40000, "loss": 0.8102, "lr": 4.736449356744409e-05, "epoch": 0.18884834517636515, "percentage": 14.75, "elapsed_time": "3:23:11", "remaining_time": "19:34:20", "throughput": 666.31, "total_tokens": 8123088} {"current_steps": 5905, "total_steps": 40000, "loss": 0.8797, "lr": 4.736010433053064e-05, "epoch": 0.18900838614685359, "percentage": 14.76, "elapsed_time": "3:23:12", "remaining_time": "19:33:20", "throughput": 666.78, "total_tokens": 8129984} {"current_steps": 5910, "total_steps": 40000, "loss": 0.8945, "lr": 4.73557116454081e-05, "epoch": 0.18916842711734205, "percentage": 14.77, "elapsed_time": "3:23:14", "remaining_time": "19:32:20", "throughput": 667.27, "total_tokens": 8137136} {"current_steps": 5915, "total_steps": 40000, "loss": 0.7281, "lr": 4.735131551275389e-05, "epoch": 0.1893284680878305, "percentage": 14.79, "elapsed_time": "3:23:16", "remaining_time": "19:31:20", "throughput": 667.72, "total_tokens": 8143760} {"current_steps": 5920, "total_steps": 40000, "loss": 0.763, "lr": 4.734691593324594e-05, "epoch": 0.18948850905831893, "percentage": 14.8, "elapsed_time": "3:23:18", "remaining_time": "19:30:21", "throughput": 668.14, "total_tokens": 8150048} {"current_steps": 5925, "total_steps": 40000, "loss": 0.9735, "lr": 4.734251290756272e-05, "epoch": 0.18964855002880737, "percentage": 14.81, "elapsed_time": "3:23:19", "remaining_time": "19:29:21", "throughput": 668.61, "total_tokens": 8156896} {"current_steps": 5930, "total_steps": 40000, "loss": 0.8747, "lr": 4.7338106436383246e-05, "epoch": 0.1898085909992958, "percentage": 14.82, "elapsed_time": "3:23:21", "remaining_time": "19:28:22", "throughput": 669.06, "total_tokens": 8163584} {"current_steps": 5935, "total_steps": 40000, "loss": 1.0622, "lr": 4.733369652038703e-05, "epoch": 0.18996863196978425, "percentage": 14.84, "elapsed_time": "3:23:23", "remaining_time": "19:27:22", "throughput": 669.52, "total_tokens": 8170352} {"current_steps": 5940, "total_steps": 40000, "loss": 0.8747, "lr": 4.7329283160254156e-05, "epoch": 0.19012867294027272, "percentage": 14.85, "elapsed_time": "3:23:24", "remaining_time": "19:26:23", "throughput": 670.0, "total_tokens": 8177392} {"current_steps": 5945, "total_steps": 40000, "loss": 0.7384, "lr": 4.732486635666521e-05, "epoch": 0.19028871391076116, "percentage": 14.86, "elapsed_time": "3:23:26", "remaining_time": "19:25:24", "throughput": 670.5, "total_tokens": 8184576} {"current_steps": 5950, "total_steps": 40000, "loss": 0.8357, "lr": 4.732044611030132e-05, "epoch": 0.1904487548812496, "percentage": 14.88, "elapsed_time": "3:23:28", "remaining_time": "19:24:25", "throughput": 670.94, "total_tokens": 8191200} {"current_steps": 5955, "total_steps": 40000, "loss": 0.7353, "lr": 4.731602242184414e-05, "epoch": 0.19060879585173804, "percentage": 14.89, "elapsed_time": "3:23:30", "remaining_time": "19:23:26", "throughput": 671.42, "total_tokens": 8198144} {"current_steps": 5960, "total_steps": 40000, "loss": 0.6143, "lr": 4.7311595291975864e-05, "epoch": 0.19076883682222648, "percentage": 14.9, "elapsed_time": "3:23:31", "remaining_time": "19:22:27", "throughput": 671.86, "total_tokens": 8204704} {"current_steps": 5965, "total_steps": 40000, "loss": 0.8201, "lr": 4.7307164721379216e-05, "epoch": 0.19092887779271495, "percentage": 14.91, "elapsed_time": "3:23:33", "remaining_time": "19:21:28", "throughput": 672.33, "total_tokens": 8211584} {"current_steps": 5970, "total_steps": 40000, "loss": 0.6302, "lr": 4.730273071073743e-05, "epoch": 0.19108891876320339, "percentage": 14.92, "elapsed_time": "3:23:35", "remaining_time": "19:20:29", "throughput": 672.78, "total_tokens": 8218336} {"current_steps": 5975, "total_steps": 40000, "loss": 0.4612, "lr": 4.729829326073429e-05, "epoch": 0.19124895973369183, "percentage": 14.94, "elapsed_time": "3:23:37", "remaining_time": "19:19:31", "throughput": 673.27, "total_tokens": 8225392} {"current_steps": 5980, "total_steps": 40000, "loss": 0.8262, "lr": 4.7293852372054126e-05, "epoch": 0.19140900070418027, "percentage": 14.95, "elapsed_time": "3:23:38", "remaining_time": "19:18:32", "throughput": 673.75, "total_tokens": 8232464} {"current_steps": 5985, "total_steps": 40000, "loss": 0.9121, "lr": 4.728940804538176e-05, "epoch": 0.1915690416746687, "percentage": 14.96, "elapsed_time": "3:23:40", "remaining_time": "19:17:34", "throughput": 674.21, "total_tokens": 8239216} {"current_steps": 5990, "total_steps": 40000, "loss": 0.7943, "lr": 4.7284960281402556e-05, "epoch": 0.19172908264515717, "percentage": 14.97, "elapsed_time": "3:23:42", "remaining_time": "19:16:35", "throughput": 674.64, "total_tokens": 8245696} {"current_steps": 5995, "total_steps": 40000, "loss": 0.6839, "lr": 4.728050908080244e-05, "epoch": 0.1918891236156456, "percentage": 14.99, "elapsed_time": "3:23:44", "remaining_time": "19:15:37", "throughput": 675.1, "total_tokens": 8252432} {"current_steps": 6000, "total_steps": 40000, "loss": 0.7569, "lr": 4.727605444426782e-05, "epoch": 0.19204916458613405, "percentage": 15.0, "elapsed_time": "3:23:45", "remaining_time": "19:14:39", "throughput": 675.58, "total_tokens": 8259552} {"current_steps": 6000, "total_steps": 40000, "eval_loss": 0.8326534628868103, "epoch": 0.19204916458613405, "percentage": 15.0, "elapsed_time": "3:29:33", "remaining_time": "19:47:31", "throughput": 656.89, "total_tokens": 8259552} {"current_steps": 6005, "total_steps": 40000, "loss": 0.6173, "lr": 4.727159637248567e-05, "epoch": 0.1922092055566225, "percentage": 15.01, "elapsed_time": "3:29:37", "remaining_time": "19:46:40", "throughput": 657.25, "total_tokens": 8266208} {"current_steps": 6010, "total_steps": 40000, "loss": 0.9877, "lr": 4.7267134866143474e-05, "epoch": 0.19236924652711093, "percentage": 15.02, "elapsed_time": "3:29:38", "remaining_time": "19:45:40", "throughput": 657.71, "total_tokens": 8273216} {"current_steps": 6015, "total_steps": 40000, "loss": 0.7087, "lr": 4.726266992592926e-05, "epoch": 0.19252928749759937, "percentage": 15.04, "elapsed_time": "3:29:40", "remaining_time": "19:44:40", "throughput": 658.16, "total_tokens": 8280032} {"current_steps": 6020, "total_steps": 40000, "loss": 0.8019, "lr": 4.725820155253157e-05, "epoch": 0.19268932846808784, "percentage": 15.05, "elapsed_time": "3:29:42", "remaining_time": "19:43:40", "throughput": 658.62, "total_tokens": 8286928} {"current_steps": 6025, "total_steps": 40000, "loss": 0.9013, "lr": 4.725372974663948e-05, "epoch": 0.19284936943857628, "percentage": 15.06, "elapsed_time": "3:29:43", "remaining_time": "19:42:41", "throughput": 659.09, "total_tokens": 8293968} {"current_steps": 6030, "total_steps": 40000, "loss": 0.631, "lr": 4.724925450894262e-05, "epoch": 0.19300941040906472, "percentage": 15.07, "elapsed_time": "3:29:45", "remaining_time": "19:41:41", "throughput": 659.56, "total_tokens": 8301024} {"current_steps": 6035, "total_steps": 40000, "loss": 0.7288, "lr": 4.72447758401311e-05, "epoch": 0.19316945137955316, "percentage": 15.09, "elapsed_time": "3:29:47", "remaining_time": "19:40:42", "throughput": 659.98, "total_tokens": 8307504} {"current_steps": 6040, "total_steps": 40000, "loss": 0.7574, "lr": 4.7240293740895616e-05, "epoch": 0.1933294923500416, "percentage": 15.1, "elapsed_time": "3:29:49", "remaining_time": "19:39:42", "throughput": 660.45, "total_tokens": 8314560} {"current_steps": 6045, "total_steps": 40000, "loss": 0.8227, "lr": 4.723580821192733e-05, "epoch": 0.19348953332053007, "percentage": 15.11, "elapsed_time": "3:29:50", "remaining_time": "19:38:43", "throughput": 660.9, "total_tokens": 8321392} {"current_steps": 6050, "total_steps": 40000, "loss": 0.6994, "lr": 4.7231319253917996e-05, "epoch": 0.1936495742910185, "percentage": 15.12, "elapsed_time": "3:29:52", "remaining_time": "19:37:44", "throughput": 661.36, "total_tokens": 8328256} {"current_steps": 6055, "total_steps": 40000, "loss": 0.781, "lr": 4.722682686755986e-05, "epoch": 0.19380961526150695, "percentage": 15.14, "elapsed_time": "3:29:54", "remaining_time": "19:36:45", "throughput": 661.81, "total_tokens": 8335072} {"current_steps": 6060, "total_steps": 40000, "loss": 0.6027, "lr": 4.722233105354569e-05, "epoch": 0.19396965623199539, "percentage": 15.15, "elapsed_time": "3:29:56", "remaining_time": "19:35:46", "throughput": 662.27, "total_tokens": 8342096} {"current_steps": 6065, "total_steps": 40000, "loss": 0.7845, "lr": 4.7217831812568815e-05, "epoch": 0.19412969720248383, "percentage": 15.16, "elapsed_time": "3:29:57", "remaining_time": "19:34:47", "throughput": 662.75, "total_tokens": 8349232} {"current_steps": 6070, "total_steps": 40000, "loss": 1.1418, "lr": 4.721332914532307e-05, "epoch": 0.1942897381729723, "percentage": 15.17, "elapsed_time": "3:29:59", "remaining_time": "19:33:49", "throughput": 663.22, "total_tokens": 8356256} {"current_steps": 6075, "total_steps": 40000, "loss": 0.8777, "lr": 4.720882305250281e-05, "epoch": 0.19444977914346073, "percentage": 15.19, "elapsed_time": "3:30:01", "remaining_time": "19:32:50", "throughput": 663.64, "total_tokens": 8362752} {"current_steps": 6080, "total_steps": 40000, "loss": 0.6868, "lr": 4.720431353480295e-05, "epoch": 0.19460982011394917, "percentage": 15.2, "elapsed_time": "3:30:03", "remaining_time": "19:31:51", "throughput": 664.1, "total_tokens": 8369696} {"current_steps": 6085, "total_steps": 40000, "loss": 0.8747, "lr": 4.719980059291891e-05, "epoch": 0.1947698610844376, "percentage": 15.21, "elapsed_time": "3:30:04", "remaining_time": "19:30:53", "throughput": 664.54, "total_tokens": 8376352} {"current_steps": 6090, "total_steps": 40000, "loss": 0.6714, "lr": 4.7195284227546634e-05, "epoch": 0.19492990205492605, "percentage": 15.22, "elapsed_time": "3:30:06", "remaining_time": "19:29:55", "throughput": 664.98, "total_tokens": 8383120} {"current_steps": 6095, "total_steps": 40000, "loss": 0.771, "lr": 4.7190764439382604e-05, "epoch": 0.19508994302541452, "percentage": 15.24, "elapsed_time": "3:30:08", "remaining_time": "19:28:56", "throughput": 665.43, "total_tokens": 8389920} {"current_steps": 6100, "total_steps": 40000, "loss": 0.9312, "lr": 4.7186241229123826e-05, "epoch": 0.19524998399590296, "percentage": 15.25, "elapsed_time": "3:30:10", "remaining_time": "19:27:58", "throughput": 665.89, "total_tokens": 8396928} {"current_steps": 6105, "total_steps": 40000, "loss": 0.5883, "lr": 4.718171459746785e-05, "epoch": 0.1954100249663914, "percentage": 15.26, "elapsed_time": "3:30:11", "remaining_time": "19:27:00", "throughput": 666.39, "total_tokens": 8404288} {"current_steps": 6110, "total_steps": 40000, "loss": 0.8357, "lr": 4.717718454511273e-05, "epoch": 0.19557006593687984, "percentage": 15.28, "elapsed_time": "3:30:13", "remaining_time": "19:26:02", "throughput": 666.83, "total_tokens": 8411104} {"current_steps": 6115, "total_steps": 40000, "loss": 0.8311, "lr": 4.7172651072757056e-05, "epoch": 0.19573010690736828, "percentage": 15.29, "elapsed_time": "3:30:15", "remaining_time": "19:25:04", "throughput": 667.32, "total_tokens": 8418368} {"current_steps": 6120, "total_steps": 40000, "loss": 1.1016, "lr": 4.7168114181099945e-05, "epoch": 0.19589014787785672, "percentage": 15.3, "elapsed_time": "3:30:16", "remaining_time": "19:24:06", "throughput": 667.77, "total_tokens": 8425248} {"current_steps": 6125, "total_steps": 40000, "loss": 0.6195, "lr": 4.716357387084105e-05, "epoch": 0.19605018884834519, "percentage": 15.31, "elapsed_time": "3:30:18", "remaining_time": "19:23:09", "throughput": 668.23, "total_tokens": 8432144} {"current_steps": 6130, "total_steps": 40000, "loss": 0.8316, "lr": 4.715903014268054e-05, "epoch": 0.19621022981883363, "percentage": 15.32, "elapsed_time": "3:30:20", "remaining_time": "19:22:11", "throughput": 668.7, "total_tokens": 8439328} {"current_steps": 6135, "total_steps": 40000, "loss": 0.9849, "lr": 4.715448299731911e-05, "epoch": 0.19637027078932207, "percentage": 15.34, "elapsed_time": "3:30:22", "remaining_time": "19:21:13", "throughput": 669.13, "total_tokens": 8445856} {"current_steps": 6140, "total_steps": 40000, "loss": 0.7034, "lr": 4.7149932435457986e-05, "epoch": 0.1965303117598105, "percentage": 15.35, "elapsed_time": "3:30:23", "remaining_time": "19:20:16", "throughput": 669.59, "total_tokens": 8452880} {"current_steps": 6145, "total_steps": 40000, "loss": 0.7889, "lr": 4.714537845779894e-05, "epoch": 0.19669035273029895, "percentage": 15.36, "elapsed_time": "3:30:25", "remaining_time": "19:19:19", "throughput": 670.09, "total_tokens": 8460320} {"current_steps": 6150, "total_steps": 40000, "loss": 0.7185, "lr": 4.714082106504423e-05, "epoch": 0.1968503937007874, "percentage": 15.38, "elapsed_time": "3:30:27", "remaining_time": "19:18:21", "throughput": 670.56, "total_tokens": 8467456} {"current_steps": 6155, "total_steps": 40000, "loss": 0.8382, "lr": 4.713626025789667e-05, "epoch": 0.19701043467127585, "percentage": 15.39, "elapsed_time": "3:30:29", "remaining_time": "19:17:24", "throughput": 671.0, "total_tokens": 8474080} {"current_steps": 6160, "total_steps": 40000, "loss": 0.7139, "lr": 4.7131696037059606e-05, "epoch": 0.1971704756417643, "percentage": 15.4, "elapsed_time": "3:30:30", "remaining_time": "19:16:27", "throughput": 671.46, "total_tokens": 8481168} {"current_steps": 6165, "total_steps": 40000, "loss": 0.8023, "lr": 4.712712840323689e-05, "epoch": 0.19733051661225273, "percentage": 15.41, "elapsed_time": "3:30:32", "remaining_time": "19:15:30", "throughput": 671.92, "total_tokens": 8488080} {"current_steps": 6170, "total_steps": 40000, "loss": 0.6996, "lr": 4.71225573571329e-05, "epoch": 0.19749055758274117, "percentage": 15.43, "elapsed_time": "3:30:34", "remaining_time": "19:14:33", "throughput": 672.36, "total_tokens": 8494880} {"current_steps": 6175, "total_steps": 40000, "loss": 0.8162, "lr": 4.711798289945256e-05, "epoch": 0.19765059855322964, "percentage": 15.44, "elapsed_time": "3:30:36", "remaining_time": "19:13:37", "throughput": 672.82, "total_tokens": 8501824} {"current_steps": 6180, "total_steps": 40000, "loss": 0.7361, "lr": 4.71134050309013e-05, "epoch": 0.19781063952371808, "percentage": 15.45, "elapsed_time": "3:30:37", "remaining_time": "19:12:40", "throughput": 673.25, "total_tokens": 8508448} {"current_steps": 6185, "total_steps": 40000, "loss": 0.8381, "lr": 4.710882375218509e-05, "epoch": 0.19797068049420652, "percentage": 15.46, "elapsed_time": "3:30:39", "remaining_time": "19:11:43", "throughput": 673.7, "total_tokens": 8515200} {"current_steps": 6190, "total_steps": 40000, "loss": 0.7256, "lr": 4.7104239064010424e-05, "epoch": 0.19813072146469496, "percentage": 15.47, "elapsed_time": "3:30:41", "remaining_time": "19:10:47", "throughput": 674.14, "total_tokens": 8522016} {"current_steps": 6195, "total_steps": 40000, "loss": 0.8063, "lr": 4.709965096708432e-05, "epoch": 0.1982907624351834, "percentage": 15.49, "elapsed_time": "3:30:43", "remaining_time": "19:09:50", "throughput": 674.63, "total_tokens": 8529344} {"current_steps": 6200, "total_steps": 40000, "loss": 1.0037, "lr": 4.709505946211431e-05, "epoch": 0.19845080340567184, "percentage": 15.5, "elapsed_time": "3:30:44", "remaining_time": "19:08:54", "throughput": 675.06, "total_tokens": 8535952} {"current_steps": 6200, "total_steps": 40000, "eval_loss": 0.83376544713974, "epoch": 0.19845080340567184, "percentage": 15.5, "elapsed_time": "3:36:32", "remaining_time": "19:40:32", "throughput": 656.97, "total_tokens": 8535952} {"current_steps": 6205, "total_steps": 40000, "loss": 0.6792, "lr": 4.709046454980846e-05, "epoch": 0.1986108443761603, "percentage": 15.51, "elapsed_time": "3:36:36", "remaining_time": "19:39:43", "throughput": 657.34, "total_tokens": 8542912} {"current_steps": 6210, "total_steps": 40000, "loss": 0.7797, "lr": 4.708586623087538e-05, "epoch": 0.19877088534664875, "percentage": 15.53, "elapsed_time": "3:36:38", "remaining_time": "19:38:45", "throughput": 657.75, "total_tokens": 8549504} {"current_steps": 6215, "total_steps": 40000, "loss": 0.8423, "lr": 4.708126450602418e-05, "epoch": 0.19893092631713719, "percentage": 15.54, "elapsed_time": "3:36:39", "remaining_time": "19:37:47", "throughput": 658.19, "total_tokens": 8556352} {"current_steps": 6220, "total_steps": 40000, "loss": 0.9483, "lr": 4.7076659375964495e-05, "epoch": 0.19909096728762563, "percentage": 15.55, "elapsed_time": "3:36:41", "remaining_time": "19:36:49", "throughput": 658.65, "total_tokens": 8563472} {"current_steps": 6225, "total_steps": 40000, "loss": 0.7403, "lr": 4.707205084140651e-05, "epoch": 0.19925100825811407, "percentage": 15.56, "elapsed_time": "3:36:43", "remaining_time": "19:35:51", "throughput": 659.1, "total_tokens": 8570368} {"current_steps": 6230, "total_steps": 40000, "loss": 1.0372, "lr": 4.7067438903060904e-05, "epoch": 0.19941104922860253, "percentage": 15.57, "elapsed_time": "3:36:44", "remaining_time": "19:34:54", "throughput": 659.53, "total_tokens": 8577168} {"current_steps": 6235, "total_steps": 40000, "loss": 0.8848, "lr": 4.70628235616389e-05, "epoch": 0.19957109019909097, "percentage": 15.59, "elapsed_time": "3:36:46", "remaining_time": "19:33:56", "throughput": 659.96, "total_tokens": 8583872} {"current_steps": 6240, "total_steps": 40000, "loss": 0.8427, "lr": 4.7058204817852256e-05, "epoch": 0.1997311311695794, "percentage": 15.6, "elapsed_time": "3:36:48", "remaining_time": "19:32:58", "throughput": 660.44, "total_tokens": 8591264} {"current_steps": 6245, "total_steps": 40000, "loss": 0.8562, "lr": 4.705358267241322e-05, "epoch": 0.19989117214006785, "percentage": 15.61, "elapsed_time": "3:36:50", "remaining_time": "19:32:01", "throughput": 660.87, "total_tokens": 8598016} {"current_steps": 6250, "total_steps": 40000, "loss": 0.7638, "lr": 4.704895712603459e-05, "epoch": 0.2000512131105563, "percentage": 15.62, "elapsed_time": "3:36:51", "remaining_time": "19:31:04", "throughput": 661.28, "total_tokens": 8604544} {"current_steps": 6255, "total_steps": 40000, "loss": 1.0406, "lr": 4.704432817942969e-05, "epoch": 0.20021125408104476, "percentage": 15.64, "elapsed_time": "3:36:53", "remaining_time": "19:30:07", "throughput": 661.74, "total_tokens": 8611696} {"current_steps": 6260, "total_steps": 40000, "loss": 0.9446, "lr": 4.703969583331236e-05, "epoch": 0.2003712950515332, "percentage": 15.65, "elapsed_time": "3:36:55", "remaining_time": "19:29:10", "throughput": 662.17, "total_tokens": 8618416} {"current_steps": 6265, "total_steps": 40000, "loss": 0.9858, "lr": 4.7035060088396965e-05, "epoch": 0.20053133602202164, "percentage": 15.66, "elapsed_time": "3:36:57", "remaining_time": "19:28:13", "throughput": 662.63, "total_tokens": 8625504} {"current_steps": 6270, "total_steps": 40000, "loss": 0.7832, "lr": 4.703042094539839e-05, "epoch": 0.20069137699251008, "percentage": 15.68, "elapsed_time": "3:36:58", "remaining_time": "19:27:16", "throughput": 663.05, "total_tokens": 8632096} {"current_steps": 6275, "total_steps": 40000, "loss": 0.7149, "lr": 4.702577840503206e-05, "epoch": 0.20085141796299852, "percentage": 15.69, "elapsed_time": "3:37:00", "remaining_time": "19:26:19", "throughput": 663.47, "total_tokens": 8638736} {"current_steps": 6280, "total_steps": 40000, "loss": 0.6522, "lr": 4.70211324680139e-05, "epoch": 0.201011458933487, "percentage": 15.7, "elapsed_time": "3:37:02", "remaining_time": "19:25:22", "throughput": 663.9, "total_tokens": 8645536} {"current_steps": 6285, "total_steps": 40000, "loss": 0.7277, "lr": 4.7016483135060386e-05, "epoch": 0.20117149990397543, "percentage": 15.71, "elapsed_time": "3:37:04", "remaining_time": "19:24:25", "throughput": 664.34, "total_tokens": 8652448} {"current_steps": 6290, "total_steps": 40000, "loss": 0.796, "lr": 4.701183040688849e-05, "epoch": 0.20133154087446387, "percentage": 15.72, "elapsed_time": "3:37:05", "remaining_time": "19:23:29", "throughput": 664.76, "total_tokens": 8659024} {"current_steps": 6295, "total_steps": 40000, "loss": 0.7349, "lr": 4.700717428421573e-05, "epoch": 0.2014915818449523, "percentage": 15.74, "elapsed_time": "3:37:07", "remaining_time": "19:22:32", "throughput": 665.2, "total_tokens": 8665872} {"current_steps": 6300, "total_steps": 40000, "loss": 0.7477, "lr": 4.700251476776014e-05, "epoch": 0.20165162281544075, "percentage": 15.75, "elapsed_time": "3:37:09", "remaining_time": "19:21:36", "throughput": 665.6, "total_tokens": 8672336} {"current_steps": 6305, "total_steps": 40000, "loss": 0.6565, "lr": 4.699785185824026e-05, "epoch": 0.20181166378592919, "percentage": 15.76, "elapsed_time": "3:37:11", "remaining_time": "19:20:40", "throughput": 666.06, "total_tokens": 8679392} {"current_steps": 6310, "total_steps": 40000, "loss": 0.8798, "lr": 4.699318555637519e-05, "epoch": 0.20197170475641765, "percentage": 15.78, "elapsed_time": "3:37:12", "remaining_time": "19:19:43", "throughput": 666.5, "total_tokens": 8686384} {"current_steps": 6315, "total_steps": 40000, "loss": 1.0588, "lr": 4.6988515862884525e-05, "epoch": 0.2021317457269061, "percentage": 15.79, "elapsed_time": "3:37:14", "remaining_time": "19:18:47", "throughput": 666.95, "total_tokens": 8693328} {"current_steps": 6320, "total_steps": 40000, "loss": 1.0207, "lr": 4.698384277848838e-05, "epoch": 0.20229178669739453, "percentage": 15.8, "elapsed_time": "3:37:16", "remaining_time": "19:17:51", "throughput": 667.39, "total_tokens": 8700208} {"current_steps": 6325, "total_steps": 40000, "loss": 0.9232, "lr": 4.6979166303907425e-05, "epoch": 0.20245182766788297, "percentage": 15.81, "elapsed_time": "3:37:17", "remaining_time": "19:16:55", "throughput": 667.84, "total_tokens": 8707344} {"current_steps": 6330, "total_steps": 40000, "loss": 0.7211, "lr": 4.697448643986281e-05, "epoch": 0.2026118686383714, "percentage": 15.82, "elapsed_time": "3:37:19", "remaining_time": "19:15:59", "throughput": 668.29, "total_tokens": 8714272} {"current_steps": 6335, "total_steps": 40000, "loss": 0.8952, "lr": 4.696980318707624e-05, "epoch": 0.20277190960885988, "percentage": 15.84, "elapsed_time": "3:37:21", "remaining_time": "19:15:03", "throughput": 668.71, "total_tokens": 8720976} {"current_steps": 6340, "total_steps": 40000, "loss": 0.8678, "lr": 4.6965116546269924e-05, "epoch": 0.20293195057934832, "percentage": 15.85, "elapsed_time": "3:37:23", "remaining_time": "19:14:08", "throughput": 669.14, "total_tokens": 8727744} {"current_steps": 6345, "total_steps": 40000, "loss": 0.8421, "lr": 4.6960426518166615e-05, "epoch": 0.20309199154983676, "percentage": 15.86, "elapsed_time": "3:37:24", "remaining_time": "19:13:12", "throughput": 669.58, "total_tokens": 8734608} {"current_steps": 6350, "total_steps": 40000, "loss": 0.8413, "lr": 4.6955733103489556e-05, "epoch": 0.2032520325203252, "percentage": 15.88, "elapsed_time": "3:37:26", "remaining_time": "19:12:17", "throughput": 670.01, "total_tokens": 8741408} {"current_steps": 6355, "total_steps": 40000, "loss": 0.8168, "lr": 4.695103630296255e-05, "epoch": 0.20341207349081364, "percentage": 15.89, "elapsed_time": "3:37:28", "remaining_time": "19:11:21", "throughput": 670.47, "total_tokens": 8748544} {"current_steps": 6360, "total_steps": 40000, "loss": 0.6952, "lr": 4.694633611730988e-05, "epoch": 0.2035721144613021, "percentage": 15.9, "elapsed_time": "3:37:30", "remaining_time": "19:10:26", "throughput": 670.89, "total_tokens": 8755216} {"current_steps": 6365, "total_steps": 40000, "loss": 0.6612, "lr": 4.694163254725639e-05, "epoch": 0.20373215543179055, "percentage": 15.91, "elapsed_time": "3:37:31", "remaining_time": "19:09:30", "throughput": 671.32, "total_tokens": 8761952} {"current_steps": 6370, "total_steps": 40000, "loss": 0.7498, "lr": 4.693692559352743e-05, "epoch": 0.20389219640227899, "percentage": 15.93, "elapsed_time": "3:37:33", "remaining_time": "19:08:35", "throughput": 671.74, "total_tokens": 8768608} {"current_steps": 6375, "total_steps": 40000, "loss": 0.726, "lr": 4.693221525684886e-05, "epoch": 0.20405223737276743, "percentage": 15.94, "elapsed_time": "3:37:35", "remaining_time": "19:07:40", "throughput": 672.2, "total_tokens": 8775840} {"current_steps": 6380, "total_steps": 40000, "loss": 0.745, "lr": 4.6927501537947084e-05, "epoch": 0.20421227834325587, "percentage": 15.95, "elapsed_time": "3:37:37", "remaining_time": "19:06:45", "throughput": 672.64, "total_tokens": 8782736} {"current_steps": 6385, "total_steps": 40000, "loss": 1.0293, "lr": 4.692278443754901e-05, "epoch": 0.2043723193137443, "percentage": 15.96, "elapsed_time": "3:37:38", "remaining_time": "19:05:50", "throughput": 673.06, "total_tokens": 8789392} {"current_steps": 6390, "total_steps": 40000, "loss": 0.9744, "lr": 4.691806395638208e-05, "epoch": 0.20453236028423277, "percentage": 15.97, "elapsed_time": "3:37:40", "remaining_time": "19:04:55", "throughput": 673.51, "total_tokens": 8796368} {"current_steps": 6395, "total_steps": 40000, "loss": 0.6039, "lr": 4.6913340095174255e-05, "epoch": 0.2046924012547212, "percentage": 15.99, "elapsed_time": "3:37:42", "remaining_time": "19:04:00", "throughput": 673.93, "total_tokens": 8803088} {"current_steps": 6400, "total_steps": 40000, "loss": 0.661, "lr": 4.690861285465399e-05, "epoch": 0.20485244222520965, "percentage": 16.0, "elapsed_time": "3:37:44", "remaining_time": "19:03:06", "throughput": 674.37, "total_tokens": 8809968} {"current_steps": 6400, "total_steps": 40000, "eval_loss": 0.8255951404571533, "epoch": 0.20485244222520965, "percentage": 16.0, "elapsed_time": "3:43:31", "remaining_time": "19:33:30", "throughput": 656.89, "total_tokens": 8809968} {"current_steps": 6405, "total_steps": 40000, "loss": 0.7215, "lr": 4.690388223555031e-05, "epoch": 0.2050124831956981, "percentage": 16.01, "elapsed_time": "3:43:34", "remaining_time": "19:32:43", "throughput": 657.21, "total_tokens": 8816432} {"current_steps": 6410, "total_steps": 40000, "loss": 0.7379, "lr": 4.689914823859273e-05, "epoch": 0.20517252416618653, "percentage": 16.02, "elapsed_time": "3:43:36", "remaining_time": "19:31:47", "throughput": 657.65, "total_tokens": 8823568} {"current_steps": 6415, "total_steps": 40000, "loss": 0.7667, "lr": 4.689441086451129e-05, "epoch": 0.205332565136675, "percentage": 16.04, "elapsed_time": "3:43:38", "remaining_time": "19:30:50", "throughput": 658.1, "total_tokens": 8830736} {"current_steps": 6420, "total_steps": 40000, "loss": 0.6229, "lr": 4.688967011403655e-05, "epoch": 0.20549260610716344, "percentage": 16.05, "elapsed_time": "3:43:40", "remaining_time": "19:29:54", "throughput": 658.55, "total_tokens": 8837824} {"current_steps": 6425, "total_steps": 40000, "loss": 0.739, "lr": 4.68849259878996e-05, "epoch": 0.20565264707765188, "percentage": 16.06, "elapsed_time": "3:43:41", "remaining_time": "19:28:58", "throughput": 658.95, "total_tokens": 8844432} {"current_steps": 6430, "total_steps": 40000, "loss": 0.716, "lr": 4.6880178486832036e-05, "epoch": 0.20581268804814032, "percentage": 16.07, "elapsed_time": "3:43:43", "remaining_time": "19:28:02", "throughput": 659.37, "total_tokens": 8851200} {"current_steps": 6435, "total_steps": 40000, "loss": 0.7373, "lr": 4.687542761156598e-05, "epoch": 0.20597272901862876, "percentage": 16.09, "elapsed_time": "3:43:45", "remaining_time": "19:27:07", "throughput": 659.77, "total_tokens": 8857680} {"current_steps": 6440, "total_steps": 40000, "loss": 0.7609, "lr": 4.6870673362834096e-05, "epoch": 0.20613276998911723, "percentage": 16.1, "elapsed_time": "3:43:47", "remaining_time": "19:26:11", "throughput": 660.22, "total_tokens": 8864896} {"current_steps": 6445, "total_steps": 40000, "loss": 0.6463, "lr": 4.6865915741369526e-05, "epoch": 0.20629281095960567, "percentage": 16.11, "elapsed_time": "3:43:48", "remaining_time": "19:25:15", "throughput": 660.64, "total_tokens": 8871632} {"current_steps": 6450, "total_steps": 40000, "loss": 0.6871, "lr": 4.686115474790597e-05, "epoch": 0.2064528519300941, "percentage": 16.12, "elapsed_time": "3:43:50", "remaining_time": "19:24:20", "throughput": 661.09, "total_tokens": 8878848} {"current_steps": 6455, "total_steps": 40000, "loss": 0.998, "lr": 4.685639038317762e-05, "epoch": 0.20661289290058255, "percentage": 16.14, "elapsed_time": "3:43:52", "remaining_time": "19:23:24", "throughput": 661.53, "total_tokens": 8885872} {"current_steps": 6460, "total_steps": 40000, "loss": 0.9796, "lr": 4.685162264791921e-05, "epoch": 0.20677293387107099, "percentage": 16.15, "elapsed_time": "3:43:54", "remaining_time": "19:22:29", "throughput": 661.93, "total_tokens": 8892480} {"current_steps": 6465, "total_steps": 40000, "loss": 0.8552, "lr": 4.684685154286599e-05, "epoch": 0.20693297484155945, "percentage": 16.16, "elapsed_time": "3:43:55", "remaining_time": "19:21:33", "throughput": 662.38, "total_tokens": 8899616} {"current_steps": 6470, "total_steps": 40000, "loss": 0.8403, "lr": 4.684207706875371e-05, "epoch": 0.2070930158120479, "percentage": 16.18, "elapsed_time": "3:43:57", "remaining_time": "19:20:38", "throughput": 662.79, "total_tokens": 8906304} {"current_steps": 6475, "total_steps": 40000, "loss": 0.802, "lr": 4.683729922631866e-05, "epoch": 0.20725305678253633, "percentage": 16.19, "elapsed_time": "3:43:59", "remaining_time": "19:19:43", "throughput": 663.2, "total_tokens": 8912896} {"current_steps": 6480, "total_steps": 40000, "loss": 0.8149, "lr": 4.683251801629765e-05, "epoch": 0.20741309775302477, "percentage": 16.2, "elapsed_time": "3:44:01", "remaining_time": "19:18:48", "throughput": 663.61, "total_tokens": 8919664} {"current_steps": 6485, "total_steps": 40000, "loss": 0.8538, "lr": 4.6827733439428e-05, "epoch": 0.2075731387235132, "percentage": 16.21, "elapsed_time": "3:44:02", "remaining_time": "19:17:53", "throughput": 664.03, "total_tokens": 8926464} {"current_steps": 6490, "total_steps": 40000, "loss": 0.763, "lr": 4.682294549644754e-05, "epoch": 0.20773317969400165, "percentage": 16.23, "elapsed_time": "3:44:04", "remaining_time": "19:16:58", "throughput": 664.47, "total_tokens": 8933472} {"current_steps": 6495, "total_steps": 40000, "loss": 0.9184, "lr": 4.681815418809464e-05, "epoch": 0.20789322066449012, "percentage": 16.24, "elapsed_time": "3:44:06", "remaining_time": "19:16:03", "throughput": 664.91, "total_tokens": 8940544} {"current_steps": 6500, "total_steps": 40000, "loss": 0.7775, "lr": 4.681335951510819e-05, "epoch": 0.20805326163497856, "percentage": 16.25, "elapsed_time": "3:44:07", "remaining_time": "19:15:08", "throughput": 665.33, "total_tokens": 8947392} {"current_steps": 6505, "total_steps": 40000, "loss": 0.9163, "lr": 4.6808561478227576e-05, "epoch": 0.208213302605467, "percentage": 16.26, "elapsed_time": "3:44:09", "remaining_time": "19:14:14", "throughput": 665.77, "total_tokens": 8954400} {"current_steps": 6510, "total_steps": 40000, "loss": 0.8841, "lr": 4.680376007819271e-05, "epoch": 0.20837334357595544, "percentage": 16.28, "elapsed_time": "3:44:11", "remaining_time": "19:13:19", "throughput": 666.16, "total_tokens": 8960864} {"current_steps": 6515, "total_steps": 40000, "loss": 0.9179, "lr": 4.679895531574405e-05, "epoch": 0.20853338454644388, "percentage": 16.29, "elapsed_time": "3:44:13", "remaining_time": "19:12:25", "throughput": 666.57, "total_tokens": 8967520} {"current_steps": 6520, "total_steps": 40000, "loss": 0.6545, "lr": 4.679414719162253e-05, "epoch": 0.20869342551693235, "percentage": 16.3, "elapsed_time": "3:44:14", "remaining_time": "19:11:30", "throughput": 666.99, "total_tokens": 8974256} {"current_steps": 6525, "total_steps": 40000, "loss": 0.7887, "lr": 4.6789335706569635e-05, "epoch": 0.20885346648742079, "percentage": 16.31, "elapsed_time": "3:44:16", "remaining_time": "19:10:36", "throughput": 667.4, "total_tokens": 8980976} {"current_steps": 6530, "total_steps": 40000, "loss": 1.0239, "lr": 4.678452086132734e-05, "epoch": 0.20901350745790923, "percentage": 16.32, "elapsed_time": "3:44:18", "remaining_time": "19:09:42", "throughput": 667.81, "total_tokens": 8987680} {"current_steps": 6535, "total_steps": 40000, "loss": 0.6982, "lr": 4.677970265663818e-05, "epoch": 0.20917354842839767, "percentage": 16.34, "elapsed_time": "3:44:20", "remaining_time": "19:08:47", "throughput": 668.22, "total_tokens": 8994384} {"current_steps": 6540, "total_steps": 40000, "loss": 0.863, "lr": 4.677488109324517e-05, "epoch": 0.2093335893988861, "percentage": 16.35, "elapsed_time": "3:44:22", "remaining_time": "19:07:54", "throughput": 668.64, "total_tokens": 9001360} {"current_steps": 6545, "total_steps": 40000, "loss": 0.7275, "lr": 4.6770056171891846e-05, "epoch": 0.20949363036937457, "percentage": 16.36, "elapsed_time": "3:44:23", "remaining_time": "19:07:00", "throughput": 669.1, "total_tokens": 9008704} {"current_steps": 6550, "total_steps": 40000, "loss": 0.7433, "lr": 4.6765227893322286e-05, "epoch": 0.209653671339863, "percentage": 16.38, "elapsed_time": "3:44:25", "remaining_time": "19:06:07", "throughput": 669.54, "total_tokens": 9015712} {"current_steps": 6555, "total_steps": 40000, "loss": 0.9659, "lr": 4.676039625828107e-05, "epoch": 0.20981371231035145, "percentage": 16.39, "elapsed_time": "3:44:27", "remaining_time": "19:05:13", "throughput": 669.97, "total_tokens": 9022736} {"current_steps": 6560, "total_steps": 40000, "loss": 0.9928, "lr": 4.675556126751328e-05, "epoch": 0.2099737532808399, "percentage": 16.4, "elapsed_time": "3:44:29", "remaining_time": "19:04:19", "throughput": 670.4, "total_tokens": 9029648} {"current_steps": 6565, "total_steps": 40000, "loss": 0.9245, "lr": 4.6750722921764556e-05, "epoch": 0.21013379425132833, "percentage": 16.41, "elapsed_time": "3:44:30", "remaining_time": "19:03:25", "throughput": 670.83, "total_tokens": 9036672} {"current_steps": 6570, "total_steps": 40000, "loss": 0.5897, "lr": 4.674588122178102e-05, "epoch": 0.21029383522181677, "percentage": 16.43, "elapsed_time": "3:44:32", "remaining_time": "19:02:32", "throughput": 671.25, "total_tokens": 9043456} {"current_steps": 6575, "total_steps": 40000, "loss": 0.6492, "lr": 4.674103616830931e-05, "epoch": 0.21045387619230524, "percentage": 16.44, "elapsed_time": "3:44:34", "remaining_time": "19:01:38", "throughput": 671.67, "total_tokens": 9050320} {"current_steps": 6580, "total_steps": 40000, "loss": 0.8043, "lr": 4.673618776209663e-05, "epoch": 0.21061391716279368, "percentage": 16.45, "elapsed_time": "3:44:35", "remaining_time": "19:00:44", "throughput": 672.08, "total_tokens": 9056976} {"current_steps": 6585, "total_steps": 40000, "loss": 0.7961, "lr": 4.673133600389063e-05, "epoch": 0.21077395813328212, "percentage": 16.46, "elapsed_time": "3:44:37", "remaining_time": "18:59:51", "throughput": 672.48, "total_tokens": 9063504} {"current_steps": 6590, "total_steps": 40000, "loss": 0.7358, "lr": 4.672648089443953e-05, "epoch": 0.21093399910377056, "percentage": 16.48, "elapsed_time": "3:44:39", "remaining_time": "18:58:58", "throughput": 672.89, "total_tokens": 9070240} {"current_steps": 6595, "total_steps": 40000, "loss": 0.8884, "lr": 4.672162243449204e-05, "epoch": 0.211094040074259, "percentage": 16.49, "elapsed_time": "3:44:41", "remaining_time": "18:58:04", "throughput": 673.3, "total_tokens": 9076880} {"current_steps": 6600, "total_steps": 40000, "loss": 0.9558, "lr": 4.67167606247974e-05, "epoch": 0.21125408104474747, "percentage": 16.5, "elapsed_time": "3:44:42", "remaining_time": "18:57:11", "throughput": 673.74, "total_tokens": 9084016} {"current_steps": 6600, "total_steps": 40000, "eval_loss": 0.8226393461227417, "epoch": 0.21125408104474747, "percentage": 16.5, "elapsed_time": "3:50:30", "remaining_time": "19:26:30", "throughput": 656.81, "total_tokens": 9084016} {"current_steps": 6605, "total_steps": 40000, "loss": 0.8834, "lr": 4.671189546610536e-05, "epoch": 0.2114141220152359, "percentage": 16.51, "elapsed_time": "3:50:33", "remaining_time": "19:25:44", "throughput": 657.16, "total_tokens": 9091120} {"current_steps": 6610, "total_steps": 40000, "loss": 0.7807, "lr": 4.67070269591662e-05, "epoch": 0.21157416298572435, "percentage": 16.53, "elapsed_time": "3:50:35", "remaining_time": "19:24:49", "throughput": 657.55, "total_tokens": 9097552} {"current_steps": 6615, "total_steps": 40000, "loss": 0.9411, "lr": 4.670215510473068e-05, "epoch": 0.21173420395621279, "percentage": 16.54, "elapsed_time": "3:50:37", "remaining_time": "19:23:55", "throughput": 657.96, "total_tokens": 9104416} {"current_steps": 6620, "total_steps": 40000, "loss": 0.719, "lr": 4.669727990355013e-05, "epoch": 0.21189424492670123, "percentage": 16.55, "elapsed_time": "3:50:39", "remaining_time": "19:23:00", "throughput": 658.35, "total_tokens": 9111008} {"current_steps": 6625, "total_steps": 40000, "loss": 0.7804, "lr": 4.669240135637635e-05, "epoch": 0.2120542858971897, "percentage": 16.56, "elapsed_time": "3:50:40", "remaining_time": "19:22:06", "throughput": 658.75, "total_tokens": 9117664} {"current_steps": 6630, "total_steps": 40000, "loss": 0.9248, "lr": 4.6687519463961675e-05, "epoch": 0.21221432686767813, "percentage": 16.57, "elapsed_time": "3:50:42", "remaining_time": "19:21:12", "throughput": 659.16, "total_tokens": 9124400} {"current_steps": 6635, "total_steps": 40000, "loss": 0.6906, "lr": 4.668263422705896e-05, "epoch": 0.21237436783816657, "percentage": 16.59, "elapsed_time": "3:50:44", "remaining_time": "19:20:17", "throughput": 659.55, "total_tokens": 9131024} {"current_steps": 6640, "total_steps": 40000, "loss": 0.7424, "lr": 4.667774564642156e-05, "epoch": 0.212534408808655, "percentage": 16.6, "elapsed_time": "3:50:46", "remaining_time": "19:19:23", "throughput": 659.98, "total_tokens": 9138064} {"current_steps": 6645, "total_steps": 40000, "loss": 0.7824, "lr": 4.6672853722803365e-05, "epoch": 0.21269444977914345, "percentage": 16.61, "elapsed_time": "3:50:47", "remaining_time": "19:18:29", "throughput": 660.39, "total_tokens": 9144976} {"current_steps": 6650, "total_steps": 40000, "loss": 0.7646, "lr": 4.666795845695877e-05, "epoch": 0.21285449074963192, "percentage": 16.62, "elapsed_time": "3:50:49", "remaining_time": "19:17:35", "throughput": 660.79, "total_tokens": 9151664} {"current_steps": 6655, "total_steps": 40000, "loss": 0.7957, "lr": 4.666305984964269e-05, "epoch": 0.21301453172012036, "percentage": 16.64, "elapsed_time": "3:50:51", "remaining_time": "19:16:41", "throughput": 661.23, "total_tokens": 9158784} {"current_steps": 6660, "total_steps": 40000, "loss": 0.673, "lr": 4.6658157901610535e-05, "epoch": 0.2131745726906088, "percentage": 16.65, "elapsed_time": "3:50:52", "remaining_time": "19:15:48", "throughput": 661.64, "total_tokens": 9165664} {"current_steps": 6665, "total_steps": 40000, "loss": 0.7131, "lr": 4.665325261361826e-05, "epoch": 0.21333461366109724, "percentage": 16.66, "elapsed_time": "3:50:54", "remaining_time": "19:14:54", "throughput": 662.02, "total_tokens": 9172096} {"current_steps": 6670, "total_steps": 40000, "loss": 0.8012, "lr": 4.664834398642232e-05, "epoch": 0.21349465463158568, "percentage": 16.68, "elapsed_time": "3:50:56", "remaining_time": "19:14:00", "throughput": 662.4, "total_tokens": 9178528} {"current_steps": 6675, "total_steps": 40000, "loss": 0.8464, "lr": 4.6643432020779686e-05, "epoch": 0.21365469560207412, "percentage": 16.69, "elapsed_time": "3:50:58", "remaining_time": "19:13:07", "throughput": 662.85, "total_tokens": 9185872} {"current_steps": 6680, "total_steps": 40000, "loss": 0.7086, "lr": 4.663851671744786e-05, "epoch": 0.21381473657256259, "percentage": 16.7, "elapsed_time": "3:50:59", "remaining_time": "19:12:13", "throughput": 663.3, "total_tokens": 9193232} {"current_steps": 6685, "total_steps": 40000, "loss": 0.9254, "lr": 4.6633598077184815e-05, "epoch": 0.21397477754305103, "percentage": 16.71, "elapsed_time": "3:51:01", "remaining_time": "19:11:20", "throughput": 663.69, "total_tokens": 9199808} {"current_steps": 6690, "total_steps": 40000, "loss": 0.8844, "lr": 4.662867610074908e-05, "epoch": 0.21413481851353947, "percentage": 16.73, "elapsed_time": "3:51:03", "remaining_time": "19:10:26", "throughput": 664.1, "total_tokens": 9206672} {"current_steps": 6695, "total_steps": 40000, "loss": 0.7923, "lr": 4.6623750788899696e-05, "epoch": 0.2142948594840279, "percentage": 16.74, "elapsed_time": "3:51:05", "remaining_time": "19:09:33", "throughput": 664.52, "total_tokens": 9213600} {"current_steps": 6700, "total_steps": 40000, "loss": 0.8528, "lr": 4.6618822142396195e-05, "epoch": 0.21445490045451635, "percentage": 16.75, "elapsed_time": "3:51:06", "remaining_time": "19:08:40", "throughput": 664.92, "total_tokens": 9220352} {"current_steps": 6705, "total_steps": 40000, "loss": 0.7461, "lr": 4.661389016199864e-05, "epoch": 0.2146149414250048, "percentage": 16.76, "elapsed_time": "3:51:08", "remaining_time": "19:07:47", "throughput": 665.34, "total_tokens": 9227328} {"current_steps": 6710, "total_steps": 40000, "loss": 0.945, "lr": 4.660895484846761e-05, "epoch": 0.21477498239549325, "percentage": 16.78, "elapsed_time": "3:51:10", "remaining_time": "19:06:54", "throughput": 665.76, "total_tokens": 9234304} {"current_steps": 6715, "total_steps": 40000, "loss": 0.8167, "lr": 4.660401620256418e-05, "epoch": 0.2149350233659817, "percentage": 16.79, "elapsed_time": "3:51:12", "remaining_time": "19:06:01", "throughput": 666.17, "total_tokens": 9241136} {"current_steps": 6720, "total_steps": 40000, "loss": 0.9096, "lr": 4.659907422504997e-05, "epoch": 0.21509506433647013, "percentage": 16.8, "elapsed_time": "3:51:13", "remaining_time": "19:05:08", "throughput": 666.62, "total_tokens": 9248576} {"current_steps": 6725, "total_steps": 40000, "loss": 0.8071, "lr": 4.6594128916687074e-05, "epoch": 0.21525510530695857, "percentage": 16.81, "elapsed_time": "3:51:15", "remaining_time": "19:04:15", "throughput": 667.01, "total_tokens": 9255168} {"current_steps": 6730, "total_steps": 40000, "loss": 0.6857, "lr": 4.658918027823813e-05, "epoch": 0.21541514627744704, "percentage": 16.83, "elapsed_time": "3:51:17", "remaining_time": "19:03:22", "throughput": 667.42, "total_tokens": 9261904} {"current_steps": 6735, "total_steps": 40000, "loss": 0.8868, "lr": 4.658422831046628e-05, "epoch": 0.21557518724793548, "percentage": 16.84, "elapsed_time": "3:51:18", "remaining_time": "19:02:30", "throughput": 667.83, "total_tokens": 9268816} {"current_steps": 6740, "total_steps": 40000, "loss": 0.8168, "lr": 4.657927301413518e-05, "epoch": 0.21573522821842392, "percentage": 16.85, "elapsed_time": "3:51:20", "remaining_time": "19:01:37", "throughput": 668.22, "total_tokens": 9275408} {"current_steps": 6745, "total_steps": 40000, "loss": 0.8695, "lr": 4.657431439000901e-05, "epoch": 0.21589526918891236, "percentage": 16.86, "elapsed_time": "3:51:22", "remaining_time": "19:00:44", "throughput": 668.63, "total_tokens": 9282272} {"current_steps": 6750, "total_steps": 40000, "loss": 0.6352, "lr": 4.656935243885243e-05, "epoch": 0.2160553101594008, "percentage": 16.88, "elapsed_time": "3:51:24", "remaining_time": "18:59:52", "throughput": 669.0, "total_tokens": 9288560} {"current_steps": 6755, "total_steps": 40000, "loss": 0.6547, "lr": 4.656438716143066e-05, "epoch": 0.21621535112988924, "percentage": 16.89, "elapsed_time": "3:51:25", "remaining_time": "18:59:00", "throughput": 669.42, "total_tokens": 9295488} {"current_steps": 6760, "total_steps": 40000, "loss": 0.8793, "lr": 4.6559418558509384e-05, "epoch": 0.2163753921003777, "percentage": 16.9, "elapsed_time": "3:51:27", "remaining_time": "18:58:07", "throughput": 669.83, "total_tokens": 9302352} {"current_steps": 6765, "total_steps": 40000, "loss": 0.6113, "lr": 4.6554446630854833e-05, "epoch": 0.21653543307086615, "percentage": 16.91, "elapsed_time": "3:51:29", "remaining_time": "18:57:15", "throughput": 670.24, "total_tokens": 9309232} {"current_steps": 6770, "total_steps": 40000, "loss": 0.7974, "lr": 4.654947137923374e-05, "epoch": 0.21669547404135459, "percentage": 16.93, "elapsed_time": "3:51:31", "remaining_time": "18:56:23", "throughput": 670.63, "total_tokens": 9315792} {"current_steps": 6775, "total_steps": 40000, "loss": 0.8265, "lr": 4.654449280441335e-05, "epoch": 0.21685551501184303, "percentage": 16.94, "elapsed_time": "3:51:32", "remaining_time": "18:55:31", "throughput": 671.06, "total_tokens": 9322976} {"current_steps": 6780, "total_steps": 40000, "loss": 0.8184, "lr": 4.653951090716143e-05, "epoch": 0.21701555598233147, "percentage": 16.95, "elapsed_time": "3:51:34", "remaining_time": "18:54:39", "throughput": 671.49, "total_tokens": 9330080} {"current_steps": 6785, "total_steps": 40000, "loss": 0.7, "lr": 4.653452568824625e-05, "epoch": 0.21717559695281993, "percentage": 16.96, "elapsed_time": "3:51:36", "remaining_time": "18:53:47", "throughput": 671.89, "total_tokens": 9336848} {"current_steps": 6790, "total_steps": 40000, "loss": 0.8038, "lr": 4.6529537148436585e-05, "epoch": 0.21733563792330837, "percentage": 16.98, "elapsed_time": "3:51:38", "remaining_time": "18:52:55", "throughput": 672.3, "total_tokens": 9343632} {"current_steps": 6795, "total_steps": 40000, "loss": 0.7561, "lr": 4.6524545288501734e-05, "epoch": 0.2174956788937968, "percentage": 16.99, "elapsed_time": "3:51:39", "remaining_time": "18:52:04", "throughput": 672.7, "total_tokens": 9350400} {"current_steps": 6800, "total_steps": 40000, "loss": 0.869, "lr": 4.6519550109211506e-05, "epoch": 0.21765571986428525, "percentage": 17.0, "elapsed_time": "3:51:41", "remaining_time": "18:51:12", "throughput": 673.12, "total_tokens": 9357456} {"current_steps": 6800, "total_steps": 40000, "eval_loss": 0.8197910785675049, "epoch": 0.21765571986428525, "percentage": 17.0, "elapsed_time": "3:57:29", "remaining_time": "19:19:32", "throughput": 656.68, "total_tokens": 9357456} {"current_steps": 6805, "total_steps": 40000, "loss": 0.8722, "lr": 4.651455161133622e-05, "epoch": 0.2178157608347737, "percentage": 17.01, "elapsed_time": "3:57:33", "remaining_time": "19:18:47", "throughput": 656.98, "total_tokens": 9363968} {"current_steps": 6810, "total_steps": 40000, "loss": 0.6671, "lr": 4.6509549795646704e-05, "epoch": 0.21797580180526216, "percentage": 17.03, "elapsed_time": "3:57:34", "remaining_time": "19:17:53", "throughput": 657.38, "total_tokens": 9370848} {"current_steps": 6815, "total_steps": 40000, "loss": 0.9254, "lr": 4.6504544662914306e-05, "epoch": 0.2181358427757506, "percentage": 17.04, "elapsed_time": "3:57:36", "remaining_time": "19:17:01", "throughput": 657.77, "total_tokens": 9377584} {"current_steps": 6820, "total_steps": 40000, "loss": 0.822, "lr": 4.6499536213910876e-05, "epoch": 0.21829588374623904, "percentage": 17.05, "elapsed_time": "3:57:38", "remaining_time": "19:16:08", "throughput": 658.17, "total_tokens": 9384416} {"current_steps": 6825, "total_steps": 40000, "loss": 1.0208, "lr": 4.6494524449408786e-05, "epoch": 0.21845592471672748, "percentage": 17.06, "elapsed_time": "3:57:40", "remaining_time": "19:15:15", "throughput": 658.56, "total_tokens": 9391072} {"current_steps": 6830, "total_steps": 40000, "loss": 0.8097, "lr": 4.6489509370180903e-05, "epoch": 0.21861596568721592, "percentage": 17.08, "elapsed_time": "3:57:41", "remaining_time": "19:14:22", "throughput": 658.95, "total_tokens": 9397808} {"current_steps": 6835, "total_steps": 40000, "loss": 0.818, "lr": 4.648449097700063e-05, "epoch": 0.21877600665770439, "percentage": 17.09, "elapsed_time": "3:57:43", "remaining_time": "19:13:29", "throughput": 659.37, "total_tokens": 9404960} {"current_steps": 6840, "total_steps": 40000, "loss": 1.0221, "lr": 4.647946927064185e-05, "epoch": 0.21893604762819283, "percentage": 17.1, "elapsed_time": "3:57:45", "remaining_time": "19:12:37", "throughput": 659.76, "total_tokens": 9411584} {"current_steps": 6845, "total_steps": 40000, "loss": 0.8949, "lr": 4.647444425187898e-05, "epoch": 0.21909608859868127, "percentage": 17.11, "elapsed_time": "3:57:47", "remaining_time": "19:11:44", "throughput": 660.15, "total_tokens": 9418368} {"current_steps": 6850, "total_steps": 40000, "loss": 0.882, "lr": 4.646941592148695e-05, "epoch": 0.2192561295691697, "percentage": 17.12, "elapsed_time": "3:57:48", "remaining_time": "19:10:52", "throughput": 660.56, "total_tokens": 9425376} {"current_steps": 6855, "total_steps": 40000, "loss": 0.9177, "lr": 4.646438428024117e-05, "epoch": 0.21941617053965815, "percentage": 17.14, "elapsed_time": "3:57:50", "remaining_time": "19:09:59", "throughput": 660.99, "total_tokens": 9432608} {"current_steps": 6860, "total_steps": 40000, "loss": 0.8406, "lr": 4.64593493289176e-05, "epoch": 0.21957621151014659, "percentage": 17.15, "elapsed_time": "3:57:52", "remaining_time": "19:09:07", "throughput": 661.38, "total_tokens": 9439328} {"current_steps": 6865, "total_steps": 40000, "loss": 0.7051, "lr": 4.64543110682927e-05, "epoch": 0.21973625248063505, "percentage": 17.16, "elapsed_time": "3:57:53", "remaining_time": "19:08:15", "throughput": 661.74, "total_tokens": 9445664} {"current_steps": 6870, "total_steps": 40000, "loss": 0.9554, "lr": 4.644926949914341e-05, "epoch": 0.2198962934511235, "percentage": 17.18, "elapsed_time": "3:57:55", "remaining_time": "19:07:23", "throughput": 662.15, "total_tokens": 9452688} {"current_steps": 6875, "total_steps": 40000, "loss": 0.8377, "lr": 4.644422462224722e-05, "epoch": 0.22005633442161193, "percentage": 17.19, "elapsed_time": "3:57:57", "remaining_time": "19:06:31", "throughput": 662.56, "total_tokens": 9459664} {"current_steps": 6880, "total_steps": 40000, "loss": 0.871, "lr": 4.643917643838211e-05, "epoch": 0.22021637539210037, "percentage": 17.2, "elapsed_time": "3:57:59", "remaining_time": "19:05:39", "throughput": 662.97, "total_tokens": 9466688} {"current_steps": 6885, "total_steps": 40000, "loss": 0.7714, "lr": 4.6434124948326564e-05, "epoch": 0.2203764163625888, "percentage": 17.21, "elapsed_time": "3:58:00", "remaining_time": "19:04:47", "throughput": 663.38, "total_tokens": 9473616} {"current_steps": 6890, "total_steps": 40000, "loss": 0.8701, "lr": 4.6429070152859594e-05, "epoch": 0.22053645733307728, "percentage": 17.22, "elapsed_time": "3:58:02", "remaining_time": "19:03:55", "throughput": 663.77, "total_tokens": 9480400} {"current_steps": 6895, "total_steps": 40000, "loss": 0.9742, "lr": 4.6424012052760714e-05, "epoch": 0.22069649830356572, "percentage": 17.24, "elapsed_time": "3:58:04", "remaining_time": "19:03:03", "throughput": 664.18, "total_tokens": 9487456} {"current_steps": 6900, "total_steps": 40000, "loss": 0.7405, "lr": 4.6418950648809945e-05, "epoch": 0.22085653927405416, "percentage": 17.25, "elapsed_time": "3:58:06", "remaining_time": "19:02:12", "throughput": 664.56, "total_tokens": 9494016} {"current_steps": 6905, "total_steps": 40000, "loss": 0.7935, "lr": 4.641388594178782e-05, "epoch": 0.2210165802445426, "percentage": 17.26, "elapsed_time": "3:58:07", "remaining_time": "19:01:20", "throughput": 664.99, "total_tokens": 9501232} {"current_steps": 6910, "total_steps": 40000, "loss": 0.7947, "lr": 4.640881793247538e-05, "epoch": 0.22117662121503104, "percentage": 17.27, "elapsed_time": "3:58:09", "remaining_time": "19:00:28", "throughput": 665.37, "total_tokens": 9507904} {"current_steps": 6915, "total_steps": 40000, "loss": 0.9655, "lr": 4.6403746621654173e-05, "epoch": 0.2213366621855195, "percentage": 17.29, "elapsed_time": "3:58:11", "remaining_time": "18:59:37", "throughput": 665.77, "total_tokens": 9514736} {"current_steps": 6920, "total_steps": 40000, "loss": 0.8982, "lr": 4.639867201010626e-05, "epoch": 0.22149670315600795, "percentage": 17.3, "elapsed_time": "3:58:13", "remaining_time": "18:58:45", "throughput": 666.15, "total_tokens": 9521312} {"current_steps": 6925, "total_steps": 40000, "loss": 0.8842, "lr": 4.6393594098614204e-05, "epoch": 0.22165674412649639, "percentage": 17.31, "elapsed_time": "3:58:14", "remaining_time": "18:57:54", "throughput": 666.55, "total_tokens": 9528176} {"current_steps": 6930, "total_steps": 40000, "loss": 0.9456, "lr": 4.63885128879611e-05, "epoch": 0.22181678509698483, "percentage": 17.32, "elapsed_time": "3:58:16", "remaining_time": "18:57:03", "throughput": 666.95, "total_tokens": 9535040} {"current_steps": 6935, "total_steps": 40000, "loss": 0.9854, "lr": 4.638342837893052e-05, "epoch": 0.22197682606747327, "percentage": 17.34, "elapsed_time": "3:58:18", "remaining_time": "18:56:12", "throughput": 667.37, "total_tokens": 9542240} {"current_steps": 6940, "total_steps": 40000, "loss": 0.7343, "lr": 4.6378340572306565e-05, "epoch": 0.2221368670379617, "percentage": 17.35, "elapsed_time": "3:58:20", "remaining_time": "18:55:21", "throughput": 667.78, "total_tokens": 9549360} {"current_steps": 6945, "total_steps": 40000, "loss": 0.6773, "lr": 4.6373249468873833e-05, "epoch": 0.22229690800845017, "percentage": 17.36, "elapsed_time": "3:58:21", "remaining_time": "18:54:29", "throughput": 668.19, "total_tokens": 9556288} {"current_steps": 6950, "total_steps": 40000, "loss": 0.7969, "lr": 4.636815506941744e-05, "epoch": 0.2224569489789386, "percentage": 17.38, "elapsed_time": "3:58:23", "remaining_time": "18:53:38", "throughput": 668.58, "total_tokens": 9563040} {"current_steps": 6955, "total_steps": 40000, "loss": 0.9265, "lr": 4.6363057374723004e-05, "epoch": 0.22261698994942705, "percentage": 17.39, "elapsed_time": "3:58:25", "remaining_time": "18:52:48", "throughput": 668.95, "total_tokens": 9569552} {"current_steps": 6960, "total_steps": 40000, "loss": 0.6549, "lr": 4.635795638557666e-05, "epoch": 0.2227770309199155, "percentage": 17.4, "elapsed_time": "3:58:27", "remaining_time": "18:51:57", "throughput": 669.33, "total_tokens": 9576176} {"current_steps": 6965, "total_steps": 40000, "loss": 0.7109, "lr": 4.635285210276504e-05, "epoch": 0.22293707189040393, "percentage": 17.41, "elapsed_time": "3:58:28", "remaining_time": "18:51:06", "throughput": 669.76, "total_tokens": 9583408} {"current_steps": 6970, "total_steps": 40000, "loss": 0.9033, "lr": 4.6347744527075295e-05, "epoch": 0.2230971128608924, "percentage": 17.42, "elapsed_time": "3:58:30", "remaining_time": "18:50:15", "throughput": 670.15, "total_tokens": 9590224} {"current_steps": 6975, "total_steps": 40000, "loss": 0.7744, "lr": 4.634263365929506e-05, "epoch": 0.22325715383138084, "percentage": 17.44, "elapsed_time": "3:58:32", "remaining_time": "18:49:25", "throughput": 670.53, "total_tokens": 9596816} {"current_steps": 6980, "total_steps": 40000, "loss": 0.8952, "lr": 4.6337519500212515e-05, "epoch": 0.22341719480186928, "percentage": 17.45, "elapsed_time": "3:58:33", "remaining_time": "18:48:34", "throughput": 670.9, "total_tokens": 9603232} {"current_steps": 6985, "total_steps": 40000, "loss": 0.6506, "lr": 4.633240205061632e-05, "epoch": 0.22357723577235772, "percentage": 17.46, "elapsed_time": "3:58:35", "remaining_time": "18:47:44", "throughput": 671.28, "total_tokens": 9609920} {"current_steps": 6990, "total_steps": 40000, "loss": 0.8069, "lr": 4.632728131129565e-05, "epoch": 0.22373727674284616, "percentage": 17.47, "elapsed_time": "3:58:37", "remaining_time": "18:46:53", "throughput": 671.68, "total_tokens": 9616720} {"current_steps": 6995, "total_steps": 40000, "loss": 0.9975, "lr": 4.632215728304018e-05, "epoch": 0.22389731771333463, "percentage": 17.49, "elapsed_time": "3:58:39", "remaining_time": "18:46:03", "throughput": 672.09, "total_tokens": 9623712} {"current_steps": 7000, "total_steps": 40000, "loss": 0.6787, "lr": 4.63170299666401e-05, "epoch": 0.22405735868382307, "percentage": 17.5, "elapsed_time": "3:58:40", "remaining_time": "18:45:12", "throughput": 672.49, "total_tokens": 9630608} {"current_steps": 7000, "total_steps": 40000, "eval_loss": 0.8196972608566284, "epoch": 0.22405735868382307, "percentage": 17.5, "elapsed_time": "4:04:28", "remaining_time": "19:12:32", "throughput": 656.55, "total_tokens": 9630608} {"current_steps": 7005, "total_steps": 40000, "loss": 0.8934, "lr": 4.631189936288612e-05, "epoch": 0.2242173996543115, "percentage": 17.51, "elapsed_time": "4:04:32", "remaining_time": "19:11:49", "throughput": 656.84, "total_tokens": 9637248} {"current_steps": 7010, "total_steps": 40000, "loss": 0.6839, "lr": 4.630676547256944e-05, "epoch": 0.22437744062479995, "percentage": 17.52, "elapsed_time": "4:04:33", "remaining_time": "19:10:57", "throughput": 657.22, "total_tokens": 9644064} {"current_steps": 7015, "total_steps": 40000, "loss": 0.746, "lr": 4.630162829648176e-05, "epoch": 0.22453748159528839, "percentage": 17.54, "elapsed_time": "4:04:35", "remaining_time": "19:10:06", "throughput": 657.65, "total_tokens": 9651424} {"current_steps": 7020, "total_steps": 40000, "loss": 0.939, "lr": 4.629648783541531e-05, "epoch": 0.22469752256577685, "percentage": 17.55, "elapsed_time": "4:04:37", "remaining_time": "19:09:14", "throughput": 658.04, "total_tokens": 9658272} {"current_steps": 7025, "total_steps": 40000, "loss": 0.9754, "lr": 4.6291344090162804e-05, "epoch": 0.2248575635362653, "percentage": 17.56, "elapsed_time": "4:04:39", "remaining_time": "19:08:23", "throughput": 658.47, "total_tokens": 9665792} {"current_steps": 7030, "total_steps": 40000, "loss": 1.045, "lr": 4.628619706151748e-05, "epoch": 0.22501760450675373, "percentage": 17.57, "elapsed_time": "4:04:40", "remaining_time": "19:07:31", "throughput": 658.86, "total_tokens": 9672640} {"current_steps": 7035, "total_steps": 40000, "loss": 0.6897, "lr": 4.628104675027306e-05, "epoch": 0.22517764547724217, "percentage": 17.59, "elapsed_time": "4:04:42", "remaining_time": "19:06:40", "throughput": 659.25, "total_tokens": 9679568} {"current_steps": 7040, "total_steps": 40000, "loss": 0.7912, "lr": 4.6275893157223805e-05, "epoch": 0.2253376864477306, "percentage": 17.6, "elapsed_time": "4:04:44", "remaining_time": "19:05:49", "throughput": 659.67, "total_tokens": 9686800} {"current_steps": 7045, "total_steps": 40000, "loss": 0.9482, "lr": 4.627073628316445e-05, "epoch": 0.22549772741821905, "percentage": 17.61, "elapsed_time": "4:04:46", "remaining_time": "19:04:58", "throughput": 660.08, "total_tokens": 9693984} {"current_steps": 7050, "total_steps": 40000, "loss": 0.7506, "lr": 4.626557612889026e-05, "epoch": 0.22565776838870752, "percentage": 17.62, "elapsed_time": "4:04:47", "remaining_time": "19:04:07", "throughput": 660.45, "total_tokens": 9700560} {"current_steps": 7055, "total_steps": 40000, "loss": 0.6749, "lr": 4.626041269519699e-05, "epoch": 0.22581780935919596, "percentage": 17.64, "elapsed_time": "4:04:49", "remaining_time": "19:03:16", "throughput": 660.84, "total_tokens": 9707392} {"current_steps": 7060, "total_steps": 40000, "loss": 0.8601, "lr": 4.6255245982880905e-05, "epoch": 0.2259778503296844, "percentage": 17.65, "elapsed_time": "4:04:51", "remaining_time": "19:02:25", "throughput": 661.24, "total_tokens": 9714480} {"current_steps": 7065, "total_steps": 40000, "loss": 0.6933, "lr": 4.625007599273879e-05, "epoch": 0.22613789130017284, "percentage": 17.66, "elapsed_time": "4:04:53", "remaining_time": "19:01:34", "throughput": 661.65, "total_tokens": 9721616} {"current_steps": 7070, "total_steps": 40000, "loss": 0.693, "lr": 4.6244902725567895e-05, "epoch": 0.22629793227066128, "percentage": 17.68, "elapsed_time": "4:04:54", "remaining_time": "19:00:44", "throughput": 662.05, "total_tokens": 9728656} {"current_steps": 7075, "total_steps": 40000, "loss": 0.9216, "lr": 4.6239726182166024e-05, "epoch": 0.22645797324114975, "percentage": 17.69, "elapsed_time": "4:04:56", "remaining_time": "18:59:53", "throughput": 662.41, "total_tokens": 9735184} {"current_steps": 7080, "total_steps": 40000, "loss": 0.6417, "lr": 4.623454636333147e-05, "epoch": 0.22661801421163819, "percentage": 17.7, "elapsed_time": "4:04:58", "remaining_time": "18:59:02", "throughput": 662.81, "total_tokens": 9742112} {"current_steps": 7085, "total_steps": 40000, "loss": 0.8901, "lr": 4.622936326986301e-05, "epoch": 0.22677805518212663, "percentage": 17.71, "elapsed_time": "4:05:00", "remaining_time": "18:58:12", "throughput": 663.19, "total_tokens": 9748880} {"current_steps": 7090, "total_steps": 40000, "loss": 0.6993, "lr": 4.6224176902559946e-05, "epoch": 0.22693809615261507, "percentage": 17.72, "elapsed_time": "4:05:01", "remaining_time": "18:57:21", "throughput": 663.58, "total_tokens": 9755824} {"current_steps": 7095, "total_steps": 40000, "loss": 0.6648, "lr": 4.621898726222209e-05, "epoch": 0.2270981371231035, "percentage": 17.74, "elapsed_time": "4:05:03", "remaining_time": "18:56:31", "throughput": 663.95, "total_tokens": 9762416} {"current_steps": 7100, "total_steps": 40000, "loss": 0.7395, "lr": 4.6213794349649744e-05, "epoch": 0.22725817809359197, "percentage": 17.75, "elapsed_time": "4:05:05", "remaining_time": "18:55:41", "throughput": 664.37, "total_tokens": 9769680} {"current_steps": 7105, "total_steps": 40000, "loss": 0.5873, "lr": 4.6208598165643715e-05, "epoch": 0.2274182190640804, "percentage": 17.76, "elapsed_time": "4:05:06", "remaining_time": "18:54:50", "throughput": 664.73, "total_tokens": 9776192} {"current_steps": 7110, "total_steps": 40000, "loss": 0.6537, "lr": 4.620339871100533e-05, "epoch": 0.22757826003456885, "percentage": 17.77, "elapsed_time": "4:05:08", "remaining_time": "18:54:00", "throughput": 665.13, "total_tokens": 9783136} {"current_steps": 7115, "total_steps": 40000, "loss": 0.8549, "lr": 4.6198195986536394e-05, "epoch": 0.2277383010050573, "percentage": 17.79, "elapsed_time": "4:05:10", "remaining_time": "18:53:10", "throughput": 665.51, "total_tokens": 9789952} {"current_steps": 7120, "total_steps": 40000, "loss": 0.6316, "lr": 4.619298999303926e-05, "epoch": 0.22789834197554573, "percentage": 17.8, "elapsed_time": "4:05:12", "remaining_time": "18:52:20", "throughput": 665.9, "total_tokens": 9796784} {"current_steps": 7125, "total_steps": 40000, "loss": 0.7203, "lr": 4.618778073131673e-05, "epoch": 0.22805838294603417, "percentage": 17.81, "elapsed_time": "4:05:13", "remaining_time": "18:51:30", "throughput": 666.29, "total_tokens": 9803792} {"current_steps": 7130, "total_steps": 40000, "loss": 0.9138, "lr": 4.618256820217215e-05, "epoch": 0.22821842391652264, "percentage": 17.82, "elapsed_time": "4:05:15", "remaining_time": "18:50:40", "throughput": 666.66, "total_tokens": 9810320} {"current_steps": 7135, "total_steps": 40000, "loss": 0.9094, "lr": 4.617735240640936e-05, "epoch": 0.22837846488701108, "percentage": 17.84, "elapsed_time": "4:05:17", "remaining_time": "18:49:50", "throughput": 667.03, "total_tokens": 9816960} {"current_steps": 7140, "total_steps": 40000, "loss": 0.9702, "lr": 4.6172133344832705e-05, "epoch": 0.22853850585749952, "percentage": 17.85, "elapsed_time": "4:05:19", "remaining_time": "18:49:00", "throughput": 667.43, "total_tokens": 9823968} {"current_steps": 7145, "total_steps": 40000, "loss": 1.0251, "lr": 4.6166911018247004e-05, "epoch": 0.22869854682798796, "percentage": 17.86, "elapsed_time": "4:05:20", "remaining_time": "18:48:11", "throughput": 667.81, "total_tokens": 9830752} {"current_steps": 7150, "total_steps": 40000, "loss": 1.0148, "lr": 4.616168542745764e-05, "epoch": 0.2288585877984764, "percentage": 17.88, "elapsed_time": "4:05:22", "remaining_time": "18:47:21", "throughput": 668.19, "total_tokens": 9837488} {"current_steps": 7155, "total_steps": 40000, "loss": 0.8059, "lr": 4.6156456573270446e-05, "epoch": 0.22901862876896487, "percentage": 17.89, "elapsed_time": "4:05:24", "remaining_time": "18:46:31", "throughput": 668.64, "total_tokens": 9845216} {"current_steps": 7160, "total_steps": 40000, "loss": 0.9253, "lr": 4.615122445649177e-05, "epoch": 0.2291786697394533, "percentage": 17.9, "elapsed_time": "4:05:26", "remaining_time": "18:45:42", "throughput": 669.02, "total_tokens": 9852000} {"current_steps": 7165, "total_steps": 40000, "loss": 0.9062, "lr": 4.6145989077928486e-05, "epoch": 0.22933871070994175, "percentage": 17.91, "elapsed_time": "4:05:27", "remaining_time": "18:44:52", "throughput": 669.39, "total_tokens": 9858608} {"current_steps": 7170, "total_steps": 40000, "loss": 0.9123, "lr": 4.6140750438387953e-05, "epoch": 0.22949875168043019, "percentage": 17.93, "elapsed_time": "4:05:29", "remaining_time": "18:44:03", "throughput": 669.77, "total_tokens": 9865392} {"current_steps": 7175, "total_steps": 40000, "loss": 0.5986, "lr": 4.613550853867803e-05, "epoch": 0.22965879265091863, "percentage": 17.94, "elapsed_time": "4:05:31", "remaining_time": "18:43:14", "throughput": 670.16, "total_tokens": 9872352} {"current_steps": 7180, "total_steps": 40000, "loss": 0.663, "lr": 4.613026337960708e-05, "epoch": 0.2298188336214071, "percentage": 17.95, "elapsed_time": "4:05:33", "remaining_time": "18:42:25", "throughput": 670.56, "total_tokens": 9879408} {"current_steps": 7185, "total_steps": 40000, "loss": 0.7586, "lr": 4.612501496198398e-05, "epoch": 0.22997887459189553, "percentage": 17.96, "elapsed_time": "4:05:34", "remaining_time": "18:41:35", "throughput": 670.96, "total_tokens": 9886400} {"current_steps": 7190, "total_steps": 40000, "loss": 1.1115, "lr": 4.61197632866181e-05, "epoch": 0.23013891556238397, "percentage": 17.97, "elapsed_time": "4:05:36", "remaining_time": "18:40:46", "throughput": 671.35, "total_tokens": 9893376} {"current_steps": 7195, "total_steps": 40000, "loss": 0.8043, "lr": 4.611450835431931e-05, "epoch": 0.2302989565328724, "percentage": 17.99, "elapsed_time": "4:05:38", "remaining_time": "18:39:57", "throughput": 671.75, "total_tokens": 9900400} {"current_steps": 7200, "total_steps": 40000, "loss": 0.6022, "lr": 4.6109250165898e-05, "epoch": 0.23045899750336085, "percentage": 18.0, "elapsed_time": "4:05:39", "remaining_time": "18:39:08", "throughput": 672.18, "total_tokens": 9907888} {"current_steps": 7200, "total_steps": 40000, "eval_loss": 0.8148825168609619, "epoch": 0.23045899750336085, "percentage": 18.0, "elapsed_time": "4:11:28", "remaining_time": "19:05:35", "throughput": 656.66, "total_tokens": 9907888} {"current_steps": 7205, "total_steps": 40000, "loss": 0.8083, "lr": 4.610398872216503e-05, "epoch": 0.2306190384738493, "percentage": 18.01, "elapsed_time": "4:11:32", "remaining_time": "19:04:54", "throughput": 656.98, "total_tokens": 9915168} {"current_steps": 7210, "total_steps": 40000, "loss": 0.6635, "lr": 4.6098724023931796e-05, "epoch": 0.23077907944433776, "percentage": 18.02, "elapsed_time": "4:11:33", "remaining_time": "19:04:04", "throughput": 657.37, "total_tokens": 9922144} {"current_steps": 7215, "total_steps": 40000, "loss": 0.62, "lr": 4.609345607201017e-05, "epoch": 0.2309391204148262, "percentage": 18.04, "elapsed_time": "4:11:35", "remaining_time": "19:03:14", "throughput": 657.74, "total_tokens": 9928976} {"current_steps": 7220, "total_steps": 40000, "loss": 0.6339, "lr": 4.608818486721254e-05, "epoch": 0.23109916138531464, "percentage": 18.05, "elapsed_time": "4:11:37", "remaining_time": "19:02:24", "throughput": 658.1, "total_tokens": 9935520} {"current_steps": 7225, "total_steps": 40000, "loss": 0.8756, "lr": 4.608291041035179e-05, "epoch": 0.23125920235580308, "percentage": 18.06, "elapsed_time": "4:11:39", "remaining_time": "19:01:34", "throughput": 658.47, "total_tokens": 9942320} {"current_steps": 7230, "total_steps": 40000, "loss": 0.718, "lr": 4.607763270224132e-05, "epoch": 0.23141924332629152, "percentage": 18.07, "elapsed_time": "4:11:40", "remaining_time": "19:00:44", "throughput": 658.87, "total_tokens": 9949360} {"current_steps": 7235, "total_steps": 40000, "loss": 0.8944, "lr": 4.6072351743695e-05, "epoch": 0.23157928429677999, "percentage": 18.09, "elapsed_time": "4:11:42", "remaining_time": "18:59:54", "throughput": 659.24, "total_tokens": 9956144} {"current_steps": 7240, "total_steps": 40000, "loss": 0.8051, "lr": 4.606706753552723e-05, "epoch": 0.23173932526726843, "percentage": 18.1, "elapsed_time": "4:11:44", "remaining_time": "18:59:04", "throughput": 659.63, "total_tokens": 9963120} {"current_steps": 7245, "total_steps": 40000, "loss": 0.6962, "lr": 4.6061780078552906e-05, "epoch": 0.23189936623775687, "percentage": 18.11, "elapsed_time": "4:11:45", "remaining_time": "18:58:14", "throughput": 659.99, "total_tokens": 9969808} {"current_steps": 7250, "total_steps": 40000, "loss": 0.7782, "lr": 4.605648937358742e-05, "epoch": 0.2320594072082453, "percentage": 18.12, "elapsed_time": "4:11:47", "remaining_time": "18:57:25", "throughput": 660.37, "total_tokens": 9976736} {"current_steps": 7255, "total_steps": 40000, "loss": 0.7275, "lr": 4.605119542144665e-05, "epoch": 0.23221944817873375, "percentage": 18.14, "elapsed_time": "4:11:49", "remaining_time": "18:56:35", "throughput": 660.75, "total_tokens": 9983616} {"current_steps": 7260, "total_steps": 40000, "loss": 0.7336, "lr": 4.604589822294701e-05, "epoch": 0.2323794891492222, "percentage": 18.15, "elapsed_time": "4:11:51", "remaining_time": "18:55:45", "throughput": 661.13, "total_tokens": 9990448} {"current_steps": 7265, "total_steps": 40000, "loss": 0.7905, "lr": 4.604059777890537e-05, "epoch": 0.23253953011971065, "percentage": 18.16, "elapsed_time": "4:11:52", "remaining_time": "18:54:56", "throughput": 661.53, "total_tokens": 9997664} {"current_steps": 7270, "total_steps": 40000, "loss": 0.8397, "lr": 4.6035294090139145e-05, "epoch": 0.2326995710901991, "percentage": 18.18, "elapsed_time": "4:11:54", "remaining_time": "18:54:07", "throughput": 661.93, "total_tokens": 10004896} {"current_steps": 7275, "total_steps": 40000, "loss": 0.8665, "lr": 4.6029987157466226e-05, "epoch": 0.23285961206068753, "percentage": 18.19, "elapsed_time": "4:11:56", "remaining_time": "18:53:17", "throughput": 662.31, "total_tokens": 10011776} {"current_steps": 7280, "total_steps": 40000, "loss": 0.9992, "lr": 4.602467698170502e-05, "epoch": 0.23301965303117597, "percentage": 18.2, "elapsed_time": "4:11:58", "remaining_time": "18:52:28", "throughput": 662.72, "total_tokens": 10019136} {"current_steps": 7285, "total_steps": 40000, "loss": 1.0027, "lr": 4.601936356367439e-05, "epoch": 0.23317969400166444, "percentage": 18.21, "elapsed_time": "4:11:59", "remaining_time": "18:51:39", "throughput": 663.1, "total_tokens": 10026016} {"current_steps": 7290, "total_steps": 40000, "loss": 0.8272, "lr": 4.601404690419377e-05, "epoch": 0.23333973497215288, "percentage": 18.22, "elapsed_time": "4:12:01", "remaining_time": "18:50:50", "throughput": 663.49, "total_tokens": 10033056} {"current_steps": 7295, "total_steps": 40000, "loss": 0.9769, "lr": 4.600872700408303e-05, "epoch": 0.23349977594264132, "percentage": 18.24, "elapsed_time": "4:12:03", "remaining_time": "18:50:00", "throughput": 663.87, "total_tokens": 10039920} {"current_steps": 7300, "total_steps": 40000, "loss": 0.9978, "lr": 4.600340386416258e-05, "epoch": 0.23365981691312976, "percentage": 18.25, "elapsed_time": "4:12:05", "remaining_time": "18:49:11", "throughput": 664.22, "total_tokens": 10046384} {"current_steps": 7305, "total_steps": 40000, "loss": 0.6698, "lr": 4.5998077485253296e-05, "epoch": 0.2338198578836182, "percentage": 18.26, "elapsed_time": "4:12:06", "remaining_time": "18:48:22", "throughput": 664.6, "total_tokens": 10053296} {"current_steps": 7310, "total_steps": 40000, "loss": 1.0031, "lr": 4.59927478681766e-05, "epoch": 0.23397989885410664, "percentage": 18.27, "elapsed_time": "4:12:08", "remaining_time": "18:47:34", "throughput": 664.98, "total_tokens": 10060096} {"current_steps": 7315, "total_steps": 40000, "loss": 0.8855, "lr": 4.5987415013754366e-05, "epoch": 0.2341399398245951, "percentage": 18.29, "elapsed_time": "4:12:10", "remaining_time": "18:46:45", "throughput": 665.38, "total_tokens": 10067424} {"current_steps": 7320, "total_steps": 40000, "loss": 0.6961, "lr": 4.598207892280899e-05, "epoch": 0.23429998079508355, "percentage": 18.3, "elapsed_time": "4:12:11", "remaining_time": "18:45:56", "throughput": 665.75, "total_tokens": 10074160} {"current_steps": 7325, "total_steps": 40000, "loss": 0.8955, "lr": 4.597673959616337e-05, "epoch": 0.23446002176557199, "percentage": 18.31, "elapsed_time": "4:12:13", "remaining_time": "18:45:07", "throughput": 666.11, "total_tokens": 10080736} {"current_steps": 7330, "total_steps": 40000, "loss": 0.8378, "lr": 4.597139703464089e-05, "epoch": 0.23462006273606043, "percentage": 18.32, "elapsed_time": "4:12:15", "remaining_time": "18:44:19", "throughput": 666.49, "total_tokens": 10087696} {"current_steps": 7335, "total_steps": 40000, "loss": 0.7489, "lr": 4.596605123906545e-05, "epoch": 0.23478010370654886, "percentage": 18.34, "elapsed_time": "4:12:17", "remaining_time": "18:43:30", "throughput": 666.86, "total_tokens": 10094400} {"current_steps": 7340, "total_steps": 40000, "loss": 0.8932, "lr": 4.596070221026143e-05, "epoch": 0.23494014467703733, "percentage": 18.35, "elapsed_time": "4:12:18", "remaining_time": "18:42:42", "throughput": 667.21, "total_tokens": 10100864} {"current_steps": 7345, "total_steps": 40000, "loss": 0.9516, "lr": 4.595534994905372e-05, "epoch": 0.23510018564752577, "percentage": 18.36, "elapsed_time": "4:12:20", "remaining_time": "18:41:53", "throughput": 667.57, "total_tokens": 10107520} {"current_steps": 7350, "total_steps": 40000, "loss": 0.7939, "lr": 4.594999445626771e-05, "epoch": 0.2352602266180142, "percentage": 18.38, "elapsed_time": "4:12:22", "remaining_time": "18:41:05", "throughput": 667.94, "total_tokens": 10114288} {"current_steps": 7355, "total_steps": 40000, "loss": 0.9179, "lr": 4.5944635732729276e-05, "epoch": 0.23542026758850265, "percentage": 18.39, "elapsed_time": "4:12:24", "remaining_time": "18:40:16", "throughput": 668.29, "total_tokens": 10120752} {"current_steps": 7360, "total_steps": 40000, "loss": 0.7058, "lr": 4.5939273779264804e-05, "epoch": 0.2355803085589911, "percentage": 18.4, "elapsed_time": "4:12:25", "remaining_time": "18:39:28", "throughput": 668.67, "total_tokens": 10127616} {"current_steps": 7365, "total_steps": 40000, "loss": 0.9027, "lr": 4.593390859670118e-05, "epoch": 0.23574034952947956, "percentage": 18.41, "elapsed_time": "4:12:27", "remaining_time": "18:38:40", "throughput": 669.05, "total_tokens": 10134480} {"current_steps": 7370, "total_steps": 40000, "loss": 0.6264, "lr": 4.5928540185865776e-05, "epoch": 0.235900390499968, "percentage": 18.43, "elapsed_time": "4:12:29", "remaining_time": "18:37:52", "throughput": 669.42, "total_tokens": 10141248} {"current_steps": 7375, "total_steps": 40000, "loss": 1.0176, "lr": 4.592316854758648e-05, "epoch": 0.23606043147045644, "percentage": 18.44, "elapsed_time": "4:12:31", "remaining_time": "18:37:04", "throughput": 669.79, "total_tokens": 10148016} {"current_steps": 7380, "total_steps": 40000, "loss": 0.8258, "lr": 4.5917793682691646e-05, "epoch": 0.23622047244094488, "percentage": 18.45, "elapsed_time": "4:12:32", "remaining_time": "18:36:16", "throughput": 670.15, "total_tokens": 10154688} {"current_steps": 7385, "total_steps": 40000, "loss": 0.6578, "lr": 4.5912415592010164e-05, "epoch": 0.23638051341143332, "percentage": 18.46, "elapsed_time": "4:12:34", "remaining_time": "18:35:28", "throughput": 670.51, "total_tokens": 10161232} {"current_steps": 7390, "total_steps": 40000, "loss": 1.0137, "lr": 4.5907034276371386e-05, "epoch": 0.23654055438192176, "percentage": 18.48, "elapsed_time": "4:12:36", "remaining_time": "18:34:40", "throughput": 670.85, "total_tokens": 10167648} {"current_steps": 7395, "total_steps": 40000, "loss": 0.7693, "lr": 4.5901649736605196e-05, "epoch": 0.23670059535241023, "percentage": 18.49, "elapsed_time": "4:12:38", "remaining_time": "18:33:52", "throughput": 671.26, "total_tokens": 10174912} {"current_steps": 7400, "total_steps": 40000, "loss": 0.6105, "lr": 4.589626197354195e-05, "epoch": 0.23686063632289867, "percentage": 18.5, "elapsed_time": "4:12:39", "remaining_time": "18:33:04", "throughput": 671.65, "total_tokens": 10182048} {"current_steps": 7400, "total_steps": 40000, "eval_loss": 0.8123799562454224, "epoch": 0.23686063632289867, "percentage": 18.5, "elapsed_time": "4:18:27", "remaining_time": "18:58:36", "throughput": 656.6, "total_tokens": 10182048} {"current_steps": 7405, "total_steps": 40000, "loss": 0.8291, "lr": 4.5890870988012504e-05, "epoch": 0.2370206772933871, "percentage": 18.51, "elapsed_time": "4:18:30", "remaining_time": "18:57:54", "throughput": 656.87, "total_tokens": 10188544} {"current_steps": 7410, "total_steps": 40000, "loss": 1.1409, "lr": 4.5885476780848226e-05, "epoch": 0.23718071826387555, "percentage": 18.52, "elapsed_time": "4:18:32", "remaining_time": "18:57:05", "throughput": 657.26, "total_tokens": 10195824} {"current_steps": 7415, "total_steps": 40000, "loss": 0.8521, "lr": 4.5880079352880964e-05, "epoch": 0.23734075923436398, "percentage": 18.54, "elapsed_time": "4:18:34", "remaining_time": "18:56:16", "throughput": 657.63, "total_tokens": 10202672} {"current_steps": 7420, "total_steps": 40000, "loss": 0.76, "lr": 4.5874678704943065e-05, "epoch": 0.23750080020485245, "percentage": 18.55, "elapsed_time": "4:18:35", "remaining_time": "18:55:28", "throughput": 658.01, "total_tokens": 10209728} {"current_steps": 7425, "total_steps": 40000, "loss": 0.9528, "lr": 4.5869274837867394e-05, "epoch": 0.2376608411753409, "percentage": 18.56, "elapsed_time": "4:18:37", "remaining_time": "18:54:39", "throughput": 658.38, "total_tokens": 10216480} {"current_steps": 7430, "total_steps": 40000, "loss": 0.6253, "lr": 4.5863867752487275e-05, "epoch": 0.23782088214582933, "percentage": 18.57, "elapsed_time": "4:18:39", "remaining_time": "18:53:50", "throughput": 658.73, "total_tokens": 10223104} {"current_steps": 7435, "total_steps": 40000, "loss": 0.9164, "lr": 4.5858457449636554e-05, "epoch": 0.23798092311631777, "percentage": 18.59, "elapsed_time": "4:18:41", "remaining_time": "18:53:02", "throughput": 659.12, "total_tokens": 10230336} {"current_steps": 7440, "total_steps": 40000, "loss": 0.652, "lr": 4.5853043930149574e-05, "epoch": 0.2381409640868062, "percentage": 18.6, "elapsed_time": "4:18:42", "remaining_time": "18:52:13", "throughput": 659.49, "total_tokens": 10237152} {"current_steps": 7445, "total_steps": 40000, "loss": 0.7526, "lr": 4.584762719486117e-05, "epoch": 0.23830100505729468, "percentage": 18.61, "elapsed_time": "4:18:44", "remaining_time": "18:51:25", "throughput": 659.84, "total_tokens": 10243824} {"current_steps": 7450, "total_steps": 40000, "loss": 0.7221, "lr": 4.584220724460665e-05, "epoch": 0.23846104602778312, "percentage": 18.62, "elapsed_time": "4:18:46", "remaining_time": "18:50:36", "throughput": 660.19, "total_tokens": 10250400} {"current_steps": 7455, "total_steps": 40000, "loss": 0.777, "lr": 4.5836784080221865e-05, "epoch": 0.23862108699827156, "percentage": 18.64, "elapsed_time": "4:18:48", "remaining_time": "18:49:48", "throughput": 660.55, "total_tokens": 10257088} {"current_steps": 7460, "total_steps": 40000, "loss": 0.7304, "lr": 4.583135770254312e-05, "epoch": 0.23878112796876, "percentage": 18.65, "elapsed_time": "4:18:49", "remaining_time": "18:49:00", "throughput": 660.94, "total_tokens": 10264336} {"current_steps": 7465, "total_steps": 40000, "loss": 0.8128, "lr": 4.5825928112407236e-05, "epoch": 0.23894116893924844, "percentage": 18.66, "elapsed_time": "4:18:51", "remaining_time": "18:48:11", "throughput": 661.31, "total_tokens": 10271200} {"current_steps": 7470, "total_steps": 40000, "loss": 0.832, "lr": 4.582049531065152e-05, "epoch": 0.2391012099097369, "percentage": 18.68, "elapsed_time": "4:18:53", "remaining_time": "18:47:23", "throughput": 661.7, "total_tokens": 10278336} {"current_steps": 7475, "total_steps": 40000, "loss": 0.6879, "lr": 4.5815059298113783e-05, "epoch": 0.23926125088022535, "percentage": 18.69, "elapsed_time": "4:18:55", "remaining_time": "18:46:35", "throughput": 662.06, "total_tokens": 10285136} {"current_steps": 7480, "total_steps": 40000, "loss": 0.7968, "lr": 4.580962007563232e-05, "epoch": 0.23942129185071379, "percentage": 18.7, "elapsed_time": "4:18:56", "remaining_time": "18:45:47", "throughput": 662.43, "total_tokens": 10292032} {"current_steps": 7485, "total_steps": 40000, "loss": 0.9282, "lr": 4.5804177644045935e-05, "epoch": 0.23958133282120223, "percentage": 18.71, "elapsed_time": "4:18:58", "remaining_time": "18:44:59", "throughput": 662.8, "total_tokens": 10299008} {"current_steps": 7490, "total_steps": 40000, "loss": 0.5704, "lr": 4.579873200419391e-05, "epoch": 0.23974137379169067, "percentage": 18.73, "elapsed_time": "4:19:00", "remaining_time": "18:44:11", "throughput": 663.17, "total_tokens": 10305872} {"current_steps": 7495, "total_steps": 40000, "loss": 0.7106, "lr": 4.5793283156916046e-05, "epoch": 0.2399014147621791, "percentage": 18.74, "elapsed_time": "4:19:02", "remaining_time": "18:43:24", "throughput": 663.53, "total_tokens": 10312560} {"current_steps": 7500, "total_steps": 40000, "loss": 0.8579, "lr": 4.578783110305261e-05, "epoch": 0.24006145573266757, "percentage": 18.75, "elapsed_time": "4:19:03", "remaining_time": "18:42:36", "throughput": 663.91, "total_tokens": 10319712} {"current_steps": 7505, "total_steps": 40000, "loss": 0.7612, "lr": 4.578237584344438e-05, "epoch": 0.240221496703156, "percentage": 18.76, "elapsed_time": "4:19:05", "remaining_time": "18:41:48", "throughput": 664.29, "total_tokens": 10326640} {"current_steps": 7510, "total_steps": 40000, "loss": 0.6065, "lr": 4.577691737893263e-05, "epoch": 0.24038153767364445, "percentage": 18.77, "elapsed_time": "4:19:07", "remaining_time": "18:41:00", "throughput": 664.66, "total_tokens": 10333552} {"current_steps": 7515, "total_steps": 40000, "loss": 0.9393, "lr": 4.577145571035912e-05, "epoch": 0.2405415786441329, "percentage": 18.79, "elapsed_time": "4:19:08", "remaining_time": "18:40:13", "throughput": 665.02, "total_tokens": 10340368} {"current_steps": 7520, "total_steps": 40000, "loss": 0.76, "lr": 4.576599083856611e-05, "epoch": 0.24070161961462133, "percentage": 18.8, "elapsed_time": "4:19:10", "remaining_time": "18:39:25", "throughput": 665.4, "total_tokens": 10347376} {"current_steps": 7525, "total_steps": 40000, "loss": 0.6897, "lr": 4.576052276439635e-05, "epoch": 0.2408616605851098, "percentage": 18.81, "elapsed_time": "4:19:12", "remaining_time": "18:38:38", "throughput": 665.74, "total_tokens": 10353936} {"current_steps": 7530, "total_steps": 40000, "loss": 0.6435, "lr": 4.575505148869308e-05, "epoch": 0.24102170155559824, "percentage": 18.82, "elapsed_time": "4:19:14", "remaining_time": "18:37:50", "throughput": 666.12, "total_tokens": 10360880} {"current_steps": 7535, "total_steps": 40000, "loss": 0.8829, "lr": 4.574957701230006e-05, "epoch": 0.24118174252608668, "percentage": 18.84, "elapsed_time": "4:19:15", "remaining_time": "18:37:03", "throughput": 666.5, "total_tokens": 10368064} {"current_steps": 7540, "total_steps": 40000, "loss": 0.9036, "lr": 4.57440993360615e-05, "epoch": 0.24134178349657512, "percentage": 18.85, "elapsed_time": "4:19:17", "remaining_time": "18:36:16", "throughput": 666.9, "total_tokens": 10375328} {"current_steps": 7545, "total_steps": 40000, "loss": 0.6245, "lr": 4.5738618460822134e-05, "epoch": 0.24150182446706356, "percentage": 18.86, "elapsed_time": "4:19:19", "remaining_time": "18:35:28", "throughput": 667.27, "total_tokens": 10382352} {"current_steps": 7550, "total_steps": 40000, "loss": 0.7687, "lr": 4.573313438742719e-05, "epoch": 0.24166186543755203, "percentage": 18.88, "elapsed_time": "4:19:21", "remaining_time": "18:34:41", "throughput": 667.65, "total_tokens": 10389392} {"current_steps": 7555, "total_steps": 40000, "loss": 0.7307, "lr": 4.5727647116722374e-05, "epoch": 0.24182190640804047, "percentage": 18.89, "elapsed_time": "4:19:22", "remaining_time": "18:33:54", "throughput": 668.03, "total_tokens": 10396448} {"current_steps": 7560, "total_steps": 40000, "loss": 1.0676, "lr": 4.5722156649553884e-05, "epoch": 0.2419819473785289, "percentage": 18.9, "elapsed_time": "4:19:24", "remaining_time": "18:33:07", "throughput": 668.41, "total_tokens": 10403488} {"current_steps": 7565, "total_steps": 40000, "loss": 0.878, "lr": 4.571666298676843e-05, "epoch": 0.24214198834901735, "percentage": 18.91, "elapsed_time": "4:19:26", "remaining_time": "18:32:20", "throughput": 668.76, "total_tokens": 10410144} {"current_steps": 7570, "total_steps": 40000, "loss": 0.7533, "lr": 4.571116612921321e-05, "epoch": 0.24230202931950579, "percentage": 18.93, "elapsed_time": "4:19:28", "remaining_time": "18:31:33", "throughput": 669.11, "total_tokens": 10416768} {"current_steps": 7575, "total_steps": 40000, "loss": 0.6363, "lr": 4.57056660777359e-05, "epoch": 0.24246207028999422, "percentage": 18.94, "elapsed_time": "4:19:29", "remaining_time": "18:30:46", "throughput": 669.47, "total_tokens": 10423536} {"current_steps": 7580, "total_steps": 40000, "loss": 0.7886, "lr": 4.5700162833184666e-05, "epoch": 0.2426221112604827, "percentage": 18.95, "elapsed_time": "4:19:31", "remaining_time": "18:30:00", "throughput": 669.86, "total_tokens": 10430784} {"current_steps": 7585, "total_steps": 40000, "loss": 0.6432, "lr": 4.5694656396408195e-05, "epoch": 0.24278215223097113, "percentage": 18.96, "elapsed_time": "4:19:33", "remaining_time": "18:29:13", "throughput": 670.25, "total_tokens": 10437904} {"current_steps": 7590, "total_steps": 40000, "loss": 0.7679, "lr": 4.5689146768255646e-05, "epoch": 0.24294219320145957, "percentage": 18.98, "elapsed_time": "4:19:34", "remaining_time": "18:28:26", "throughput": 670.6, "total_tokens": 10444560} {"current_steps": 7595, "total_steps": 40000, "loss": 0.7348, "lr": 4.568363394957667e-05, "epoch": 0.243102234171948, "percentage": 18.99, "elapsed_time": "4:19:36", "remaining_time": "18:27:39", "throughput": 670.99, "total_tokens": 10451840} {"current_steps": 7600, "total_steps": 40000, "loss": 1.0618, "lr": 4.567811794122141e-05, "epoch": 0.24326227514243645, "percentage": 19.0, "elapsed_time": "4:19:38", "remaining_time": "18:26:53", "throughput": 671.35, "total_tokens": 10458544} {"current_steps": 7600, "total_steps": 40000, "eval_loss": 0.8104472160339355, "epoch": 0.24326227514243645, "percentage": 19.0, "elapsed_time": "4:25:25", "remaining_time": "18:51:34", "throughput": 656.7, "total_tokens": 10458544} {"current_steps": 7605, "total_steps": 40000, "loss": 0.7831, "lr": 4.56725987440405e-05, "epoch": 0.24342231611292492, "percentage": 19.01, "elapsed_time": "4:25:29", "remaining_time": "18:50:53", "throughput": 657.01, "total_tokens": 10465648} {"current_steps": 7610, "total_steps": 40000, "loss": 0.7957, "lr": 4.566707635888508e-05, "epoch": 0.24358235708341336, "percentage": 19.02, "elapsed_time": "4:25:31", "remaining_time": "18:50:06", "throughput": 657.37, "total_tokens": 10472624} {"current_steps": 7615, "total_steps": 40000, "loss": 0.7791, "lr": 4.566155078660677e-05, "epoch": 0.2437423980539018, "percentage": 19.04, "elapsed_time": "4:25:32", "remaining_time": "18:49:18", "throughput": 657.75, "total_tokens": 10479808} {"current_steps": 7620, "total_steps": 40000, "loss": 0.7279, "lr": 4.565602202805768e-05, "epoch": 0.24390243902439024, "percentage": 19.05, "elapsed_time": "4:25:34", "remaining_time": "18:48:31", "throughput": 658.11, "total_tokens": 10486560} {"current_steps": 7625, "total_steps": 40000, "loss": 0.7979, "lr": 4.56504900840904e-05, "epoch": 0.24406247999487868, "percentage": 19.06, "elapsed_time": "4:25:36", "remaining_time": "18:47:43", "throughput": 658.5, "total_tokens": 10493920} {"current_steps": 7630, "total_steps": 40000, "loss": 0.7027, "lr": 4.564495495555805e-05, "epoch": 0.24422252096536715, "percentage": 19.07, "elapsed_time": "4:25:37", "remaining_time": "18:46:56", "throughput": 658.85, "total_tokens": 10500640} {"current_steps": 7635, "total_steps": 40000, "loss": 0.7868, "lr": 4.5639416643314204e-05, "epoch": 0.24438256193585559, "percentage": 19.09, "elapsed_time": "4:25:39", "remaining_time": "18:46:08", "throughput": 659.19, "total_tokens": 10507312} {"current_steps": 7640, "total_steps": 40000, "loss": 0.8643, "lr": 4.5633875148212946e-05, "epoch": 0.24454260290634403, "percentage": 19.1, "elapsed_time": "4:25:41", "remaining_time": "18:45:21", "throughput": 659.56, "total_tokens": 10514304} {"current_steps": 7645, "total_steps": 40000, "loss": 0.9213, "lr": 4.562833047110883e-05, "epoch": 0.24470264387683247, "percentage": 19.11, "elapsed_time": "4:25:43", "remaining_time": "18:44:34", "throughput": 659.95, "total_tokens": 10521600} {"current_steps": 7650, "total_steps": 40000, "loss": 0.7714, "lr": 4.5622782612856923e-05, "epoch": 0.2448626848473209, "percentage": 19.12, "elapsed_time": "4:25:44", "remaining_time": "18:43:47", "throughput": 660.31, "total_tokens": 10528544} {"current_steps": 7655, "total_steps": 40000, "loss": 0.7688, "lr": 4.561723157431278e-05, "epoch": 0.24502272581780937, "percentage": 19.14, "elapsed_time": "4:25:46", "remaining_time": "18:42:59", "throughput": 660.67, "total_tokens": 10535408} {"current_steps": 7660, "total_steps": 40000, "loss": 0.7482, "lr": 4.5611677356332435e-05, "epoch": 0.2451827667882978, "percentage": 19.15, "elapsed_time": "4:25:48", "remaining_time": "18:42:12", "throughput": 661.03, "total_tokens": 10542384} {"current_steps": 7665, "total_steps": 40000, "loss": 0.8361, "lr": 4.560611995977242e-05, "epoch": 0.24534280775878625, "percentage": 19.16, "elapsed_time": "4:25:50", "remaining_time": "18:41:25", "throughput": 661.4, "total_tokens": 10549328} {"current_steps": 7670, "total_steps": 40000, "loss": 0.8841, "lr": 4.560055938548975e-05, "epoch": 0.2455028487292747, "percentage": 19.18, "elapsed_time": "4:25:51", "remaining_time": "18:40:38", "throughput": 661.75, "total_tokens": 10556048} {"current_steps": 7675, "total_steps": 40000, "loss": 0.7887, "lr": 4.5594995634341944e-05, "epoch": 0.24566288969976313, "percentage": 19.19, "elapsed_time": "4:25:53", "remaining_time": "18:39:51", "throughput": 662.13, "total_tokens": 10563264} {"current_steps": 7680, "total_steps": 40000, "loss": 0.8845, "lr": 4.5589428707187e-05, "epoch": 0.24582293067025157, "percentage": 19.2, "elapsed_time": "4:25:55", "remaining_time": "18:39:05", "throughput": 662.47, "total_tokens": 10569952} {"current_steps": 7685, "total_steps": 40000, "loss": 0.9573, "lr": 4.55838586048834e-05, "epoch": 0.24598297164074004, "percentage": 19.21, "elapsed_time": "4:25:57", "remaining_time": "18:38:18", "throughput": 662.81, "total_tokens": 10576416} {"current_steps": 7690, "total_steps": 40000, "loss": 0.8051, "lr": 4.557828532829013e-05, "epoch": 0.24614301261122848, "percentage": 19.23, "elapsed_time": "4:25:58", "remaining_time": "18:37:31", "throughput": 663.16, "total_tokens": 10583216} {"current_steps": 7695, "total_steps": 40000, "loss": 0.7701, "lr": 4.557270887826667e-05, "epoch": 0.24630305358171692, "percentage": 19.24, "elapsed_time": "4:26:00", "remaining_time": "18:36:44", "throughput": 663.52, "total_tokens": 10590064} {"current_steps": 7700, "total_steps": 40000, "loss": 0.8264, "lr": 4.556712925567296e-05, "epoch": 0.24646309455220536, "percentage": 19.25, "elapsed_time": "4:26:02", "remaining_time": "18:35:58", "throughput": 663.89, "total_tokens": 10597152} {"current_steps": 7705, "total_steps": 40000, "loss": 0.9088, "lr": 4.5561546461369454e-05, "epoch": 0.2466231355226938, "percentage": 19.26, "elapsed_time": "4:26:03", "remaining_time": "18:35:11", "throughput": 664.26, "total_tokens": 10604176} {"current_steps": 7710, "total_steps": 40000, "loss": 0.6752, "lr": 4.55559604962171e-05, "epoch": 0.24678317649318227, "percentage": 19.28, "elapsed_time": "4:26:05", "remaining_time": "18:34:25", "throughput": 664.65, "total_tokens": 10611600} {"current_steps": 7715, "total_steps": 40000, "loss": 0.7172, "lr": 4.55503713610773e-05, "epoch": 0.2469432174636707, "percentage": 19.29, "elapsed_time": "4:26:07", "remaining_time": "18:33:38", "throughput": 665.0, "total_tokens": 10618384} {"current_steps": 7720, "total_steps": 40000, "loss": 0.6127, "lr": 4.5544779056812e-05, "epoch": 0.24710325843415915, "percentage": 19.3, "elapsed_time": "4:26:09", "remaining_time": "18:32:52", "throughput": 665.36, "total_tokens": 10625200} {"current_steps": 7725, "total_steps": 40000, "loss": 0.8339, "lr": 4.553918358428358e-05, "epoch": 0.24726329940464759, "percentage": 19.31, "elapsed_time": "4:26:10", "remaining_time": "18:32:06", "throughput": 665.71, "total_tokens": 10631920} {"current_steps": 7730, "total_steps": 40000, "loss": 0.6065, "lr": 4.553358494435494e-05, "epoch": 0.24742334037513602, "percentage": 19.32, "elapsed_time": "4:26:12", "remaining_time": "18:31:19", "throughput": 666.05, "total_tokens": 10638608} {"current_steps": 7735, "total_steps": 40000, "loss": 0.8759, "lr": 4.5527983137889464e-05, "epoch": 0.2475833813456245, "percentage": 19.34, "elapsed_time": "4:26:14", "remaining_time": "18:30:33", "throughput": 666.42, "total_tokens": 10645568} {"current_steps": 7740, "total_steps": 40000, "loss": 0.6454, "lr": 4.5522378165751015e-05, "epoch": 0.24774342231611293, "percentage": 19.35, "elapsed_time": "4:26:16", "remaining_time": "18:29:47", "throughput": 666.82, "total_tokens": 10653104} {"current_steps": 7745, "total_steps": 40000, "loss": 0.6532, "lr": 4.5516770028803954e-05, "epoch": 0.24790346328660137, "percentage": 19.36, "elapsed_time": "4:26:17", "remaining_time": "18:29:01", "throughput": 667.17, "total_tokens": 10660000} {"current_steps": 7750, "total_steps": 40000, "loss": 1.0333, "lr": 4.5511158727913116e-05, "epoch": 0.2480635042570898, "percentage": 19.38, "elapsed_time": "4:26:19", "remaining_time": "18:28:15", "throughput": 667.53, "total_tokens": 10666880} {"current_steps": 7755, "total_steps": 40000, "loss": 0.7189, "lr": 4.5505544263943856e-05, "epoch": 0.24822354522757825, "percentage": 19.39, "elapsed_time": "4:26:21", "remaining_time": "18:27:29", "throughput": 667.93, "total_tokens": 10674416} {"current_steps": 7760, "total_steps": 40000, "loss": 0.7598, "lr": 4.549992663776197e-05, "epoch": 0.2483835861980667, "percentage": 19.4, "elapsed_time": "4:26:23", "remaining_time": "18:26:43", "throughput": 668.28, "total_tokens": 10681152} {"current_steps": 7765, "total_steps": 40000, "loss": 0.8172, "lr": 4.5494305850233786e-05, "epoch": 0.24854362716855516, "percentage": 19.41, "elapsed_time": "4:26:24", "remaining_time": "18:25:57", "throughput": 668.61, "total_tokens": 10687616} {"current_steps": 7770, "total_steps": 40000, "loss": 0.7785, "lr": 4.5488681902226094e-05, "epoch": 0.2487036681390436, "percentage": 19.43, "elapsed_time": "4:26:26", "remaining_time": "18:25:12", "throughput": 668.98, "total_tokens": 10694672} {"current_steps": 7775, "total_steps": 40000, "loss": 0.8774, "lr": 4.5483054794606174e-05, "epoch": 0.24886370910953204, "percentage": 19.44, "elapsed_time": "4:26:28", "remaining_time": "18:24:26", "throughput": 669.38, "total_tokens": 10702240} {"current_steps": 7780, "total_steps": 40000, "loss": 0.7112, "lr": 4.547742452824179e-05, "epoch": 0.24902375008002048, "percentage": 19.45, "elapsed_time": "4:26:29", "remaining_time": "18:23:40", "throughput": 669.72, "total_tokens": 10708752} {"current_steps": 7785, "total_steps": 40000, "loss": 0.9129, "lr": 4.5471791104001215e-05, "epoch": 0.24918379105050892, "percentage": 19.46, "elapsed_time": "4:26:31", "remaining_time": "18:22:55", "throughput": 670.07, "total_tokens": 10715648} {"current_steps": 7790, "total_steps": 40000, "loss": 0.6788, "lr": 4.546615452275319e-05, "epoch": 0.24934383202099739, "percentage": 19.48, "elapsed_time": "4:26:33", "remaining_time": "18:22:09", "throughput": 670.44, "total_tokens": 10722624} {"current_steps": 7795, "total_steps": 40000, "loss": 1.252, "lr": 4.5460514785366944e-05, "epoch": 0.24950387299148583, "percentage": 19.49, "elapsed_time": "4:26:35", "remaining_time": "18:21:24", "throughput": 670.78, "total_tokens": 10729264} {"current_steps": 7800, "total_steps": 40000, "loss": 0.7117, "lr": 4.545487189271219e-05, "epoch": 0.24966391396197427, "percentage": 19.5, "elapsed_time": "4:26:36", "remaining_time": "18:20:38", "throughput": 671.14, "total_tokens": 10736144} {"current_steps": 7800, "total_steps": 40000, "eval_loss": 0.8074867725372314, "epoch": 0.24966391396197427, "percentage": 19.5, "elapsed_time": "4:32:24", "remaining_time": "18:44:34", "throughput": 656.85, "total_tokens": 10736144} {"current_steps": 7805, "total_steps": 40000, "loss": 0.8578, "lr": 4.544922584565914e-05, "epoch": 0.2498239549324627, "percentage": 19.51, "elapsed_time": "4:32:28", "remaining_time": "18:43:55", "throughput": 657.11, "total_tokens": 10742688} {"current_steps": 7810, "total_steps": 40000, "loss": 0.78, "lr": 4.544357664507848e-05, "epoch": 0.24998399590295114, "percentage": 19.53, "elapsed_time": "4:32:30", "remaining_time": "18:43:09", "throughput": 657.47, "total_tokens": 10749680} {"current_steps": 7815, "total_steps": 40000, "loss": 0.6716, "lr": 4.54379242918414e-05, "epoch": 0.2501440368734396, "percentage": 19.54, "elapsed_time": "4:32:31", "remaining_time": "18:42:23", "throughput": 657.83, "total_tokens": 10756800} {"current_steps": 7820, "total_steps": 40000, "loss": 0.5756, "lr": 4.543226878681955e-05, "epoch": 0.25030407784392805, "percentage": 19.55, "elapsed_time": "4:32:33", "remaining_time": "18:41:36", "throughput": 658.17, "total_tokens": 10763552} {"current_steps": 7825, "total_steps": 40000, "loss": 0.6826, "lr": 4.5426610130885087e-05, "epoch": 0.2504641188144165, "percentage": 19.56, "elapsed_time": "4:32:35", "remaining_time": "18:40:50", "throughput": 658.5, "total_tokens": 10769984} {"current_steps": 7830, "total_steps": 40000, "loss": 0.5883, "lr": 4.542094832491064e-05, "epoch": 0.25062415978490493, "percentage": 19.57, "elapsed_time": "4:32:37", "remaining_time": "18:40:04", "throughput": 658.85, "total_tokens": 10776880} {"current_steps": 7835, "total_steps": 40000, "loss": 0.7832, "lr": 4.541528336976934e-05, "epoch": 0.25078420075539337, "percentage": 19.59, "elapsed_time": "4:32:38", "remaining_time": "18:39:17", "throughput": 659.19, "total_tokens": 10783616} {"current_steps": 7840, "total_steps": 40000, "loss": 0.8057, "lr": 4.540961526633479e-05, "epoch": 0.2509442417258818, "percentage": 19.6, "elapsed_time": "4:32:40", "remaining_time": "18:38:31", "throughput": 659.55, "total_tokens": 10790624} {"current_steps": 7845, "total_steps": 40000, "loss": 0.965, "lr": 4.540394401548108e-05, "epoch": 0.25110428269637025, "percentage": 19.61, "elapsed_time": "4:32:42", "remaining_time": "18:37:45", "throughput": 659.9, "total_tokens": 10797552} {"current_steps": 7850, "total_steps": 40000, "loss": 0.9526, "lr": 4.539826961808279e-05, "epoch": 0.2512643236668587, "percentage": 19.62, "elapsed_time": "4:32:44", "remaining_time": "18:36:59", "throughput": 660.26, "total_tokens": 10804576} {"current_steps": 7855, "total_steps": 40000, "loss": 0.7392, "lr": 4.5392592075014994e-05, "epoch": 0.2514243646373472, "percentage": 19.64, "elapsed_time": "4:32:45", "remaining_time": "18:36:13", "throughput": 660.64, "total_tokens": 10811840} {"current_steps": 7860, "total_steps": 40000, "loss": 0.7826, "lr": 4.538691138715322e-05, "epoch": 0.2515844056078356, "percentage": 19.65, "elapsed_time": "4:32:47", "remaining_time": "18:35:27", "throughput": 660.99, "total_tokens": 10818800} {"current_steps": 7865, "total_steps": 40000, "loss": 0.812, "lr": 4.5381227555373516e-05, "epoch": 0.25174444657832407, "percentage": 19.66, "elapsed_time": "4:32:49", "remaining_time": "18:34:41", "throughput": 661.34, "total_tokens": 10825584} {"current_steps": 7870, "total_steps": 40000, "loss": 0.6033, "lr": 4.537554058055239e-05, "epoch": 0.2519044875488125, "percentage": 19.68, "elapsed_time": "4:32:51", "remaining_time": "18:33:56", "throughput": 661.69, "total_tokens": 10832560} {"current_steps": 7875, "total_steps": 40000, "loss": 0.7168, "lr": 4.5369850463566865e-05, "epoch": 0.25206452851930095, "percentage": 19.69, "elapsed_time": "4:32:52", "remaining_time": "18:33:10", "throughput": 662.03, "total_tokens": 10839264} {"current_steps": 7880, "total_steps": 40000, "loss": 0.981, "lr": 4.5364157205294404e-05, "epoch": 0.2522245694897894, "percentage": 19.7, "elapsed_time": "4:32:54", "remaining_time": "18:32:24", "throughput": 662.38, "total_tokens": 10846128} {"current_steps": 7885, "total_steps": 40000, "loss": 0.7731, "lr": 4.5358460806612996e-05, "epoch": 0.2523846104602778, "percentage": 19.71, "elapsed_time": "4:32:56", "remaining_time": "18:31:39", "throughput": 662.75, "total_tokens": 10853376} {"current_steps": 7890, "total_steps": 40000, "loss": 0.7949, "lr": 4.535276126840109e-05, "epoch": 0.25254465143076626, "percentage": 19.73, "elapsed_time": "4:32:57", "remaining_time": "18:30:53", "throughput": 663.11, "total_tokens": 10860384} {"current_steps": 7895, "total_steps": 40000, "loss": 0.969, "lr": 4.5347058591537626e-05, "epoch": 0.2527046924012547, "percentage": 19.74, "elapsed_time": "4:32:59", "remaining_time": "18:30:08", "throughput": 663.46, "total_tokens": 10867264} {"current_steps": 7900, "total_steps": 40000, "loss": 0.8201, "lr": 4.534135277690203e-05, "epoch": 0.25286473337174314, "percentage": 19.75, "elapsed_time": "4:33:01", "remaining_time": "18:29:22", "throughput": 663.85, "total_tokens": 10874848} {"current_steps": 7905, "total_steps": 40000, "loss": 0.7391, "lr": 4.533564382537421e-05, "epoch": 0.2530247743422316, "percentage": 19.76, "elapsed_time": "4:33:03", "remaining_time": "18:28:37", "throughput": 664.18, "total_tokens": 10881344} {"current_steps": 7910, "total_steps": 40000, "loss": 0.7967, "lr": 4.532993173783456e-05, "epoch": 0.2531848153127201, "percentage": 19.78, "elapsed_time": "4:33:04", "remaining_time": "18:27:51", "throughput": 664.52, "total_tokens": 10888080} {"current_steps": 7915, "total_steps": 40000, "loss": 0.6, "lr": 4.5324216515163954e-05, "epoch": 0.2533448562832085, "percentage": 19.79, "elapsed_time": "4:33:06", "remaining_time": "18:27:06", "throughput": 664.87, "total_tokens": 10895072} {"current_steps": 7920, "total_steps": 40000, "loss": 0.7961, "lr": 4.531849815824375e-05, "epoch": 0.25350489725369696, "percentage": 19.8, "elapsed_time": "4:33:08", "remaining_time": "18:26:21", "throughput": 665.23, "total_tokens": 10902128} {"current_steps": 7925, "total_steps": 40000, "loss": 0.7359, "lr": 4.5312776667955795e-05, "epoch": 0.2536649382241854, "percentage": 19.81, "elapsed_time": "4:33:10", "remaining_time": "18:25:36", "throughput": 665.59, "total_tokens": 10909104} {"current_steps": 7930, "total_steps": 40000, "loss": 0.8584, "lr": 4.5307052045182405e-05, "epoch": 0.25382497919467384, "percentage": 19.82, "elapsed_time": "4:33:11", "remaining_time": "18:24:50", "throughput": 665.93, "total_tokens": 10915776} {"current_steps": 7935, "total_steps": 40000, "loss": 0.8748, "lr": 4.53013242908064e-05, "epoch": 0.2539850201651623, "percentage": 19.84, "elapsed_time": "4:33:13", "remaining_time": "18:24:05", "throughput": 666.26, "total_tokens": 10922336} {"current_steps": 7940, "total_steps": 40000, "loss": 0.709, "lr": 4.529559340571107e-05, "epoch": 0.2541450611356507, "percentage": 19.85, "elapsed_time": "4:33:15", "remaining_time": "18:23:20", "throughput": 666.58, "total_tokens": 10928752} {"current_steps": 7945, "total_steps": 40000, "loss": 0.8659, "lr": 4.528985939078018e-05, "epoch": 0.25430510210613916, "percentage": 19.86, "elapsed_time": "4:33:17", "remaining_time": "18:22:35", "throughput": 666.89, "total_tokens": 10935120} {"current_steps": 7950, "total_steps": 40000, "loss": 0.8368, "lr": 4.5284122246898e-05, "epoch": 0.2544651430766276, "percentage": 19.88, "elapsed_time": "4:33:18", "remaining_time": "18:21:51", "throughput": 667.27, "total_tokens": 10942448} {"current_steps": 7955, "total_steps": 40000, "loss": 0.9478, "lr": 4.527838197494926e-05, "epoch": 0.25462518404711604, "percentage": 19.89, "elapsed_time": "4:33:20", "remaining_time": "18:21:06", "throughput": 667.62, "total_tokens": 10949392} {"current_steps": 7960, "total_steps": 40000, "loss": 0.7861, "lr": 4.527263857581918e-05, "epoch": 0.25478522501760453, "percentage": 19.9, "elapsed_time": "4:33:22", "remaining_time": "18:20:21", "throughput": 667.96, "total_tokens": 10956144} {"current_steps": 7965, "total_steps": 40000, "loss": 0.7764, "lr": 4.526689205039347e-05, "epoch": 0.254945265988093, "percentage": 19.91, "elapsed_time": "4:33:24", "remaining_time": "18:19:36", "throughput": 668.29, "total_tokens": 10962736} {"current_steps": 7970, "total_steps": 40000, "loss": 0.7394, "lr": 4.5261142399558324e-05, "epoch": 0.2551053069585814, "percentage": 19.93, "elapsed_time": "4:33:25", "remaining_time": "18:18:51", "throughput": 668.64, "total_tokens": 10969488} {"current_steps": 7975, "total_steps": 40000, "loss": 0.7968, "lr": 4.525538962420041e-05, "epoch": 0.25526534792906985, "percentage": 19.94, "elapsed_time": "4:33:27", "remaining_time": "18:18:07", "throughput": 668.99, "total_tokens": 10976416} {"current_steps": 7980, "total_steps": 40000, "loss": 0.7935, "lr": 4.524963372520685e-05, "epoch": 0.2554253888995583, "percentage": 19.95, "elapsed_time": "4:33:29", "remaining_time": "18:17:22", "throughput": 669.34, "total_tokens": 10983328} {"current_steps": 7985, "total_steps": 40000, "loss": 0.6879, "lr": 4.524387470346531e-05, "epoch": 0.25558542987004673, "percentage": 19.96, "elapsed_time": "4:33:31", "remaining_time": "18:16:38", "throughput": 669.68, "total_tokens": 10990112} {"current_steps": 7990, "total_steps": 40000, "loss": 0.843, "lr": 4.5238112559863885e-05, "epoch": 0.25574547084053517, "percentage": 19.98, "elapsed_time": "4:33:32", "remaining_time": "18:15:53", "throughput": 670.02, "total_tokens": 10996928} {"current_steps": 7995, "total_steps": 40000, "loss": 0.7428, "lr": 4.5232347295291175e-05, "epoch": 0.2559055118110236, "percentage": 19.99, "elapsed_time": "4:33:34", "remaining_time": "18:15:09", "throughput": 670.36, "total_tokens": 11003632} {"current_steps": 8000, "total_steps": 40000, "loss": 0.8245, "lr": 4.522657891063626e-05, "epoch": 0.25606555278151205, "percentage": 20.0, "elapsed_time": "4:33:36", "remaining_time": "18:14:24", "throughput": 670.71, "total_tokens": 11010512} {"current_steps": 8000, "total_steps": 40000, "eval_loss": 0.8047347068786621, "epoch": 0.25606555278151205, "percentage": 20.0, "elapsed_time": "4:39:24", "remaining_time": "18:37:36", "throughput": 656.79, "total_tokens": 11010512} {"current_steps": 8005, "total_steps": 40000, "loss": 0.6589, "lr": 4.52208074067887e-05, "epoch": 0.2562255937520005, "percentage": 20.01, "elapsed_time": "4:39:27", "remaining_time": "18:36:57", "throughput": 657.09, "total_tokens": 11017616} {"current_steps": 8010, "total_steps": 40000, "loss": 0.6991, "lr": 4.5215032784638516e-05, "epoch": 0.25638563472248893, "percentage": 20.03, "elapsed_time": "4:39:29", "remaining_time": "18:36:11", "throughput": 657.42, "total_tokens": 11024288} {"current_steps": 8015, "total_steps": 40000, "loss": 0.8158, "lr": 4.5209255045076245e-05, "epoch": 0.2565456756929774, "percentage": 20.04, "elapsed_time": "4:39:30", "remaining_time": "18:35:26", "throughput": 657.75, "total_tokens": 11031024} {"current_steps": 8020, "total_steps": 40000, "loss": 0.7138, "lr": 4.5203474188992875e-05, "epoch": 0.25670571666346587, "percentage": 20.05, "elapsed_time": "4:39:32", "remaining_time": "18:34:41", "throughput": 658.09, "total_tokens": 11037952} {"current_steps": 8025, "total_steps": 40000, "loss": 0.8326, "lr": 4.51976902172799e-05, "epoch": 0.2568657576339543, "percentage": 20.06, "elapsed_time": "4:39:34", "remaining_time": "18:33:56", "throughput": 658.42, "total_tokens": 11044640} {"current_steps": 8030, "total_steps": 40000, "loss": 0.7952, "lr": 4.519190313082927e-05, "epoch": 0.25702579860444275, "percentage": 20.08, "elapsed_time": "4:39:36", "remaining_time": "18:33:10", "throughput": 658.76, "total_tokens": 11051376} {"current_steps": 8035, "total_steps": 40000, "loss": 0.7299, "lr": 4.518611293053343e-05, "epoch": 0.2571858395749312, "percentage": 20.09, "elapsed_time": "4:39:37", "remaining_time": "18:32:25", "throughput": 659.11, "total_tokens": 11058496} {"current_steps": 8040, "total_steps": 40000, "loss": 0.5339, "lr": 4.51803196172853e-05, "epoch": 0.2573458805454196, "percentage": 20.1, "elapsed_time": "4:39:39", "remaining_time": "18:31:40", "throughput": 659.45, "total_tokens": 11065264} {"current_steps": 8045, "total_steps": 40000, "loss": 0.7572, "lr": 4.517452319197828e-05, "epoch": 0.25750592151590807, "percentage": 20.11, "elapsed_time": "4:39:41", "remaining_time": "18:30:55", "throughput": 659.8, "total_tokens": 11072288} {"current_steps": 8050, "total_steps": 40000, "loss": 1.0265, "lr": 4.5168723655506265e-05, "epoch": 0.2576659624863965, "percentage": 20.12, "elapsed_time": "4:39:43", "remaining_time": "18:30:10", "throughput": 660.15, "total_tokens": 11079264} {"current_steps": 8055, "total_steps": 40000, "loss": 0.6469, "lr": 4.51629210087636e-05, "epoch": 0.25782600345688494, "percentage": 20.14, "elapsed_time": "4:39:44", "remaining_time": "18:29:25", "throughput": 660.49, "total_tokens": 11086080} {"current_steps": 8060, "total_steps": 40000, "loss": 0.9814, "lr": 4.515711525264513e-05, "epoch": 0.2579860444273734, "percentage": 20.15, "elapsed_time": "4:39:46", "remaining_time": "18:28:41", "throughput": 660.84, "total_tokens": 11093264} {"current_steps": 8065, "total_steps": 40000, "loss": 0.9178, "lr": 4.5151306388046175e-05, "epoch": 0.2581460853978619, "percentage": 20.16, "elapsed_time": "4:39:48", "remaining_time": "18:27:56", "throughput": 661.18, "total_tokens": 11100080} {"current_steps": 8070, "total_steps": 40000, "loss": 0.7838, "lr": 4.514549441586255e-05, "epoch": 0.2583061263683503, "percentage": 20.18, "elapsed_time": "4:39:50", "remaining_time": "18:27:12", "throughput": 661.53, "total_tokens": 11107248} {"current_steps": 8075, "total_steps": 40000, "loss": 0.8067, "lr": 4.513967933699051e-05, "epoch": 0.25846616733883876, "percentage": 20.19, "elapsed_time": "4:39:51", "remaining_time": "18:26:27", "throughput": 661.87, "total_tokens": 11114112} {"current_steps": 8080, "total_steps": 40000, "loss": 0.6956, "lr": 4.513386115232684e-05, "epoch": 0.2586262083093272, "percentage": 20.2, "elapsed_time": "4:39:53", "remaining_time": "18:25:43", "throughput": 662.21, "total_tokens": 11120976} {"current_steps": 8085, "total_steps": 40000, "loss": 0.8097, "lr": 4.5128039862768745e-05, "epoch": 0.25878624927981564, "percentage": 20.21, "elapsed_time": "4:39:55", "remaining_time": "18:24:58", "throughput": 662.54, "total_tokens": 11127680} {"current_steps": 8090, "total_steps": 40000, "loss": 0.7326, "lr": 4.512221546921397e-05, "epoch": 0.2589462902503041, "percentage": 20.23, "elapsed_time": "4:39:57", "remaining_time": "18:24:14", "throughput": 662.9, "total_tokens": 11134736} {"current_steps": 8095, "total_steps": 40000, "loss": 0.7551, "lr": 4.5116387972560694e-05, "epoch": 0.2591063312207925, "percentage": 20.24, "elapsed_time": "4:39:58", "remaining_time": "18:23:29", "throughput": 663.23, "total_tokens": 11141440} {"current_steps": 8100, "total_steps": 40000, "loss": 0.7341, "lr": 4.511055737370759e-05, "epoch": 0.25926637219128096, "percentage": 20.25, "elapsed_time": "4:40:00", "remaining_time": "18:22:45", "throughput": 663.55, "total_tokens": 11147968} {"current_steps": 8105, "total_steps": 40000, "loss": 0.6932, "lr": 4.510472367355383e-05, "epoch": 0.2594264131617694, "percentage": 20.26, "elapsed_time": "4:40:02", "remaining_time": "18:22:00", "throughput": 663.89, "total_tokens": 11154880} {"current_steps": 8110, "total_steps": 40000, "loss": 1.076, "lr": 4.509888687299901e-05, "epoch": 0.25958645413225784, "percentage": 20.28, "elapsed_time": "4:40:04", "remaining_time": "18:21:16", "throughput": 664.22, "total_tokens": 11161504} {"current_steps": 8115, "total_steps": 40000, "loss": 0.7725, "lr": 4.5093046972943266e-05, "epoch": 0.2597464951027463, "percentage": 20.29, "elapsed_time": "4:40:05", "remaining_time": "18:20:32", "throughput": 664.59, "total_tokens": 11168912} {"current_steps": 8120, "total_steps": 40000, "loss": 0.6752, "lr": 4.508720397428717e-05, "epoch": 0.2599065360732348, "percentage": 20.3, "elapsed_time": "4:40:07", "remaining_time": "18:19:48", "throughput": 664.93, "total_tokens": 11175744} {"current_steps": 8125, "total_steps": 40000, "loss": 0.875, "lr": 4.508135787793178e-05, "epoch": 0.2600665770437232, "percentage": 20.31, "elapsed_time": "4:40:09", "remaining_time": "18:19:03", "throughput": 665.26, "total_tokens": 11182464} {"current_steps": 8130, "total_steps": 40000, "loss": 0.7867, "lr": 4.5075508684778664e-05, "epoch": 0.26022661801421165, "percentage": 20.32, "elapsed_time": "4:40:10", "remaining_time": "18:18:19", "throughput": 665.61, "total_tokens": 11189536} {"current_steps": 8135, "total_steps": 40000, "loss": 0.9755, "lr": 4.506965639572982e-05, "epoch": 0.2603866589847001, "percentage": 20.34, "elapsed_time": "4:40:12", "remaining_time": "18:17:35", "throughput": 665.96, "total_tokens": 11196672} {"current_steps": 8140, "total_steps": 40000, "loss": 0.7639, "lr": 4.506380101168774e-05, "epoch": 0.26054669995518853, "percentage": 20.35, "elapsed_time": "4:40:14", "remaining_time": "18:16:51", "throughput": 666.29, "total_tokens": 11203248} {"current_steps": 8145, "total_steps": 40000, "loss": 0.846, "lr": 4.505794253355542e-05, "epoch": 0.26070674092567697, "percentage": 20.36, "elapsed_time": "4:40:16", "remaining_time": "18:16:07", "throughput": 666.64, "total_tokens": 11210352} {"current_steps": 8150, "total_steps": 40000, "loss": 0.6965, "lr": 4.5052080962236286e-05, "epoch": 0.2608667818961654, "percentage": 20.38, "elapsed_time": "4:40:17", "remaining_time": "18:15:23", "throughput": 666.98, "total_tokens": 11217248} {"current_steps": 8155, "total_steps": 40000, "loss": 0.6479, "lr": 4.504621629863428e-05, "epoch": 0.26102682286665385, "percentage": 20.39, "elapsed_time": "4:40:19", "remaining_time": "18:14:40", "throughput": 667.3, "total_tokens": 11223792} {"current_steps": 8160, "total_steps": 40000, "loss": 0.8582, "lr": 4.504034854365381e-05, "epoch": 0.2611868638371423, "percentage": 20.4, "elapsed_time": "4:40:21", "remaining_time": "18:13:56", "throughput": 667.64, "total_tokens": 11230544} {"current_steps": 8165, "total_steps": 40000, "loss": 0.9226, "lr": 4.503447769819974e-05, "epoch": 0.26134690480763073, "percentage": 20.41, "elapsed_time": "4:40:23", "remaining_time": "18:13:12", "throughput": 667.95, "total_tokens": 11236976} {"current_steps": 8170, "total_steps": 40000, "loss": 0.8236, "lr": 4.502860376317745e-05, "epoch": 0.26150694577811917, "percentage": 20.42, "elapsed_time": "4:40:24", "remaining_time": "18:12:28", "throughput": 668.29, "total_tokens": 11243936} {"current_steps": 8175, "total_steps": 40000, "loss": 0.9074, "lr": 4.502272673949276e-05, "epoch": 0.26166698674860767, "percentage": 20.44, "elapsed_time": "4:40:26", "remaining_time": "18:11:45", "throughput": 668.62, "total_tokens": 11250576} {"current_steps": 8180, "total_steps": 40000, "loss": 0.578, "lr": 4.501684662805199e-05, "epoch": 0.2618270277190961, "percentage": 20.45, "elapsed_time": "4:40:28", "remaining_time": "18:11:01", "throughput": 668.93, "total_tokens": 11257008} {"current_steps": 8185, "total_steps": 40000, "loss": 0.5554, "lr": 4.5010963429761924e-05, "epoch": 0.26198706868958455, "percentage": 20.46, "elapsed_time": "4:40:30", "remaining_time": "18:10:18", "throughput": 669.28, "total_tokens": 11263952} {"current_steps": 8190, "total_steps": 40000, "loss": 0.736, "lr": 4.500507714552982e-05, "epoch": 0.262147109660073, "percentage": 20.47, "elapsed_time": "4:40:31", "remaining_time": "18:09:34", "throughput": 669.63, "total_tokens": 11271056} {"current_steps": 8195, "total_steps": 40000, "loss": 0.8353, "lr": 4.499918777626342e-05, "epoch": 0.2623071506305614, "percentage": 20.49, "elapsed_time": "4:40:33", "remaining_time": "18:08:51", "throughput": 669.94, "total_tokens": 11277456} {"current_steps": 8200, "total_steps": 40000, "loss": 0.6891, "lr": 4.499329532287093e-05, "epoch": 0.26246719160104987, "percentage": 20.5, "elapsed_time": "4:40:35", "remaining_time": "18:08:07", "throughput": 670.27, "total_tokens": 11284128} {"current_steps": 8200, "total_steps": 40000, "eval_loss": 0.8022733330726624, "epoch": 0.26246719160104987, "percentage": 20.5, "elapsed_time": "4:46:22", "remaining_time": "18:30:35", "throughput": 656.72, "total_tokens": 11284128} {"current_steps": 8205, "total_steps": 40000, "loss": 0.7967, "lr": 4.4987399786261064e-05, "epoch": 0.2626272325715383, "percentage": 20.51, "elapsed_time": "4:46:26", "remaining_time": "18:29:57", "throughput": 656.98, "total_tokens": 11290816} {"current_steps": 8210, "total_steps": 40000, "loss": 0.7657, "lr": 4.498150116734297e-05, "epoch": 0.26278727354202674, "percentage": 20.52, "elapsed_time": "4:46:27", "remaining_time": "18:29:12", "throughput": 657.28, "total_tokens": 11297120} {"current_steps": 8215, "total_steps": 40000, "loss": 0.7951, "lr": 4.4975599467026294e-05, "epoch": 0.2629473145125152, "percentage": 20.54, "elapsed_time": "4:46:29", "remaining_time": "18:28:28", "throughput": 657.62, "total_tokens": 11304192} {"current_steps": 8220, "total_steps": 40000, "loss": 0.73, "lr": 4.496969468622114e-05, "epoch": 0.2631073554830036, "percentage": 20.55, "elapsed_time": "4:46:31", "remaining_time": "18:27:44", "throughput": 657.94, "total_tokens": 11310736} {"current_steps": 8225, "total_steps": 40000, "loss": 0.7888, "lr": 4.496378682583813e-05, "epoch": 0.2632673964534921, "percentage": 20.56, "elapsed_time": "4:46:32", "remaining_time": "18:27:00", "throughput": 658.26, "total_tokens": 11317520} {"current_steps": 8230, "total_steps": 40000, "loss": 1.07, "lr": 4.495787588678829e-05, "epoch": 0.26342743742398056, "percentage": 20.57, "elapsed_time": "4:46:34", "remaining_time": "18:26:16", "throughput": 658.61, "total_tokens": 11324544} {"current_steps": 8235, "total_steps": 40000, "loss": 0.6886, "lr": 4.4951961869983196e-05, "epoch": 0.263587478394469, "percentage": 20.59, "elapsed_time": "4:46:36", "remaining_time": "18:25:32", "throughput": 658.93, "total_tokens": 11331296} {"current_steps": 8240, "total_steps": 40000, "loss": 0.7698, "lr": 4.494604477633485e-05, "epoch": 0.26374751936495744, "percentage": 20.6, "elapsed_time": "4:46:38", "remaining_time": "18:24:48", "throughput": 659.25, "total_tokens": 11337920} {"current_steps": 8245, "total_steps": 40000, "loss": 0.6424, "lr": 4.4940124606755734e-05, "epoch": 0.2639075603354459, "percentage": 20.61, "elapsed_time": "4:46:39", "remaining_time": "18:24:04", "throughput": 659.6, "total_tokens": 11345072} {"current_steps": 8250, "total_steps": 40000, "loss": 0.6193, "lr": 4.493420136215882e-05, "epoch": 0.2640676013059343, "percentage": 20.62, "elapsed_time": "4:46:41", "remaining_time": "18:23:20", "throughput": 659.93, "total_tokens": 11351856} {"current_steps": 8255, "total_steps": 40000, "loss": 0.8344, "lr": 4.492827504345756e-05, "epoch": 0.26422764227642276, "percentage": 20.64, "elapsed_time": "4:46:43", "remaining_time": "18:22:36", "throughput": 660.28, "total_tokens": 11359088} {"current_steps": 8260, "total_steps": 40000, "loss": 0.7309, "lr": 4.492234565156584e-05, "epoch": 0.2643876832469112, "percentage": 20.65, "elapsed_time": "4:46:45", "remaining_time": "18:21:52", "throughput": 660.6, "total_tokens": 11365680} {"current_steps": 8265, "total_steps": 40000, "loss": 0.5442, "lr": 4.491641318739807e-05, "epoch": 0.26454772421739964, "percentage": 20.66, "elapsed_time": "4:46:46", "remaining_time": "18:21:09", "throughput": 660.93, "total_tokens": 11372576} {"current_steps": 8270, "total_steps": 40000, "loss": 0.8971, "lr": 4.4910477651869096e-05, "epoch": 0.2647077651878881, "percentage": 20.67, "elapsed_time": "4:46:48", "remaining_time": "18:20:25", "throughput": 661.25, "total_tokens": 11379120} {"current_steps": 8275, "total_steps": 40000, "loss": 1.0839, "lr": 4.4904539045894254e-05, "epoch": 0.2648678061583765, "percentage": 20.69, "elapsed_time": "4:46:50", "remaining_time": "18:19:41", "throughput": 661.57, "total_tokens": 11385888} {"current_steps": 8280, "total_steps": 40000, "loss": 0.6296, "lr": 4.4898597370389364e-05, "epoch": 0.265027847128865, "percentage": 20.7, "elapsed_time": "4:46:52", "remaining_time": "18:18:58", "throughput": 661.93, "total_tokens": 11393152} {"current_steps": 8285, "total_steps": 40000, "loss": 0.8768, "lr": 4.489265262627069e-05, "epoch": 0.26518788809935345, "percentage": 20.71, "elapsed_time": "4:46:53", "remaining_time": "18:18:14", "throughput": 662.23, "total_tokens": 11399584} {"current_steps": 8290, "total_steps": 40000, "loss": 0.6973, "lr": 4.488670481445499e-05, "epoch": 0.2653479290698419, "percentage": 20.72, "elapsed_time": "4:46:55", "remaining_time": "18:17:31", "throughput": 662.56, "total_tokens": 11406384} {"current_steps": 8295, "total_steps": 40000, "loss": 0.8432, "lr": 4.488075393585951e-05, "epoch": 0.26550797004033033, "percentage": 20.74, "elapsed_time": "4:46:57", "remaining_time": "18:16:47", "throughput": 662.89, "total_tokens": 11413232} {"current_steps": 8300, "total_steps": 40000, "loss": 0.841, "lr": 4.487479999140193e-05, "epoch": 0.26566801101081877, "percentage": 20.75, "elapsed_time": "4:46:59", "remaining_time": "18:16:04", "throughput": 663.25, "total_tokens": 11420560} {"current_steps": 8305, "total_steps": 40000, "loss": 0.7301, "lr": 4.4868842982000425e-05, "epoch": 0.2658280519813072, "percentage": 20.76, "elapsed_time": "4:47:00", "remaining_time": "18:15:20", "throughput": 663.56, "total_tokens": 11427024} {"current_steps": 8310, "total_steps": 40000, "loss": 0.7947, "lr": 4.486288290857365e-05, "epoch": 0.26598809295179565, "percentage": 20.77, "elapsed_time": "4:47:02", "remaining_time": "18:14:37", "throughput": 663.88, "total_tokens": 11433696} {"current_steps": 8315, "total_steps": 40000, "loss": 0.7445, "lr": 4.4856919772040715e-05, "epoch": 0.2661481339222841, "percentage": 20.79, "elapsed_time": "4:47:04", "remaining_time": "18:13:54", "throughput": 664.2, "total_tokens": 11440352} {"current_steps": 8320, "total_steps": 40000, "loss": 0.7537, "lr": 4.485095357332122e-05, "epoch": 0.26630817489277253, "percentage": 20.8, "elapsed_time": "4:47:05", "remaining_time": "18:13:11", "throughput": 664.52, "total_tokens": 11446912} {"current_steps": 8325, "total_steps": 40000, "loss": 0.9364, "lr": 4.484498431333521e-05, "epoch": 0.26646821586326097, "percentage": 20.81, "elapsed_time": "4:47:07", "remaining_time": "18:12:28", "throughput": 664.85, "total_tokens": 11453872} {"current_steps": 8330, "total_steps": 40000, "loss": 0.7625, "lr": 4.4839011993003245e-05, "epoch": 0.26662825683374947, "percentage": 20.82, "elapsed_time": "4:47:09", "remaining_time": "18:11:44", "throughput": 665.19, "total_tokens": 11460832} {"current_steps": 8335, "total_steps": 40000, "loss": 0.8641, "lr": 4.4833036613246305e-05, "epoch": 0.2667882978042379, "percentage": 20.84, "elapsed_time": "4:47:11", "remaining_time": "18:11:01", "throughput": 665.53, "total_tokens": 11467904} {"current_steps": 8340, "total_steps": 40000, "loss": 0.703, "lr": 4.482705817498589e-05, "epoch": 0.26694833877472635, "percentage": 20.85, "elapsed_time": "4:47:12", "remaining_time": "18:10:18", "throughput": 665.85, "total_tokens": 11474560} {"current_steps": 8345, "total_steps": 40000, "loss": 0.5081, "lr": 4.4821076679143934e-05, "epoch": 0.2671083797452148, "percentage": 20.86, "elapsed_time": "4:47:14", "remaining_time": "18:09:35", "throughput": 666.17, "total_tokens": 11481264} {"current_steps": 8350, "total_steps": 40000, "loss": 0.8506, "lr": 4.481509212664288e-05, "epoch": 0.2672684207157032, "percentage": 20.88, "elapsed_time": "4:47:16", "remaining_time": "18:08:53", "throughput": 666.58, "total_tokens": 11489360} {"current_steps": 8355, "total_steps": 40000, "loss": 0.9078, "lr": 4.480910451840559e-05, "epoch": 0.26742846168619167, "percentage": 20.89, "elapsed_time": "4:47:18", "remaining_time": "18:08:10", "throughput": 666.9, "total_tokens": 11496112} {"current_steps": 8360, "total_steps": 40000, "loss": 0.9545, "lr": 4.480311385535546e-05, "epoch": 0.2675885026566801, "percentage": 20.9, "elapsed_time": "4:47:19", "remaining_time": "18:07:27", "throughput": 667.24, "total_tokens": 11503088} {"current_steps": 8365, "total_steps": 40000, "loss": 0.9921, "lr": 4.47971201384163e-05, "epoch": 0.26774854362716854, "percentage": 20.91, "elapsed_time": "4:47:21", "remaining_time": "18:06:44", "throughput": 667.55, "total_tokens": 11509632} {"current_steps": 8370, "total_steps": 40000, "loss": 0.7421, "lr": 4.4791123368512446e-05, "epoch": 0.267908584597657, "percentage": 20.93, "elapsed_time": "4:47:23", "remaining_time": "18:06:02", "throughput": 667.86, "total_tokens": 11516160} {"current_steps": 8375, "total_steps": 40000, "loss": 0.575, "lr": 4.478512354656864e-05, "epoch": 0.2680686255681454, "percentage": 20.94, "elapsed_time": "4:47:25", "remaining_time": "18:05:19", "throughput": 668.18, "total_tokens": 11522720} {"current_steps": 8380, "total_steps": 40000, "loss": 0.5385, "lr": 4.477912067351016e-05, "epoch": 0.26822866653863386, "percentage": 20.95, "elapsed_time": "4:47:26", "remaining_time": "18:04:36", "throughput": 668.51, "total_tokens": 11529696} {"current_steps": 8385, "total_steps": 40000, "loss": 0.6108, "lr": 4.477311475026271e-05, "epoch": 0.26838870750912236, "percentage": 20.96, "elapsed_time": "4:47:28", "remaining_time": "18:03:54", "throughput": 668.83, "total_tokens": 11536304} {"current_steps": 8390, "total_steps": 40000, "loss": 0.513, "lr": 4.476710577775248e-05, "epoch": 0.2685487484796108, "percentage": 20.97, "elapsed_time": "4:47:30", "remaining_time": "18:03:11", "throughput": 669.17, "total_tokens": 11543392} {"current_steps": 8395, "total_steps": 40000, "loss": 0.9666, "lr": 4.476109375690612e-05, "epoch": 0.26870878945009924, "percentage": 20.99, "elapsed_time": "4:47:31", "remaining_time": "18:02:29", "throughput": 669.49, "total_tokens": 11550112} {"current_steps": 8400, "total_steps": 40000, "loss": 0.8266, "lr": 4.4755078688650784e-05, "epoch": 0.2688688304205877, "percentage": 21.0, "elapsed_time": "4:47:33", "remaining_time": "18:01:46", "throughput": 669.82, "total_tokens": 11556816} {"current_steps": 8400, "total_steps": 40000, "eval_loss": 0.8010474443435669, "epoch": 0.2688688304205877, "percentage": 21.0, "elapsed_time": "4:53:22", "remaining_time": "18:23:38", "throughput": 656.55, "total_tokens": 11556816} {"current_steps": 8405, "total_steps": 40000, "loss": 0.7031, "lr": 4.474906057391406e-05, "epoch": 0.2690288713910761, "percentage": 21.01, "elapsed_time": "4:53:25", "remaining_time": "18:23:01", "throughput": 656.82, "total_tokens": 11563776} {"current_steps": 8410, "total_steps": 40000, "loss": 0.6968, "lr": 4.4743039413624e-05, "epoch": 0.26918891236156456, "percentage": 21.02, "elapsed_time": "4:53:27", "remaining_time": "18:22:18", "throughput": 657.15, "total_tokens": 11570752} {"current_steps": 8415, "total_steps": 40000, "loss": 0.7314, "lr": 4.473701520870916e-05, "epoch": 0.269348953332053, "percentage": 21.04, "elapsed_time": "4:53:29", "remaining_time": "18:21:35", "throughput": 657.46, "total_tokens": 11577392} {"current_steps": 8420, "total_steps": 40000, "loss": 0.6907, "lr": 4.4730987960098544e-05, "epoch": 0.26950899430254144, "percentage": 21.05, "elapsed_time": "4:53:31", "remaining_time": "18:20:51", "throughput": 657.75, "total_tokens": 11583760} {"current_steps": 8425, "total_steps": 40000, "loss": 0.9258, "lr": 4.4724957668721635e-05, "epoch": 0.2696690352730299, "percentage": 21.06, "elapsed_time": "4:53:32", "remaining_time": "18:20:08", "throughput": 658.06, "total_tokens": 11590304} {"current_steps": 8430, "total_steps": 40000, "loss": 0.7573, "lr": 4.471892433550836e-05, "epoch": 0.2698290762435183, "percentage": 21.07, "elapsed_time": "4:53:34", "remaining_time": "18:19:25", "throughput": 658.39, "total_tokens": 11597232} {"current_steps": 8435, "total_steps": 40000, "loss": 0.6952, "lr": 4.471288796138916e-05, "epoch": 0.2699891172140068, "percentage": 21.09, "elapsed_time": "4:53:36", "remaining_time": "18:18:42", "throughput": 658.72, "total_tokens": 11604192} {"current_steps": 8440, "total_steps": 40000, "loss": 0.7604, "lr": 4.470684854729491e-05, "epoch": 0.27014915818449525, "percentage": 21.1, "elapsed_time": "4:53:38", "remaining_time": "18:17:59", "throughput": 659.05, "total_tokens": 11611152} {"current_steps": 8445, "total_steps": 40000, "loss": 0.8223, "lr": 4.4700806094156955e-05, "epoch": 0.2703091991549837, "percentage": 21.11, "elapsed_time": "4:53:39", "remaining_time": "18:17:16", "throughput": 659.41, "total_tokens": 11618640} {"current_steps": 8450, "total_steps": 40000, "loss": 0.7713, "lr": 4.469476060290713e-05, "epoch": 0.27046924012547213, "percentage": 21.12, "elapsed_time": "4:53:41", "remaining_time": "18:16:33", "throughput": 659.74, "total_tokens": 11625520} {"current_steps": 8455, "total_steps": 40000, "loss": 0.7054, "lr": 4.468871207447772e-05, "epoch": 0.27062928109596057, "percentage": 21.14, "elapsed_time": "4:53:43", "remaining_time": "18:15:50", "throughput": 660.05, "total_tokens": 11632224} {"current_steps": 8460, "total_steps": 40000, "loss": 0.8985, "lr": 4.4682660509801486e-05, "epoch": 0.270789322066449, "percentage": 21.15, "elapsed_time": "4:53:44", "remaining_time": "18:15:08", "throughput": 660.36, "total_tokens": 11638736} {"current_steps": 8465, "total_steps": 40000, "loss": 0.676, "lr": 4.467660590981165e-05, "epoch": 0.27094936303693745, "percentage": 21.16, "elapsed_time": "4:53:46", "remaining_time": "18:14:25", "throughput": 660.67, "total_tokens": 11645440} {"current_steps": 8470, "total_steps": 40000, "loss": 0.5955, "lr": 4.467054827544191e-05, "epoch": 0.2711094040074259, "percentage": 21.18, "elapsed_time": "4:53:48", "remaining_time": "18:13:42", "throughput": 660.97, "total_tokens": 11651840} {"current_steps": 8475, "total_steps": 40000, "loss": 0.7763, "lr": 4.4664487607626434e-05, "epoch": 0.27126944497791433, "percentage": 21.19, "elapsed_time": "4:53:50", "remaining_time": "18:13:00", "throughput": 661.3, "total_tokens": 11658848} {"current_steps": 8480, "total_steps": 40000, "loss": 0.9152, "lr": 4.4658423907299845e-05, "epoch": 0.27142948594840277, "percentage": 21.2, "elapsed_time": "4:53:51", "remaining_time": "18:12:17", "throughput": 661.63, "total_tokens": 11665728} {"current_steps": 8485, "total_steps": 40000, "loss": 0.8197, "lr": 4.465235717539725e-05, "epoch": 0.2715895269188912, "percentage": 21.21, "elapsed_time": "4:53:53", "remaining_time": "18:11:34", "throughput": 661.94, "total_tokens": 11672352} {"current_steps": 8490, "total_steps": 40000, "loss": 0.8217, "lr": 4.464628741285421e-05, "epoch": 0.2717495678893797, "percentage": 21.22, "elapsed_time": "4:53:55", "remaining_time": "18:10:52", "throughput": 662.24, "total_tokens": 11678912} {"current_steps": 8495, "total_steps": 40000, "loss": 0.7768, "lr": 4.4640214620606754e-05, "epoch": 0.27190960885986815, "percentage": 21.24, "elapsed_time": "4:53:57", "remaining_time": "18:10:09", "throughput": 662.55, "total_tokens": 11685408} {"current_steps": 8500, "total_steps": 40000, "loss": 0.774, "lr": 4.46341387995914e-05, "epoch": 0.2720696498303566, "percentage": 21.25, "elapsed_time": "4:53:58", "remaining_time": "18:09:27", "throughput": 662.87, "total_tokens": 11692336} {"current_steps": 8505, "total_steps": 40000, "loss": 0.6098, "lr": 4.4628059950745106e-05, "epoch": 0.272229690800845, "percentage": 21.26, "elapsed_time": "4:54:00", "remaining_time": "18:08:45", "throughput": 663.22, "total_tokens": 11699536} {"current_steps": 8510, "total_steps": 40000, "loss": 0.5726, "lr": 4.4621978075005297e-05, "epoch": 0.27238973177133347, "percentage": 21.27, "elapsed_time": "4:54:02", "remaining_time": "18:08:02", "throughput": 663.56, "total_tokens": 11706816} {"current_steps": 8515, "total_steps": 40000, "loss": 0.9518, "lr": 4.461589317330989e-05, "epoch": 0.2725497727418219, "percentage": 21.29, "elapsed_time": "4:54:04", "remaining_time": "18:07:20", "throughput": 663.92, "total_tokens": 11714224} {"current_steps": 8520, "total_steps": 40000, "loss": 0.7795, "lr": 4.460980524659724e-05, "epoch": 0.27270981371231034, "percentage": 21.3, "elapsed_time": "4:54:05", "remaining_time": "18:06:38", "throughput": 664.24, "total_tokens": 11721024} {"current_steps": 8525, "total_steps": 40000, "loss": 0.7904, "lr": 4.46037142958062e-05, "epoch": 0.2728698546827988, "percentage": 21.31, "elapsed_time": "4:54:07", "remaining_time": "18:05:56", "throughput": 664.56, "total_tokens": 11727872} {"current_steps": 8530, "total_steps": 40000, "loss": 0.9366, "lr": 4.4597620321876046e-05, "epoch": 0.2730298956532872, "percentage": 21.32, "elapsed_time": "4:54:09", "remaining_time": "18:05:14", "throughput": 664.88, "total_tokens": 11734688} {"current_steps": 8535, "total_steps": 40000, "loss": 0.6497, "lr": 4.459152332574656e-05, "epoch": 0.27318993662377566, "percentage": 21.34, "elapsed_time": "4:54:11", "remaining_time": "18:04:31", "throughput": 665.2, "total_tokens": 11741392} {"current_steps": 8540, "total_steps": 40000, "loss": 0.6896, "lr": 4.4585423308357985e-05, "epoch": 0.2733499775942641, "percentage": 21.35, "elapsed_time": "4:54:12", "remaining_time": "18:03:49", "throughput": 665.51, "total_tokens": 11748000} {"current_steps": 8545, "total_steps": 40000, "loss": 0.7808, "lr": 4.457932027065102e-05, "epoch": 0.2735100185647526, "percentage": 21.36, "elapsed_time": "4:54:14", "remaining_time": "18:03:07", "throughput": 665.83, "total_tokens": 11754896} {"current_steps": 8550, "total_steps": 40000, "loss": 0.7977, "lr": 4.45732142135668e-05, "epoch": 0.27367005953524104, "percentage": 21.38, "elapsed_time": "4:54:16", "remaining_time": "18:02:26", "throughput": 666.16, "total_tokens": 11761952} {"current_steps": 8555, "total_steps": 40000, "loss": 0.7315, "lr": 4.4567105138046986e-05, "epoch": 0.2738301005057295, "percentage": 21.39, "elapsed_time": "4:54:17", "remaining_time": "18:01:44", "throughput": 666.48, "total_tokens": 11768688} {"current_steps": 8560, "total_steps": 40000, "loss": 0.8712, "lr": 4.456099304503365e-05, "epoch": 0.2739901414762179, "percentage": 21.4, "elapsed_time": "4:54:19", "remaining_time": "18:01:02", "throughput": 666.81, "total_tokens": 11775632} {"current_steps": 8565, "total_steps": 40000, "loss": 0.6637, "lr": 4.455487793546939e-05, "epoch": 0.27415018244670636, "percentage": 21.41, "elapsed_time": "4:54:21", "remaining_time": "18:00:20", "throughput": 667.13, "total_tokens": 11782464} {"current_steps": 8570, "total_steps": 40000, "loss": 1.1532, "lr": 4.454875981029719e-05, "epoch": 0.2743102234171948, "percentage": 21.43, "elapsed_time": "4:54:23", "remaining_time": "17:59:38", "throughput": 667.45, "total_tokens": 11789264} {"current_steps": 8575, "total_steps": 40000, "loss": 0.6277, "lr": 4.454263867046057e-05, "epoch": 0.27447026438768324, "percentage": 21.44, "elapsed_time": "4:54:24", "remaining_time": "17:58:57", "throughput": 667.75, "total_tokens": 11795680} {"current_steps": 8580, "total_steps": 40000, "loss": 0.8329, "lr": 4.4536514516903484e-05, "epoch": 0.2746303053581717, "percentage": 21.45, "elapsed_time": "4:54:26", "remaining_time": "17:58:15", "throughput": 668.04, "total_tokens": 11802064} {"current_steps": 8585, "total_steps": 40000, "loss": 0.7633, "lr": 4.453038735057034e-05, "epoch": 0.2747903463286601, "percentage": 21.46, "elapsed_time": "4:54:28", "remaining_time": "17:57:33", "throughput": 668.35, "total_tokens": 11808720} {"current_steps": 8590, "total_steps": 40000, "loss": 0.5594, "lr": 4.4524257172406034e-05, "epoch": 0.27495038729914856, "percentage": 21.48, "elapsed_time": "4:54:30", "remaining_time": "17:56:52", "throughput": 668.67, "total_tokens": 11815536} {"current_steps": 8595, "total_steps": 40000, "loss": 0.7566, "lr": 4.451812398335592e-05, "epoch": 0.27511042826963705, "percentage": 21.49, "elapsed_time": "4:54:31", "remaining_time": "17:56:10", "throughput": 668.98, "total_tokens": 11822080} {"current_steps": 8600, "total_steps": 40000, "loss": 0.9607, "lr": 4.4511987784365805e-05, "epoch": 0.2752704692401255, "percentage": 21.5, "elapsed_time": "4:54:33", "remaining_time": "17:55:29", "throughput": 669.29, "total_tokens": 11828816} {"current_steps": 8600, "total_steps": 40000, "eval_loss": 0.7989036440849304, "epoch": 0.2752704692401255, "percentage": 21.5, "elapsed_time": "5:00:21", "remaining_time": "18:16:38", "throughput": 656.38, "total_tokens": 11828816} {"current_steps": 8605, "total_steps": 40000, "loss": 0.7878, "lr": 4.450584857638197e-05, "epoch": 0.27543051021061393, "percentage": 21.51, "elapsed_time": "5:00:24", "remaining_time": "18:16:02", "throughput": 656.61, "total_tokens": 11835328} {"current_steps": 8610, "total_steps": 40000, "loss": 0.5343, "lr": 4.449970636035116e-05, "epoch": 0.2755905511811024, "percentage": 21.52, "elapsed_time": "5:00:26", "remaining_time": "18:15:20", "throughput": 656.93, "total_tokens": 11842192} {"current_steps": 8615, "total_steps": 40000, "loss": 0.7751, "lr": 4.4493561137220574e-05, "epoch": 0.2757505921515908, "percentage": 21.54, "elapsed_time": "5:00:28", "remaining_time": "18:14:38", "throughput": 657.26, "total_tokens": 11849296} {"current_steps": 8620, "total_steps": 40000, "loss": 0.7897, "lr": 4.44874129079379e-05, "epoch": 0.27591063312207925, "percentage": 21.55, "elapsed_time": "5:00:29", "remaining_time": "18:13:55", "throughput": 657.57, "total_tokens": 11856048} {"current_steps": 8625, "total_steps": 40000, "loss": 0.7726, "lr": 4.4481261673451255e-05, "epoch": 0.2760706740925677, "percentage": 21.56, "elapsed_time": "5:00:31", "remaining_time": "18:13:13", "throughput": 657.89, "total_tokens": 11862848} {"current_steps": 8630, "total_steps": 40000, "loss": 0.8829, "lr": 4.4475107434709245e-05, "epoch": 0.27623071506305613, "percentage": 21.57, "elapsed_time": "5:00:33", "remaining_time": "18:12:31", "throughput": 658.21, "total_tokens": 11869760} {"current_steps": 8635, "total_steps": 40000, "loss": 0.8068, "lr": 4.446895019266093e-05, "epoch": 0.27639075603354457, "percentage": 21.59, "elapsed_time": "5:00:35", "remaining_time": "18:11:49", "throughput": 658.52, "total_tokens": 11876576} {"current_steps": 8640, "total_steps": 40000, "loss": 0.902, "lr": 4.446278994825583e-05, "epoch": 0.276550797004033, "percentage": 21.6, "elapsed_time": "5:00:36", "remaining_time": "18:11:07", "throughput": 658.82, "total_tokens": 11883104} {"current_steps": 8645, "total_steps": 40000, "loss": 0.6619, "lr": 4.445662670244394e-05, "epoch": 0.27671083797452145, "percentage": 21.61, "elapsed_time": "5:00:38", "remaining_time": "18:10:25", "throughput": 659.13, "total_tokens": 11889872} {"current_steps": 8650, "total_steps": 40000, "loss": 0.7129, "lr": 4.44504604561757e-05, "epoch": 0.27687087894500995, "percentage": 21.62, "elapsed_time": "5:00:40", "remaining_time": "18:09:43", "throughput": 659.45, "total_tokens": 11896784} {"current_steps": 8655, "total_steps": 40000, "loss": 0.7621, "lr": 4.4444291210402035e-05, "epoch": 0.2770309199154984, "percentage": 21.64, "elapsed_time": "5:00:42", "remaining_time": "18:09:01", "throughput": 659.75, "total_tokens": 11903264} {"current_steps": 8660, "total_steps": 40000, "loss": 0.7015, "lr": 4.443811896607431e-05, "epoch": 0.2771909608859868, "percentage": 21.65, "elapsed_time": "5:00:43", "remaining_time": "18:08:19", "throughput": 660.08, "total_tokens": 11910464} {"current_steps": 8665, "total_steps": 40000, "loss": 0.5367, "lr": 4.443194372414436e-05, "epoch": 0.27735100185647527, "percentage": 21.66, "elapsed_time": "5:00:45", "remaining_time": "18:07:37", "throughput": 660.39, "total_tokens": 11917152} {"current_steps": 8670, "total_steps": 40000, "loss": 0.6894, "lr": 4.442576548556449e-05, "epoch": 0.2775110428269637, "percentage": 21.68, "elapsed_time": "5:00:47", "remaining_time": "18:06:56", "throughput": 660.72, "total_tokens": 11924240} {"current_steps": 8675, "total_steps": 40000, "loss": 0.9754, "lr": 4.441958425128747e-05, "epoch": 0.27767108379745215, "percentage": 21.69, "elapsed_time": "5:00:49", "remaining_time": "18:06:14", "throughput": 661.05, "total_tokens": 11931376} {"current_steps": 8680, "total_steps": 40000, "loss": 0.9123, "lr": 4.4413400022266515e-05, "epoch": 0.2778311247679406, "percentage": 21.7, "elapsed_time": "5:00:50", "remaining_time": "18:05:32", "throughput": 661.37, "total_tokens": 11938352} {"current_steps": 8685, "total_steps": 40000, "loss": 0.8623, "lr": 4.4407212799455313e-05, "epoch": 0.277991165738429, "percentage": 21.71, "elapsed_time": "5:00:52", "remaining_time": "18:04:51", "throughput": 661.71, "total_tokens": 11945504} {"current_steps": 8690, "total_steps": 40000, "loss": 0.6239, "lr": 4.4401022583808003e-05, "epoch": 0.27815120670891746, "percentage": 21.73, "elapsed_time": "5:00:54", "remaining_time": "18:04:09", "throughput": 662.01, "total_tokens": 11952224} {"current_steps": 8695, "total_steps": 40000, "loss": 0.7066, "lr": 4.439482937627921e-05, "epoch": 0.2783112476794059, "percentage": 21.74, "elapsed_time": "5:00:56", "remaining_time": "18:03:28", "throughput": 662.33, "total_tokens": 11959104} {"current_steps": 8700, "total_steps": 40000, "loss": 0.7747, "lr": 4.4388633177824004e-05, "epoch": 0.2784712886498944, "percentage": 21.75, "elapsed_time": "5:00:57", "remaining_time": "18:02:46", "throughput": 662.63, "total_tokens": 11965568} {"current_steps": 8705, "total_steps": 40000, "loss": 0.8833, "lr": 4.4382433989397895e-05, "epoch": 0.27863132962038284, "percentage": 21.76, "elapsed_time": "5:00:59", "remaining_time": "18:02:05", "throughput": 662.94, "total_tokens": 11972336} {"current_steps": 8710, "total_steps": 40000, "loss": 0.8644, "lr": 4.4376231811956895e-05, "epoch": 0.2787913705908713, "percentage": 21.77, "elapsed_time": "5:01:01", "remaining_time": "18:01:23", "throughput": 663.26, "total_tokens": 11979392} {"current_steps": 8715, "total_steps": 40000, "loss": 0.8656, "lr": 4.437002664645745e-05, "epoch": 0.2789514115613597, "percentage": 21.79, "elapsed_time": "5:01:03", "remaining_time": "18:00:42", "throughput": 663.6, "total_tokens": 11986528} {"current_steps": 8720, "total_steps": 40000, "loss": 0.989, "lr": 4.436381849385649e-05, "epoch": 0.27911145253184816, "percentage": 21.8, "elapsed_time": "5:01:04", "remaining_time": "18:00:01", "throughput": 663.91, "total_tokens": 11993344} {"current_steps": 8725, "total_steps": 40000, "loss": 0.7564, "lr": 4.435760735511136e-05, "epoch": 0.2792714935023366, "percentage": 21.81, "elapsed_time": "5:01:06", "remaining_time": "17:59:19", "throughput": 664.24, "total_tokens": 12000400} {"current_steps": 8730, "total_steps": 40000, "loss": 0.8378, "lr": 4.435139323117992e-05, "epoch": 0.27943153447282504, "percentage": 21.82, "elapsed_time": "5:01:08", "remaining_time": "17:58:38", "throughput": 664.54, "total_tokens": 12007120} {"current_steps": 8735, "total_steps": 40000, "loss": 0.7885, "lr": 4.434517612302046e-05, "epoch": 0.2795915754433135, "percentage": 21.84, "elapsed_time": "5:01:09", "remaining_time": "17:57:57", "throughput": 664.85, "total_tokens": 12013760} {"current_steps": 8740, "total_steps": 40000, "loss": 0.9677, "lr": 4.433895603159174e-05, "epoch": 0.2797516164138019, "percentage": 21.85, "elapsed_time": "5:01:11", "remaining_time": "17:57:16", "throughput": 665.16, "total_tokens": 12020512} {"current_steps": 8745, "total_steps": 40000, "loss": 0.6741, "lr": 4.433273295785296e-05, "epoch": 0.27991165738429036, "percentage": 21.86, "elapsed_time": "5:01:13", "remaining_time": "17:56:35", "throughput": 665.47, "total_tokens": 12027392} {"current_steps": 8750, "total_steps": 40000, "loss": 0.8575, "lr": 4.432650690276382e-05, "epoch": 0.2800716983547788, "percentage": 21.88, "elapsed_time": "5:01:15", "remaining_time": "17:55:54", "throughput": 665.79, "total_tokens": 12034320} {"current_steps": 8755, "total_steps": 40000, "loss": 0.6631, "lr": 4.4320277867284435e-05, "epoch": 0.2802317393252673, "percentage": 21.89, "elapsed_time": "5:01:16", "remaining_time": "17:55:13", "throughput": 666.13, "total_tokens": 12041520} {"current_steps": 8760, "total_steps": 40000, "loss": 0.8997, "lr": 4.431404585237541e-05, "epoch": 0.28039178029575573, "percentage": 21.9, "elapsed_time": "5:01:18", "remaining_time": "17:54:32", "throughput": 666.44, "total_tokens": 12048400} {"current_steps": 8765, "total_steps": 40000, "loss": 0.5116, "lr": 4.43078108589978e-05, "epoch": 0.2805518212662442, "percentage": 21.91, "elapsed_time": "5:01:20", "remaining_time": "17:53:51", "throughput": 666.75, "total_tokens": 12055072} {"current_steps": 8770, "total_steps": 40000, "loss": 0.7375, "lr": 4.4301572888113116e-05, "epoch": 0.2807118622367326, "percentage": 21.93, "elapsed_time": "5:01:22", "remaining_time": "17:53:10", "throughput": 667.06, "total_tokens": 12061920} {"current_steps": 8775, "total_steps": 40000, "loss": 0.7022, "lr": 4.4295331940683337e-05, "epoch": 0.28087190320722105, "percentage": 21.94, "elapsed_time": "5:01:23", "remaining_time": "17:52:29", "throughput": 667.39, "total_tokens": 12068976} {"current_steps": 8780, "total_steps": 40000, "loss": 0.7009, "lr": 4.428908801767089e-05, "epoch": 0.2810319441777095, "percentage": 21.95, "elapsed_time": "5:01:25", "remaining_time": "17:51:48", "throughput": 667.72, "total_tokens": 12076112} {"current_steps": 8785, "total_steps": 40000, "loss": 0.8072, "lr": 4.428284112003868e-05, "epoch": 0.28119198514819793, "percentage": 21.96, "elapsed_time": "5:01:27", "remaining_time": "17:51:08", "throughput": 668.02, "total_tokens": 12082640} {"current_steps": 8790, "total_steps": 40000, "loss": 0.8122, "lr": 4.4276591248750033e-05, "epoch": 0.28135202611868637, "percentage": 21.98, "elapsed_time": "5:01:29", "remaining_time": "17:50:27", "throughput": 668.36, "total_tokens": 12090016} {"current_steps": 8795, "total_steps": 40000, "loss": 0.7824, "lr": 4.4270338404768774e-05, "epoch": 0.2815120670891748, "percentage": 21.99, "elapsed_time": "5:01:30", "remaining_time": "17:49:46", "throughput": 668.7, "total_tokens": 12097280} {"current_steps": 8800, "total_steps": 40000, "loss": 0.6199, "lr": 4.426408258905917e-05, "epoch": 0.28167210805966325, "percentage": 22.0, "elapsed_time": "5:01:32", "remaining_time": "17:49:06", "throughput": 669.01, "total_tokens": 12104176} {"current_steps": 8800, "total_steps": 40000, "eval_loss": 0.7967371344566345, "epoch": 0.28167210805966325, "percentage": 22.0, "elapsed_time": "5:07:20", "remaining_time": "18:09:40", "throughput": 656.38, "total_tokens": 12104176} {"current_steps": 8805, "total_steps": 40000, "loss": 0.7675, "lr": 4.425782380258594e-05, "epoch": 0.28183214903015175, "percentage": 22.01, "elapsed_time": "5:07:24", "remaining_time": "18:09:07", "throughput": 656.61, "total_tokens": 12110960} {"current_steps": 8810, "total_steps": 40000, "loss": 0.7465, "lr": 4.425156204631427e-05, "epoch": 0.2819921900006402, "percentage": 22.02, "elapsed_time": "5:07:26", "remaining_time": "18:08:25", "throughput": 656.92, "total_tokens": 12117776} {"current_steps": 8815, "total_steps": 40000, "loss": 0.716, "lr": 4.424529732120981e-05, "epoch": 0.2821522309711286, "percentage": 22.04, "elapsed_time": "5:07:28", "remaining_time": "18:07:44", "throughput": 657.22, "total_tokens": 12124480} {"current_steps": 8820, "total_steps": 40000, "loss": 0.9319, "lr": 4.423902962823864e-05, "epoch": 0.28231227194161707, "percentage": 22.05, "elapsed_time": "5:07:29", "remaining_time": "18:07:03", "throughput": 657.54, "total_tokens": 12131568} {"current_steps": 8825, "total_steps": 40000, "loss": 0.6287, "lr": 4.423275896836733e-05, "epoch": 0.2824723129121055, "percentage": 22.06, "elapsed_time": "5:07:31", "remaining_time": "18:06:22", "throughput": 657.87, "total_tokens": 12138896} {"current_steps": 8830, "total_steps": 40000, "loss": 0.7833, "lr": 4.42264853425629e-05, "epoch": 0.28263235388259395, "percentage": 22.07, "elapsed_time": "5:07:33", "remaining_time": "18:05:40", "throughput": 658.19, "total_tokens": 12145920} {"current_steps": 8835, "total_steps": 40000, "loss": 0.8451, "lr": 4.4220208751792816e-05, "epoch": 0.2827923948530824, "percentage": 22.09, "elapsed_time": "5:07:35", "remaining_time": "18:04:59", "throughput": 658.51, "total_tokens": 12153008} {"current_steps": 8840, "total_steps": 40000, "loss": 0.7165, "lr": 4.421392919702499e-05, "epoch": 0.2829524358235708, "percentage": 22.1, "elapsed_time": "5:07:36", "remaining_time": "18:04:18", "throughput": 658.82, "total_tokens": 12159792} {"current_steps": 8845, "total_steps": 40000, "loss": 0.7826, "lr": 4.4207646679227846e-05, "epoch": 0.28311247679405926, "percentage": 22.11, "elapsed_time": "5:07:38", "remaining_time": "18:03:37", "throughput": 659.13, "total_tokens": 12166624} {"current_steps": 8850, "total_steps": 40000, "loss": 0.8884, "lr": 4.42013611993702e-05, "epoch": 0.2832725177645477, "percentage": 22.12, "elapsed_time": "5:07:40", "remaining_time": "18:02:56", "throughput": 659.43, "total_tokens": 12173248} {"current_steps": 8855, "total_steps": 40000, "loss": 0.7564, "lr": 4.419507275842135e-05, "epoch": 0.28343255873503614, "percentage": 22.14, "elapsed_time": "5:07:42", "remaining_time": "18:02:15", "throughput": 659.73, "total_tokens": 12179952} {"current_steps": 8860, "total_steps": 40000, "loss": 0.9528, "lr": 4.418878135735106e-05, "epoch": 0.28359259970552464, "percentage": 22.15, "elapsed_time": "5:07:43", "remaining_time": "18:01:34", "throughput": 660.06, "total_tokens": 12187216} {"current_steps": 8865, "total_steps": 40000, "loss": 0.7151, "lr": 4.418248699712955e-05, "epoch": 0.2837526406760131, "percentage": 22.16, "elapsed_time": "5:07:45", "remaining_time": "18:00:53", "throughput": 660.35, "total_tokens": 12193712} {"current_steps": 8870, "total_steps": 40000, "loss": 0.9068, "lr": 4.417618967872748e-05, "epoch": 0.2839126816465015, "percentage": 22.18, "elapsed_time": "5:07:47", "remaining_time": "18:00:12", "throughput": 660.65, "total_tokens": 12200400} {"current_steps": 8875, "total_steps": 40000, "loss": 0.8683, "lr": 4.4169889403115985e-05, "epoch": 0.28407272261698996, "percentage": 22.19, "elapsed_time": "5:07:49", "remaining_time": "17:59:31", "throughput": 660.96, "total_tokens": 12207280} {"current_steps": 8880, "total_steps": 40000, "loss": 0.7426, "lr": 4.4163586171266627e-05, "epoch": 0.2842327635874784, "percentage": 22.2, "elapsed_time": "5:07:50", "remaining_time": "17:58:50", "throughput": 661.26, "total_tokens": 12214064} {"current_steps": 8885, "total_steps": 40000, "loss": 0.7268, "lr": 4.415727998415147e-05, "epoch": 0.28439280455796684, "percentage": 22.21, "elapsed_time": "5:07:52", "remaining_time": "17:58:10", "throughput": 661.58, "total_tokens": 12221104} {"current_steps": 8890, "total_steps": 40000, "loss": 0.763, "lr": 4.4150970842742985e-05, "epoch": 0.2845528455284553, "percentage": 22.23, "elapsed_time": "5:07:54", "remaining_time": "17:57:29", "throughput": 661.89, "total_tokens": 12227968} {"current_steps": 8895, "total_steps": 40000, "loss": 0.7955, "lr": 4.4144658748014134e-05, "epoch": 0.2847128864989437, "percentage": 22.24, "elapsed_time": "5:07:55", "remaining_time": "17:56:48", "throughput": 662.2, "total_tokens": 12234752} {"current_steps": 8900, "total_steps": 40000, "loss": 0.8033, "lr": 4.413834370093831e-05, "epoch": 0.28487292746943216, "percentage": 22.25, "elapsed_time": "5:07:57", "remaining_time": "17:56:08", "throughput": 662.51, "total_tokens": 12241696} {"current_steps": 8905, "total_steps": 40000, "loss": 1.2584, "lr": 4.413202570248939e-05, "epoch": 0.2850329684399206, "percentage": 22.26, "elapsed_time": "5:07:59", "remaining_time": "17:55:27", "throughput": 662.85, "total_tokens": 12249024} {"current_steps": 8910, "total_steps": 40000, "loss": 0.6992, "lr": 4.412570475364167e-05, "epoch": 0.28519300941040904, "percentage": 22.27, "elapsed_time": "5:08:01", "remaining_time": "17:54:47", "throughput": 663.15, "total_tokens": 12255792} {"current_steps": 8915, "total_steps": 40000, "loss": 0.759, "lr": 4.411938085536994e-05, "epoch": 0.28535305038089753, "percentage": 22.29, "elapsed_time": "5:08:02", "remaining_time": "17:54:06", "throughput": 663.46, "total_tokens": 12262720} {"current_steps": 8920, "total_steps": 40000, "loss": 0.833, "lr": 4.41130540086494e-05, "epoch": 0.285513091351386, "percentage": 22.3, "elapsed_time": "5:08:04", "remaining_time": "17:53:26", "throughput": 663.77, "total_tokens": 12269568} {"current_steps": 8925, "total_steps": 40000, "loss": 0.5077, "lr": 4.4106724214455754e-05, "epoch": 0.2856731323218744, "percentage": 22.31, "elapsed_time": "5:08:06", "remaining_time": "17:52:45", "throughput": 664.07, "total_tokens": 12276288} {"current_steps": 8930, "total_steps": 40000, "loss": 0.7836, "lr": 4.4100391473765115e-05, "epoch": 0.28583317329236285, "percentage": 22.32, "elapsed_time": "5:08:08", "remaining_time": "17:52:05", "throughput": 664.36, "total_tokens": 12282800} {"current_steps": 8935, "total_steps": 40000, "loss": 0.8402, "lr": 4.409405578755408e-05, "epoch": 0.2859932142628513, "percentage": 22.34, "elapsed_time": "5:08:09", "remaining_time": "17:51:25", "throughput": 664.68, "total_tokens": 12289840} {"current_steps": 8940, "total_steps": 40000, "loss": 0.6467, "lr": 4.4087717156799705e-05, "epoch": 0.28615325523333973, "percentage": 22.35, "elapsed_time": "5:08:11", "remaining_time": "17:50:44", "throughput": 664.97, "total_tokens": 12296432} {"current_steps": 8945, "total_steps": 40000, "loss": 0.9221, "lr": 4.408137558247946e-05, "epoch": 0.28631329620382817, "percentage": 22.36, "elapsed_time": "5:08:13", "remaining_time": "17:50:04", "throughput": 665.28, "total_tokens": 12303248} {"current_steps": 8950, "total_steps": 40000, "loss": 0.8839, "lr": 4.4075031065571306e-05, "epoch": 0.2864733371743166, "percentage": 22.38, "elapsed_time": "5:08:15", "remaining_time": "17:49:24", "throughput": 665.6, "total_tokens": 12310400} {"current_steps": 8955, "total_steps": 40000, "loss": 0.5667, "lr": 4.406868360705366e-05, "epoch": 0.28663337814480505, "percentage": 22.39, "elapsed_time": "5:08:16", "remaining_time": "17:48:44", "throughput": 665.9, "total_tokens": 12317120} {"current_steps": 8960, "total_steps": 40000, "loss": 0.614, "lr": 4.406233320790536e-05, "epoch": 0.2867934191152935, "percentage": 22.4, "elapsed_time": "5:08:18", "remaining_time": "17:48:04", "throughput": 666.21, "total_tokens": 12323920} {"current_steps": 8965, "total_steps": 40000, "loss": 0.7439, "lr": 4.4055979869105734e-05, "epoch": 0.286953460085782, "percentage": 22.41, "elapsed_time": "5:08:20", "remaining_time": "17:47:24", "throughput": 666.51, "total_tokens": 12330720} {"current_steps": 8970, "total_steps": 40000, "loss": 0.8045, "lr": 4.404962359163454e-05, "epoch": 0.2871135010562704, "percentage": 22.43, "elapsed_time": "5:08:22", "remaining_time": "17:46:44", "throughput": 666.84, "total_tokens": 12337888} {"current_steps": 8975, "total_steps": 40000, "loss": 0.7393, "lr": 4.404326437647199e-05, "epoch": 0.28727354202675887, "percentage": 22.44, "elapsed_time": "5:08:23", "remaining_time": "17:46:04", "throughput": 667.14, "total_tokens": 12344592} {"current_steps": 8980, "total_steps": 40000, "loss": 0.7459, "lr": 4.403690222459877e-05, "epoch": 0.2874335829972473, "percentage": 22.45, "elapsed_time": "5:08:25", "remaining_time": "17:45:24", "throughput": 667.45, "total_tokens": 12351568} {"current_steps": 8985, "total_steps": 40000, "loss": 0.8426, "lr": 4.4030537136995984e-05, "epoch": 0.28759362396773575, "percentage": 22.46, "elapsed_time": "5:08:27", "remaining_time": "17:44:44", "throughput": 667.74, "total_tokens": 12358064} {"current_steps": 8990, "total_steps": 40000, "loss": 0.8141, "lr": 4.402416911464523e-05, "epoch": 0.2877536649382242, "percentage": 22.48, "elapsed_time": "5:08:28", "remaining_time": "17:44:04", "throughput": 668.05, "total_tokens": 12364928} {"current_steps": 8995, "total_steps": 40000, "loss": 0.6623, "lr": 4.4017798158528516e-05, "epoch": 0.2879137059087126, "percentage": 22.49, "elapsed_time": "5:08:30", "remaining_time": "17:43:24", "throughput": 668.37, "total_tokens": 12372064} {"current_steps": 9000, "total_steps": 40000, "loss": 0.733, "lr": 4.401142426962834e-05, "epoch": 0.28807374687920106, "percentage": 22.5, "elapsed_time": "5:08:32", "remaining_time": "17:42:45", "throughput": 668.67, "total_tokens": 12378784} {"current_steps": 9000, "total_steps": 40000, "eval_loss": 0.7947989702224731, "epoch": 0.28807374687920106, "percentage": 22.5, "elapsed_time": "5:14:20", "remaining_time": "18:02:43", "throughput": 656.34, "total_tokens": 12378784} {"current_steps": 9005, "total_steps": 40000, "loss": 0.9539, "lr": 4.400504744892763e-05, "epoch": 0.2882337878496895, "percentage": 22.51, "elapsed_time": "5:14:24", "remaining_time": "18:02:10", "throughput": 656.59, "total_tokens": 12385984} {"current_steps": 9010, "total_steps": 40000, "loss": 0.8287, "lr": 4.399866769740975e-05, "epoch": 0.28839382882017794, "percentage": 22.53, "elapsed_time": "5:14:25", "remaining_time": "18:01:29", "throughput": 656.89, "total_tokens": 12392912} {"current_steps": 9015, "total_steps": 40000, "loss": 0.7522, "lr": 4.399228501605859e-05, "epoch": 0.2885538697906664, "percentage": 22.54, "elapsed_time": "5:14:27", "remaining_time": "18:00:49", "throughput": 657.22, "total_tokens": 12400304} {"current_steps": 9020, "total_steps": 40000, "loss": 0.8959, "lr": 4.398589940585839e-05, "epoch": 0.2887139107611549, "percentage": 22.55, "elapsed_time": "5:14:29", "remaining_time": "18:00:08", "throughput": 657.52, "total_tokens": 12407088} {"current_steps": 9025, "total_steps": 40000, "loss": 0.7355, "lr": 4.3979510867793917e-05, "epoch": 0.2888739517316433, "percentage": 22.56, "elapsed_time": "5:14:31", "remaining_time": "17:59:28", "throughput": 657.85, "total_tokens": 12414336} {"current_steps": 9030, "total_steps": 40000, "loss": 0.9056, "lr": 4.3973119402850346e-05, "epoch": 0.28903399270213176, "percentage": 22.57, "elapsed_time": "5:14:32", "remaining_time": "17:58:47", "throughput": 658.14, "total_tokens": 12421056} {"current_steps": 9035, "total_steps": 40000, "loss": 0.6469, "lr": 4.396672501201334e-05, "epoch": 0.2891940336726202, "percentage": 22.59, "elapsed_time": "5:14:34", "remaining_time": "17:58:07", "throughput": 658.45, "total_tokens": 12427984} {"current_steps": 9040, "total_steps": 40000, "loss": 0.9577, "lr": 4.396032769626899e-05, "epoch": 0.28935407464310864, "percentage": 22.6, "elapsed_time": "5:14:36", "remaining_time": "17:57:27", "throughput": 658.75, "total_tokens": 12434848} {"current_steps": 9045, "total_steps": 40000, "loss": 0.6267, "lr": 4.395392745660384e-05, "epoch": 0.2895141156135971, "percentage": 22.61, "elapsed_time": "5:14:38", "remaining_time": "17:56:47", "throughput": 659.05, "total_tokens": 12441664} {"current_steps": 9050, "total_steps": 40000, "loss": 0.7598, "lr": 4.394752429400488e-05, "epoch": 0.2896741565840855, "percentage": 22.62, "elapsed_time": "5:14:39", "remaining_time": "17:56:06", "throughput": 659.35, "total_tokens": 12448512} {"current_steps": 9055, "total_steps": 40000, "loss": 0.7333, "lr": 4.394111820945957e-05, "epoch": 0.28983419755457396, "percentage": 22.64, "elapsed_time": "5:14:41", "remaining_time": "17:55:26", "throughput": 659.67, "total_tokens": 12455584} {"current_steps": 9060, "total_steps": 40000, "loss": 0.5621, "lr": 4.393470920395579e-05, "epoch": 0.2899942385250624, "percentage": 22.65, "elapsed_time": "5:14:43", "remaining_time": "17:54:46", "throughput": 659.96, "total_tokens": 12462176} {"current_steps": 9065, "total_steps": 40000, "loss": 0.8119, "lr": 4.392829727848192e-05, "epoch": 0.29015427949555084, "percentage": 22.66, "elapsed_time": "5:14:45", "remaining_time": "17:54:06", "throughput": 660.26, "total_tokens": 12469024} {"current_steps": 9070, "total_steps": 40000, "loss": 0.8429, "lr": 4.392188243402673e-05, "epoch": 0.29031432046603933, "percentage": 22.68, "elapsed_time": "5:14:46", "remaining_time": "17:53:26", "throughput": 660.58, "total_tokens": 12476144} {"current_steps": 9075, "total_steps": 40000, "loss": 0.6998, "lr": 4.391546467157949e-05, "epoch": 0.2904743614365278, "percentage": 22.69, "elapsed_time": "5:14:48", "remaining_time": "17:52:46", "throughput": 660.88, "total_tokens": 12483072} {"current_steps": 9080, "total_steps": 40000, "loss": 0.7714, "lr": 4.390904399212988e-05, "epoch": 0.2906344024070162, "percentage": 22.7, "elapsed_time": "5:14:50", "remaining_time": "17:52:06", "throughput": 661.18, "total_tokens": 12489776} {"current_steps": 9085, "total_steps": 40000, "loss": 0.8208, "lr": 4.390262039666807e-05, "epoch": 0.29079444337750465, "percentage": 22.71, "elapsed_time": "5:14:51", "remaining_time": "17:51:26", "throughput": 661.49, "total_tokens": 12496832} {"current_steps": 9090, "total_steps": 40000, "loss": 0.6998, "lr": 4.389619388618464e-05, "epoch": 0.2909544843479931, "percentage": 22.73, "elapsed_time": "5:14:53", "remaining_time": "17:50:47", "throughput": 661.79, "total_tokens": 12503680} {"current_steps": 9095, "total_steps": 40000, "loss": 0.6682, "lr": 4.3889764461670655e-05, "epoch": 0.29111452531848153, "percentage": 22.74, "elapsed_time": "5:14:55", "remaining_time": "17:50:07", "throughput": 662.08, "total_tokens": 12510352} {"current_steps": 9100, "total_steps": 40000, "loss": 0.7664, "lr": 4.38833321241176e-05, "epoch": 0.29127456628896997, "percentage": 22.75, "elapsed_time": "5:14:57", "remaining_time": "17:49:27", "throughput": 662.37, "total_tokens": 12516944} {"current_steps": 9105, "total_steps": 40000, "loss": 0.6018, "lr": 4.3876896874517434e-05, "epoch": 0.2914346072594584, "percentage": 22.76, "elapsed_time": "5:14:58", "remaining_time": "17:48:47", "throughput": 662.67, "total_tokens": 12523792} {"current_steps": 9110, "total_steps": 40000, "loss": 0.6356, "lr": 4.3870458713862554e-05, "epoch": 0.29159464822994685, "percentage": 22.78, "elapsed_time": "5:15:00", "remaining_time": "17:48:08", "throughput": 662.99, "total_tokens": 12530944} {"current_steps": 9115, "total_steps": 40000, "loss": 0.8369, "lr": 4.386401764314579e-05, "epoch": 0.2917546892004353, "percentage": 22.79, "elapsed_time": "5:15:02", "remaining_time": "17:47:28", "throughput": 663.3, "total_tokens": 12538064} {"current_steps": 9120, "total_steps": 40000, "loss": 0.5469, "lr": 4.385757366336045e-05, "epoch": 0.29191473017092373, "percentage": 22.8, "elapsed_time": "5:15:04", "remaining_time": "17:46:48", "throughput": 663.6, "total_tokens": 12544800} {"current_steps": 9125, "total_steps": 40000, "loss": 0.7588, "lr": 4.385112677550027e-05, "epoch": 0.2920747711414122, "percentage": 22.81, "elapsed_time": "5:15:05", "remaining_time": "17:46:09", "throughput": 663.9, "total_tokens": 12551552} {"current_steps": 9130, "total_steps": 40000, "loss": 1.049, "lr": 4.384467698055945e-05, "epoch": 0.29223481211190067, "percentage": 22.82, "elapsed_time": "5:15:07", "remaining_time": "17:45:29", "throughput": 664.21, "total_tokens": 12558608} {"current_steps": 9135, "total_steps": 40000, "loss": 1.1376, "lr": 4.383822427953261e-05, "epoch": 0.2923948530823891, "percentage": 22.84, "elapsed_time": "5:15:09", "remaining_time": "17:44:50", "throughput": 664.51, "total_tokens": 12565552} {"current_steps": 9140, "total_steps": 40000, "loss": 0.9532, "lr": 4.3831768673414864e-05, "epoch": 0.29255489405287755, "percentage": 22.85, "elapsed_time": "5:15:11", "remaining_time": "17:44:10", "throughput": 664.82, "total_tokens": 12572560} {"current_steps": 9145, "total_steps": 40000, "loss": 0.787, "lr": 4.382531016320173e-05, "epoch": 0.292714935023366, "percentage": 22.86, "elapsed_time": "5:15:12", "remaining_time": "17:43:31", "throughput": 665.12, "total_tokens": 12579216} {"current_steps": 9150, "total_steps": 40000, "loss": 0.9189, "lr": 4.3818848749889184e-05, "epoch": 0.2928749759938544, "percentage": 22.88, "elapsed_time": "5:15:14", "remaining_time": "17:42:52", "throughput": 665.42, "total_tokens": 12586080} {"current_steps": 9155, "total_steps": 40000, "loss": 0.852, "lr": 4.381238443447368e-05, "epoch": 0.29303501696434286, "percentage": 22.89, "elapsed_time": "5:15:16", "remaining_time": "17:42:12", "throughput": 665.73, "total_tokens": 12593136} {"current_steps": 9160, "total_steps": 40000, "loss": 0.8542, "lr": 4.380591721795208e-05, "epoch": 0.2931950579348313, "percentage": 22.9, "elapsed_time": "5:15:18", "remaining_time": "17:41:33", "throughput": 666.04, "total_tokens": 12600144} {"current_steps": 9165, "total_steps": 40000, "loss": 0.9103, "lr": 4.3799447101321723e-05, "epoch": 0.29335509890531974, "percentage": 22.91, "elapsed_time": "5:15:19", "remaining_time": "17:40:54", "throughput": 666.33, "total_tokens": 12606896} {"current_steps": 9170, "total_steps": 40000, "loss": 0.706, "lr": 4.379297408558036e-05, "epoch": 0.2935151398758082, "percentage": 22.93, "elapsed_time": "5:15:21", "remaining_time": "17:40:15", "throughput": 666.64, "total_tokens": 12613824} {"current_steps": 9175, "total_steps": 40000, "loss": 0.6996, "lr": 4.378649817172624e-05, "epoch": 0.2936751808462967, "percentage": 22.94, "elapsed_time": "5:15:23", "remaining_time": "17:39:35", "throughput": 666.93, "total_tokens": 12620448} {"current_steps": 9180, "total_steps": 40000, "loss": 0.7773, "lr": 4.378001936075801e-05, "epoch": 0.2938352218167851, "percentage": 22.95, "elapsed_time": "5:15:24", "remaining_time": "17:38:56", "throughput": 667.23, "total_tokens": 12627232} {"current_steps": 9185, "total_steps": 40000, "loss": 0.8504, "lr": 4.377353765367479e-05, "epoch": 0.29399526278727356, "percentage": 22.96, "elapsed_time": "5:15:26", "remaining_time": "17:38:17", "throughput": 667.51, "total_tokens": 12633792} {"current_steps": 9190, "total_steps": 40000, "loss": 0.7745, "lr": 4.376705305147614e-05, "epoch": 0.294155303757762, "percentage": 22.98, "elapsed_time": "5:15:28", "remaining_time": "17:37:38", "throughput": 667.8, "total_tokens": 12640384} {"current_steps": 9195, "total_steps": 40000, "loss": 0.6341, "lr": 4.376056555516206e-05, "epoch": 0.29431534472825044, "percentage": 22.99, "elapsed_time": "5:15:30", "remaining_time": "17:36:59", "throughput": 668.11, "total_tokens": 12647392} {"current_steps": 9200, "total_steps": 40000, "loss": 0.7747, "lr": 4.375407516573302e-05, "epoch": 0.2944753856987389, "percentage": 23.0, "elapsed_time": "5:15:31", "remaining_time": "17:36:20", "throughput": 668.41, "total_tokens": 12654368} {"current_steps": 9200, "total_steps": 40000, "eval_loss": 0.7927456498146057, "epoch": 0.2944753856987389, "percentage": 23.0, "elapsed_time": "5:21:19", "remaining_time": "17:55:45", "throughput": 656.35, "total_tokens": 12654368} {"current_steps": 9205, "total_steps": 40000, "loss": 0.7703, "lr": 4.3747581884189913e-05, "epoch": 0.2946354266692273, "percentage": 23.01, "elapsed_time": "5:21:23", "remaining_time": "17:55:11", "throughput": 656.58, "total_tokens": 12661088} {"current_steps": 9210, "total_steps": 40000, "loss": 0.9311, "lr": 4.374108571153408e-05, "epoch": 0.29479546763971576, "percentage": 23.03, "elapsed_time": "5:21:25", "remaining_time": "17:54:32", "throughput": 656.87, "total_tokens": 12667888} {"current_steps": 9215, "total_steps": 40000, "loss": 0.7356, "lr": 4.3734586648767316e-05, "epoch": 0.2949555086102042, "percentage": 23.04, "elapsed_time": "5:21:26", "remaining_time": "17:53:52", "throughput": 657.17, "total_tokens": 12674832} {"current_steps": 9220, "total_steps": 40000, "loss": 0.8012, "lr": 4.372808469689186e-05, "epoch": 0.29511554958069264, "percentage": 23.05, "elapsed_time": "5:21:28", "remaining_time": "17:53:13", "throughput": 657.48, "total_tokens": 12681792} {"current_steps": 9225, "total_steps": 40000, "loss": 0.7663, "lr": 4.372157985691039e-05, "epoch": 0.2952755905511811, "percentage": 23.06, "elapsed_time": "5:21:30", "remaining_time": "17:52:33", "throughput": 657.77, "total_tokens": 12688544} {"current_steps": 9230, "total_steps": 40000, "loss": 0.6343, "lr": 4.371507212982603e-05, "epoch": 0.2954356315216696, "percentage": 23.08, "elapsed_time": "5:21:32", "remaining_time": "17:51:53", "throughput": 658.06, "total_tokens": 12695312} {"current_steps": 9235, "total_steps": 40000, "loss": 0.6988, "lr": 4.370856151664236e-05, "epoch": 0.295595672492158, "percentage": 23.09, "elapsed_time": "5:21:33", "remaining_time": "17:51:14", "throughput": 658.34, "total_tokens": 12701872} {"current_steps": 9240, "total_steps": 40000, "loss": 0.7443, "lr": 4.3702048018363404e-05, "epoch": 0.29575571346264645, "percentage": 23.1, "elapsed_time": "5:21:35", "remaining_time": "17:50:35", "throughput": 658.65, "total_tokens": 12708976} {"current_steps": 9245, "total_steps": 40000, "loss": 0.738, "lr": 4.369553163599362e-05, "epoch": 0.2959157544331349, "percentage": 23.11, "elapsed_time": "5:21:37", "remaining_time": "17:49:55", "throughput": 658.95, "total_tokens": 12715872} {"current_steps": 9250, "total_steps": 40000, "loss": 0.6059, "lr": 4.3689012370537904e-05, "epoch": 0.29607579540362333, "percentage": 23.12, "elapsed_time": "5:21:39", "remaining_time": "17:49:16", "throughput": 659.26, "total_tokens": 12723008} {"current_steps": 9255, "total_steps": 40000, "loss": 0.9381, "lr": 4.368249022300164e-05, "epoch": 0.29623583637411177, "percentage": 23.14, "elapsed_time": "5:21:40", "remaining_time": "17:48:36", "throughput": 659.53, "total_tokens": 12729360} {"current_steps": 9260, "total_steps": 40000, "loss": 0.6069, "lr": 4.367596519439059e-05, "epoch": 0.2963958773446002, "percentage": 23.15, "elapsed_time": "5:21:42", "remaining_time": "17:47:57", "throughput": 659.83, "total_tokens": 12736432} {"current_steps": 9265, "total_steps": 40000, "loss": 0.8149, "lr": 4.366943728571101e-05, "epoch": 0.29655591831508865, "percentage": 23.16, "elapsed_time": "5:21:44", "remaining_time": "17:47:18", "throughput": 660.11, "total_tokens": 12742880} {"current_steps": 9270, "total_steps": 40000, "loss": 0.6112, "lr": 4.366290649796959e-05, "epoch": 0.2967159592855771, "percentage": 23.18, "elapsed_time": "5:21:45", "remaining_time": "17:46:39", "throughput": 660.41, "total_tokens": 12749904} {"current_steps": 9275, "total_steps": 40000, "loss": 0.9305, "lr": 4.3656372832173456e-05, "epoch": 0.29687600025606553, "percentage": 23.19, "elapsed_time": "5:21:47", "remaining_time": "17:46:00", "throughput": 660.7, "total_tokens": 12756656} {"current_steps": 9280, "total_steps": 40000, "loss": 0.8584, "lr": 4.364983628933017e-05, "epoch": 0.29703604122655397, "percentage": 23.2, "elapsed_time": "5:21:49", "remaining_time": "17:45:20", "throughput": 660.98, "total_tokens": 12763216} {"current_steps": 9285, "total_steps": 40000, "loss": 0.837, "lr": 4.364329687044777e-05, "epoch": 0.29719608219704247, "percentage": 23.21, "elapsed_time": "5:21:51", "remaining_time": "17:44:41", "throughput": 661.29, "total_tokens": 12770256} {"current_steps": 9290, "total_steps": 40000, "loss": 0.7204, "lr": 4.36367545765347e-05, "epoch": 0.2973561231675309, "percentage": 23.23, "elapsed_time": "5:21:52", "remaining_time": "17:44:02", "throughput": 661.57, "total_tokens": 12776784} {"current_steps": 9295, "total_steps": 40000, "loss": 0.7525, "lr": 4.363020940859988e-05, "epoch": 0.29751616413801935, "percentage": 23.24, "elapsed_time": "5:21:54", "remaining_time": "17:43:23", "throughput": 661.84, "total_tokens": 12783264} {"current_steps": 9300, "total_steps": 40000, "loss": 0.7756, "lr": 4.362366136765263e-05, "epoch": 0.2976762051085078, "percentage": 23.25, "elapsed_time": "5:21:56", "remaining_time": "17:42:44", "throughput": 662.15, "total_tokens": 12790272} {"current_steps": 9305, "total_steps": 40000, "loss": 1.1271, "lr": 4.361711045470278e-05, "epoch": 0.2978362460789962, "percentage": 23.26, "elapsed_time": "5:21:58", "remaining_time": "17:42:05", "throughput": 662.44, "total_tokens": 12797168} {"current_steps": 9310, "total_steps": 40000, "loss": 0.7501, "lr": 4.3610556670760524e-05, "epoch": 0.29799628704948466, "percentage": 23.28, "elapsed_time": "5:21:59", "remaining_time": "17:41:27", "throughput": 662.72, "total_tokens": 12803664} {"current_steps": 9315, "total_steps": 40000, "loss": 0.8625, "lr": 4.360400001683657e-05, "epoch": 0.2981563280199731, "percentage": 23.29, "elapsed_time": "5:22:01", "remaining_time": "17:40:48", "throughput": 663.03, "total_tokens": 12810864} {"current_steps": 9320, "total_steps": 40000, "loss": 0.936, "lr": 4.3597440493942e-05, "epoch": 0.29831636899046154, "percentage": 23.3, "elapsed_time": "5:22:03", "remaining_time": "17:40:09", "throughput": 663.31, "total_tokens": 12817440} {"current_steps": 9325, "total_steps": 40000, "loss": 0.685, "lr": 4.3590878103088405e-05, "epoch": 0.29847640996095, "percentage": 23.31, "elapsed_time": "5:22:05", "remaining_time": "17:39:30", "throughput": 663.6, "total_tokens": 12824096} {"current_steps": 9330, "total_steps": 40000, "loss": 0.8416, "lr": 4.358431284528779e-05, "epoch": 0.2986364509314384, "percentage": 23.33, "elapsed_time": "5:22:06", "remaining_time": "17:38:51", "throughput": 663.9, "total_tokens": 12831088} {"current_steps": 9335, "total_steps": 40000, "loss": 0.8171, "lr": 4.357774472155257e-05, "epoch": 0.2987964919019269, "percentage": 23.34, "elapsed_time": "5:22:08", "remaining_time": "17:38:13", "throughput": 664.21, "total_tokens": 12838176} {"current_steps": 9340, "total_steps": 40000, "loss": 0.7452, "lr": 4.3571173732895664e-05, "epoch": 0.29895653287241536, "percentage": 23.35, "elapsed_time": "5:22:10", "remaining_time": "17:37:34", "throughput": 664.49, "total_tokens": 12844800} {"current_steps": 9345, "total_steps": 40000, "loss": 0.807, "lr": 4.356459988033039e-05, "epoch": 0.2991165738429038, "percentage": 23.36, "elapsed_time": "5:22:12", "remaining_time": "17:36:56", "throughput": 664.79, "total_tokens": 12851696} {"current_steps": 9350, "total_steps": 40000, "loss": 0.775, "lr": 4.355802316487051e-05, "epoch": 0.29927661481339224, "percentage": 23.38, "elapsed_time": "5:22:13", "remaining_time": "17:36:17", "throughput": 665.07, "total_tokens": 12858224} {"current_steps": 9355, "total_steps": 40000, "loss": 0.5157, "lr": 4.355144358753025e-05, "epoch": 0.2994366557838807, "percentage": 23.39, "elapsed_time": "5:22:15", "remaining_time": "17:35:39", "throughput": 665.35, "total_tokens": 12864896} {"current_steps": 9360, "total_steps": 40000, "loss": 0.7479, "lr": 4.354486114932425e-05, "epoch": 0.2995966967543691, "percentage": 23.4, "elapsed_time": "5:22:17", "remaining_time": "17:35:00", "throughput": 665.63, "total_tokens": 12871456} {"current_steps": 9365, "total_steps": 40000, "loss": 0.7352, "lr": 4.353827585126762e-05, "epoch": 0.29975673772485756, "percentage": 23.41, "elapsed_time": "5:22:18", "remaining_time": "17:34:22", "throughput": 665.92, "total_tokens": 12878144} {"current_steps": 9370, "total_steps": 40000, "loss": 0.6997, "lr": 4.353168769437588e-05, "epoch": 0.299916778695346, "percentage": 23.43, "elapsed_time": "5:22:20", "remaining_time": "17:33:43", "throughput": 666.23, "total_tokens": 12885296} {"current_steps": 9375, "total_steps": 40000, "loss": 0.9706, "lr": 4.3525096679665014e-05, "epoch": 0.30007681966583444, "percentage": 23.44, "elapsed_time": "5:22:22", "remaining_time": "17:33:05", "throughput": 666.52, "total_tokens": 12892160} {"current_steps": 9380, "total_steps": 40000, "loss": 0.6235, "lr": 4.351850280815144e-05, "epoch": 0.3002368606363229, "percentage": 23.45, "elapsed_time": "5:22:24", "remaining_time": "17:32:26", "throughput": 666.84, "total_tokens": 12899520} {"current_steps": 9385, "total_steps": 40000, "loss": 0.536, "lr": 4.3511906080852014e-05, "epoch": 0.3003969016068113, "percentage": 23.46, "elapsed_time": "5:22:25", "remaining_time": "17:31:48", "throughput": 667.16, "total_tokens": 12906752} {"current_steps": 9390, "total_steps": 40000, "loss": 0.7925, "lr": 4.350530649878404e-05, "epoch": 0.3005569425772998, "percentage": 23.47, "elapsed_time": "5:22:27", "remaining_time": "17:31:10", "throughput": 667.45, "total_tokens": 12913632} {"current_steps": 9395, "total_steps": 40000, "loss": 0.6955, "lr": 4.3498704062965246e-05, "epoch": 0.30071698354778825, "percentage": 23.49, "elapsed_time": "5:22:29", "remaining_time": "17:30:32", "throughput": 667.75, "total_tokens": 12920528} {"current_steps": 9400, "total_steps": 40000, "loss": 0.6677, "lr": 4.3492098774413815e-05, "epoch": 0.3008770245182767, "percentage": 23.5, "elapsed_time": "5:22:31", "remaining_time": "17:29:54", "throughput": 668.03, "total_tokens": 12927088} {"current_steps": 9400, "total_steps": 40000, "eval_loss": 0.7914193868637085, "epoch": 0.3008770245182767, "percentage": 23.5, "elapsed_time": "5:28:18", "remaining_time": "17:48:44", "throughput": 656.25, "total_tokens": 12927088} {"current_steps": 9405, "total_steps": 40000, "loss": 0.5515, "lr": 4.3485490634148375e-05, "epoch": 0.30103706548876513, "percentage": 23.51, "elapsed_time": "5:28:22", "remaining_time": "17:48:12", "throughput": 656.47, "total_tokens": 12933744} {"current_steps": 9410, "total_steps": 40000, "loss": 0.9925, "lr": 4.347887964318797e-05, "epoch": 0.30119710645925357, "percentage": 23.52, "elapsed_time": "5:28:23", "remaining_time": "17:47:33", "throughput": 656.74, "total_tokens": 12940384} {"current_steps": 9415, "total_steps": 40000, "loss": 0.8017, "lr": 4.34722658025521e-05, "epoch": 0.301357147429742, "percentage": 23.54, "elapsed_time": "5:28:25", "remaining_time": "17:46:54", "throughput": 657.05, "total_tokens": 12947584} {"current_steps": 9420, "total_steps": 40000, "loss": 0.803, "lr": 4.346564911326071e-05, "epoch": 0.30151718840023045, "percentage": 23.55, "elapsed_time": "5:28:27", "remaining_time": "17:46:15", "throughput": 657.34, "total_tokens": 12954384} {"current_steps": 9425, "total_steps": 40000, "loss": 0.6686, "lr": 4.345902957633418e-05, "epoch": 0.3016772293707189, "percentage": 23.56, "elapsed_time": "5:28:29", "remaining_time": "17:45:36", "throughput": 657.63, "total_tokens": 12961328} {"current_steps": 9430, "total_steps": 40000, "loss": 0.7749, "lr": 4.345240719279331e-05, "epoch": 0.30183727034120733, "percentage": 23.57, "elapsed_time": "5:28:30", "remaining_time": "17:44:58", "throughput": 657.93, "total_tokens": 12968320} {"current_steps": 9435, "total_steps": 40000, "loss": 0.7045, "lr": 4.3445781963659374e-05, "epoch": 0.30199731131169577, "percentage": 23.59, "elapsed_time": "5:28:32", "remaining_time": "17:44:19", "throughput": 658.2, "total_tokens": 12974688} {"current_steps": 9440, "total_steps": 40000, "loss": 0.7658, "lr": 4.3439153889954045e-05, "epoch": 0.30215735228218427, "percentage": 23.6, "elapsed_time": "5:28:34", "remaining_time": "17:43:40", "throughput": 658.49, "total_tokens": 12981568} {"current_steps": 9445, "total_steps": 40000, "loss": 0.5756, "lr": 4.343252297269946e-05, "epoch": 0.3023173932526727, "percentage": 23.61, "elapsed_time": "5:28:35", "remaining_time": "17:43:02", "throughput": 658.78, "total_tokens": 12988448} {"current_steps": 9450, "total_steps": 40000, "loss": 0.8406, "lr": 4.342588921291821e-05, "epoch": 0.30247743422316115, "percentage": 23.62, "elapsed_time": "5:28:37", "remaining_time": "17:42:23", "throughput": 659.07, "total_tokens": 12995376} {"current_steps": 9455, "total_steps": 40000, "loss": 0.702, "lr": 4.341925261163328e-05, "epoch": 0.3026374751936496, "percentage": 23.64, "elapsed_time": "5:28:39", "remaining_time": "17:41:44", "throughput": 659.37, "total_tokens": 13002320} {"current_steps": 9460, "total_steps": 40000, "loss": 0.8595, "lr": 4.341261316986813e-05, "epoch": 0.302797516164138, "percentage": 23.65, "elapsed_time": "5:28:41", "remaining_time": "17:41:06", "throughput": 659.64, "total_tokens": 13008880} {"current_steps": 9465, "total_steps": 40000, "loss": 0.9076, "lr": 4.340597088864664e-05, "epoch": 0.30295755713462647, "percentage": 23.66, "elapsed_time": "5:28:42", "remaining_time": "17:40:28", "throughput": 659.94, "total_tokens": 13016000} {"current_steps": 9470, "total_steps": 40000, "loss": 0.9044, "lr": 4.339932576899313e-05, "epoch": 0.3031175981051149, "percentage": 23.67, "elapsed_time": "5:28:44", "remaining_time": "17:39:49", "throughput": 660.24, "total_tokens": 13022944} {"current_steps": 9475, "total_steps": 40000, "loss": 0.9001, "lr": 4.3392677811932375e-05, "epoch": 0.30327763907560334, "percentage": 23.69, "elapsed_time": "5:28:46", "remaining_time": "17:39:11", "throughput": 660.52, "total_tokens": 13029776} {"current_steps": 9480, "total_steps": 40000, "loss": 0.8171, "lr": 4.338602701848956e-05, "epoch": 0.3034376800460918, "percentage": 23.7, "elapsed_time": "5:28:48", "remaining_time": "17:38:32", "throughput": 660.81, "total_tokens": 13036608} {"current_steps": 9485, "total_steps": 40000, "loss": 0.6629, "lr": 4.337937338969033e-05, "epoch": 0.3035977210165802, "percentage": 23.71, "elapsed_time": "5:28:49", "remaining_time": "17:37:54", "throughput": 661.1, "total_tokens": 13043344} {"current_steps": 9490, "total_steps": 40000, "loss": 0.6598, "lr": 4.337271692656075e-05, "epoch": 0.30375776198706866, "percentage": 23.72, "elapsed_time": "5:28:51", "remaining_time": "17:37:16", "throughput": 661.4, "total_tokens": 13050496} {"current_steps": 9495, "total_steps": 40000, "loss": 0.755, "lr": 4.336605763012733e-05, "epoch": 0.30391780295755716, "percentage": 23.74, "elapsed_time": "5:28:53", "remaining_time": "17:36:38", "throughput": 661.72, "total_tokens": 13057968} {"current_steps": 9500, "total_steps": 40000, "loss": 0.7603, "lr": 4.3359395501417026e-05, "epoch": 0.3040778439280456, "percentage": 23.75, "elapsed_time": "5:28:55", "remaining_time": "17:36:00", "throughput": 662.0, "total_tokens": 13064672} {"current_steps": 9505, "total_steps": 40000, "loss": 0.7553, "lr": 4.335273054145722e-05, "epoch": 0.30423788489853404, "percentage": 23.76, "elapsed_time": "5:28:56", "remaining_time": "17:35:21", "throughput": 662.27, "total_tokens": 13071088} {"current_steps": 9510, "total_steps": 40000, "loss": 0.8551, "lr": 4.334606275127572e-05, "epoch": 0.3043979258690225, "percentage": 23.77, "elapsed_time": "5:28:58", "remaining_time": "17:34:43", "throughput": 662.54, "total_tokens": 13077632} {"current_steps": 9515, "total_steps": 40000, "loss": 0.5855, "lr": 4.33393921319008e-05, "epoch": 0.3045579668395109, "percentage": 23.79, "elapsed_time": "5:29:00", "remaining_time": "17:34:05", "throughput": 662.81, "total_tokens": 13084048} {"current_steps": 9520, "total_steps": 40000, "loss": 0.6904, "lr": 4.3332718684361146e-05, "epoch": 0.30471800780999936, "percentage": 23.8, "elapsed_time": "5:29:02", "remaining_time": "17:33:27", "throughput": 663.1, "total_tokens": 13090912} {"current_steps": 9525, "total_steps": 40000, "loss": 0.8526, "lr": 4.332604240968588e-05, "epoch": 0.3048780487804878, "percentage": 23.81, "elapsed_time": "5:29:03", "remaining_time": "17:32:49", "throughput": 663.39, "total_tokens": 13097872} {"current_steps": 9530, "total_steps": 40000, "loss": 0.6614, "lr": 4.331936330890459e-05, "epoch": 0.30503808975097624, "percentage": 23.82, "elapsed_time": "5:29:05", "remaining_time": "17:32:11", "throughput": 663.69, "total_tokens": 13104944} {"current_steps": 9535, "total_steps": 40000, "loss": 1.0207, "lr": 4.331268138304725e-05, "epoch": 0.3051981307214647, "percentage": 23.84, "elapsed_time": "5:29:07", "remaining_time": "17:31:33", "throughput": 663.95, "total_tokens": 13111264} {"current_steps": 9540, "total_steps": 40000, "loss": 0.6689, "lr": 4.330599663314431e-05, "epoch": 0.3053581716919531, "percentage": 23.85, "elapsed_time": "5:29:08", "remaining_time": "17:30:55", "throughput": 664.23, "total_tokens": 13117936} {"current_steps": 9545, "total_steps": 40000, "loss": 0.7971, "lr": 4.329930906022665e-05, "epoch": 0.3055182126624416, "percentage": 23.86, "elapsed_time": "5:29:10", "remaining_time": "17:30:18", "throughput": 664.52, "total_tokens": 13124736} {"current_steps": 9550, "total_steps": 40000, "loss": 0.6823, "lr": 4.3292618665325564e-05, "epoch": 0.30567825363293005, "percentage": 23.88, "elapsed_time": "5:29:12", "remaining_time": "17:29:40", "throughput": 664.8, "total_tokens": 13131520} {"current_steps": 9555, "total_steps": 40000, "loss": 0.7585, "lr": 4.3285925449472796e-05, "epoch": 0.3058382946034185, "percentage": 23.89, "elapsed_time": "5:29:14", "remaining_time": "17:29:02", "throughput": 665.09, "total_tokens": 13138336} {"current_steps": 9560, "total_steps": 40000, "loss": 0.8741, "lr": 4.327922941370054e-05, "epoch": 0.30599833557390693, "percentage": 23.9, "elapsed_time": "5:29:15", "remaining_time": "17:28:24", "throughput": 665.39, "total_tokens": 13145360} {"current_steps": 9565, "total_steps": 40000, "loss": 0.7049, "lr": 4.3272530559041384e-05, "epoch": 0.30615837654439537, "percentage": 23.91, "elapsed_time": "5:29:17", "remaining_time": "17:27:47", "throughput": 665.69, "total_tokens": 13152448} {"current_steps": 9570, "total_steps": 40000, "loss": 0.7236, "lr": 4.32658288865284e-05, "epoch": 0.3063184175148838, "percentage": 23.93, "elapsed_time": "5:29:19", "remaining_time": "17:27:09", "throughput": 665.98, "total_tokens": 13159280} {"current_steps": 9575, "total_steps": 40000, "loss": 0.985, "lr": 4.325912439719505e-05, "epoch": 0.30647845848537225, "percentage": 23.94, "elapsed_time": "5:29:21", "remaining_time": "17:26:31", "throughput": 666.24, "total_tokens": 13165616} {"current_steps": 9580, "total_steps": 40000, "loss": 0.8658, "lr": 4.3252417092075266e-05, "epoch": 0.3066384994558607, "percentage": 23.95, "elapsed_time": "5:29:22", "remaining_time": "17:25:54", "throughput": 666.5, "total_tokens": 13172016} {"current_steps": 9585, "total_steps": 40000, "loss": 0.9661, "lr": 4.3245706972203385e-05, "epoch": 0.30679854042634913, "percentage": 23.96, "elapsed_time": "5:29:24", "remaining_time": "17:25:16", "throughput": 666.79, "total_tokens": 13178848} {"current_steps": 9590, "total_steps": 40000, "loss": 0.705, "lr": 4.323899403861421e-05, "epoch": 0.30695858139683757, "percentage": 23.97, "elapsed_time": "5:29:26", "remaining_time": "17:24:39", "throughput": 667.07, "total_tokens": 13185600} {"current_steps": 9595, "total_steps": 40000, "loss": 0.7, "lr": 4.3232278292342935e-05, "epoch": 0.307118622367326, "percentage": 23.99, "elapsed_time": "5:29:28", "remaining_time": "17:24:01", "throughput": 667.38, "total_tokens": 13192720} {"current_steps": 9600, "total_steps": 40000, "loss": 0.9276, "lr": 4.322555973442524e-05, "epoch": 0.3072786633378145, "percentage": 24.0, "elapsed_time": "5:29:29", "remaining_time": "17:23:24", "throughput": 667.66, "total_tokens": 13199552} {"current_steps": 9600, "total_steps": 40000, "eval_loss": 0.7888292670249939, "epoch": 0.3072786633378145, "percentage": 24.0, "elapsed_time": "5:35:18", "remaining_time": "17:41:47", "throughput": 656.1, "total_tokens": 13199552} {"current_steps": 9605, "total_steps": 40000, "loss": 0.6972, "lr": 4.3218838365897184e-05, "epoch": 0.30743870430830295, "percentage": 24.01, "elapsed_time": "5:35:21", "remaining_time": "17:41:14", "throughput": 656.32, "total_tokens": 13206208} {"current_steps": 9610, "total_steps": 40000, "loss": 0.796, "lr": 4.3212114187795306e-05, "epoch": 0.3075987452787914, "percentage": 24.02, "elapsed_time": "5:35:23", "remaining_time": "17:40:36", "throughput": 656.62, "total_tokens": 13213296} {"current_steps": 9615, "total_steps": 40000, "loss": 0.7003, "lr": 4.320538720115656e-05, "epoch": 0.3077587862492798, "percentage": 24.04, "elapsed_time": "5:35:25", "remaining_time": "17:39:58", "throughput": 656.88, "total_tokens": 13219920} {"current_steps": 9620, "total_steps": 40000, "loss": 0.9022, "lr": 4.319865740701831e-05, "epoch": 0.30791882721976827, "percentage": 24.05, "elapsed_time": "5:35:26", "remaining_time": "17:39:20", "throughput": 657.17, "total_tokens": 13226816} {"current_steps": 9625, "total_steps": 40000, "loss": 0.6996, "lr": 4.3191924806418396e-05, "epoch": 0.3080788681902567, "percentage": 24.06, "elapsed_time": "5:35:28", "remaining_time": "17:38:42", "throughput": 657.45, "total_tokens": 13233664} {"current_steps": 9630, "total_steps": 40000, "loss": 0.7068, "lr": 4.318518940039507e-05, "epoch": 0.30823890916074514, "percentage": 24.07, "elapsed_time": "5:35:30", "remaining_time": "17:38:05", "throughput": 657.72, "total_tokens": 13240160} {"current_steps": 9635, "total_steps": 40000, "loss": 0.8666, "lr": 4.3178451189987e-05, "epoch": 0.3083989501312336, "percentage": 24.09, "elapsed_time": "5:35:32", "remaining_time": "17:37:27", "throughput": 658.02, "total_tokens": 13247344} {"current_steps": 9640, "total_steps": 40000, "loss": 0.6229, "lr": 4.3171710176233315e-05, "epoch": 0.308558991101722, "percentage": 24.1, "elapsed_time": "5:35:33", "remaining_time": "17:36:49", "throughput": 658.32, "total_tokens": 13254448} {"current_steps": 9645, "total_steps": 40000, "loss": 0.5893, "lr": 4.316496636017355e-05, "epoch": 0.30871903207221046, "percentage": 24.11, "elapsed_time": "5:35:35", "remaining_time": "17:36:11", "throughput": 658.59, "total_tokens": 13261216} {"current_steps": 9650, "total_steps": 40000, "loss": 0.966, "lr": 4.315821974284771e-05, "epoch": 0.3088790730426989, "percentage": 24.12, "elapsed_time": "5:35:37", "remaining_time": "17:35:33", "throughput": 658.89, "total_tokens": 13268272} {"current_steps": 9655, "total_steps": 40000, "loss": 0.7171, "lr": 4.315147032529619e-05, "epoch": 0.3090391140131874, "percentage": 24.14, "elapsed_time": "5:35:39", "remaining_time": "17:34:55", "throughput": 659.18, "total_tokens": 13275296} {"current_steps": 9660, "total_steps": 40000, "loss": 0.8885, "lr": 4.3144718108559845e-05, "epoch": 0.30919915498367584, "percentage": 24.15, "elapsed_time": "5:35:40", "remaining_time": "17:34:18", "throughput": 659.47, "total_tokens": 13282240} {"current_steps": 9665, "total_steps": 40000, "loss": 0.8726, "lr": 4.3137963093679945e-05, "epoch": 0.3093591959541643, "percentage": 24.16, "elapsed_time": "5:35:42", "remaining_time": "17:33:40", "throughput": 659.79, "total_tokens": 13289808} {"current_steps": 9670, "total_steps": 40000, "loss": 0.7214, "lr": 4.31312052816982e-05, "epoch": 0.3095192369246527, "percentage": 24.18, "elapsed_time": "5:35:44", "remaining_time": "17:33:02", "throughput": 660.08, "total_tokens": 13296800} {"current_steps": 9675, "total_steps": 40000, "loss": 0.8728, "lr": 4.312444467365675e-05, "epoch": 0.30967927789514116, "percentage": 24.19, "elapsed_time": "5:35:46", "remaining_time": "17:32:25", "throughput": 660.37, "total_tokens": 13303792} {"current_steps": 9680, "total_steps": 40000, "loss": 0.6969, "lr": 4.311768127059816e-05, "epoch": 0.3098393188656296, "percentage": 24.2, "elapsed_time": "5:35:47", "remaining_time": "17:31:47", "throughput": 660.64, "total_tokens": 13310368} {"current_steps": 9685, "total_steps": 40000, "loss": 0.4998, "lr": 4.3110915073565444e-05, "epoch": 0.30999935983611804, "percentage": 24.21, "elapsed_time": "5:35:49", "remaining_time": "17:31:09", "throughput": 660.91, "total_tokens": 13316928} {"current_steps": 9690, "total_steps": 40000, "loss": 1.1004, "lr": 4.310414608360203e-05, "epoch": 0.3101594008066065, "percentage": 24.22, "elapsed_time": "5:35:51", "remaining_time": "17:30:32", "throughput": 661.19, "total_tokens": 13323840} {"current_steps": 9695, "total_steps": 40000, "loss": 0.6687, "lr": 4.309737430175177e-05, "epoch": 0.3103194417770949, "percentage": 24.24, "elapsed_time": "5:35:52", "remaining_time": "17:29:54", "throughput": 661.48, "total_tokens": 13330704} {"current_steps": 9700, "total_steps": 40000, "loss": 0.835, "lr": 4.309059972905897e-05, "epoch": 0.31047948274758336, "percentage": 24.25, "elapsed_time": "5:35:54", "remaining_time": "17:29:17", "throughput": 661.75, "total_tokens": 13337472} {"current_steps": 9705, "total_steps": 40000, "loss": 0.5921, "lr": 4.308382236656836e-05, "epoch": 0.31063952371807185, "percentage": 24.26, "elapsed_time": "5:35:56", "remaining_time": "17:28:40", "throughput": 662.04, "total_tokens": 13344320} {"current_steps": 9710, "total_steps": 40000, "loss": 0.7914, "lr": 4.307704221532507e-05, "epoch": 0.3107995646885603, "percentage": 24.27, "elapsed_time": "5:35:58", "remaining_time": "17:28:02", "throughput": 662.32, "total_tokens": 13351072} {"current_steps": 9715, "total_steps": 40000, "loss": 1.1318, "lr": 4.307025927637471e-05, "epoch": 0.31095960565904873, "percentage": 24.29, "elapsed_time": "5:35:59", "remaining_time": "17:27:25", "throughput": 662.6, "total_tokens": 13358016} {"current_steps": 9720, "total_steps": 40000, "loss": 0.5981, "lr": 4.306347355076328e-05, "epoch": 0.31111964662953717, "percentage": 24.3, "elapsed_time": "5:36:01", "remaining_time": "17:26:48", "throughput": 662.88, "total_tokens": 13364704} {"current_steps": 9725, "total_steps": 40000, "loss": 0.7701, "lr": 4.305668503953724e-05, "epoch": 0.3112796876000256, "percentage": 24.31, "elapsed_time": "5:36:03", "remaining_time": "17:26:10", "throughput": 663.15, "total_tokens": 13371456} {"current_steps": 9730, "total_steps": 40000, "loss": 0.7952, "lr": 4.3049893743743436e-05, "epoch": 0.31143972857051405, "percentage": 24.32, "elapsed_time": "5:36:05", "remaining_time": "17:25:33", "throughput": 663.46, "total_tokens": 13378672} {"current_steps": 9735, "total_steps": 40000, "loss": 0.8278, "lr": 4.304309966442919e-05, "epoch": 0.3115997695410025, "percentage": 24.34, "elapsed_time": "5:36:06", "remaining_time": "17:24:56", "throughput": 663.74, "total_tokens": 13385584} {"current_steps": 9740, "total_steps": 40000, "loss": 0.6988, "lr": 4.303630280264224e-05, "epoch": 0.31175981051149093, "percentage": 24.35, "elapsed_time": "5:36:08", "remaining_time": "17:24:19", "throughput": 664.03, "total_tokens": 13392608} {"current_steps": 9745, "total_steps": 40000, "loss": 0.8863, "lr": 4.302950315943074e-05, "epoch": 0.31191985148197937, "percentage": 24.36, "elapsed_time": "5:36:10", "remaining_time": "17:23:42", "throughput": 664.31, "total_tokens": 13399424} {"current_steps": 9750, "total_steps": 40000, "loss": 0.6416, "lr": 4.3022700735843275e-05, "epoch": 0.3120798924524678, "percentage": 24.38, "elapsed_time": "5:36:12", "remaining_time": "17:23:05", "throughput": 664.58, "total_tokens": 13405952} {"current_steps": 9755, "total_steps": 40000, "loss": 0.7502, "lr": 4.301589553292887e-05, "epoch": 0.31223993342295625, "percentage": 24.39, "elapsed_time": "5:36:13", "remaining_time": "17:22:28", "throughput": 664.85, "total_tokens": 13412560} {"current_steps": 9760, "total_steps": 40000, "loss": 0.8757, "lr": 4.300908755173697e-05, "epoch": 0.31239997439344475, "percentage": 24.4, "elapsed_time": "5:36:15", "remaining_time": "17:21:51", "throughput": 665.14, "total_tokens": 13419600} {"current_steps": 9765, "total_steps": 40000, "loss": 0.7853, "lr": 4.300227679331745e-05, "epoch": 0.3125600153639332, "percentage": 24.41, "elapsed_time": "5:36:17", "remaining_time": "17:21:14", "throughput": 665.43, "total_tokens": 13426560} {"current_steps": 9770, "total_steps": 40000, "loss": 0.8045, "lr": 4.299546325872063e-05, "epoch": 0.3127200563344216, "percentage": 24.43, "elapsed_time": "5:36:19", "remaining_time": "17:20:37", "throughput": 665.71, "total_tokens": 13433392} {"current_steps": 9775, "total_steps": 40000, "loss": 0.8056, "lr": 4.2988646948997225e-05, "epoch": 0.31288009730491007, "percentage": 24.44, "elapsed_time": "5:36:20", "remaining_time": "17:20:00", "throughput": 666.0, "total_tokens": 13440352} {"current_steps": 9780, "total_steps": 40000, "loss": 0.8227, "lr": 4.29818278651984e-05, "epoch": 0.3130401382753985, "percentage": 24.45, "elapsed_time": "5:36:22", "remaining_time": "17:19:23", "throughput": 666.27, "total_tokens": 13447008} {"current_steps": 9785, "total_steps": 40000, "loss": 0.8972, "lr": 4.297500600837574e-05, "epoch": 0.31320017924588694, "percentage": 24.46, "elapsed_time": "5:36:24", "remaining_time": "17:18:46", "throughput": 666.55, "total_tokens": 13453856} {"current_steps": 9790, "total_steps": 40000, "loss": 0.8193, "lr": 4.2968181379581276e-05, "epoch": 0.3133602202163754, "percentage": 24.47, "elapsed_time": "5:36:25", "remaining_time": "17:18:09", "throughput": 666.83, "total_tokens": 13460720} {"current_steps": 9795, "total_steps": 40000, "loss": 0.8765, "lr": 4.296135397986743e-05, "epoch": 0.3135202611868638, "percentage": 24.49, "elapsed_time": "5:36:27", "remaining_time": "17:17:33", "throughput": 667.1, "total_tokens": 13467280} {"current_steps": 9800, "total_steps": 40000, "loss": 0.8887, "lr": 4.295452381028709e-05, "epoch": 0.31368030215735226, "percentage": 24.5, "elapsed_time": "5:36:29", "remaining_time": "17:16:56", "throughput": 667.38, "total_tokens": 13473952} {"current_steps": 9800, "total_steps": 40000, "eval_loss": 0.7876874208450317, "epoch": 0.31368030215735226, "percentage": 24.5, "elapsed_time": "5:42:16", "remaining_time": "17:34:47", "throughput": 656.08, "total_tokens": 13473952} {"current_steps": 9805, "total_steps": 40000, "loss": 0.9005, "lr": 4.294769087189354e-05, "epoch": 0.3138403431278407, "percentage": 24.51, "elapsed_time": "5:42:20", "remaining_time": "17:34:16", "throughput": 656.31, "total_tokens": 13481168} {"current_steps": 9810, "total_steps": 40000, "loss": 0.7143, "lr": 4.294085516574052e-05, "epoch": 0.3140003840983292, "percentage": 24.52, "elapsed_time": "5:42:22", "remaining_time": "17:33:39", "throughput": 656.6, "total_tokens": 13488240} {"current_steps": 9815, "total_steps": 40000, "loss": 0.769, "lr": 4.2934016692882176e-05, "epoch": 0.31416042506881764, "percentage": 24.54, "elapsed_time": "5:42:24", "remaining_time": "17:33:01", "throughput": 656.88, "total_tokens": 13495072} {"current_steps": 9820, "total_steps": 40000, "loss": 0.5777, "lr": 4.292717545437308e-05, "epoch": 0.3143204660393061, "percentage": 24.55, "elapsed_time": "5:42:25", "remaining_time": "17:32:24", "throughput": 657.15, "total_tokens": 13501760} {"current_steps": 9825, "total_steps": 40000, "loss": 0.7888, "lr": 4.292033145126825e-05, "epoch": 0.3144805070097945, "percentage": 24.56, "elapsed_time": "5:42:27", "remaining_time": "17:31:47", "throughput": 657.41, "total_tokens": 13508304} {"current_steps": 9830, "total_steps": 40000, "loss": 0.6782, "lr": 4.29134846846231e-05, "epoch": 0.31464054798028296, "percentage": 24.57, "elapsed_time": "5:42:29", "remaining_time": "17:31:09", "throughput": 657.67, "total_tokens": 13514816} {"current_steps": 9835, "total_steps": 40000, "loss": 0.8073, "lr": 4.29066351554935e-05, "epoch": 0.3148005889507714, "percentage": 24.59, "elapsed_time": "5:42:31", "remaining_time": "17:30:32", "throughput": 657.94, "total_tokens": 13521472} {"current_steps": 9840, "total_steps": 40000, "loss": 0.7698, "lr": 4.289978286493574e-05, "epoch": 0.31496062992125984, "percentage": 24.6, "elapsed_time": "5:42:32", "remaining_time": "17:29:55", "throughput": 658.2, "total_tokens": 13528032} {"current_steps": 9845, "total_steps": 40000, "loss": 0.9596, "lr": 4.28929278140065e-05, "epoch": 0.3151206708917483, "percentage": 24.61, "elapsed_time": "5:42:34", "remaining_time": "17:29:18", "throughput": 658.48, "total_tokens": 13534800} {"current_steps": 9850, "total_steps": 40000, "loss": 0.6806, "lr": 4.288607000376295e-05, "epoch": 0.3152807118622367, "percentage": 24.62, "elapsed_time": "5:42:36", "remaining_time": "17:28:41", "throughput": 658.74, "total_tokens": 13541360} {"current_steps": 9855, "total_steps": 40000, "loss": 0.7136, "lr": 4.2879209435262624e-05, "epoch": 0.31544075283272516, "percentage": 24.64, "elapsed_time": "5:42:38", "remaining_time": "17:28:04", "throughput": 659.05, "total_tokens": 13548880} {"current_steps": 9860, "total_steps": 40000, "loss": 0.5812, "lr": 4.287234610956353e-05, "epoch": 0.3156007938032136, "percentage": 24.65, "elapsed_time": "5:42:39", "remaining_time": "17:27:27", "throughput": 659.35, "total_tokens": 13556080} {"current_steps": 9865, "total_steps": 40000, "loss": 0.8537, "lr": 4.2865480027724056e-05, "epoch": 0.3157608347737021, "percentage": 24.66, "elapsed_time": "5:42:41", "remaining_time": "17:26:50", "throughput": 659.63, "total_tokens": 13562992} {"current_steps": 9870, "total_steps": 40000, "loss": 0.9228, "lr": 4.285861119080306e-05, "epoch": 0.31592087574419053, "percentage": 24.68, "elapsed_time": "5:42:43", "remaining_time": "17:26:13", "throughput": 659.91, "total_tokens": 13569984} {"current_steps": 9875, "total_steps": 40000, "loss": 0.8478, "lr": 4.2851739599859784e-05, "epoch": 0.31608091671467897, "percentage": 24.69, "elapsed_time": "5:42:45", "remaining_time": "17:25:36", "throughput": 660.19, "total_tokens": 13576784} {"current_steps": 9880, "total_steps": 40000, "loss": 0.6851, "lr": 4.2844865255953934e-05, "epoch": 0.3162409576851674, "percentage": 24.7, "elapsed_time": "5:42:46", "remaining_time": "17:24:59", "throughput": 660.47, "total_tokens": 13583712} {"current_steps": 9885, "total_steps": 40000, "loss": 0.6887, "lr": 4.2837988160145605e-05, "epoch": 0.31640099865565585, "percentage": 24.71, "elapsed_time": "5:42:48", "remaining_time": "17:24:22", "throughput": 660.75, "total_tokens": 13590656} {"current_steps": 9890, "total_steps": 40000, "loss": 0.7364, "lr": 4.2831108313495336e-05, "epoch": 0.3165610396261443, "percentage": 24.73, "elapsed_time": "5:42:50", "remaining_time": "17:23:46", "throughput": 661.05, "total_tokens": 13598000} {"current_steps": 9895, "total_steps": 40000, "loss": 0.6421, "lr": 4.282422571706408e-05, "epoch": 0.31672108059663273, "percentage": 24.74, "elapsed_time": "5:42:52", "remaining_time": "17:23:09", "throughput": 661.36, "total_tokens": 13605456} {"current_steps": 9900, "total_steps": 40000, "loss": 0.7326, "lr": 4.281734037191323e-05, "epoch": 0.31688112156712117, "percentage": 24.75, "elapsed_time": "5:42:53", "remaining_time": "17:22:32", "throughput": 661.62, "total_tokens": 13611968} {"current_steps": 9905, "total_steps": 40000, "loss": 0.7909, "lr": 4.281045227910459e-05, "epoch": 0.3170411625376096, "percentage": 24.76, "elapsed_time": "5:42:55", "remaining_time": "17:21:55", "throughput": 661.9, "total_tokens": 13618864} {"current_steps": 9910, "total_steps": 40000, "loss": 0.6207, "lr": 4.280356143970038e-05, "epoch": 0.31720120350809805, "percentage": 24.77, "elapsed_time": "5:42:57", "remaining_time": "17:21:19", "throughput": 662.17, "total_tokens": 13625680} {"current_steps": 9915, "total_steps": 40000, "loss": 0.7954, "lr": 4.279666785476327e-05, "epoch": 0.3173612444785865, "percentage": 24.79, "elapsed_time": "5:42:58", "remaining_time": "17:20:42", "throughput": 662.47, "total_tokens": 13632928} {"current_steps": 9920, "total_steps": 40000, "loss": 0.7047, "lr": 4.2789771525356325e-05, "epoch": 0.317521285449075, "percentage": 24.8, "elapsed_time": "5:43:00", "remaining_time": "17:20:06", "throughput": 662.78, "total_tokens": 13640512} {"current_steps": 9925, "total_steps": 40000, "loss": 0.6552, "lr": 4.2782872452543056e-05, "epoch": 0.3176813264195634, "percentage": 24.81, "elapsed_time": "5:43:02", "remaining_time": "17:19:29", "throughput": 663.06, "total_tokens": 13647376} {"current_steps": 9930, "total_steps": 40000, "loss": 0.7618, "lr": 4.2775970637387376e-05, "epoch": 0.31784136739005187, "percentage": 24.82, "elapsed_time": "5:43:04", "remaining_time": "17:18:53", "throughput": 663.34, "total_tokens": 13654352} {"current_steps": 9935, "total_steps": 40000, "loss": 0.6827, "lr": 4.276906608095363e-05, "epoch": 0.3180014083605403, "percentage": 24.84, "elapsed_time": "5:43:05", "remaining_time": "17:18:16", "throughput": 663.63, "total_tokens": 13661424} {"current_steps": 9940, "total_steps": 40000, "loss": 0.7324, "lr": 4.276215878430661e-05, "epoch": 0.31816144933102875, "percentage": 24.85, "elapsed_time": "5:43:07", "remaining_time": "17:17:40", "throughput": 663.89, "total_tokens": 13667984} {"current_steps": 9945, "total_steps": 40000, "loss": 0.7978, "lr": 4.275524874851149e-05, "epoch": 0.3183214903015172, "percentage": 24.86, "elapsed_time": "5:43:09", "remaining_time": "17:17:03", "throughput": 664.16, "total_tokens": 13674608} {"current_steps": 9950, "total_steps": 40000, "loss": 0.8376, "lr": 4.274833597463388e-05, "epoch": 0.3184815312720056, "percentage": 24.88, "elapsed_time": "5:43:11", "remaining_time": "17:16:27", "throughput": 664.44, "total_tokens": 13681536} {"current_steps": 9955, "total_steps": 40000, "loss": 0.8112, "lr": 4.2741420463739824e-05, "epoch": 0.31864157224249406, "percentage": 24.89, "elapsed_time": "5:43:12", "remaining_time": "17:15:50", "throughput": 664.72, "total_tokens": 13688576} {"current_steps": 9960, "total_steps": 40000, "loss": 0.7748, "lr": 4.273450221689578e-05, "epoch": 0.3188016132129825, "percentage": 24.9, "elapsed_time": "5:43:14", "remaining_time": "17:15:14", "throughput": 665.0, "total_tokens": 13695488} {"current_steps": 9965, "total_steps": 40000, "loss": 0.8372, "lr": 4.272758123516863e-05, "epoch": 0.31896165418347094, "percentage": 24.91, "elapsed_time": "5:43:16", "remaining_time": "17:14:38", "throughput": 665.28, "total_tokens": 13702352} {"current_steps": 9970, "total_steps": 40000, "loss": 0.6867, "lr": 4.272065751962567e-05, "epoch": 0.31912169515395944, "percentage": 24.93, "elapsed_time": "5:43:18", "remaining_time": "17:14:02", "throughput": 665.57, "total_tokens": 13709456} {"current_steps": 9975, "total_steps": 40000, "loss": 0.8256, "lr": 4.271373107133464e-05, "epoch": 0.3192817361244479, "percentage": 24.94, "elapsed_time": "5:43:19", "remaining_time": "17:13:25", "throughput": 665.84, "total_tokens": 13716256} {"current_steps": 9980, "total_steps": 40000, "loss": 0.9571, "lr": 4.270680189136366e-05, "epoch": 0.3194417770949363, "percentage": 24.95, "elapsed_time": "5:43:21", "remaining_time": "17:12:49", "throughput": 666.13, "total_tokens": 13723296} {"current_steps": 9985, "total_steps": 40000, "loss": 0.8947, "lr": 4.269986998078132e-05, "epoch": 0.31960181806542476, "percentage": 24.96, "elapsed_time": "5:43:23", "remaining_time": "17:12:13", "throughput": 666.39, "total_tokens": 13729808} {"current_steps": 9990, "total_steps": 40000, "loss": 0.8158, "lr": 4.2692935340656595e-05, "epoch": 0.3197618590359132, "percentage": 24.98, "elapsed_time": "5:43:24", "remaining_time": "17:11:37", "throughput": 666.67, "total_tokens": 13736800} {"current_steps": 9995, "total_steps": 40000, "loss": 0.7462, "lr": 4.26859979720589e-05, "epoch": 0.31992190000640164, "percentage": 24.99, "elapsed_time": "5:43:26", "remaining_time": "17:11:01", "throughput": 666.96, "total_tokens": 13743792} {"current_steps": 10000, "total_steps": 40000, "loss": 0.7798, "lr": 4.267905787605806e-05, "epoch": 0.3200819409768901, "percentage": 25.0, "elapsed_time": "5:43:28", "remaining_time": "17:10:25", "throughput": 667.22, "total_tokens": 13750288} {"current_steps": 10000, "total_steps": 40000, "eval_loss": 0.7863858342170715, "epoch": 0.3200819409768901, "percentage": 25.0, "elapsed_time": "5:49:16", "remaining_time": "17:27:49", "throughput": 656.13, "total_tokens": 13750288} {"current_steps": 10005, "total_steps": 40000, "loss": 0.7475, "lr": 4.267211505372433e-05, "epoch": 0.3202419819473785, "percentage": 25.01, "elapsed_time": "5:49:19", "remaining_time": "17:27:17", "throughput": 656.36, "total_tokens": 13757184} {"current_steps": 10010, "total_steps": 40000, "loss": 0.6563, "lr": 4.266516950612837e-05, "epoch": 0.32040202291786696, "percentage": 25.02, "elapsed_time": "5:49:21", "remaining_time": "17:26:40", "throughput": 656.63, "total_tokens": 13763920} {"current_steps": 10015, "total_steps": 40000, "loss": 0.6406, "lr": 4.265822123434128e-05, "epoch": 0.3205620638883554, "percentage": 25.04, "elapsed_time": "5:49:23", "remaining_time": "17:26:04", "throughput": 656.91, "total_tokens": 13771056} {"current_steps": 10020, "total_steps": 40000, "loss": 0.7979, "lr": 4.265127023943457e-05, "epoch": 0.32072210485884384, "percentage": 25.05, "elapsed_time": "5:49:25", "remaining_time": "17:25:27", "throughput": 657.19, "total_tokens": 13778112} {"current_steps": 10025, "total_steps": 40000, "loss": 0.682, "lr": 4.2644316522480176e-05, "epoch": 0.32088214582933233, "percentage": 25.06, "elapsed_time": "5:49:26", "remaining_time": "17:24:51", "throughput": 657.48, "total_tokens": 13785184} {"current_steps": 10030, "total_steps": 40000, "loss": 0.7791, "lr": 4.263736008455044e-05, "epoch": 0.3210421867998208, "percentage": 25.07, "elapsed_time": "5:49:28", "remaining_time": "17:24:14", "throughput": 657.75, "total_tokens": 13791968} {"current_steps": 10035, "total_steps": 40000, "loss": 0.9644, "lr": 4.2630400926718125e-05, "epoch": 0.3212022277703092, "percentage": 25.09, "elapsed_time": "5:49:30", "remaining_time": "17:23:38", "throughput": 658.05, "total_tokens": 13799552} {"current_steps": 10040, "total_steps": 40000, "loss": 0.7581, "lr": 4.262343905005644e-05, "epoch": 0.32136226874079765, "percentage": 25.1, "elapsed_time": "5:49:31", "remaining_time": "17:23:01", "throughput": 658.32, "total_tokens": 13806224} {"current_steps": 10045, "total_steps": 40000, "loss": 1.0649, "lr": 4.261647445563897e-05, "epoch": 0.3215223097112861, "percentage": 25.11, "elapsed_time": "5:49:33", "remaining_time": "17:22:25", "throughput": 658.62, "total_tokens": 13813664} {"current_steps": 10050, "total_steps": 40000, "loss": 0.738, "lr": 4.260950714453976e-05, "epoch": 0.32168235068177453, "percentage": 25.12, "elapsed_time": "5:49:35", "remaining_time": "17:21:48", "throughput": 658.88, "total_tokens": 13820256} {"current_steps": 10055, "total_steps": 40000, "loss": 0.7557, "lr": 4.2602537117833266e-05, "epoch": 0.32184239165226297, "percentage": 25.14, "elapsed_time": "5:49:37", "remaining_time": "17:21:12", "throughput": 659.13, "total_tokens": 13826736} {"current_steps": 10060, "total_steps": 40000, "loss": 0.7275, "lr": 4.259556437659433e-05, "epoch": 0.3220024326227514, "percentage": 25.15, "elapsed_time": "5:49:38", "remaining_time": "17:20:36", "throughput": 659.4, "total_tokens": 13833440} {"current_steps": 10065, "total_steps": 40000, "loss": 0.8981, "lr": 4.258858892189825e-05, "epoch": 0.32216247359323985, "percentage": 25.16, "elapsed_time": "5:49:40", "remaining_time": "17:19:59", "throughput": 659.67, "total_tokens": 13840288} {"current_steps": 10070, "total_steps": 40000, "loss": 0.674, "lr": 4.2581610754820725e-05, "epoch": 0.3223225145637283, "percentage": 25.17, "elapsed_time": "5:49:42", "remaining_time": "17:19:23", "throughput": 659.95, "total_tokens": 13847328} {"current_steps": 10075, "total_steps": 40000, "loss": 0.9279, "lr": 4.2574629876437876e-05, "epoch": 0.3224825555342168, "percentage": 25.19, "elapsed_time": "5:49:44", "remaining_time": "17:18:47", "throughput": 660.21, "total_tokens": 13853952} {"current_steps": 10080, "total_steps": 40000, "loss": 0.5258, "lr": 4.256764628782625e-05, "epoch": 0.3226425965047052, "percentage": 25.2, "elapsed_time": "5:49:45", "remaining_time": "17:18:11", "throughput": 660.48, "total_tokens": 13860816} {"current_steps": 10085, "total_steps": 40000, "loss": 0.9014, "lr": 4.256065999006279e-05, "epoch": 0.32280263747519367, "percentage": 25.21, "elapsed_time": "5:49:47", "remaining_time": "17:17:35", "throughput": 660.74, "total_tokens": 13867440} {"current_steps": 10090, "total_steps": 40000, "loss": 0.8922, "lr": 4.2553670984224885e-05, "epoch": 0.3229626784456821, "percentage": 25.22, "elapsed_time": "5:49:49", "remaining_time": "17:16:59", "throughput": 661.0, "total_tokens": 13874016} {"current_steps": 10095, "total_steps": 40000, "loss": 0.7817, "lr": 4.254667927139032e-05, "epoch": 0.32312271941617055, "percentage": 25.24, "elapsed_time": "5:49:51", "remaining_time": "17:16:23", "throughput": 661.27, "total_tokens": 13880768} {"current_steps": 10100, "total_steps": 40000, "loss": 0.8139, "lr": 4.2539684852637295e-05, "epoch": 0.323282760386659, "percentage": 25.25, "elapsed_time": "5:49:52", "remaining_time": "17:15:47", "throughput": 661.56, "total_tokens": 13887984} {"current_steps": 10105, "total_steps": 40000, "loss": 0.6835, "lr": 4.253268772904446e-05, "epoch": 0.3234428013571474, "percentage": 25.26, "elapsed_time": "5:49:54", "remaining_time": "17:15:10", "throughput": 661.82, "total_tokens": 13894656} {"current_steps": 10110, "total_steps": 40000, "loss": 0.9274, "lr": 4.252568790169085e-05, "epoch": 0.32360284232763586, "percentage": 25.27, "elapsed_time": "5:49:56", "remaining_time": "17:14:35", "throughput": 662.12, "total_tokens": 13901968} {"current_steps": 10115, "total_steps": 40000, "loss": 0.8147, "lr": 4.251868537165592e-05, "epoch": 0.3237628832981243, "percentage": 25.29, "elapsed_time": "5:49:58", "remaining_time": "17:13:59", "throughput": 662.39, "total_tokens": 13908896} {"current_steps": 10120, "total_steps": 40000, "loss": 0.7231, "lr": 4.251168014001955e-05, "epoch": 0.32392292426861274, "percentage": 25.3, "elapsed_time": "5:49:59", "remaining_time": "17:13:23", "throughput": 662.65, "total_tokens": 13915504} {"current_steps": 10125, "total_steps": 40000, "loss": 0.7268, "lr": 4.250467220786204e-05, "epoch": 0.3240829652391012, "percentage": 25.31, "elapsed_time": "5:50:01", "remaining_time": "17:12:47", "throughput": 662.92, "total_tokens": 13922240} {"current_steps": 10130, "total_steps": 40000, "loss": 0.9547, "lr": 4.249766157626409e-05, "epoch": 0.3242430062095897, "percentage": 25.32, "elapsed_time": "5:50:03", "remaining_time": "17:12:11", "throughput": 663.2, "total_tokens": 13929312} {"current_steps": 10135, "total_steps": 40000, "loss": 0.8649, "lr": 4.249064824630684e-05, "epoch": 0.3244030471800781, "percentage": 25.34, "elapsed_time": "5:50:04", "remaining_time": "17:11:35", "throughput": 663.46, "total_tokens": 13935872} {"current_steps": 10140, "total_steps": 40000, "loss": 0.7161, "lr": 4.248363221907183e-05, "epoch": 0.32456308815056656, "percentage": 25.35, "elapsed_time": "5:50:06", "remaining_time": "17:10:59", "throughput": 663.74, "total_tokens": 13942928} {"current_steps": 10145, "total_steps": 40000, "loss": 0.7058, "lr": 4.2476613495641026e-05, "epoch": 0.324723129121055, "percentage": 25.36, "elapsed_time": "5:50:08", "remaining_time": "17:10:24", "throughput": 664.0, "total_tokens": 13949680} {"current_steps": 10150, "total_steps": 40000, "loss": 0.6162, "lr": 4.246959207709679e-05, "epoch": 0.32488317009154344, "percentage": 25.37, "elapsed_time": "5:50:10", "remaining_time": "17:09:48", "throughput": 664.26, "total_tokens": 13956208} {"current_steps": 10155, "total_steps": 40000, "loss": 0.8185, "lr": 4.246256796452192e-05, "epoch": 0.3250432110620319, "percentage": 25.39, "elapsed_time": "5:50:11", "remaining_time": "17:09:12", "throughput": 664.53, "total_tokens": 13962992} {"current_steps": 10160, "total_steps": 40000, "loss": 0.6717, "lr": 4.245554115899962e-05, "epoch": 0.3252032520325203, "percentage": 25.4, "elapsed_time": "5:50:13", "remaining_time": "17:08:37", "throughput": 664.79, "total_tokens": 13969680} {"current_steps": 10165, "total_steps": 40000, "loss": 0.8279, "lr": 4.2448511661613514e-05, "epoch": 0.32536329300300876, "percentage": 25.41, "elapsed_time": "5:50:15", "remaining_time": "17:08:01", "throughput": 665.07, "total_tokens": 13976592} {"current_steps": 10170, "total_steps": 40000, "loss": 0.8058, "lr": 4.2441479473447635e-05, "epoch": 0.3255233339734972, "percentage": 25.42, "elapsed_time": "5:50:17", "remaining_time": "17:07:26", "throughput": 665.34, "total_tokens": 13983568} {"current_steps": 10175, "total_steps": 40000, "loss": 0.7766, "lr": 4.243444459558644e-05, "epoch": 0.32568337494398564, "percentage": 25.44, "elapsed_time": "5:50:18", "remaining_time": "17:06:50", "throughput": 665.64, "total_tokens": 13990928} {"current_steps": 10180, "total_steps": 40000, "loss": 0.804, "lr": 4.24274070291148e-05, "epoch": 0.32584341591447413, "percentage": 25.45, "elapsed_time": "5:50:20", "remaining_time": "17:06:14", "throughput": 665.91, "total_tokens": 13997776} {"current_steps": 10185, "total_steps": 40000, "loss": 0.7162, "lr": 4.242036677511798e-05, "epoch": 0.3260034568849626, "percentage": 25.46, "elapsed_time": "5:50:22", "remaining_time": "17:05:39", "throughput": 666.17, "total_tokens": 14004464} {"current_steps": 10190, "total_steps": 40000, "loss": 1.067, "lr": 4.241332383468169e-05, "epoch": 0.326163497855451, "percentage": 25.47, "elapsed_time": "5:50:24", "remaining_time": "17:05:03", "throughput": 666.45, "total_tokens": 14011520} {"current_steps": 10195, "total_steps": 40000, "loss": 0.6731, "lr": 4.2406278208892034e-05, "epoch": 0.32632353882593945, "percentage": 25.49, "elapsed_time": "5:50:25", "remaining_time": "17:04:28", "throughput": 666.73, "total_tokens": 14018464} {"current_steps": 10200, "total_steps": 40000, "loss": 0.7029, "lr": 4.2399229898835536e-05, "epoch": 0.3264835797964279, "percentage": 25.5, "elapsed_time": "5:50:27", "remaining_time": "17:03:53", "throughput": 667.0, "total_tokens": 14025248} {"current_steps": 10200, "total_steps": 40000, "eval_loss": 0.786490797996521, "epoch": 0.3264835797964279, "percentage": 25.5, "elapsed_time": "5:56:15", "remaining_time": "17:20:49", "throughput": 656.14, "total_tokens": 14025248} {"current_steps": 10205, "total_steps": 40000, "loss": 0.9221, "lr": 4.239217890559914e-05, "epoch": 0.32664362076691633, "percentage": 25.51, "elapsed_time": "5:56:18", "remaining_time": "17:20:18", "throughput": 656.35, "total_tokens": 14032096} {"current_steps": 10210, "total_steps": 40000, "loss": 1.1775, "lr": 4.238512523027019e-05, "epoch": 0.32680366173740477, "percentage": 25.52, "elapsed_time": "5:56:20", "remaining_time": "17:19:42", "throughput": 656.62, "total_tokens": 14038944} {"current_steps": 10215, "total_steps": 40000, "loss": 0.664, "lr": 4.237806887393645e-05, "epoch": 0.3269637027078932, "percentage": 25.54, "elapsed_time": "5:56:22", "remaining_time": "17:19:06", "throughput": 656.89, "total_tokens": 14045920} {"current_steps": 10220, "total_steps": 40000, "loss": 0.6116, "lr": 4.237100983768611e-05, "epoch": 0.32712374367838165, "percentage": 25.55, "elapsed_time": "5:56:24", "remaining_time": "17:18:31", "throughput": 657.17, "total_tokens": 14052992} {"current_steps": 10225, "total_steps": 40000, "loss": 0.8621, "lr": 4.2363948122607756e-05, "epoch": 0.3272837846488701, "percentage": 25.56, "elapsed_time": "5:56:25", "remaining_time": "17:17:55", "throughput": 657.43, "total_tokens": 14059632} {"current_steps": 10230, "total_steps": 40000, "loss": 0.6945, "lr": 4.235688372979039e-05, "epoch": 0.32744382561935853, "percentage": 25.57, "elapsed_time": "5:56:27", "remaining_time": "17:17:19", "throughput": 657.67, "total_tokens": 14066080} {"current_steps": 10235, "total_steps": 40000, "loss": 0.9958, "lr": 4.234981666032343e-05, "epoch": 0.327603866589847, "percentage": 25.59, "elapsed_time": "5:56:29", "remaining_time": "17:16:43", "throughput": 657.95, "total_tokens": 14073024} {"current_steps": 10240, "total_steps": 40000, "loss": 0.7525, "lr": 4.2342746915296704e-05, "epoch": 0.32776390756033547, "percentage": 25.6, "elapsed_time": "5:56:31", "remaining_time": "17:16:07", "throughput": 658.23, "total_tokens": 14080304} {"current_steps": 10245, "total_steps": 40000, "loss": 0.868, "lr": 4.233567449580047e-05, "epoch": 0.3279239485308239, "percentage": 25.61, "elapsed_time": "5:56:32", "remaining_time": "17:15:32", "throughput": 658.5, "total_tokens": 14087104} {"current_steps": 10250, "total_steps": 40000, "loss": 0.6703, "lr": 4.232859940292537e-05, "epoch": 0.32808398950131235, "percentage": 25.62, "elapsed_time": "5:56:34", "remaining_time": "17:14:56", "throughput": 658.74, "total_tokens": 14093440} {"current_steps": 10255, "total_steps": 40000, "loss": 0.7516, "lr": 4.232152163776248e-05, "epoch": 0.3282440304718008, "percentage": 25.64, "elapsed_time": "5:56:36", "remaining_time": "17:14:20", "throughput": 659.03, "total_tokens": 14100720} {"current_steps": 10260, "total_steps": 40000, "loss": 1.0275, "lr": 4.231444120140328e-05, "epoch": 0.3284040714422892, "percentage": 25.65, "elapsed_time": "5:56:38", "remaining_time": "17:13:45", "throughput": 659.29, "total_tokens": 14107552} {"current_steps": 10265, "total_steps": 40000, "loss": 0.8918, "lr": 4.230735809493967e-05, "epoch": 0.32856411241277766, "percentage": 25.66, "elapsed_time": "5:56:39", "remaining_time": "17:13:09", "throughput": 659.56, "total_tokens": 14114352} {"current_steps": 10270, "total_steps": 40000, "loss": 0.8189, "lr": 4.2300272319463926e-05, "epoch": 0.3287241533832661, "percentage": 25.67, "elapsed_time": "5:56:41", "remaining_time": "17:12:33", "throughput": 659.83, "total_tokens": 14121376} {"current_steps": 10275, "total_steps": 40000, "loss": 0.631, "lr": 4.2293183876068786e-05, "epoch": 0.32888419435375454, "percentage": 25.69, "elapsed_time": "5:56:43", "remaining_time": "17:11:58", "throughput": 660.08, "total_tokens": 14127792} {"current_steps": 10280, "total_steps": 40000, "loss": 0.7821, "lr": 4.228609276584737e-05, "epoch": 0.329044235324243, "percentage": 25.7, "elapsed_time": "5:56:44", "remaining_time": "17:11:22", "throughput": 660.35, "total_tokens": 14134864} {"current_steps": 10285, "total_steps": 40000, "loss": 0.7885, "lr": 4.227899898989323e-05, "epoch": 0.3292042762947314, "percentage": 25.71, "elapsed_time": "5:56:46", "remaining_time": "17:10:47", "throughput": 660.63, "total_tokens": 14141856} {"current_steps": 10290, "total_steps": 40000, "loss": 0.7735, "lr": 4.2271902549300293e-05, "epoch": 0.3293643172652199, "percentage": 25.72, "elapsed_time": "5:56:48", "remaining_time": "17:10:11", "throughput": 660.91, "total_tokens": 14148992} {"current_steps": 10295, "total_steps": 40000, "loss": 0.8265, "lr": 4.226480344516294e-05, "epoch": 0.32952435823570836, "percentage": 25.74, "elapsed_time": "5:56:50", "remaining_time": "17:09:36", "throughput": 661.17, "total_tokens": 14155856} {"current_steps": 10300, "total_steps": 40000, "loss": 0.641, "lr": 4.2257701678575925e-05, "epoch": 0.3296843992061968, "percentage": 25.75, "elapsed_time": "5:56:51", "remaining_time": "17:09:01", "throughput": 661.45, "total_tokens": 14162896} {"current_steps": 10305, "total_steps": 40000, "loss": 0.7062, "lr": 4.225059725063444e-05, "epoch": 0.32984444017668524, "percentage": 25.76, "elapsed_time": "5:56:53", "remaining_time": "17:08:25", "throughput": 661.72, "total_tokens": 14169824} {"current_steps": 10310, "total_steps": 40000, "loss": 0.8045, "lr": 4.2243490162434074e-05, "epoch": 0.3300044811471737, "percentage": 25.77, "elapsed_time": "5:56:55", "remaining_time": "17:07:50", "throughput": 661.98, "total_tokens": 14176576} {"current_steps": 10315, "total_steps": 40000, "loss": 0.7863, "lr": 4.223638041507083e-05, "epoch": 0.3301645221176621, "percentage": 25.79, "elapsed_time": "5:56:57", "remaining_time": "17:07:15", "throughput": 662.26, "total_tokens": 14183728} {"current_steps": 10320, "total_steps": 40000, "loss": 0.8439, "lr": 4.2229268009641124e-05, "epoch": 0.33032456308815056, "percentage": 25.8, "elapsed_time": "5:56:58", "remaining_time": "17:06:39", "throughput": 662.51, "total_tokens": 14190272} {"current_steps": 10325, "total_steps": 40000, "loss": 0.9193, "lr": 4.222215294724177e-05, "epoch": 0.330484604058639, "percentage": 25.81, "elapsed_time": "5:57:00", "remaining_time": "17:06:04", "throughput": 662.77, "total_tokens": 14196880} {"current_steps": 10330, "total_steps": 40000, "loss": 0.7526, "lr": 4.2215035228970005e-05, "epoch": 0.33064464502912744, "percentage": 25.82, "elapsed_time": "5:57:02", "remaining_time": "17:05:29", "throughput": 663.05, "total_tokens": 14204096} {"current_steps": 10335, "total_steps": 40000, "loss": 0.8162, "lr": 4.2207914855923464e-05, "epoch": 0.3308046859996159, "percentage": 25.84, "elapsed_time": "5:57:04", "remaining_time": "17:04:54", "throughput": 663.31, "total_tokens": 14210784} {"current_steps": 10340, "total_steps": 40000, "loss": 0.6849, "lr": 4.220079182920021e-05, "epoch": 0.3309647269701044, "percentage": 25.85, "elapsed_time": "5:57:05", "remaining_time": "17:04:19", "throughput": 663.56, "total_tokens": 14217312} {"current_steps": 10345, "total_steps": 40000, "loss": 0.6483, "lr": 4.2193666149898705e-05, "epoch": 0.3311247679405928, "percentage": 25.86, "elapsed_time": "5:57:07", "remaining_time": "17:03:44", "throughput": 663.82, "total_tokens": 14223936} {"current_steps": 10350, "total_steps": 40000, "loss": 0.8389, "lr": 4.21865378191178e-05, "epoch": 0.33128480891108125, "percentage": 25.87, "elapsed_time": "5:57:09", "remaining_time": "17:03:09", "throughput": 664.1, "total_tokens": 14231184} {"current_steps": 10355, "total_steps": 40000, "loss": 0.8514, "lr": 4.217940683795678e-05, "epoch": 0.3314448498815697, "percentage": 25.89, "elapsed_time": "5:57:11", "remaining_time": "17:02:34", "throughput": 664.37, "total_tokens": 14238048} {"current_steps": 10360, "total_steps": 40000, "loss": 0.7886, "lr": 4.217227320751534e-05, "epoch": 0.33160489085205813, "percentage": 25.9, "elapsed_time": "5:57:12", "remaining_time": "17:01:59", "throughput": 664.64, "total_tokens": 14245040} {"current_steps": 10365, "total_steps": 40000, "loss": 0.6389, "lr": 4.216513692889358e-05, "epoch": 0.33176493182254657, "percentage": 25.91, "elapsed_time": "5:57:14", "remaining_time": "17:01:24", "throughput": 664.89, "total_tokens": 14251664} {"current_steps": 10370, "total_steps": 40000, "loss": 0.7769, "lr": 4.215799800319199e-05, "epoch": 0.331924972793035, "percentage": 25.92, "elapsed_time": "5:57:16", "remaining_time": "17:00:49", "throughput": 665.17, "total_tokens": 14258752} {"current_steps": 10375, "total_steps": 40000, "loss": 0.9611, "lr": 4.2150856431511485e-05, "epoch": 0.33208501376352345, "percentage": 25.94, "elapsed_time": "5:57:17", "remaining_time": "17:00:14", "throughput": 665.44, "total_tokens": 14265584} {"current_steps": 10380, "total_steps": 40000, "loss": 0.7087, "lr": 4.214371221495339e-05, "epoch": 0.3322450547340119, "percentage": 25.95, "elapsed_time": "5:57:19", "remaining_time": "16:59:39", "throughput": 665.69, "total_tokens": 14272144} {"current_steps": 10385, "total_steps": 40000, "loss": 0.7745, "lr": 4.213656535461942e-05, "epoch": 0.33240509570450033, "percentage": 25.96, "elapsed_time": "5:57:21", "remaining_time": "16:59:04", "throughput": 665.96, "total_tokens": 14279056} {"current_steps": 10390, "total_steps": 40000, "loss": 0.7548, "lr": 4.2129415851611734e-05, "epoch": 0.33256513667498877, "percentage": 25.97, "elapsed_time": "5:57:23", "remaining_time": "16:58:29", "throughput": 666.22, "total_tokens": 14285856} {"current_steps": 10395, "total_steps": 40000, "loss": 0.7331, "lr": 4.2122263707032855e-05, "epoch": 0.33272517764547727, "percentage": 25.99, "elapsed_time": "5:57:24", "remaining_time": "16:57:55", "throughput": 666.49, "total_tokens": 14292928} {"current_steps": 10400, "total_steps": 40000, "loss": 0.7353, "lr": 4.211510892198574e-05, "epoch": 0.3328852186159657, "percentage": 26.0, "elapsed_time": "5:57:26", "remaining_time": "16:57:20", "throughput": 666.78, "total_tokens": 14300160} {"current_steps": 10400, "total_steps": 40000, "eval_loss": 0.7840673923492432, "epoch": 0.3328852186159657, "percentage": 26.0, "elapsed_time": "6:03:14", "remaining_time": "17:13:49", "throughput": 656.15, "total_tokens": 14300160} {"current_steps": 10405, "total_steps": 40000, "loss": 0.6854, "lr": 4.210795149757375e-05, "epoch": 0.33304525958645415, "percentage": 26.01, "elapsed_time": "6:03:17", "remaining_time": "17:13:19", "throughput": 656.34, "total_tokens": 14306800} {"current_steps": 10410, "total_steps": 40000, "loss": 0.842, "lr": 4.210079143490065e-05, "epoch": 0.3332053005569426, "percentage": 26.02, "elapsed_time": "6:03:19", "remaining_time": "17:12:44", "throughput": 656.61, "total_tokens": 14313792} {"current_steps": 10415, "total_steps": 40000, "loss": 0.8093, "lr": 4.2093628735070604e-05, "epoch": 0.333365341527431, "percentage": 26.04, "elapsed_time": "6:03:21", "remaining_time": "17:12:09", "throughput": 656.89, "total_tokens": 14320992} {"current_steps": 10420, "total_steps": 40000, "loss": 0.7657, "lr": 4.208646339918819e-05, "epoch": 0.33352538249791946, "percentage": 26.05, "elapsed_time": "6:03:23", "remaining_time": "17:11:33", "throughput": 657.15, "total_tokens": 14327872} {"current_steps": 10425, "total_steps": 40000, "loss": 0.7025, "lr": 4.2079295428358414e-05, "epoch": 0.3336854234684079, "percentage": 26.06, "elapsed_time": "6:03:24", "remaining_time": "17:10:58", "throughput": 657.41, "total_tokens": 14334624} {"current_steps": 10430, "total_steps": 40000, "loss": 0.9865, "lr": 4.207212482368664e-05, "epoch": 0.33384546443889634, "percentage": 26.07, "elapsed_time": "6:03:26", "remaining_time": "17:10:23", "throughput": 657.68, "total_tokens": 14341648} {"current_steps": 10435, "total_steps": 40000, "loss": 0.5592, "lr": 4.206495158627867e-05, "epoch": 0.3340055054093848, "percentage": 26.09, "elapsed_time": "6:03:28", "remaining_time": "17:09:48", "throughput": 657.92, "total_tokens": 14348000} {"current_steps": 10440, "total_steps": 40000, "loss": 0.8238, "lr": 4.205777571724073e-05, "epoch": 0.3341655463798732, "percentage": 26.1, "elapsed_time": "6:03:29", "remaining_time": "17:09:13", "throughput": 658.19, "total_tokens": 14355024} {"current_steps": 10445, "total_steps": 40000, "loss": 0.8741, "lr": 4.20505972176794e-05, "epoch": 0.3343255873503617, "percentage": 26.11, "elapsed_time": "6:03:31", "remaining_time": "17:08:38", "throughput": 658.45, "total_tokens": 14361904} {"current_steps": 10450, "total_steps": 40000, "loss": 0.6699, "lr": 4.204341608870171e-05, "epoch": 0.33448562832085016, "percentage": 26.12, "elapsed_time": "6:03:33", "remaining_time": "17:08:03", "throughput": 658.71, "total_tokens": 14368752} {"current_steps": 10455, "total_steps": 40000, "loss": 0.7328, "lr": 4.203623233141508e-05, "epoch": 0.3346456692913386, "percentage": 26.14, "elapsed_time": "6:03:35", "remaining_time": "17:07:28", "throughput": 658.97, "total_tokens": 14375552} {"current_steps": 10460, "total_steps": 40000, "loss": 0.9928, "lr": 4.2029045946927334e-05, "epoch": 0.33480571026182704, "percentage": 26.15, "elapsed_time": "6:03:36", "remaining_time": "17:06:52", "throughput": 659.23, "total_tokens": 14382304} {"current_steps": 10465, "total_steps": 40000, "loss": 1.0253, "lr": 4.20218569363467e-05, "epoch": 0.3349657512323155, "percentage": 26.16, "elapsed_time": "6:03:38", "remaining_time": "17:06:18", "throughput": 659.5, "total_tokens": 14389392} {"current_steps": 10470, "total_steps": 40000, "loss": 0.6027, "lr": 4.2014665300781834e-05, "epoch": 0.3351257922028039, "percentage": 26.17, "elapsed_time": "6:03:40", "remaining_time": "17:05:43", "throughput": 659.78, "total_tokens": 14396640} {"current_steps": 10475, "total_steps": 40000, "loss": 0.6823, "lr": 4.200747104134174e-05, "epoch": 0.33528583317329236, "percentage": 26.19, "elapsed_time": "6:03:42", "remaining_time": "17:05:08", "throughput": 660.05, "total_tokens": 14403632} {"current_steps": 10480, "total_steps": 40000, "loss": 0.7597, "lr": 4.200027415913588e-05, "epoch": 0.3354458741437808, "percentage": 26.2, "elapsed_time": "6:03:43", "remaining_time": "17:04:33", "throughput": 660.31, "total_tokens": 14410496} {"current_steps": 10485, "total_steps": 40000, "loss": 0.9132, "lr": 4.1993074655274126e-05, "epoch": 0.33560591511426924, "percentage": 26.21, "elapsed_time": "6:03:45", "remaining_time": "17:03:58", "throughput": 660.6, "total_tokens": 14417904} {"current_steps": 10490, "total_steps": 40000, "loss": 0.7953, "lr": 4.198587253086669e-05, "epoch": 0.3357659560847577, "percentage": 26.22, "elapsed_time": "6:03:47", "remaining_time": "17:03:23", "throughput": 660.88, "total_tokens": 14425216} {"current_steps": 10495, "total_steps": 40000, "loss": 0.6498, "lr": 4.197866778702426e-05, "epoch": 0.3359259970552461, "percentage": 26.24, "elapsed_time": "6:03:49", "remaining_time": "17:02:48", "throughput": 661.14, "total_tokens": 14432048} {"current_steps": 10500, "total_steps": 40000, "loss": 0.7044, "lr": 4.197146042485789e-05, "epoch": 0.3360860380257346, "percentage": 26.25, "elapsed_time": "6:03:50", "remaining_time": "17:02:14", "throughput": 661.4, "total_tokens": 14438832} {"current_steps": 10505, "total_steps": 40000, "loss": 0.678, "lr": 4.1964250445479046e-05, "epoch": 0.33624607899622305, "percentage": 26.26, "elapsed_time": "6:03:52", "remaining_time": "17:01:39", "throughput": 661.66, "total_tokens": 14445792} {"current_steps": 10510, "total_steps": 40000, "loss": 1.0384, "lr": 4.19570378499996e-05, "epoch": 0.3364061199667115, "percentage": 26.27, "elapsed_time": "6:03:54", "remaining_time": "17:01:04", "throughput": 661.95, "total_tokens": 14453200} {"current_steps": 10515, "total_steps": 40000, "loss": 0.7917, "lr": 4.194982263953182e-05, "epoch": 0.33656616093719993, "percentage": 26.29, "elapsed_time": "6:03:56", "remaining_time": "17:00:30", "throughput": 662.2, "total_tokens": 14459920} {"current_steps": 10520, "total_steps": 40000, "loss": 0.8899, "lr": 4.194260481518838e-05, "epoch": 0.33672620190768837, "percentage": 26.3, "elapsed_time": "6:03:57", "remaining_time": "16:59:55", "throughput": 662.46, "total_tokens": 14466544} {"current_steps": 10525, "total_steps": 40000, "loss": 0.8107, "lr": 4.1935384378082366e-05, "epoch": 0.3368862428781768, "percentage": 26.31, "elapsed_time": "6:03:59", "remaining_time": "16:59:20", "throughput": 662.72, "total_tokens": 14473424} {"current_steps": 10530, "total_steps": 40000, "loss": 0.6747, "lr": 4.1928161329327267e-05, "epoch": 0.33704628384866525, "percentage": 26.32, "elapsed_time": "6:04:01", "remaining_time": "16:58:46", "throughput": 663.0, "total_tokens": 14480800} {"current_steps": 10535, "total_steps": 40000, "loss": 0.6857, "lr": 4.1920935670036945e-05, "epoch": 0.3372063248191537, "percentage": 26.34, "elapsed_time": "6:04:02", "remaining_time": "16:58:11", "throughput": 663.29, "total_tokens": 14488256} {"current_steps": 10540, "total_steps": 40000, "loss": 0.7642, "lr": 4.1913707401325705e-05, "epoch": 0.33736636578964213, "percentage": 26.35, "elapsed_time": "6:04:04", "remaining_time": "16:57:37", "throughput": 663.55, "total_tokens": 14495040} {"current_steps": 10545, "total_steps": 40000, "loss": 0.7177, "lr": 4.1906476524308235e-05, "epoch": 0.33752640676013057, "percentage": 26.36, "elapsed_time": "6:04:06", "remaining_time": "16:57:02", "throughput": 663.81, "total_tokens": 14501792} {"current_steps": 10550, "total_steps": 40000, "loss": 0.6428, "lr": 4.189924304009962e-05, "epoch": 0.33768644773061907, "percentage": 26.38, "elapsed_time": "6:04:08", "remaining_time": "16:56:28", "throughput": 664.08, "total_tokens": 14508848} {"current_steps": 10555, "total_steps": 40000, "loss": 0.6529, "lr": 4.189200694981537e-05, "epoch": 0.3378464887011075, "percentage": 26.39, "elapsed_time": "6:04:09", "remaining_time": "16:55:54", "throughput": 664.34, "total_tokens": 14515712} {"current_steps": 10560, "total_steps": 40000, "loss": 0.5614, "lr": 4.188476825457136e-05, "epoch": 0.33800652967159595, "percentage": 26.4, "elapsed_time": "6:04:11", "remaining_time": "16:55:19", "throughput": 664.6, "total_tokens": 14522704} {"current_steps": 10565, "total_steps": 40000, "loss": 0.8893, "lr": 4.18775269554839e-05, "epoch": 0.3381665706420844, "percentage": 26.41, "elapsed_time": "6:04:13", "remaining_time": "16:54:45", "throughput": 664.86, "total_tokens": 14529472} {"current_steps": 10570, "total_steps": 40000, "loss": 0.7902, "lr": 4.187028305366969e-05, "epoch": 0.3383266116125728, "percentage": 26.42, "elapsed_time": "6:04:15", "remaining_time": "16:54:11", "throughput": 665.14, "total_tokens": 14536784} {"current_steps": 10575, "total_steps": 40000, "loss": 0.714, "lr": 4.1863036550245824e-05, "epoch": 0.33848665258306126, "percentage": 26.44, "elapsed_time": "6:04:16", "remaining_time": "16:53:36", "throughput": 665.41, "total_tokens": 14543856} {"current_steps": 10580, "total_steps": 40000, "loss": 0.7709, "lr": 4.1855787446329806e-05, "epoch": 0.3386466935535497, "percentage": 26.45, "elapsed_time": "6:04:18", "remaining_time": "16:53:02", "throughput": 665.69, "total_tokens": 14550992} {"current_steps": 10585, "total_steps": 40000, "loss": 0.7807, "lr": 4.184853574303955e-05, "epoch": 0.33880673452403814, "percentage": 26.46, "elapsed_time": "6:04:20", "remaining_time": "16:52:28", "throughput": 665.94, "total_tokens": 14557584} {"current_steps": 10590, "total_steps": 40000, "loss": 0.6749, "lr": 4.184128144149334e-05, "epoch": 0.3389667754945266, "percentage": 26.47, "elapsed_time": "6:04:22", "remaining_time": "16:51:54", "throughput": 666.21, "total_tokens": 14564640} {"current_steps": 10595, "total_steps": 40000, "loss": 0.7026, "lr": 4.1834024542809896e-05, "epoch": 0.339126816465015, "percentage": 26.49, "elapsed_time": "6:04:23", "remaining_time": "16:51:19", "throughput": 666.46, "total_tokens": 14571232} {"current_steps": 10600, "total_steps": 40000, "loss": 0.6306, "lr": 4.1826765048108315e-05, "epoch": 0.33928685743550346, "percentage": 26.5, "elapsed_time": "6:04:25", "remaining_time": "16:50:45", "throughput": 666.7, "total_tokens": 14577760} {"current_steps": 10600, "total_steps": 40000, "eval_loss": 0.7832810282707214, "epoch": 0.33928685743550346, "percentage": 26.5, "elapsed_time": "6:10:13", "remaining_time": "17:06:50", "throughput": 656.27, "total_tokens": 14577760} {"current_steps": 10605, "total_steps": 40000, "loss": 0.6927, "lr": 4.181950295850811e-05, "epoch": 0.33944689840599196, "percentage": 26.51, "elapsed_time": "6:10:16", "remaining_time": "17:06:20", "throughput": 656.45, "total_tokens": 14584336} {"current_steps": 10610, "total_steps": 40000, "loss": 0.6307, "lr": 4.181223827512918e-05, "epoch": 0.3396069393764804, "percentage": 26.52, "elapsed_time": "6:10:18", "remaining_time": "17:05:46", "throughput": 656.71, "total_tokens": 14591232} {"current_steps": 10615, "total_steps": 40000, "loss": 0.5836, "lr": 4.180497099909183e-05, "epoch": 0.33976698034696884, "percentage": 26.54, "elapsed_time": "6:10:20", "remaining_time": "17:05:11", "throughput": 656.97, "total_tokens": 14598064} {"current_steps": 10620, "total_steps": 40000, "loss": 0.6466, "lr": 4.179770113151677e-05, "epoch": 0.3399270213174573, "percentage": 26.55, "elapsed_time": "6:10:22", "remaining_time": "17:04:36", "throughput": 657.22, "total_tokens": 14604896} {"current_steps": 10625, "total_steps": 40000, "loss": 0.6594, "lr": 4.179042867352511e-05, "epoch": 0.3400870622879457, "percentage": 26.56, "elapsed_time": "6:10:23", "remaining_time": "17:04:02", "throughput": 657.49, "total_tokens": 14611904} {"current_steps": 10630, "total_steps": 40000, "loss": 0.8214, "lr": 4.1783153626238334e-05, "epoch": 0.34024710325843416, "percentage": 26.57, "elapsed_time": "6:10:25", "remaining_time": "17:03:27", "throughput": 657.74, "total_tokens": 14618544} {"current_steps": 10635, "total_steps": 40000, "loss": 0.9281, "lr": 4.177587599077836e-05, "epoch": 0.3404071442289226, "percentage": 26.59, "elapsed_time": "6:10:27", "remaining_time": "17:02:53", "throughput": 657.99, "total_tokens": 14625296} {"current_steps": 10640, "total_steps": 40000, "loss": 0.9485, "lr": 4.1768595768267494e-05, "epoch": 0.34056718519941104, "percentage": 26.6, "elapsed_time": "6:10:29", "remaining_time": "17:02:18", "throughput": 658.26, "total_tokens": 14632528} {"current_steps": 10645, "total_steps": 40000, "loss": 0.8476, "lr": 4.176131295982843e-05, "epoch": 0.3407272261698995, "percentage": 26.61, "elapsed_time": "6:10:30", "remaining_time": "17:01:44", "throughput": 658.5, "total_tokens": 14638976} {"current_steps": 10650, "total_steps": 40000, "loss": 0.872, "lr": 4.1754027566584276e-05, "epoch": 0.3408872671403879, "percentage": 26.62, "elapsed_time": "6:10:32", "remaining_time": "17:01:09", "throughput": 658.76, "total_tokens": 14645792} {"current_steps": 10655, "total_steps": 40000, "loss": 0.9137, "lr": 4.174673958965852e-05, "epoch": 0.34104730811087636, "percentage": 26.64, "elapsed_time": "6:10:34", "remaining_time": "17:00:35", "throughput": 659.03, "total_tokens": 14653040} {"current_steps": 10660, "total_steps": 40000, "loss": 0.6959, "lr": 4.173944903017507e-05, "epoch": 0.34120734908136485, "percentage": 26.65, "elapsed_time": "6:10:35", "remaining_time": "17:00:01", "throughput": 659.28, "total_tokens": 14659792} {"current_steps": 10665, "total_steps": 40000, "loss": 0.949, "lr": 4.173215588925822e-05, "epoch": 0.3413673900518533, "percentage": 26.66, "elapsed_time": "6:10:37", "remaining_time": "16:59:26", "throughput": 659.53, "total_tokens": 14666400} {"current_steps": 10670, "total_steps": 40000, "loss": 0.7117, "lr": 4.172486016803266e-05, "epoch": 0.34152743102234173, "percentage": 26.67, "elapsed_time": "6:10:39", "remaining_time": "16:58:52", "throughput": 659.79, "total_tokens": 14673360} {"current_steps": 10675, "total_steps": 40000, "loss": 0.796, "lr": 4.171756186762349e-05, "epoch": 0.34168747199283017, "percentage": 26.69, "elapsed_time": "6:10:41", "remaining_time": "16:58:18", "throughput": 660.05, "total_tokens": 14680192} {"current_steps": 10680, "total_steps": 40000, "loss": 0.7992, "lr": 4.171026098915619e-05, "epoch": 0.3418475129633186, "percentage": 26.7, "elapsed_time": "6:10:42", "remaining_time": "16:57:43", "throughput": 660.3, "total_tokens": 14686912} {"current_steps": 10685, "total_steps": 40000, "loss": 0.9144, "lr": 4.170295753375665e-05, "epoch": 0.34200755393380705, "percentage": 26.71, "elapsed_time": "6:10:44", "remaining_time": "16:57:09", "throughput": 660.55, "total_tokens": 14693792} {"current_steps": 10690, "total_steps": 40000, "loss": 0.7715, "lr": 4.169565150255117e-05, "epoch": 0.3421675949042955, "percentage": 26.72, "elapsed_time": "6:10:46", "remaining_time": "16:56:35", "throughput": 660.83, "total_tokens": 14700992} {"current_steps": 10695, "total_steps": 40000, "loss": 0.7191, "lr": 4.16883428966664e-05, "epoch": 0.34232763587478393, "percentage": 26.74, "elapsed_time": "6:10:48", "remaining_time": "16:56:01", "throughput": 661.08, "total_tokens": 14707840} {"current_steps": 10700, "total_steps": 40000, "loss": 0.7095, "lr": 4.168103171722944e-05, "epoch": 0.34248767684527237, "percentage": 26.75, "elapsed_time": "6:10:49", "remaining_time": "16:55:27", "throughput": 661.34, "total_tokens": 14714656} {"current_steps": 10705, "total_steps": 40000, "loss": 0.7284, "lr": 4.167371796536777e-05, "epoch": 0.3426477178157608, "percentage": 26.76, "elapsed_time": "6:10:51", "remaining_time": "16:54:53", "throughput": 661.61, "total_tokens": 14721808} {"current_steps": 10710, "total_steps": 40000, "loss": 0.8767, "lr": 4.166640164220924e-05, "epoch": 0.3428077587862493, "percentage": 26.77, "elapsed_time": "6:10:53", "remaining_time": "16:54:19", "throughput": 661.88, "total_tokens": 14729008} {"current_steps": 10715, "total_steps": 40000, "loss": 0.7199, "lr": 4.1659082748882144e-05, "epoch": 0.34296779975673775, "percentage": 26.79, "elapsed_time": "6:10:55", "remaining_time": "16:53:44", "throughput": 662.14, "total_tokens": 14735952} {"current_steps": 10720, "total_steps": 40000, "loss": 1.0117, "lr": 4.1651761286515135e-05, "epoch": 0.3431278407272262, "percentage": 26.8, "elapsed_time": "6:10:56", "remaining_time": "16:53:10", "throughput": 662.39, "total_tokens": 14742736} {"current_steps": 10725, "total_steps": 40000, "loss": 0.7192, "lr": 4.164443725623728e-05, "epoch": 0.3432878816977146, "percentage": 26.81, "elapsed_time": "6:10:58", "remaining_time": "16:52:36", "throughput": 662.63, "total_tokens": 14749120} {"current_steps": 10730, "total_steps": 40000, "loss": 0.7357, "lr": 4.163711065917802e-05, "epoch": 0.34344792266820307, "percentage": 26.82, "elapsed_time": "6:11:00", "remaining_time": "16:52:03", "throughput": 662.89, "total_tokens": 14756064} {"current_steps": 10735, "total_steps": 40000, "loss": 0.7823, "lr": 4.1629781496467234e-05, "epoch": 0.3436079636386915, "percentage": 26.84, "elapsed_time": "6:11:02", "remaining_time": "16:51:29", "throughput": 663.16, "total_tokens": 14763184} {"current_steps": 10740, "total_steps": 40000, "loss": 0.7719, "lr": 4.1622449769235164e-05, "epoch": 0.34376800460917994, "percentage": 26.85, "elapsed_time": "6:11:03", "remaining_time": "16:50:55", "throughput": 663.41, "total_tokens": 14769984} {"current_steps": 10745, "total_steps": 40000, "loss": 0.9049, "lr": 4.161511547861243e-05, "epoch": 0.3439280455796684, "percentage": 26.86, "elapsed_time": "6:11:05", "remaining_time": "16:50:21", "throughput": 663.67, "total_tokens": 14777008} {"current_steps": 10750, "total_steps": 40000, "loss": 0.6514, "lr": 4.1607778625730104e-05, "epoch": 0.3440880865501568, "percentage": 26.88, "elapsed_time": "6:11:07", "remaining_time": "16:49:47", "throughput": 663.93, "total_tokens": 14783808} {"current_steps": 10755, "total_steps": 40000, "loss": 0.6548, "lr": 4.160043921171961e-05, "epoch": 0.34424812752064526, "percentage": 26.89, "elapsed_time": "6:11:08", "remaining_time": "16:49:13", "throughput": 664.2, "total_tokens": 14791040} {"current_steps": 10760, "total_steps": 40000, "loss": 0.7258, "lr": 4.159309723771276e-05, "epoch": 0.3444081684911337, "percentage": 26.9, "elapsed_time": "6:11:10", "remaining_time": "16:48:39", "throughput": 664.45, "total_tokens": 14797840} {"current_steps": 10765, "total_steps": 40000, "loss": 0.5638, "lr": 4.158575270484181e-05, "epoch": 0.3445682094616222, "percentage": 26.91, "elapsed_time": "6:11:12", "remaining_time": "16:48:06", "throughput": 664.69, "total_tokens": 14804240} {"current_steps": 10770, "total_steps": 40000, "loss": 0.8798, "lr": 4.157840561423936e-05, "epoch": 0.34472825043211064, "percentage": 26.92, "elapsed_time": "6:11:14", "remaining_time": "16:47:32", "throughput": 664.93, "total_tokens": 14810768} {"current_steps": 10775, "total_steps": 40000, "loss": 0.6754, "lr": 4.1571055967038416e-05, "epoch": 0.3448882914025991, "percentage": 26.94, "elapsed_time": "6:11:15", "remaining_time": "16:46:58", "throughput": 665.17, "total_tokens": 14817280} {"current_steps": 10780, "total_steps": 40000, "loss": 0.6911, "lr": 4.156370376437241e-05, "epoch": 0.3450483323730875, "percentage": 26.95, "elapsed_time": "6:11:17", "remaining_time": "16:46:25", "throughput": 665.42, "total_tokens": 14824016} {"current_steps": 10785, "total_steps": 40000, "loss": 0.7852, "lr": 4.155634900737513e-05, "epoch": 0.34520837334357596, "percentage": 26.96, "elapsed_time": "6:11:19", "remaining_time": "16:45:51", "throughput": 665.67, "total_tokens": 14830720} {"current_steps": 10790, "total_steps": 40000, "loss": 0.7233, "lr": 4.1548991697180764e-05, "epoch": 0.3453684143140644, "percentage": 26.97, "elapsed_time": "6:11:21", "remaining_time": "16:45:17", "throughput": 665.92, "total_tokens": 14837312} {"current_steps": 10795, "total_steps": 40000, "loss": 0.5619, "lr": 4.1541631834923914e-05, "epoch": 0.34552845528455284, "percentage": 26.99, "elapsed_time": "6:11:22", "remaining_time": "16:44:44", "throughput": 666.16, "total_tokens": 14844016} {"current_steps": 10800, "total_steps": 40000, "loss": 0.7592, "lr": 4.153426942173956e-05, "epoch": 0.3456884962550413, "percentage": 27.0, "elapsed_time": "6:11:24", "remaining_time": "16:44:10", "throughput": 666.44, "total_tokens": 14851280} {"current_steps": 10800, "total_steps": 40000, "eval_loss": 0.780483603477478, "epoch": 0.3456884962550413, "percentage": 27.0, "elapsed_time": "6:17:12", "remaining_time": "16:59:51", "throughput": 656.19, "total_tokens": 14851280} {"current_steps": 10805, "total_steps": 40000, "loss": 0.7926, "lr": 4.152690445876308e-05, "epoch": 0.3458485372255297, "percentage": 27.01, "elapsed_time": "6:17:17", "remaining_time": "16:59:25", "throughput": 656.37, "total_tokens": 14858480} {"current_steps": 10810, "total_steps": 40000, "loss": 0.962, "lr": 4.1519536947130245e-05, "epoch": 0.34600857819601816, "percentage": 27.02, "elapsed_time": "6:17:19", "remaining_time": "16:58:51", "throughput": 656.63, "total_tokens": 14865456} {"current_steps": 10815, "total_steps": 40000, "loss": 0.6573, "lr": 4.151216688797722e-05, "epoch": 0.34616861916650665, "percentage": 27.04, "elapsed_time": "6:17:20", "remaining_time": "16:58:17", "throughput": 656.87, "total_tokens": 14872096} {"current_steps": 10820, "total_steps": 40000, "loss": 0.8531, "lr": 4.150479428244054e-05, "epoch": 0.3463286601369951, "percentage": 27.05, "elapsed_time": "6:17:22", "remaining_time": "16:57:43", "throughput": 657.11, "total_tokens": 14878640} {"current_steps": 10825, "total_steps": 40000, "loss": 0.7761, "lr": 4.1497419131657176e-05, "epoch": 0.34648870110748353, "percentage": 27.06, "elapsed_time": "6:17:24", "remaining_time": "16:57:09", "throughput": 657.35, "total_tokens": 14885216} {"current_steps": 10830, "total_steps": 40000, "loss": 0.6914, "lr": 4.149004143676447e-05, "epoch": 0.34664874207797197, "percentage": 27.07, "elapsed_time": "6:17:26", "remaining_time": "16:56:35", "throughput": 657.6, "total_tokens": 14891936} {"current_steps": 10835, "total_steps": 40000, "loss": 0.9962, "lr": 4.148266119890015e-05, "epoch": 0.3468087830484604, "percentage": 27.09, "elapsed_time": "6:17:27", "remaining_time": "16:56:01", "throughput": 657.86, "total_tokens": 14899088} {"current_steps": 10840, "total_steps": 40000, "loss": 0.8452, "lr": 4.1475278419202324e-05, "epoch": 0.34696882401894885, "percentage": 27.1, "elapsed_time": "6:17:29", "remaining_time": "16:55:27", "throughput": 658.12, "total_tokens": 14906032} {"current_steps": 10845, "total_steps": 40000, "loss": 0.8799, "lr": 4.146789309880953e-05, "epoch": 0.3471288649894373, "percentage": 27.11, "elapsed_time": "6:17:31", "remaining_time": "16:54:54", "throughput": 658.36, "total_tokens": 14912752} {"current_steps": 10850, "total_steps": 40000, "loss": 0.8095, "lr": 4.146050523886068e-05, "epoch": 0.34728890595992573, "percentage": 27.12, "elapsed_time": "6:17:32", "remaining_time": "16:54:20", "throughput": 658.62, "total_tokens": 14919776} {"current_steps": 10855, "total_steps": 40000, "loss": 0.8022, "lr": 4.1453114840495055e-05, "epoch": 0.34744894693041417, "percentage": 27.14, "elapsed_time": "6:17:34", "remaining_time": "16:53:46", "throughput": 658.86, "total_tokens": 14926304} {"current_steps": 10860, "total_steps": 40000, "loss": 0.7896, "lr": 4.1445721904852364e-05, "epoch": 0.3476089879009026, "percentage": 27.15, "elapsed_time": "6:17:36", "remaining_time": "16:53:12", "throughput": 659.12, "total_tokens": 14933376} {"current_steps": 10865, "total_steps": 40000, "loss": 0.667, "lr": 4.143832643307269e-05, "epoch": 0.34776902887139105, "percentage": 27.16, "elapsed_time": "6:17:38", "remaining_time": "16:52:38", "throughput": 659.36, "total_tokens": 14939792} {"current_steps": 10870, "total_steps": 40000, "loss": 0.704, "lr": 4.1430928426296503e-05, "epoch": 0.34792906984187955, "percentage": 27.18, "elapsed_time": "6:17:39", "remaining_time": "16:52:05", "throughput": 659.63, "total_tokens": 14947104} {"current_steps": 10875, "total_steps": 40000, "loss": 0.6994, "lr": 4.142352788566466e-05, "epoch": 0.348089110812368, "percentage": 27.19, "elapsed_time": "6:17:41", "remaining_time": "16:51:31", "throughput": 659.9, "total_tokens": 14954336} {"current_steps": 10880, "total_steps": 40000, "loss": 0.9255, "lr": 4.1416124812318424e-05, "epoch": 0.3482491517828564, "percentage": 27.2, "elapsed_time": "6:17:43", "remaining_time": "16:50:57", "throughput": 660.14, "total_tokens": 14960928} {"current_steps": 10885, "total_steps": 40000, "loss": 0.639, "lr": 4.1408719207399453e-05, "epoch": 0.34840919275334487, "percentage": 27.21, "elapsed_time": "6:17:45", "remaining_time": "16:50:24", "throughput": 660.39, "total_tokens": 14967824} {"current_steps": 10890, "total_steps": 40000, "loss": 0.873, "lr": 4.140131107204978e-05, "epoch": 0.3485692337238333, "percentage": 27.22, "elapsed_time": "6:17:46", "remaining_time": "16:49:50", "throughput": 660.65, "total_tokens": 14974928} {"current_steps": 10895, "total_steps": 40000, "loss": 0.6901, "lr": 4.139390040741182e-05, "epoch": 0.34872927469432174, "percentage": 27.24, "elapsed_time": "6:17:48", "remaining_time": "16:49:17", "throughput": 660.9, "total_tokens": 14981696} {"current_steps": 10900, "total_steps": 40000, "loss": 0.66, "lr": 4.1386487214628396e-05, "epoch": 0.3488893156648102, "percentage": 27.25, "elapsed_time": "6:17:50", "remaining_time": "16:48:43", "throughput": 661.14, "total_tokens": 14988336} {"current_steps": 10905, "total_steps": 40000, "loss": 0.8526, "lr": 4.137907149484272e-05, "epoch": 0.3490493566352986, "percentage": 27.26, "elapsed_time": "6:17:52", "remaining_time": "16:48:09", "throughput": 661.41, "total_tokens": 14995440} {"current_steps": 10910, "total_steps": 40000, "loss": 0.7186, "lr": 4.137165324919839e-05, "epoch": 0.34920939760578706, "percentage": 27.27, "elapsed_time": "6:17:53", "remaining_time": "16:47:36", "throughput": 661.65, "total_tokens": 15002048} {"current_steps": 10915, "total_steps": 40000, "loss": 0.7465, "lr": 4.136423247883939e-05, "epoch": 0.3493694385762755, "percentage": 27.29, "elapsed_time": "6:17:55", "remaining_time": "16:47:03", "throughput": 661.9, "total_tokens": 15008960} {"current_steps": 10920, "total_steps": 40000, "loss": 0.6967, "lr": 4.135680918491009e-05, "epoch": 0.349529479546764, "percentage": 27.3, "elapsed_time": "6:17:57", "remaining_time": "16:46:29", "throughput": 662.16, "total_tokens": 15015904} {"current_steps": 10925, "total_steps": 40000, "loss": 0.8418, "lr": 4.1349383368555265e-05, "epoch": 0.34968952051725244, "percentage": 27.31, "elapsed_time": "6:17:58", "remaining_time": "16:45:56", "throughput": 662.41, "total_tokens": 15022800} {"current_steps": 10930, "total_steps": 40000, "loss": 0.5173, "lr": 4.1341955030920065e-05, "epoch": 0.3498495614877409, "percentage": 27.32, "elapsed_time": "6:18:00", "remaining_time": "16:45:22", "throughput": 662.65, "total_tokens": 15029424} {"current_steps": 10935, "total_steps": 40000, "loss": 0.8862, "lr": 4.1334524173150036e-05, "epoch": 0.3500096024582293, "percentage": 27.34, "elapsed_time": "6:18:02", "remaining_time": "16:44:49", "throughput": 662.92, "total_tokens": 15036656} {"current_steps": 10940, "total_steps": 40000, "loss": 0.6299, "lr": 4.13270907963911e-05, "epoch": 0.35016964342871776, "percentage": 27.35, "elapsed_time": "6:18:04", "remaining_time": "16:44:16", "throughput": 663.17, "total_tokens": 15043376} {"current_steps": 10945, "total_steps": 40000, "loss": 0.817, "lr": 4.131965490178959e-05, "epoch": 0.3503296843992062, "percentage": 27.36, "elapsed_time": "6:18:05", "remaining_time": "16:43:42", "throughput": 663.42, "total_tokens": 15050400} {"current_steps": 10950, "total_steps": 40000, "loss": 0.8737, "lr": 4.131221649049222e-05, "epoch": 0.35048972536969464, "percentage": 27.38, "elapsed_time": "6:18:07", "remaining_time": "16:43:09", "throughput": 663.67, "total_tokens": 15057168} {"current_steps": 10955, "total_steps": 40000, "loss": 0.9117, "lr": 4.130477556364606e-05, "epoch": 0.3506497663401831, "percentage": 27.39, "elapsed_time": "6:18:09", "remaining_time": "16:42:36", "throughput": 663.92, "total_tokens": 15063872} {"current_steps": 10960, "total_steps": 40000, "loss": 0.6702, "lr": 4.129733212239861e-05, "epoch": 0.3508098073106715, "percentage": 27.4, "elapsed_time": "6:18:11", "remaining_time": "16:42:03", "throughput": 664.16, "total_tokens": 15070640} {"current_steps": 10965, "total_steps": 40000, "loss": 0.8563, "lr": 4.128988616789774e-05, "epoch": 0.35096984828115996, "percentage": 27.41, "elapsed_time": "6:18:12", "remaining_time": "16:41:30", "throughput": 664.42, "total_tokens": 15077664} {"current_steps": 10970, "total_steps": 40000, "loss": 0.6123, "lr": 4.1282437701291724e-05, "epoch": 0.3511298892516484, "percentage": 27.43, "elapsed_time": "6:18:14", "remaining_time": "16:40:56", "throughput": 664.68, "total_tokens": 15084704} {"current_steps": 10975, "total_steps": 40000, "loss": 0.711, "lr": 4.1274986723729184e-05, "epoch": 0.3512899302221369, "percentage": 27.44, "elapsed_time": "6:18:16", "remaining_time": "16:40:23", "throughput": 664.94, "total_tokens": 15091664} {"current_steps": 10980, "total_steps": 40000, "loss": 0.835, "lr": 4.126753323635917e-05, "epoch": 0.35144997119262533, "percentage": 27.45, "elapsed_time": "6:18:18", "remaining_time": "16:39:50", "throughput": 665.17, "total_tokens": 15098192} {"current_steps": 10985, "total_steps": 40000, "loss": 0.8553, "lr": 4.12600772403311e-05, "epoch": 0.35161001216311377, "percentage": 27.46, "elapsed_time": "6:18:19", "remaining_time": "16:39:17", "throughput": 665.42, "total_tokens": 15104960} {"current_steps": 10990, "total_steps": 40000, "loss": 0.8151, "lr": 4.125261873679479e-05, "epoch": 0.3517700531336022, "percentage": 27.47, "elapsed_time": "6:18:21", "remaining_time": "16:38:44", "throughput": 665.67, "total_tokens": 15111680} {"current_steps": 10995, "total_steps": 40000, "loss": 0.9169, "lr": 4.124515772690042e-05, "epoch": 0.35193009410409065, "percentage": 27.49, "elapsed_time": "6:18:23", "remaining_time": "16:38:11", "throughput": 665.92, "total_tokens": 15118480} {"current_steps": 11000, "total_steps": 40000, "loss": 0.588, "lr": 4.123769421179858e-05, "epoch": 0.3520901350745791, "percentage": 27.5, "elapsed_time": "6:18:25", "remaining_time": "16:37:38", "throughput": 666.16, "total_tokens": 15125104} {"current_steps": 11000, "total_steps": 40000, "eval_loss": 0.7807932496070862, "epoch": 0.3520901350745791, "percentage": 27.5, "elapsed_time": "6:24:12", "remaining_time": "16:52:54", "throughput": 656.11, "total_tokens": 15125104} {"current_steps": 11005, "total_steps": 40000, "loss": 0.6338, "lr": 4.1230228192640236e-05, "epoch": 0.35225017604506753, "percentage": 27.51, "elapsed_time": "6:24:16", "remaining_time": "16:52:25", "throughput": 656.31, "total_tokens": 15131968} {"current_steps": 11010, "total_steps": 40000, "loss": 0.7446, "lr": 4.122275967057675e-05, "epoch": 0.35241021701555597, "percentage": 27.52, "elapsed_time": "6:24:17", "remaining_time": "16:51:52", "throughput": 656.56, "total_tokens": 15138752} {"current_steps": 11015, "total_steps": 40000, "loss": 0.8414, "lr": 4.1215288646759846e-05, "epoch": 0.3525702579860444, "percentage": 27.54, "elapsed_time": "6:24:19", "remaining_time": "16:51:19", "throughput": 656.8, "total_tokens": 15145600} {"current_steps": 11020, "total_steps": 40000, "loss": 0.5403, "lr": 4.120781512234166e-05, "epoch": 0.35273029895653285, "percentage": 27.55, "elapsed_time": "6:24:21", "remaining_time": "16:50:45", "throughput": 657.06, "total_tokens": 15152560} {"current_steps": 11025, "total_steps": 40000, "loss": 0.8192, "lr": 4.120033909847471e-05, "epoch": 0.3528903399270213, "percentage": 27.56, "elapsed_time": "6:24:22", "remaining_time": "16:50:12", "throughput": 657.3, "total_tokens": 15159328} {"current_steps": 11030, "total_steps": 40000, "loss": 1.0038, "lr": 4.119286057631187e-05, "epoch": 0.3530503808975098, "percentage": 27.57, "elapsed_time": "6:24:24", "remaining_time": "16:49:38", "throughput": 657.56, "total_tokens": 15166448} {"current_steps": 11035, "total_steps": 40000, "loss": 0.813, "lr": 4.118537955700646e-05, "epoch": 0.3532104218679982, "percentage": 27.59, "elapsed_time": "6:24:26", "remaining_time": "16:49:05", "throughput": 657.8, "total_tokens": 15173232} {"current_steps": 11040, "total_steps": 40000, "loss": 0.7737, "lr": 4.11778960417121e-05, "epoch": 0.35337046283848667, "percentage": 27.6, "elapsed_time": "6:24:28", "remaining_time": "16:48:32", "throughput": 658.04, "total_tokens": 15179792} {"current_steps": 11045, "total_steps": 40000, "loss": 0.9253, "lr": 4.117041003158288e-05, "epoch": 0.3535305038089751, "percentage": 27.61, "elapsed_time": "6:24:29", "remaining_time": "16:47:58", "throughput": 658.28, "total_tokens": 15186576} {"current_steps": 11050, "total_steps": 40000, "loss": 0.8089, "lr": 4.1162921527773215e-05, "epoch": 0.35369054477946354, "percentage": 27.62, "elapsed_time": "6:24:31", "remaining_time": "16:47:25", "throughput": 658.53, "total_tokens": 15193328} {"current_steps": 11055, "total_steps": 40000, "loss": 0.6448, "lr": 4.115543053143794e-05, "epoch": 0.353850585749952, "percentage": 27.64, "elapsed_time": "6:24:33", "remaining_time": "16:46:52", "throughput": 658.78, "total_tokens": 15200208} {"current_steps": 11060, "total_steps": 40000, "loss": 0.7646, "lr": 4.114793704373226e-05, "epoch": 0.3540106267204404, "percentage": 27.65, "elapsed_time": "6:24:35", "remaining_time": "16:46:19", "throughput": 659.02, "total_tokens": 15207040} {"current_steps": 11065, "total_steps": 40000, "loss": 0.7543, "lr": 4.114044106581175e-05, "epoch": 0.35417066769092886, "percentage": 27.66, "elapsed_time": "6:24:36", "remaining_time": "16:45:46", "throughput": 659.27, "total_tokens": 15213984} {"current_steps": 11070, "total_steps": 40000, "loss": 0.5879, "lr": 4.11329425988324e-05, "epoch": 0.3543307086614173, "percentage": 27.68, "elapsed_time": "6:24:38", "remaining_time": "16:45:12", "throughput": 659.52, "total_tokens": 15220768} {"current_steps": 11075, "total_steps": 40000, "loss": 0.7361, "lr": 4.112544164395056e-05, "epoch": 0.35449074963190574, "percentage": 27.69, "elapsed_time": "6:24:40", "remaining_time": "16:44:39", "throughput": 659.74, "total_tokens": 15227104} {"current_steps": 11080, "total_steps": 40000, "loss": 0.9567, "lr": 4.111793820232297e-05, "epoch": 0.35465079060239424, "percentage": 27.7, "elapsed_time": "6:24:42", "remaining_time": "16:44:06", "throughput": 660.01, "total_tokens": 15234432} {"current_steps": 11085, "total_steps": 40000, "loss": 0.7473, "lr": 4.1110432275106767e-05, "epoch": 0.3548108315728827, "percentage": 27.71, "elapsed_time": "6:24:43", "remaining_time": "16:43:33", "throughput": 660.26, "total_tokens": 15241280} {"current_steps": 11090, "total_steps": 40000, "loss": 0.6019, "lr": 4.110292386345944e-05, "epoch": 0.3549708725433711, "percentage": 27.73, "elapsed_time": "6:24:45", "remaining_time": "16:43:00", "throughput": 660.5, "total_tokens": 15248128} {"current_steps": 11095, "total_steps": 40000, "loss": 0.7418, "lr": 4.109541296853891e-05, "epoch": 0.35513091351385956, "percentage": 27.74, "elapsed_time": "6:24:47", "remaining_time": "16:42:27", "throughput": 660.74, "total_tokens": 15254640} {"current_steps": 11100, "total_steps": 40000, "loss": 0.5798, "lr": 4.108789959150341e-05, "epoch": 0.355290954484348, "percentage": 27.75, "elapsed_time": "6:24:49", "remaining_time": "16:41:54", "throughput": 660.98, "total_tokens": 15261488} {"current_steps": 11105, "total_steps": 40000, "loss": 0.5373, "lr": 4.108038373351163e-05, "epoch": 0.35545099545483644, "percentage": 27.76, "elapsed_time": "6:24:50", "remaining_time": "16:41:21", "throughput": 661.23, "total_tokens": 15268240} {"current_steps": 11110, "total_steps": 40000, "loss": 0.813, "lr": 4.10728653957226e-05, "epoch": 0.3556110364253249, "percentage": 27.77, "elapsed_time": "6:24:52", "remaining_time": "16:40:48", "throughput": 661.48, "total_tokens": 15275120} {"current_steps": 11115, "total_steps": 40000, "loss": 0.7362, "lr": 4.106534457929575e-05, "epoch": 0.3557710773958133, "percentage": 27.79, "elapsed_time": "6:24:54", "remaining_time": "16:40:15", "throughput": 661.75, "total_tokens": 15282656} {"current_steps": 11120, "total_steps": 40000, "loss": 0.7186, "lr": 4.105782128539086e-05, "epoch": 0.35593111836630176, "percentage": 27.8, "elapsed_time": "6:24:55", "remaining_time": "16:39:43", "throughput": 662.01, "total_tokens": 15289856} {"current_steps": 11125, "total_steps": 40000, "loss": 0.7356, "lr": 4.1050295515168144e-05, "epoch": 0.3560911593367902, "percentage": 27.81, "elapsed_time": "6:24:57", "remaining_time": "16:39:10", "throughput": 662.25, "total_tokens": 15296400} {"current_steps": 11130, "total_steps": 40000, "loss": 0.7628, "lr": 4.1042767269788155e-05, "epoch": 0.35625120030727864, "percentage": 27.82, "elapsed_time": "6:24:59", "remaining_time": "16:38:37", "throughput": 662.49, "total_tokens": 15303152} {"current_steps": 11135, "total_steps": 40000, "loss": 0.7067, "lr": 4.103523655041185e-05, "epoch": 0.35641124127776713, "percentage": 27.84, "elapsed_time": "6:25:01", "remaining_time": "16:38:04", "throughput": 662.72, "total_tokens": 15309648} {"current_steps": 11140, "total_steps": 40000, "loss": 0.8985, "lr": 4.102770335820055e-05, "epoch": 0.35657128224825557, "percentage": 27.85, "elapsed_time": "6:25:02", "remaining_time": "16:37:31", "throughput": 662.98, "total_tokens": 15316768} {"current_steps": 11145, "total_steps": 40000, "loss": 0.7584, "lr": 4.1020167694315984e-05, "epoch": 0.356731323218744, "percentage": 27.86, "elapsed_time": "6:25:04", "remaining_time": "16:36:59", "throughput": 663.24, "total_tokens": 15323856} {"current_steps": 11150, "total_steps": 40000, "loss": 0.8116, "lr": 4.101262955992023e-05, "epoch": 0.35689136418923245, "percentage": 27.88, "elapsed_time": "6:25:06", "remaining_time": "16:36:26", "throughput": 663.49, "total_tokens": 15330752} {"current_steps": 11155, "total_steps": 40000, "loss": 0.6181, "lr": 4.100508895617578e-05, "epoch": 0.3570514051597209, "percentage": 27.89, "elapsed_time": "6:25:08", "remaining_time": "16:35:53", "throughput": 663.73, "total_tokens": 15337584} {"current_steps": 11160, "total_steps": 40000, "loss": 0.8406, "lr": 4.099754588424547e-05, "epoch": 0.35721144613020933, "percentage": 27.9, "elapsed_time": "6:25:09", "remaining_time": "16:35:21", "throughput": 663.97, "total_tokens": 15344288} {"current_steps": 11165, "total_steps": 40000, "loss": 0.8197, "lr": 4.0990000345292546e-05, "epoch": 0.35737148710069777, "percentage": 27.91, "elapsed_time": "6:25:11", "remaining_time": "16:34:48", "throughput": 664.22, "total_tokens": 15351280} {"current_steps": 11170, "total_steps": 40000, "loss": 0.7903, "lr": 4.098245234048064e-05, "epoch": 0.3575315280711862, "percentage": 27.93, "elapsed_time": "6:25:13", "remaining_time": "16:34:15", "throughput": 664.45, "total_tokens": 15357696} {"current_steps": 11175, "total_steps": 40000, "loss": 0.7726, "lr": 4.0974901870973726e-05, "epoch": 0.35769156904167465, "percentage": 27.94, "elapsed_time": "6:25:15", "remaining_time": "16:33:43", "throughput": 664.69, "total_tokens": 15364464} {"current_steps": 11180, "total_steps": 40000, "loss": 0.7114, "lr": 4.096734893793619e-05, "epoch": 0.3578516100121631, "percentage": 27.95, "elapsed_time": "6:25:16", "remaining_time": "16:33:10", "throughput": 664.94, "total_tokens": 15371408} {"current_steps": 11185, "total_steps": 40000, "loss": 0.7821, "lr": 4.095979354253279e-05, "epoch": 0.3580116509826516, "percentage": 27.96, "elapsed_time": "6:25:18", "remaining_time": "16:32:38", "throughput": 665.19, "total_tokens": 15378240} {"current_steps": 11190, "total_steps": 40000, "loss": 1.0472, "lr": 4.0952235685928656e-05, "epoch": 0.35817169195314, "percentage": 27.98, "elapsed_time": "6:25:20", "remaining_time": "16:32:05", "throughput": 665.44, "total_tokens": 15385056} {"current_steps": 11195, "total_steps": 40000, "loss": 0.663, "lr": 4.094467536928932e-05, "epoch": 0.35833173292362847, "percentage": 27.99, "elapsed_time": "6:25:22", "remaining_time": "16:31:33", "throughput": 665.69, "total_tokens": 15392048} {"current_steps": 11200, "total_steps": 40000, "loss": 0.7482, "lr": 4.093711259378067e-05, "epoch": 0.3584917738941169, "percentage": 28.0, "elapsed_time": "6:25:23", "remaining_time": "16:31:01", "throughput": 665.92, "total_tokens": 15398624} {"current_steps": 11200, "total_steps": 40000, "eval_loss": 0.7781204581260681, "epoch": 0.3584917738941169, "percentage": 28.0, "elapsed_time": "6:31:11", "remaining_time": "16:45:54", "throughput": 656.06, "total_tokens": 15398624} {"current_steps": 11205, "total_steps": 40000, "loss": 0.8605, "lr": 4.092954736056897e-05, "epoch": 0.35865181486460534, "percentage": 28.01, "elapsed_time": "6:31:15", "remaining_time": "16:45:27", "throughput": 656.25, "total_tokens": 15405712} {"current_steps": 11210, "total_steps": 40000, "loss": 0.5829, "lr": 4.09219796708209e-05, "epoch": 0.3588118558350938, "percentage": 28.02, "elapsed_time": "6:31:16", "remaining_time": "16:44:54", "throughput": 656.5, "total_tokens": 15412512} {"current_steps": 11215, "total_steps": 40000, "loss": 0.838, "lr": 4.0914409525703464e-05, "epoch": 0.3589718968055822, "percentage": 28.04, "elapsed_time": "6:31:18", "remaining_time": "16:44:21", "throughput": 656.75, "total_tokens": 15419520} {"current_steps": 11220, "total_steps": 40000, "loss": 0.8115, "lr": 4.090683692638408e-05, "epoch": 0.35913193777607066, "percentage": 28.05, "elapsed_time": "6:31:20", "remaining_time": "16:43:48", "throughput": 656.98, "total_tokens": 15426080} {"current_steps": 11225, "total_steps": 40000, "loss": 0.6021, "lr": 4.089926187403056e-05, "epoch": 0.3592919787465591, "percentage": 28.06, "elapsed_time": "6:31:22", "remaining_time": "16:43:15", "throughput": 657.22, "total_tokens": 15432928} {"current_steps": 11230, "total_steps": 40000, "loss": 0.6862, "lr": 4.0891684369811044e-05, "epoch": 0.35945201971704754, "percentage": 28.07, "elapsed_time": "6:31:23", "remaining_time": "16:42:43", "throughput": 657.44, "total_tokens": 15439296} {"current_steps": 11235, "total_steps": 40000, "loss": 0.8926, "lr": 4.0884104414894107e-05, "epoch": 0.359612060687536, "percentage": 28.09, "elapsed_time": "6:31:25", "remaining_time": "16:42:10", "throughput": 657.7, "total_tokens": 15446576} {"current_steps": 11240, "total_steps": 40000, "loss": 0.74, "lr": 4.087652201044864e-05, "epoch": 0.3597721016580245, "percentage": 28.1, "elapsed_time": "6:31:27", "remaining_time": "16:41:37", "throughput": 657.94, "total_tokens": 15453280} {"current_steps": 11245, "total_steps": 40000, "loss": 0.6711, "lr": 4.086893715764397e-05, "epoch": 0.3599321426285129, "percentage": 28.11, "elapsed_time": "6:31:29", "remaining_time": "16:41:04", "throughput": 658.2, "total_tokens": 15460416} {"current_steps": 11250, "total_steps": 40000, "loss": 0.8388, "lr": 4.086134985764977e-05, "epoch": 0.36009218359900136, "percentage": 28.12, "elapsed_time": "6:31:30", "remaining_time": "16:40:32", "throughput": 658.44, "total_tokens": 15467248} {"current_steps": 11255, "total_steps": 40000, "loss": 0.9025, "lr": 4.0853760111636085e-05, "epoch": 0.3602522245694898, "percentage": 28.14, "elapsed_time": "6:31:32", "remaining_time": "16:39:59", "throughput": 658.67, "total_tokens": 15473856} {"current_steps": 11260, "total_steps": 40000, "loss": 0.4795, "lr": 4.084616792077337e-05, "epoch": 0.36041226553997824, "percentage": 28.15, "elapsed_time": "6:31:34", "remaining_time": "16:39:26", "throughput": 658.91, "total_tokens": 15480608} {"current_steps": 11265, "total_steps": 40000, "loss": 0.8194, "lr": 4.083857328623243e-05, "epoch": 0.3605723065104667, "percentage": 28.16, "elapsed_time": "6:31:36", "remaining_time": "16:38:54", "throughput": 659.16, "total_tokens": 15487920} {"current_steps": 11270, "total_steps": 40000, "loss": 0.8379, "lr": 4.083097620918444e-05, "epoch": 0.3607323474809551, "percentage": 28.18, "elapsed_time": "6:31:38", "remaining_time": "16:38:22", "throughput": 659.41, "total_tokens": 15494864} {"current_steps": 11275, "total_steps": 40000, "loss": 0.8567, "lr": 4.082337669080097e-05, "epoch": 0.36089238845144356, "percentage": 28.19, "elapsed_time": "6:31:39", "remaining_time": "16:37:49", "throughput": 659.64, "total_tokens": 15501376} {"current_steps": 11280, "total_steps": 40000, "loss": 0.6844, "lr": 4.081577473225398e-05, "epoch": 0.361052429421932, "percentage": 28.2, "elapsed_time": "6:31:41", "remaining_time": "16:37:17", "throughput": 659.88, "total_tokens": 15508160} {"current_steps": 11285, "total_steps": 40000, "loss": 0.8561, "lr": 4.080817033471577e-05, "epoch": 0.36121247039242044, "percentage": 28.21, "elapsed_time": "6:31:43", "remaining_time": "16:36:44", "throughput": 660.13, "total_tokens": 15515088} {"current_steps": 11290, "total_steps": 40000, "loss": 0.844, "lr": 4.080056349935903e-05, "epoch": 0.3613725113629089, "percentage": 28.23, "elapsed_time": "6:31:44", "remaining_time": "16:36:12", "throughput": 660.38, "total_tokens": 15522288} {"current_steps": 11295, "total_steps": 40000, "loss": 0.7649, "lr": 4.079295422735684e-05, "epoch": 0.3615325523333974, "percentage": 28.24, "elapsed_time": "6:31:46", "remaining_time": "16:35:39", "throughput": 660.62, "total_tokens": 15528976} {"current_steps": 11300, "total_steps": 40000, "loss": 1.0319, "lr": 4.078534251988264e-05, "epoch": 0.3616925933038858, "percentage": 28.25, "elapsed_time": "6:31:48", "remaining_time": "16:35:07", "throughput": 660.87, "total_tokens": 15536096} {"current_steps": 11305, "total_steps": 40000, "loss": 0.7124, "lr": 4.077772837811025e-05, "epoch": 0.36185263427437425, "percentage": 28.26, "elapsed_time": "6:31:50", "remaining_time": "16:34:34", "throughput": 661.11, "total_tokens": 15542896} {"current_steps": 11310, "total_steps": 40000, "loss": 0.6824, "lr": 4.0770111803213874e-05, "epoch": 0.3620126752448627, "percentage": 28.27, "elapsed_time": "6:31:51", "remaining_time": "16:34:02", "throughput": 661.36, "total_tokens": 15549808} {"current_steps": 11315, "total_steps": 40000, "loss": 0.8791, "lr": 4.076249279636807e-05, "epoch": 0.36217271621535113, "percentage": 28.29, "elapsed_time": "6:31:53", "remaining_time": "16:33:30", "throughput": 661.6, "total_tokens": 15556688} {"current_steps": 11320, "total_steps": 40000, "loss": 0.6668, "lr": 4.075487135874781e-05, "epoch": 0.36233275718583957, "percentage": 28.3, "elapsed_time": "6:31:55", "remaining_time": "16:32:57", "throughput": 661.82, "total_tokens": 15562992} {"current_steps": 11325, "total_steps": 40000, "loss": 0.601, "lr": 4.074724749152837e-05, "epoch": 0.362492798156328, "percentage": 28.31, "elapsed_time": "6:31:57", "remaining_time": "16:32:25", "throughput": 662.06, "total_tokens": 15569632} {"current_steps": 11330, "total_steps": 40000, "loss": 0.7926, "lr": 4.07396211958855e-05, "epoch": 0.36265283912681645, "percentage": 28.32, "elapsed_time": "6:31:58", "remaining_time": "16:31:53", "throughput": 662.29, "total_tokens": 15576368} {"current_steps": 11335, "total_steps": 40000, "loss": 0.9341, "lr": 4.073199247299523e-05, "epoch": 0.3628128800973049, "percentage": 28.34, "elapsed_time": "6:32:00", "remaining_time": "16:31:20", "throughput": 662.53, "total_tokens": 15583136} {"current_steps": 11340, "total_steps": 40000, "loss": 0.6649, "lr": 4.072436132403403e-05, "epoch": 0.36297292106779333, "percentage": 28.35, "elapsed_time": "6:32:02", "remaining_time": "16:30:48", "throughput": 662.78, "total_tokens": 15590112} {"current_steps": 11345, "total_steps": 40000, "loss": 0.9499, "lr": 4.0716727750178704e-05, "epoch": 0.3631329620382818, "percentage": 28.36, "elapsed_time": "6:32:04", "remaining_time": "16:30:16", "throughput": 663.03, "total_tokens": 15597216} {"current_steps": 11350, "total_steps": 40000, "loss": 0.7113, "lr": 4.0709091752606455e-05, "epoch": 0.36329300300877027, "percentage": 28.38, "elapsed_time": "6:32:05", "remaining_time": "16:29:44", "throughput": 663.29, "total_tokens": 15604512} {"current_steps": 11355, "total_steps": 40000, "loss": 0.6445, "lr": 4.070145333249484e-05, "epoch": 0.3634530439792587, "percentage": 28.39, "elapsed_time": "6:32:07", "remaining_time": "16:29:12", "throughput": 663.53, "total_tokens": 15611120} {"current_steps": 11360, "total_steps": 40000, "loss": 0.7173, "lr": 4.069381249102181e-05, "epoch": 0.36361308494974715, "percentage": 28.4, "elapsed_time": "6:32:09", "remaining_time": "16:28:40", "throughput": 663.78, "total_tokens": 15618208} {"current_steps": 11365, "total_steps": 40000, "loss": 0.7971, "lr": 4.0686169229365665e-05, "epoch": 0.3637731259202356, "percentage": 28.41, "elapsed_time": "6:32:10", "remaining_time": "16:28:08", "throughput": 664.01, "total_tokens": 15624736} {"current_steps": 11370, "total_steps": 40000, "loss": 0.9747, "lr": 4.067852354870511e-05, "epoch": 0.363933166890724, "percentage": 28.43, "elapsed_time": "6:32:12", "remaining_time": "16:27:35", "throughput": 664.25, "total_tokens": 15631664} {"current_steps": 11375, "total_steps": 40000, "loss": 0.8772, "lr": 4.067087545021919e-05, "epoch": 0.36409320786121246, "percentage": 28.44, "elapsed_time": "6:32:14", "remaining_time": "16:27:03", "throughput": 664.48, "total_tokens": 15638176} {"current_steps": 11380, "total_steps": 40000, "loss": 1.0111, "lr": 4.066322493508734e-05, "epoch": 0.3642532488317009, "percentage": 28.45, "elapsed_time": "6:32:16", "remaining_time": "16:26:31", "throughput": 664.71, "total_tokens": 15644816} {"current_steps": 11385, "total_steps": 40000, "loss": 0.8092, "lr": 4.065557200448937e-05, "epoch": 0.36441328980218934, "percentage": 28.46, "elapsed_time": "6:32:17", "remaining_time": "16:26:00", "throughput": 664.95, "total_tokens": 15651504} {"current_steps": 11390, "total_steps": 40000, "loss": 0.7034, "lr": 4.064791665960546e-05, "epoch": 0.3645733307726778, "percentage": 28.48, "elapsed_time": "6:32:19", "remaining_time": "16:25:28", "throughput": 665.23, "total_tokens": 15659168} {"current_steps": 11395, "total_steps": 40000, "loss": 0.7588, "lr": 4.064025890161615e-05, "epoch": 0.3647333717431662, "percentage": 28.49, "elapsed_time": "6:32:21", "remaining_time": "16:24:56", "throughput": 665.45, "total_tokens": 15665664} {"current_steps": 11400, "total_steps": 40000, "loss": 0.9051, "lr": 4.0632598731702373e-05, "epoch": 0.3648934127136547, "percentage": 28.5, "elapsed_time": "6:32:23", "remaining_time": "16:24:24", "throughput": 665.69, "total_tokens": 15672384} {"current_steps": 11400, "total_steps": 40000, "eval_loss": 0.7770912051200867, "epoch": 0.3648934127136547, "percentage": 28.5, "elapsed_time": "6:38:10", "remaining_time": "16:38:56", "throughput": 656.0, "total_tokens": 15672384} {"current_steps": 11405, "total_steps": 40000, "loss": 0.7676, "lr": 4.0624936151045426e-05, "epoch": 0.36505345368414316, "percentage": 28.51, "elapsed_time": "6:38:14", "remaining_time": "16:38:28", "throughput": 656.19, "total_tokens": 15679152} {"current_steps": 11410, "total_steps": 40000, "loss": 0.7651, "lr": 4.061727116082696e-05, "epoch": 0.3652134946546316, "percentage": 28.52, "elapsed_time": "6:38:15", "remaining_time": "16:37:56", "throughput": 656.43, "total_tokens": 15686032} {"current_steps": 11415, "total_steps": 40000, "loss": 0.8763, "lr": 4.060960376222903e-05, "epoch": 0.36537353562512004, "percentage": 28.54, "elapsed_time": "6:38:17", "remaining_time": "16:37:23", "throughput": 656.69, "total_tokens": 15693312} {"current_steps": 11420, "total_steps": 40000, "loss": 0.6972, "lr": 4.0601933956434034e-05, "epoch": 0.3655335765956085, "percentage": 28.55, "elapsed_time": "6:38:19", "remaining_time": "16:36:51", "throughput": 656.95, "total_tokens": 15700800} {"current_steps": 11425, "total_steps": 40000, "loss": 0.6852, "lr": 4.059426174462476e-05, "epoch": 0.3656936175660969, "percentage": 28.56, "elapsed_time": "6:38:21", "remaining_time": "16:36:19", "throughput": 657.18, "total_tokens": 15707328} {"current_steps": 11430, "total_steps": 40000, "loss": 0.6497, "lr": 4.058658712798435e-05, "epoch": 0.36585365853658536, "percentage": 28.57, "elapsed_time": "6:38:22", "remaining_time": "16:35:46", "throughput": 657.41, "total_tokens": 15714016} {"current_steps": 11435, "total_steps": 40000, "loss": 0.6942, "lr": 4.0578910107696336e-05, "epoch": 0.3660136995070738, "percentage": 28.59, "elapsed_time": "6:38:24", "remaining_time": "16:35:14", "throughput": 657.66, "total_tokens": 15721088} {"current_steps": 11440, "total_steps": 40000, "loss": 0.6414, "lr": 4.05712306849446e-05, "epoch": 0.36617374047756224, "percentage": 28.6, "elapsed_time": "6:38:26", "remaining_time": "16:34:42", "throughput": 657.88, "total_tokens": 15727552} {"current_steps": 11445, "total_steps": 40000, "loss": 0.7176, "lr": 4.0563548860913415e-05, "epoch": 0.3663337814480507, "percentage": 28.61, "elapsed_time": "6:38:28", "remaining_time": "16:34:10", "throughput": 658.11, "total_tokens": 15734288} {"current_steps": 11450, "total_steps": 40000, "loss": 0.6227, "lr": 4.0555864636787414e-05, "epoch": 0.3664938224185392, "percentage": 28.62, "elapsed_time": "6:38:29", "remaining_time": "16:33:38", "throughput": 658.35, "total_tokens": 15741136} {"current_steps": 11455, "total_steps": 40000, "loss": 0.8782, "lr": 4.054817801375159e-05, "epoch": 0.3666538633890276, "percentage": 28.64, "elapsed_time": "6:38:31", "remaining_time": "16:33:05", "throughput": 658.6, "total_tokens": 15748288} {"current_steps": 11460, "total_steps": 40000, "loss": 0.757, "lr": 4.054048899299134e-05, "epoch": 0.36681390435951605, "percentage": 28.65, "elapsed_time": "6:38:33", "remaining_time": "16:32:33", "throughput": 658.84, "total_tokens": 15755120} {"current_steps": 11465, "total_steps": 40000, "loss": 0.852, "lr": 4.0532797575692385e-05, "epoch": 0.3669739453300045, "percentage": 28.66, "elapsed_time": "6:38:35", "remaining_time": "16:32:01", "throughput": 659.08, "total_tokens": 15762032} {"current_steps": 11470, "total_steps": 40000, "loss": 0.607, "lr": 4.052510376304085e-05, "epoch": 0.36713398630049293, "percentage": 28.68, "elapsed_time": "6:38:36", "remaining_time": "16:31:29", "throughput": 659.34, "total_tokens": 15769296} {"current_steps": 11475, "total_steps": 40000, "loss": 0.7025, "lr": 4.051740755622321e-05, "epoch": 0.36729402727098137, "percentage": 28.69, "elapsed_time": "6:38:38", "remaining_time": "16:30:57", "throughput": 659.57, "total_tokens": 15775872} {"current_steps": 11480, "total_steps": 40000, "loss": 0.9281, "lr": 4.050970895642632e-05, "epoch": 0.3674540682414698, "percentage": 28.7, "elapsed_time": "6:38:40", "remaining_time": "16:30:25", "throughput": 659.81, "total_tokens": 15782720} {"current_steps": 11485, "total_steps": 40000, "loss": 0.8365, "lr": 4.050200796483741e-05, "epoch": 0.36761410921195825, "percentage": 28.71, "elapsed_time": "6:38:42", "remaining_time": "16:29:53", "throughput": 660.06, "total_tokens": 15790080} {"current_steps": 11490, "total_steps": 40000, "loss": 0.9, "lr": 4.049430458264405e-05, "epoch": 0.3677741501824467, "percentage": 28.73, "elapsed_time": "6:38:43", "remaining_time": "16:29:21", "throughput": 660.31, "total_tokens": 15796992} {"current_steps": 11495, "total_steps": 40000, "loss": 0.7148, "lr": 4.048659881103422e-05, "epoch": 0.36793419115293513, "percentage": 28.74, "elapsed_time": "6:38:45", "remaining_time": "16:28:49", "throughput": 660.54, "total_tokens": 15803728} {"current_steps": 11500, "total_steps": 40000, "loss": 0.7989, "lr": 4.0478890651196235e-05, "epoch": 0.36809423212342357, "percentage": 28.75, "elapsed_time": "6:38:47", "remaining_time": "16:28:17", "throughput": 660.77, "total_tokens": 15810480} {"current_steps": 11505, "total_steps": 40000, "loss": 0.675, "lr": 4.047118010431879e-05, "epoch": 0.36825427309391207, "percentage": 28.76, "elapsed_time": "6:38:48", "remaining_time": "16:27:46", "throughput": 661.0, "total_tokens": 15816960} {"current_steps": 11510, "total_steps": 40000, "loss": 0.6193, "lr": 4.046346717159094e-05, "epoch": 0.3684143140644005, "percentage": 28.78, "elapsed_time": "6:38:50", "remaining_time": "16:27:14", "throughput": 661.24, "total_tokens": 15824032} {"current_steps": 11515, "total_steps": 40000, "loss": 0.8476, "lr": 4.045575185420214e-05, "epoch": 0.36857435503488895, "percentage": 28.79, "elapsed_time": "6:38:52", "remaining_time": "16:26:42", "throughput": 661.48, "total_tokens": 15830896} {"current_steps": 11520, "total_steps": 40000, "loss": 0.7801, "lr": 4.0448034153342165e-05, "epoch": 0.3687343960053774, "percentage": 28.8, "elapsed_time": "6:38:54", "remaining_time": "16:26:10", "throughput": 661.69, "total_tokens": 15837104} {"current_steps": 11525, "total_steps": 40000, "loss": 0.8732, "lr": 4.0440314070201194e-05, "epoch": 0.3688944369758658, "percentage": 28.81, "elapsed_time": "6:38:55", "remaining_time": "16:25:38", "throughput": 661.91, "total_tokens": 15843536} {"current_steps": 11530, "total_steps": 40000, "loss": 0.8417, "lr": 4.043259160596976e-05, "epoch": 0.36905447794635426, "percentage": 28.82, "elapsed_time": "6:38:57", "remaining_time": "16:25:07", "throughput": 662.13, "total_tokens": 15849840} {"current_steps": 11535, "total_steps": 40000, "loss": 0.7406, "lr": 4.0424866761838767e-05, "epoch": 0.3692145189168427, "percentage": 28.84, "elapsed_time": "6:38:59", "remaining_time": "16:24:35", "throughput": 662.36, "total_tokens": 15856384} {"current_steps": 11540, "total_steps": 40000, "loss": 0.8726, "lr": 4.041713953899948e-05, "epoch": 0.36937455988733114, "percentage": 28.85, "elapsed_time": "6:39:01", "remaining_time": "16:24:03", "throughput": 662.6, "total_tokens": 15863408} {"current_steps": 11545, "total_steps": 40000, "loss": 0.7794, "lr": 4.0409409938643515e-05, "epoch": 0.3695346008578196, "percentage": 28.86, "elapsed_time": "6:39:02", "remaining_time": "16:23:32", "throughput": 662.83, "total_tokens": 15870160} {"current_steps": 11550, "total_steps": 40000, "loss": 0.6968, "lr": 4.0401677961962904e-05, "epoch": 0.369694641828308, "percentage": 28.88, "elapsed_time": "6:39:04", "remaining_time": "16:23:00", "throughput": 663.07, "total_tokens": 15877008} {"current_steps": 11555, "total_steps": 40000, "loss": 0.5682, "lr": 4.039394361015001e-05, "epoch": 0.3698546827987965, "percentage": 28.89, "elapsed_time": "6:39:06", "remaining_time": "16:22:28", "throughput": 663.31, "total_tokens": 15883760} {"current_steps": 11560, "total_steps": 40000, "loss": 0.8261, "lr": 4.038620688439755e-05, "epoch": 0.37001472376928496, "percentage": 28.9, "elapsed_time": "6:39:08", "remaining_time": "16:21:57", "throughput": 663.54, "total_tokens": 15890592} {"current_steps": 11565, "total_steps": 40000, "loss": 1.005, "lr": 4.037846778589862e-05, "epoch": 0.3701747647397734, "percentage": 28.91, "elapsed_time": "6:39:09", "remaining_time": "16:21:25", "throughput": 663.79, "total_tokens": 15897568} {"current_steps": 11570, "total_steps": 40000, "loss": 0.6934, "lr": 4.0370726315846715e-05, "epoch": 0.37033480571026184, "percentage": 28.93, "elapsed_time": "6:39:11", "remaining_time": "16:20:54", "throughput": 664.02, "total_tokens": 15904384} {"current_steps": 11575, "total_steps": 40000, "loss": 0.6541, "lr": 4.036298247543565e-05, "epoch": 0.3704948466807503, "percentage": 28.94, "elapsed_time": "6:39:13", "remaining_time": "16:20:22", "throughput": 664.25, "total_tokens": 15910960} {"current_steps": 11580, "total_steps": 40000, "loss": 0.7719, "lr": 4.035523626585962e-05, "epoch": 0.3706548876512387, "percentage": 28.95, "elapsed_time": "6:39:15", "remaining_time": "16:19:51", "throughput": 664.51, "total_tokens": 15918256} {"current_steps": 11585, "total_steps": 40000, "loss": 0.625, "lr": 4.0347487688313194e-05, "epoch": 0.37081492862172716, "percentage": 28.96, "elapsed_time": "6:39:16", "remaining_time": "16:19:19", "throughput": 664.74, "total_tokens": 15925024} {"current_steps": 11590, "total_steps": 40000, "loss": 0.6659, "lr": 4.0339736743991296e-05, "epoch": 0.3709749695922156, "percentage": 28.98, "elapsed_time": "6:39:18", "remaining_time": "16:18:48", "throughput": 664.98, "total_tokens": 15931824} {"current_steps": 11595, "total_steps": 40000, "loss": 0.6418, "lr": 4.0331983434089227e-05, "epoch": 0.37113501056270404, "percentage": 28.99, "elapsed_time": "6:39:20", "remaining_time": "16:18:16", "throughput": 665.23, "total_tokens": 15939104} {"current_steps": 11600, "total_steps": 40000, "loss": 0.8379, "lr": 4.032422775980264e-05, "epoch": 0.3712950515331925, "percentage": 29.0, "elapsed_time": "6:39:21", "remaining_time": "16:17:45", "throughput": 665.49, "total_tokens": 15946384} {"current_steps": 11600, "total_steps": 40000, "eval_loss": 0.7754366993904114, "epoch": 0.3712950515331925, "percentage": 29.0, "elapsed_time": "6:45:09", "remaining_time": "16:31:57", "throughput": 655.96, "total_tokens": 15946384} {"current_steps": 11605, "total_steps": 40000, "loss": 0.5616, "lr": 4.031646972232754e-05, "epoch": 0.3714550925036809, "percentage": 29.01, "elapsed_time": "6:45:13", "remaining_time": "16:31:30", "throughput": 656.14, "total_tokens": 15953024} {"current_steps": 11610, "total_steps": 40000, "loss": 0.8078, "lr": 4.0308709322860344e-05, "epoch": 0.3716151334741694, "percentage": 29.03, "elapsed_time": "6:45:15", "remaining_time": "16:30:58", "throughput": 656.37, "total_tokens": 15959904} {"current_steps": 11615, "total_steps": 40000, "loss": 0.7619, "lr": 4.0300946562597784e-05, "epoch": 0.37177517444465785, "percentage": 29.04, "elapsed_time": "6:45:17", "remaining_time": "16:30:26", "throughput": 656.62, "total_tokens": 15967008} {"current_steps": 11620, "total_steps": 40000, "loss": 0.4816, "lr": 4.029318144273698e-05, "epoch": 0.3719352154151463, "percentage": 29.05, "elapsed_time": "6:45:18", "remaining_time": "16:29:54", "throughput": 656.84, "total_tokens": 15973584} {"current_steps": 11625, "total_steps": 40000, "loss": 0.6797, "lr": 4.0285413964475415e-05, "epoch": 0.37209525638563473, "percentage": 29.06, "elapsed_time": "6:45:20", "remaining_time": "16:29:23", "throughput": 657.07, "total_tokens": 15980400} {"current_steps": 11630, "total_steps": 40000, "loss": 0.9049, "lr": 4.0277644129010927e-05, "epoch": 0.37225529735612317, "percentage": 29.07, "elapsed_time": "6:45:22", "remaining_time": "16:28:51", "throughput": 657.3, "total_tokens": 15987136} {"current_steps": 11635, "total_steps": 40000, "loss": 0.786, "lr": 4.0269871937541724e-05, "epoch": 0.3724153383266116, "percentage": 29.09, "elapsed_time": "6:45:24", "remaining_time": "16:28:19", "throughput": 657.54, "total_tokens": 15994064} {"current_steps": 11640, "total_steps": 40000, "loss": 0.6799, "lr": 4.026209739126637e-05, "epoch": 0.37257537929710005, "percentage": 29.1, "elapsed_time": "6:45:25", "remaining_time": "16:27:47", "throughput": 657.77, "total_tokens": 16000752} {"current_steps": 11645, "total_steps": 40000, "loss": 0.6207, "lr": 4.025432049138381e-05, "epoch": 0.3727354202675885, "percentage": 29.11, "elapsed_time": "6:45:27", "remaining_time": "16:27:16", "throughput": 658.01, "total_tokens": 16007664} {"current_steps": 11650, "total_steps": 40000, "loss": 0.8932, "lr": 4.0246541239093325e-05, "epoch": 0.37289546123807693, "percentage": 29.12, "elapsed_time": "6:45:29", "remaining_time": "16:26:44", "throughput": 658.24, "total_tokens": 16014576} {"current_steps": 11655, "total_steps": 40000, "loss": 0.8041, "lr": 4.023875963559459e-05, "epoch": 0.37305550220856537, "percentage": 29.14, "elapsed_time": "6:45:30", "remaining_time": "16:26:12", "throughput": 658.48, "total_tokens": 16021424} {"current_steps": 11660, "total_steps": 40000, "loss": 1.0115, "lr": 4.023097568208761e-05, "epoch": 0.3732155431790538, "percentage": 29.15, "elapsed_time": "6:45:32", "remaining_time": "16:25:41", "throughput": 658.71, "total_tokens": 16028304} {"current_steps": 11665, "total_steps": 40000, "loss": 0.8091, "lr": 4.022318937977277e-05, "epoch": 0.3733755841495423, "percentage": 29.16, "elapsed_time": "6:45:34", "remaining_time": "16:25:09", "throughput": 658.96, "total_tokens": 16035360} {"current_steps": 11670, "total_steps": 40000, "loss": 0.7093, "lr": 4.021540072985084e-05, "epoch": 0.37353562512003075, "percentage": 29.18, "elapsed_time": "6:45:36", "remaining_time": "16:24:38", "throughput": 659.18, "total_tokens": 16041920} {"current_steps": 11675, "total_steps": 40000, "loss": 0.824, "lr": 4.020760973352289e-05, "epoch": 0.3736956660905192, "percentage": 29.19, "elapsed_time": "6:45:37", "remaining_time": "16:24:06", "throughput": 659.43, "total_tokens": 16049088} {"current_steps": 11680, "total_steps": 40000, "loss": 0.7625, "lr": 4.019981639199042e-05, "epoch": 0.3738557070610076, "percentage": 29.2, "elapsed_time": "6:45:39", "remaining_time": "16:23:35", "throughput": 659.64, "total_tokens": 16055440} {"current_steps": 11685, "total_steps": 40000, "loss": 0.9211, "lr": 4.0192020706455245e-05, "epoch": 0.37401574803149606, "percentage": 29.21, "elapsed_time": "6:45:41", "remaining_time": "16:23:03", "throughput": 659.87, "total_tokens": 16062256} {"current_steps": 11690, "total_steps": 40000, "loss": 0.8321, "lr": 4.018422267811956e-05, "epoch": 0.3741757890019845, "percentage": 29.23, "elapsed_time": "6:45:43", "remaining_time": "16:22:32", "throughput": 660.1, "total_tokens": 16068832} {"current_steps": 11695, "total_steps": 40000, "loss": 0.814, "lr": 4.017642230818592e-05, "epoch": 0.37433582997247294, "percentage": 29.24, "elapsed_time": "6:45:44", "remaining_time": "16:22:00", "throughput": 660.34, "total_tokens": 16075968} {"current_steps": 11700, "total_steps": 40000, "loss": 0.6937, "lr": 4.0168619597857246e-05, "epoch": 0.3744958709429614, "percentage": 29.25, "elapsed_time": "6:45:46", "remaining_time": "16:21:29", "throughput": 660.58, "total_tokens": 16082896} {"current_steps": 11705, "total_steps": 40000, "loss": 0.7933, "lr": 4.016081454833681e-05, "epoch": 0.3746559119134498, "percentage": 29.26, "elapsed_time": "6:45:48", "remaining_time": "16:20:58", "throughput": 660.81, "total_tokens": 16089584} {"current_steps": 11710, "total_steps": 40000, "loss": 0.8578, "lr": 4.0153007160828245e-05, "epoch": 0.37481595288393826, "percentage": 29.28, "elapsed_time": "6:45:50", "remaining_time": "16:20:26", "throughput": 661.05, "total_tokens": 16096608} {"current_steps": 11715, "total_steps": 40000, "loss": 0.79, "lr": 4.0145197436535555e-05, "epoch": 0.37497599385442676, "percentage": 29.29, "elapsed_time": "6:45:51", "remaining_time": "16:19:55", "throughput": 661.28, "total_tokens": 16103424} {"current_steps": 11720, "total_steps": 40000, "loss": 0.755, "lr": 4.0137385376663095e-05, "epoch": 0.3751360348249152, "percentage": 29.3, "elapsed_time": "6:45:53", "remaining_time": "16:19:24", "throughput": 661.52, "total_tokens": 16110240} {"current_steps": 11725, "total_steps": 40000, "loss": 0.8343, "lr": 4.012957098241558e-05, "epoch": 0.37529607579540364, "percentage": 29.31, "elapsed_time": "6:45:55", "remaining_time": "16:18:53", "throughput": 661.76, "total_tokens": 16117440} {"current_steps": 11730, "total_steps": 40000, "loss": 0.62, "lr": 4.0121754254998076e-05, "epoch": 0.3754561167658921, "percentage": 29.33, "elapsed_time": "6:45:57", "remaining_time": "16:18:21", "throughput": 661.99, "total_tokens": 16124176} {"current_steps": 11735, "total_steps": 40000, "loss": 0.8492, "lr": 4.011393519561606e-05, "epoch": 0.3756161577363805, "percentage": 29.34, "elapsed_time": "6:45:58", "remaining_time": "16:17:50", "throughput": 662.23, "total_tokens": 16131056} {"current_steps": 11740, "total_steps": 40000, "loss": 0.7354, "lr": 4.010611380547529e-05, "epoch": 0.37577619870686896, "percentage": 29.35, "elapsed_time": "6:46:00", "remaining_time": "16:17:19", "throughput": 662.46, "total_tokens": 16137904} {"current_steps": 11745, "total_steps": 40000, "loss": 0.6246, "lr": 4.009829008578192e-05, "epoch": 0.3759362396773574, "percentage": 29.36, "elapsed_time": "6:46:02", "remaining_time": "16:16:48", "throughput": 662.69, "total_tokens": 16144640} {"current_steps": 11750, "total_steps": 40000, "loss": 0.9995, "lr": 4.00904640377425e-05, "epoch": 0.37609628064784584, "percentage": 29.38, "elapsed_time": "6:46:03", "remaining_time": "16:16:17", "throughput": 662.92, "total_tokens": 16151408} {"current_steps": 11755, "total_steps": 40000, "loss": 0.8021, "lr": 4.0082635662563886e-05, "epoch": 0.3762563216183343, "percentage": 29.39, "elapsed_time": "6:46:05", "remaining_time": "16:15:46", "throughput": 663.17, "total_tokens": 16158640} {"current_steps": 11760, "total_steps": 40000, "loss": 0.8237, "lr": 4.007480496145331e-05, "epoch": 0.3764163625888227, "percentage": 29.4, "elapsed_time": "6:46:07", "remaining_time": "16:15:14", "throughput": 663.42, "total_tokens": 16165808} {"current_steps": 11765, "total_steps": 40000, "loss": 0.7802, "lr": 4.006697193561837e-05, "epoch": 0.37657640355931116, "percentage": 29.41, "elapsed_time": "6:46:09", "remaining_time": "16:14:43", "throughput": 663.65, "total_tokens": 16172480} {"current_steps": 11770, "total_steps": 40000, "loss": 0.6937, "lr": 4.005913658626701e-05, "epoch": 0.37673644452979965, "percentage": 29.43, "elapsed_time": "6:46:10", "remaining_time": "16:14:12", "throughput": 663.87, "total_tokens": 16179152} {"current_steps": 11775, "total_steps": 40000, "loss": 0.6527, "lr": 4.005129891460754e-05, "epoch": 0.3768964855002881, "percentage": 29.44, "elapsed_time": "6:46:12", "remaining_time": "16:13:41", "throughput": 664.09, "total_tokens": 16185696} {"current_steps": 11780, "total_steps": 40000, "loss": 0.6281, "lr": 4.004345892184864e-05, "epoch": 0.37705652647077653, "percentage": 29.45, "elapsed_time": "6:46:14", "remaining_time": "16:13:10", "throughput": 664.33, "total_tokens": 16192672} {"current_steps": 11785, "total_steps": 40000, "loss": 0.8719, "lr": 4.003561660919932e-05, "epoch": 0.37721656744126497, "percentage": 29.46, "elapsed_time": "6:46:16", "remaining_time": "16:12:39", "throughput": 664.57, "total_tokens": 16199712} {"current_steps": 11790, "total_steps": 40000, "loss": 0.8686, "lr": 4.002777197786897e-05, "epoch": 0.3773766084117534, "percentage": 29.48, "elapsed_time": "6:46:17", "remaining_time": "16:12:09", "throughput": 664.8, "total_tokens": 16206464} {"current_steps": 11795, "total_steps": 40000, "loss": 0.565, "lr": 4.0019925029067326e-05, "epoch": 0.37753664938224185, "percentage": 29.49, "elapsed_time": "6:46:19", "remaining_time": "16:11:38", "throughput": 665.04, "total_tokens": 16213376} {"current_steps": 11800, "total_steps": 40000, "loss": 0.6137, "lr": 4.0012075764004495e-05, "epoch": 0.3776966903527303, "percentage": 29.5, "elapsed_time": "6:46:21", "remaining_time": "16:11:07", "throughput": 665.27, "total_tokens": 16220112} {"current_steps": 11800, "total_steps": 40000, "eval_loss": 0.7736344337463379, "epoch": 0.3776966903527303, "percentage": 29.5, "elapsed_time": "6:52:09", "remaining_time": "16:24:59", "throughput": 655.89, "total_tokens": 16220112} {"current_steps": 11805, "total_steps": 40000, "loss": 0.7346, "lr": 4.000422418389094e-05, "epoch": 0.37785673132321873, "percentage": 29.51, "elapsed_time": "6:52:13", "remaining_time": "16:24:34", "throughput": 656.06, "total_tokens": 16226912} {"current_steps": 11810, "total_steps": 40000, "loss": 0.7369, "lr": 3.999637028993744e-05, "epoch": 0.37801677229370717, "percentage": 29.53, "elapsed_time": "6:52:15", "remaining_time": "16:24:03", "throughput": 656.3, "total_tokens": 16234048} {"current_steps": 11815, "total_steps": 40000, "loss": 0.7138, "lr": 3.99885140833552e-05, "epoch": 0.3781768132641956, "percentage": 29.54, "elapsed_time": "6:52:17", "remaining_time": "16:23:31", "throughput": 656.52, "total_tokens": 16240560} {"current_steps": 11820, "total_steps": 40000, "loss": 0.7861, "lr": 3.998065556535572e-05, "epoch": 0.3783368542346841, "percentage": 29.55, "elapsed_time": "6:52:19", "remaining_time": "16:23:00", "throughput": 656.74, "total_tokens": 16247200} {"current_steps": 11825, "total_steps": 40000, "loss": 0.6722, "lr": 3.9972794737150895e-05, "epoch": 0.37849689520517255, "percentage": 29.56, "elapsed_time": "6:52:20", "remaining_time": "16:22:29", "throughput": 656.97, "total_tokens": 16254080} {"current_steps": 11830, "total_steps": 40000, "loss": 0.7604, "lr": 3.996493159995297e-05, "epoch": 0.378656936175661, "percentage": 29.58, "elapsed_time": "6:52:22", "remaining_time": "16:21:57", "throughput": 657.2, "total_tokens": 16260896} {"current_steps": 11835, "total_steps": 40000, "loss": 0.7801, "lr": 3.995706615497453e-05, "epoch": 0.3788169771461494, "percentage": 29.59, "elapsed_time": "6:52:24", "remaining_time": "16:21:26", "throughput": 657.43, "total_tokens": 16267600} {"current_steps": 11840, "total_steps": 40000, "loss": 0.7328, "lr": 3.994919840342852e-05, "epoch": 0.37897701811663786, "percentage": 29.6, "elapsed_time": "6:52:26", "remaining_time": "16:20:55", "throughput": 657.67, "total_tokens": 16274672} {"current_steps": 11845, "total_steps": 40000, "loss": 0.7095, "lr": 3.994132834652825e-05, "epoch": 0.3791370590871263, "percentage": 29.61, "elapsed_time": "6:52:27", "remaining_time": "16:20:24", "throughput": 657.91, "total_tokens": 16281760} {"current_steps": 11850, "total_steps": 40000, "loss": 0.7676, "lr": 3.99334559854874e-05, "epoch": 0.37929710005761474, "percentage": 29.62, "elapsed_time": "6:52:29", "remaining_time": "16:19:53", "throughput": 658.14, "total_tokens": 16288656} {"current_steps": 11855, "total_steps": 40000, "loss": 0.7908, "lr": 3.9925581321519955e-05, "epoch": 0.3794571410281032, "percentage": 29.64, "elapsed_time": "6:52:31", "remaining_time": "16:19:22", "throughput": 658.37, "total_tokens": 16295472} {"current_steps": 11860, "total_steps": 40000, "loss": 0.8555, "lr": 3.991770435584031e-05, "epoch": 0.3796171819985916, "percentage": 29.65, "elapsed_time": "6:52:33", "remaining_time": "16:18:51", "throughput": 658.59, "total_tokens": 16302208} {"current_steps": 11865, "total_steps": 40000, "loss": 0.7752, "lr": 3.990982508966319e-05, "epoch": 0.37977722296908006, "percentage": 29.66, "elapsed_time": "6:52:34", "remaining_time": "16:18:20", "throughput": 658.82, "total_tokens": 16308992} {"current_steps": 11870, "total_steps": 40000, "loss": 0.6595, "lr": 3.990194352420367e-05, "epoch": 0.3799372639395685, "percentage": 29.68, "elapsed_time": "6:52:36", "remaining_time": "16:17:48", "throughput": 659.06, "total_tokens": 16315936} {"current_steps": 11875, "total_steps": 40000, "loss": 0.6504, "lr": 3.9894059660677184e-05, "epoch": 0.380097304910057, "percentage": 29.69, "elapsed_time": "6:52:38", "remaining_time": "16:17:17", "throughput": 659.27, "total_tokens": 16322352} {"current_steps": 11880, "total_steps": 40000, "loss": 1.0546, "lr": 3.9886173500299526e-05, "epoch": 0.38025734588054544, "percentage": 29.7, "elapsed_time": "6:52:39", "remaining_time": "16:16:46", "throughput": 659.5, "total_tokens": 16329248} {"current_steps": 11885, "total_steps": 40000, "loss": 0.68, "lr": 3.987828504428685e-05, "epoch": 0.3804173868510339, "percentage": 29.71, "elapsed_time": "6:52:41", "remaining_time": "16:16:16", "throughput": 659.73, "total_tokens": 16335984} {"current_steps": 11890, "total_steps": 40000, "loss": 0.8016, "lr": 3.987039429385565e-05, "epoch": 0.3805774278215223, "percentage": 29.73, "elapsed_time": "6:52:43", "remaining_time": "16:15:45", "throughput": 659.96, "total_tokens": 16342864} {"current_steps": 11895, "total_steps": 40000, "loss": 0.9169, "lr": 3.986250125022277e-05, "epoch": 0.38073746879201076, "percentage": 29.74, "elapsed_time": "6:52:45", "remaining_time": "16:15:14", "throughput": 660.2, "total_tokens": 16349904} {"current_steps": 11900, "total_steps": 40000, "loss": 0.7838, "lr": 3.985460591460544e-05, "epoch": 0.3808975097624992, "percentage": 29.75, "elapsed_time": "6:52:46", "remaining_time": "16:14:43", "throughput": 660.41, "total_tokens": 16356256} {"current_steps": 11905, "total_steps": 40000, "loss": 0.7765, "lr": 3.984670828822118e-05, "epoch": 0.38105755073298764, "percentage": 29.76, "elapsed_time": "6:52:48", "remaining_time": "16:14:12", "throughput": 660.65, "total_tokens": 16363424} {"current_steps": 11910, "total_steps": 40000, "loss": 0.7968, "lr": 3.983880837228794e-05, "epoch": 0.3812175917034761, "percentage": 29.78, "elapsed_time": "6:52:50", "remaining_time": "16:13:41", "throughput": 660.9, "total_tokens": 16370784} {"current_steps": 11915, "total_steps": 40000, "loss": 0.9363, "lr": 3.983090616802396e-05, "epoch": 0.3813776326739645, "percentage": 29.79, "elapsed_time": "6:52:52", "remaining_time": "16:13:10", "throughput": 661.14, "total_tokens": 16377952} {"current_steps": 11920, "total_steps": 40000, "loss": 0.6558, "lr": 3.982300167664788e-05, "epoch": 0.38153767364445296, "percentage": 29.8, "elapsed_time": "6:52:53", "remaining_time": "16:12:40", "throughput": 661.37, "total_tokens": 16384640} {"current_steps": 11925, "total_steps": 40000, "loss": 0.6472, "lr": 3.981509489937868e-05, "epoch": 0.38169771461494145, "percentage": 29.81, "elapsed_time": "6:52:55", "remaining_time": "16:12:09", "throughput": 661.59, "total_tokens": 16391312} {"current_steps": 11930, "total_steps": 40000, "loss": 0.8337, "lr": 3.9807185837435643e-05, "epoch": 0.3818577555854299, "percentage": 29.83, "elapsed_time": "6:52:57", "remaining_time": "16:11:38", "throughput": 661.82, "total_tokens": 16398176} {"current_steps": 11935, "total_steps": 40000, "loss": 0.7162, "lr": 3.9799274492038484e-05, "epoch": 0.38201779655591833, "percentage": 29.84, "elapsed_time": "6:52:59", "remaining_time": "16:11:07", "throughput": 662.03, "total_tokens": 16404608} {"current_steps": 11940, "total_steps": 40000, "loss": 0.8587, "lr": 3.979136086440722e-05, "epoch": 0.38217783752640677, "percentage": 29.85, "elapsed_time": "6:53:00", "remaining_time": "16:10:37", "throughput": 662.27, "total_tokens": 16411696} {"current_steps": 11945, "total_steps": 40000, "loss": 0.9106, "lr": 3.9783444955762226e-05, "epoch": 0.3823378784968952, "percentage": 29.86, "elapsed_time": "6:53:02", "remaining_time": "16:10:06", "throughput": 662.53, "total_tokens": 16419184} {"current_steps": 11950, "total_steps": 40000, "loss": 0.7115, "lr": 3.977552676732424e-05, "epoch": 0.38249791946738365, "percentage": 29.88, "elapsed_time": "6:53:04", "remaining_time": "16:09:35", "throughput": 662.77, "total_tokens": 16426208} {"current_steps": 11955, "total_steps": 40000, "loss": 0.6483, "lr": 3.976760630031435e-05, "epoch": 0.3826579604378721, "percentage": 29.89, "elapsed_time": "6:53:06", "remaining_time": "16:09:05", "throughput": 662.99, "total_tokens": 16432832} {"current_steps": 11960, "total_steps": 40000, "loss": 0.8642, "lr": 3.975968355595398e-05, "epoch": 0.38281800140836053, "percentage": 29.9, "elapsed_time": "6:53:07", "remaining_time": "16:08:34", "throughput": 663.21, "total_tokens": 16439504} {"current_steps": 11965, "total_steps": 40000, "loss": 0.7768, "lr": 3.9751758535464935e-05, "epoch": 0.38297804237884897, "percentage": 29.91, "elapsed_time": "6:53:09", "remaining_time": "16:08:04", "throughput": 663.43, "total_tokens": 16446160} {"current_steps": 11970, "total_steps": 40000, "loss": 0.6591, "lr": 3.9743831240069326e-05, "epoch": 0.3831380833493374, "percentage": 29.93, "elapsed_time": "6:53:11", "remaining_time": "16:07:33", "throughput": 663.67, "total_tokens": 16453184} {"current_steps": 11975, "total_steps": 40000, "loss": 0.558, "lr": 3.9735901670989675e-05, "epoch": 0.38329812431982585, "percentage": 29.94, "elapsed_time": "6:53:13", "remaining_time": "16:07:02", "throughput": 663.88, "total_tokens": 16459712} {"current_steps": 11980, "total_steps": 40000, "loss": 0.8392, "lr": 3.97279698294488e-05, "epoch": 0.38345816529031435, "percentage": 29.95, "elapsed_time": "6:53:14", "remaining_time": "16:06:32", "throughput": 664.11, "total_tokens": 16466528} {"current_steps": 11985, "total_steps": 40000, "loss": 0.9373, "lr": 3.9720035716669876e-05, "epoch": 0.3836182062608028, "percentage": 29.96, "elapsed_time": "6:53:16", "remaining_time": "16:06:01", "throughput": 664.34, "total_tokens": 16473408} {"current_steps": 11990, "total_steps": 40000, "loss": 0.7442, "lr": 3.9712099333876474e-05, "epoch": 0.3837782472312912, "percentage": 29.98, "elapsed_time": "6:53:18", "remaining_time": "16:05:31", "throughput": 664.57, "total_tokens": 16480240} {"current_steps": 11995, "total_steps": 40000, "loss": 0.7947, "lr": 3.9704160682292475e-05, "epoch": 0.38393828820177966, "percentage": 29.99, "elapsed_time": "6:53:19", "remaining_time": "16:05:01", "throughput": 664.79, "total_tokens": 16486880} {"current_steps": 12000, "total_steps": 40000, "loss": 0.7876, "lr": 3.9696219763142106e-05, "epoch": 0.3840983291722681, "percentage": 30.0, "elapsed_time": "6:53:21", "remaining_time": "16:04:30", "throughput": 665.03, "total_tokens": 16493920} {"current_steps": 12000, "total_steps": 40000, "eval_loss": 0.773281455039978, "epoch": 0.3840983291722681, "percentage": 30.0, "elapsed_time": "6:59:10", "remaining_time": "16:18:04", "throughput": 655.81, "total_tokens": 16493920} {"current_steps": 12005, "total_steps": 40000, "loss": 0.743, "lr": 3.968827657764997e-05, "epoch": 0.38425837014275654, "percentage": 30.01, "elapsed_time": "6:59:14", "remaining_time": "16:17:38", "throughput": 655.98, "total_tokens": 16500720} {"current_steps": 12010, "total_steps": 40000, "loss": 0.8315, "lr": 3.9680331127041e-05, "epoch": 0.384418411113245, "percentage": 30.03, "elapsed_time": "6:59:15", "remaining_time": "16:17:07", "throughput": 656.21, "total_tokens": 16507504} {"current_steps": 12015, "total_steps": 40000, "loss": 0.7965, "lr": 3.9672383412540495e-05, "epoch": 0.3845784520837334, "percentage": 30.04, "elapsed_time": "6:59:17", "remaining_time": "16:16:36", "throughput": 656.42, "total_tokens": 16513920} {"current_steps": 12020, "total_steps": 40000, "loss": 0.8216, "lr": 3.966443343537407e-05, "epoch": 0.38473849305422186, "percentage": 30.05, "elapsed_time": "6:59:19", "remaining_time": "16:16:05", "throughput": 656.65, "total_tokens": 16520912} {"current_steps": 12025, "total_steps": 40000, "loss": 0.6705, "lr": 3.965648119676772e-05, "epoch": 0.3848985340247103, "percentage": 30.06, "elapsed_time": "6:59:21", "remaining_time": "16:15:34", "throughput": 656.89, "total_tokens": 16528160} {"current_steps": 12030, "total_steps": 40000, "loss": 0.838, "lr": 3.96485266979478e-05, "epoch": 0.38505857499519874, "percentage": 30.08, "elapsed_time": "6:59:22", "remaining_time": "16:15:04", "throughput": 657.11, "total_tokens": 16534848} {"current_steps": 12035, "total_steps": 40000, "loss": 0.6423, "lr": 3.9640569940140974e-05, "epoch": 0.38521861596568724, "percentage": 30.09, "elapsed_time": "6:59:24", "remaining_time": "16:14:33", "throughput": 657.33, "total_tokens": 16541472} {"current_steps": 12040, "total_steps": 40000, "loss": 0.8042, "lr": 3.963261092457428e-05, "epoch": 0.3853786569361757, "percentage": 30.1, "elapsed_time": "6:59:26", "remaining_time": "16:14:02", "throughput": 657.57, "total_tokens": 16548640} {"current_steps": 12045, "total_steps": 40000, "loss": 0.9242, "lr": 3.962464965247509e-05, "epoch": 0.3855386979066641, "percentage": 30.11, "elapsed_time": "6:59:28", "remaining_time": "16:13:32", "throughput": 657.8, "total_tokens": 16555600} {"current_steps": 12050, "total_steps": 40000, "loss": 0.7792, "lr": 3.9616686125071135e-05, "epoch": 0.38569873887715256, "percentage": 30.12, "elapsed_time": "6:59:29", "remaining_time": "16:13:01", "throughput": 658.03, "total_tokens": 16562576} {"current_steps": 12055, "total_steps": 40000, "loss": 0.6912, "lr": 3.9608720343590506e-05, "epoch": 0.385858779847641, "percentage": 30.14, "elapsed_time": "6:59:31", "remaining_time": "16:12:30", "throughput": 658.27, "total_tokens": 16569552} {"current_steps": 12060, "total_steps": 40000, "loss": 0.805, "lr": 3.960075230926161e-05, "epoch": 0.38601882081812944, "percentage": 30.15, "elapsed_time": "6:59:33", "remaining_time": "16:12:00", "throughput": 658.48, "total_tokens": 16576096} {"current_steps": 12065, "total_steps": 40000, "loss": 0.6356, "lr": 3.959278202331322e-05, "epoch": 0.3861788617886179, "percentage": 30.16, "elapsed_time": "6:59:34", "remaining_time": "16:11:29", "throughput": 658.72, "total_tokens": 16583152} {"current_steps": 12070, "total_steps": 40000, "loss": 0.8839, "lr": 3.958480948697446e-05, "epoch": 0.3863389027591063, "percentage": 30.18, "elapsed_time": "6:59:36", "remaining_time": "16:10:58", "throughput": 658.95, "total_tokens": 16590272} {"current_steps": 12075, "total_steps": 40000, "loss": 0.8512, "lr": 3.95768347014748e-05, "epoch": 0.38649894372959476, "percentage": 30.19, "elapsed_time": "6:59:38", "remaining_time": "16:10:28", "throughput": 659.16, "total_tokens": 16596752} {"current_steps": 12080, "total_steps": 40000, "loss": 0.7023, "lr": 3.956885766804404e-05, "epoch": 0.3866589847000832, "percentage": 30.2, "elapsed_time": "6:59:40", "remaining_time": "16:09:57", "throughput": 659.39, "total_tokens": 16603616} {"current_steps": 12085, "total_steps": 40000, "loss": 0.6455, "lr": 3.956087838791235e-05, "epoch": 0.3868190256705717, "percentage": 30.21, "elapsed_time": "6:59:41", "remaining_time": "16:09:27", "throughput": 659.61, "total_tokens": 16610256} {"current_steps": 12090, "total_steps": 40000, "loss": 0.7459, "lr": 3.955289686231022e-05, "epoch": 0.38697906664106013, "percentage": 30.23, "elapsed_time": "6:59:43", "remaining_time": "16:08:57", "throughput": 659.84, "total_tokens": 16617120} {"current_steps": 12095, "total_steps": 40000, "loss": 0.9405, "lr": 3.9544913092468504e-05, "epoch": 0.38713910761154857, "percentage": 30.24, "elapsed_time": "6:59:45", "remaining_time": "16:08:26", "throughput": 660.05, "total_tokens": 16623536} {"current_steps": 12100, "total_steps": 40000, "loss": 0.6195, "lr": 3.9536927079618425e-05, "epoch": 0.387299148582037, "percentage": 30.25, "elapsed_time": "6:59:47", "remaining_time": "16:07:56", "throughput": 660.26, "total_tokens": 16630032} {"current_steps": 12105, "total_steps": 40000, "loss": 1.0328, "lr": 3.9528938824991494e-05, "epoch": 0.38745918955252545, "percentage": 30.26, "elapsed_time": "6:59:48", "remaining_time": "16:07:25", "throughput": 660.49, "total_tokens": 16636976} {"current_steps": 12110, "total_steps": 40000, "loss": 0.7353, "lr": 3.952094832981962e-05, "epoch": 0.3876192305230139, "percentage": 30.28, "elapsed_time": "6:59:50", "remaining_time": "16:06:55", "throughput": 660.71, "total_tokens": 16643824} {"current_steps": 12115, "total_steps": 40000, "loss": 0.6675, "lr": 3.951295559533503e-05, "epoch": 0.38777927149350233, "percentage": 30.29, "elapsed_time": "6:59:52", "remaining_time": "16:06:25", "throughput": 660.93, "total_tokens": 16650400} {"current_steps": 12120, "total_steps": 40000, "loss": 0.7724, "lr": 3.95049606227703e-05, "epoch": 0.38793931246399077, "percentage": 30.3, "elapsed_time": "6:59:54", "remaining_time": "16:05:54", "throughput": 661.15, "total_tokens": 16657056} {"current_steps": 12125, "total_steps": 40000, "loss": 0.7182, "lr": 3.949696341335838e-05, "epoch": 0.3880993534344792, "percentage": 30.31, "elapsed_time": "6:59:55", "remaining_time": "16:05:24", "throughput": 661.39, "total_tokens": 16664240} {"current_steps": 12130, "total_steps": 40000, "loss": 0.5878, "lr": 3.9488963968332503e-05, "epoch": 0.38825939440496765, "percentage": 30.33, "elapsed_time": "6:59:57", "remaining_time": "16:04:54", "throughput": 661.6, "total_tokens": 16670800} {"current_steps": 12135, "total_steps": 40000, "loss": 0.8711, "lr": 3.948096228892631e-05, "epoch": 0.3884194353754561, "percentage": 30.34, "elapsed_time": "6:59:59", "remaining_time": "16:04:23", "throughput": 661.83, "total_tokens": 16677792} {"current_steps": 12140, "total_steps": 40000, "loss": 0.6465, "lr": 3.947295837637375e-05, "epoch": 0.3885794763459446, "percentage": 30.35, "elapsed_time": "7:00:01", "remaining_time": "16:03:53", "throughput": 662.06, "total_tokens": 16684528} {"current_steps": 12145, "total_steps": 40000, "loss": 0.7855, "lr": 3.9464952231909135e-05, "epoch": 0.388739517316433, "percentage": 30.36, "elapsed_time": "7:00:02", "remaining_time": "16:03:23", "throughput": 662.28, "total_tokens": 16691376} {"current_steps": 12150, "total_steps": 40000, "loss": 0.674, "lr": 3.945694385676711e-05, "epoch": 0.38889955828692147, "percentage": 30.38, "elapsed_time": "7:00:04", "remaining_time": "16:02:53", "throughput": 662.52, "total_tokens": 16698400} {"current_steps": 12155, "total_steps": 40000, "loss": 0.6343, "lr": 3.944893325218265e-05, "epoch": 0.3890595992574099, "percentage": 30.39, "elapsed_time": "7:00:06", "remaining_time": "16:02:23", "throughput": 662.76, "total_tokens": 16705808} {"current_steps": 12160, "total_steps": 40000, "loss": 0.8584, "lr": 3.944092041939112e-05, "epoch": 0.38921964022789834, "percentage": 30.4, "elapsed_time": "7:00:08", "remaining_time": "16:01:53", "throughput": 663.01, "total_tokens": 16713120} {"current_steps": 12165, "total_steps": 40000, "loss": 1.0089, "lr": 3.943290535962818e-05, "epoch": 0.3893796811983868, "percentage": 30.41, "elapsed_time": "7:00:09", "remaining_time": "16:01:22", "throughput": 663.23, "total_tokens": 16719808} {"current_steps": 12170, "total_steps": 40000, "loss": 0.6456, "lr": 3.942488807412985e-05, "epoch": 0.3895397221688752, "percentage": 30.43, "elapsed_time": "7:00:11", "remaining_time": "16:00:52", "throughput": 663.45, "total_tokens": 16726512} {"current_steps": 12175, "total_steps": 40000, "loss": 0.8549, "lr": 3.941686856413251e-05, "epoch": 0.38969976313936366, "percentage": 30.44, "elapsed_time": "7:00:13", "remaining_time": "16:00:22", "throughput": 663.68, "total_tokens": 16733424} {"current_steps": 12180, "total_steps": 40000, "loss": 0.7814, "lr": 3.9408846830872874e-05, "epoch": 0.3898598041098521, "percentage": 30.45, "elapsed_time": "7:00:14", "remaining_time": "15:59:52", "throughput": 663.9, "total_tokens": 16740224} {"current_steps": 12185, "total_steps": 40000, "loss": 0.9112, "lr": 3.940082287558798e-05, "epoch": 0.39001984508034054, "percentage": 30.46, "elapsed_time": "7:00:16", "remaining_time": "15:59:22", "throughput": 664.13, "total_tokens": 16747152} {"current_steps": 12190, "total_steps": 40000, "loss": 1.0349, "lr": 3.939279669951522e-05, "epoch": 0.39017988605082904, "percentage": 30.48, "elapsed_time": "7:00:18", "remaining_time": "15:58:53", "throughput": 664.48, "total_tokens": 16757456} {"current_steps": 12195, "total_steps": 40000, "loss": 0.4994, "lr": 3.938476830389234e-05, "epoch": 0.3903399270213175, "percentage": 30.49, "elapsed_time": "7:00:20", "remaining_time": "15:58:23", "throughput": 664.72, "total_tokens": 16764496} {"current_steps": 12200, "total_steps": 40000, "loss": 0.7736, "lr": 3.937673768995742e-05, "epoch": 0.3904999679918059, "percentage": 30.5, "elapsed_time": "7:00:22", "remaining_time": "15:57:53", "throughput": 664.94, "total_tokens": 16771376} {"current_steps": 12200, "total_steps": 40000, "eval_loss": 0.7743721604347229, "epoch": 0.3904999679918059, "percentage": 30.5, "elapsed_time": "7:06:09", "remaining_time": "16:11:05", "throughput": 655.9, "total_tokens": 16771376} {"current_steps": 12205, "total_steps": 40000, "loss": 0.7363, "lr": 3.936870485894888e-05, "epoch": 0.39066000896229436, "percentage": 30.51, "elapsed_time": "7:06:13", "remaining_time": "16:10:39", "throughput": 656.07, "total_tokens": 16778048} {"current_steps": 12210, "total_steps": 40000, "loss": 0.7147, "lr": 3.9360669812105475e-05, "epoch": 0.3908200499327828, "percentage": 30.53, "elapsed_time": "7:06:15", "remaining_time": "16:10:09", "throughput": 656.3, "total_tokens": 16784864} {"current_steps": 12215, "total_steps": 40000, "loss": 1.042, "lr": 3.9352632550666325e-05, "epoch": 0.39098009090327124, "percentage": 30.54, "elapsed_time": "7:06:16", "remaining_time": "16:09:38", "throughput": 656.52, "total_tokens": 16791760} {"current_steps": 12220, "total_steps": 40000, "loss": 0.5716, "lr": 3.9344593075870866e-05, "epoch": 0.3911401318737597, "percentage": 30.55, "elapsed_time": "7:06:18", "remaining_time": "16:09:08", "throughput": 656.75, "total_tokens": 16798752} {"current_steps": 12225, "total_steps": 40000, "loss": 0.7739, "lr": 3.933655138895889e-05, "epoch": 0.3913001728442481, "percentage": 30.56, "elapsed_time": "7:06:20", "remaining_time": "16:08:38", "throughput": 656.97, "total_tokens": 16805648} {"current_steps": 12230, "total_steps": 40000, "loss": 0.8743, "lr": 3.932850749117053e-05, "epoch": 0.39146021381473656, "percentage": 30.58, "elapsed_time": "7:06:22", "remaining_time": "16:08:07", "throughput": 657.2, "total_tokens": 16812624} {"current_steps": 12235, "total_steps": 40000, "loss": 0.7355, "lr": 3.932046138374624e-05, "epoch": 0.391620254785225, "percentage": 30.59, "elapsed_time": "7:06:23", "remaining_time": "16:07:37", "throughput": 657.43, "total_tokens": 16819520} {"current_steps": 12240, "total_steps": 40000, "loss": 0.6823, "lr": 3.9312413067926854e-05, "epoch": 0.39178029575571344, "percentage": 30.6, "elapsed_time": "7:06:25", "remaining_time": "16:07:07", "throughput": 657.65, "total_tokens": 16826224} {"current_steps": 12245, "total_steps": 40000, "loss": 0.8457, "lr": 3.9304362544953506e-05, "epoch": 0.39194033672620193, "percentage": 30.61, "elapsed_time": "7:06:27", "remaining_time": "16:06:37", "throughput": 657.87, "total_tokens": 16833152} {"current_steps": 12250, "total_steps": 40000, "loss": 0.6375, "lr": 3.929630981606769e-05, "epoch": 0.39210037769669037, "percentage": 30.63, "elapsed_time": "7:06:29", "remaining_time": "16:06:07", "throughput": 658.09, "total_tokens": 16839904} {"current_steps": 12255, "total_steps": 40000, "loss": 0.6494, "lr": 3.928825488251124e-05, "epoch": 0.3922604186671788, "percentage": 30.64, "elapsed_time": "7:06:30", "remaining_time": "16:05:36", "throughput": 658.32, "total_tokens": 16847008} {"current_steps": 12260, "total_steps": 40000, "loss": 0.8002, "lr": 3.9280197745526344e-05, "epoch": 0.39242045963766725, "percentage": 30.65, "elapsed_time": "7:06:32", "remaining_time": "16:05:06", "throughput": 658.55, "total_tokens": 16853888} {"current_steps": 12265, "total_steps": 40000, "loss": 0.7165, "lr": 3.9272138406355495e-05, "epoch": 0.3925805006081557, "percentage": 30.66, "elapsed_time": "7:06:34", "remaining_time": "16:04:36", "throughput": 658.77, "total_tokens": 16860720} {"current_steps": 12270, "total_steps": 40000, "loss": 0.7561, "lr": 3.926407686624154e-05, "epoch": 0.39274054157864413, "percentage": 30.68, "elapsed_time": "7:06:35", "remaining_time": "16:04:06", "throughput": 658.99, "total_tokens": 16867520} {"current_steps": 12275, "total_steps": 40000, "loss": 0.8273, "lr": 3.9256013126427684e-05, "epoch": 0.39290058254913257, "percentage": 30.69, "elapsed_time": "7:06:37", "remaining_time": "16:03:36", "throughput": 659.2, "total_tokens": 16874032} {"current_steps": 12280, "total_steps": 40000, "loss": 0.6492, "lr": 3.9247947188157455e-05, "epoch": 0.393060623519621, "percentage": 30.7, "elapsed_time": "7:06:39", "remaining_time": "16:03:06", "throughput": 659.44, "total_tokens": 16881360} {"current_steps": 12285, "total_steps": 40000, "loss": 0.8159, "lr": 3.9239879052674715e-05, "epoch": 0.39322066449010945, "percentage": 30.71, "elapsed_time": "7:06:41", "remaining_time": "16:02:36", "throughput": 659.67, "total_tokens": 16888304} {"current_steps": 12290, "total_steps": 40000, "loss": 0.7295, "lr": 3.9231808721223673e-05, "epoch": 0.3933807054605979, "percentage": 30.73, "elapsed_time": "7:06:42", "remaining_time": "16:02:06", "throughput": 659.89, "total_tokens": 16895184} {"current_steps": 12295, "total_steps": 40000, "loss": 0.5673, "lr": 3.9223736195048886e-05, "epoch": 0.3935407464310864, "percentage": 30.74, "elapsed_time": "7:06:44", "remaining_time": "16:01:36", "throughput": 660.12, "total_tokens": 16902240} {"current_steps": 12300, "total_steps": 40000, "loss": 0.8745, "lr": 3.921566147539523e-05, "epoch": 0.3937007874015748, "percentage": 30.75, "elapsed_time": "7:06:46", "remaining_time": "16:01:06", "throughput": 660.34, "total_tokens": 16909040} {"current_steps": 12305, "total_steps": 40000, "loss": 0.6857, "lr": 3.920758456350792e-05, "epoch": 0.39386082837206327, "percentage": 30.76, "elapsed_time": "7:06:48", "remaining_time": "16:00:36", "throughput": 660.57, "total_tokens": 16915936} {"current_steps": 12310, "total_steps": 40000, "loss": 0.8168, "lr": 3.919950546063253e-05, "epoch": 0.3940208693425517, "percentage": 30.78, "elapsed_time": "7:06:49", "remaining_time": "16:00:06", "throughput": 660.8, "total_tokens": 16923072} {"current_steps": 12315, "total_steps": 40000, "loss": 0.6314, "lr": 3.919142416801496e-05, "epoch": 0.39418091031304014, "percentage": 30.79, "elapsed_time": "7:06:51", "remaining_time": "15:59:36", "throughput": 661.02, "total_tokens": 16929744} {"current_steps": 12320, "total_steps": 40000, "loss": 0.6812, "lr": 3.918334068690144e-05, "epoch": 0.3943409512835286, "percentage": 30.8, "elapsed_time": "7:06:53", "remaining_time": "15:59:06", "throughput": 661.25, "total_tokens": 16936864} {"current_steps": 12325, "total_steps": 40000, "loss": 0.7536, "lr": 3.917525501853855e-05, "epoch": 0.394500992254017, "percentage": 30.81, "elapsed_time": "7:06:55", "remaining_time": "15:58:37", "throughput": 661.47, "total_tokens": 16943680} {"current_steps": 12330, "total_steps": 40000, "loss": 0.9271, "lr": 3.916716716417319e-05, "epoch": 0.39466103322450546, "percentage": 30.83, "elapsed_time": "7:06:56", "remaining_time": "15:58:07", "throughput": 661.69, "total_tokens": 16950288} {"current_steps": 12335, "total_steps": 40000, "loss": 0.7435, "lr": 3.915907712505263e-05, "epoch": 0.3948210741949939, "percentage": 30.84, "elapsed_time": "7:06:58", "remaining_time": "15:57:37", "throughput": 661.9, "total_tokens": 16956880} {"current_steps": 12340, "total_steps": 40000, "loss": 0.9169, "lr": 3.915098490242444e-05, "epoch": 0.39498111516548234, "percentage": 30.85, "elapsed_time": "7:07:00", "remaining_time": "15:57:07", "throughput": 662.11, "total_tokens": 16963520} {"current_steps": 12345, "total_steps": 40000, "loss": 0.6054, "lr": 3.914289049753654e-05, "epoch": 0.3951411561359708, "percentage": 30.86, "elapsed_time": "7:07:02", "remaining_time": "15:56:37", "throughput": 662.33, "total_tokens": 16970336} {"current_steps": 12350, "total_steps": 40000, "loss": 0.7039, "lr": 3.913479391163719e-05, "epoch": 0.3953011971064593, "percentage": 30.88, "elapsed_time": "7:07:03", "remaining_time": "15:56:08", "throughput": 662.58, "total_tokens": 16977696} {"current_steps": 12355, "total_steps": 40000, "loss": 0.8068, "lr": 3.9126695145975e-05, "epoch": 0.3954612380769477, "percentage": 30.89, "elapsed_time": "7:07:05", "remaining_time": "15:55:38", "throughput": 662.81, "total_tokens": 16984784} {"current_steps": 12360, "total_steps": 40000, "loss": 0.887, "lr": 3.911859420179889e-05, "epoch": 0.39562127904743616, "percentage": 30.9, "elapsed_time": "7:07:07", "remaining_time": "15:55:08", "throughput": 663.02, "total_tokens": 16991488} {"current_steps": 12365, "total_steps": 40000, "loss": 0.6194, "lr": 3.911049108035813e-05, "epoch": 0.3957813200179246, "percentage": 30.91, "elapsed_time": "7:07:08", "remaining_time": "15:54:39", "throughput": 663.24, "total_tokens": 16998080} {"current_steps": 12370, "total_steps": 40000, "loss": 0.6838, "lr": 3.910238578290232e-05, "epoch": 0.39594136098841304, "percentage": 30.93, "elapsed_time": "7:07:10", "remaining_time": "15:54:09", "throughput": 663.45, "total_tokens": 17004608} {"current_steps": 12375, "total_steps": 40000, "loss": 0.6918, "lr": 3.90942783106814e-05, "epoch": 0.3961014019589015, "percentage": 30.94, "elapsed_time": "7:07:12", "remaining_time": "15:53:39", "throughput": 663.67, "total_tokens": 17011408} {"current_steps": 12380, "total_steps": 40000, "loss": 0.7938, "lr": 3.908616866494564e-05, "epoch": 0.3962614429293899, "percentage": 30.95, "elapsed_time": "7:07:14", "remaining_time": "15:53:10", "throughput": 663.89, "total_tokens": 17018352} {"current_steps": 12385, "total_steps": 40000, "loss": 0.9231, "lr": 3.907805684694566e-05, "epoch": 0.39642148389987836, "percentage": 30.96, "elapsed_time": "7:07:15", "remaining_time": "15:52:40", "throughput": 664.14, "total_tokens": 17025776} {"current_steps": 12390, "total_steps": 40000, "loss": 0.8372, "lr": 3.90699428579324e-05, "epoch": 0.3965815248703668, "percentage": 30.98, "elapsed_time": "7:07:17", "remaining_time": "15:52:11", "throughput": 664.37, "total_tokens": 17032880} {"current_steps": 12395, "total_steps": 40000, "loss": 0.7728, "lr": 3.906182669915713e-05, "epoch": 0.39674156584085524, "percentage": 30.99, "elapsed_time": "7:07:19", "remaining_time": "15:51:41", "throughput": 664.6, "total_tokens": 17040016} {"current_steps": 12400, "total_steps": 40000, "loss": 0.877, "lr": 3.9053708371871476e-05, "epoch": 0.3969016068113437, "percentage": 31.0, "elapsed_time": "7:07:21", "remaining_time": "15:51:12", "throughput": 664.82, "total_tokens": 17046656} {"current_steps": 12400, "total_steps": 40000, "eval_loss": 0.7717086672782898, "epoch": 0.3969016068113437, "percentage": 31.0, "elapsed_time": "7:13:08", "remaining_time": "16:04:05", "throughput": 655.93, "total_tokens": 17046656} {"current_steps": 12405, "total_steps": 40000, "loss": 0.7364, "lr": 3.904558787732738e-05, "epoch": 0.39706164778183217, "percentage": 31.01, "elapsed_time": "7:13:12", "remaining_time": "16:03:40", "throughput": 656.11, "total_tokens": 17053904} {"current_steps": 12410, "total_steps": 40000, "loss": 0.5809, "lr": 3.9037465216777135e-05, "epoch": 0.3972216887523206, "percentage": 31.03, "elapsed_time": "7:13:14", "remaining_time": "16:03:10", "throughput": 656.32, "total_tokens": 17060624} {"current_steps": 12415, "total_steps": 40000, "loss": 0.843, "lr": 3.902934039147334e-05, "epoch": 0.39738172972280905, "percentage": 31.04, "elapsed_time": "7:13:15", "remaining_time": "16:02:40", "throughput": 656.53, "total_tokens": 17067216} {"current_steps": 12420, "total_steps": 40000, "loss": 0.6862, "lr": 3.902121340266894e-05, "epoch": 0.3975417706932975, "percentage": 31.05, "elapsed_time": "7:13:17", "remaining_time": "16:02:10", "throughput": 656.75, "total_tokens": 17073984} {"current_steps": 12425, "total_steps": 40000, "loss": 0.529, "lr": 3.9013084251617246e-05, "epoch": 0.39770181166378593, "percentage": 31.06, "elapsed_time": "7:13:19", "remaining_time": "16:01:40", "throughput": 656.96, "total_tokens": 17080624} {"current_steps": 12430, "total_steps": 40000, "loss": 0.8354, "lr": 3.9004952939571865e-05, "epoch": 0.39786185263427437, "percentage": 31.08, "elapsed_time": "7:13:21", "remaining_time": "16:01:11", "throughput": 657.18, "total_tokens": 17087568} {"current_steps": 12435, "total_steps": 40000, "loss": 0.7839, "lr": 3.899681946778673e-05, "epoch": 0.3980218936047628, "percentage": 31.09, "elapsed_time": "7:13:22", "remaining_time": "16:00:41", "throughput": 657.4, "total_tokens": 17094352} {"current_steps": 12440, "total_steps": 40000, "loss": 0.6181, "lr": 3.898868383751615e-05, "epoch": 0.39818193457525125, "percentage": 31.1, "elapsed_time": "7:13:24", "remaining_time": "16:00:11", "throughput": 657.62, "total_tokens": 17101200} {"current_steps": 12445, "total_steps": 40000, "loss": 0.5265, "lr": 3.8980546050014724e-05, "epoch": 0.3983419755457397, "percentage": 31.11, "elapsed_time": "7:13:26", "remaining_time": "15:59:41", "throughput": 657.85, "total_tokens": 17108336} {"current_steps": 12450, "total_steps": 40000, "loss": 0.8629, "lr": 3.897240610653741e-05, "epoch": 0.39850201651622813, "percentage": 31.13, "elapsed_time": "7:13:28", "remaining_time": "15:59:12", "throughput": 658.05, "total_tokens": 17114624} {"current_steps": 12455, "total_steps": 40000, "loss": 0.4981, "lr": 3.896426400833948e-05, "epoch": 0.3986620574867166, "percentage": 31.14, "elapsed_time": "7:13:29", "remaining_time": "15:58:42", "throughput": 658.26, "total_tokens": 17121280} {"current_steps": 12460, "total_steps": 40000, "loss": 0.6233, "lr": 3.895611975667656e-05, "epoch": 0.39882209845720507, "percentage": 31.15, "elapsed_time": "7:13:31", "remaining_time": "15:58:12", "throughput": 658.49, "total_tokens": 17128272} {"current_steps": 12465, "total_steps": 40000, "loss": 0.8758, "lr": 3.8947973352804584e-05, "epoch": 0.3989821394276935, "percentage": 31.16, "elapsed_time": "7:13:33", "remaining_time": "15:57:43", "throughput": 658.72, "total_tokens": 17135472} {"current_steps": 12470, "total_steps": 40000, "loss": 0.6611, "lr": 3.893982479797984e-05, "epoch": 0.39914218039818194, "percentage": 31.18, "elapsed_time": "7:13:35", "remaining_time": "15:57:13", "throughput": 658.95, "total_tokens": 17142624} {"current_steps": 12475, "total_steps": 40000, "loss": 0.7452, "lr": 3.8931674093458926e-05, "epoch": 0.3993022213686704, "percentage": 31.19, "elapsed_time": "7:13:36", "remaining_time": "15:56:43", "throughput": 659.16, "total_tokens": 17149312} {"current_steps": 12480, "total_steps": 40000, "loss": 0.8514, "lr": 3.89235212404988e-05, "epoch": 0.3994622623391588, "percentage": 31.2, "elapsed_time": "7:13:38", "remaining_time": "15:56:14", "throughput": 659.37, "total_tokens": 17155952} {"current_steps": 12485, "total_steps": 40000, "loss": 0.7864, "lr": 3.891536624035672e-05, "epoch": 0.39962230330964726, "percentage": 31.21, "elapsed_time": "7:13:40", "remaining_time": "15:55:44", "throughput": 659.6, "total_tokens": 17162960} {"current_steps": 12490, "total_steps": 40000, "loss": 0.6975, "lr": 3.8907209094290295e-05, "epoch": 0.3997823442801357, "percentage": 31.23, "elapsed_time": "7:13:41", "remaining_time": "15:55:15", "throughput": 659.85, "total_tokens": 17170528} {"current_steps": 12495, "total_steps": 40000, "loss": 0.7492, "lr": 3.8899049803557466e-05, "epoch": 0.39994238525062414, "percentage": 31.24, "elapsed_time": "7:13:43", "remaining_time": "15:54:45", "throughput": 660.07, "total_tokens": 17177552} {"current_steps": 12500, "total_steps": 40000, "loss": 0.5519, "lr": 3.889088836941648e-05, "epoch": 0.4001024262211126, "percentage": 31.25, "elapsed_time": "7:13:45", "remaining_time": "15:54:16", "throughput": 660.28, "total_tokens": 17184016} {"current_steps": 12505, "total_steps": 40000, "loss": 0.6565, "lr": 3.8882724793125946e-05, "epoch": 0.400262467191601, "percentage": 31.26, "elapsed_time": "7:13:47", "remaining_time": "15:53:46", "throughput": 660.49, "total_tokens": 17190752} {"current_steps": 12510, "total_steps": 40000, "loss": 0.7906, "lr": 3.8874559075944794e-05, "epoch": 0.4004225081620895, "percentage": 31.27, "elapsed_time": "7:13:48", "remaining_time": "15:53:17", "throughput": 660.71, "total_tokens": 17197552} {"current_steps": 12515, "total_steps": 40000, "loss": 0.6807, "lr": 3.886639121913227e-05, "epoch": 0.40058254913257796, "percentage": 31.29, "elapsed_time": "7:13:50", "remaining_time": "15:52:47", "throughput": 660.91, "total_tokens": 17203840} {"current_steps": 12520, "total_steps": 40000, "loss": 0.6314, "lr": 3.885822122394797e-05, "epoch": 0.4007425901030664, "percentage": 31.3, "elapsed_time": "7:13:52", "remaining_time": "15:52:18", "throughput": 661.13, "total_tokens": 17210784} {"current_steps": 12525, "total_steps": 40000, "loss": 0.878, "lr": 3.8850049091651794e-05, "epoch": 0.40090263107355484, "percentage": 31.31, "elapsed_time": "7:13:54", "remaining_time": "15:51:48", "throughput": 661.35, "total_tokens": 17217680} {"current_steps": 12530, "total_steps": 40000, "loss": 0.7172, "lr": 3.8841874823504e-05, "epoch": 0.4010626720440433, "percentage": 31.32, "elapsed_time": "7:13:55", "remaining_time": "15:51:19", "throughput": 661.56, "total_tokens": 17224320} {"current_steps": 12535, "total_steps": 40000, "loss": 0.6602, "lr": 3.8833698420765157e-05, "epoch": 0.4012227130145317, "percentage": 31.34, "elapsed_time": "7:13:57", "remaining_time": "15:50:50", "throughput": 661.77, "total_tokens": 17230976} {"current_steps": 12540, "total_steps": 40000, "loss": 0.7999, "lr": 3.882551988469618e-05, "epoch": 0.40138275398502016, "percentage": 31.35, "elapsed_time": "7:13:59", "remaining_time": "15:50:20", "throughput": 661.98, "total_tokens": 17237552} {"current_steps": 12545, "total_steps": 40000, "loss": 0.8216, "lr": 3.881733921655829e-05, "epoch": 0.4015427949555086, "percentage": 31.36, "elapsed_time": "7:14:01", "remaining_time": "15:49:51", "throughput": 662.18, "total_tokens": 17243968} {"current_steps": 12550, "total_steps": 40000, "loss": 0.7861, "lr": 3.8809156417613054e-05, "epoch": 0.40170283592599704, "percentage": 31.37, "elapsed_time": "7:14:02", "remaining_time": "15:49:22", "throughput": 662.41, "total_tokens": 17251136} {"current_steps": 12555, "total_steps": 40000, "loss": 0.5566, "lr": 3.8800971489122364e-05, "epoch": 0.4018628768964855, "percentage": 31.39, "elapsed_time": "7:14:04", "remaining_time": "15:48:52", "throughput": 662.64, "total_tokens": 17258160} {"current_steps": 12560, "total_steps": 40000, "loss": 0.725, "lr": 3.8792784432348434e-05, "epoch": 0.402022917866974, "percentage": 31.4, "elapsed_time": "7:14:06", "remaining_time": "15:48:23", "throughput": 662.85, "total_tokens": 17264784} {"current_steps": 12565, "total_steps": 40000, "loss": 0.6339, "lr": 3.878459524855381e-05, "epoch": 0.4021829588374624, "percentage": 31.41, "elapsed_time": "7:14:08", "remaining_time": "15:47:54", "throughput": 663.07, "total_tokens": 17271584} {"current_steps": 12570, "total_steps": 40000, "loss": 0.7855, "lr": 3.8776403939001384e-05, "epoch": 0.40234299980795085, "percentage": 31.42, "elapsed_time": "7:14:09", "remaining_time": "15:47:25", "throughput": 663.28, "total_tokens": 17278368} {"current_steps": 12575, "total_steps": 40000, "loss": 0.6194, "lr": 3.876821050495433e-05, "epoch": 0.4025030407784393, "percentage": 31.44, "elapsed_time": "7:14:11", "remaining_time": "15:46:56", "throughput": 663.49, "total_tokens": 17284912} {"current_steps": 12580, "total_steps": 40000, "loss": 0.6899, "lr": 3.87600149476762e-05, "epoch": 0.40266308174892773, "percentage": 31.45, "elapsed_time": "7:14:13", "remaining_time": "15:46:26", "throughput": 663.7, "total_tokens": 17291536} {"current_steps": 12585, "total_steps": 40000, "loss": 0.6115, "lr": 3.8751817268430843e-05, "epoch": 0.40282312271941617, "percentage": 31.46, "elapsed_time": "7:14:14", "remaining_time": "15:45:57", "throughput": 663.91, "total_tokens": 17298080} {"current_steps": 12590, "total_steps": 40000, "loss": 0.7451, "lr": 3.8743617468482464e-05, "epoch": 0.4029831636899046, "percentage": 31.47, "elapsed_time": "7:14:16", "remaining_time": "15:45:28", "throughput": 664.11, "total_tokens": 17304624} {"current_steps": 12595, "total_steps": 40000, "loss": 0.7494, "lr": 3.8735415549095535e-05, "epoch": 0.40314320466039305, "percentage": 31.49, "elapsed_time": "7:14:18", "remaining_time": "15:44:59", "throughput": 664.34, "total_tokens": 17311664} {"current_steps": 12600, "total_steps": 40000, "loss": 0.6752, "lr": 3.8727211511534934e-05, "epoch": 0.4033032456308815, "percentage": 31.5, "elapsed_time": "7:14:20", "remaining_time": "15:44:30", "throughput": 664.55, "total_tokens": 17318272} {"current_steps": 12600, "total_steps": 40000, "eval_loss": 0.7705758810043335, "epoch": 0.4033032456308815, "percentage": 31.5, "elapsed_time": "7:20:08", "remaining_time": "15:57:07", "throughput": 655.79, "total_tokens": 17318272} {"current_steps": 12605, "total_steps": 40000, "loss": 0.7772, "lr": 3.8719005357065804e-05, "epoch": 0.40346328660136993, "percentage": 31.51, "elapsed_time": "7:20:11", "remaining_time": "15:56:41", "throughput": 655.96, "total_tokens": 17324960} {"current_steps": 12610, "total_steps": 40000, "loss": 0.8223, "lr": 3.8710797086953645e-05, "epoch": 0.40362332757185837, "percentage": 31.52, "elapsed_time": "7:20:13", "remaining_time": "15:56:12", "throughput": 656.17, "total_tokens": 17331728} {"current_steps": 12615, "total_steps": 40000, "loss": 0.8426, "lr": 3.870258670246427e-05, "epoch": 0.40378336854234687, "percentage": 31.54, "elapsed_time": "7:20:15", "remaining_time": "15:55:43", "throughput": 656.38, "total_tokens": 17338320} {"current_steps": 12620, "total_steps": 40000, "loss": 0.6845, "lr": 3.869437420486384e-05, "epoch": 0.4039434095128353, "percentage": 31.55, "elapsed_time": "7:20:17", "remaining_time": "15:55:13", "throughput": 656.58, "total_tokens": 17344896} {"current_steps": 12625, "total_steps": 40000, "loss": 0.7207, "lr": 3.8686159595418805e-05, "epoch": 0.40410345048332375, "percentage": 31.56, "elapsed_time": "7:20:18", "remaining_time": "15:54:44", "throughput": 656.81, "total_tokens": 17352080} {"current_steps": 12630, "total_steps": 40000, "loss": 0.8269, "lr": 3.867794287539597e-05, "epoch": 0.4042634914538122, "percentage": 31.57, "elapsed_time": "7:20:20", "remaining_time": "15:54:14", "throughput": 657.05, "total_tokens": 17359488} {"current_steps": 12635, "total_steps": 40000, "loss": 0.7038, "lr": 3.866972404606245e-05, "epoch": 0.4044235324243006, "percentage": 31.59, "elapsed_time": "7:20:22", "remaining_time": "15:53:45", "throughput": 657.26, "total_tokens": 17366336} {"current_steps": 12640, "total_steps": 40000, "loss": 0.6209, "lr": 3.866150310868571e-05, "epoch": 0.40458357339478906, "percentage": 31.6, "elapsed_time": "7:20:23", "remaining_time": "15:53:16", "throughput": 657.47, "total_tokens": 17372848} {"current_steps": 12645, "total_steps": 40000, "loss": 1.0016, "lr": 3.8653280064533506e-05, "epoch": 0.4047436143652775, "percentage": 31.61, "elapsed_time": "7:20:25", "remaining_time": "15:52:46", "throughput": 657.68, "total_tokens": 17379712} {"current_steps": 12650, "total_steps": 40000, "loss": 0.776, "lr": 3.864505491487394e-05, "epoch": 0.40490365533576594, "percentage": 31.62, "elapsed_time": "7:20:27", "remaining_time": "15:52:17", "throughput": 657.9, "total_tokens": 17386576} {"current_steps": 12655, "total_steps": 40000, "loss": 0.6467, "lr": 3.8636827660975414e-05, "epoch": 0.4050636963062544, "percentage": 31.64, "elapsed_time": "7:20:29", "remaining_time": "15:51:48", "throughput": 658.11, "total_tokens": 17393200} {"current_steps": 12660, "total_steps": 40000, "loss": 0.6338, "lr": 3.862859830410671e-05, "epoch": 0.4052237372767428, "percentage": 31.65, "elapsed_time": "7:20:30", "remaining_time": "15:51:19", "throughput": 658.31, "total_tokens": 17399824} {"current_steps": 12665, "total_steps": 40000, "loss": 0.6179, "lr": 3.862036684553688e-05, "epoch": 0.4053837782472313, "percentage": 31.66, "elapsed_time": "7:20:32", "remaining_time": "15:50:49", "throughput": 658.52, "total_tokens": 17406512} {"current_steps": 12670, "total_steps": 40000, "loss": 0.6609, "lr": 3.8612133286535314e-05, "epoch": 0.40554381921771976, "percentage": 31.67, "elapsed_time": "7:20:34", "remaining_time": "15:50:20", "throughput": 658.74, "total_tokens": 17413248} {"current_steps": 12675, "total_steps": 40000, "loss": 1.0622, "lr": 3.860389762837173e-05, "epoch": 0.4057038601882082, "percentage": 31.69, "elapsed_time": "7:20:36", "remaining_time": "15:49:51", "throughput": 658.95, "total_tokens": 17420112} {"current_steps": 12680, "total_steps": 40000, "loss": 0.6893, "lr": 3.859565987231618e-05, "epoch": 0.40586390115869664, "percentage": 31.7, "elapsed_time": "7:20:37", "remaining_time": "15:49:22", "throughput": 659.18, "total_tokens": 17427184} {"current_steps": 12685, "total_steps": 40000, "loss": 0.7556, "lr": 3.858742001963902e-05, "epoch": 0.4060239421291851, "percentage": 31.71, "elapsed_time": "7:20:39", "remaining_time": "15:48:53", "throughput": 659.39, "total_tokens": 17434032} {"current_steps": 12690, "total_steps": 40000, "loss": 0.6392, "lr": 3.857917807161094e-05, "epoch": 0.4061839830996735, "percentage": 31.72, "elapsed_time": "7:20:41", "remaining_time": "15:48:23", "throughput": 659.6, "total_tokens": 17440544} {"current_steps": 12695, "total_steps": 40000, "loss": 0.7787, "lr": 3.857093402950296e-05, "epoch": 0.40634402407016196, "percentage": 31.74, "elapsed_time": "7:20:43", "remaining_time": "15:47:54", "throughput": 659.82, "total_tokens": 17447616} {"current_steps": 12700, "total_steps": 40000, "loss": 0.6287, "lr": 3.8562687894586414e-05, "epoch": 0.4065040650406504, "percentage": 31.75, "elapsed_time": "7:20:44", "remaining_time": "15:47:25", "throughput": 660.06, "total_tokens": 17455008} {"current_steps": 12705, "total_steps": 40000, "loss": 0.7108, "lr": 3.8554439668132946e-05, "epoch": 0.40666410601113884, "percentage": 31.76, "elapsed_time": "7:20:46", "remaining_time": "15:46:56", "throughput": 660.27, "total_tokens": 17461872} {"current_steps": 12710, "total_steps": 40000, "loss": 0.8464, "lr": 3.854618935141455e-05, "epoch": 0.4068241469816273, "percentage": 31.77, "elapsed_time": "7:20:48", "remaining_time": "15:46:27", "throughput": 660.49, "total_tokens": 17468656} {"current_steps": 12715, "total_steps": 40000, "loss": 0.7775, "lr": 3.8537936945703525e-05, "epoch": 0.4069841879521157, "percentage": 31.79, "elapsed_time": "7:20:49", "remaining_time": "15:45:58", "throughput": 660.7, "total_tokens": 17475552} {"current_steps": 12720, "total_steps": 40000, "loss": 0.874, "lr": 3.852968245227249e-05, "epoch": 0.4071442289226042, "percentage": 31.8, "elapsed_time": "7:20:51", "remaining_time": "15:45:29", "throughput": 660.91, "total_tokens": 17482256} {"current_steps": 12725, "total_steps": 40000, "loss": 0.6431, "lr": 3.85214258723944e-05, "epoch": 0.40730426989309265, "percentage": 31.81, "elapsed_time": "7:20:53", "remaining_time": "15:45:00", "throughput": 661.13, "total_tokens": 17489232} {"current_steps": 12730, "total_steps": 40000, "loss": 0.7617, "lr": 3.8513167207342524e-05, "epoch": 0.4074643108635811, "percentage": 31.82, "elapsed_time": "7:20:55", "remaining_time": "15:44:31", "throughput": 661.34, "total_tokens": 17495728} {"current_steps": 12735, "total_steps": 40000, "loss": 0.6968, "lr": 3.850490645839044e-05, "epoch": 0.40762435183406953, "percentage": 31.84, "elapsed_time": "7:20:56", "remaining_time": "15:44:02", "throughput": 661.55, "total_tokens": 17502640} {"current_steps": 12740, "total_steps": 40000, "loss": 0.6097, "lr": 3.849664362681207e-05, "epoch": 0.40778439280455797, "percentage": 31.85, "elapsed_time": "7:20:58", "remaining_time": "15:43:33", "throughput": 661.77, "total_tokens": 17509536} {"current_steps": 12745, "total_steps": 40000, "loss": 0.6204, "lr": 3.848837871388165e-05, "epoch": 0.4079444337750464, "percentage": 31.86, "elapsed_time": "7:21:00", "remaining_time": "15:43:05", "throughput": 661.98, "total_tokens": 17516352} {"current_steps": 12750, "total_steps": 40000, "loss": 0.6918, "lr": 3.848011172087371e-05, "epoch": 0.40810447474553485, "percentage": 31.87, "elapsed_time": "7:21:02", "remaining_time": "15:42:36", "throughput": 662.21, "total_tokens": 17523344} {"current_steps": 12755, "total_steps": 40000, "loss": 0.788, "lr": 3.847184264906315e-05, "epoch": 0.4082645157160233, "percentage": 31.89, "elapsed_time": "7:21:03", "remaining_time": "15:42:07", "throughput": 662.43, "total_tokens": 17530512} {"current_steps": 12760, "total_steps": 40000, "loss": 0.6739, "lr": 3.846357149972516e-05, "epoch": 0.40842455668651173, "percentage": 31.9, "elapsed_time": "7:21:05", "remaining_time": "15:41:38", "throughput": 662.64, "total_tokens": 17537136} {"current_steps": 12765, "total_steps": 40000, "loss": 0.544, "lr": 3.8455298274135246e-05, "epoch": 0.40858459765700017, "percentage": 31.91, "elapsed_time": "7:21:07", "remaining_time": "15:41:09", "throughput": 662.85, "total_tokens": 17543888} {"current_steps": 12770, "total_steps": 40000, "loss": 0.6061, "lr": 3.8447022973569254e-05, "epoch": 0.4087446386274886, "percentage": 31.92, "elapsed_time": "7:21:09", "remaining_time": "15:40:41", "throughput": 663.07, "total_tokens": 17550896} {"current_steps": 12775, "total_steps": 40000, "loss": 0.6516, "lr": 3.843874559930332e-05, "epoch": 0.4089046795979771, "percentage": 31.94, "elapsed_time": "7:21:10", "remaining_time": "15:40:12", "throughput": 663.28, "total_tokens": 17557520} {"current_steps": 12780, "total_steps": 40000, "loss": 0.8575, "lr": 3.843046615261394e-05, "epoch": 0.40906472056846555, "percentage": 31.95, "elapsed_time": "7:21:12", "remaining_time": "15:39:43", "throughput": 663.49, "total_tokens": 17564352} {"current_steps": 12785, "total_steps": 40000, "loss": 0.5221, "lr": 3.842218463477791e-05, "epoch": 0.409224761538954, "percentage": 31.96, "elapsed_time": "7:21:14", "remaining_time": "15:39:14", "throughput": 663.72, "total_tokens": 17571472} {"current_steps": 12790, "total_steps": 40000, "loss": 0.6628, "lr": 3.841390104707233e-05, "epoch": 0.4093848025094424, "percentage": 31.97, "elapsed_time": "7:21:15", "remaining_time": "15:38:46", "throughput": 663.94, "total_tokens": 17578368} {"current_steps": 12795, "total_steps": 40000, "loss": 0.9586, "lr": 3.8405615390774643e-05, "epoch": 0.40954484347993086, "percentage": 31.99, "elapsed_time": "7:21:17", "remaining_time": "15:38:17", "throughput": 664.14, "total_tokens": 17585024} {"current_steps": 12800, "total_steps": 40000, "loss": 0.6949, "lr": 3.839732766716259e-05, "epoch": 0.4097048844504193, "percentage": 32.0, "elapsed_time": "7:21:19", "remaining_time": "15:37:48", "throughput": 664.35, "total_tokens": 17591696} {"current_steps": 12800, "total_steps": 40000, "eval_loss": 0.7698276042938232, "epoch": 0.4097048844504193, "percentage": 32.0, "elapsed_time": "7:27:07", "remaining_time": "15:50:08", "throughput": 655.74, "total_tokens": 17591696} {"current_steps": 12805, "total_steps": 40000, "loss": 0.8577, "lr": 3.838903787751425e-05, "epoch": 0.40986492542090774, "percentage": 32.01, "elapsed_time": "7:27:10", "remaining_time": "15:49:42", "throughput": 655.92, "total_tokens": 17598736} {"current_steps": 12810, "total_steps": 40000, "loss": 0.6957, "lr": 3.838074602310802e-05, "epoch": 0.4100249663913962, "percentage": 32.02, "elapsed_time": "7:27:12", "remaining_time": "15:49:13", "throughput": 656.11, "total_tokens": 17605088} {"current_steps": 12815, "total_steps": 40000, "loss": 0.9031, "lr": 3.837245210522258e-05, "epoch": 0.4101850073618846, "percentage": 32.04, "elapsed_time": "7:27:14", "remaining_time": "15:48:44", "throughput": 656.32, "total_tokens": 17611920} {"current_steps": 12820, "total_steps": 40000, "loss": 0.4897, "lr": 3.8364156125136996e-05, "epoch": 0.41034504833237306, "percentage": 32.05, "elapsed_time": "7:27:15", "remaining_time": "15:48:15", "throughput": 656.53, "total_tokens": 17618496} {"current_steps": 12825, "total_steps": 40000, "loss": 0.6107, "lr": 3.835585808413059e-05, "epoch": 0.41050508930286156, "percentage": 32.06, "elapsed_time": "7:27:17", "remaining_time": "15:47:46", "throughput": 656.74, "total_tokens": 17625472} {"current_steps": 12830, "total_steps": 40000, "loss": 0.716, "lr": 3.8347557983483024e-05, "epoch": 0.41066513027335, "percentage": 32.07, "elapsed_time": "7:27:19", "remaining_time": "15:47:17", "throughput": 656.96, "total_tokens": 17632320} {"current_steps": 12835, "total_steps": 40000, "loss": 0.7408, "lr": 3.833925582447428e-05, "epoch": 0.41082517124383844, "percentage": 32.09, "elapsed_time": "7:27:21", "remaining_time": "15:46:48", "throughput": 657.18, "total_tokens": 17639424} {"current_steps": 12840, "total_steps": 40000, "loss": 0.5488, "lr": 3.8330951608384656e-05, "epoch": 0.4109852122143269, "percentage": 32.1, "elapsed_time": "7:27:23", "remaining_time": "15:46:20", "throughput": 657.4, "total_tokens": 17646592} {"current_steps": 12845, "total_steps": 40000, "loss": 0.7453, "lr": 3.832264533649477e-05, "epoch": 0.4111452531848153, "percentage": 32.11, "elapsed_time": "7:27:24", "remaining_time": "15:45:51", "throughput": 657.6, "total_tokens": 17653232} {"current_steps": 12850, "total_steps": 40000, "loss": 0.7008, "lr": 3.8314337010085555e-05, "epoch": 0.41130529415530376, "percentage": 32.12, "elapsed_time": "7:27:26", "remaining_time": "15:45:22", "throughput": 657.82, "total_tokens": 17660144} {"current_steps": 12855, "total_steps": 40000, "loss": 0.6311, "lr": 3.830602663043824e-05, "epoch": 0.4114653351257922, "percentage": 32.14, "elapsed_time": "7:27:28", "remaining_time": "15:44:53", "throughput": 658.02, "total_tokens": 17666736} {"current_steps": 12860, "total_steps": 40000, "loss": 0.7443, "lr": 3.8297714198834414e-05, "epoch": 0.41162537609628064, "percentage": 32.15, "elapsed_time": "7:27:30", "remaining_time": "15:44:24", "throughput": 658.22, "total_tokens": 17673296} {"current_steps": 12865, "total_steps": 40000, "loss": 0.6803, "lr": 3.828939971655595e-05, "epoch": 0.4117854170667691, "percentage": 32.16, "elapsed_time": "7:27:31", "remaining_time": "15:43:56", "throughput": 658.44, "total_tokens": 17680304} {"current_steps": 12870, "total_steps": 40000, "loss": 0.8618, "lr": 3.828108318488505e-05, "epoch": 0.4119454580372575, "percentage": 32.17, "elapsed_time": "7:27:33", "remaining_time": "15:43:27", "throughput": 658.64, "total_tokens": 17686912} {"current_steps": 12875, "total_steps": 40000, "loss": 0.7984, "lr": 3.8272764605104216e-05, "epoch": 0.41210549900774596, "percentage": 32.19, "elapsed_time": "7:27:35", "remaining_time": "15:42:58", "throughput": 658.86, "total_tokens": 17693728} {"current_steps": 12880, "total_steps": 40000, "loss": 0.7171, "lr": 3.826444397849628e-05, "epoch": 0.41226553997823445, "percentage": 32.2, "elapsed_time": "7:27:36", "remaining_time": "15:42:29", "throughput": 659.08, "total_tokens": 17700752} {"current_steps": 12885, "total_steps": 40000, "loss": 0.6589, "lr": 3.825612130634439e-05, "epoch": 0.4124255809487229, "percentage": 32.21, "elapsed_time": "7:27:38", "remaining_time": "15:42:01", "throughput": 659.27, "total_tokens": 17707168} {"current_steps": 12890, "total_steps": 40000, "loss": 0.7773, "lr": 3.824779658993202e-05, "epoch": 0.41258562191921133, "percentage": 32.23, "elapsed_time": "7:27:40", "remaining_time": "15:41:32", "throughput": 659.49, "total_tokens": 17714080} {"current_steps": 12895, "total_steps": 40000, "loss": 0.6496, "lr": 3.823946983054292e-05, "epoch": 0.41274566288969977, "percentage": 32.24, "elapsed_time": "7:27:42", "remaining_time": "15:41:03", "throughput": 659.69, "total_tokens": 17720704} {"current_steps": 12900, "total_steps": 40000, "loss": 0.6565, "lr": 3.82311410294612e-05, "epoch": 0.4129057038601882, "percentage": 32.25, "elapsed_time": "7:27:43", "remaining_time": "15:40:34", "throughput": 659.9, "total_tokens": 17727392} {"current_steps": 12905, "total_steps": 40000, "loss": 0.7544, "lr": 3.822281018797127e-05, "epoch": 0.41306574483067665, "percentage": 32.26, "elapsed_time": "7:27:45", "remaining_time": "15:40:06", "throughput": 660.12, "total_tokens": 17734448} {"current_steps": 12910, "total_steps": 40000, "loss": 0.6594, "lr": 3.821447730735783e-05, "epoch": 0.4132257858011651, "percentage": 32.27, "elapsed_time": "7:27:47", "remaining_time": "15:39:37", "throughput": 660.32, "total_tokens": 17740944} {"current_steps": 12915, "total_steps": 40000, "loss": 0.739, "lr": 3.820614238890592e-05, "epoch": 0.41338582677165353, "percentage": 32.29, "elapsed_time": "7:27:49", "remaining_time": "15:39:09", "throughput": 660.51, "total_tokens": 17747296} {"current_steps": 12920, "total_steps": 40000, "loss": 0.5572, "lr": 3.819780543390091e-05, "epoch": 0.41354586774214197, "percentage": 32.3, "elapsed_time": "7:27:50", "remaining_time": "15:38:40", "throughput": 660.74, "total_tokens": 17754544} {"current_steps": 12925, "total_steps": 40000, "loss": 0.8319, "lr": 3.818946644362844e-05, "epoch": 0.4137059087126304, "percentage": 32.31, "elapsed_time": "7:27:52", "remaining_time": "15:38:12", "throughput": 660.93, "total_tokens": 17760864} {"current_steps": 12930, "total_steps": 40000, "loss": 0.737, "lr": 3.81811254193745e-05, "epoch": 0.4138659496831189, "percentage": 32.32, "elapsed_time": "7:27:54", "remaining_time": "15:37:43", "throughput": 661.16, "total_tokens": 17768112} {"current_steps": 12935, "total_steps": 40000, "loss": 0.6666, "lr": 3.8172782362425366e-05, "epoch": 0.41402599065360735, "percentage": 32.34, "elapsed_time": "7:27:56", "remaining_time": "15:37:15", "throughput": 661.37, "total_tokens": 17775120} {"current_steps": 12940, "total_steps": 40000, "loss": 0.6712, "lr": 3.816443727406765e-05, "epoch": 0.4141860316240958, "percentage": 32.35, "elapsed_time": "7:27:57", "remaining_time": "15:36:46", "throughput": 661.59, "total_tokens": 17782000} {"current_steps": 12945, "total_steps": 40000, "loss": 0.6412, "lr": 3.815609015558829e-05, "epoch": 0.4143460725945842, "percentage": 32.36, "elapsed_time": "7:27:59", "remaining_time": "15:36:18", "throughput": 661.81, "total_tokens": 17789008} {"current_steps": 12950, "total_steps": 40000, "loss": 0.6425, "lr": 3.814774100827448e-05, "epoch": 0.41450611356507266, "percentage": 32.38, "elapsed_time": "7:28:01", "remaining_time": "15:35:49", "throughput": 662.01, "total_tokens": 17795744} {"current_steps": 12955, "total_steps": 40000, "loss": 0.5887, "lr": 3.813938983341379e-05, "epoch": 0.4146661545355611, "percentage": 32.39, "elapsed_time": "7:28:02", "remaining_time": "15:35:21", "throughput": 662.23, "total_tokens": 17802672} {"current_steps": 12960, "total_steps": 40000, "loss": 0.8129, "lr": 3.813103663229407e-05, "epoch": 0.41482619550604954, "percentage": 32.4, "elapsed_time": "7:28:04", "remaining_time": "15:34:52", "throughput": 662.45, "total_tokens": 17809696} {"current_steps": 12965, "total_steps": 40000, "loss": 0.7815, "lr": 3.812268140620349e-05, "epoch": 0.414986236476538, "percentage": 32.41, "elapsed_time": "7:28:06", "remaining_time": "15:34:24", "throughput": 662.66, "total_tokens": 17816640} {"current_steps": 12970, "total_steps": 40000, "loss": 0.75, "lr": 3.811432415643051e-05, "epoch": 0.4151462774470264, "percentage": 32.42, "elapsed_time": "7:28:08", "remaining_time": "15:33:56", "throughput": 662.88, "total_tokens": 17823616} {"current_steps": 12975, "total_steps": 40000, "loss": 0.7554, "lr": 3.8105964884263954e-05, "epoch": 0.41530631841751486, "percentage": 32.44, "elapsed_time": "7:28:09", "remaining_time": "15:33:27", "throughput": 663.09, "total_tokens": 17830464} {"current_steps": 12980, "total_steps": 40000, "loss": 0.6776, "lr": 3.809760359099291e-05, "epoch": 0.4154663593880033, "percentage": 32.45, "elapsed_time": "7:28:11", "remaining_time": "15:32:59", "throughput": 663.3, "total_tokens": 17837184} {"current_steps": 12985, "total_steps": 40000, "loss": 0.9802, "lr": 3.8089240277906804e-05, "epoch": 0.4156264003584918, "percentage": 32.46, "elapsed_time": "7:28:13", "remaining_time": "15:32:31", "throughput": 663.51, "total_tokens": 17843904} {"current_steps": 12990, "total_steps": 40000, "loss": 0.8364, "lr": 3.808087494629535e-05, "epoch": 0.41578644132898024, "percentage": 32.48, "elapsed_time": "7:28:15", "remaining_time": "15:32:02", "throughput": 663.73, "total_tokens": 17850992} {"current_steps": 12995, "total_steps": 40000, "loss": 0.8168, "lr": 3.8072507597448595e-05, "epoch": 0.4159464822994687, "percentage": 32.49, "elapsed_time": "7:28:16", "remaining_time": "15:31:34", "throughput": 663.92, "total_tokens": 17857456} {"current_steps": 13000, "total_steps": 40000, "loss": 0.7197, "lr": 3.806413823265689e-05, "epoch": 0.4161065232699571, "percentage": 32.5, "elapsed_time": "7:28:18", "remaining_time": "15:31:06", "throughput": 664.13, "total_tokens": 17864256} {"current_steps": 13000, "total_steps": 40000, "eval_loss": 0.7688626646995544, "epoch": 0.4161065232699571, "percentage": 32.5, "elapsed_time": "7:34:06", "remaining_time": "15:43:08", "throughput": 655.66, "total_tokens": 17864256} {"current_steps": 13005, "total_steps": 40000, "loss": 0.8413, "lr": 3.805576685321089e-05, "epoch": 0.41626656424044556, "percentage": 32.51, "elapsed_time": "7:34:10", "remaining_time": "15:42:44", "throughput": 655.83, "total_tokens": 17871376} {"current_steps": 13010, "total_steps": 40000, "loss": 0.5358, "lr": 3.804739346040158e-05, "epoch": 0.416426605210934, "percentage": 32.52, "elapsed_time": "7:34:11", "remaining_time": "15:42:15", "throughput": 656.04, "total_tokens": 17878384} {"current_steps": 13015, "total_steps": 40000, "loss": 0.6942, "lr": 3.8039018055520234e-05, "epoch": 0.41658664618142244, "percentage": 32.54, "elapsed_time": "7:34:13", "remaining_time": "15:41:46", "throughput": 656.27, "total_tokens": 17885776} {"current_steps": 13020, "total_steps": 40000, "loss": 0.5211, "lr": 3.803064063985844e-05, "epoch": 0.4167466871519109, "percentage": 32.55, "elapsed_time": "7:34:15", "remaining_time": "15:41:18", "throughput": 656.48, "total_tokens": 17892560} {"current_steps": 13025, "total_steps": 40000, "loss": 0.9342, "lr": 3.802226121470811e-05, "epoch": 0.4169067281223993, "percentage": 32.56, "elapsed_time": "7:34:17", "remaining_time": "15:40:49", "throughput": 656.68, "total_tokens": 17899056} {"current_steps": 13030, "total_steps": 40000, "loss": 0.8063, "lr": 3.801387978136145e-05, "epoch": 0.41706676909288776, "percentage": 32.57, "elapsed_time": "7:34:18", "remaining_time": "15:40:21", "throughput": 656.89, "total_tokens": 17906016} {"current_steps": 13035, "total_steps": 40000, "loss": 0.653, "lr": 3.800549634111099e-05, "epoch": 0.4172268100633762, "percentage": 32.59, "elapsed_time": "7:34:20", "remaining_time": "15:39:52", "throughput": 657.11, "total_tokens": 17913104} {"current_steps": 13040, "total_steps": 40000, "loss": 0.8119, "lr": 3.799711089524955e-05, "epoch": 0.4173868510338647, "percentage": 32.6, "elapsed_time": "7:34:22", "remaining_time": "15:39:24", "throughput": 657.33, "total_tokens": 17920240} {"current_steps": 13045, "total_steps": 40000, "loss": 0.7269, "lr": 3.7988723445070285e-05, "epoch": 0.41754689200435313, "percentage": 32.61, "elapsed_time": "7:34:23", "remaining_time": "15:38:55", "throughput": 657.54, "total_tokens": 17927232} {"current_steps": 13050, "total_steps": 40000, "loss": 0.6832, "lr": 3.798033399186663e-05, "epoch": 0.41770693297484157, "percentage": 32.62, "elapsed_time": "7:34:25", "remaining_time": "15:38:27", "throughput": 657.75, "total_tokens": 17933936} {"current_steps": 13055, "total_steps": 40000, "loss": 0.7335, "lr": 3.797194253693237e-05, "epoch": 0.41786697394533, "percentage": 32.64, "elapsed_time": "7:34:27", "remaining_time": "15:37:58", "throughput": 657.97, "total_tokens": 17941232} {"current_steps": 13060, "total_steps": 40000, "loss": 1.0027, "lr": 3.796354908156153e-05, "epoch": 0.41802701491581845, "percentage": 32.65, "elapsed_time": "7:34:29", "remaining_time": "15:37:30", "throughput": 658.2, "total_tokens": 17948640} {"current_steps": 13065, "total_steps": 40000, "loss": 0.7288, "lr": 3.795515362704853e-05, "epoch": 0.4181870558863069, "percentage": 32.66, "elapsed_time": "7:34:30", "remaining_time": "15:37:02", "throughput": 658.42, "total_tokens": 17955680} {"current_steps": 13070, "total_steps": 40000, "loss": 0.6602, "lr": 3.794675617468803e-05, "epoch": 0.41834709685679533, "percentage": 32.67, "elapsed_time": "7:34:32", "remaining_time": "15:36:33", "throughput": 658.62, "total_tokens": 17962272} {"current_steps": 13075, "total_steps": 40000, "loss": 0.7938, "lr": 3.793835672577503e-05, "epoch": 0.41850713782728377, "percentage": 32.69, "elapsed_time": "7:34:34", "remaining_time": "15:36:05", "throughput": 658.82, "total_tokens": 17968832} {"current_steps": 13080, "total_steps": 40000, "loss": 0.8657, "lr": 3.7929955281604826e-05, "epoch": 0.4186671787977722, "percentage": 32.7, "elapsed_time": "7:34:36", "remaining_time": "15:35:37", "throughput": 659.02, "total_tokens": 17975616} {"current_steps": 13085, "total_steps": 40000, "loss": 0.8434, "lr": 3.7921551843473036e-05, "epoch": 0.41882721976826065, "percentage": 32.71, "elapsed_time": "7:34:37", "remaining_time": "15:35:08", "throughput": 659.23, "total_tokens": 17982272} {"current_steps": 13090, "total_steps": 40000, "loss": 0.7638, "lr": 3.791314641267557e-05, "epoch": 0.41898726073874915, "percentage": 32.73, "elapsed_time": "7:34:39", "remaining_time": "15:34:40", "throughput": 659.43, "total_tokens": 17988944} {"current_steps": 13095, "total_steps": 40000, "loss": 0.6981, "lr": 3.790473899050864e-05, "epoch": 0.4191473017092376, "percentage": 32.74, "elapsed_time": "7:34:41", "remaining_time": "15:34:12", "throughput": 659.62, "total_tokens": 17995408} {"current_steps": 13100, "total_steps": 40000, "loss": 0.7903, "lr": 3.7896329578268794e-05, "epoch": 0.419307342679726, "percentage": 32.75, "elapsed_time": "7:34:43", "remaining_time": "15:33:43", "throughput": 659.85, "total_tokens": 18002592} {"current_steps": 13105, "total_steps": 40000, "loss": 0.6682, "lr": 3.7887918177252855e-05, "epoch": 0.41946738365021446, "percentage": 32.76, "elapsed_time": "7:34:44", "remaining_time": "15:33:15", "throughput": 660.05, "total_tokens": 18009392} {"current_steps": 13110, "total_steps": 40000, "loss": 0.8852, "lr": 3.787950478875798e-05, "epoch": 0.4196274246207029, "percentage": 32.77, "elapsed_time": "7:34:46", "remaining_time": "15:32:47", "throughput": 660.26, "total_tokens": 18016160} {"current_steps": 13115, "total_steps": 40000, "loss": 0.7821, "lr": 3.787108941408162e-05, "epoch": 0.41978746559119134, "percentage": 32.79, "elapsed_time": "7:34:48", "remaining_time": "15:32:19", "throughput": 660.47, "total_tokens": 18023056} {"current_steps": 13120, "total_steps": 40000, "loss": 0.7553, "lr": 3.786267205452151e-05, "epoch": 0.4199475065616798, "percentage": 32.8, "elapsed_time": "7:34:49", "remaining_time": "15:31:51", "throughput": 660.68, "total_tokens": 18030048} {"current_steps": 13125, "total_steps": 40000, "loss": 0.6239, "lr": 3.785425271137573e-05, "epoch": 0.4201075475321682, "percentage": 32.81, "elapsed_time": "7:34:51", "remaining_time": "15:31:23", "throughput": 660.89, "total_tokens": 18036784} {"current_steps": 13130, "total_steps": 40000, "loss": 0.855, "lr": 3.7845831385942655e-05, "epoch": 0.42026758850265666, "percentage": 32.82, "elapsed_time": "7:34:53", "remaining_time": "15:30:54", "throughput": 661.09, "total_tokens": 18043488} {"current_steps": 13135, "total_steps": 40000, "loss": 0.9562, "lr": 3.7837408079520944e-05, "epoch": 0.4204276294731451, "percentage": 32.84, "elapsed_time": "7:34:55", "remaining_time": "15:30:26", "throughput": 661.29, "total_tokens": 18050112} {"current_steps": 13140, "total_steps": 40000, "loss": 0.9554, "lr": 3.782898279340957e-05, "epoch": 0.42058767044363354, "percentage": 32.85, "elapsed_time": "7:34:56", "remaining_time": "15:29:58", "throughput": 661.49, "total_tokens": 18056592} {"current_steps": 13145, "total_steps": 40000, "loss": 0.8136, "lr": 3.782055552890784e-05, "epoch": 0.42074771141412204, "percentage": 32.86, "elapsed_time": "7:34:58", "remaining_time": "15:29:30", "throughput": 661.69, "total_tokens": 18063136} {"current_steps": 13150, "total_steps": 40000, "loss": 0.9375, "lr": 3.781212628731534e-05, "epoch": 0.4209077523846105, "percentage": 32.88, "elapsed_time": "7:35:00", "remaining_time": "15:29:02", "throughput": 661.88, "total_tokens": 18069616} {"current_steps": 13155, "total_steps": 40000, "loss": 0.7994, "lr": 3.7803695069931946e-05, "epoch": 0.4210677933550989, "percentage": 32.89, "elapsed_time": "7:35:02", "remaining_time": "15:28:34", "throughput": 662.09, "total_tokens": 18076416} {"current_steps": 13160, "total_steps": 40000, "loss": 0.7273, "lr": 3.779526187805789e-05, "epoch": 0.42122783432558736, "percentage": 32.9, "elapsed_time": "7:35:03", "remaining_time": "15:28:06", "throughput": 662.3, "total_tokens": 18083360} {"current_steps": 13165, "total_steps": 40000, "loss": 0.5558, "lr": 3.778682671299364e-05, "epoch": 0.4213878752960758, "percentage": 32.91, "elapsed_time": "7:35:05", "remaining_time": "15:27:38", "throughput": 662.52, "total_tokens": 18090384} {"current_steps": 13170, "total_steps": 40000, "loss": 0.7397, "lr": 3.777838957604003e-05, "epoch": 0.42154791626656424, "percentage": 32.92, "elapsed_time": "7:35:07", "remaining_time": "15:27:10", "throughput": 662.73, "total_tokens": 18097296} {"current_steps": 13175, "total_steps": 40000, "loss": 0.9562, "lr": 3.776995046849816e-05, "epoch": 0.4217079572370527, "percentage": 32.94, "elapsed_time": "7:35:09", "remaining_time": "15:26:42", "throughput": 662.93, "total_tokens": 18104096} {"current_steps": 13180, "total_steps": 40000, "loss": 0.8861, "lr": 3.776150939166945e-05, "epoch": 0.4218679982075411, "percentage": 32.95, "elapsed_time": "7:35:10", "remaining_time": "15:26:14", "throughput": 663.14, "total_tokens": 18110976} {"current_steps": 13185, "total_steps": 40000, "loss": 0.8387, "lr": 3.775306634685562e-05, "epoch": 0.42202803917802956, "percentage": 32.96, "elapsed_time": "7:35:12", "remaining_time": "15:25:46", "throughput": 663.36, "total_tokens": 18117968} {"current_steps": 13190, "total_steps": 40000, "loss": 0.7493, "lr": 3.7744621335358696e-05, "epoch": 0.422188080148518, "percentage": 32.98, "elapsed_time": "7:35:14", "remaining_time": "15:25:18", "throughput": 663.57, "total_tokens": 18124816} {"current_steps": 13195, "total_steps": 40000, "loss": 0.7055, "lr": 3.7736174358481e-05, "epoch": 0.4223481211190065, "percentage": 32.99, "elapsed_time": "7:35:16", "remaining_time": "15:24:51", "throughput": 663.76, "total_tokens": 18131328} {"current_steps": 13200, "total_steps": 40000, "loss": 0.6706, "lr": 3.7727725417525175e-05, "epoch": 0.42250816208949493, "percentage": 33.0, "elapsed_time": "7:35:17", "remaining_time": "15:24:23", "throughput": 663.96, "total_tokens": 18137984} {"current_steps": 13200, "total_steps": 40000, "eval_loss": 0.7704335451126099, "epoch": 0.42250816208949493, "percentage": 33.0, "elapsed_time": "7:41:05", "remaining_time": "15:36:09", "throughput": 655.62, "total_tokens": 18137984} {"current_steps": 13205, "total_steps": 40000, "loss": 0.6859, "lr": 3.771927451379414e-05, "epoch": 0.42266820305998337, "percentage": 33.01, "elapsed_time": "7:41:08", "remaining_time": "15:35:44", "throughput": 655.81, "total_tokens": 18145664} {"current_steps": 13210, "total_steps": 40000, "loss": 0.6301, "lr": 3.7710821648591135e-05, "epoch": 0.4228282440304718, "percentage": 33.02, "elapsed_time": "7:41:10", "remaining_time": "15:35:16", "throughput": 656.01, "total_tokens": 18152224} {"current_steps": 13215, "total_steps": 40000, "loss": 0.5219, "lr": 3.7702366823219694e-05, "epoch": 0.42298828500096025, "percentage": 33.04, "elapsed_time": "7:41:12", "remaining_time": "15:34:48", "throughput": 656.22, "total_tokens": 18159264} {"current_steps": 13220, "total_steps": 40000, "loss": 0.6857, "lr": 3.769391003898366e-05, "epoch": 0.4231483259714487, "percentage": 33.05, "elapsed_time": "7:41:14", "remaining_time": "15:34:19", "throughput": 656.43, "total_tokens": 18166128} {"current_steps": 13225, "total_steps": 40000, "loss": 1.0588, "lr": 3.768545129718718e-05, "epoch": 0.42330836694193713, "percentage": 33.06, "elapsed_time": "7:41:15", "remaining_time": "15:33:51", "throughput": 656.64, "total_tokens": 18173040} {"current_steps": 13230, "total_steps": 40000, "loss": 0.8615, "lr": 3.7676990599134686e-05, "epoch": 0.42346840791242557, "percentage": 33.07, "elapsed_time": "7:41:17", "remaining_time": "15:33:23", "throughput": 656.86, "total_tokens": 18180192} {"current_steps": 13235, "total_steps": 40000, "loss": 0.9327, "lr": 3.766852794613095e-05, "epoch": 0.423628448882914, "percentage": 33.09, "elapsed_time": "7:41:19", "remaining_time": "15:32:55", "throughput": 657.06, "total_tokens": 18186912} {"current_steps": 13240, "total_steps": 40000, "loss": 0.8998, "lr": 3.766006333948099e-05, "epoch": 0.42378848985340245, "percentage": 33.1, "elapsed_time": "7:41:21", "remaining_time": "15:32:27", "throughput": 657.27, "total_tokens": 18194032} {"current_steps": 13245, "total_steps": 40000, "loss": 0.8389, "lr": 3.765159678049017e-05, "epoch": 0.4239485308238909, "percentage": 33.11, "elapsed_time": "7:41:22", "remaining_time": "15:31:59", "throughput": 657.47, "total_tokens": 18200672} {"current_steps": 13250, "total_steps": 40000, "loss": 0.8018, "lr": 3.7643128270464134e-05, "epoch": 0.4241085717943794, "percentage": 33.12, "elapsed_time": "7:41:24", "remaining_time": "15:31:31", "throughput": 657.69, "total_tokens": 18207904} {"current_steps": 13255, "total_steps": 40000, "loss": 0.707, "lr": 3.763465781070884e-05, "epoch": 0.4242686127648678, "percentage": 33.14, "elapsed_time": "7:41:26", "remaining_time": "15:31:03", "throughput": 657.92, "total_tokens": 18215216} {"current_steps": 13260, "total_steps": 40000, "loss": 0.8951, "lr": 3.762618540253052e-05, "epoch": 0.42442865373535626, "percentage": 33.15, "elapsed_time": "7:41:27", "remaining_time": "15:30:35", "throughput": 658.15, "total_tokens": 18222864} {"current_steps": 13265, "total_steps": 40000, "loss": 0.7759, "lr": 3.761771104723576e-05, "epoch": 0.4245886947058447, "percentage": 33.16, "elapsed_time": "7:41:29", "remaining_time": "15:30:07", "throughput": 658.35, "total_tokens": 18229536} {"current_steps": 13270, "total_steps": 40000, "loss": 0.7367, "lr": 3.7609234746131386e-05, "epoch": 0.42474873567633314, "percentage": 33.17, "elapsed_time": "7:41:31", "remaining_time": "15:29:39", "throughput": 658.56, "total_tokens": 18236480} {"current_steps": 13275, "total_steps": 40000, "loss": 0.8243, "lr": 3.7600756500524556e-05, "epoch": 0.4249087766468216, "percentage": 33.19, "elapsed_time": "7:41:33", "remaining_time": "15:29:11", "throughput": 658.76, "total_tokens": 18243248} {"current_steps": 13280, "total_steps": 40000, "loss": 0.5947, "lr": 3.759227631172271e-05, "epoch": 0.42506881761731, "percentage": 33.2, "elapsed_time": "7:41:34", "remaining_time": "15:28:43", "throughput": 658.96, "total_tokens": 18249952} {"current_steps": 13285, "total_steps": 40000, "loss": 0.7434, "lr": 3.758379418103363e-05, "epoch": 0.42522885858779846, "percentage": 33.21, "elapsed_time": "7:41:36", "remaining_time": "15:28:15", "throughput": 659.17, "total_tokens": 18256784} {"current_steps": 13290, "total_steps": 40000, "loss": 0.6657, "lr": 3.757531010976534e-05, "epoch": 0.4253888995582869, "percentage": 33.23, "elapsed_time": "7:41:38", "remaining_time": "15:27:47", "throughput": 659.39, "total_tokens": 18263936} {"current_steps": 13295, "total_steps": 40000, "loss": 0.7514, "lr": 3.75668240992262e-05, "epoch": 0.42554894052877534, "percentage": 33.24, "elapsed_time": "7:41:40", "remaining_time": "15:27:19", "throughput": 659.6, "total_tokens": 18270944} {"current_steps": 13300, "total_steps": 40000, "loss": 0.7918, "lr": 3.7558336150724865e-05, "epoch": 0.42570898149926384, "percentage": 33.25, "elapsed_time": "7:41:41", "remaining_time": "15:26:52", "throughput": 659.82, "total_tokens": 18278208} {"current_steps": 13305, "total_steps": 40000, "loss": 0.8193, "lr": 3.754984626557028e-05, "epoch": 0.4258690224697523, "percentage": 33.26, "elapsed_time": "7:41:43", "remaining_time": "15:26:24", "throughput": 660.02, "total_tokens": 18284976} {"current_steps": 13310, "total_steps": 40000, "loss": 0.9187, "lr": 3.754135444507168e-05, "epoch": 0.4260290634402407, "percentage": 33.27, "elapsed_time": "7:41:45", "remaining_time": "15:25:56", "throughput": 660.22, "total_tokens": 18291744} {"current_steps": 13315, "total_steps": 40000, "loss": 0.695, "lr": 3.753286069053863e-05, "epoch": 0.42618910441072916, "percentage": 33.29, "elapsed_time": "7:41:47", "remaining_time": "15:25:28", "throughput": 660.42, "total_tokens": 18298208} {"current_steps": 13320, "total_steps": 40000, "loss": 1.0223, "lr": 3.7524365003280945e-05, "epoch": 0.4263491453812176, "percentage": 33.3, "elapsed_time": "7:41:48", "remaining_time": "15:25:00", "throughput": 660.63, "total_tokens": 18305248} {"current_steps": 13325, "total_steps": 40000, "loss": 0.5615, "lr": 3.75158673846088e-05, "epoch": 0.42650918635170604, "percentage": 33.31, "elapsed_time": "7:41:50", "remaining_time": "15:24:33", "throughput": 660.82, "total_tokens": 18311760} {"current_steps": 13330, "total_steps": 40000, "loss": 0.703, "lr": 3.750736783583262e-05, "epoch": 0.4266692273221945, "percentage": 33.32, "elapsed_time": "7:41:52", "remaining_time": "15:24:05", "throughput": 661.03, "total_tokens": 18318768} {"current_steps": 13335, "total_steps": 40000, "loss": 0.756, "lr": 3.7498866358263144e-05, "epoch": 0.4268292682926829, "percentage": 33.34, "elapsed_time": "7:41:54", "remaining_time": "15:23:37", "throughput": 661.24, "total_tokens": 18325616} {"current_steps": 13340, "total_steps": 40000, "loss": 0.8082, "lr": 3.74903629532114e-05, "epoch": 0.42698930926317136, "percentage": 33.35, "elapsed_time": "7:41:55", "remaining_time": "15:23:09", "throughput": 661.44, "total_tokens": 18332256} {"current_steps": 13345, "total_steps": 40000, "loss": 0.7075, "lr": 3.748185762198873e-05, "epoch": 0.4271493502336598, "percentage": 33.36, "elapsed_time": "7:41:57", "remaining_time": "15:22:42", "throughput": 661.63, "total_tokens": 18338832} {"current_steps": 13350, "total_steps": 40000, "loss": 0.7161, "lr": 3.747335036590676e-05, "epoch": 0.42730939120414824, "percentage": 33.38, "elapsed_time": "7:41:59", "remaining_time": "15:22:14", "throughput": 661.83, "total_tokens": 18345456} {"current_steps": 13355, "total_steps": 40000, "loss": 0.8059, "lr": 3.7464841186277405e-05, "epoch": 0.42746943217463673, "percentage": 33.39, "elapsed_time": "7:42:00", "remaining_time": "15:21:46", "throughput": 662.03, "total_tokens": 18352048} {"current_steps": 13360, "total_steps": 40000, "loss": 0.7413, "lr": 3.7456330084412896e-05, "epoch": 0.42762947314512517, "percentage": 33.4, "elapsed_time": "7:42:02", "remaining_time": "15:21:19", "throughput": 662.24, "total_tokens": 18358976} {"current_steps": 13365, "total_steps": 40000, "loss": 0.6043, "lr": 3.744781706162576e-05, "epoch": 0.4277895141156136, "percentage": 33.41, "elapsed_time": "7:42:04", "remaining_time": "15:20:51", "throughput": 662.44, "total_tokens": 18365776} {"current_steps": 13370, "total_steps": 40000, "loss": 0.6381, "lr": 3.743930211922879e-05, "epoch": 0.42794955508610205, "percentage": 33.42, "elapsed_time": "7:42:06", "remaining_time": "15:20:24", "throughput": 662.64, "total_tokens": 18372528} {"current_steps": 13375, "total_steps": 40000, "loss": 0.7769, "lr": 3.743078525853513e-05, "epoch": 0.4281095960565905, "percentage": 33.44, "elapsed_time": "7:42:07", "remaining_time": "15:19:56", "throughput": 662.84, "total_tokens": 18379104} {"current_steps": 13380, "total_steps": 40000, "loss": 0.7792, "lr": 3.7422266480858154e-05, "epoch": 0.42826963702707893, "percentage": 33.45, "elapsed_time": "7:42:09", "remaining_time": "15:19:29", "throughput": 663.04, "total_tokens": 18385824} {"current_steps": 13385, "total_steps": 40000, "loss": 0.9016, "lr": 3.741374578751158e-05, "epoch": 0.42842967799756737, "percentage": 33.46, "elapsed_time": "7:42:11", "remaining_time": "15:19:01", "throughput": 663.23, "total_tokens": 18392368} {"current_steps": 13390, "total_steps": 40000, "loss": 0.6897, "lr": 3.740522317980941e-05, "epoch": 0.4285897189680558, "percentage": 33.48, "elapsed_time": "7:42:13", "remaining_time": "15:18:34", "throughput": 663.45, "total_tokens": 18399584} {"current_steps": 13395, "total_steps": 40000, "loss": 0.6893, "lr": 3.739669865906593e-05, "epoch": 0.42874975993854425, "percentage": 33.49, "elapsed_time": "7:42:14", "remaining_time": "15:18:06", "throughput": 663.66, "total_tokens": 18406480} {"current_steps": 13400, "total_steps": 40000, "loss": 0.8119, "lr": 3.738817222659573e-05, "epoch": 0.4289098009090327, "percentage": 33.5, "elapsed_time": "7:42:16", "remaining_time": "15:17:39", "throughput": 663.87, "total_tokens": 18413504} {"current_steps": 13400, "total_steps": 40000, "eval_loss": 0.7683921456336975, "epoch": 0.4289098009090327, "percentage": 33.5, "elapsed_time": "7:48:04", "remaining_time": "15:29:09", "throughput": 655.65, "total_tokens": 18413504} {"current_steps": 13405, "total_steps": 40000, "loss": 0.6335, "lr": 3.73796438837137e-05, "epoch": 0.42906984187952113, "percentage": 33.51, "elapsed_time": "7:48:08", "remaining_time": "15:28:46", "throughput": 655.81, "total_tokens": 18420640} {"current_steps": 13410, "total_steps": 40000, "loss": 0.948, "lr": 3.7371113631735e-05, "epoch": 0.4292298828500096, "percentage": 33.52, "elapsed_time": "7:48:10", "remaining_time": "15:28:18", "throughput": 656.01, "total_tokens": 18427360} {"current_steps": 13415, "total_steps": 40000, "loss": 0.775, "lr": 3.736258147197512e-05, "epoch": 0.42938992382049807, "percentage": 33.54, "elapsed_time": "7:48:11", "remaining_time": "15:27:50", "throughput": 656.22, "total_tokens": 18434304} {"current_steps": 13420, "total_steps": 40000, "loss": 0.5569, "lr": 3.735404740574981e-05, "epoch": 0.4295499647909865, "percentage": 33.55, "elapsed_time": "7:48:13", "remaining_time": "15:27:22", "throughput": 656.43, "total_tokens": 18441440} {"current_steps": 13425, "total_steps": 40000, "loss": 0.6977, "lr": 3.7345511434375145e-05, "epoch": 0.42971000576147494, "percentage": 33.56, "elapsed_time": "7:48:15", "remaining_time": "15:26:55", "throughput": 656.63, "total_tokens": 18448144} {"current_steps": 13430, "total_steps": 40000, "loss": 0.8576, "lr": 3.733697355916748e-05, "epoch": 0.4298700467319634, "percentage": 33.58, "elapsed_time": "7:48:17", "remaining_time": "15:26:27", "throughput": 656.85, "total_tokens": 18455472} {"current_steps": 13435, "total_steps": 40000, "loss": 0.7865, "lr": 3.732843378144345e-05, "epoch": 0.4300300877024518, "percentage": 33.59, "elapsed_time": "7:48:18", "remaining_time": "15:25:59", "throughput": 657.06, "total_tokens": 18462592} {"current_steps": 13440, "total_steps": 40000, "loss": 0.5839, "lr": 3.7319892102519995e-05, "epoch": 0.43019012867294026, "percentage": 33.6, "elapsed_time": "7:48:20", "remaining_time": "15:25:31", "throughput": 657.27, "total_tokens": 18469728} {"current_steps": 13445, "total_steps": 40000, "loss": 0.7378, "lr": 3.731134852371436e-05, "epoch": 0.4303501696434287, "percentage": 33.61, "elapsed_time": "7:48:22", "remaining_time": "15:25:04", "throughput": 657.47, "total_tokens": 18476512} {"current_steps": 13450, "total_steps": 40000, "loss": 0.8613, "lr": 3.730280304634408e-05, "epoch": 0.43051021061391714, "percentage": 33.62, "elapsed_time": "7:48:23", "remaining_time": "15:24:36", "throughput": 657.68, "total_tokens": 18483424} {"current_steps": 13455, "total_steps": 40000, "loss": 0.7596, "lr": 3.729425567172696e-05, "epoch": 0.4306702515844056, "percentage": 33.64, "elapsed_time": "7:48:25", "remaining_time": "15:24:09", "throughput": 657.88, "total_tokens": 18490272} {"current_steps": 13460, "total_steps": 40000, "loss": 0.722, "lr": 3.728570640118111e-05, "epoch": 0.4308302925548941, "percentage": 33.65, "elapsed_time": "7:48:27", "remaining_time": "15:23:41", "throughput": 658.08, "total_tokens": 18497056} {"current_steps": 13465, "total_steps": 40000, "loss": 0.8824, "lr": 3.727715523602494e-05, "epoch": 0.4309903335253825, "percentage": 33.66, "elapsed_time": "7:48:29", "remaining_time": "15:23:13", "throughput": 658.28, "total_tokens": 18503744} {"current_steps": 13470, "total_steps": 40000, "loss": 0.7264, "lr": 3.726860217757715e-05, "epoch": 0.43115037449587096, "percentage": 33.67, "elapsed_time": "7:48:30", "remaining_time": "15:22:46", "throughput": 658.48, "total_tokens": 18510544} {"current_steps": 13475, "total_steps": 40000, "loss": 1.0973, "lr": 3.726004722715673e-05, "epoch": 0.4313104154663594, "percentage": 33.69, "elapsed_time": "7:48:32", "remaining_time": "15:22:18", "throughput": 658.7, "total_tokens": 18517920} {"current_steps": 13480, "total_steps": 40000, "loss": 0.5561, "lr": 3.725149038608296e-05, "epoch": 0.43147045643684784, "percentage": 33.7, "elapsed_time": "7:48:34", "remaining_time": "15:21:51", "throughput": 658.92, "total_tokens": 18525024} {"current_steps": 13485, "total_steps": 40000, "loss": 0.5709, "lr": 3.7242931655675404e-05, "epoch": 0.4316304974073363, "percentage": 33.71, "elapsed_time": "7:48:36", "remaining_time": "15:21:23", "throughput": 659.14, "total_tokens": 18532416} {"current_steps": 13490, "total_steps": 40000, "loss": 0.6904, "lr": 3.7234371037253937e-05, "epoch": 0.4317905383778247, "percentage": 33.73, "elapsed_time": "7:48:37", "remaining_time": "15:20:56", "throughput": 659.35, "total_tokens": 18539392} {"current_steps": 13495, "total_steps": 40000, "loss": 0.6606, "lr": 3.7225808532138705e-05, "epoch": 0.43195057934831316, "percentage": 33.74, "elapsed_time": "7:48:39", "remaining_time": "15:20:28", "throughput": 659.56, "total_tokens": 18546640} {"current_steps": 13500, "total_steps": 40000, "loss": 0.6909, "lr": 3.721724414165016e-05, "epoch": 0.4321106203188016, "percentage": 33.75, "elapsed_time": "7:48:41", "remaining_time": "15:20:01", "throughput": 659.76, "total_tokens": 18553248} {"current_steps": 13505, "total_steps": 40000, "loss": 0.7439, "lr": 3.720867786710904e-05, "epoch": 0.43227066128929004, "percentage": 33.76, "elapsed_time": "7:48:43", "remaining_time": "15:19:33", "throughput": 659.96, "total_tokens": 18560048} {"current_steps": 13510, "total_steps": 40000, "loss": 0.5497, "lr": 3.7200109709836366e-05, "epoch": 0.4324307022597785, "percentage": 33.77, "elapsed_time": "7:48:44", "remaining_time": "15:19:06", "throughput": 660.15, "total_tokens": 18566688} {"current_steps": 13515, "total_steps": 40000, "loss": 0.6339, "lr": 3.7191539671153465e-05, "epoch": 0.43259074323026697, "percentage": 33.79, "elapsed_time": "7:48:46", "remaining_time": "15:18:38", "throughput": 660.35, "total_tokens": 18573520} {"current_steps": 13520, "total_steps": 40000, "loss": 0.6228, "lr": 3.718296775238193e-05, "epoch": 0.4327507842007554, "percentage": 33.8, "elapsed_time": "7:48:48", "remaining_time": "15:18:11", "throughput": 660.56, "total_tokens": 18580576} {"current_steps": 13525, "total_steps": 40000, "loss": 0.8469, "lr": 3.7174393954843675e-05, "epoch": 0.43291082517124385, "percentage": 33.81, "elapsed_time": "7:48:50", "remaining_time": "15:17:44", "throughput": 660.77, "total_tokens": 18587504} {"current_steps": 13530, "total_steps": 40000, "loss": 1.0611, "lr": 3.716581827986087e-05, "epoch": 0.4330708661417323, "percentage": 33.83, "elapsed_time": "7:48:51", "remaining_time": "15:17:16", "throughput": 660.98, "total_tokens": 18594432} {"current_steps": 13535, "total_steps": 40000, "loss": 0.6672, "lr": 3.7157240728756004e-05, "epoch": 0.43323090711222073, "percentage": 33.84, "elapsed_time": "7:48:53", "remaining_time": "15:16:49", "throughput": 661.17, "total_tokens": 18601120} {"current_steps": 13540, "total_steps": 40000, "loss": 0.7964, "lr": 3.714866130285184e-05, "epoch": 0.43339094808270917, "percentage": 33.85, "elapsed_time": "7:48:55", "remaining_time": "15:16:22", "throughput": 661.38, "total_tokens": 18608208} {"current_steps": 13545, "total_steps": 40000, "loss": 0.6958, "lr": 3.714008000347143e-05, "epoch": 0.4335509890531976, "percentage": 33.86, "elapsed_time": "7:48:56", "remaining_time": "15:15:54", "throughput": 661.6, "total_tokens": 18615456} {"current_steps": 13550, "total_steps": 40000, "loss": 0.8587, "lr": 3.7131496831938126e-05, "epoch": 0.43371103002368605, "percentage": 33.88, "elapsed_time": "7:48:58", "remaining_time": "15:15:27", "throughput": 661.81, "total_tokens": 18622432} {"current_steps": 13555, "total_steps": 40000, "loss": 0.7673, "lr": 3.7122911789575565e-05, "epoch": 0.4338710709941745, "percentage": 33.89, "elapsed_time": "7:49:00", "remaining_time": "15:15:00", "throughput": 662.02, "total_tokens": 18629584} {"current_steps": 13560, "total_steps": 40000, "loss": 0.6719, "lr": 3.711432487770765e-05, "epoch": 0.43403111196466293, "percentage": 33.9, "elapsed_time": "7:49:02", "remaining_time": "15:14:33", "throughput": 662.22, "total_tokens": 18636416} {"current_steps": 13565, "total_steps": 40000, "loss": 0.7928, "lr": 3.710573609765861e-05, "epoch": 0.4341911529351514, "percentage": 33.91, "elapsed_time": "7:49:03", "remaining_time": "15:14:05", "throughput": 662.41, "total_tokens": 18642800} {"current_steps": 13570, "total_steps": 40000, "loss": 0.6338, "lr": 3.709714545075292e-05, "epoch": 0.43435119390563987, "percentage": 33.92, "elapsed_time": "7:49:05", "remaining_time": "15:13:38", "throughput": 662.61, "total_tokens": 18649648} {"current_steps": 13575, "total_steps": 40000, "loss": 0.8568, "lr": 3.708855293831538e-05, "epoch": 0.4345112348761283, "percentage": 33.94, "elapsed_time": "7:49:07", "remaining_time": "15:13:11", "throughput": 662.81, "total_tokens": 18656496} {"current_steps": 13580, "total_steps": 40000, "loss": 0.735, "lr": 3.707995856167107e-05, "epoch": 0.43467127584661674, "percentage": 33.95, "elapsed_time": "7:49:09", "remaining_time": "15:12:44", "throughput": 663.02, "total_tokens": 18663392} {"current_steps": 13585, "total_steps": 40000, "loss": 0.8237, "lr": 3.707136232214534e-05, "epoch": 0.4348313168171052, "percentage": 33.96, "elapsed_time": "7:49:10", "remaining_time": "15:12:17", "throughput": 663.22, "total_tokens": 18670304} {"current_steps": 13590, "total_steps": 40000, "loss": 0.74, "lr": 3.7062764221063844e-05, "epoch": 0.4349913577875936, "percentage": 33.98, "elapsed_time": "7:49:12", "remaining_time": "15:11:50", "throughput": 663.42, "total_tokens": 18676976} {"current_steps": 13595, "total_steps": 40000, "loss": 0.7687, "lr": 3.705416425975252e-05, "epoch": 0.43515139875808206, "percentage": 33.99, "elapsed_time": "7:49:14", "remaining_time": "15:11:22", "throughput": 663.61, "total_tokens": 18683600} {"current_steps": 13600, "total_steps": 40000, "loss": 0.8481, "lr": 3.704556243953758e-05, "epoch": 0.4353114397285705, "percentage": 34.0, "elapsed_time": "7:49:16", "remaining_time": "15:10:55", "throughput": 663.82, "total_tokens": 18690528} {"current_steps": 13600, "total_steps": 40000, "eval_loss": 0.7664963603019714, "epoch": 0.4353114397285705, "percentage": 34.0, "elapsed_time": "7:55:03", "remaining_time": "15:22:10", "throughput": 655.72, "total_tokens": 18690528} {"current_steps": 13605, "total_steps": 40000, "loss": 0.8482, "lr": 3.7036958761745535e-05, "epoch": 0.43547148069905894, "percentage": 34.01, "elapsed_time": "7:55:07", "remaining_time": "15:21:47", "throughput": 655.87, "total_tokens": 18697200} {"current_steps": 13610, "total_steps": 40000, "loss": 0.7677, "lr": 3.702835322770318e-05, "epoch": 0.4356315216695474, "percentage": 34.02, "elapsed_time": "7:55:09", "remaining_time": "15:21:19", "throughput": 656.05, "total_tokens": 18703552} {"current_steps": 13615, "total_steps": 40000, "loss": 0.6311, "lr": 3.701974583873761e-05, "epoch": 0.4357915626400358, "percentage": 34.04, "elapsed_time": "7:55:10", "remaining_time": "15:20:52", "throughput": 656.25, "total_tokens": 18710416} {"current_steps": 13620, "total_steps": 40000, "loss": 0.7617, "lr": 3.701113659617618e-05, "epoch": 0.4359516036105243, "percentage": 34.05, "elapsed_time": "7:55:12", "remaining_time": "15:20:24", "throughput": 656.46, "total_tokens": 18717328} {"current_steps": 13625, "total_steps": 40000, "loss": 0.9545, "lr": 3.7002525501346535e-05, "epoch": 0.43611164458101276, "percentage": 34.06, "elapsed_time": "7:55:14", "remaining_time": "15:19:57", "throughput": 656.65, "total_tokens": 18724080} {"current_steps": 13630, "total_steps": 40000, "loss": 0.8905, "lr": 3.699391255557664e-05, "epoch": 0.4362716855515012, "percentage": 34.08, "elapsed_time": "7:55:16", "remaining_time": "15:19:30", "throughput": 656.84, "total_tokens": 18730608} {"current_steps": 13635, "total_steps": 40000, "loss": 0.7607, "lr": 3.69852977601947e-05, "epoch": 0.43643172652198964, "percentage": 34.09, "elapsed_time": "7:55:17", "remaining_time": "15:19:02", "throughput": 657.06, "total_tokens": 18737904} {"current_steps": 13640, "total_steps": 40000, "loss": 0.7196, "lr": 3.697668111652922e-05, "epoch": 0.4365917674924781, "percentage": 34.1, "elapsed_time": "7:55:19", "remaining_time": "15:18:35", "throughput": 657.27, "total_tokens": 18744944} {"current_steps": 13645, "total_steps": 40000, "loss": 0.7917, "lr": 3.6968062625909005e-05, "epoch": 0.4367518084629665, "percentage": 34.11, "elapsed_time": "7:55:21", "remaining_time": "15:18:08", "throughput": 657.49, "total_tokens": 18752384} {"current_steps": 13650, "total_steps": 40000, "loss": 0.7532, "lr": 3.6959442289663135e-05, "epoch": 0.43691184943345496, "percentage": 34.12, "elapsed_time": "7:55:23", "remaining_time": "15:17:41", "throughput": 657.7, "total_tokens": 18759600} {"current_steps": 13655, "total_steps": 40000, "loss": 0.8548, "lr": 3.695082010912098e-05, "epoch": 0.4370718904039434, "percentage": 34.14, "elapsed_time": "7:55:24", "remaining_time": "15:17:13", "throughput": 657.9, "total_tokens": 18766496} {"current_steps": 13660, "total_steps": 40000, "loss": 0.7771, "lr": 3.694219608561217e-05, "epoch": 0.43723193137443184, "percentage": 34.15, "elapsed_time": "7:55:26", "remaining_time": "15:16:46", "throughput": 658.1, "total_tokens": 18773216} {"current_steps": 13665, "total_steps": 40000, "loss": 0.6937, "lr": 3.693357022046665e-05, "epoch": 0.4373919723449203, "percentage": 34.16, "elapsed_time": "7:55:28", "remaining_time": "15:16:19", "throughput": 658.3, "total_tokens": 18780176} {"current_steps": 13670, "total_steps": 40000, "loss": 0.7426, "lr": 3.6924942515014644e-05, "epoch": 0.43755201331540877, "percentage": 34.17, "elapsed_time": "7:55:30", "remaining_time": "15:15:52", "throughput": 658.51, "total_tokens": 18787376} {"current_steps": 13675, "total_steps": 40000, "loss": 0.7678, "lr": 3.691631297058664e-05, "epoch": 0.4377120542858972, "percentage": 34.19, "elapsed_time": "7:55:31", "remaining_time": "15:15:24", "throughput": 658.71, "total_tokens": 18794176} {"current_steps": 13680, "total_steps": 40000, "loss": 0.6185, "lr": 3.6907681588513424e-05, "epoch": 0.43787209525638565, "percentage": 34.2, "elapsed_time": "7:55:33", "remaining_time": "15:14:57", "throughput": 658.92, "total_tokens": 18801248} {"current_steps": 13685, "total_steps": 40000, "loss": 0.6679, "lr": 3.689904837012606e-05, "epoch": 0.4380321362268741, "percentage": 34.21, "elapsed_time": "7:55:35", "remaining_time": "15:14:30", "throughput": 659.12, "total_tokens": 18808032} {"current_steps": 13690, "total_steps": 40000, "loss": 0.8646, "lr": 3.689041331675591e-05, "epoch": 0.43819217719736253, "percentage": 34.23, "elapsed_time": "7:55:36", "remaining_time": "15:14:03", "throughput": 659.32, "total_tokens": 18815120} {"current_steps": 13695, "total_steps": 40000, "loss": 0.6495, "lr": 3.688177642973461e-05, "epoch": 0.43835221816785097, "percentage": 34.24, "elapsed_time": "7:55:38", "remaining_time": "15:13:36", "throughput": 659.52, "total_tokens": 18821936} {"current_steps": 13700, "total_steps": 40000, "loss": 0.839, "lr": 3.687313771039406e-05, "epoch": 0.4385122591383394, "percentage": 34.25, "elapsed_time": "7:55:40", "remaining_time": "15:13:09", "throughput": 659.72, "total_tokens": 18828768} {"current_steps": 13705, "total_steps": 40000, "loss": 1.0043, "lr": 3.686449716006647e-05, "epoch": 0.43867230010882785, "percentage": 34.26, "elapsed_time": "7:55:42", "remaining_time": "15:12:42", "throughput": 659.93, "total_tokens": 18835696} {"current_steps": 13710, "total_steps": 40000, "loss": 0.7475, "lr": 3.685585478008432e-05, "epoch": 0.4388323410793163, "percentage": 34.27, "elapsed_time": "7:55:43", "remaining_time": "15:12:15", "throughput": 660.14, "total_tokens": 18843088} {"current_steps": 13715, "total_steps": 40000, "loss": 0.7402, "lr": 3.6847210571780364e-05, "epoch": 0.43899238204980473, "percentage": 34.29, "elapsed_time": "7:55:45", "remaining_time": "15:11:48", "throughput": 660.34, "total_tokens": 18849840} {"current_steps": 13720, "total_steps": 40000, "loss": 0.7616, "lr": 3.683856453648767e-05, "epoch": 0.43915242302029317, "percentage": 34.3, "elapsed_time": "7:55:47", "remaining_time": "15:11:21", "throughput": 660.54, "total_tokens": 18856816} {"current_steps": 13725, "total_steps": 40000, "loss": 0.9379, "lr": 3.682991667553954e-05, "epoch": 0.43931246399078167, "percentage": 34.31, "elapsed_time": "7:55:49", "remaining_time": "15:10:54", "throughput": 660.74, "total_tokens": 18863616} {"current_steps": 13730, "total_steps": 40000, "loss": 0.6415, "lr": 3.6821266990269606e-05, "epoch": 0.4394725049612701, "percentage": 34.33, "elapsed_time": "7:55:50", "remaining_time": "15:10:27", "throughput": 660.95, "total_tokens": 18870560} {"current_steps": 13735, "total_steps": 40000, "loss": 0.9385, "lr": 3.681261548201174e-05, "epoch": 0.43963254593175854, "percentage": 34.34, "elapsed_time": "7:55:52", "remaining_time": "15:10:00", "throughput": 661.14, "total_tokens": 18877344} {"current_steps": 13740, "total_steps": 40000, "loss": 0.8564, "lr": 3.6803962152100125e-05, "epoch": 0.439792586902247, "percentage": 34.35, "elapsed_time": "7:55:54", "remaining_time": "15:09:33", "throughput": 661.35, "total_tokens": 18884368} {"current_steps": 13745, "total_steps": 40000, "loss": 0.6207, "lr": 3.67953070018692e-05, "epoch": 0.4399526278727354, "percentage": 34.36, "elapsed_time": "7:55:56", "remaining_time": "15:09:06", "throughput": 661.55, "total_tokens": 18891200} {"current_steps": 13750, "total_steps": 40000, "loss": 0.7955, "lr": 3.678665003265371e-05, "epoch": 0.44011266884322386, "percentage": 34.38, "elapsed_time": "7:55:57", "remaining_time": "15:08:39", "throughput": 661.74, "total_tokens": 18897744} {"current_steps": 13755, "total_steps": 40000, "loss": 0.8367, "lr": 3.677799124578867e-05, "epoch": 0.4402727098137123, "percentage": 34.39, "elapsed_time": "7:55:59", "remaining_time": "15:08:12", "throughput": 661.93, "total_tokens": 18904336} {"current_steps": 13760, "total_steps": 40000, "loss": 0.7043, "lr": 3.676933064260937e-05, "epoch": 0.44043275078420074, "percentage": 34.4, "elapsed_time": "7:56:01", "remaining_time": "15:07:45", "throughput": 662.13, "total_tokens": 18911376} {"current_steps": 13765, "total_steps": 40000, "loss": 0.8227, "lr": 3.6760668224451365e-05, "epoch": 0.4405927917546892, "percentage": 34.41, "elapsed_time": "7:56:03", "remaining_time": "15:07:18", "throughput": 662.34, "total_tokens": 18918288} {"current_steps": 13770, "total_steps": 40000, "loss": 0.6133, "lr": 3.675200399265054e-05, "epoch": 0.4407528327251776, "percentage": 34.42, "elapsed_time": "7:56:04", "remaining_time": "15:06:52", "throughput": 662.54, "total_tokens": 18925392} {"current_steps": 13775, "total_steps": 40000, "loss": 0.7936, "lr": 3.6743337948543014e-05, "epoch": 0.44091287369566606, "percentage": 34.44, "elapsed_time": "7:56:06", "remaining_time": "15:06:25", "throughput": 662.74, "total_tokens": 18932144} {"current_steps": 13780, "total_steps": 40000, "loss": 0.5632, "lr": 3.6734670093465204e-05, "epoch": 0.44107291466615456, "percentage": 34.45, "elapsed_time": "7:56:08", "remaining_time": "15:05:58", "throughput": 662.94, "total_tokens": 18938912} {"current_steps": 13785, "total_steps": 40000, "loss": 0.7052, "lr": 3.672600042875379e-05, "epoch": 0.441232955636643, "percentage": 34.46, "elapsed_time": "7:56:09", "remaining_time": "15:05:31", "throughput": 663.14, "total_tokens": 18945792} {"current_steps": 13790, "total_steps": 40000, "loss": 0.6877, "lr": 3.671732895574575e-05, "epoch": 0.44139299660713144, "percentage": 34.48, "elapsed_time": "7:56:11", "remaining_time": "15:05:04", "throughput": 663.34, "total_tokens": 18952768} {"current_steps": 13795, "total_steps": 40000, "loss": 0.7854, "lr": 3.670865567577834e-05, "epoch": 0.4415530375776199, "percentage": 34.49, "elapsed_time": "7:56:13", "remaining_time": "15:04:38", "throughput": 663.54, "total_tokens": 18959504} {"current_steps": 13800, "total_steps": 40000, "loss": 0.8423, "lr": 3.669998059018909e-05, "epoch": 0.4417130785481083, "percentage": 34.5, "elapsed_time": "7:56:15", "remaining_time": "15:04:11", "throughput": 663.74, "total_tokens": 18966352} {"current_steps": 13800, "total_steps": 40000, "eval_loss": 0.7651934623718262, "epoch": 0.4417130785481083, "percentage": 34.5, "elapsed_time": "8:02:03", "remaining_time": "15:15:11", "throughput": 655.75, "total_tokens": 18966352} {"current_steps": 13805, "total_steps": 40000, "loss": 0.7862, "lr": 3.6691303700315796e-05, "epoch": 0.44187311951859676, "percentage": 34.51, "elapsed_time": "8:02:06", "remaining_time": "15:14:48", "throughput": 655.93, "total_tokens": 18973856} {"current_steps": 13810, "total_steps": 40000, "loss": 0.741, "lr": 3.668262500749655e-05, "epoch": 0.4420331604890852, "percentage": 34.52, "elapsed_time": "8:02:08", "remaining_time": "15:14:21", "throughput": 656.13, "total_tokens": 18980752} {"current_steps": 13815, "total_steps": 40000, "loss": 0.8532, "lr": 3.667394451306971e-05, "epoch": 0.44219320145957364, "percentage": 34.54, "elapsed_time": "8:02:10", "remaining_time": "15:13:54", "throughput": 656.33, "total_tokens": 18987712} {"current_steps": 13820, "total_steps": 40000, "loss": 0.5624, "lr": 3.666526221837393e-05, "epoch": 0.4423532424300621, "percentage": 34.55, "elapsed_time": "8:02:11", "remaining_time": "15:13:27", "throughput": 656.53, "total_tokens": 18994704} {"current_steps": 13825, "total_steps": 40000, "loss": 0.7298, "lr": 3.665657812474812e-05, "epoch": 0.4425132834005505, "percentage": 34.56, "elapsed_time": "8:02:13", "remaining_time": "15:13:00", "throughput": 656.72, "total_tokens": 19001344} {"current_steps": 13830, "total_steps": 40000, "loss": 0.9896, "lr": 3.664789223353147e-05, "epoch": 0.442673324371039, "percentage": 34.58, "elapsed_time": "8:02:15", "remaining_time": "15:12:33", "throughput": 656.92, "total_tokens": 19008256} {"current_steps": 13835, "total_steps": 40000, "loss": 0.765, "lr": 3.663920454606347e-05, "epoch": 0.44283336534152745, "percentage": 34.59, "elapsed_time": "8:02:17", "remaining_time": "15:12:06", "throughput": 657.12, "total_tokens": 19015104} {"current_steps": 13840, "total_steps": 40000, "loss": 0.7814, "lr": 3.6630515063683856e-05, "epoch": 0.4429934063120159, "percentage": 34.6, "elapsed_time": "8:02:18", "remaining_time": "15:11:39", "throughput": 657.32, "total_tokens": 19022128} {"current_steps": 13845, "total_steps": 40000, "loss": 0.7345, "lr": 3.662182378773267e-05, "epoch": 0.44315344728250433, "percentage": 34.61, "elapsed_time": "8:02:20", "remaining_time": "15:11:12", "throughput": 657.52, "total_tokens": 19028960} {"current_steps": 13850, "total_steps": 40000, "loss": 0.7695, "lr": 3.66131307195502e-05, "epoch": 0.44331348825299277, "percentage": 34.62, "elapsed_time": "8:02:22", "remaining_time": "15:10:45", "throughput": 657.72, "total_tokens": 19035968} {"current_steps": 13855, "total_steps": 40000, "loss": 0.7604, "lr": 3.6604435860477034e-05, "epoch": 0.4434735292234812, "percentage": 34.64, "elapsed_time": "8:02:23", "remaining_time": "15:10:18", "throughput": 657.92, "total_tokens": 19042832} {"current_steps": 13860, "total_steps": 40000, "loss": 0.6868, "lr": 3.6595739211854025e-05, "epoch": 0.44363357019396965, "percentage": 34.65, "elapsed_time": "8:02:25", "remaining_time": "15:09:51", "throughput": 658.12, "total_tokens": 19049616} {"current_steps": 13865, "total_steps": 40000, "loss": 1.0323, "lr": 3.658704077502231e-05, "epoch": 0.4437936111644581, "percentage": 34.66, "elapsed_time": "8:02:27", "remaining_time": "15:09:24", "throughput": 658.31, "total_tokens": 19056400} {"current_steps": 13870, "total_steps": 40000, "loss": 0.8031, "lr": 3.65783405513233e-05, "epoch": 0.44395365213494653, "percentage": 34.67, "elapsed_time": "8:02:29", "remaining_time": "15:08:58", "throughput": 658.5, "total_tokens": 19062944} {"current_steps": 13875, "total_steps": 40000, "loss": 0.6511, "lr": 3.656963854209867e-05, "epoch": 0.44411369310543497, "percentage": 34.69, "elapsed_time": "8:02:30", "remaining_time": "15:08:31", "throughput": 658.69, "total_tokens": 19069584} {"current_steps": 13880, "total_steps": 40000, "loss": 0.6547, "lr": 3.656093474869038e-05, "epoch": 0.4442737340759234, "percentage": 34.7, "elapsed_time": "8:02:32", "remaining_time": "15:08:04", "throughput": 658.89, "total_tokens": 19076576} {"current_steps": 13885, "total_steps": 40000, "loss": 0.8317, "lr": 3.655222917244068e-05, "epoch": 0.4444337750464119, "percentage": 34.71, "elapsed_time": "8:02:34", "remaining_time": "15:07:37", "throughput": 659.09, "total_tokens": 19083552} {"current_steps": 13890, "total_steps": 40000, "loss": 1.0201, "lr": 3.6543521814692054e-05, "epoch": 0.44459381601690035, "percentage": 34.73, "elapsed_time": "8:02:36", "remaining_time": "15:07:10", "throughput": 659.28, "total_tokens": 19090352} {"current_steps": 13895, "total_steps": 40000, "loss": 0.6828, "lr": 3.653481267678731e-05, "epoch": 0.4447538569873888, "percentage": 34.74, "elapsed_time": "8:02:37", "remaining_time": "15:06:44", "throughput": 659.48, "total_tokens": 19097088} {"current_steps": 13900, "total_steps": 40000, "loss": 0.6384, "lr": 3.652610176006949e-05, "epoch": 0.4449138979578772, "percentage": 34.75, "elapsed_time": "8:02:39", "remaining_time": "15:06:17", "throughput": 659.67, "total_tokens": 19103824} {"current_steps": 13905, "total_steps": 40000, "loss": 0.6315, "lr": 3.6517389065881925e-05, "epoch": 0.44507393892836566, "percentage": 34.76, "elapsed_time": "8:02:41", "remaining_time": "15:05:50", "throughput": 659.86, "total_tokens": 19110432} {"current_steps": 13910, "total_steps": 40000, "loss": 0.6577, "lr": 3.650867459556824e-05, "epoch": 0.4452339798988541, "percentage": 34.77, "elapsed_time": "8:02:43", "remaining_time": "15:05:24", "throughput": 660.05, "total_tokens": 19117216} {"current_steps": 13915, "total_steps": 40000, "loss": 0.8475, "lr": 3.64999583504723e-05, "epoch": 0.44539402086934254, "percentage": 34.79, "elapsed_time": "8:02:44", "remaining_time": "15:04:57", "throughput": 660.25, "total_tokens": 19124160} {"current_steps": 13920, "total_steps": 40000, "loss": 0.7659, "lr": 3.649124033193827e-05, "epoch": 0.445554061839831, "percentage": 34.8, "elapsed_time": "8:02:46", "remaining_time": "15:04:30", "throughput": 660.45, "total_tokens": 19131104} {"current_steps": 13925, "total_steps": 40000, "loss": 0.8368, "lr": 3.648252054131057e-05, "epoch": 0.4457141028103194, "percentage": 34.81, "elapsed_time": "8:02:48", "remaining_time": "15:04:04", "throughput": 660.66, "total_tokens": 19138144} {"current_steps": 13930, "total_steps": 40000, "loss": 0.7132, "lr": 3.647379897993391e-05, "epoch": 0.44587414378080786, "percentage": 34.83, "elapsed_time": "8:02:50", "remaining_time": "15:03:37", "throughput": 660.87, "total_tokens": 19145328} {"current_steps": 13935, "total_steps": 40000, "loss": 0.5958, "lr": 3.646507564915325e-05, "epoch": 0.44603418475129636, "percentage": 34.84, "elapsed_time": "8:02:51", "remaining_time": "15:03:10", "throughput": 661.06, "total_tokens": 19152144} {"current_steps": 13940, "total_steps": 40000, "loss": 0.7455, "lr": 3.645635055031385e-05, "epoch": 0.4461942257217848, "percentage": 34.85, "elapsed_time": "8:02:53", "remaining_time": "15:02:44", "throughput": 661.27, "total_tokens": 19159360} {"current_steps": 13945, "total_steps": 40000, "loss": 0.711, "lr": 3.6447623684761224e-05, "epoch": 0.44635426669227324, "percentage": 34.86, "elapsed_time": "8:02:55", "remaining_time": "15:02:17", "throughput": 661.46, "total_tokens": 19165888} {"current_steps": 13950, "total_steps": 40000, "loss": 0.7431, "lr": 3.643889505384117e-05, "epoch": 0.4465143076627617, "percentage": 34.88, "elapsed_time": "8:02:57", "remaining_time": "15:01:51", "throughput": 661.65, "total_tokens": 19172752} {"current_steps": 13955, "total_steps": 40000, "loss": 0.6194, "lr": 3.6430164658899744e-05, "epoch": 0.4466743486332501, "percentage": 34.89, "elapsed_time": "8:02:58", "remaining_time": "15:01:24", "throughput": 661.86, "total_tokens": 19179936} {"current_steps": 13960, "total_steps": 40000, "loss": 1.0027, "lr": 3.642143250128329e-05, "epoch": 0.44683438960373856, "percentage": 34.9, "elapsed_time": "8:03:00", "remaining_time": "15:00:58", "throughput": 662.07, "total_tokens": 19187056} {"current_steps": 13965, "total_steps": 40000, "loss": 0.745, "lr": 3.641269858233841e-05, "epoch": 0.446994430574227, "percentage": 34.91, "elapsed_time": "8:03:02", "remaining_time": "15:00:31", "throughput": 662.26, "total_tokens": 19193696} {"current_steps": 13970, "total_steps": 40000, "loss": 0.6499, "lr": 3.640396290341199e-05, "epoch": 0.44715447154471544, "percentage": 34.92, "elapsed_time": "8:03:03", "remaining_time": "15:00:05", "throughput": 662.46, "total_tokens": 19200720} {"current_steps": 13975, "total_steps": 40000, "loss": 0.6604, "lr": 3.639522546585118e-05, "epoch": 0.4473145125152039, "percentage": 34.94, "elapsed_time": "8:03:05", "remaining_time": "14:59:38", "throughput": 662.66, "total_tokens": 19207696} {"current_steps": 13980, "total_steps": 40000, "loss": 0.5571, "lr": 3.6386486271003404e-05, "epoch": 0.4474745534856923, "percentage": 34.95, "elapsed_time": "8:03:07", "remaining_time": "14:59:12", "throughput": 662.87, "total_tokens": 19214816} {"current_steps": 13985, "total_steps": 40000, "loss": 0.7867, "lr": 3.6377745320216346e-05, "epoch": 0.44763459445618076, "percentage": 34.96, "elapsed_time": "8:03:09", "remaining_time": "14:58:45", "throughput": 663.06, "total_tokens": 19221616} {"current_steps": 13990, "total_steps": 40000, "loss": 0.7518, "lr": 3.636900261483798e-05, "epoch": 0.44779463542666925, "percentage": 34.98, "elapsed_time": "8:03:10", "remaining_time": "14:58:19", "throughput": 663.25, "total_tokens": 19228304} {"current_steps": 13995, "total_steps": 40000, "loss": 0.8082, "lr": 3.636025815621654e-05, "epoch": 0.4479546763971577, "percentage": 34.99, "elapsed_time": "8:03:12", "remaining_time": "14:57:53", "throughput": 663.45, "total_tokens": 19235120} {"current_steps": 14000, "total_steps": 40000, "loss": 0.8398, "lr": 3.635151194570054e-05, "epoch": 0.44811471736764613, "percentage": 35.0, "elapsed_time": "8:03:14", "remaining_time": "14:57:26", "throughput": 663.65, "total_tokens": 19242160} {"current_steps": 14000, "total_steps": 40000, "eval_loss": 0.7639604806900024, "epoch": 0.44811471736764613, "percentage": 35.0, "elapsed_time": "8:09:01", "remaining_time": "15:08:11", "throughput": 655.79, "total_tokens": 19242160} {"current_steps": 14005, "total_steps": 40000, "loss": 0.6861, "lr": 3.634276398463873e-05, "epoch": 0.44827475833813457, "percentage": 35.01, "elapsed_time": "8:09:05", "remaining_time": "15:07:48", "throughput": 655.95, "total_tokens": 19249008} {"current_steps": 14010, "total_steps": 40000, "loss": 0.6814, "lr": 3.633401427438018e-05, "epoch": 0.448434799308623, "percentage": 35.02, "elapsed_time": "8:09:07", "remaining_time": "15:07:21", "throughput": 656.15, "total_tokens": 19255968} {"current_steps": 14015, "total_steps": 40000, "loss": 0.5638, "lr": 3.63252628162742e-05, "epoch": 0.44859484027911145, "percentage": 35.04, "elapsed_time": "8:09:08", "remaining_time": "15:06:55", "throughput": 656.34, "total_tokens": 19262736} {"current_steps": 14020, "total_steps": 40000, "loss": 0.8252, "lr": 3.6316509611670364e-05, "epoch": 0.4487548812495999, "percentage": 35.05, "elapsed_time": "8:09:10", "remaining_time": "15:06:28", "throughput": 656.53, "total_tokens": 19269616} {"current_steps": 14025, "total_steps": 40000, "loss": 0.561, "lr": 3.630775466191854e-05, "epoch": 0.44891492222008833, "percentage": 35.06, "elapsed_time": "8:09:12", "remaining_time": "15:06:01", "throughput": 656.72, "total_tokens": 19276320} {"current_steps": 14030, "total_steps": 40000, "loss": 0.6824, "lr": 3.629899796836884e-05, "epoch": 0.44907496319057677, "percentage": 35.08, "elapsed_time": "8:09:14", "remaining_time": "15:05:35", "throughput": 656.91, "total_tokens": 19282976} {"current_steps": 14035, "total_steps": 40000, "loss": 0.6721, "lr": 3.6290239532371666e-05, "epoch": 0.4492350041610652, "percentage": 35.09, "elapsed_time": "8:09:15", "remaining_time": "15:05:08", "throughput": 657.1, "total_tokens": 19289840} {"current_steps": 14040, "total_steps": 40000, "loss": 0.7971, "lr": 3.628147935527767e-05, "epoch": 0.4493950451315537, "percentage": 35.1, "elapsed_time": "8:09:17", "remaining_time": "15:04:42", "throughput": 657.31, "total_tokens": 19297104} {"current_steps": 14045, "total_steps": 40000, "loss": 0.6019, "lr": 3.627271743843779e-05, "epoch": 0.44955508610204215, "percentage": 35.11, "elapsed_time": "8:09:19", "remaining_time": "15:04:15", "throughput": 657.51, "total_tokens": 19303936} {"current_steps": 14050, "total_steps": 40000, "loss": 0.6033, "lr": 3.626395378320321e-05, "epoch": 0.4497151270725306, "percentage": 35.12, "elapsed_time": "8:09:21", "remaining_time": "15:03:49", "throughput": 657.7, "total_tokens": 19310640} {"current_steps": 14055, "total_steps": 40000, "loss": 0.7764, "lr": 3.625518839092541e-05, "epoch": 0.449875168043019, "percentage": 35.14, "elapsed_time": "8:09:22", "remaining_time": "15:03:22", "throughput": 657.89, "total_tokens": 19317488} {"current_steps": 14060, "total_steps": 40000, "loss": 0.6697, "lr": 3.624642126295612e-05, "epoch": 0.45003520901350746, "percentage": 35.15, "elapsed_time": "8:09:24", "remaining_time": "15:02:55", "throughput": 658.08, "total_tokens": 19324224} {"current_steps": 14065, "total_steps": 40000, "loss": 0.7908, "lr": 3.6237652400647345e-05, "epoch": 0.4501952499839959, "percentage": 35.16, "elapsed_time": "8:09:26", "remaining_time": "15:02:29", "throughput": 658.28, "total_tokens": 19331216} {"current_steps": 14070, "total_steps": 40000, "loss": 0.683, "lr": 3.622888180535134e-05, "epoch": 0.45035529095448434, "percentage": 35.17, "elapsed_time": "8:09:27", "remaining_time": "15:02:03", "throughput": 658.49, "total_tokens": 19338528} {"current_steps": 14075, "total_steps": 40000, "loss": 0.6612, "lr": 3.6220109478420655e-05, "epoch": 0.4505153319249728, "percentage": 35.19, "elapsed_time": "8:09:29", "remaining_time": "15:01:36", "throughput": 658.68, "total_tokens": 19345328} {"current_steps": 14080, "total_steps": 40000, "loss": 0.7662, "lr": 3.6211335421208084e-05, "epoch": 0.4506753728954612, "percentage": 35.2, "elapsed_time": "8:09:31", "remaining_time": "15:01:10", "throughput": 658.87, "total_tokens": 19352080} {"current_steps": 14085, "total_steps": 40000, "loss": 0.7652, "lr": 3.62025596350667e-05, "epoch": 0.45083541386594966, "percentage": 35.21, "elapsed_time": "8:09:33", "remaining_time": "15:00:43", "throughput": 659.05, "total_tokens": 19358512} {"current_steps": 14090, "total_steps": 40000, "loss": 0.5434, "lr": 3.619378212134984e-05, "epoch": 0.4509954548364381, "percentage": 35.23, "elapsed_time": "8:09:34", "remaining_time": "15:00:17", "throughput": 659.26, "total_tokens": 19365744} {"current_steps": 14095, "total_steps": 40000, "loss": 0.6667, "lr": 3.618500288141111e-05, "epoch": 0.4511554958069266, "percentage": 35.24, "elapsed_time": "8:09:36", "remaining_time": "14:59:50", "throughput": 659.45, "total_tokens": 19372432} {"current_steps": 14100, "total_steps": 40000, "loss": 0.8226, "lr": 3.617622191660438e-05, "epoch": 0.45131553677741504, "percentage": 35.25, "elapsed_time": "8:09:38", "remaining_time": "14:59:24", "throughput": 659.66, "total_tokens": 19379664} {"current_steps": 14105, "total_steps": 40000, "loss": 0.7709, "lr": 3.616743922828377e-05, "epoch": 0.4514755777479035, "percentage": 35.26, "elapsed_time": "8:09:40", "remaining_time": "14:58:58", "throughput": 659.87, "total_tokens": 19386992} {"current_steps": 14110, "total_steps": 40000, "loss": 0.597, "lr": 3.615865481780371e-05, "epoch": 0.4516356187183919, "percentage": 35.27, "elapsed_time": "8:09:41", "remaining_time": "14:58:31", "throughput": 660.06, "total_tokens": 19393856} {"current_steps": 14115, "total_steps": 40000, "loss": 0.7979, "lr": 3.614986868651883e-05, "epoch": 0.45179565968888036, "percentage": 35.29, "elapsed_time": "8:09:43", "remaining_time": "14:58:05", "throughput": 660.26, "total_tokens": 19400656} {"current_steps": 14120, "total_steps": 40000, "loss": 0.5588, "lr": 3.614108083578409e-05, "epoch": 0.4519557006593688, "percentage": 35.3, "elapsed_time": "8:09:45", "remaining_time": "14:57:39", "throughput": 660.44, "total_tokens": 19407216} {"current_steps": 14125, "total_steps": 40000, "loss": 0.7313, "lr": 3.613229126695467e-05, "epoch": 0.45211574162985724, "percentage": 35.31, "elapsed_time": "8:09:47", "remaining_time": "14:57:12", "throughput": 660.64, "total_tokens": 19414384} {"current_steps": 14130, "total_steps": 40000, "loss": 0.7339, "lr": 3.612349998138605e-05, "epoch": 0.4522757826003457, "percentage": 35.33, "elapsed_time": "8:09:48", "remaining_time": "14:56:46", "throughput": 660.84, "total_tokens": 19421216} {"current_steps": 14135, "total_steps": 40000, "loss": 0.8069, "lr": 3.6114706980433946e-05, "epoch": 0.4524358235708341, "percentage": 35.34, "elapsed_time": "8:09:50", "remaining_time": "14:56:20", "throughput": 661.03, "total_tokens": 19428080} {"current_steps": 14140, "total_steps": 40000, "loss": 0.6912, "lr": 3.610591226545435e-05, "epoch": 0.45259586454132256, "percentage": 35.35, "elapsed_time": "8:09:52", "remaining_time": "14:55:54", "throughput": 661.24, "total_tokens": 19435312} {"current_steps": 14145, "total_steps": 40000, "loss": 0.8949, "lr": 3.6097115837803505e-05, "epoch": 0.452755905511811, "percentage": 35.36, "elapsed_time": "8:09:53", "remaining_time": "14:55:27", "throughput": 661.43, "total_tokens": 19442176} {"current_steps": 14150, "total_steps": 40000, "loss": 0.9976, "lr": 3.608831769883795e-05, "epoch": 0.4529159464822995, "percentage": 35.38, "elapsed_time": "8:09:55", "remaining_time": "14:55:01", "throughput": 661.65, "total_tokens": 19449584} {"current_steps": 14155, "total_steps": 40000, "loss": 0.7424, "lr": 3.607951784991446e-05, "epoch": 0.45307598745278793, "percentage": 35.39, "elapsed_time": "8:09:57", "remaining_time": "14:54:35", "throughput": 661.85, "total_tokens": 19456560} {"current_steps": 14160, "total_steps": 40000, "loss": 0.6849, "lr": 3.6070716292390085e-05, "epoch": 0.45323602842327637, "percentage": 35.4, "elapsed_time": "8:09:59", "remaining_time": "14:54:09", "throughput": 662.03, "total_tokens": 19463168} {"current_steps": 14165, "total_steps": 40000, "loss": 0.83, "lr": 3.606191302762213e-05, "epoch": 0.4533960693937648, "percentage": 35.41, "elapsed_time": "8:10:00", "remaining_time": "14:53:43", "throughput": 662.21, "total_tokens": 19469728} {"current_steps": 14170, "total_steps": 40000, "loss": 0.7138, "lr": 3.605310805696818e-05, "epoch": 0.45355611036425325, "percentage": 35.43, "elapsed_time": "8:10:02", "remaining_time": "14:53:17", "throughput": 662.4, "total_tokens": 19476384} {"current_steps": 14175, "total_steps": 40000, "loss": 0.7541, "lr": 3.6044301381786067e-05, "epoch": 0.4537161513347417, "percentage": 35.44, "elapsed_time": "8:10:04", "remaining_time": "14:52:50", "throughput": 662.6, "total_tokens": 19483248} {"current_steps": 14180, "total_steps": 40000, "loss": 0.7686, "lr": 3.6035493003433883e-05, "epoch": 0.45387619230523013, "percentage": 35.45, "elapsed_time": "8:10:06", "remaining_time": "14:52:24", "throughput": 662.79, "total_tokens": 19490176} {"current_steps": 14185, "total_steps": 40000, "loss": 0.8242, "lr": 3.6026682923269994e-05, "epoch": 0.45403623327571857, "percentage": 35.46, "elapsed_time": "8:10:07", "remaining_time": "14:51:58", "throughput": 662.99, "total_tokens": 19497104} {"current_steps": 14190, "total_steps": 40000, "loss": 0.655, "lr": 3.6017871142653034e-05, "epoch": 0.454196274246207, "percentage": 35.48, "elapsed_time": "8:10:09", "remaining_time": "14:51:32", "throughput": 663.2, "total_tokens": 19504416} {"current_steps": 14195, "total_steps": 40000, "loss": 0.6078, "lr": 3.600905766294189e-05, "epoch": 0.45435631521669545, "percentage": 35.49, "elapsed_time": "8:10:11", "remaining_time": "14:51:06", "throughput": 663.41, "total_tokens": 19511712} {"current_steps": 14200, "total_steps": 40000, "loss": 0.7095, "lr": 3.60002424854957e-05, "epoch": 0.45451635618718395, "percentage": 35.5, "elapsed_time": "8:10:13", "remaining_time": "14:50:40", "throughput": 663.61, "total_tokens": 19518832} {"current_steps": 14200, "total_steps": 40000, "eval_loss": 0.7628713846206665, "epoch": 0.45451635618718395, "percentage": 35.5, "elapsed_time": "8:16:01", "remaining_time": "15:01:13", "throughput": 655.85, "total_tokens": 19518832} {"current_steps": 14205, "total_steps": 40000, "loss": 0.566, "lr": 3.5991425611673876e-05, "epoch": 0.4546763971576724, "percentage": 35.51, "elapsed_time": "8:16:04", "remaining_time": "15:00:49", "throughput": 656.0, "total_tokens": 19525488} {"current_steps": 14210, "total_steps": 40000, "loss": 0.5852, "lr": 3.5982607042836105e-05, "epoch": 0.4548364381281608, "percentage": 35.52, "elapsed_time": "8:16:06", "remaining_time": "15:00:23", "throughput": 656.18, "total_tokens": 19532224} {"current_steps": 14215, "total_steps": 40000, "loss": 0.6306, "lr": 3.597378678034231e-05, "epoch": 0.45499647909864926, "percentage": 35.54, "elapsed_time": "8:16:08", "remaining_time": "14:59:57", "throughput": 656.37, "total_tokens": 19538992} {"current_steps": 14220, "total_steps": 40000, "loss": 0.8307, "lr": 3.596496482555269e-05, "epoch": 0.4551565200691377, "percentage": 35.55, "elapsed_time": "8:16:09", "remaining_time": "14:59:30", "throughput": 656.57, "total_tokens": 19546048} {"current_steps": 14225, "total_steps": 40000, "loss": 0.7402, "lr": 3.595614117982769e-05, "epoch": 0.45531656103962614, "percentage": 35.56, "elapsed_time": "8:16:11", "remaining_time": "14:59:04", "throughput": 656.77, "total_tokens": 19553008} {"current_steps": 14230, "total_steps": 40000, "loss": 0.6677, "lr": 3.594731584452805e-05, "epoch": 0.4554766020101146, "percentage": 35.58, "elapsed_time": "8:16:13", "remaining_time": "14:58:38", "throughput": 656.97, "total_tokens": 19560160} {"current_steps": 14235, "total_steps": 40000, "loss": 0.8915, "lr": 3.593848882101472e-05, "epoch": 0.455636642980603, "percentage": 35.59, "elapsed_time": "8:16:15", "remaining_time": "14:58:12", "throughput": 657.16, "total_tokens": 19567056} {"current_steps": 14240, "total_steps": 40000, "loss": 0.829, "lr": 3.592966011064896e-05, "epoch": 0.45579668395109146, "percentage": 35.6, "elapsed_time": "8:16:16", "remaining_time": "14:57:45", "throughput": 657.36, "total_tokens": 19574128} {"current_steps": 14245, "total_steps": 40000, "loss": 0.6556, "lr": 3.592082971479226e-05, "epoch": 0.4559567249215799, "percentage": 35.61, "elapsed_time": "8:16:18", "remaining_time": "14:57:19", "throughput": 657.57, "total_tokens": 19581520} {"current_steps": 14250, "total_steps": 40000, "loss": 0.6738, "lr": 3.5911997634806385e-05, "epoch": 0.45611676589206834, "percentage": 35.62, "elapsed_time": "8:16:20", "remaining_time": "14:56:53", "throughput": 657.77, "total_tokens": 19588432} {"current_steps": 14255, "total_steps": 40000, "loss": 1.1625, "lr": 3.5903163872053336e-05, "epoch": 0.45627680686255684, "percentage": 35.64, "elapsed_time": "8:16:22", "remaining_time": "14:56:27", "throughput": 657.96, "total_tokens": 19595328} {"current_steps": 14260, "total_steps": 40000, "loss": 0.7781, "lr": 3.58943284278954e-05, "epoch": 0.4564368478330453, "percentage": 35.65, "elapsed_time": "8:16:23", "remaining_time": "14:56:01", "throughput": 658.14, "total_tokens": 19601824} {"current_steps": 14265, "total_steps": 40000, "loss": 0.7124, "lr": 3.588549130369512e-05, "epoch": 0.4565968888035337, "percentage": 35.66, "elapsed_time": "8:16:25", "remaining_time": "14:55:34", "throughput": 658.34, "total_tokens": 19608976} {"current_steps": 14270, "total_steps": 40000, "loss": 0.6637, "lr": 3.5876652500815274e-05, "epoch": 0.45675692977402216, "percentage": 35.68, "elapsed_time": "8:16:27", "remaining_time": "14:55:08", "throughput": 658.54, "total_tokens": 19615984} {"current_steps": 14275, "total_steps": 40000, "loss": 1.0256, "lr": 3.586781202061894e-05, "epoch": 0.4569169707445106, "percentage": 35.69, "elapsed_time": "8:16:28", "remaining_time": "14:54:42", "throughput": 658.73, "total_tokens": 19622816} {"current_steps": 14280, "total_steps": 40000, "loss": 0.6387, "lr": 3.585896986446942e-05, "epoch": 0.45707701171499904, "percentage": 35.7, "elapsed_time": "8:16:30", "remaining_time": "14:54:16", "throughput": 658.91, "total_tokens": 19629424} {"current_steps": 14285, "total_steps": 40000, "loss": 0.8843, "lr": 3.585012603373028e-05, "epoch": 0.4572370526854875, "percentage": 35.71, "elapsed_time": "8:16:32", "remaining_time": "14:53:50", "throughput": 659.1, "total_tokens": 19636160} {"current_steps": 14290, "total_steps": 40000, "loss": 0.7538, "lr": 3.584128052976535e-05, "epoch": 0.4573970936559759, "percentage": 35.73, "elapsed_time": "8:16:34", "remaining_time": "14:53:24", "throughput": 659.28, "total_tokens": 19642784} {"current_steps": 14295, "total_steps": 40000, "loss": 0.7571, "lr": 3.5832433353938724e-05, "epoch": 0.45755713462646436, "percentage": 35.74, "elapsed_time": "8:16:35", "remaining_time": "14:52:58", "throughput": 659.48, "total_tokens": 19649664} {"current_steps": 14300, "total_steps": 40000, "loss": 0.7552, "lr": 3.5823584507614746e-05, "epoch": 0.4577171755969528, "percentage": 35.75, "elapsed_time": "8:16:37", "remaining_time": "14:52:32", "throughput": 659.67, "total_tokens": 19656528} {"current_steps": 14305, "total_steps": 40000, "loss": 0.6769, "lr": 3.581473399215802e-05, "epoch": 0.4578772165674413, "percentage": 35.76, "elapsed_time": "8:16:39", "remaining_time": "14:52:06", "throughput": 659.87, "total_tokens": 19663584} {"current_steps": 14310, "total_steps": 40000, "loss": 0.8201, "lr": 3.580588180893341e-05, "epoch": 0.45803725753792973, "percentage": 35.77, "elapsed_time": "8:16:41", "remaining_time": "14:51:40", "throughput": 660.06, "total_tokens": 19670640} {"current_steps": 14315, "total_steps": 40000, "loss": 0.8265, "lr": 3.579702795930602e-05, "epoch": 0.45819729850841817, "percentage": 35.79, "elapsed_time": "8:16:42", "remaining_time": "14:51:14", "throughput": 660.27, "total_tokens": 19677840} {"current_steps": 14320, "total_steps": 40000, "loss": 0.6629, "lr": 3.578817244464125e-05, "epoch": 0.4583573394789066, "percentage": 35.8, "elapsed_time": "8:16:44", "remaining_time": "14:50:48", "throughput": 660.46, "total_tokens": 19684880} {"current_steps": 14325, "total_steps": 40000, "loss": 0.6655, "lr": 3.577931526630471e-05, "epoch": 0.45851738044939505, "percentage": 35.81, "elapsed_time": "8:16:46", "remaining_time": "14:50:22", "throughput": 660.68, "total_tokens": 19692400} {"current_steps": 14330, "total_steps": 40000, "loss": 0.6184, "lr": 3.577045642566229e-05, "epoch": 0.4586774214198835, "percentage": 35.83, "elapsed_time": "8:16:48", "remaining_time": "14:49:56", "throughput": 660.86, "total_tokens": 19698976} {"current_steps": 14335, "total_steps": 40000, "loss": 0.7115, "lr": 3.576159592408014e-05, "epoch": 0.45883746239037193, "percentage": 35.84, "elapsed_time": "8:16:49", "remaining_time": "14:49:30", "throughput": 661.05, "total_tokens": 19705872} {"current_steps": 14340, "total_steps": 40000, "loss": 0.7995, "lr": 3.575273376292466e-05, "epoch": 0.45899750336086037, "percentage": 35.85, "elapsed_time": "8:16:51", "remaining_time": "14:49:04", "throughput": 661.23, "total_tokens": 19712240} {"current_steps": 14345, "total_steps": 40000, "loss": 0.6845, "lr": 3.574386994356251e-05, "epoch": 0.4591575443313488, "percentage": 35.86, "elapsed_time": "8:16:53", "remaining_time": "14:48:38", "throughput": 661.42, "total_tokens": 19719152} {"current_steps": 14350, "total_steps": 40000, "loss": 0.9655, "lr": 3.573500446736059e-05, "epoch": 0.45931758530183725, "percentage": 35.88, "elapsed_time": "8:16:55", "remaining_time": "14:48:13", "throughput": 661.6, "total_tokens": 19725600} {"current_steps": 14355, "total_steps": 40000, "loss": 0.7567, "lr": 3.5726137335686094e-05, "epoch": 0.4594776262723257, "percentage": 35.89, "elapsed_time": "8:16:56", "remaining_time": "14:47:47", "throughput": 661.81, "total_tokens": 19732976} {"current_steps": 14360, "total_steps": 40000, "loss": 0.675, "lr": 3.571726854990642e-05, "epoch": 0.4596376672428142, "percentage": 35.9, "elapsed_time": "8:16:58", "remaining_time": "14:47:21", "throughput": 662.01, "total_tokens": 19740128} {"current_steps": 14365, "total_steps": 40000, "loss": 0.775, "lr": 3.570839811138925e-05, "epoch": 0.4597977082133026, "percentage": 35.91, "elapsed_time": "8:17:00", "remaining_time": "14:46:55", "throughput": 662.2, "total_tokens": 19746912} {"current_steps": 14370, "total_steps": 40000, "loss": 1.1097, "lr": 3.569952602150252e-05, "epoch": 0.45995774918379106, "percentage": 35.93, "elapsed_time": "8:17:01", "remaining_time": "14:46:29", "throughput": 662.39, "total_tokens": 19753904} {"current_steps": 14375, "total_steps": 40000, "loss": 0.5961, "lr": 3.569065228161442e-05, "epoch": 0.4601177901542795, "percentage": 35.94, "elapsed_time": "8:17:03", "remaining_time": "14:46:03", "throughput": 662.58, "total_tokens": 19760688} {"current_steps": 14380, "total_steps": 40000, "loss": 0.8385, "lr": 3.5681776893093395e-05, "epoch": 0.46027783112476794, "percentage": 35.95, "elapsed_time": "8:17:05", "remaining_time": "14:45:38", "throughput": 662.78, "total_tokens": 19767776} {"current_steps": 14385, "total_steps": 40000, "loss": 0.934, "lr": 3.5672899857308134e-05, "epoch": 0.4604378720952564, "percentage": 35.96, "elapsed_time": "8:17:07", "remaining_time": "14:45:12", "throughput": 662.96, "total_tokens": 19774336} {"current_steps": 14390, "total_steps": 40000, "loss": 0.8979, "lr": 3.566402117562759e-05, "epoch": 0.4605979130657448, "percentage": 35.98, "elapsed_time": "8:17:08", "remaining_time": "14:44:46", "throughput": 663.17, "total_tokens": 19781568} {"current_steps": 14395, "total_steps": 40000, "loss": 0.8691, "lr": 3.565514084942097e-05, "epoch": 0.46075795403623326, "percentage": 35.99, "elapsed_time": "8:17:10", "remaining_time": "14:44:21", "throughput": 663.38, "total_tokens": 19788912} {"current_steps": 14400, "total_steps": 40000, "loss": 0.7228, "lr": 3.564625888005773e-05, "epoch": 0.4609179950067217, "percentage": 36.0, "elapsed_time": "8:17:12", "remaining_time": "14:43:55", "throughput": 663.57, "total_tokens": 19795920} {"current_steps": 14400, "total_steps": 40000, "eval_loss": 0.762434184551239, "epoch": 0.4609179950067217, "percentage": 36.0, "elapsed_time": "8:23:00", "remaining_time": "14:54:14", "throughput": 655.92, "total_tokens": 19795920} {"current_steps": 14405, "total_steps": 40000, "loss": 0.6987, "lr": 3.563737526890759e-05, "epoch": 0.46107803597721014, "percentage": 36.01, "elapsed_time": "8:23:05", "remaining_time": "14:53:53", "throughput": 656.04, "total_tokens": 19802704} {"current_steps": 14410, "total_steps": 40000, "loss": 0.7754, "lr": 3.562849001734049e-05, "epoch": 0.4612380769476986, "percentage": 36.02, "elapsed_time": "8:23:06", "remaining_time": "14:53:27", "throughput": 656.23, "total_tokens": 19809552} {"current_steps": 14415, "total_steps": 40000, "loss": 0.805, "lr": 3.561960312672667e-05, "epoch": 0.4613981179181871, "percentage": 36.04, "elapsed_time": "8:23:08", "remaining_time": "14:53:01", "throughput": 656.41, "total_tokens": 19816016} {"current_steps": 14420, "total_steps": 40000, "loss": 0.707, "lr": 3.5610714598436596e-05, "epoch": 0.4615581588886755, "percentage": 36.05, "elapsed_time": "8:23:10", "remaining_time": "14:52:35", "throughput": 656.6, "total_tokens": 19822928} {"current_steps": 14425, "total_steps": 40000, "loss": 0.6181, "lr": 3.5601824433840986e-05, "epoch": 0.46171819985916396, "percentage": 36.06, "elapsed_time": "8:23:12", "remaining_time": "14:52:09", "throughput": 656.78, "total_tokens": 19829584} {"current_steps": 14430, "total_steps": 40000, "loss": 0.8727, "lr": 3.559293263431082e-05, "epoch": 0.4618782408296524, "percentage": 36.08, "elapsed_time": "8:23:13", "remaining_time": "14:51:43", "throughput": 656.96, "total_tokens": 19836256} {"current_steps": 14435, "total_steps": 40000, "loss": 0.716, "lr": 3.558403920121732e-05, "epoch": 0.46203828180014084, "percentage": 36.09, "elapsed_time": "8:23:15", "remaining_time": "14:51:17", "throughput": 657.15, "total_tokens": 19843040} {"current_steps": 14440, "total_steps": 40000, "loss": 0.6854, "lr": 3.557514413593197e-05, "epoch": 0.4621983227706293, "percentage": 36.1, "elapsed_time": "8:23:17", "remaining_time": "14:50:51", "throughput": 657.34, "total_tokens": 19849856} {"current_steps": 14445, "total_steps": 40000, "loss": 0.7526, "lr": 3.55662474398265e-05, "epoch": 0.4623583637411177, "percentage": 36.11, "elapsed_time": "8:23:19", "remaining_time": "14:50:25", "throughput": 657.53, "total_tokens": 19856832} {"current_steps": 14450, "total_steps": 40000, "loss": 0.6558, "lr": 3.555734911427288e-05, "epoch": 0.46251840471160616, "percentage": 36.12, "elapsed_time": "8:23:20", "remaining_time": "14:50:00", "throughput": 657.72, "total_tokens": 19863568} {"current_steps": 14455, "total_steps": 40000, "loss": 0.6149, "lr": 3.5548449160643363e-05, "epoch": 0.4626784456820946, "percentage": 36.14, "elapsed_time": "8:23:22", "remaining_time": "14:49:34", "throughput": 657.91, "total_tokens": 19870448} {"current_steps": 14460, "total_steps": 40000, "loss": 0.831, "lr": 3.553954758031043e-05, "epoch": 0.46283848665258304, "percentage": 36.15, "elapsed_time": "8:23:24", "remaining_time": "14:49:08", "throughput": 658.1, "total_tokens": 19877392} {"current_steps": 14465, "total_steps": 40000, "loss": 0.7705, "lr": 3.5530644374646815e-05, "epoch": 0.46299852762307153, "percentage": 36.16, "elapsed_time": "8:23:26", "remaining_time": "14:48:42", "throughput": 658.28, "total_tokens": 19884176} {"current_steps": 14470, "total_steps": 40000, "loss": 0.5879, "lr": 3.552173954502549e-05, "epoch": 0.46315856859355997, "percentage": 36.18, "elapsed_time": "8:23:27", "remaining_time": "14:48:16", "throughput": 658.47, "total_tokens": 19890896} {"current_steps": 14475, "total_steps": 40000, "loss": 0.7765, "lr": 3.55128330928197e-05, "epoch": 0.4633186095640484, "percentage": 36.19, "elapsed_time": "8:23:29", "remaining_time": "14:47:50", "throughput": 658.65, "total_tokens": 19897536} {"current_steps": 14480, "total_steps": 40000, "loss": 0.7099, "lr": 3.550392501940294e-05, "epoch": 0.46347865053453685, "percentage": 36.2, "elapsed_time": "8:23:31", "remaining_time": "14:47:25", "throughput": 658.83, "total_tokens": 19904144} {"current_steps": 14485, "total_steps": 40000, "loss": 0.8883, "lr": 3.5495015326148945e-05, "epoch": 0.4636386915050253, "percentage": 36.21, "elapsed_time": "8:23:32", "remaining_time": "14:46:59", "throughput": 659.02, "total_tokens": 19911040} {"current_steps": 14490, "total_steps": 40000, "loss": 0.6573, "lr": 3.548610401443169e-05, "epoch": 0.46379873247551373, "percentage": 36.23, "elapsed_time": "8:23:34", "remaining_time": "14:46:33", "throughput": 659.21, "total_tokens": 19917936} {"current_steps": 14495, "total_steps": 40000, "loss": 0.6873, "lr": 3.547719108562543e-05, "epoch": 0.46395877344600217, "percentage": 36.24, "elapsed_time": "8:23:36", "remaining_time": "14:46:08", "throughput": 659.4, "total_tokens": 19924624} {"current_steps": 14500, "total_steps": 40000, "loss": 0.7677, "lr": 3.546827654110464e-05, "epoch": 0.4641188144164906, "percentage": 36.25, "elapsed_time": "8:23:38", "remaining_time": "14:45:42", "throughput": 659.58, "total_tokens": 19931216} {"current_steps": 14505, "total_steps": 40000, "loss": 0.6323, "lr": 3.545936038224405e-05, "epoch": 0.46427885538697905, "percentage": 36.26, "elapsed_time": "8:23:39", "remaining_time": "14:45:16", "throughput": 659.77, "total_tokens": 19938064} {"current_steps": 14510, "total_steps": 40000, "loss": 0.8719, "lr": 3.545044261041864e-05, "epoch": 0.4644388963574675, "percentage": 36.27, "elapsed_time": "8:23:41", "remaining_time": "14:44:50", "throughput": 659.95, "total_tokens": 19944864} {"current_steps": 14515, "total_steps": 40000, "loss": 0.7023, "lr": 3.5441523227003657e-05, "epoch": 0.46459893732795593, "percentage": 36.29, "elapsed_time": "8:23:43", "remaining_time": "14:44:25", "throughput": 660.16, "total_tokens": 19952160} {"current_steps": 14520, "total_steps": 40000, "loss": 0.7521, "lr": 3.543260223337459e-05, "epoch": 0.4647589782984444, "percentage": 36.3, "elapsed_time": "8:23:45", "remaining_time": "14:43:59", "throughput": 660.34, "total_tokens": 19958896} {"current_steps": 14525, "total_steps": 40000, "loss": 0.6762, "lr": 3.542367963090714e-05, "epoch": 0.46491901926893286, "percentage": 36.31, "elapsed_time": "8:23:46", "remaining_time": "14:43:34", "throughput": 660.54, "total_tokens": 19965936} {"current_steps": 14530, "total_steps": 40000, "loss": 0.8621, "lr": 3.5414755420977295e-05, "epoch": 0.4650790602394213, "percentage": 36.33, "elapsed_time": "8:23:48", "remaining_time": "14:43:08", "throughput": 660.73, "total_tokens": 19972896} {"current_steps": 14535, "total_steps": 40000, "loss": 0.7125, "lr": 3.54058296049613e-05, "epoch": 0.46523910120990974, "percentage": 36.34, "elapsed_time": "8:23:50", "remaining_time": "14:42:42", "throughput": 660.93, "total_tokens": 19980128} {"current_steps": 14540, "total_steps": 40000, "loss": 0.7069, "lr": 3.53969021842356e-05, "epoch": 0.4653991421803982, "percentage": 36.35, "elapsed_time": "8:23:52", "remaining_time": "14:42:17", "throughput": 661.12, "total_tokens": 19987024} {"current_steps": 14545, "total_steps": 40000, "loss": 0.6383, "lr": 3.5387973160176926e-05, "epoch": 0.4655591831508866, "percentage": 36.36, "elapsed_time": "8:23:53", "remaining_time": "14:41:51", "throughput": 661.31, "total_tokens": 19993872} {"current_steps": 14550, "total_steps": 40000, "loss": 0.5944, "lr": 3.537904253416224e-05, "epoch": 0.46571922412137506, "percentage": 36.38, "elapsed_time": "8:23:55", "remaining_time": "14:41:26", "throughput": 661.5, "total_tokens": 20000800} {"current_steps": 14555, "total_steps": 40000, "loss": 1.1344, "lr": 3.537011030756878e-05, "epoch": 0.4658792650918635, "percentage": 36.39, "elapsed_time": "8:23:57", "remaining_time": "14:41:01", "throughput": 661.79, "total_tokens": 20011056} {"current_steps": 14560, "total_steps": 40000, "loss": 0.7924, "lr": 3.536117648177399e-05, "epoch": 0.46603930606235194, "percentage": 36.4, "elapsed_time": "8:23:59", "remaining_time": "14:40:35", "throughput": 661.99, "total_tokens": 20018096} {"current_steps": 14565, "total_steps": 40000, "loss": 0.8938, "lr": 3.535224105815558e-05, "epoch": 0.4661993470328404, "percentage": 36.41, "elapsed_time": "8:24:01", "remaining_time": "14:40:10", "throughput": 662.17, "total_tokens": 20024880} {"current_steps": 14570, "total_steps": 40000, "loss": 0.8137, "lr": 3.5343304038091494e-05, "epoch": 0.4663593880033289, "percentage": 36.43, "elapsed_time": "8:24:02", "remaining_time": "14:39:44", "throughput": 662.36, "total_tokens": 20031696} {"current_steps": 14575, "total_steps": 40000, "loss": 0.6869, "lr": 3.5334365422959955e-05, "epoch": 0.4665194289738173, "percentage": 36.44, "elapsed_time": "8:24:04", "remaining_time": "14:39:19", "throughput": 662.55, "total_tokens": 20038576} {"current_steps": 14580, "total_steps": 40000, "loss": 0.9055, "lr": 3.5325425214139396e-05, "epoch": 0.46667946994430576, "percentage": 36.45, "elapsed_time": "8:24:06", "remaining_time": "14:38:53", "throughput": 662.74, "total_tokens": 20045376} {"current_steps": 14585, "total_steps": 40000, "loss": 0.7697, "lr": 3.531648341300851e-05, "epoch": 0.4668395109147942, "percentage": 36.46, "elapsed_time": "8:24:08", "remaining_time": "14:38:28", "throughput": 662.94, "total_tokens": 20052544} {"current_steps": 14590, "total_steps": 40000, "loss": 0.7834, "lr": 3.530754002094623e-05, "epoch": 0.46699955188528264, "percentage": 36.48, "elapsed_time": "8:24:09", "remaining_time": "14:38:03", "throughput": 663.12, "total_tokens": 20059344} {"current_steps": 14595, "total_steps": 40000, "loss": 0.6802, "lr": 3.529859503933175e-05, "epoch": 0.4671595928557711, "percentage": 36.49, "elapsed_time": "8:24:11", "remaining_time": "14:37:37", "throughput": 663.32, "total_tokens": 20066384} {"current_steps": 14600, "total_steps": 40000, "loss": 0.4926, "lr": 3.52896484695445e-05, "epoch": 0.4673196338262595, "percentage": 36.5, "elapsed_time": "8:24:13", "remaining_time": "14:37:12", "throughput": 663.51, "total_tokens": 20073168} {"current_steps": 14600, "total_steps": 40000, "eval_loss": 0.7622380256652832, "epoch": 0.4673196338262595, "percentage": 36.5, "elapsed_time": "8:30:00", "remaining_time": "14:47:16", "throughput": 655.97, "total_tokens": 20073168} {"current_steps": 14605, "total_steps": 40000, "loss": 0.879, "lr": 3.528070031296414e-05, "epoch": 0.46747967479674796, "percentage": 36.51, "elapsed_time": "8:30:04", "remaining_time": "14:46:54", "throughput": 656.13, "total_tokens": 20080384} {"current_steps": 14610, "total_steps": 40000, "loss": 0.9214, "lr": 3.5271750570970605e-05, "epoch": 0.4676397157672364, "percentage": 36.52, "elapsed_time": "8:30:06", "remaining_time": "14:46:28", "throughput": 656.32, "total_tokens": 20087568} {"current_steps": 14615, "total_steps": 40000, "loss": 0.6962, "lr": 3.526279924494405e-05, "epoch": 0.46779975673772484, "percentage": 36.54, "elapsed_time": "8:30:07", "remaining_time": "14:46:03", "throughput": 656.52, "total_tokens": 20094576} {"current_steps": 14620, "total_steps": 40000, "loss": 0.7285, "lr": 3.5253846336264874e-05, "epoch": 0.4679597977082133, "percentage": 36.55, "elapsed_time": "8:30:09", "remaining_time": "14:45:37", "throughput": 656.7, "total_tokens": 20101408} {"current_steps": 14625, "total_steps": 40000, "loss": 0.6907, "lr": 3.5244891846313736e-05, "epoch": 0.46811983867870177, "percentage": 36.56, "elapsed_time": "8:30:11", "remaining_time": "14:45:12", "throughput": 656.88, "total_tokens": 20108080} {"current_steps": 14630, "total_steps": 40000, "loss": 0.6654, "lr": 3.5235935776471527e-05, "epoch": 0.4682798796491902, "percentage": 36.58, "elapsed_time": "8:30:13", "remaining_time": "14:44:46", "throughput": 657.06, "total_tokens": 20114736} {"current_steps": 14635, "total_steps": 40000, "loss": 0.8689, "lr": 3.522697812811939e-05, "epoch": 0.46843992061967865, "percentage": 36.59, "elapsed_time": "8:30:14", "remaining_time": "14:44:20", "throughput": 657.26, "total_tokens": 20121760} {"current_steps": 14640, "total_steps": 40000, "loss": 0.9571, "lr": 3.521801890263871e-05, "epoch": 0.4685999615901671, "percentage": 36.6, "elapsed_time": "8:30:16", "remaining_time": "14:43:55", "throughput": 657.43, "total_tokens": 20128384} {"current_steps": 14645, "total_steps": 40000, "loss": 0.7061, "lr": 3.5209058101411114e-05, "epoch": 0.46876000256065553, "percentage": 36.61, "elapsed_time": "8:30:18", "remaining_time": "14:43:29", "throughput": 657.63, "total_tokens": 20135616} {"current_steps": 14650, "total_steps": 40000, "loss": 0.6003, "lr": 3.520009572581845e-05, "epoch": 0.46892004353114397, "percentage": 36.62, "elapsed_time": "8:30:20", "remaining_time": "14:43:04", "throughput": 657.82, "total_tokens": 20142496} {"current_steps": 14655, "total_steps": 40000, "loss": 0.6267, "lr": 3.519113177724285e-05, "epoch": 0.4690800845016324, "percentage": 36.64, "elapsed_time": "8:30:21", "remaining_time": "14:42:38", "throughput": 658.01, "total_tokens": 20149552} {"current_steps": 14660, "total_steps": 40000, "loss": 0.7528, "lr": 3.5182166257066656e-05, "epoch": 0.46924012547212085, "percentage": 36.65, "elapsed_time": "8:30:23", "remaining_time": "14:42:13", "throughput": 658.21, "total_tokens": 20156768} {"current_steps": 14665, "total_steps": 40000, "loss": 0.6085, "lr": 3.517319916667247e-05, "epoch": 0.4694001664426093, "percentage": 36.66, "elapsed_time": "8:30:25", "remaining_time": "14:41:47", "throughput": 658.39, "total_tokens": 20163440} {"current_steps": 14670, "total_steps": 40000, "loss": 0.7309, "lr": 3.516423050744313e-05, "epoch": 0.46956020741309773, "percentage": 36.68, "elapsed_time": "8:30:26", "remaining_time": "14:41:22", "throughput": 658.58, "total_tokens": 20170336} {"current_steps": 14675, "total_steps": 40000, "loss": 0.6813, "lr": 3.5155260280761704e-05, "epoch": 0.4697202483835862, "percentage": 36.69, "elapsed_time": "8:30:28", "remaining_time": "14:40:56", "throughput": 658.76, "total_tokens": 20177072} {"current_steps": 14680, "total_steps": 40000, "loss": 0.7149, "lr": 3.514628848801154e-05, "epoch": 0.46988028935407467, "percentage": 36.7, "elapsed_time": "8:30:30", "remaining_time": "14:40:31", "throughput": 658.95, "total_tokens": 20183872} {"current_steps": 14685, "total_steps": 40000, "loss": 0.7081, "lr": 3.5137315130576174e-05, "epoch": 0.4700403303245631, "percentage": 36.71, "elapsed_time": "8:30:32", "remaining_time": "14:40:05", "throughput": 659.15, "total_tokens": 20191104} {"current_steps": 14690, "total_steps": 40000, "loss": 0.7108, "lr": 3.512834020983942e-05, "epoch": 0.47020037129505154, "percentage": 36.73, "elapsed_time": "8:30:33", "remaining_time": "14:39:40", "throughput": 659.33, "total_tokens": 20197776} {"current_steps": 14695, "total_steps": 40000, "loss": 0.7591, "lr": 3.5119363727185334e-05, "epoch": 0.47036041226554, "percentage": 36.74, "elapsed_time": "8:30:35", "remaining_time": "14:39:15", "throughput": 659.51, "total_tokens": 20204416} {"current_steps": 14700, "total_steps": 40000, "loss": 0.752, "lr": 3.511038568399819e-05, "epoch": 0.4705204532360284, "percentage": 36.75, "elapsed_time": "8:30:37", "remaining_time": "14:38:49", "throughput": 659.7, "total_tokens": 20211520} {"current_steps": 14705, "total_steps": 40000, "loss": 0.7776, "lr": 3.510140608166251e-05, "epoch": 0.47068049420651686, "percentage": 36.76, "elapsed_time": "8:30:39", "remaining_time": "14:38:24", "throughput": 659.9, "total_tokens": 20218864} {"current_steps": 14710, "total_steps": 40000, "loss": 0.6862, "lr": 3.509242492156308e-05, "epoch": 0.4708405351770053, "percentage": 36.78, "elapsed_time": "8:30:40", "remaining_time": "14:37:58", "throughput": 660.09, "total_tokens": 20225680} {"current_steps": 14715, "total_steps": 40000, "loss": 0.5765, "lr": 3.5083442205084896e-05, "epoch": 0.47100057614749374, "percentage": 36.79, "elapsed_time": "8:30:42", "remaining_time": "14:37:33", "throughput": 660.26, "total_tokens": 20232144} {"current_steps": 14720, "total_steps": 40000, "loss": 0.5806, "lr": 3.507445793361321e-05, "epoch": 0.4711606171179822, "percentage": 36.8, "elapsed_time": "8:30:44", "remaining_time": "14:37:08", "throughput": 660.45, "total_tokens": 20238928} {"current_steps": 14725, "total_steps": 40000, "loss": 0.5799, "lr": 3.5065472108533505e-05, "epoch": 0.4713206580884706, "percentage": 36.81, "elapsed_time": "8:30:46", "remaining_time": "14:36:43", "throughput": 660.63, "total_tokens": 20245840} {"current_steps": 14730, "total_steps": 40000, "loss": 0.8025, "lr": 3.5056484731231504e-05, "epoch": 0.4714806990589591, "percentage": 36.83, "elapsed_time": "8:30:47", "remaining_time": "14:36:17", "throughput": 660.82, "total_tokens": 20252768} {"current_steps": 14735, "total_steps": 40000, "loss": 1.0019, "lr": 3.504749580309319e-05, "epoch": 0.47164074002944756, "percentage": 36.84, "elapsed_time": "8:30:49", "remaining_time": "14:35:52", "throughput": 661.02, "total_tokens": 20259984} {"current_steps": 14740, "total_steps": 40000, "loss": 0.7547, "lr": 3.5038505325504753e-05, "epoch": 0.471800780999936, "percentage": 36.85, "elapsed_time": "8:30:51", "remaining_time": "14:35:27", "throughput": 661.21, "total_tokens": 20266816} {"current_steps": 14745, "total_steps": 40000, "loss": 0.6107, "lr": 3.502951329985264e-05, "epoch": 0.47196082197042444, "percentage": 36.86, "elapsed_time": "8:30:52", "remaining_time": "14:35:01", "throughput": 661.39, "total_tokens": 20273584} {"current_steps": 14750, "total_steps": 40000, "loss": 0.7466, "lr": 3.502051972752354e-05, "epoch": 0.4721208629409129, "percentage": 36.88, "elapsed_time": "8:30:54", "remaining_time": "14:34:36", "throughput": 661.58, "total_tokens": 20280464} {"current_steps": 14755, "total_steps": 40000, "loss": 0.7291, "lr": 3.5011524609904374e-05, "epoch": 0.4722809039114013, "percentage": 36.89, "elapsed_time": "8:30:56", "remaining_time": "14:34:11", "throughput": 661.77, "total_tokens": 20287488} {"current_steps": 14760, "total_steps": 40000, "loss": 0.7977, "lr": 3.50025279483823e-05, "epoch": 0.47244094488188976, "percentage": 36.9, "elapsed_time": "8:30:58", "remaining_time": "14:33:46", "throughput": 661.96, "total_tokens": 20294624} {"current_steps": 14765, "total_steps": 40000, "loss": 0.8335, "lr": 3.499352974434472e-05, "epoch": 0.4726009858523782, "percentage": 36.91, "elapsed_time": "8:30:59", "remaining_time": "14:33:21", "throughput": 662.16, "total_tokens": 20301632} {"current_steps": 14770, "total_steps": 40000, "loss": 0.7809, "lr": 3.498452999917926e-05, "epoch": 0.47276102682286664, "percentage": 36.93, "elapsed_time": "8:31:01", "remaining_time": "14:32:56", "throughput": 662.34, "total_tokens": 20308432} {"current_steps": 14775, "total_steps": 40000, "loss": 0.7942, "lr": 3.4975528714273795e-05, "epoch": 0.4729210677933551, "percentage": 36.94, "elapsed_time": "8:31:03", "remaining_time": "14:32:30", "throughput": 662.52, "total_tokens": 20315248} {"current_steps": 14780, "total_steps": 40000, "loss": 0.8994, "lr": 3.4966525891016454e-05, "epoch": 0.4730811087638435, "percentage": 36.95, "elapsed_time": "8:31:05", "remaining_time": "14:32:05", "throughput": 662.71, "total_tokens": 20322096} {"current_steps": 14785, "total_steps": 40000, "loss": 0.6463, "lr": 3.495752153079557e-05, "epoch": 0.473241149734332, "percentage": 36.96, "elapsed_time": "8:31:06", "remaining_time": "14:31:40", "throughput": 662.89, "total_tokens": 20328672} {"current_steps": 14790, "total_steps": 40000, "loss": 0.7826, "lr": 3.494851563499974e-05, "epoch": 0.47340119070482045, "percentage": 36.98, "elapsed_time": "8:31:08", "remaining_time": "14:31:15", "throughput": 663.07, "total_tokens": 20335296} {"current_steps": 14795, "total_steps": 40000, "loss": 0.8312, "lr": 3.493950820501777e-05, "epoch": 0.4735612316753089, "percentage": 36.99, "elapsed_time": "8:31:10", "remaining_time": "14:30:50", "throughput": 663.24, "total_tokens": 20341840} {"current_steps": 14800, "total_steps": 40000, "loss": 0.4827, "lr": 3.493049924223872e-05, "epoch": 0.47372127264579733, "percentage": 37.0, "elapsed_time": "8:31:12", "remaining_time": "14:30:25", "throughput": 663.44, "total_tokens": 20349056} {"current_steps": 14800, "total_steps": 40000, "eval_loss": 0.7613592147827148, "epoch": 0.47372127264579733, "percentage": 37.0, "elapsed_time": "8:36:59", "remaining_time": "14:40:17", "throughput": 656.0, "total_tokens": 20349056} {"current_steps": 14805, "total_steps": 40000, "loss": 0.7283, "lr": 3.49214887480519e-05, "epoch": 0.47388131361628577, "percentage": 37.01, "elapsed_time": "8:37:03", "remaining_time": "14:39:55", "throughput": 656.14, "total_tokens": 20355936} {"current_steps": 14810, "total_steps": 40000, "loss": 0.7389, "lr": 3.4912476723846834e-05, "epoch": 0.4740413545867742, "percentage": 37.03, "elapsed_time": "8:37:05", "remaining_time": "14:39:30", "throughput": 656.34, "total_tokens": 20363136} {"current_steps": 14815, "total_steps": 40000, "loss": 0.6342, "lr": 3.490346317101328e-05, "epoch": 0.47420139555726265, "percentage": 37.04, "elapsed_time": "8:37:07", "remaining_time": "14:39:04", "throughput": 656.52, "total_tokens": 20369856} {"current_steps": 14820, "total_steps": 40000, "loss": 0.6496, "lr": 3.4894448090941266e-05, "epoch": 0.4743614365277511, "percentage": 37.05, "elapsed_time": "8:37:08", "remaining_time": "14:38:39", "throughput": 656.71, "total_tokens": 20376848} {"current_steps": 14825, "total_steps": 40000, "loss": 0.806, "lr": 3.488543148502101e-05, "epoch": 0.47452147749823953, "percentage": 37.06, "elapsed_time": "8:37:10", "remaining_time": "14:38:14", "throughput": 656.88, "total_tokens": 20383360} {"current_steps": 14830, "total_steps": 40000, "loss": 0.5989, "lr": 3.487641335464299e-05, "epoch": 0.47468151846872797, "percentage": 37.08, "elapsed_time": "8:37:12", "remaining_time": "14:37:49", "throughput": 657.06, "total_tokens": 20389920} {"current_steps": 14835, "total_steps": 40000, "loss": 0.7875, "lr": 3.4867393701197914e-05, "epoch": 0.47484155943921647, "percentage": 37.09, "elapsed_time": "8:37:14", "remaining_time": "14:37:23", "throughput": 657.24, "total_tokens": 20396688} {"current_steps": 14840, "total_steps": 40000, "loss": 0.7492, "lr": 3.485837252607673e-05, "epoch": 0.4750016004097049, "percentage": 37.1, "elapsed_time": "8:37:15", "remaining_time": "14:36:58", "throughput": 657.42, "total_tokens": 20403520} {"current_steps": 14845, "total_steps": 40000, "loss": 0.6016, "lr": 3.4849349830670615e-05, "epoch": 0.47516164138019334, "percentage": 37.11, "elapsed_time": "8:37:17", "remaining_time": "14:36:33", "throughput": 657.61, "total_tokens": 20410464} {"current_steps": 14850, "total_steps": 40000, "loss": 0.9074, "lr": 3.4840325616370976e-05, "epoch": 0.4753216823506818, "percentage": 37.12, "elapsed_time": "8:37:19", "remaining_time": "14:36:08", "throughput": 657.79, "total_tokens": 20417344} {"current_steps": 14855, "total_steps": 40000, "loss": 0.7057, "lr": 3.483129988456947e-05, "epoch": 0.4754817233211702, "percentage": 37.14, "elapsed_time": "8:37:20", "remaining_time": "14:35:42", "throughput": 657.98, "total_tokens": 20424368} {"current_steps": 14860, "total_steps": 40000, "loss": 0.685, "lr": 3.482227263665797e-05, "epoch": 0.47564176429165866, "percentage": 37.15, "elapsed_time": "8:37:22", "remaining_time": "14:35:17", "throughput": 658.17, "total_tokens": 20431472} {"current_steps": 14865, "total_steps": 40000, "loss": 0.6512, "lr": 3.48132438740286e-05, "epoch": 0.4758018052621471, "percentage": 37.16, "elapsed_time": "8:37:24", "remaining_time": "14:34:52", "throughput": 658.35, "total_tokens": 20438176} {"current_steps": 14870, "total_steps": 40000, "loss": 0.6025, "lr": 3.48042135980737e-05, "epoch": 0.47596184623263554, "percentage": 37.18, "elapsed_time": "8:37:26", "remaining_time": "14:34:27", "throughput": 658.53, "total_tokens": 20444912} {"current_steps": 14875, "total_steps": 40000, "loss": 0.6284, "lr": 3.479518181018586e-05, "epoch": 0.476121887203124, "percentage": 37.19, "elapsed_time": "8:37:27", "remaining_time": "14:34:02", "throughput": 658.72, "total_tokens": 20451824} {"current_steps": 14880, "total_steps": 40000, "loss": 0.8362, "lr": 3.4786148511757886e-05, "epoch": 0.4762819281736124, "percentage": 37.2, "elapsed_time": "8:37:29", "remaining_time": "14:33:37", "throughput": 658.9, "total_tokens": 20458736} {"current_steps": 14885, "total_steps": 40000, "loss": 0.8203, "lr": 3.477711370418284e-05, "epoch": 0.47644196914410086, "percentage": 37.21, "elapsed_time": "8:37:31", "remaining_time": "14:33:12", "throughput": 659.09, "total_tokens": 20465760} {"current_steps": 14890, "total_steps": 40000, "loss": 0.5971, "lr": 3.476807738885399e-05, "epoch": 0.47660201011458936, "percentage": 37.23, "elapsed_time": "8:37:33", "remaining_time": "14:32:46", "throughput": 659.28, "total_tokens": 20472624} {"current_steps": 14895, "total_steps": 40000, "loss": 0.6822, "lr": 3.475903956716485e-05, "epoch": 0.4767620510850778, "percentage": 37.24, "elapsed_time": "8:37:34", "remaining_time": "14:32:21", "throughput": 659.45, "total_tokens": 20479184} {"current_steps": 14900, "total_steps": 40000, "loss": 0.8002, "lr": 3.475000024050917e-05, "epoch": 0.47692209205556624, "percentage": 37.25, "elapsed_time": "8:37:36", "remaining_time": "14:31:56", "throughput": 659.62, "total_tokens": 20485680} {"current_steps": 14905, "total_steps": 40000, "loss": 0.8122, "lr": 3.4740959410280926e-05, "epoch": 0.4770821330260547, "percentage": 37.26, "elapsed_time": "8:37:38", "remaining_time": "14:31:31", "throughput": 659.81, "total_tokens": 20492432} {"current_steps": 14910, "total_steps": 40000, "loss": 0.7957, "lr": 3.4731917077874324e-05, "epoch": 0.4772421739965431, "percentage": 37.28, "elapsed_time": "8:37:40", "remaining_time": "14:31:06", "throughput": 659.99, "total_tokens": 20499296} {"current_steps": 14915, "total_steps": 40000, "loss": 0.7592, "lr": 3.4722873244683816e-05, "epoch": 0.47740221496703156, "percentage": 37.29, "elapsed_time": "8:37:41", "remaining_time": "14:30:41", "throughput": 660.17, "total_tokens": 20505888} {"current_steps": 14920, "total_steps": 40000, "loss": 0.8553, "lr": 3.4713827912104065e-05, "epoch": 0.47756225593752, "percentage": 37.3, "elapsed_time": "8:37:43", "remaining_time": "14:30:16", "throughput": 660.35, "total_tokens": 20512768} {"current_steps": 14925, "total_steps": 40000, "loss": 0.74, "lr": 3.470478108152998e-05, "epoch": 0.47772229690800844, "percentage": 37.31, "elapsed_time": "8:37:45", "remaining_time": "14:29:51", "throughput": 660.54, "total_tokens": 20519808} {"current_steps": 14930, "total_steps": 40000, "loss": 0.7383, "lr": 3.4695732754356695e-05, "epoch": 0.4778823378784969, "percentage": 37.33, "elapsed_time": "8:37:46", "remaining_time": "14:29:26", "throughput": 660.73, "total_tokens": 20526880} {"current_steps": 14935, "total_steps": 40000, "loss": 0.8054, "lr": 3.4686682931979576e-05, "epoch": 0.4780423788489853, "percentage": 37.34, "elapsed_time": "8:37:48", "remaining_time": "14:29:01", "throughput": 660.9, "total_tokens": 20533408} {"current_steps": 14940, "total_steps": 40000, "loss": 0.7927, "lr": 3.467763161579422e-05, "epoch": 0.4782024198194738, "percentage": 37.35, "elapsed_time": "8:37:50", "remaining_time": "14:28:36", "throughput": 661.1, "total_tokens": 20540528} {"current_steps": 14945, "total_steps": 40000, "loss": 0.6727, "lr": 3.466857880719645e-05, "epoch": 0.47836246078996225, "percentage": 37.36, "elapsed_time": "8:37:52", "remaining_time": "14:28:11", "throughput": 661.29, "total_tokens": 20547760} {"current_steps": 14950, "total_steps": 40000, "loss": 0.872, "lr": 3.465952450758233e-05, "epoch": 0.4785225017604507, "percentage": 37.38, "elapsed_time": "8:37:53", "remaining_time": "14:27:46", "throughput": 661.46, "total_tokens": 20554288} {"current_steps": 14955, "total_steps": 40000, "loss": 0.772, "lr": 3.4650468718348126e-05, "epoch": 0.47868254273093913, "percentage": 37.39, "elapsed_time": "8:37:55", "remaining_time": "14:27:22", "throughput": 661.66, "total_tokens": 20561392} {"current_steps": 14960, "total_steps": 40000, "loss": 0.7099, "lr": 3.464141144089038e-05, "epoch": 0.47884258370142757, "percentage": 37.4, "elapsed_time": "8:37:57", "remaining_time": "14:26:57", "throughput": 661.84, "total_tokens": 20568160} {"current_steps": 14965, "total_steps": 40000, "loss": 0.6909, "lr": 3.463235267660583e-05, "epoch": 0.479002624671916, "percentage": 37.41, "elapsed_time": "8:37:59", "remaining_time": "14:26:32", "throughput": 662.02, "total_tokens": 20574912} {"current_steps": 14970, "total_steps": 40000, "loss": 0.6115, "lr": 3.462329242689145e-05, "epoch": 0.47916266564240445, "percentage": 37.43, "elapsed_time": "8:38:00", "remaining_time": "14:26:07", "throughput": 662.2, "total_tokens": 20581680} {"current_steps": 14975, "total_steps": 40000, "loss": 0.752, "lr": 3.461423069314444e-05, "epoch": 0.4793227066128929, "percentage": 37.44, "elapsed_time": "8:38:02", "remaining_time": "14:25:42", "throughput": 662.38, "total_tokens": 20588464} {"current_steps": 14980, "total_steps": 40000, "loss": 0.6225, "lr": 3.460516747676224e-05, "epoch": 0.47948274758338133, "percentage": 37.45, "elapsed_time": "8:38:04", "remaining_time": "14:25:17", "throughput": 662.56, "total_tokens": 20595328} {"current_steps": 14985, "total_steps": 40000, "loss": 0.8159, "lr": 3.459610277914251e-05, "epoch": 0.47964278855386977, "percentage": 37.46, "elapsed_time": "8:38:06", "remaining_time": "14:24:53", "throughput": 662.74, "total_tokens": 20602128} {"current_steps": 14990, "total_steps": 40000, "loss": 0.6295, "lr": 3.458703660168314e-05, "epoch": 0.4798028295243582, "percentage": 37.48, "elapsed_time": "8:38:07", "remaining_time": "14:24:28", "throughput": 662.93, "total_tokens": 20609136} {"current_steps": 14995, "total_steps": 40000, "loss": 0.656, "lr": 3.457796894578224e-05, "epoch": 0.4799628704948467, "percentage": 37.49, "elapsed_time": "8:38:09", "remaining_time": "14:24:03", "throughput": 663.11, "total_tokens": 20615856} {"current_steps": 15000, "total_steps": 40000, "loss": 0.9413, "lr": 3.456889981283817e-05, "epoch": 0.48012291146533514, "percentage": 37.5, "elapsed_time": "8:38:11", "remaining_time": "14:23:38", "throughput": 663.3, "total_tokens": 20622896} {"current_steps": 15000, "total_steps": 40000, "eval_loss": 0.7602530121803284, "epoch": 0.48012291146533514, "percentage": 37.5, "elapsed_time": "8:43:58", "remaining_time": "14:33:17", "throughput": 655.97, "total_tokens": 20622896} {"current_steps": 15005, "total_steps": 40000, "loss": 0.8772, "lr": 3.45598292042495e-05, "epoch": 0.4802829524358236, "percentage": 37.51, "elapsed_time": "8:44:03", "remaining_time": "14:32:57", "throughput": 656.1, "total_tokens": 20629872} {"current_steps": 15010, "total_steps": 40000, "loss": 0.479, "lr": 3.4550757121415035e-05, "epoch": 0.480442993406312, "percentage": 37.52, "elapsed_time": "8:44:04", "remaining_time": "14:32:32", "throughput": 656.27, "total_tokens": 20636336} {"current_steps": 15015, "total_steps": 40000, "loss": 0.9185, "lr": 3.454168356573378e-05, "epoch": 0.48060303437680046, "percentage": 37.54, "elapsed_time": "8:44:06", "remaining_time": "14:32:07", "throughput": 656.43, "total_tokens": 20642640} {"current_steps": 15020, "total_steps": 40000, "loss": 0.7686, "lr": 3.453260853860503e-05, "epoch": 0.4807630753472889, "percentage": 37.55, "elapsed_time": "8:44:08", "remaining_time": "14:31:42", "throughput": 656.63, "total_tokens": 20649824} {"current_steps": 15025, "total_steps": 40000, "loss": 0.782, "lr": 3.452353204142824e-05, "epoch": 0.48092311631777734, "percentage": 37.56, "elapsed_time": "8:44:10", "remaining_time": "14:31:17", "throughput": 656.8, "total_tokens": 20656528} {"current_steps": 15030, "total_steps": 40000, "loss": 0.664, "lr": 3.4514454075603136e-05, "epoch": 0.4810831572882658, "percentage": 37.57, "elapsed_time": "8:44:11", "remaining_time": "14:30:52", "throughput": 656.98, "total_tokens": 20663280} {"current_steps": 15035, "total_steps": 40000, "loss": 0.7473, "lr": 3.450537464252964e-05, "epoch": 0.4812431982587542, "percentage": 37.59, "elapsed_time": "8:44:13", "remaining_time": "14:30:27", "throughput": 657.18, "total_tokens": 20670496} {"current_steps": 15040, "total_steps": 40000, "loss": 0.8339, "lr": 3.4496293743607925e-05, "epoch": 0.48140323922924266, "percentage": 37.6, "elapsed_time": "8:44:15", "remaining_time": "14:30:02", "throughput": 657.35, "total_tokens": 20677120} {"current_steps": 15045, "total_steps": 40000, "loss": 0.7447, "lr": 3.448721138023838e-05, "epoch": 0.48156328019973116, "percentage": 37.61, "elapsed_time": "8:44:17", "remaining_time": "14:29:37", "throughput": 657.53, "total_tokens": 20683968} {"current_steps": 15050, "total_steps": 40000, "loss": 0.9571, "lr": 3.447812755382162e-05, "epoch": 0.4817233211702196, "percentage": 37.62, "elapsed_time": "8:44:18", "remaining_time": "14:29:12", "throughput": 657.71, "total_tokens": 20690672} {"current_steps": 15055, "total_steps": 40000, "loss": 0.6965, "lr": 3.446904226575847e-05, "epoch": 0.48188336214070804, "percentage": 37.64, "elapsed_time": "8:44:20", "remaining_time": "14:28:47", "throughput": 657.88, "total_tokens": 20697088} {"current_steps": 15060, "total_steps": 40000, "loss": 0.8938, "lr": 3.445995551745002e-05, "epoch": 0.4820434031111965, "percentage": 37.65, "elapsed_time": "8:44:22", "remaining_time": "14:28:22", "throughput": 658.07, "total_tokens": 20704272} {"current_steps": 15065, "total_steps": 40000, "loss": 0.9174, "lr": 3.445086731029753e-05, "epoch": 0.4822034440816849, "percentage": 37.66, "elapsed_time": "8:44:23", "remaining_time": "14:27:57", "throughput": 658.25, "total_tokens": 20711072} {"current_steps": 15070, "total_steps": 40000, "loss": 0.8627, "lr": 3.444177764570255e-05, "epoch": 0.48236348505217336, "percentage": 37.67, "elapsed_time": "8:44:25", "remaining_time": "14:27:33", "throughput": 658.43, "total_tokens": 20717872} {"current_steps": 15075, "total_steps": 40000, "loss": 0.9551, "lr": 3.44326865250668e-05, "epoch": 0.4825235260226618, "percentage": 37.69, "elapsed_time": "8:44:27", "remaining_time": "14:27:08", "throughput": 658.61, "total_tokens": 20724624} {"current_steps": 15080, "total_steps": 40000, "loss": 0.5546, "lr": 3.442359394979225e-05, "epoch": 0.48268356699315024, "percentage": 37.7, "elapsed_time": "8:44:29", "remaining_time": "14:26:43", "throughput": 658.78, "total_tokens": 20731392} {"current_steps": 15085, "total_steps": 40000, "loss": 0.8873, "lr": 3.441449992128108e-05, "epoch": 0.4828436079636387, "percentage": 37.71, "elapsed_time": "8:44:30", "remaining_time": "14:26:18", "throughput": 658.97, "total_tokens": 20738416} {"current_steps": 15090, "total_steps": 40000, "loss": 0.6794, "lr": 3.440540444093573e-05, "epoch": 0.4830036489341271, "percentage": 37.72, "elapsed_time": "8:44:32", "remaining_time": "14:25:53", "throughput": 659.15, "total_tokens": 20745216} {"current_steps": 15095, "total_steps": 40000, "loss": 0.8017, "lr": 3.43963075101588e-05, "epoch": 0.48316368990461556, "percentage": 37.74, "elapsed_time": "8:44:34", "remaining_time": "14:25:29", "throughput": 659.34, "total_tokens": 20752144} {"current_steps": 15100, "total_steps": 40000, "loss": 0.602, "lr": 3.438720913035318e-05, "epoch": 0.48332373087510405, "percentage": 37.75, "elapsed_time": "8:44:36", "remaining_time": "14:25:04", "throughput": 659.51, "total_tokens": 20758944} {"current_steps": 15105, "total_steps": 40000, "loss": 0.6176, "lr": 3.437810930292195e-05, "epoch": 0.4834837718455925, "percentage": 37.76, "elapsed_time": "8:44:37", "remaining_time": "14:24:39", "throughput": 659.7, "total_tokens": 20766000} {"current_steps": 15110, "total_steps": 40000, "loss": 0.722, "lr": 3.43690080292684e-05, "epoch": 0.48364381281608093, "percentage": 37.77, "elapsed_time": "8:44:39", "remaining_time": "14:24:14", "throughput": 659.88, "total_tokens": 20772688} {"current_steps": 15115, "total_steps": 40000, "loss": 0.7053, "lr": 3.435990531079608e-05, "epoch": 0.48380385378656937, "percentage": 37.79, "elapsed_time": "8:44:41", "remaining_time": "14:23:50", "throughput": 660.05, "total_tokens": 20779264} {"current_steps": 15120, "total_steps": 40000, "loss": 0.6563, "lr": 3.435080114890874e-05, "epoch": 0.4839638947570578, "percentage": 37.8, "elapsed_time": "8:44:43", "remaining_time": "14:23:25", "throughput": 660.23, "total_tokens": 20786144} {"current_steps": 15125, "total_steps": 40000, "loss": 0.7129, "lr": 3.434169554501035e-05, "epoch": 0.48412393572754625, "percentage": 37.81, "elapsed_time": "8:44:44", "remaining_time": "14:23:00", "throughput": 660.41, "total_tokens": 20793008} {"current_steps": 15130, "total_steps": 40000, "loss": 0.6502, "lr": 3.433258850050511e-05, "epoch": 0.4842839766980347, "percentage": 37.82, "elapsed_time": "8:44:46", "remaining_time": "14:22:36", "throughput": 660.61, "total_tokens": 20800144} {"current_steps": 15135, "total_steps": 40000, "loss": 0.7516, "lr": 3.4323480016797446e-05, "epoch": 0.48444401766852313, "percentage": 37.84, "elapsed_time": "8:44:48", "remaining_time": "14:22:11", "throughput": 660.79, "total_tokens": 20807056} {"current_steps": 15140, "total_steps": 40000, "loss": 0.8152, "lr": 3.4314370095291995e-05, "epoch": 0.48460405863901157, "percentage": 37.85, "elapsed_time": "8:44:49", "remaining_time": "14:21:46", "throughput": 660.98, "total_tokens": 20814192} {"current_steps": 15145, "total_steps": 40000, "loss": 0.7285, "lr": 3.430525873739363e-05, "epoch": 0.4847640996095, "percentage": 37.86, "elapsed_time": "8:44:51", "remaining_time": "14:21:22", "throughput": 661.17, "total_tokens": 20821248} {"current_steps": 15150, "total_steps": 40000, "loss": 0.6871, "lr": 3.429614594450743e-05, "epoch": 0.48492414057998845, "percentage": 37.88, "elapsed_time": "8:44:53", "remaining_time": "14:20:57", "throughput": 661.36, "total_tokens": 20828496} {"current_steps": 15155, "total_steps": 40000, "loss": 0.8743, "lr": 3.428703171803869e-05, "epoch": 0.48508418155047694, "percentage": 37.89, "elapsed_time": "8:44:55", "remaining_time": "14:20:32", "throughput": 661.55, "total_tokens": 20835616} {"current_steps": 15160, "total_steps": 40000, "loss": 0.7555, "lr": 3.4277916059392964e-05, "epoch": 0.4852442225209654, "percentage": 37.9, "elapsed_time": "8:44:56", "remaining_time": "14:20:08", "throughput": 661.73, "total_tokens": 20842560} {"current_steps": 15165, "total_steps": 40000, "loss": 0.7121, "lr": 3.426879896997598e-05, "epoch": 0.4854042634914538, "percentage": 37.91, "elapsed_time": "8:44:58", "remaining_time": "14:19:43", "throughput": 661.92, "total_tokens": 20849680} {"current_steps": 15170, "total_steps": 40000, "loss": 0.779, "lr": 3.425968045119372e-05, "epoch": 0.48556430446194226, "percentage": 37.92, "elapsed_time": "8:45:00", "remaining_time": "14:19:19", "throughput": 662.1, "total_tokens": 20856432} {"current_steps": 15175, "total_steps": 40000, "loss": 0.7431, "lr": 3.425056050445237e-05, "epoch": 0.4857243454324307, "percentage": 37.94, "elapsed_time": "8:45:02", "remaining_time": "14:18:54", "throughput": 662.28, "total_tokens": 20863296} {"current_steps": 15180, "total_steps": 40000, "loss": 0.6855, "lr": 3.4241439131158336e-05, "epoch": 0.48588438640291914, "percentage": 37.95, "elapsed_time": "8:45:03", "remaining_time": "14:18:30", "throughput": 662.47, "total_tokens": 20870320} {"current_steps": 15185, "total_steps": 40000, "loss": 1.2712, "lr": 3.423231633271825e-05, "epoch": 0.4860444273734076, "percentage": 37.96, "elapsed_time": "8:45:05", "remaining_time": "14:18:05", "throughput": 662.64, "total_tokens": 20876960} {"current_steps": 15190, "total_steps": 40000, "loss": 0.5324, "lr": 3.4223192110538985e-05, "epoch": 0.486204468343896, "percentage": 37.97, "elapsed_time": "8:45:07", "remaining_time": "14:17:41", "throughput": 662.81, "total_tokens": 20883440} {"current_steps": 15195, "total_steps": 40000, "loss": 0.5981, "lr": 3.4214066466027575e-05, "epoch": 0.48636450931438446, "percentage": 37.99, "elapsed_time": "8:45:09", "remaining_time": "14:17:16", "throughput": 662.99, "total_tokens": 20890096} {"current_steps": 15200, "total_steps": 40000, "loss": 0.83, "lr": 3.4204939400591325e-05, "epoch": 0.4865245502848729, "percentage": 38.0, "elapsed_time": "8:45:10", "remaining_time": "14:16:52", "throughput": 663.16, "total_tokens": 20896768} {"current_steps": 15200, "total_steps": 40000, "eval_loss": 0.7597824931144714, "epoch": 0.4865245502848729, "percentage": 38.0, "elapsed_time": "8:50:58", "remaining_time": "14:26:19", "throughput": 655.93, "total_tokens": 20896768} {"current_steps": 15205, "total_steps": 40000, "loss": 0.947, "lr": 3.419581091563775e-05, "epoch": 0.4866845912553614, "percentage": 38.01, "elapsed_time": "8:51:01", "remaining_time": "14:25:57", "throughput": 656.07, "total_tokens": 20903488} {"current_steps": 15210, "total_steps": 40000, "loss": 0.6388, "lr": 3.418668101257456e-05, "epoch": 0.48684463222584984, "percentage": 38.02, "elapsed_time": "8:51:03", "remaining_time": "14:25:32", "throughput": 656.25, "total_tokens": 20910608} {"current_steps": 15215, "total_steps": 40000, "loss": 0.6475, "lr": 3.417754969280971e-05, "epoch": 0.4870046731963383, "percentage": 38.04, "elapsed_time": "8:51:05", "remaining_time": "14:25:08", "throughput": 656.44, "total_tokens": 20917760} {"current_steps": 15220, "total_steps": 40000, "loss": 0.8673, "lr": 3.416841695775137e-05, "epoch": 0.4871647141668267, "percentage": 38.05, "elapsed_time": "8:51:07", "remaining_time": "14:24:43", "throughput": 656.62, "total_tokens": 20924448} {"current_steps": 15225, "total_steps": 40000, "loss": 0.6523, "lr": 3.415928280880792e-05, "epoch": 0.48732475513731516, "percentage": 38.06, "elapsed_time": "8:51:08", "remaining_time": "14:24:18", "throughput": 656.79, "total_tokens": 20931200} {"current_steps": 15230, "total_steps": 40000, "loss": 0.9131, "lr": 3.4150147247387965e-05, "epoch": 0.4874847961078036, "percentage": 38.07, "elapsed_time": "8:51:10", "remaining_time": "14:23:54", "throughput": 656.96, "total_tokens": 20937696} {"current_steps": 15235, "total_steps": 40000, "loss": 0.6006, "lr": 3.4141010274900306e-05, "epoch": 0.48764483707829204, "percentage": 38.09, "elapsed_time": "8:51:12", "remaining_time": "14:23:29", "throughput": 657.14, "total_tokens": 20944560} {"current_steps": 15240, "total_steps": 40000, "loss": 0.7658, "lr": 3.413187189275399e-05, "epoch": 0.4878048780487805, "percentage": 38.1, "elapsed_time": "8:51:14", "remaining_time": "14:23:04", "throughput": 657.32, "total_tokens": 20951312} {"current_steps": 15245, "total_steps": 40000, "loss": 0.6982, "lr": 3.4122732102358265e-05, "epoch": 0.4879649190192689, "percentage": 38.11, "elapsed_time": "8:51:15", "remaining_time": "14:22:40", "throughput": 657.49, "total_tokens": 20958112} {"current_steps": 15250, "total_steps": 40000, "loss": 0.8727, "lr": 3.411359090512261e-05, "epoch": 0.48812495998975736, "percentage": 38.12, "elapsed_time": "8:51:17", "remaining_time": "14:22:15", "throughput": 657.67, "total_tokens": 20964736} {"current_steps": 15255, "total_steps": 40000, "loss": 0.5673, "lr": 3.410444830245672e-05, "epoch": 0.4882850009602458, "percentage": 38.14, "elapsed_time": "8:51:19", "remaining_time": "14:21:51", "throughput": 657.84, "total_tokens": 20971456} {"current_steps": 15260, "total_steps": 40000, "loss": 0.8176, "lr": 3.409530429577048e-05, "epoch": 0.4884450419307343, "percentage": 38.15, "elapsed_time": "8:51:20", "remaining_time": "14:21:26", "throughput": 658.02, "total_tokens": 20978288} {"current_steps": 15265, "total_steps": 40000, "loss": 0.4966, "lr": 3.408615888647402e-05, "epoch": 0.48860508290122273, "percentage": 38.16, "elapsed_time": "8:51:22", "remaining_time": "14:21:01", "throughput": 658.19, "total_tokens": 20984976} {"current_steps": 15270, "total_steps": 40000, "loss": 0.6955, "lr": 3.4077012075977675e-05, "epoch": 0.48876512387171117, "percentage": 38.17, "elapsed_time": "8:51:24", "remaining_time": "14:20:37", "throughput": 658.38, "total_tokens": 20991984} {"current_steps": 15275, "total_steps": 40000, "loss": 0.6173, "lr": 3.4067863865692e-05, "epoch": 0.4889251648421996, "percentage": 38.19, "elapsed_time": "8:51:26", "remaining_time": "14:20:12", "throughput": 658.56, "total_tokens": 20998832} {"current_steps": 15280, "total_steps": 40000, "loss": 1.0051, "lr": 3.4058714257027755e-05, "epoch": 0.48908520581268805, "percentage": 38.2, "elapsed_time": "8:51:27", "remaining_time": "14:19:48", "throughput": 658.74, "total_tokens": 21005872} {"current_steps": 15285, "total_steps": 40000, "loss": 0.9284, "lr": 3.404956325139594e-05, "epoch": 0.4892452467831765, "percentage": 38.21, "elapsed_time": "8:51:29", "remaining_time": "14:19:23", "throughput": 658.92, "total_tokens": 21012672} {"current_steps": 15290, "total_steps": 40000, "loss": 0.7557, "lr": 3.404041085020775e-05, "epoch": 0.48940528775366493, "percentage": 38.22, "elapsed_time": "8:51:31", "remaining_time": "14:18:59", "throughput": 659.1, "total_tokens": 21019552} {"current_steps": 15295, "total_steps": 40000, "loss": 0.7462, "lr": 3.403125705487459e-05, "epoch": 0.48956532872415337, "percentage": 38.24, "elapsed_time": "8:51:33", "remaining_time": "14:18:34", "throughput": 659.27, "total_tokens": 21026224} {"current_steps": 15300, "total_steps": 40000, "loss": 0.7838, "lr": 3.402210186680811e-05, "epoch": 0.4897253696946418, "percentage": 38.25, "elapsed_time": "8:51:34", "remaining_time": "14:18:10", "throughput": 659.46, "total_tokens": 21033296} {"current_steps": 15305, "total_steps": 40000, "loss": 0.7473, "lr": 3.4012945287420137e-05, "epoch": 0.48988541066513025, "percentage": 38.26, "elapsed_time": "8:51:36", "remaining_time": "14:17:45", "throughput": 659.64, "total_tokens": 21040240} {"current_steps": 15310, "total_steps": 40000, "loss": 0.8423, "lr": 3.400378731812274e-05, "epoch": 0.49004545163561875, "percentage": 38.27, "elapsed_time": "8:51:38", "remaining_time": "14:17:21", "throughput": 659.84, "total_tokens": 21047936} {"current_steps": 15315, "total_steps": 40000, "loss": 0.7172, "lr": 3.399462796032817e-05, "epoch": 0.4902054926061072, "percentage": 38.29, "elapsed_time": "8:51:40", "remaining_time": "14:16:57", "throughput": 660.01, "total_tokens": 21054400} {"current_steps": 15320, "total_steps": 40000, "loss": 0.6885, "lr": 3.3985467215448954e-05, "epoch": 0.4903655335765956, "percentage": 38.3, "elapsed_time": "8:51:41", "remaining_time": "14:16:32", "throughput": 660.18, "total_tokens": 21061088} {"current_steps": 15325, "total_steps": 40000, "loss": 0.8773, "lr": 3.3976305084897776e-05, "epoch": 0.49052557454708406, "percentage": 38.31, "elapsed_time": "8:51:43", "remaining_time": "14:16:08", "throughput": 660.35, "total_tokens": 21067488} {"current_steps": 15330, "total_steps": 40000, "loss": 0.6281, "lr": 3.3967141570087544e-05, "epoch": 0.4906856155175725, "percentage": 38.32, "elapsed_time": "8:51:45", "remaining_time": "14:15:44", "throughput": 660.53, "total_tokens": 21074304} {"current_steps": 15335, "total_steps": 40000, "loss": 0.727, "lr": 3.39579766724314e-05, "epoch": 0.49084565648806094, "percentage": 38.34, "elapsed_time": "8:51:47", "remaining_time": "14:15:19", "throughput": 660.7, "total_tokens": 21080928} {"current_steps": 15340, "total_steps": 40000, "loss": 0.6528, "lr": 3.3948810393342677e-05, "epoch": 0.4910056974585494, "percentage": 38.35, "elapsed_time": "8:51:48", "remaining_time": "14:14:55", "throughput": 660.87, "total_tokens": 21087680} {"current_steps": 15345, "total_steps": 40000, "loss": 0.6067, "lr": 3.3939642734234936e-05, "epoch": 0.4911657384290378, "percentage": 38.36, "elapsed_time": "8:51:50", "remaining_time": "14:14:31", "throughput": 661.07, "total_tokens": 21094960} {"current_steps": 15350, "total_steps": 40000, "loss": 0.6007, "lr": 3.393047369652194e-05, "epoch": 0.49132577939952626, "percentage": 38.38, "elapsed_time": "8:51:52", "remaining_time": "14:14:06", "throughput": 661.26, "total_tokens": 21102192} {"current_steps": 15355, "total_steps": 40000, "loss": 0.5562, "lr": 3.3921303281617664e-05, "epoch": 0.4914858203700147, "percentage": 38.39, "elapsed_time": "8:51:53", "remaining_time": "14:13:42", "throughput": 661.43, "total_tokens": 21109008} {"current_steps": 15360, "total_steps": 40000, "loss": 0.636, "lr": 3.391213149093632e-05, "epoch": 0.49164586134050314, "percentage": 38.4, "elapsed_time": "8:51:55", "remaining_time": "14:13:18", "throughput": 661.62, "total_tokens": 21116240} {"current_steps": 15365, "total_steps": 40000, "loss": 0.5716, "lr": 3.3902958325892303e-05, "epoch": 0.49180590231099164, "percentage": 38.41, "elapsed_time": "8:51:57", "remaining_time": "14:12:53", "throughput": 661.8, "total_tokens": 21123104} {"current_steps": 15370, "total_steps": 40000, "loss": 0.799, "lr": 3.389378378790023e-05, "epoch": 0.4919659432814801, "percentage": 38.42, "elapsed_time": "8:51:59", "remaining_time": "14:12:29", "throughput": 662.0, "total_tokens": 21130496} {"current_steps": 15375, "total_steps": 40000, "loss": 0.803, "lr": 3.388460787837493e-05, "epoch": 0.4921259842519685, "percentage": 38.44, "elapsed_time": "8:52:00", "remaining_time": "14:12:05", "throughput": 662.17, "total_tokens": 21137248} {"current_steps": 15380, "total_steps": 40000, "loss": 0.6767, "lr": 3.387543059873145e-05, "epoch": 0.49228602522245696, "percentage": 38.45, "elapsed_time": "8:52:02", "remaining_time": "14:11:41", "throughput": 662.37, "total_tokens": 21144496} {"current_steps": 15385, "total_steps": 40000, "loss": 0.6683, "lr": 3.386625195038503e-05, "epoch": 0.4924460661929454, "percentage": 38.46, "elapsed_time": "8:52:04", "remaining_time": "14:11:16", "throughput": 662.55, "total_tokens": 21151632} {"current_steps": 15390, "total_steps": 40000, "loss": 0.8623, "lr": 3.3857071934751136e-05, "epoch": 0.49260610716343384, "percentage": 38.48, "elapsed_time": "8:52:06", "remaining_time": "14:10:52", "throughput": 662.72, "total_tokens": 21158224} {"current_steps": 15395, "total_steps": 40000, "loss": 0.7463, "lr": 3.384789055324544e-05, "epoch": 0.4927661481339223, "percentage": 38.49, "elapsed_time": "8:52:07", "remaining_time": "14:10:28", "throughput": 662.89, "total_tokens": 21164800} {"current_steps": 15400, "total_steps": 40000, "loss": 0.5562, "lr": 3.3838707807283843e-05, "epoch": 0.4929261891044107, "percentage": 38.5, "elapsed_time": "8:52:09", "remaining_time": "14:10:04", "throughput": 663.06, "total_tokens": 21171376} {"current_steps": 15400, "total_steps": 40000, "eval_loss": 0.7582990527153015, "epoch": 0.4929261891044107, "percentage": 38.5, "elapsed_time": "8:57:57", "remaining_time": "14:19:19", "throughput": 655.93, "total_tokens": 21171376} {"current_steps": 15405, "total_steps": 40000, "loss": 0.6622, "lr": 3.382952369828243e-05, "epoch": 0.49308623007489916, "percentage": 38.51, "elapsed_time": "8:58:00", "remaining_time": "14:18:58", "throughput": 656.07, "total_tokens": 21178352} {"current_steps": 15410, "total_steps": 40000, "loss": 0.7696, "lr": 3.38203382276575e-05, "epoch": 0.4932462710453876, "percentage": 38.52, "elapsed_time": "8:58:02", "remaining_time": "14:18:33", "throughput": 656.24, "total_tokens": 21184912} {"current_steps": 15415, "total_steps": 40000, "loss": 0.7336, "lr": 3.381115139682557e-05, "epoch": 0.4934063120158761, "percentage": 38.54, "elapsed_time": "8:58:04", "remaining_time": "14:18:09", "throughput": 656.43, "total_tokens": 21192288} {"current_steps": 15420, "total_steps": 40000, "loss": 0.9902, "lr": 3.3801963207203366e-05, "epoch": 0.49356635298636453, "percentage": 38.55, "elapsed_time": "8:58:05", "remaining_time": "14:17:44", "throughput": 656.6, "total_tokens": 21199024} {"current_steps": 15425, "total_steps": 40000, "loss": 0.788, "lr": 3.379277366020782e-05, "epoch": 0.49372639395685297, "percentage": 38.56, "elapsed_time": "8:58:07", "remaining_time": "14:17:20", "throughput": 656.8, "total_tokens": 21206496} {"current_steps": 15430, "total_steps": 40000, "loss": 0.9365, "lr": 3.3783582757256085e-05, "epoch": 0.4938864349273414, "percentage": 38.57, "elapsed_time": "8:58:09", "remaining_time": "14:16:56", "throughput": 656.98, "total_tokens": 21213424} {"current_steps": 15435, "total_steps": 40000, "loss": 0.7856, "lr": 3.3774390499765504e-05, "epoch": 0.49404647589782985, "percentage": 38.59, "elapsed_time": "8:58:11", "remaining_time": "14:16:31", "throughput": 657.16, "total_tokens": 21220480} {"current_steps": 15440, "total_steps": 40000, "loss": 0.5791, "lr": 3.376519688915364e-05, "epoch": 0.4942065168683183, "percentage": 38.6, "elapsed_time": "8:58:12", "remaining_time": "14:16:07", "throughput": 657.33, "total_tokens": 21226976} {"current_steps": 15445, "total_steps": 40000, "loss": 0.8331, "lr": 3.3756001926838273e-05, "epoch": 0.49436655783880673, "percentage": 38.61, "elapsed_time": "8:58:14", "remaining_time": "14:15:43", "throughput": 657.5, "total_tokens": 21233728} {"current_steps": 15450, "total_steps": 40000, "loss": 0.7475, "lr": 3.374680561423737e-05, "epoch": 0.49452659880929517, "percentage": 38.62, "elapsed_time": "8:58:16", "remaining_time": "14:15:18", "throughput": 657.67, "total_tokens": 21240256} {"current_steps": 15455, "total_steps": 40000, "loss": 0.7101, "lr": 3.373760795276912e-05, "epoch": 0.4946866397797836, "percentage": 38.64, "elapsed_time": "8:58:18", "remaining_time": "14:14:54", "throughput": 657.84, "total_tokens": 21246976} {"current_steps": 15460, "total_steps": 40000, "loss": 0.8897, "lr": 3.372840894385192e-05, "epoch": 0.49484668075027205, "percentage": 38.65, "elapsed_time": "8:58:19", "remaining_time": "14:14:30", "throughput": 658.02, "total_tokens": 21253888} {"current_steps": 15465, "total_steps": 40000, "loss": 0.768, "lr": 3.3719208588904375e-05, "epoch": 0.4950067217207605, "percentage": 38.66, "elapsed_time": "8:58:21", "remaining_time": "14:14:05", "throughput": 658.19, "total_tokens": 21260448} {"current_steps": 15470, "total_steps": 40000, "loss": 0.8912, "lr": 3.371000688934529e-05, "epoch": 0.495166762691249, "percentage": 38.67, "elapsed_time": "8:58:23", "remaining_time": "14:13:41", "throughput": 658.36, "total_tokens": 21267216} {"current_steps": 15475, "total_steps": 40000, "loss": 0.8359, "lr": 3.370080384659369e-05, "epoch": 0.4953268036617374, "percentage": 38.69, "elapsed_time": "8:58:24", "remaining_time": "14:13:17", "throughput": 658.54, "total_tokens": 21274144} {"current_steps": 15480, "total_steps": 40000, "loss": 0.741, "lr": 3.36915994620688e-05, "epoch": 0.49548684463222586, "percentage": 38.7, "elapsed_time": "8:58:26", "remaining_time": "14:12:53", "throughput": 658.72, "total_tokens": 21281136} {"current_steps": 15485, "total_steps": 40000, "loss": 0.6956, "lr": 3.3682393737190035e-05, "epoch": 0.4956468856027143, "percentage": 38.71, "elapsed_time": "8:58:28", "remaining_time": "14:12:28", "throughput": 658.9, "total_tokens": 21288112} {"current_steps": 15490, "total_steps": 40000, "loss": 0.7701, "lr": 3.3673186673377054e-05, "epoch": 0.49580692657320274, "percentage": 38.73, "elapsed_time": "8:58:30", "remaining_time": "14:12:04", "throughput": 659.08, "total_tokens": 21294928} {"current_steps": 15495, "total_steps": 40000, "loss": 0.8373, "lr": 3.366397827204969e-05, "epoch": 0.4959669675436912, "percentage": 38.74, "elapsed_time": "8:58:31", "remaining_time": "14:11:40", "throughput": 659.27, "total_tokens": 21302224} {"current_steps": 15500, "total_steps": 40000, "loss": 0.5537, "lr": 3.3654768534628e-05, "epoch": 0.4961270085141796, "percentage": 38.75, "elapsed_time": "8:58:33", "remaining_time": "14:11:16", "throughput": 659.43, "total_tokens": 21308736} {"current_steps": 15505, "total_steps": 40000, "loss": 0.8497, "lr": 3.3645557462532245e-05, "epoch": 0.49628704948466806, "percentage": 38.76, "elapsed_time": "8:58:35", "remaining_time": "14:10:52", "throughput": 659.6, "total_tokens": 21315088} {"current_steps": 15510, "total_steps": 40000, "loss": 0.7031, "lr": 3.363634505718288e-05, "epoch": 0.4964470904551565, "percentage": 38.77, "elapsed_time": "8:58:37", "remaining_time": "14:10:28", "throughput": 659.77, "total_tokens": 21321760} {"current_steps": 15515, "total_steps": 40000, "loss": 0.783, "lr": 3.362713132000057e-05, "epoch": 0.49660713142564494, "percentage": 38.79, "elapsed_time": "8:58:38", "remaining_time": "14:10:04", "throughput": 659.94, "total_tokens": 21328624} {"current_steps": 15520, "total_steps": 40000, "loss": 0.7653, "lr": 3.36179162524062e-05, "epoch": 0.4967671723961334, "percentage": 38.8, "elapsed_time": "8:58:40", "remaining_time": "14:09:39", "throughput": 660.13, "total_tokens": 21335936} {"current_steps": 15525, "total_steps": 40000, "loss": 0.7514, "lr": 3.3608699855820846e-05, "epoch": 0.4969272133666219, "percentage": 38.81, "elapsed_time": "8:58:42", "remaining_time": "14:09:15", "throughput": 660.32, "total_tokens": 21343136} {"current_steps": 15530, "total_steps": 40000, "loss": 0.8536, "lr": 3.359948213166578e-05, "epoch": 0.4970872543371103, "percentage": 38.82, "elapsed_time": "8:58:44", "remaining_time": "14:08:51", "throughput": 660.51, "total_tokens": 21350448} {"current_steps": 15535, "total_steps": 40000, "loss": 0.6805, "lr": 3.359026308136252e-05, "epoch": 0.49724729530759876, "percentage": 38.84, "elapsed_time": "8:58:45", "remaining_time": "14:08:27", "throughput": 660.69, "total_tokens": 21357360} {"current_steps": 15540, "total_steps": 40000, "loss": 0.8372, "lr": 3.358104270633272e-05, "epoch": 0.4974073362780872, "percentage": 38.85, "elapsed_time": "8:58:47", "remaining_time": "14:08:03", "throughput": 660.87, "total_tokens": 21364480} {"current_steps": 15545, "total_steps": 40000, "loss": 0.7557, "lr": 3.357182100799831e-05, "epoch": 0.49756737724857564, "percentage": 38.86, "elapsed_time": "8:58:49", "remaining_time": "14:07:39", "throughput": 661.05, "total_tokens": 21371328} {"current_steps": 15550, "total_steps": 40000, "loss": 0.925, "lr": 3.3562597987781384e-05, "epoch": 0.4977274182190641, "percentage": 38.88, "elapsed_time": "8:58:51", "remaining_time": "14:07:15", "throughput": 661.22, "total_tokens": 21378032} {"current_steps": 15555, "total_steps": 40000, "loss": 0.952, "lr": 3.355337364710424e-05, "epoch": 0.4978874591895525, "percentage": 38.89, "elapsed_time": "8:58:52", "remaining_time": "14:06:51", "throughput": 661.41, "total_tokens": 21385248} {"current_steps": 15560, "total_steps": 40000, "loss": 0.5597, "lr": 3.354414798738939e-05, "epoch": 0.49804750016004096, "percentage": 38.9, "elapsed_time": "8:58:54", "remaining_time": "14:06:27", "throughput": 661.59, "total_tokens": 21392336} {"current_steps": 15565, "total_steps": 40000, "loss": 0.5671, "lr": 3.353492101005955e-05, "epoch": 0.4982075411305294, "percentage": 38.91, "elapsed_time": "8:58:56", "remaining_time": "14:06:03", "throughput": 661.77, "total_tokens": 21399136} {"current_steps": 15570, "total_steps": 40000, "loss": 0.7928, "lr": 3.352569271653763e-05, "epoch": 0.49836758210101784, "percentage": 38.92, "elapsed_time": "8:58:57", "remaining_time": "14:05:39", "throughput": 661.95, "total_tokens": 21406192} {"current_steps": 15575, "total_steps": 40000, "loss": 0.8638, "lr": 3.351646310824675e-05, "epoch": 0.49852762307150633, "percentage": 38.94, "elapsed_time": "8:58:59", "remaining_time": "14:05:15", "throughput": 662.13, "total_tokens": 21412944} {"current_steps": 15580, "total_steps": 40000, "loss": 0.6162, "lr": 3.350723218661023e-05, "epoch": 0.49868766404199477, "percentage": 38.95, "elapsed_time": "8:59:01", "remaining_time": "14:04:51", "throughput": 662.31, "total_tokens": 21420112} {"current_steps": 15585, "total_steps": 40000, "loss": 0.8113, "lr": 3.349799995305162e-05, "epoch": 0.4988477050124832, "percentage": 38.96, "elapsed_time": "8:59:03", "remaining_time": "14:04:27", "throughput": 662.49, "total_tokens": 21427120} {"current_steps": 15590, "total_steps": 40000, "loss": 0.7378, "lr": 3.348876640899461e-05, "epoch": 0.49900774598297165, "percentage": 38.98, "elapsed_time": "8:59:04", "remaining_time": "14:04:03", "throughput": 662.67, "total_tokens": 21433984} {"current_steps": 15595, "total_steps": 40000, "loss": 0.7357, "lr": 3.3479531555863144e-05, "epoch": 0.4991677869534601, "percentage": 38.99, "elapsed_time": "8:59:06", "remaining_time": "14:03:40", "throughput": 662.85, "total_tokens": 21440928} {"current_steps": 15600, "total_steps": 40000, "loss": 0.7659, "lr": 3.3470295395081344e-05, "epoch": 0.49932782792394853, "percentage": 39.0, "elapsed_time": "8:59:08", "remaining_time": "14:03:16", "throughput": 663.02, "total_tokens": 21447568} {"current_steps": 15600, "total_steps": 40000, "eval_loss": 0.7580332159996033, "epoch": 0.49932782792394853, "percentage": 39.0, "elapsed_time": "9:04:56", "remaining_time": "14:12:20", "throughput": 655.96, "total_tokens": 21447568} {"current_steps": 15605, "total_steps": 40000, "loss": 0.76, "lr": 3.3461057928073556e-05, "epoch": 0.49948786889443697, "percentage": 39.01, "elapsed_time": "9:04:59", "remaining_time": "14:11:59", "throughput": 656.11, "total_tokens": 21454848} {"current_steps": 15610, "total_steps": 40000, "loss": 0.7019, "lr": 3.345181915626431e-05, "epoch": 0.4996479098649254, "percentage": 39.02, "elapsed_time": "9:05:01", "remaining_time": "14:11:34", "throughput": 656.29, "total_tokens": 21461888} {"current_steps": 15615, "total_steps": 40000, "loss": 0.7187, "lr": 3.344257908107834e-05, "epoch": 0.49980795083541385, "percentage": 39.04, "elapsed_time": "9:05:03", "remaining_time": "14:11:10", "throughput": 656.47, "total_tokens": 21468640} {"current_steps": 15620, "total_steps": 40000, "loss": 0.5026, "lr": 3.343333770394058e-05, "epoch": 0.4999679918059023, "percentage": 39.05, "elapsed_time": "9:05:05", "remaining_time": "14:10:46", "throughput": 656.63, "total_tokens": 21475280} {"current_steps": 15625, "total_steps": 40000, "loss": 0.6479, "lr": 3.342409502627616e-05, "epoch": 0.5001280327763907, "percentage": 39.06, "elapsed_time": "9:05:06", "remaining_time": "14:10:22", "throughput": 656.8, "total_tokens": 21481920} {"current_steps": 15630, "total_steps": 40000, "loss": 0.9198, "lr": 3.341485104951043e-05, "epoch": 0.5002880737468792, "percentage": 39.07, "elapsed_time": "9:05:08", "remaining_time": "14:09:58", "throughput": 656.98, "total_tokens": 21489040} {"current_steps": 15635, "total_steps": 40000, "loss": 0.737, "lr": 3.340560577506892e-05, "epoch": 0.5004481147173676, "percentage": 39.09, "elapsed_time": "9:05:10", "remaining_time": "14:09:34", "throughput": 657.15, "total_tokens": 21495504} {"current_steps": 15640, "total_steps": 40000, "loss": 0.6014, "lr": 3.339635920437735e-05, "epoch": 0.5006081556878561, "percentage": 39.1, "elapsed_time": "9:05:12", "remaining_time": "14:09:10", "throughput": 657.32, "total_tokens": 21502240} {"current_steps": 15645, "total_steps": 40000, "loss": 0.7455, "lr": 3.338711133886169e-05, "epoch": 0.5007681966583445, "percentage": 39.11, "elapsed_time": "9:05:13", "remaining_time": "14:08:46", "throughput": 657.49, "total_tokens": 21509104} {"current_steps": 15650, "total_steps": 40000, "loss": 0.845, "lr": 3.3377862179948064e-05, "epoch": 0.500928237628833, "percentage": 39.12, "elapsed_time": "9:05:15", "remaining_time": "14:08:22", "throughput": 657.66, "total_tokens": 21515840} {"current_steps": 15655, "total_steps": 40000, "loss": 0.8045, "lr": 3.336861172906281e-05, "epoch": 0.5010882785993215, "percentage": 39.14, "elapsed_time": "9:05:17", "remaining_time": "14:07:58", "throughput": 657.84, "total_tokens": 21522576} {"current_steps": 15660, "total_steps": 40000, "loss": 0.8702, "lr": 3.335935998763245e-05, "epoch": 0.5012483195698099, "percentage": 39.15, "elapsed_time": "9:05:19", "remaining_time": "14:07:34", "throughput": 658.01, "total_tokens": 21529568} {"current_steps": 15665, "total_steps": 40000, "loss": 0.7122, "lr": 3.3350106957083744e-05, "epoch": 0.5014083605402984, "percentage": 39.16, "elapsed_time": "9:05:20", "remaining_time": "14:07:10", "throughput": 658.19, "total_tokens": 21536592} {"current_steps": 15670, "total_steps": 40000, "loss": 0.8767, "lr": 3.33408526388436e-05, "epoch": 0.5015684015107867, "percentage": 39.17, "elapsed_time": "9:05:22", "remaining_time": "14:06:46", "throughput": 658.37, "total_tokens": 21543424} {"current_steps": 15675, "total_steps": 40000, "loss": 0.7546, "lr": 3.3331597034339166e-05, "epoch": 0.5017284424812752, "percentage": 39.19, "elapsed_time": "9:05:24", "remaining_time": "14:06:22", "throughput": 658.55, "total_tokens": 21550400} {"current_steps": 15680, "total_steps": 40000, "loss": 0.7149, "lr": 3.3322340144997764e-05, "epoch": 0.5018884834517636, "percentage": 39.2, "elapsed_time": "9:05:25", "remaining_time": "14:05:58", "throughput": 658.72, "total_tokens": 21557216} {"current_steps": 15685, "total_steps": 40000, "loss": 0.6826, "lr": 3.331308197224693e-05, "epoch": 0.5020485244222521, "percentage": 39.21, "elapsed_time": "9:05:27", "remaining_time": "14:05:34", "throughput": 658.91, "total_tokens": 21564624} {"current_steps": 15690, "total_steps": 40000, "loss": 0.6821, "lr": 3.330382251751438e-05, "epoch": 0.5022085653927405, "percentage": 39.23, "elapsed_time": "9:05:29", "remaining_time": "14:05:10", "throughput": 659.09, "total_tokens": 21571520} {"current_steps": 15695, "total_steps": 40000, "loss": 0.8956, "lr": 3.3294561782228054e-05, "epoch": 0.502368606363229, "percentage": 39.24, "elapsed_time": "9:05:31", "remaining_time": "14:04:46", "throughput": 659.26, "total_tokens": 21578304} {"current_steps": 15700, "total_steps": 40000, "loss": 0.7383, "lr": 3.328529976781607e-05, "epoch": 0.5025286473337174, "percentage": 39.25, "elapsed_time": "9:05:32", "remaining_time": "14:04:23", "throughput": 659.45, "total_tokens": 21585568} {"current_steps": 15705, "total_steps": 40000, "loss": 0.6972, "lr": 3.327603647570673e-05, "epoch": 0.5026886883042059, "percentage": 39.26, "elapsed_time": "9:05:34", "remaining_time": "14:03:59", "throughput": 659.62, "total_tokens": 21592432} {"current_steps": 15710, "total_steps": 40000, "loss": 0.8876, "lr": 3.326677190732857e-05, "epoch": 0.5028487292746944, "percentage": 39.27, "elapsed_time": "9:05:36", "remaining_time": "14:03:35", "throughput": 659.8, "total_tokens": 21599344} {"current_steps": 15715, "total_steps": 40000, "loss": 0.6714, "lr": 3.325750606411029e-05, "epoch": 0.5030087702451828, "percentage": 39.29, "elapsed_time": "9:05:38", "remaining_time": "14:03:11", "throughput": 659.98, "total_tokens": 21606544} {"current_steps": 15720, "total_steps": 40000, "loss": 0.8836, "lr": 3.3248238947480804e-05, "epoch": 0.5031688112156713, "percentage": 39.3, "elapsed_time": "9:05:39", "remaining_time": "14:02:47", "throughput": 660.15, "total_tokens": 21613344} {"current_steps": 15725, "total_steps": 40000, "loss": 0.8597, "lr": 3.323897055886922e-05, "epoch": 0.5033288521861596, "percentage": 39.31, "elapsed_time": "9:05:41", "remaining_time": "14:02:23", "throughput": 660.33, "total_tokens": 21620208} {"current_steps": 15730, "total_steps": 40000, "loss": 0.7846, "lr": 3.322970089970484e-05, "epoch": 0.5034888931566481, "percentage": 39.32, "elapsed_time": "9:05:43", "remaining_time": "14:02:00", "throughput": 660.5, "total_tokens": 21627056} {"current_steps": 15735, "total_steps": 40000, "loss": 0.7871, "lr": 3.3220429971417165e-05, "epoch": 0.5036489341271365, "percentage": 39.34, "elapsed_time": "9:05:45", "remaining_time": "14:01:36", "throughput": 660.68, "total_tokens": 21633872} {"current_steps": 15740, "total_steps": 40000, "loss": 0.3904, "lr": 3.321115777543588e-05, "epoch": 0.503808975097625, "percentage": 39.35, "elapsed_time": "9:05:46", "remaining_time": "14:01:12", "throughput": 660.84, "total_tokens": 21640432} {"current_steps": 15745, "total_steps": 40000, "loss": 0.7371, "lr": 3.320188431319088e-05, "epoch": 0.5039690160681134, "percentage": 39.36, "elapsed_time": "9:05:48", "remaining_time": "14:00:48", "throughput": 661.03, "total_tokens": 21647760} {"current_steps": 15750, "total_steps": 40000, "loss": 0.6417, "lr": 3.319260958611224e-05, "epoch": 0.5041290570386019, "percentage": 39.38, "elapsed_time": "9:05:50", "remaining_time": "14:00:25", "throughput": 661.19, "total_tokens": 21654208} {"current_steps": 15755, "total_steps": 40000, "loss": 0.5506, "lr": 3.3183333595630256e-05, "epoch": 0.5042890980090903, "percentage": 39.39, "elapsed_time": "9:05:52", "remaining_time": "14:00:01", "throughput": 661.36, "total_tokens": 21660896} {"current_steps": 15760, "total_steps": 40000, "loss": 0.8279, "lr": 3.317405634317538e-05, "epoch": 0.5044491389795788, "percentage": 39.4, "elapsed_time": "9:05:53", "remaining_time": "13:59:37", "throughput": 661.54, "total_tokens": 21667808} {"current_steps": 15765, "total_steps": 40000, "loss": 0.5404, "lr": 3.3164777830178315e-05, "epoch": 0.5046091799500673, "percentage": 39.41, "elapsed_time": "9:05:55", "remaining_time": "13:59:13", "throughput": 661.7, "total_tokens": 21674224} {"current_steps": 15770, "total_steps": 40000, "loss": 0.8097, "lr": 3.315549805806989e-05, "epoch": 0.5047692209205557, "percentage": 39.42, "elapsed_time": "9:05:57", "remaining_time": "13:58:50", "throughput": 661.86, "total_tokens": 21680832} {"current_steps": 15775, "total_steps": 40000, "loss": 0.8559, "lr": 3.314621702828118e-05, "epoch": 0.5049292618910441, "percentage": 39.44, "elapsed_time": "9:05:58", "remaining_time": "13:58:26", "throughput": 662.04, "total_tokens": 21687728} {"current_steps": 15780, "total_steps": 40000, "loss": 0.6506, "lr": 3.313693474224342e-05, "epoch": 0.5050893028615325, "percentage": 39.45, "elapsed_time": "9:06:00", "remaining_time": "13:58:02", "throughput": 662.22, "total_tokens": 21694688} {"current_steps": 15785, "total_steps": 40000, "loss": 0.7082, "lr": 3.312765120138809e-05, "epoch": 0.505249343832021, "percentage": 39.46, "elapsed_time": "9:06:02", "remaining_time": "13:57:39", "throughput": 662.39, "total_tokens": 21701616} {"current_steps": 15790, "total_steps": 40000, "loss": 0.7768, "lr": 3.311836640714679e-05, "epoch": 0.5054093848025094, "percentage": 39.48, "elapsed_time": "9:06:04", "remaining_time": "13:57:15", "throughput": 662.56, "total_tokens": 21708288} {"current_steps": 15795, "total_steps": 40000, "loss": 0.6091, "lr": 3.310908036095137e-05, "epoch": 0.5055694257729979, "percentage": 39.49, "elapsed_time": "9:06:05", "remaining_time": "13:56:52", "throughput": 662.73, "total_tokens": 21715056} {"current_steps": 15800, "total_steps": 40000, "loss": 0.9216, "lr": 3.309979306423386e-05, "epoch": 0.5057294667434863, "percentage": 39.5, "elapsed_time": "9:06:07", "remaining_time": "13:56:28", "throughput": 662.92, "total_tokens": 21722256} {"current_steps": 15800, "total_steps": 40000, "eval_loss": 0.7575474977493286, "epoch": 0.5057294667434863, "percentage": 39.5, "elapsed_time": "9:11:55", "remaining_time": "14:05:21", "throughput": 655.96, "total_tokens": 21722256} {"current_steps": 15805, "total_steps": 40000, "loss": 0.6896, "lr": 3.309050451842647e-05, "epoch": 0.5058895077139748, "percentage": 39.51, "elapsed_time": "9:11:58", "remaining_time": "14:04:59", "throughput": 656.1, "total_tokens": 21729328} {"current_steps": 15810, "total_steps": 40000, "loss": 0.77, "lr": 3.3081214724961604e-05, "epoch": 0.5060495486844632, "percentage": 39.52, "elapsed_time": "9:12:00", "remaining_time": "14:04:35", "throughput": 656.27, "total_tokens": 21736128} {"current_steps": 15815, "total_steps": 40000, "loss": 0.4976, "lr": 3.307192368527188e-05, "epoch": 0.5062095896549517, "percentage": 39.54, "elapsed_time": "9:12:02", "remaining_time": "14:04:11", "throughput": 656.46, "total_tokens": 21743328} {"current_steps": 15820, "total_steps": 40000, "loss": 0.5989, "lr": 3.306263140079008e-05, "epoch": 0.5063696306254402, "percentage": 39.55, "elapsed_time": "9:12:03", "remaining_time": "14:03:48", "throughput": 656.62, "total_tokens": 21749872} {"current_steps": 15825, "total_steps": 40000, "loss": 0.8161, "lr": 3.30533378729492e-05, "epoch": 0.5065296715959285, "percentage": 39.56, "elapsed_time": "9:12:05", "remaining_time": "14:03:24", "throughput": 656.8, "total_tokens": 21757088} {"current_steps": 15830, "total_steps": 40000, "loss": 0.6325, "lr": 3.304404310318242e-05, "epoch": 0.506689712566417, "percentage": 39.57, "elapsed_time": "9:12:07", "remaining_time": "14:03:00", "throughput": 656.96, "total_tokens": 21763424} {"current_steps": 15835, "total_steps": 40000, "loss": 0.5667, "lr": 3.3034747092923105e-05, "epoch": 0.5068497535369054, "percentage": 39.59, "elapsed_time": "9:12:09", "remaining_time": "14:02:36", "throughput": 657.14, "total_tokens": 21770400} {"current_steps": 15840, "total_steps": 40000, "loss": 0.6663, "lr": 3.3025449843604806e-05, "epoch": 0.5070097945073939, "percentage": 39.6, "elapsed_time": "9:12:10", "remaining_time": "14:02:13", "throughput": 657.31, "total_tokens": 21777184} {"current_steps": 15845, "total_steps": 40000, "loss": 0.7287, "lr": 3.30161513566613e-05, "epoch": 0.5071698354778823, "percentage": 39.61, "elapsed_time": "9:12:12", "remaining_time": "14:01:49", "throughput": 657.49, "total_tokens": 21784512} {"current_steps": 15850, "total_steps": 40000, "loss": 0.729, "lr": 3.3006851633526506e-05, "epoch": 0.5073298764483708, "percentage": 39.62, "elapsed_time": "9:12:14", "remaining_time": "14:01:25", "throughput": 657.67, "total_tokens": 21791392} {"current_steps": 15855, "total_steps": 40000, "loss": 0.8097, "lr": 3.2997550675634584e-05, "epoch": 0.5074899174188592, "percentage": 39.64, "elapsed_time": "9:12:16", "remaining_time": "14:01:01", "throughput": 657.84, "total_tokens": 21798272} {"current_steps": 15860, "total_steps": 40000, "loss": 0.5068, "lr": 3.2988248484419825e-05, "epoch": 0.5076499583893477, "percentage": 39.65, "elapsed_time": "9:12:17", "remaining_time": "14:00:38", "throughput": 658.01, "total_tokens": 21805152} {"current_steps": 15865, "total_steps": 40000, "loss": 1.0067, "lr": 3.2978945061316776e-05, "epoch": 0.5078099993598362, "percentage": 39.66, "elapsed_time": "9:12:19", "remaining_time": "14:00:14", "throughput": 658.17, "total_tokens": 21811632} {"current_steps": 15870, "total_steps": 40000, "loss": 0.6752, "lr": 3.296964040776013e-05, "epoch": 0.5079700403303246, "percentage": 39.67, "elapsed_time": "9:12:21", "remaining_time": "13:59:50", "throughput": 658.33, "total_tokens": 21818032} {"current_steps": 15875, "total_steps": 40000, "loss": 0.6769, "lr": 3.296033452518478e-05, "epoch": 0.508130081300813, "percentage": 39.69, "elapsed_time": "9:12:23", "remaining_time": "13:59:27", "throughput": 658.5, "total_tokens": 21824688} {"current_steps": 15880, "total_steps": 40000, "loss": 0.6105, "lr": 3.2951027415025806e-05, "epoch": 0.5082901222713014, "percentage": 39.7, "elapsed_time": "9:12:24", "remaining_time": "13:59:03", "throughput": 658.67, "total_tokens": 21831568} {"current_steps": 15885, "total_steps": 40000, "loss": 0.7285, "lr": 3.294171907871849e-05, "epoch": 0.5084501632417899, "percentage": 39.71, "elapsed_time": "9:12:26", "remaining_time": "13:58:39", "throughput": 658.84, "total_tokens": 21838368} {"current_steps": 15890, "total_steps": 40000, "loss": 0.7838, "lr": 3.293240951769828e-05, "epoch": 0.5086102042122783, "percentage": 39.73, "elapsed_time": "9:12:28", "remaining_time": "13:58:16", "throughput": 659.01, "total_tokens": 21845136} {"current_steps": 15895, "total_steps": 40000, "loss": 0.8032, "lr": 3.2923098733400846e-05, "epoch": 0.5087702451827668, "percentage": 39.74, "elapsed_time": "9:12:30", "remaining_time": "13:57:52", "throughput": 659.2, "total_tokens": 21852656} {"current_steps": 15900, "total_steps": 40000, "loss": 0.6279, "lr": 3.291378672726202e-05, "epoch": 0.5089302861532552, "percentage": 39.75, "elapsed_time": "9:12:31", "remaining_time": "13:57:28", "throughput": 659.37, "total_tokens": 21859296} {"current_steps": 15905, "total_steps": 40000, "loss": 0.8725, "lr": 3.2904473500717824e-05, "epoch": 0.5090903271237437, "percentage": 39.76, "elapsed_time": "9:12:33", "remaining_time": "13:57:05", "throughput": 659.56, "total_tokens": 21866592} {"current_steps": 15910, "total_steps": 40000, "loss": 0.7007, "lr": 3.289515905520449e-05, "epoch": 0.5092503680942321, "percentage": 39.77, "elapsed_time": "9:12:35", "remaining_time": "13:56:41", "throughput": 659.73, "total_tokens": 21873440} {"current_steps": 15915, "total_steps": 40000, "loss": 0.7324, "lr": 3.288584339215841e-05, "epoch": 0.5094104090647206, "percentage": 39.79, "elapsed_time": "9:12:36", "remaining_time": "13:56:18", "throughput": 659.89, "total_tokens": 21880080} {"current_steps": 15920, "total_steps": 40000, "loss": 0.7485, "lr": 3.287652651301617e-05, "epoch": 0.5095704500352091, "percentage": 39.8, "elapsed_time": "9:12:38", "remaining_time": "13:55:54", "throughput": 660.07, "total_tokens": 21886944} {"current_steps": 15925, "total_steps": 40000, "loss": 0.8243, "lr": 3.286720841921457e-05, "epoch": 0.5097304910056975, "percentage": 39.81, "elapsed_time": "9:12:40", "remaining_time": "13:55:31", "throughput": 660.23, "total_tokens": 21893584} {"current_steps": 15930, "total_steps": 40000, "loss": 0.7959, "lr": 3.285788911219056e-05, "epoch": 0.509890531976186, "percentage": 39.83, "elapsed_time": "9:12:42", "remaining_time": "13:55:07", "throughput": 660.41, "total_tokens": 21900752} {"current_steps": 15935, "total_steps": 40000, "loss": 0.9189, "lr": 3.284856859338131e-05, "epoch": 0.5100505729466743, "percentage": 39.84, "elapsed_time": "9:12:43", "remaining_time": "13:54:44", "throughput": 660.6, "total_tokens": 21907904} {"current_steps": 15940, "total_steps": 40000, "loss": 0.6042, "lr": 3.283924686422414e-05, "epoch": 0.5102106139171628, "percentage": 39.85, "elapsed_time": "9:12:45", "remaining_time": "13:54:20", "throughput": 660.77, "total_tokens": 21914848} {"current_steps": 15945, "total_steps": 40000, "loss": 0.7811, "lr": 3.282992392615659e-05, "epoch": 0.5103706548876512, "percentage": 39.86, "elapsed_time": "9:12:47", "remaining_time": "13:53:57", "throughput": 660.95, "total_tokens": 21921920} {"current_steps": 15950, "total_steps": 40000, "loss": 0.7155, "lr": 3.282059978061638e-05, "epoch": 0.5105306958581397, "percentage": 39.88, "elapsed_time": "9:12:49", "remaining_time": "13:53:33", "throughput": 661.12, "total_tokens": 21928784} {"current_steps": 15955, "total_steps": 40000, "loss": 0.6998, "lr": 3.28112744290414e-05, "epoch": 0.5106907368286281, "percentage": 39.89, "elapsed_time": "9:12:50", "remaining_time": "13:53:10", "throughput": 661.31, "total_tokens": 21936352} {"current_steps": 15960, "total_steps": 40000, "loss": 0.9345, "lr": 3.280194787286974e-05, "epoch": 0.5108507777991166, "percentage": 39.9, "elapsed_time": "9:12:52", "remaining_time": "13:52:46", "throughput": 661.49, "total_tokens": 21943472} {"current_steps": 15965, "total_steps": 40000, "loss": 0.7115, "lr": 3.2792620113539674e-05, "epoch": 0.511010818769605, "percentage": 39.91, "elapsed_time": "9:12:54", "remaining_time": "13:52:23", "throughput": 661.66, "total_tokens": 21950144} {"current_steps": 15970, "total_steps": 40000, "loss": 0.7325, "lr": 3.278329115248966e-05, "epoch": 0.5111708597400935, "percentage": 39.92, "elapsed_time": "9:12:56", "remaining_time": "13:51:59", "throughput": 661.84, "total_tokens": 21957248} {"current_steps": 15975, "total_steps": 40000, "loss": 0.4981, "lr": 3.277396099115834e-05, "epoch": 0.511330900710582, "percentage": 39.94, "elapsed_time": "9:12:57", "remaining_time": "13:51:36", "throughput": 662.01, "total_tokens": 21964096} {"current_steps": 15980, "total_steps": 40000, "loss": 0.8624, "lr": 3.276462963098454e-05, "epoch": 0.5114909416810703, "percentage": 39.95, "elapsed_time": "9:12:59", "remaining_time": "13:51:13", "throughput": 662.19, "total_tokens": 21970992} {"current_steps": 15985, "total_steps": 40000, "loss": 0.7893, "lr": 3.275529707340728e-05, "epoch": 0.5116509826515588, "percentage": 39.96, "elapsed_time": "9:13:01", "remaining_time": "13:50:49", "throughput": 662.35, "total_tokens": 21977664} {"current_steps": 15990, "total_steps": 40000, "loss": 0.9831, "lr": 3.274596331986574e-05, "epoch": 0.5118110236220472, "percentage": 39.98, "elapsed_time": "9:13:02", "remaining_time": "13:50:26", "throughput": 662.51, "total_tokens": 21984128} {"current_steps": 15995, "total_steps": 40000, "loss": 0.5685, "lr": 3.273662837179932e-05, "epoch": 0.5119710645925357, "percentage": 39.99, "elapsed_time": "9:13:04", "remaining_time": "13:50:03", "throughput": 662.69, "total_tokens": 21991184} {"current_steps": 16000, "total_steps": 40000, "loss": 0.7743, "lr": 3.272729223064758e-05, "epoch": 0.5121311055630241, "percentage": 40.0, "elapsed_time": "9:13:06", "remaining_time": "13:49:39", "throughput": 662.87, "total_tokens": 21998320} {"current_steps": 16000, "total_steps": 40000, "eval_loss": 0.7571830749511719, "epoch": 0.5121311055630241, "percentage": 40.0, "elapsed_time": "9:18:54", "remaining_time": "13:58:21", "throughput": 655.99, "total_tokens": 21998320} {"current_steps": 16005, "total_steps": 40000, "loss": 1.0109, "lr": 3.2717954897850264e-05, "epoch": 0.5122911465335126, "percentage": 40.01, "elapsed_time": "9:18:57", "remaining_time": "13:58:00", "throughput": 656.13, "total_tokens": 22004960} {"current_steps": 16010, "total_steps": 40000, "loss": 0.6538, "lr": 3.270861637484733e-05, "epoch": 0.512451187504001, "percentage": 40.02, "elapsed_time": "9:18:59", "remaining_time": "13:57:36", "throughput": 656.3, "total_tokens": 22011920} {"current_steps": 16015, "total_steps": 40000, "loss": 0.791, "lr": 3.2699276663078867e-05, "epoch": 0.5126112284744895, "percentage": 40.04, "elapsed_time": "9:19:01", "remaining_time": "13:57:13", "throughput": 656.5, "total_tokens": 22019632} {"current_steps": 16020, "total_steps": 40000, "loss": 1.1019, "lr": 3.268993576398519e-05, "epoch": 0.5127712694449779, "percentage": 40.05, "elapsed_time": "9:19:02", "remaining_time": "13:56:49", "throughput": 656.67, "total_tokens": 22026576} {"current_steps": 16025, "total_steps": 40000, "loss": 0.7513, "lr": 3.268059367900678e-05, "epoch": 0.5129313104154664, "percentage": 40.06, "elapsed_time": "9:19:04", "remaining_time": "13:56:26", "throughput": 656.83, "total_tokens": 22033168} {"current_steps": 16030, "total_steps": 40000, "loss": 0.7084, "lr": 3.26712504095843e-05, "epoch": 0.5130913513859549, "percentage": 40.08, "elapsed_time": "9:19:06", "remaining_time": "13:56:02", "throughput": 656.99, "total_tokens": 22039648} {"current_steps": 16035, "total_steps": 40000, "loss": 0.6882, "lr": 3.2661905957158615e-05, "epoch": 0.5132513923564432, "percentage": 40.09, "elapsed_time": "9:19:08", "remaining_time": "13:55:38", "throughput": 657.15, "total_tokens": 22046176} {"current_steps": 16040, "total_steps": 40000, "loss": 0.8792, "lr": 3.2652560323170734e-05, "epoch": 0.5134114333269317, "percentage": 40.1, "elapsed_time": "9:19:09", "remaining_time": "13:55:15", "throughput": 657.33, "total_tokens": 22053248} {"current_steps": 16045, "total_steps": 40000, "loss": 0.6668, "lr": 3.264321350906189e-05, "epoch": 0.5135714742974201, "percentage": 40.11, "elapsed_time": "9:19:11", "remaining_time": "13:54:52", "throughput": 657.5, "total_tokens": 22060080} {"current_steps": 16050, "total_steps": 40000, "loss": 0.6804, "lr": 3.263386551627346e-05, "epoch": 0.5137315152679086, "percentage": 40.12, "elapsed_time": "9:19:13", "remaining_time": "13:54:28", "throughput": 657.66, "total_tokens": 22066608} {"current_steps": 16055, "total_steps": 40000, "loss": 0.8172, "lr": 3.2624516346247055e-05, "epoch": 0.513891556238397, "percentage": 40.14, "elapsed_time": "9:19:14", "remaining_time": "13:54:05", "throughput": 657.83, "total_tokens": 22073376} {"current_steps": 16060, "total_steps": 40000, "loss": 0.7242, "lr": 3.2615166000424404e-05, "epoch": 0.5140515972088855, "percentage": 40.15, "elapsed_time": "9:19:16", "remaining_time": "13:53:41", "throughput": 658.0, "total_tokens": 22080480} {"current_steps": 16065, "total_steps": 40000, "loss": 0.6434, "lr": 3.260581448024745e-05, "epoch": 0.5142116381793739, "percentage": 40.16, "elapsed_time": "9:19:18", "remaining_time": "13:53:18", "throughput": 658.16, "total_tokens": 22086784} {"current_steps": 16070, "total_steps": 40000, "loss": 1.074, "lr": 3.2596461787158335e-05, "epoch": 0.5143716791498624, "percentage": 40.17, "elapsed_time": "9:19:20", "remaining_time": "13:52:54", "throughput": 658.33, "total_tokens": 22093568} {"current_steps": 16075, "total_steps": 40000, "loss": 0.6312, "lr": 3.258710792259934e-05, "epoch": 0.5145317201203508, "percentage": 40.19, "elapsed_time": "9:19:21", "remaining_time": "13:52:31", "throughput": 658.51, "total_tokens": 22100864} {"current_steps": 16080, "total_steps": 40000, "loss": 0.7315, "lr": 3.257775288801296e-05, "epoch": 0.5146917610908393, "percentage": 40.2, "elapsed_time": "9:19:23", "remaining_time": "13:52:08", "throughput": 658.69, "total_tokens": 22108048} {"current_steps": 16085, "total_steps": 40000, "loss": 0.7246, "lr": 3.256839668484186e-05, "epoch": 0.5148518020613277, "percentage": 40.21, "elapsed_time": "9:19:25", "remaining_time": "13:51:44", "throughput": 658.85, "total_tokens": 22114544} {"current_steps": 16090, "total_steps": 40000, "loss": 0.789, "lr": 3.255903931452888e-05, "epoch": 0.5150118430318161, "percentage": 40.23, "elapsed_time": "9:19:27", "remaining_time": "13:51:21", "throughput": 659.02, "total_tokens": 22121280} {"current_steps": 16095, "total_steps": 40000, "loss": 0.8166, "lr": 3.2549680778517045e-05, "epoch": 0.5151718840023046, "percentage": 40.24, "elapsed_time": "9:19:28", "remaining_time": "13:50:57", "throughput": 659.19, "total_tokens": 22128416} {"current_steps": 16100, "total_steps": 40000, "loss": 0.4849, "lr": 3.2540321078249556e-05, "epoch": 0.515331924972793, "percentage": 40.25, "elapsed_time": "9:19:30", "remaining_time": "13:50:34", "throughput": 659.36, "total_tokens": 22134976} {"current_steps": 16105, "total_steps": 40000, "loss": 0.6945, "lr": 3.2530960215169795e-05, "epoch": 0.5154919659432815, "percentage": 40.26, "elapsed_time": "9:19:32", "remaining_time": "13:50:11", "throughput": 659.52, "total_tokens": 22141632} {"current_steps": 16110, "total_steps": 40000, "loss": 0.8111, "lr": 3.2521598190721345e-05, "epoch": 0.5156520069137699, "percentage": 40.27, "elapsed_time": "9:19:34", "remaining_time": "13:49:48", "throughput": 659.71, "total_tokens": 22149056} {"current_steps": 16115, "total_steps": 40000, "loss": 0.8386, "lr": 3.251223500634792e-05, "epoch": 0.5158120478842584, "percentage": 40.29, "elapsed_time": "9:19:35", "remaining_time": "13:49:24", "throughput": 659.88, "total_tokens": 22156176} {"current_steps": 16120, "total_steps": 40000, "loss": 0.8241, "lr": 3.2502870663493445e-05, "epoch": 0.5159720888547468, "percentage": 40.3, "elapsed_time": "9:19:37", "remaining_time": "13:49:01", "throughput": 660.06, "total_tokens": 22163136} {"current_steps": 16125, "total_steps": 40000, "loss": 0.8942, "lr": 3.249350516360203e-05, "epoch": 0.5161321298252353, "percentage": 40.31, "elapsed_time": "9:19:39", "remaining_time": "13:48:38", "throughput": 660.22, "total_tokens": 22169744} {"current_steps": 16130, "total_steps": 40000, "loss": 0.724, "lr": 3.248413850811797e-05, "epoch": 0.5162921707957238, "percentage": 40.33, "elapsed_time": "9:19:41", "remaining_time": "13:48:15", "throughput": 660.38, "total_tokens": 22176560} {"current_steps": 16135, "total_steps": 40000, "loss": 0.6941, "lr": 3.2474770698485677e-05, "epoch": 0.5164522117662121, "percentage": 40.34, "elapsed_time": "9:19:42", "remaining_time": "13:47:52", "throughput": 660.56, "total_tokens": 22183552} {"current_steps": 16140, "total_steps": 40000, "loss": 0.858, "lr": 3.246540173614983e-05, "epoch": 0.5166122527367006, "percentage": 40.35, "elapsed_time": "9:19:44", "remaining_time": "13:47:28", "throughput": 660.72, "total_tokens": 22190208} {"current_steps": 16145, "total_steps": 40000, "loss": 0.8103, "lr": 3.2456031622555197e-05, "epoch": 0.516772293707189, "percentage": 40.36, "elapsed_time": "9:19:46", "remaining_time": "13:47:05", "throughput": 660.89, "total_tokens": 22197008} {"current_steps": 16150, "total_steps": 40000, "loss": 1.0461, "lr": 3.2446660359146794e-05, "epoch": 0.5169323346776775, "percentage": 40.38, "elapsed_time": "9:19:48", "remaining_time": "13:46:42", "throughput": 661.06, "total_tokens": 22203728} {"current_steps": 16155, "total_steps": 40000, "loss": 0.7767, "lr": 3.2437287947369786e-05, "epoch": 0.5170923756481659, "percentage": 40.39, "elapsed_time": "9:19:49", "remaining_time": "13:46:19", "throughput": 661.22, "total_tokens": 22210480} {"current_steps": 16160, "total_steps": 40000, "loss": 0.7721, "lr": 3.2427914388669525e-05, "epoch": 0.5172524166186544, "percentage": 40.4, "elapsed_time": "9:19:51", "remaining_time": "13:45:56", "throughput": 661.41, "total_tokens": 22217744} {"current_steps": 16165, "total_steps": 40000, "loss": 0.7058, "lr": 3.241853968449151e-05, "epoch": 0.5174124575891428, "percentage": 40.41, "elapsed_time": "9:19:53", "remaining_time": "13:45:32", "throughput": 661.6, "total_tokens": 22225440} {"current_steps": 16170, "total_steps": 40000, "loss": 0.7745, "lr": 3.240916383628144e-05, "epoch": 0.5175724985596313, "percentage": 40.42, "elapsed_time": "9:19:55", "remaining_time": "13:45:09", "throughput": 661.78, "total_tokens": 22232720} {"current_steps": 16175, "total_steps": 40000, "loss": 0.7816, "lr": 3.239978684548521e-05, "epoch": 0.5177325395301197, "percentage": 40.44, "elapsed_time": "9:19:56", "remaining_time": "13:44:46", "throughput": 661.95, "total_tokens": 22239472} {"current_steps": 16180, "total_steps": 40000, "loss": 0.7826, "lr": 3.239040871354885e-05, "epoch": 0.5178925805006082, "percentage": 40.45, "elapsed_time": "9:19:58", "remaining_time": "13:44:23", "throughput": 662.11, "total_tokens": 22245968} {"current_steps": 16185, "total_steps": 40000, "loss": 0.7723, "lr": 3.2381029441918596e-05, "epoch": 0.5180526214710967, "percentage": 40.46, "elapsed_time": "9:20:00", "remaining_time": "13:44:00", "throughput": 662.3, "total_tokens": 22253408} {"current_steps": 16190, "total_steps": 40000, "loss": 0.8395, "lr": 3.2371649032040845e-05, "epoch": 0.518212662441585, "percentage": 40.48, "elapsed_time": "9:20:02", "remaining_time": "13:43:37", "throughput": 662.46, "total_tokens": 22260128} {"current_steps": 16195, "total_steps": 40000, "loss": 0.6133, "lr": 3.2362267485362174e-05, "epoch": 0.5183727034120735, "percentage": 40.49, "elapsed_time": "9:20:03", "remaining_time": "13:43:14", "throughput": 662.64, "total_tokens": 22267104} {"current_steps": 16200, "total_steps": 40000, "loss": 0.6469, "lr": 3.235288480332934e-05, "epoch": 0.5185327443825619, "percentage": 40.5, "elapsed_time": "9:20:05", "remaining_time": "13:42:51", "throughput": 662.8, "total_tokens": 22273616} {"current_steps": 16200, "total_steps": 40000, "eval_loss": 0.7557832598686218, "epoch": 0.5185327443825619, "percentage": 40.5, "elapsed_time": "9:25:52", "remaining_time": "13:51:21", "throughput": 656.02, "total_tokens": 22273616} {"current_steps": 16205, "total_steps": 40000, "loss": 0.7829, "lr": 3.234350098738927e-05, "epoch": 0.5186927853530504, "percentage": 40.51, "elapsed_time": "9:25:57", "remaining_time": "13:51:02", "throughput": 656.13, "total_tokens": 22280704} {"current_steps": 16210, "total_steps": 40000, "loss": 0.681, "lr": 3.233411603898906e-05, "epoch": 0.5188528263235388, "percentage": 40.52, "elapsed_time": "9:25:59", "remaining_time": "13:50:39", "throughput": 656.29, "total_tokens": 22287344} {"current_steps": 16215, "total_steps": 40000, "loss": 0.7862, "lr": 3.232472995957599e-05, "epoch": 0.5190128672940273, "percentage": 40.54, "elapsed_time": "9:26:01", "remaining_time": "13:50:16", "throughput": 656.46, "total_tokens": 22294352} {"current_steps": 16220, "total_steps": 40000, "loss": 0.6967, "lr": 3.231534275059751e-05, "epoch": 0.5191729082645157, "percentage": 40.55, "elapsed_time": "9:26:03", "remaining_time": "13:49:53", "throughput": 656.63, "total_tokens": 22301216} {"current_steps": 16225, "total_steps": 40000, "loss": 0.6804, "lr": 3.230595441350125e-05, "epoch": 0.5193329492350042, "percentage": 40.56, "elapsed_time": "9:26:04", "remaining_time": "13:49:29", "throughput": 656.8, "total_tokens": 22308272} {"current_steps": 16230, "total_steps": 40000, "loss": 0.7996, "lr": 3.2296564949735e-05, "epoch": 0.5194929902054926, "percentage": 40.58, "elapsed_time": "9:26:06", "remaining_time": "13:49:06", "throughput": 656.97, "total_tokens": 22315024} {"current_steps": 16235, "total_steps": 40000, "loss": 0.8927, "lr": 3.228717436074675e-05, "epoch": 0.519653031175981, "percentage": 40.59, "elapsed_time": "9:26:08", "remaining_time": "13:48:43", "throughput": 657.15, "total_tokens": 22322384} {"current_steps": 16240, "total_steps": 40000, "loss": 0.6416, "lr": 3.227778264798463e-05, "epoch": 0.5198130721464695, "percentage": 40.6, "elapsed_time": "9:26:10", "remaining_time": "13:48:20", "throughput": 657.32, "total_tokens": 22329248} {"current_steps": 16245, "total_steps": 40000, "loss": 0.7826, "lr": 3.226838981289698e-05, "epoch": 0.5199731131169579, "percentage": 40.61, "elapsed_time": "9:26:11", "remaining_time": "13:47:56", "throughput": 657.49, "total_tokens": 22336160} {"current_steps": 16250, "total_steps": 40000, "loss": 0.8702, "lr": 3.225899585693227e-05, "epoch": 0.5201331540874464, "percentage": 40.62, "elapsed_time": "9:26:13", "remaining_time": "13:47:33", "throughput": 657.66, "total_tokens": 22342912} {"current_steps": 16255, "total_steps": 40000, "loss": 0.7481, "lr": 3.224960078153918e-05, "epoch": 0.5202931950579348, "percentage": 40.64, "elapsed_time": "9:26:15", "remaining_time": "13:47:10", "throughput": 657.82, "total_tokens": 22349808} {"current_steps": 16260, "total_steps": 40000, "loss": 0.6762, "lr": 3.224020458816655e-05, "epoch": 0.5204532360284233, "percentage": 40.65, "elapsed_time": "9:26:17", "remaining_time": "13:46:47", "throughput": 657.99, "total_tokens": 22356592} {"current_steps": 16265, "total_steps": 40000, "loss": 0.961, "lr": 3.223080727826337e-05, "epoch": 0.5206132769989117, "percentage": 40.66, "elapsed_time": "9:26:18", "remaining_time": "13:46:24", "throughput": 658.15, "total_tokens": 22363008} {"current_steps": 16270, "total_steps": 40000, "loss": 0.9585, "lr": 3.222140885327885e-05, "epoch": 0.5207733179694002, "percentage": 40.67, "elapsed_time": "9:26:20", "remaining_time": "13:46:01", "throughput": 658.32, "total_tokens": 22370064} {"current_steps": 16275, "total_steps": 40000, "loss": 0.8132, "lr": 3.221200931466234e-05, "epoch": 0.5209333589398886, "percentage": 40.69, "elapsed_time": "9:26:22", "remaining_time": "13:45:37", "throughput": 658.5, "total_tokens": 22377296} {"current_steps": 16280, "total_steps": 40000, "loss": 0.8762, "lr": 3.220260866386336e-05, "epoch": 0.5210933999103771, "percentage": 40.7, "elapsed_time": "9:26:24", "remaining_time": "13:45:14", "throughput": 658.67, "total_tokens": 22384144} {"current_steps": 16285, "total_steps": 40000, "loss": 1.2261, "lr": 3.21932069023316e-05, "epoch": 0.5212534408808654, "percentage": 40.71, "elapsed_time": "9:26:25", "remaining_time": "13:44:51", "throughput": 658.83, "total_tokens": 22390912} {"current_steps": 16290, "total_steps": 40000, "loss": 0.5817, "lr": 3.218380403151695e-05, "epoch": 0.5214134818513539, "percentage": 40.73, "elapsed_time": "9:26:27", "remaining_time": "13:44:28", "throughput": 659.0, "total_tokens": 22397664} {"current_steps": 16295, "total_steps": 40000, "loss": 0.7044, "lr": 3.217440005286943e-05, "epoch": 0.5215735228218424, "percentage": 40.74, "elapsed_time": "9:26:29", "remaining_time": "13:44:05", "throughput": 659.17, "total_tokens": 22404816} {"current_steps": 16300, "total_steps": 40000, "loss": 0.7056, "lr": 3.216499496783928e-05, "epoch": 0.5217335637923308, "percentage": 40.75, "elapsed_time": "9:26:30", "remaining_time": "13:43:42", "throughput": 659.35, "total_tokens": 22412016} {"current_steps": 16305, "total_steps": 40000, "loss": 0.6696, "lr": 3.2155588777876856e-05, "epoch": 0.5218936047628193, "percentage": 40.76, "elapsed_time": "9:26:32", "remaining_time": "13:43:19", "throughput": 659.52, "total_tokens": 22418784} {"current_steps": 16310, "total_steps": 40000, "loss": 0.773, "lr": 3.214618148443273e-05, "epoch": 0.5220536457333077, "percentage": 40.77, "elapsed_time": "9:26:34", "remaining_time": "13:42:56", "throughput": 659.68, "total_tokens": 22425552} {"current_steps": 16315, "total_steps": 40000, "loss": 0.6083, "lr": 3.2136773088957595e-05, "epoch": 0.5222136867037962, "percentage": 40.79, "elapsed_time": "9:26:36", "remaining_time": "13:42:33", "throughput": 659.84, "total_tokens": 22432208} {"current_steps": 16320, "total_steps": 40000, "loss": 0.7728, "lr": 3.2127363592902374e-05, "epoch": 0.5223737276742846, "percentage": 40.8, "elapsed_time": "9:26:37", "remaining_time": "13:42:10", "throughput": 660.02, "total_tokens": 22439264} {"current_steps": 16325, "total_steps": 40000, "loss": 0.6991, "lr": 3.211795299771812e-05, "epoch": 0.5225337686447731, "percentage": 40.81, "elapsed_time": "9:26:39", "remaining_time": "13:41:47", "throughput": 660.21, "total_tokens": 22446848} {"current_steps": 16330, "total_steps": 40000, "loss": 0.8016, "lr": 3.210854130485605e-05, "epoch": 0.5226938096152615, "percentage": 40.83, "elapsed_time": "9:26:41", "remaining_time": "13:41:24", "throughput": 660.37, "total_tokens": 22453408} {"current_steps": 16335, "total_steps": 40000, "loss": 0.7559, "lr": 3.209912851576759e-05, "epoch": 0.52285385058575, "percentage": 40.84, "elapsed_time": "9:26:43", "remaining_time": "13:41:01", "throughput": 660.54, "total_tokens": 22460320} {"current_steps": 16340, "total_steps": 40000, "loss": 0.5723, "lr": 3.208971463190431e-05, "epoch": 0.5230138915562383, "percentage": 40.85, "elapsed_time": "9:26:44", "remaining_time": "13:40:38", "throughput": 660.7, "total_tokens": 22467168} {"current_steps": 16345, "total_steps": 40000, "loss": 0.6608, "lr": 3.208029965471793e-05, "epoch": 0.5231739325267268, "percentage": 40.86, "elapsed_time": "9:26:46", "remaining_time": "13:40:15", "throughput": 660.86, "total_tokens": 22473504} {"current_steps": 16350, "total_steps": 40000, "loss": 0.6615, "lr": 3.2070883585660364e-05, "epoch": 0.5233339734972153, "percentage": 40.88, "elapsed_time": "9:26:48", "remaining_time": "13:39:52", "throughput": 661.02, "total_tokens": 22480112} {"current_steps": 16355, "total_steps": 40000, "loss": 0.7033, "lr": 3.20614664261837e-05, "epoch": 0.5234940144677037, "percentage": 40.89, "elapsed_time": "9:26:50", "remaining_time": "13:39:29", "throughput": 661.17, "total_tokens": 22486592} {"current_steps": 16360, "total_steps": 40000, "loss": 0.8796, "lr": 3.205204817774016e-05, "epoch": 0.5236540554381922, "percentage": 40.9, "elapsed_time": "9:26:51", "remaining_time": "13:39:06", "throughput": 661.35, "total_tokens": 22493584} {"current_steps": 16365, "total_steps": 40000, "loss": 0.7347, "lr": 3.204262884178218e-05, "epoch": 0.5238140964086806, "percentage": 40.91, "elapsed_time": "9:26:53", "remaining_time": "13:38:43", "throughput": 661.51, "total_tokens": 22500176} {"current_steps": 16370, "total_steps": 40000, "loss": 0.6714, "lr": 3.2033208419762314e-05, "epoch": 0.5239741373791691, "percentage": 40.92, "elapsed_time": "9:26:55", "remaining_time": "13:38:20", "throughput": 661.67, "total_tokens": 22506848} {"current_steps": 16375, "total_steps": 40000, "loss": 0.8929, "lr": 3.2023786913133344e-05, "epoch": 0.5241341783496575, "percentage": 40.94, "elapsed_time": "9:26:57", "remaining_time": "13:37:57", "throughput": 661.85, "total_tokens": 22514208} {"current_steps": 16380, "total_steps": 40000, "loss": 0.7134, "lr": 3.201436432334816e-05, "epoch": 0.524294219320146, "percentage": 40.95, "elapsed_time": "9:26:58", "remaining_time": "13:37:35", "throughput": 662.02, "total_tokens": 22521168} {"current_steps": 16385, "total_steps": 40000, "loss": 0.8919, "lr": 3.2004940651859844e-05, "epoch": 0.5244542602906344, "percentage": 40.96, "elapsed_time": "9:27:00", "remaining_time": "13:37:12", "throughput": 662.2, "total_tokens": 22528512} {"current_steps": 16390, "total_steps": 40000, "loss": 0.6292, "lr": 3.1995515900121655e-05, "epoch": 0.5246143012611229, "percentage": 40.98, "elapsed_time": "9:27:02", "remaining_time": "13:36:49", "throughput": 662.37, "total_tokens": 22535328} {"current_steps": 16395, "total_steps": 40000, "loss": 0.6961, "lr": 3.1986090069587e-05, "epoch": 0.5247743422316113, "percentage": 40.99, "elapsed_time": "9:27:03", "remaining_time": "13:36:26", "throughput": 662.54, "total_tokens": 22542256} {"current_steps": 16400, "total_steps": 40000, "loss": 0.7036, "lr": 3.1976663161709466e-05, "epoch": 0.5249343832020997, "percentage": 41.0, "elapsed_time": "9:27:05", "remaining_time": "13:36:03", "throughput": 662.71, "total_tokens": 22549280} {"current_steps": 16400, "total_steps": 40000, "eval_loss": 0.7551063299179077, "epoch": 0.5249343832020997, "percentage": 41.0, "elapsed_time": "9:32:53", "remaining_time": "13:44:24", "throughput": 656.01, "total_tokens": 22549280} {"current_steps": 16405, "total_steps": 40000, "loss": 0.8511, "lr": 3.196723517794279e-05, "epoch": 0.5250944241725882, "percentage": 41.01, "elapsed_time": "9:32:57", "remaining_time": "13:44:04", "throughput": 656.14, "total_tokens": 22556208} {"current_steps": 16410, "total_steps": 40000, "loss": 0.7175, "lr": 3.19578061197409e-05, "epoch": 0.5252544651430766, "percentage": 41.02, "elapsed_time": "9:32:58", "remaining_time": "13:43:41", "throughput": 656.29, "total_tokens": 22562608} {"current_steps": 16415, "total_steps": 40000, "loss": 0.8838, "lr": 3.194837598855787e-05, "epoch": 0.5254145061135651, "percentage": 41.04, "elapsed_time": "9:33:00", "remaining_time": "13:43:17", "throughput": 656.46, "total_tokens": 22569584} {"current_steps": 16420, "total_steps": 40000, "loss": 0.8073, "lr": 3.193894478584794e-05, "epoch": 0.5255745470840535, "percentage": 41.05, "elapsed_time": "9:33:02", "remaining_time": "13:42:54", "throughput": 656.63, "total_tokens": 22576448} {"current_steps": 16425, "total_steps": 40000, "loss": 0.6764, "lr": 3.192951251306553e-05, "epoch": 0.525734588054542, "percentage": 41.06, "elapsed_time": "9:33:04", "remaining_time": "13:42:31", "throughput": 656.8, "total_tokens": 22583552} {"current_steps": 16430, "total_steps": 40000, "loss": 0.8016, "lr": 3.192007917166521e-05, "epoch": 0.5258946290250304, "percentage": 41.08, "elapsed_time": "9:33:05", "remaining_time": "13:42:08", "throughput": 656.97, "total_tokens": 22590592} {"current_steps": 16435, "total_steps": 40000, "loss": 0.776, "lr": 3.191064476310171e-05, "epoch": 0.5260546699955189, "percentage": 41.09, "elapsed_time": "9:33:07", "remaining_time": "13:41:45", "throughput": 657.14, "total_tokens": 22597328} {"current_steps": 16440, "total_steps": 40000, "loss": 0.5091, "lr": 3.1901209288829944e-05, "epoch": 0.5262147109660072, "percentage": 41.1, "elapsed_time": "9:33:09", "remaining_time": "13:41:23", "throughput": 657.3, "total_tokens": 22604160} {"current_steps": 16445, "total_steps": 40000, "loss": 0.7906, "lr": 3.1891772750304985e-05, "epoch": 0.5263747519364957, "percentage": 41.11, "elapsed_time": "9:33:11", "remaining_time": "13:41:00", "throughput": 657.46, "total_tokens": 22610768} {"current_steps": 16450, "total_steps": 40000, "loss": 0.6925, "lr": 3.188233514898206e-05, "epoch": 0.5265347929069842, "percentage": 41.12, "elapsed_time": "9:33:12", "remaining_time": "13:40:37", "throughput": 657.64, "total_tokens": 22618208} {"current_steps": 16455, "total_steps": 40000, "loss": 0.8135, "lr": 3.187289648631657e-05, "epoch": 0.5266948338774726, "percentage": 41.14, "elapsed_time": "9:33:14", "remaining_time": "13:40:14", "throughput": 657.8, "total_tokens": 22624896} {"current_steps": 16460, "total_steps": 40000, "loss": 0.7515, "lr": 3.186345676376406e-05, "epoch": 0.5268548748479611, "percentage": 41.15, "elapsed_time": "9:33:16", "remaining_time": "13:39:51", "throughput": 657.97, "total_tokens": 22631792} {"current_steps": 16465, "total_steps": 40000, "loss": 0.8684, "lr": 3.1854015982780275e-05, "epoch": 0.5270149158184495, "percentage": 41.16, "elapsed_time": "9:33:18", "remaining_time": "13:39:28", "throughput": 658.14, "total_tokens": 22638608} {"current_steps": 16470, "total_steps": 40000, "loss": 0.7804, "lr": 3.1844574144821084e-05, "epoch": 0.527174956788938, "percentage": 41.17, "elapsed_time": "9:33:19", "remaining_time": "13:39:05", "throughput": 658.31, "total_tokens": 22645568} {"current_steps": 16475, "total_steps": 40000, "loss": 0.9709, "lr": 3.1835131251342554e-05, "epoch": 0.5273349977594264, "percentage": 41.19, "elapsed_time": "9:33:21", "remaining_time": "13:38:42", "throughput": 658.47, "total_tokens": 22652320} {"current_steps": 16480, "total_steps": 40000, "loss": 0.753, "lr": 3.182568730380089e-05, "epoch": 0.5274950387299149, "percentage": 41.2, "elapsed_time": "9:33:23", "remaining_time": "13:38:19", "throughput": 658.64, "total_tokens": 22659408} {"current_steps": 16485, "total_steps": 40000, "loss": 0.6285, "lr": 3.181624230365245e-05, "epoch": 0.5276550797004033, "percentage": 41.21, "elapsed_time": "9:33:24", "remaining_time": "13:37:56", "throughput": 658.82, "total_tokens": 22666640} {"current_steps": 16490, "total_steps": 40000, "loss": 0.9021, "lr": 3.180679625235381e-05, "epoch": 0.5278151206708918, "percentage": 41.23, "elapsed_time": "9:33:26", "remaining_time": "13:37:34", "throughput": 658.98, "total_tokens": 22673232} {"current_steps": 16495, "total_steps": 40000, "loss": 0.6753, "lr": 3.1797349151361646e-05, "epoch": 0.5279751616413801, "percentage": 41.24, "elapsed_time": "9:33:28", "remaining_time": "13:37:11", "throughput": 659.14, "total_tokens": 22679840} {"current_steps": 16500, "total_steps": 40000, "loss": 0.8746, "lr": 3.178790100213281e-05, "epoch": 0.5281352026118686, "percentage": 41.25, "elapsed_time": "9:33:30", "remaining_time": "13:36:48", "throughput": 659.3, "total_tokens": 22686560} {"current_steps": 16505, "total_steps": 40000, "loss": 0.6906, "lr": 3.1778451806124346e-05, "epoch": 0.5282952435823571, "percentage": 41.26, "elapsed_time": "9:33:31", "remaining_time": "13:36:25", "throughput": 659.47, "total_tokens": 22693584} {"current_steps": 16510, "total_steps": 40000, "loss": 0.9028, "lr": 3.176900156479342e-05, "epoch": 0.5284552845528455, "percentage": 41.27, "elapsed_time": "9:33:33", "remaining_time": "13:36:02", "throughput": 659.64, "total_tokens": 22700608} {"current_steps": 16515, "total_steps": 40000, "loss": 0.7414, "lr": 3.17595502795974e-05, "epoch": 0.528615325523334, "percentage": 41.29, "elapsed_time": "9:33:35", "remaining_time": "13:35:40", "throughput": 659.81, "total_tokens": 22707760} {"current_steps": 16520, "total_steps": 40000, "loss": 0.9468, "lr": 3.175009795199377e-05, "epoch": 0.5287753664938224, "percentage": 41.3, "elapsed_time": "9:33:37", "remaining_time": "13:35:17", "throughput": 659.99, "total_tokens": 22714800} {"current_steps": 16525, "total_steps": 40000, "loss": 0.7934, "lr": 3.1740644583440224e-05, "epoch": 0.5289354074643109, "percentage": 41.31, "elapsed_time": "9:33:38", "remaining_time": "13:34:54", "throughput": 660.14, "total_tokens": 22721376} {"current_steps": 16530, "total_steps": 40000, "loss": 0.8177, "lr": 3.173119017539457e-05, "epoch": 0.5290954484347993, "percentage": 41.33, "elapsed_time": "9:33:40", "remaining_time": "13:34:31", "throughput": 660.29, "total_tokens": 22727616} {"current_steps": 16535, "total_steps": 40000, "loss": 0.7972, "lr": 3.172173472931479e-05, "epoch": 0.5292554894052878, "percentage": 41.34, "elapsed_time": "9:33:42", "remaining_time": "13:34:09", "throughput": 660.46, "total_tokens": 22734672} {"current_steps": 16540, "total_steps": 40000, "loss": 0.6639, "lr": 3.1712278246659055e-05, "epoch": 0.5294155303757762, "percentage": 41.35, "elapsed_time": "9:33:44", "remaining_time": "13:33:46", "throughput": 660.64, "total_tokens": 22741856} {"current_steps": 16545, "total_steps": 40000, "loss": 0.7787, "lr": 3.170282072888566e-05, "epoch": 0.5295755713462647, "percentage": 41.36, "elapsed_time": "9:33:45", "remaining_time": "13:33:23", "throughput": 660.81, "total_tokens": 22748992} {"current_steps": 16550, "total_steps": 40000, "loss": 0.8102, "lr": 3.169336217745307e-05, "epoch": 0.529735612316753, "percentage": 41.38, "elapsed_time": "9:33:47", "remaining_time": "13:33:01", "throughput": 660.97, "total_tokens": 22755696} {"current_steps": 16555, "total_steps": 40000, "loss": 0.8268, "lr": 3.1683902593819924e-05, "epoch": 0.5298956532872415, "percentage": 41.39, "elapsed_time": "9:33:49", "remaining_time": "13:32:38", "throughput": 661.14, "total_tokens": 22762672} {"current_steps": 16560, "total_steps": 40000, "loss": 0.6722, "lr": 3.1674441979445e-05, "epoch": 0.53005569425773, "percentage": 41.4, "elapsed_time": "9:33:50", "remaining_time": "13:32:15", "throughput": 661.31, "total_tokens": 22769616} {"current_steps": 16565, "total_steps": 40000, "loss": 0.716, "lr": 3.166498033578725e-05, "epoch": 0.5302157352282184, "percentage": 41.41, "elapsed_time": "9:33:52", "remaining_time": "13:31:53", "throughput": 661.49, "total_tokens": 22776864} {"current_steps": 16570, "total_steps": 40000, "loss": 0.9012, "lr": 3.165551766430578e-05, "epoch": 0.5303757761987069, "percentage": 41.42, "elapsed_time": "9:33:54", "remaining_time": "13:31:30", "throughput": 661.64, "total_tokens": 22783376} {"current_steps": 16575, "total_steps": 40000, "loss": 0.6818, "lr": 3.164605396645984e-05, "epoch": 0.5305358171691953, "percentage": 41.44, "elapsed_time": "9:33:56", "remaining_time": "13:31:07", "throughput": 661.81, "total_tokens": 22790160} {"current_steps": 16580, "total_steps": 40000, "loss": 0.8208, "lr": 3.163658924370886e-05, "epoch": 0.5306958581396838, "percentage": 41.45, "elapsed_time": "9:33:57", "remaining_time": "13:30:45", "throughput": 661.96, "total_tokens": 22796544} {"current_steps": 16585, "total_steps": 40000, "loss": 0.8093, "lr": 3.1627123497512415e-05, "epoch": 0.5308558991101722, "percentage": 41.46, "elapsed_time": "9:33:59", "remaining_time": "13:30:22", "throughput": 662.13, "total_tokens": 22803584} {"current_steps": 16590, "total_steps": 40000, "loss": 0.7452, "lr": 3.1617656729330245e-05, "epoch": 0.5310159400806607, "percentage": 41.48, "elapsed_time": "9:34:01", "remaining_time": "13:29:59", "throughput": 662.29, "total_tokens": 22810224} {"current_steps": 16595, "total_steps": 40000, "loss": 0.6466, "lr": 3.1608188940622255e-05, "epoch": 0.531175981051149, "percentage": 41.49, "elapsed_time": "9:34:03", "remaining_time": "13:29:37", "throughput": 662.46, "total_tokens": 22817152} {"current_steps": 16600, "total_steps": 40000, "loss": 0.8155, "lr": 3.159872013284847e-05, "epoch": 0.5313360220216375, "percentage": 41.5, "elapsed_time": "9:34:04", "remaining_time": "13:29:14", "throughput": 662.62, "total_tokens": 22823984} {"current_steps": 16600, "total_steps": 40000, "eval_loss": 0.7545750737190247, "epoch": 0.5313360220216375, "percentage": 41.5, "elapsed_time": "9:39:52", "remaining_time": "13:37:25", "throughput": 656.0, "total_tokens": 22823984} {"current_steps": 16605, "total_steps": 40000, "loss": 0.8191, "lr": 3.1589250307469134e-05, "epoch": 0.531496062992126, "percentage": 41.51, "elapsed_time": "9:39:56", "remaining_time": "13:37:05", "throughput": 656.13, "total_tokens": 22830864} {"current_steps": 16610, "total_steps": 40000, "loss": 0.7155, "lr": 3.1579779465944586e-05, "epoch": 0.5316561039626144, "percentage": 41.52, "elapsed_time": "9:39:58", "remaining_time": "13:36:42", "throughput": 656.29, "total_tokens": 22837648} {"current_steps": 16615, "total_steps": 40000, "loss": 0.9242, "lr": 3.1570307609735363e-05, "epoch": 0.5318161449331029, "percentage": 41.54, "elapsed_time": "9:39:59", "remaining_time": "13:36:19", "throughput": 656.47, "total_tokens": 22845184} {"current_steps": 16620, "total_steps": 40000, "loss": 0.7043, "lr": 3.156083474030213e-05, "epoch": 0.5319761859035913, "percentage": 41.55, "elapsed_time": "9:40:01", "remaining_time": "13:35:56", "throughput": 656.63, "total_tokens": 22851904} {"current_steps": 16625, "total_steps": 40000, "loss": 0.8075, "lr": 3.155136085910573e-05, "epoch": 0.5321362268740798, "percentage": 41.56, "elapsed_time": "9:40:03", "remaining_time": "13:35:34", "throughput": 656.79, "total_tokens": 22858720} {"current_steps": 16630, "total_steps": 40000, "loss": 0.7303, "lr": 3.154188596760717e-05, "epoch": 0.5322962678445682, "percentage": 41.58, "elapsed_time": "9:40:05", "remaining_time": "13:35:11", "throughput": 656.96, "total_tokens": 22865648} {"current_steps": 16635, "total_steps": 40000, "loss": 0.7116, "lr": 3.153241006726757e-05, "epoch": 0.5324563088150567, "percentage": 41.59, "elapsed_time": "9:40:06", "remaining_time": "13:34:48", "throughput": 657.13, "total_tokens": 22872512} {"current_steps": 16640, "total_steps": 40000, "loss": 0.6079, "lr": 3.152293315954825e-05, "epoch": 0.5326163497855451, "percentage": 41.6, "elapsed_time": "9:40:08", "remaining_time": "13:34:26", "throughput": 657.29, "total_tokens": 22879392} {"current_steps": 16645, "total_steps": 40000, "loss": 0.8985, "lr": 3.1513455245910666e-05, "epoch": 0.5327763907560336, "percentage": 41.61, "elapsed_time": "9:40:10", "remaining_time": "13:34:03", "throughput": 657.46, "total_tokens": 22886384} {"current_steps": 16650, "total_steps": 40000, "loss": 0.709, "lr": 3.150397632781643e-05, "epoch": 0.5329364317265219, "percentage": 41.62, "elapsed_time": "9:40:12", "remaining_time": "13:33:40", "throughput": 657.62, "total_tokens": 22893184} {"current_steps": 16655, "total_steps": 40000, "loss": 0.7554, "lr": 3.149449640672731e-05, "epoch": 0.5330964726970104, "percentage": 41.64, "elapsed_time": "9:40:13", "remaining_time": "13:33:17", "throughput": 657.79, "total_tokens": 22900128} {"current_steps": 16660, "total_steps": 40000, "loss": 0.5738, "lr": 3.148501548410523e-05, "epoch": 0.5332565136674989, "percentage": 41.65, "elapsed_time": "9:40:15", "remaining_time": "13:32:55", "throughput": 657.95, "total_tokens": 22906832} {"current_steps": 16665, "total_steps": 40000, "loss": 0.6316, "lr": 3.1475533561412256e-05, "epoch": 0.5334165546379873, "percentage": 41.66, "elapsed_time": "9:40:17", "remaining_time": "13:32:32", "throughput": 658.1, "total_tokens": 22913456} {"current_steps": 16670, "total_steps": 40000, "loss": 0.6273, "lr": 3.146605064011065e-05, "epoch": 0.5335765956084758, "percentage": 41.68, "elapsed_time": "9:40:19", "remaining_time": "13:32:10", "throughput": 658.26, "total_tokens": 22919984} {"current_steps": 16675, "total_steps": 40000, "loss": 0.5411, "lr": 3.145656672166277e-05, "epoch": 0.5337366365789642, "percentage": 41.69, "elapsed_time": "9:40:20", "remaining_time": "13:31:47", "throughput": 658.42, "total_tokens": 22926704} {"current_steps": 16680, "total_steps": 40000, "loss": 1.0697, "lr": 3.144708180753116e-05, "epoch": 0.5338966775494527, "percentage": 41.7, "elapsed_time": "9:40:22", "remaining_time": "13:31:24", "throughput": 658.59, "total_tokens": 22933616} {"current_steps": 16685, "total_steps": 40000, "loss": 0.8624, "lr": 3.143759589917851e-05, "epoch": 0.5340567185199411, "percentage": 41.71, "elapsed_time": "9:40:24", "remaining_time": "13:31:02", "throughput": 658.74, "total_tokens": 22940320} {"current_steps": 16690, "total_steps": 40000, "loss": 0.6893, "lr": 3.142810899806768e-05, "epoch": 0.5342167594904296, "percentage": 41.73, "elapsed_time": "9:40:26", "remaining_time": "13:30:39", "throughput": 658.91, "total_tokens": 22947344} {"current_steps": 16695, "total_steps": 40000, "loss": 0.8821, "lr": 3.141862110566166e-05, "epoch": 0.534376800460918, "percentage": 41.74, "elapsed_time": "9:40:27", "remaining_time": "13:30:17", "throughput": 659.09, "total_tokens": 22954560} {"current_steps": 16700, "total_steps": 40000, "loss": 0.5791, "lr": 3.1409132223423606e-05, "epoch": 0.5345368414314065, "percentage": 41.75, "elapsed_time": "9:40:29", "remaining_time": "13:29:54", "throughput": 659.25, "total_tokens": 22961424} {"current_steps": 16705, "total_steps": 40000, "loss": 0.6977, "lr": 3.139964235281682e-05, "epoch": 0.5346968824018948, "percentage": 41.76, "elapsed_time": "9:40:31", "remaining_time": "13:29:31", "throughput": 659.42, "total_tokens": 22968432} {"current_steps": 16710, "total_steps": 40000, "loss": 0.5898, "lr": 3.139015149530476e-05, "epoch": 0.5348569233723833, "percentage": 41.77, "elapsed_time": "9:40:32", "remaining_time": "13:29:09", "throughput": 659.58, "total_tokens": 22975072} {"current_steps": 16715, "total_steps": 40000, "loss": 0.7168, "lr": 3.1380659652351034e-05, "epoch": 0.5350169643428718, "percentage": 41.79, "elapsed_time": "9:40:34", "remaining_time": "13:28:46", "throughput": 659.74, "total_tokens": 22981728} {"current_steps": 16720, "total_steps": 40000, "loss": 0.815, "lr": 3.137116682541941e-05, "epoch": 0.5351770053133602, "percentage": 41.8, "elapsed_time": "9:40:36", "remaining_time": "13:28:24", "throughput": 659.9, "total_tokens": 22988704} {"current_steps": 16725, "total_steps": 40000, "loss": 0.634, "lr": 3.136167301597379e-05, "epoch": 0.5353370462838487, "percentage": 41.81, "elapsed_time": "9:40:38", "remaining_time": "13:28:01", "throughput": 660.08, "total_tokens": 22995888} {"current_steps": 16730, "total_steps": 40000, "loss": 0.8517, "lr": 3.1352178225478254e-05, "epoch": 0.5354970872543371, "percentage": 41.83, "elapsed_time": "9:40:39", "remaining_time": "13:27:39", "throughput": 660.24, "total_tokens": 23002544} {"current_steps": 16735, "total_steps": 40000, "loss": 0.6642, "lr": 3.1342682455396996e-05, "epoch": 0.5356571282248256, "percentage": 41.84, "elapsed_time": "9:40:41", "remaining_time": "13:27:16", "throughput": 660.39, "total_tokens": 23009248} {"current_steps": 16740, "total_steps": 40000, "loss": 0.8683, "lr": 3.133318570719441e-05, "epoch": 0.535817169195314, "percentage": 41.85, "elapsed_time": "9:40:43", "remaining_time": "13:26:54", "throughput": 660.57, "total_tokens": 23016480} {"current_steps": 16745, "total_steps": 40000, "loss": 0.6368, "lr": 3.132368798233499e-05, "epoch": 0.5359772101658025, "percentage": 41.86, "elapsed_time": "9:40:45", "remaining_time": "13:26:31", "throughput": 660.72, "total_tokens": 23022768} {"current_steps": 16750, "total_steps": 40000, "loss": 0.77, "lr": 3.131418928228342e-05, "epoch": 0.5361372511362908, "percentage": 41.88, "elapsed_time": "9:40:46", "remaining_time": "13:26:09", "throughput": 660.87, "total_tokens": 23029296} {"current_steps": 16755, "total_steps": 40000, "loss": 0.6986, "lr": 3.1304689608504514e-05, "epoch": 0.5362972921067793, "percentage": 41.89, "elapsed_time": "9:40:48", "remaining_time": "13:25:47", "throughput": 661.03, "total_tokens": 23035984} {"current_steps": 16760, "total_steps": 40000, "loss": 0.6097, "lr": 3.129518896246324e-05, "epoch": 0.5364573330772677, "percentage": 41.9, "elapsed_time": "9:40:50", "remaining_time": "13:25:24", "throughput": 661.2, "total_tokens": 23042976} {"current_steps": 16765, "total_steps": 40000, "loss": 0.7133, "lr": 3.128568734562472e-05, "epoch": 0.5366173740477562, "percentage": 41.91, "elapsed_time": "9:40:52", "remaining_time": "13:25:02", "throughput": 661.36, "total_tokens": 23049856} {"current_steps": 16770, "total_steps": 40000, "loss": 0.7166, "lr": 3.127618475945421e-05, "epoch": 0.5367774150182447, "percentage": 41.93, "elapsed_time": "9:40:53", "remaining_time": "13:24:39", "throughput": 661.52, "total_tokens": 23056592} {"current_steps": 16775, "total_steps": 40000, "loss": 0.6396, "lr": 3.126668120541715e-05, "epoch": 0.5369374559887331, "percentage": 41.94, "elapsed_time": "9:40:55", "remaining_time": "13:24:17", "throughput": 661.69, "total_tokens": 23063408} {"current_steps": 16780, "total_steps": 40000, "loss": 0.5699, "lr": 3.1257176684979096e-05, "epoch": 0.5370974969592216, "percentage": 41.95, "elapsed_time": "9:40:57", "remaining_time": "13:23:55", "throughput": 661.86, "total_tokens": 23070688} {"current_steps": 16785, "total_steps": 40000, "loss": 0.8121, "lr": 3.124767119960576e-05, "epoch": 0.53725753792971, "percentage": 41.96, "elapsed_time": "9:40:59", "remaining_time": "13:23:32", "throughput": 662.04, "total_tokens": 23077936} {"current_steps": 16790, "total_steps": 40000, "loss": 0.7715, "lr": 3.123816475076301e-05, "epoch": 0.5374175789001985, "percentage": 41.98, "elapsed_time": "9:41:00", "remaining_time": "13:23:10", "throughput": 662.2, "total_tokens": 23084768} {"current_steps": 16795, "total_steps": 40000, "loss": 0.6421, "lr": 3.122865733991687e-05, "epoch": 0.5375776198706869, "percentage": 41.99, "elapsed_time": "9:41:02", "remaining_time": "13:22:48", "throughput": 662.37, "total_tokens": 23091728} {"current_steps": 16800, "total_steps": 40000, "loss": 0.7568, "lr": 3.1219148968533486e-05, "epoch": 0.5377376608411754, "percentage": 42.0, "elapsed_time": "9:41:04", "remaining_time": "13:22:25", "throughput": 662.52, "total_tokens": 23098384} {"current_steps": 16800, "total_steps": 40000, "eval_loss": 0.7550564408302307, "epoch": 0.5377376608411754, "percentage": 42.0, "elapsed_time": "9:46:52", "remaining_time": "13:30:26", "throughput": 655.98, "total_tokens": 23098384} {"current_steps": 16805, "total_steps": 40000, "loss": 0.8091, "lr": 3.120963963807918e-05, "epoch": 0.5378977018116637, "percentage": 42.01, "elapsed_time": "9:46:55", "remaining_time": "13:30:06", "throughput": 656.1, "total_tokens": 23105040} {"current_steps": 16810, "total_steps": 40000, "loss": 0.6958, "lr": 3.12001293500204e-05, "epoch": 0.5380577427821522, "percentage": 42.02, "elapsed_time": "9:46:57", "remaining_time": "13:29:43", "throughput": 656.25, "total_tokens": 23111536} {"current_steps": 16815, "total_steps": 40000, "loss": 0.5432, "lr": 3.1190618105823765e-05, "epoch": 0.5382177837526406, "percentage": 42.04, "elapsed_time": "9:46:59", "remaining_time": "13:29:21", "throughput": 656.41, "total_tokens": 23118176} {"current_steps": 16820, "total_steps": 40000, "loss": 0.7439, "lr": 3.118110590695603e-05, "epoch": 0.5383778247231291, "percentage": 42.05, "elapsed_time": "9:47:00", "remaining_time": "13:28:58", "throughput": 656.57, "total_tokens": 23124912} {"current_steps": 16825, "total_steps": 40000, "loss": 0.5436, "lr": 3.117159275488407e-05, "epoch": 0.5385378656936176, "percentage": 42.06, "elapsed_time": "9:47:02", "remaining_time": "13:28:36", "throughput": 656.72, "total_tokens": 23131552} {"current_steps": 16830, "total_steps": 40000, "loss": 0.6719, "lr": 3.1162078651074956e-05, "epoch": 0.538697906664106, "percentage": 42.08, "elapsed_time": "9:47:04", "remaining_time": "13:28:13", "throughput": 656.89, "total_tokens": 23138592} {"current_steps": 16835, "total_steps": 40000, "loss": 0.8127, "lr": 3.1152563596995885e-05, "epoch": 0.5388579476345945, "percentage": 42.09, "elapsed_time": "9:47:06", "remaining_time": "13:27:51", "throughput": 657.06, "total_tokens": 23145680} {"current_steps": 16840, "total_steps": 40000, "loss": 0.6881, "lr": 3.1143047594114186e-05, "epoch": 0.5390179886050829, "percentage": 42.1, "elapsed_time": "9:47:07", "remaining_time": "13:27:28", "throughput": 657.22, "total_tokens": 23152400} {"current_steps": 16845, "total_steps": 40000, "loss": 0.6589, "lr": 3.113353064389734e-05, "epoch": 0.5391780295755714, "percentage": 42.11, "elapsed_time": "9:47:09", "remaining_time": "13:27:06", "throughput": 657.39, "total_tokens": 23159376} {"current_steps": 16850, "total_steps": 40000, "loss": 0.7606, "lr": 3.1124012747812993e-05, "epoch": 0.5393380705460598, "percentage": 42.12, "elapsed_time": "9:47:11", "remaining_time": "13:26:43", "throughput": 657.53, "total_tokens": 23165744} {"current_steps": 16855, "total_steps": 40000, "loss": 0.7495, "lr": 3.1114493907328936e-05, "epoch": 0.5394981115165483, "percentage": 42.14, "elapsed_time": "9:47:12", "remaining_time": "13:26:21", "throughput": 657.7, "total_tokens": 23172656} {"current_steps": 16860, "total_steps": 40000, "loss": 0.7773, "lr": 3.110497412391306e-05, "epoch": 0.5396581524870366, "percentage": 42.15, "elapsed_time": "9:47:14", "remaining_time": "13:25:58", "throughput": 657.87, "total_tokens": 23179904} {"current_steps": 16865, "total_steps": 40000, "loss": 0.6492, "lr": 3.1095453399033466e-05, "epoch": 0.5398181934575251, "percentage": 42.16, "elapsed_time": "9:47:16", "remaining_time": "13:25:36", "throughput": 658.02, "total_tokens": 23186400} {"current_steps": 16870, "total_steps": 40000, "loss": 0.621, "lr": 3.108593173415835e-05, "epoch": 0.5399782344280136, "percentage": 42.18, "elapsed_time": "9:47:18", "remaining_time": "13:25:14", "throughput": 658.19, "total_tokens": 23193296} {"current_steps": 16875, "total_steps": 40000, "loss": 0.8532, "lr": 3.107640913075609e-05, "epoch": 0.540138275398502, "percentage": 42.19, "elapsed_time": "9:47:19", "remaining_time": "13:24:51", "throughput": 658.37, "total_tokens": 23200816} {"current_steps": 16880, "total_steps": 40000, "loss": 0.8772, "lr": 3.106688559029517e-05, "epoch": 0.5402983163689905, "percentage": 42.2, "elapsed_time": "9:47:21", "remaining_time": "13:24:29", "throughput": 658.54, "total_tokens": 23207904} {"current_steps": 16885, "total_steps": 40000, "loss": 0.7214, "lr": 3.105736111424425e-05, "epoch": 0.5404583573394789, "percentage": 42.21, "elapsed_time": "9:47:23", "remaining_time": "13:24:07", "throughput": 658.69, "total_tokens": 23214448} {"current_steps": 16890, "total_steps": 40000, "loss": 0.6663, "lr": 3.1047835704072136e-05, "epoch": 0.5406183983099674, "percentage": 42.23, "elapsed_time": "9:47:25", "remaining_time": "13:23:44", "throughput": 658.86, "total_tokens": 23221776} {"current_steps": 16895, "total_steps": 40000, "loss": 0.7711, "lr": 3.103830936124775e-05, "epoch": 0.5407784392804558, "percentage": 42.24, "elapsed_time": "9:47:26", "remaining_time": "13:23:22", "throughput": 659.03, "total_tokens": 23228720} {"current_steps": 16900, "total_steps": 40000, "loss": 0.7937, "lr": 3.102878208724018e-05, "epoch": 0.5409384802509443, "percentage": 42.25, "elapsed_time": "9:47:28", "remaining_time": "13:23:00", "throughput": 659.19, "total_tokens": 23235520} {"current_steps": 16905, "total_steps": 40000, "loss": 0.6377, "lr": 3.101925388351865e-05, "epoch": 0.5410985212214326, "percentage": 42.26, "elapsed_time": "9:47:30", "remaining_time": "13:22:37", "throughput": 659.34, "total_tokens": 23242032} {"current_steps": 16910, "total_steps": 40000, "loss": 0.9246, "lr": 3.1009724751552515e-05, "epoch": 0.5412585621919211, "percentage": 42.27, "elapsed_time": "9:47:32", "remaining_time": "13:22:15", "throughput": 659.5, "total_tokens": 23248720} {"current_steps": 16915, "total_steps": 40000, "loss": 0.8552, "lr": 3.100019469281131e-05, "epoch": 0.5414186031624095, "percentage": 42.29, "elapsed_time": "9:47:33", "remaining_time": "13:21:53", "throughput": 659.66, "total_tokens": 23255488} {"current_steps": 16920, "total_steps": 40000, "loss": 0.7723, "lr": 3.0990663708764685e-05, "epoch": 0.541578644132898, "percentage": 42.3, "elapsed_time": "9:47:35", "remaining_time": "13:21:30", "throughput": 659.82, "total_tokens": 23262336} {"current_steps": 16925, "total_steps": 40000, "loss": 0.6329, "lr": 3.098113180088243e-05, "epoch": 0.5417386851033865, "percentage": 42.31, "elapsed_time": "9:47:37", "remaining_time": "13:21:08", "throughput": 659.98, "total_tokens": 23268960} {"current_steps": 16930, "total_steps": 40000, "loss": 0.5918, "lr": 3.097159897063448e-05, "epoch": 0.5418987260738749, "percentage": 42.33, "elapsed_time": "9:47:39", "remaining_time": "13:20:46", "throughput": 660.13, "total_tokens": 23275728} {"current_steps": 16935, "total_steps": 40000, "loss": 0.6015, "lr": 3.096206521949094e-05, "epoch": 0.5420587670443634, "percentage": 42.34, "elapsed_time": "9:47:40", "remaining_time": "13:20:24", "throughput": 660.29, "total_tokens": 23282496} {"current_steps": 16940, "total_steps": 40000, "loss": 0.5608, "lr": 3.0952530548922006e-05, "epoch": 0.5422188080148518, "percentage": 42.35, "elapsed_time": "9:47:42", "remaining_time": "13:20:02", "throughput": 660.46, "total_tokens": 23289520} {"current_steps": 16945, "total_steps": 40000, "loss": 0.7257, "lr": 3.0942994960398064e-05, "epoch": 0.5423788489853403, "percentage": 42.36, "elapsed_time": "9:47:44", "remaining_time": "13:19:39", "throughput": 660.62, "total_tokens": 23296336} {"current_steps": 16950, "total_steps": 40000, "loss": 0.6838, "lr": 3.093345845538961e-05, "epoch": 0.5425388899558287, "percentage": 42.38, "elapsed_time": "9:47:46", "remaining_time": "13:19:17", "throughput": 660.79, "total_tokens": 23303264} {"current_steps": 16955, "total_steps": 40000, "loss": 0.612, "lr": 3.09239210353673e-05, "epoch": 0.5426989309263172, "percentage": 42.39, "elapsed_time": "9:47:47", "remaining_time": "13:18:55", "throughput": 660.95, "total_tokens": 23310224} {"current_steps": 16960, "total_steps": 40000, "loss": 0.6901, "lr": 3.0914382701801926e-05, "epoch": 0.5428589718968055, "percentage": 42.4, "elapsed_time": "9:47:49", "remaining_time": "13:18:33", "throughput": 661.11, "total_tokens": 23317104} {"current_steps": 16965, "total_steps": 40000, "loss": 0.914, "lr": 3.090484345616441e-05, "epoch": 0.543019012867294, "percentage": 42.41, "elapsed_time": "9:47:51", "remaining_time": "13:18:11", "throughput": 661.27, "total_tokens": 23323712} {"current_steps": 16970, "total_steps": 40000, "loss": 0.658, "lr": 3.0895303299925825e-05, "epoch": 0.5431790538377824, "percentage": 42.43, "elapsed_time": "9:47:52", "remaining_time": "13:17:48", "throughput": 661.43, "total_tokens": 23330464} {"current_steps": 16975, "total_steps": 40000, "loss": 0.6651, "lr": 3.0885762234557393e-05, "epoch": 0.5433390948082709, "percentage": 42.44, "elapsed_time": "9:47:54", "remaining_time": "13:17:26", "throughput": 661.59, "total_tokens": 23337360} {"current_steps": 16980, "total_steps": 40000, "loss": 0.6196, "lr": 3.087622026153045e-05, "epoch": 0.5434991357787594, "percentage": 42.45, "elapsed_time": "9:47:56", "remaining_time": "13:17:04", "throughput": 661.76, "total_tokens": 23344416} {"current_steps": 16985, "total_steps": 40000, "loss": 0.9035, "lr": 3.086667738231651e-05, "epoch": 0.5436591767492478, "percentage": 42.46, "elapsed_time": "9:47:58", "remaining_time": "13:16:42", "throughput": 661.92, "total_tokens": 23351200} {"current_steps": 16990, "total_steps": 40000, "loss": 0.8007, "lr": 3.085713359838718e-05, "epoch": 0.5438192177197363, "percentage": 42.48, "elapsed_time": "9:47:59", "remaining_time": "13:16:20", "throughput": 662.08, "total_tokens": 23357952} {"current_steps": 16995, "total_steps": 40000, "loss": 0.7412, "lr": 3.084758891121425e-05, "epoch": 0.5439792586902247, "percentage": 42.49, "elapsed_time": "9:48:01", "remaining_time": "13:15:58", "throughput": 662.23, "total_tokens": 23364448} {"current_steps": 17000, "total_steps": 40000, "loss": 0.7415, "lr": 3.083804332226963e-05, "epoch": 0.5441392996607132, "percentage": 42.5, "elapsed_time": "9:48:03", "remaining_time": "13:15:36", "throughput": 662.38, "total_tokens": 23371136} {"current_steps": 17000, "total_steps": 40000, "eval_loss": 0.753200888633728, "epoch": 0.5441392996607132, "percentage": 42.5, "elapsed_time": "9:53:51", "remaining_time": "13:23:27", "throughput": 655.92, "total_tokens": 23371136} {"current_steps": 17005, "total_steps": 40000, "loss": 0.9123, "lr": 3.082849683302536e-05, "epoch": 0.5442993406312016, "percentage": 42.51, "elapsed_time": "9:53:54", "remaining_time": "13:23:07", "throughput": 656.05, "total_tokens": 23378064} {"current_steps": 17010, "total_steps": 40000, "loss": 0.7298, "lr": 3.081894944495363e-05, "epoch": 0.54445938160169, "percentage": 42.52, "elapsed_time": "9:53:56", "remaining_time": "13:22:44", "throughput": 656.21, "total_tokens": 23385152} {"current_steps": 17015, "total_steps": 40000, "loss": 1.1485, "lr": 3.080940115952677e-05, "epoch": 0.5446194225721784, "percentage": 42.54, "elapsed_time": "9:53:58", "remaining_time": "13:22:22", "throughput": 656.38, "total_tokens": 23392304} {"current_steps": 17020, "total_steps": 40000, "loss": 0.7755, "lr": 3.0799851978217245e-05, "epoch": 0.5447794635426669, "percentage": 42.55, "elapsed_time": "9:53:59", "remaining_time": "13:22:00", "throughput": 656.55, "total_tokens": 23399280} {"current_steps": 17025, "total_steps": 40000, "loss": 0.816, "lr": 3.0790301902497666e-05, "epoch": 0.5449395045131553, "percentage": 42.56, "elapsed_time": "9:54:01", "remaining_time": "13:21:37", "throughput": 656.72, "total_tokens": 23406592} {"current_steps": 17030, "total_steps": 40000, "loss": 1.0099, "lr": 3.078075093384076e-05, "epoch": 0.5450995454836438, "percentage": 42.58, "elapsed_time": "9:54:03", "remaining_time": "13:21:15", "throughput": 656.89, "total_tokens": 23413712} {"current_steps": 17035, "total_steps": 40000, "loss": 0.8503, "lr": 3.077119907371942e-05, "epoch": 0.5452595864541323, "percentage": 42.59, "elapsed_time": "9:54:05", "remaining_time": "13:20:53", "throughput": 657.05, "total_tokens": 23420592} {"current_steps": 17040, "total_steps": 40000, "loss": 1.018, "lr": 3.076164632360666e-05, "epoch": 0.5454196274246207, "percentage": 42.6, "elapsed_time": "9:54:06", "remaining_time": "13:20:31", "throughput": 657.21, "total_tokens": 23427664} {"current_steps": 17045, "total_steps": 40000, "loss": 0.5547, "lr": 3.075209268497563e-05, "epoch": 0.5455796683951092, "percentage": 42.61, "elapsed_time": "9:54:08", "remaining_time": "13:20:09", "throughput": 657.38, "total_tokens": 23434864} {"current_steps": 17050, "total_steps": 40000, "loss": 0.6814, "lr": 3.074253815929961e-05, "epoch": 0.5457397093655976, "percentage": 42.62, "elapsed_time": "9:54:10", "remaining_time": "13:19:46", "throughput": 657.55, "total_tokens": 23441760} {"current_steps": 17055, "total_steps": 40000, "loss": 0.752, "lr": 3.0732982748052054e-05, "epoch": 0.5458997503360861, "percentage": 42.64, "elapsed_time": "9:54:12", "remaining_time": "13:19:24", "throughput": 657.71, "total_tokens": 23448592} {"current_steps": 17060, "total_steps": 40000, "loss": 0.8019, "lr": 3.072342645270651e-05, "epoch": 0.5460597913065744, "percentage": 42.65, "elapsed_time": "9:54:13", "remaining_time": "13:19:02", "throughput": 657.87, "total_tokens": 23455440} {"current_steps": 17065, "total_steps": 40000, "loss": 0.6265, "lr": 3.071386927473668e-05, "epoch": 0.5462198322770629, "percentage": 42.66, "elapsed_time": "9:54:15", "remaining_time": "13:18:40", "throughput": 658.03, "total_tokens": 23462400} {"current_steps": 17070, "total_steps": 40000, "loss": 0.6809, "lr": 3.0704311215616404e-05, "epoch": 0.5463798732475513, "percentage": 42.68, "elapsed_time": "9:54:17", "remaining_time": "13:18:18", "throughput": 658.18, "total_tokens": 23469040} {"current_steps": 17075, "total_steps": 40000, "loss": 0.8941, "lr": 3.0694752276819656e-05, "epoch": 0.5465399142180398, "percentage": 42.69, "elapsed_time": "9:54:19", "remaining_time": "13:17:56", "throughput": 658.33, "total_tokens": 23475568} {"current_steps": 17080, "total_steps": 40000, "loss": 0.7235, "lr": 3.068519245982054e-05, "epoch": 0.5466999551885282, "percentage": 42.7, "elapsed_time": "9:54:20", "remaining_time": "13:17:33", "throughput": 658.49, "total_tokens": 23482128} {"current_steps": 17085, "total_steps": 40000, "loss": 0.7931, "lr": 3.0675631766093304e-05, "epoch": 0.5468599961590167, "percentage": 42.71, "elapsed_time": "9:54:22", "remaining_time": "13:17:11", "throughput": 658.65, "total_tokens": 23489216} {"current_steps": 17090, "total_steps": 40000, "loss": 0.7299, "lr": 3.066607019711232e-05, "epoch": 0.5470200371295052, "percentage": 42.73, "elapsed_time": "9:54:24", "remaining_time": "13:16:49", "throughput": 658.81, "total_tokens": 23495920} {"current_steps": 17095, "total_steps": 40000, "loss": 0.8006, "lr": 3.065650775435211e-05, "epoch": 0.5471800780999936, "percentage": 42.74, "elapsed_time": "9:54:25", "remaining_time": "13:16:27", "throughput": 658.96, "total_tokens": 23502640} {"current_steps": 17100, "total_steps": 40000, "loss": 0.6508, "lr": 3.0646944439287326e-05, "epoch": 0.5473401190704821, "percentage": 42.75, "elapsed_time": "9:54:27", "remaining_time": "13:16:05", "throughput": 659.12, "total_tokens": 23509296} {"current_steps": 17105, "total_steps": 40000, "loss": 0.7517, "lr": 3.0637380253392736e-05, "epoch": 0.5475001600409705, "percentage": 42.76, "elapsed_time": "9:54:29", "remaining_time": "13:15:43", "throughput": 659.27, "total_tokens": 23515856} {"current_steps": 17110, "total_steps": 40000, "loss": 0.5808, "lr": 3.062781519814327e-05, "epoch": 0.547660201011459, "percentage": 42.77, "elapsed_time": "9:54:31", "remaining_time": "13:15:21", "throughput": 659.41, "total_tokens": 23522112} {"current_steps": 17115, "total_steps": 40000, "loss": 0.6039, "lr": 3.0618249275013985e-05, "epoch": 0.5478202419819473, "percentage": 42.79, "elapsed_time": "9:54:32", "remaining_time": "13:14:59", "throughput": 659.57, "total_tokens": 23528736} {"current_steps": 17120, "total_steps": 40000, "loss": 0.6863, "lr": 3.060868248548005e-05, "epoch": 0.5479802829524358, "percentage": 42.8, "elapsed_time": "9:54:34", "remaining_time": "13:14:37", "throughput": 659.73, "total_tokens": 23535552} {"current_steps": 17125, "total_steps": 40000, "loss": 0.6316, "lr": 3.0599114831016796e-05, "epoch": 0.5481403239229242, "percentage": 42.81, "elapsed_time": "9:54:36", "remaining_time": "13:14:15", "throughput": 659.89, "total_tokens": 23542448} {"current_steps": 17130, "total_steps": 40000, "loss": 0.7516, "lr": 3.0589546313099666e-05, "epoch": 0.5483003648934127, "percentage": 42.83, "elapsed_time": "9:54:38", "remaining_time": "13:13:53", "throughput": 660.06, "total_tokens": 23549632} {"current_steps": 17135, "total_steps": 40000, "loss": 0.6761, "lr": 3.0579976933204255e-05, "epoch": 0.5484604058639012, "percentage": 42.84, "elapsed_time": "9:54:39", "remaining_time": "13:13:31", "throughput": 660.21, "total_tokens": 23556272} {"current_steps": 17140, "total_steps": 40000, "loss": 0.6632, "lr": 3.0570406692806284e-05, "epoch": 0.5486204468343896, "percentage": 42.85, "elapsed_time": "9:54:41", "remaining_time": "13:13:09", "throughput": 660.38, "total_tokens": 23563440} {"current_steps": 17145, "total_steps": 40000, "loss": 0.6976, "lr": 3.05608355933816e-05, "epoch": 0.5487804878048781, "percentage": 42.86, "elapsed_time": "9:54:43", "remaining_time": "13:12:47", "throughput": 660.55, "total_tokens": 23570528} {"current_steps": 17150, "total_steps": 40000, "loss": 0.7658, "lr": 3.055126363640618e-05, "epoch": 0.5489405287753665, "percentage": 42.88, "elapsed_time": "9:54:45", "remaining_time": "13:12:25", "throughput": 660.7, "total_tokens": 23577264} {"current_steps": 17155, "total_steps": 40000, "loss": 0.6776, "lr": 3.0541690823356146e-05, "epoch": 0.549100569745855, "percentage": 42.89, "elapsed_time": "9:54:46", "remaining_time": "13:12:03", "throughput": 660.87, "total_tokens": 23584384} {"current_steps": 17160, "total_steps": 40000, "loss": 0.717, "lr": 3.053211715570775e-05, "epoch": 0.5492606107163434, "percentage": 42.9, "elapsed_time": "9:54:48", "remaining_time": "13:11:41", "throughput": 661.04, "total_tokens": 23591600} {"current_steps": 17165, "total_steps": 40000, "loss": 0.9943, "lr": 3.052254263493736e-05, "epoch": 0.5494206516868319, "percentage": 42.91, "elapsed_time": "9:54:50", "remaining_time": "13:11:19", "throughput": 661.21, "total_tokens": 23598944} {"current_steps": 17170, "total_steps": 40000, "loss": 0.5529, "lr": 3.0512967262521498e-05, "epoch": 0.5495806926573202, "percentage": 42.93, "elapsed_time": "9:54:52", "remaining_time": "13:10:57", "throughput": 661.39, "total_tokens": 23606304} {"current_steps": 17175, "total_steps": 40000, "loss": 0.8695, "lr": 3.0503391039936803e-05, "epoch": 0.5497407336278087, "percentage": 42.94, "elapsed_time": "9:54:53", "remaining_time": "13:10:35", "throughput": 661.54, "total_tokens": 23612992} {"current_steps": 17180, "total_steps": 40000, "loss": 0.6119, "lr": 3.0493813968660056e-05, "epoch": 0.5499007745982971, "percentage": 42.95, "elapsed_time": "9:54:55", "remaining_time": "13:10:13", "throughput": 661.71, "total_tokens": 23620176} {"current_steps": 17185, "total_steps": 40000, "loss": 0.6681, "lr": 3.0484236050168153e-05, "epoch": 0.5500608155687856, "percentage": 42.96, "elapsed_time": "9:54:57", "remaining_time": "13:09:52", "throughput": 661.88, "total_tokens": 23627264} {"current_steps": 17190, "total_steps": 40000, "loss": 0.8229, "lr": 3.0474657285938123e-05, "epoch": 0.5502208565392741, "percentage": 42.98, "elapsed_time": "9:54:58", "remaining_time": "13:09:30", "throughput": 662.04, "total_tokens": 23634288} {"current_steps": 17195, "total_steps": 40000, "loss": 0.7461, "lr": 3.046507767744715e-05, "epoch": 0.5503808975097625, "percentage": 42.99, "elapsed_time": "9:55:00", "remaining_time": "13:09:08", "throughput": 662.2, "total_tokens": 23641008} {"current_steps": 17200, "total_steps": 40000, "loss": 0.5823, "lr": 3.045549722617252e-05, "epoch": 0.550540938480251, "percentage": 43.0, "elapsed_time": "9:55:02", "remaining_time": "13:08:46", "throughput": 662.36, "total_tokens": 23647856} {"current_steps": 17200, "total_steps": 40000, "eval_loss": 0.7527135014533997, "epoch": 0.550540938480251, "percentage": 43.0, "elapsed_time": "10:00:50", "remaining_time": "13:16:28", "throughput": 655.96, "total_tokens": 23647856} {"current_steps": 17205, "total_steps": 40000, "loss": 0.8936, "lr": 3.0445915933591658e-05, "epoch": 0.5507009794507394, "percentage": 43.01, "elapsed_time": "10:00:54", "remaining_time": "13:16:08", "throughput": 656.08, "total_tokens": 23654816} {"current_steps": 17210, "total_steps": 40000, "loss": 0.7895, "lr": 3.0436333801182114e-05, "epoch": 0.5508610204212279, "percentage": 43.03, "elapsed_time": "10:00:56", "remaining_time": "13:15:46", "throughput": 656.25, "total_tokens": 23661936} {"current_steps": 17215, "total_steps": 40000, "loss": 0.7266, "lr": 3.0426750830421596e-05, "epoch": 0.5510210613917162, "percentage": 43.04, "elapsed_time": "10:00:57", "remaining_time": "13:15:24", "throughput": 656.4, "total_tokens": 23668608} {"current_steps": 17220, "total_steps": 40000, "loss": 0.8504, "lr": 3.0417167022787897e-05, "epoch": 0.5511811023622047, "percentage": 43.05, "elapsed_time": "10:00:59", "remaining_time": "13:15:02", "throughput": 656.57, "total_tokens": 23675600} {"current_steps": 17225, "total_steps": 40000, "loss": 0.7795, "lr": 3.0407582379758966e-05, "epoch": 0.5513411433326931, "percentage": 43.06, "elapsed_time": "10:01:01", "remaining_time": "13:14:40", "throughput": 656.72, "total_tokens": 23682240} {"current_steps": 17230, "total_steps": 40000, "loss": 0.7689, "lr": 3.039799690281287e-05, "epoch": 0.5515011843031816, "percentage": 43.08, "elapsed_time": "10:01:03", "remaining_time": "13:14:18", "throughput": 656.87, "total_tokens": 23688816} {"current_steps": 17235, "total_steps": 40000, "loss": 1.3287, "lr": 3.0388410593427823e-05, "epoch": 0.55166122527367, "percentage": 43.09, "elapsed_time": "10:01:04", "remaining_time": "13:13:56", "throughput": 657.02, "total_tokens": 23695536} {"current_steps": 17240, "total_steps": 40000, "loss": 0.907, "lr": 3.0378823453082146e-05, "epoch": 0.5518212662441585, "percentage": 43.1, "elapsed_time": "10:01:06", "remaining_time": "13:13:34", "throughput": 657.18, "total_tokens": 23702272} {"current_steps": 17245, "total_steps": 40000, "loss": 0.6, "lr": 3.03692354832543e-05, "epoch": 0.551981307214647, "percentage": 43.11, "elapsed_time": "10:01:08", "remaining_time": "13:13:12", "throughput": 657.33, "total_tokens": 23708832} {"current_steps": 17250, "total_steps": 40000, "loss": 0.8096, "lr": 3.0359646685422865e-05, "epoch": 0.5521413481851354, "percentage": 43.12, "elapsed_time": "10:01:10", "remaining_time": "13:12:50", "throughput": 657.49, "total_tokens": 23715616} {"current_steps": 17255, "total_steps": 40000, "loss": 0.758, "lr": 3.035005706106656e-05, "epoch": 0.5523013891556239, "percentage": 43.14, "elapsed_time": "10:01:11", "remaining_time": "13:12:28", "throughput": 657.64, "total_tokens": 23722304} {"current_steps": 17260, "total_steps": 40000, "loss": 0.6253, "lr": 3.034046661166422e-05, "epoch": 0.5524614301261123, "percentage": 43.15, "elapsed_time": "10:01:13", "remaining_time": "13:12:06", "throughput": 657.79, "total_tokens": 23728752} {"current_steps": 17265, "total_steps": 40000, "loss": 0.6975, "lr": 3.033087533869482e-05, "epoch": 0.5526214710966008, "percentage": 43.16, "elapsed_time": "10:01:15", "remaining_time": "13:11:44", "throughput": 657.94, "total_tokens": 23735472} {"current_steps": 17270, "total_steps": 40000, "loss": 0.8048, "lr": 3.0321283243637444e-05, "epoch": 0.5527815120670891, "percentage": 43.18, "elapsed_time": "10:01:17", "remaining_time": "13:11:23", "throughput": 658.1, "total_tokens": 23742464} {"current_steps": 17275, "total_steps": 40000, "loss": 0.7109, "lr": 3.0311690327971326e-05, "epoch": 0.5529415530375776, "percentage": 43.19, "elapsed_time": "10:01:18", "remaining_time": "13:11:01", "throughput": 658.26, "total_tokens": 23749424} {"current_steps": 17280, "total_steps": 40000, "loss": 0.8659, "lr": 3.030209659317581e-05, "epoch": 0.553101594008066, "percentage": 43.2, "elapsed_time": "10:01:20", "remaining_time": "13:10:39", "throughput": 658.42, "total_tokens": 23756304} {"current_steps": 17285, "total_steps": 40000, "loss": 0.7808, "lr": 3.0292502040730362e-05, "epoch": 0.5532616349785545, "percentage": 43.21, "elapsed_time": "10:01:22", "remaining_time": "13:10:17", "throughput": 658.58, "total_tokens": 23762976} {"current_steps": 17290, "total_steps": 40000, "loss": 0.7461, "lr": 3.0282906672114597e-05, "epoch": 0.5534216759490429, "percentage": 43.23, "elapsed_time": "10:01:24", "remaining_time": "13:09:55", "throughput": 658.73, "total_tokens": 23769808} {"current_steps": 17295, "total_steps": 40000, "loss": 0.6561, "lr": 3.027331048880823e-05, "epoch": 0.5535817169195314, "percentage": 43.24, "elapsed_time": "10:01:25", "remaining_time": "13:09:33", "throughput": 658.89, "total_tokens": 23776688} {"current_steps": 17300, "total_steps": 40000, "loss": 0.66, "lr": 3.0263713492291123e-05, "epoch": 0.5537417578900199, "percentage": 43.25, "elapsed_time": "10:01:27", "remaining_time": "13:09:11", "throughput": 659.06, "total_tokens": 23783952} {"current_steps": 17305, "total_steps": 40000, "loss": 0.651, "lr": 3.0254115684043242e-05, "epoch": 0.5539017988605083, "percentage": 43.26, "elapsed_time": "10:01:29", "remaining_time": "13:08:50", "throughput": 659.22, "total_tokens": 23790928} {"current_steps": 17310, "total_steps": 40000, "loss": 0.573, "lr": 3.024451706554469e-05, "epoch": 0.5540618398309968, "percentage": 43.28, "elapsed_time": "10:01:31", "remaining_time": "13:08:28", "throughput": 659.39, "total_tokens": 23797888} {"current_steps": 17315, "total_steps": 40000, "loss": 0.919, "lr": 3.0234917638275705e-05, "epoch": 0.5542218808014852, "percentage": 43.29, "elapsed_time": "10:01:32", "remaining_time": "13:08:06", "throughput": 659.54, "total_tokens": 23804544} {"current_steps": 17320, "total_steps": 40000, "loss": 0.7104, "lr": 3.0225317403716635e-05, "epoch": 0.5543819217719737, "percentage": 43.3, "elapsed_time": "10:01:34", "remaining_time": "13:07:44", "throughput": 659.7, "total_tokens": 23811376} {"current_steps": 17325, "total_steps": 40000, "loss": 0.7471, "lr": 3.0215716363347956e-05, "epoch": 0.554541962742462, "percentage": 43.31, "elapsed_time": "10:01:36", "remaining_time": "13:07:22", "throughput": 659.85, "total_tokens": 23818016} {"current_steps": 17330, "total_steps": 40000, "loss": 0.8173, "lr": 3.0206114518650275e-05, "epoch": 0.5547020037129505, "percentage": 43.33, "elapsed_time": "10:01:37", "remaining_time": "13:07:01", "throughput": 660.0, "total_tokens": 23824752} {"current_steps": 17335, "total_steps": 40000, "loss": 1.0151, "lr": 3.0196511871104304e-05, "epoch": 0.5548620446834389, "percentage": 43.34, "elapsed_time": "10:01:39", "remaining_time": "13:06:39", "throughput": 660.16, "total_tokens": 23831632} {"current_steps": 17340, "total_steps": 40000, "loss": 0.772, "lr": 3.01869084221909e-05, "epoch": 0.5550220856539274, "percentage": 43.35, "elapsed_time": "10:01:41", "remaining_time": "13:06:17", "throughput": 660.31, "total_tokens": 23838240} {"current_steps": 17345, "total_steps": 40000, "loss": 0.7424, "lr": 3.0177304173391037e-05, "epoch": 0.5551821266244159, "percentage": 43.36, "elapsed_time": "10:01:43", "remaining_time": "13:05:55", "throughput": 660.48, "total_tokens": 23845424} {"current_steps": 17350, "total_steps": 40000, "loss": 0.6467, "lr": 3.01676991261858e-05, "epoch": 0.5553421675949043, "percentage": 43.38, "elapsed_time": "10:01:44", "remaining_time": "13:05:34", "throughput": 660.63, "total_tokens": 23851856} {"current_steps": 17355, "total_steps": 40000, "loss": 0.832, "lr": 3.015809328205642e-05, "epoch": 0.5555022085653928, "percentage": 43.39, "elapsed_time": "10:01:46", "remaining_time": "13:05:12", "throughput": 660.78, "total_tokens": 23858624} {"current_steps": 17360, "total_steps": 40000, "loss": 0.7546, "lr": 3.0148486642484248e-05, "epoch": 0.5556622495358812, "percentage": 43.4, "elapsed_time": "10:01:48", "remaining_time": "13:04:50", "throughput": 660.95, "total_tokens": 23865776} {"current_steps": 17365, "total_steps": 40000, "loss": 0.4327, "lr": 3.0138879208950722e-05, "epoch": 0.5558222905063697, "percentage": 43.41, "elapsed_time": "10:01:50", "remaining_time": "13:04:28", "throughput": 661.09, "total_tokens": 23872160} {"current_steps": 17370, "total_steps": 40000, "loss": 1.0015, "lr": 3.012927098293744e-05, "epoch": 0.555982331476858, "percentage": 43.43, "elapsed_time": "10:01:51", "remaining_time": "13:04:07", "throughput": 661.25, "total_tokens": 23879152} {"current_steps": 17375, "total_steps": 40000, "loss": 0.9686, "lr": 3.0119661965926123e-05, "epoch": 0.5561423724473465, "percentage": 43.44, "elapsed_time": "10:01:53", "remaining_time": "13:03:45", "throughput": 661.42, "total_tokens": 23886368} {"current_steps": 17380, "total_steps": 40000, "loss": 0.6966, "lr": 3.0110052159398587e-05, "epoch": 0.5563024134178349, "percentage": 43.45, "elapsed_time": "10:01:55", "remaining_time": "13:03:23", "throughput": 661.58, "total_tokens": 23893088} {"current_steps": 17385, "total_steps": 40000, "loss": 0.7324, "lr": 3.0100441564836802e-05, "epoch": 0.5564624543883234, "percentage": 43.46, "elapsed_time": "10:01:57", "remaining_time": "13:03:02", "throughput": 661.73, "total_tokens": 23899728} {"current_steps": 17390, "total_steps": 40000, "loss": 0.8879, "lr": 3.0090830183722817e-05, "epoch": 0.5566224953588118, "percentage": 43.48, "elapsed_time": "10:01:58", "remaining_time": "13:02:40", "throughput": 661.9, "total_tokens": 23906896} {"current_steps": 17395, "total_steps": 40000, "loss": 0.6417, "lr": 3.0081218017538852e-05, "epoch": 0.5567825363293003, "percentage": 43.49, "elapsed_time": "10:02:00", "remaining_time": "13:02:19", "throughput": 662.05, "total_tokens": 23913776} {"current_steps": 17400, "total_steps": 40000, "loss": 0.6466, "lr": 3.0071605067767212e-05, "epoch": 0.5569425772997888, "percentage": 43.5, "elapsed_time": "10:02:02", "remaining_time": "13:01:57", "throughput": 662.22, "total_tokens": 23921008} {"current_steps": 17400, "total_steps": 40000, "eval_loss": 0.7517740726470947, "epoch": 0.5569425772997888, "percentage": 43.5, "elapsed_time": "10:07:49", "remaining_time": "13:09:28", "throughput": 655.91, "total_tokens": 23921008} {"current_steps": 17405, "total_steps": 40000, "loss": 0.8063, "lr": 3.006199133589034e-05, "epoch": 0.5571026182702772, "percentage": 43.51, "elapsed_time": "10:07:53", "remaining_time": "13:09:09", "throughput": 656.04, "total_tokens": 23928048} {"current_steps": 17410, "total_steps": 40000, "loss": 0.7181, "lr": 3.005237682339079e-05, "epoch": 0.5572626592407657, "percentage": 43.53, "elapsed_time": "10:07:55", "remaining_time": "13:08:47", "throughput": 656.19, "total_tokens": 23934816} {"current_steps": 17415, "total_steps": 40000, "loss": 0.7043, "lr": 3.0042761531751228e-05, "epoch": 0.5574227002112541, "percentage": 43.54, "elapsed_time": "10:07:56", "remaining_time": "13:08:25", "throughput": 656.35, "total_tokens": 23941632} {"current_steps": 17420, "total_steps": 40000, "loss": 0.9368, "lr": 3.0033145462454482e-05, "epoch": 0.5575827411817426, "percentage": 43.55, "elapsed_time": "10:07:58", "remaining_time": "13:08:04", "throughput": 656.5, "total_tokens": 23948416} {"current_steps": 17425, "total_steps": 40000, "loss": 0.7905, "lr": 3.002352861698345e-05, "epoch": 0.5577427821522309, "percentage": 43.56, "elapsed_time": "10:08:00", "remaining_time": "13:07:42", "throughput": 656.66, "total_tokens": 23955104} {"current_steps": 17430, "total_steps": 40000, "loss": 0.957, "lr": 3.0013910996821178e-05, "epoch": 0.5579028231227194, "percentage": 43.58, "elapsed_time": "10:08:02", "remaining_time": "13:07:20", "throughput": 656.81, "total_tokens": 23961664} {"current_steps": 17435, "total_steps": 40000, "loss": 0.8448, "lr": 3.0004292603450817e-05, "epoch": 0.5580628640932078, "percentage": 43.59, "elapsed_time": "10:08:03", "remaining_time": "13:06:58", "throughput": 656.96, "total_tokens": 23968352} {"current_steps": 17440, "total_steps": 40000, "loss": 0.7021, "lr": 2.9994673438355653e-05, "epoch": 0.5582229050636963, "percentage": 43.6, "elapsed_time": "10:08:05", "remaining_time": "13:06:36", "throughput": 657.12, "total_tokens": 23975344} {"current_steps": 17445, "total_steps": 40000, "loss": 0.7537, "lr": 2.9985053503019078e-05, "epoch": 0.5583829460341847, "percentage": 43.61, "elapsed_time": "10:08:07", "remaining_time": "13:06:15", "throughput": 657.27, "total_tokens": 23981904} {"current_steps": 17450, "total_steps": 40000, "loss": 0.7356, "lr": 2.99754327989246e-05, "epoch": 0.5585429870046732, "percentage": 43.62, "elapsed_time": "10:08:09", "remaining_time": "13:05:53", "throughput": 657.43, "total_tokens": 23988912} {"current_steps": 17455, "total_steps": 40000, "loss": 0.7546, "lr": 2.9965811327555864e-05, "epoch": 0.5587030279751617, "percentage": 43.64, "elapsed_time": "10:08:10", "remaining_time": "13:05:31", "throughput": 657.58, "total_tokens": 23995680} {"current_steps": 17460, "total_steps": 40000, "loss": 0.8557, "lr": 2.995618909039662e-05, "epoch": 0.5588630689456501, "percentage": 43.65, "elapsed_time": "10:08:12", "remaining_time": "13:05:10", "throughput": 657.74, "total_tokens": 24002480} {"current_steps": 17465, "total_steps": 40000, "loss": 0.6664, "lr": 2.9946566088930727e-05, "epoch": 0.5590231099161386, "percentage": 43.66, "elapsed_time": "10:08:14", "remaining_time": "13:04:48", "throughput": 657.89, "total_tokens": 24009360} {"current_steps": 17470, "total_steps": 40000, "loss": 0.5772, "lr": 2.9936942324642192e-05, "epoch": 0.559183150886627, "percentage": 43.68, "elapsed_time": "10:08:16", "remaining_time": "13:04:26", "throughput": 658.04, "total_tokens": 24015856} {"current_steps": 17475, "total_steps": 40000, "loss": 1.0224, "lr": 2.9927317799015097e-05, "epoch": 0.5593431918571155, "percentage": 43.69, "elapsed_time": "10:08:17", "remaining_time": "13:04:05", "throughput": 658.2, "total_tokens": 24022736} {"current_steps": 17480, "total_steps": 40000, "loss": 0.9288, "lr": 2.9917692513533685e-05, "epoch": 0.5595032328276038, "percentage": 43.7, "elapsed_time": "10:08:19", "remaining_time": "13:03:43", "throughput": 658.36, "total_tokens": 24029728} {"current_steps": 17485, "total_steps": 40000, "loss": 0.7183, "lr": 2.990806646968229e-05, "epoch": 0.5596632737980923, "percentage": 43.71, "elapsed_time": "10:08:21", "remaining_time": "13:03:21", "throughput": 658.52, "total_tokens": 24036608} {"current_steps": 17490, "total_steps": 40000, "loss": 0.7435, "lr": 2.989843966894536e-05, "epoch": 0.5598233147685807, "percentage": 43.73, "elapsed_time": "10:08:22", "remaining_time": "13:03:00", "throughput": 658.67, "total_tokens": 24043408} {"current_steps": 17495, "total_steps": 40000, "loss": 0.6422, "lr": 2.9888812112807472e-05, "epoch": 0.5599833557390692, "percentage": 43.74, "elapsed_time": "10:08:24", "remaining_time": "13:02:38", "throughput": 658.84, "total_tokens": 24050720} {"current_steps": 17500, "total_steps": 40000, "loss": 0.7022, "lr": 2.987918380275333e-05, "epoch": 0.5601433967095576, "percentage": 43.75, "elapsed_time": "10:08:26", "remaining_time": "13:02:16", "throughput": 659.0, "total_tokens": 24057616} {"current_steps": 17505, "total_steps": 40000, "loss": 0.7736, "lr": 2.9869554740267724e-05, "epoch": 0.5603034376800461, "percentage": 43.76, "elapsed_time": "10:08:28", "remaining_time": "13:01:55", "throughput": 659.17, "total_tokens": 24064944} {"current_steps": 17510, "total_steps": 40000, "loss": 0.7884, "lr": 2.9859924926835585e-05, "epoch": 0.5604634786505346, "percentage": 43.77, "elapsed_time": "10:08:29", "remaining_time": "13:01:33", "throughput": 659.33, "total_tokens": 24072128} {"current_steps": 17515, "total_steps": 40000, "loss": 0.728, "lr": 2.9850294363941944e-05, "epoch": 0.560623519621023, "percentage": 43.79, "elapsed_time": "10:08:31", "remaining_time": "13:01:12", "throughput": 659.49, "total_tokens": 24079136} {"current_steps": 17520, "total_steps": 40000, "loss": 0.7675, "lr": 2.9840663053071967e-05, "epoch": 0.5607835605915115, "percentage": 43.8, "elapsed_time": "10:08:33", "remaining_time": "13:00:50", "throughput": 659.64, "total_tokens": 24085728} {"current_steps": 17525, "total_steps": 40000, "loss": 0.7282, "lr": 2.983103099571091e-05, "epoch": 0.5609436015619998, "percentage": 43.81, "elapsed_time": "10:08:35", "remaining_time": "13:00:28", "throughput": 659.8, "total_tokens": 24092768} {"current_steps": 17530, "total_steps": 40000, "loss": 0.7112, "lr": 2.9821398193344164e-05, "epoch": 0.5611036425324883, "percentage": 43.82, "elapsed_time": "10:08:36", "remaining_time": "13:00:07", "throughput": 659.98, "total_tokens": 24100224} {"current_steps": 17535, "total_steps": 40000, "loss": 0.7019, "lr": 2.9811764647457226e-05, "epoch": 0.5612636835029767, "percentage": 43.84, "elapsed_time": "10:08:38", "remaining_time": "12:59:45", "throughput": 660.13, "total_tokens": 24106928} {"current_steps": 17540, "total_steps": 40000, "loss": 1.003, "lr": 2.9802130359535714e-05, "epoch": 0.5614237244734652, "percentage": 43.85, "elapsed_time": "10:08:40", "remaining_time": "12:59:24", "throughput": 660.28, "total_tokens": 24113744} {"current_steps": 17545, "total_steps": 40000, "loss": 0.6217, "lr": 2.979249533106535e-05, "epoch": 0.5615837654439536, "percentage": 43.86, "elapsed_time": "10:08:42", "remaining_time": "12:59:02", "throughput": 660.45, "total_tokens": 24120832} {"current_steps": 17550, "total_steps": 40000, "loss": 0.7344, "lr": 2.9782859563531986e-05, "epoch": 0.5617438064144421, "percentage": 43.88, "elapsed_time": "10:08:43", "remaining_time": "12:58:41", "throughput": 660.59, "total_tokens": 24127376} {"current_steps": 17555, "total_steps": 40000, "loss": 0.6801, "lr": 2.977322305842156e-05, "epoch": 0.5619038473849305, "percentage": 43.89, "elapsed_time": "10:08:45", "remaining_time": "12:58:19", "throughput": 660.74, "total_tokens": 24134032} {"current_steps": 17560, "total_steps": 40000, "loss": 0.8445, "lr": 2.9763585817220162e-05, "epoch": 0.562063888355419, "percentage": 43.9, "elapsed_time": "10:08:47", "remaining_time": "12:57:58", "throughput": 660.89, "total_tokens": 24140496} {"current_steps": 17565, "total_steps": 40000, "loss": 0.6509, "lr": 2.975394784141397e-05, "epoch": 0.5622239293259075, "percentage": 43.91, "elapsed_time": "10:08:48", "remaining_time": "12:57:36", "throughput": 661.04, "total_tokens": 24147072} {"current_steps": 17570, "total_steps": 40000, "loss": 0.7943, "lr": 2.974430913248928e-05, "epoch": 0.5623839702963959, "percentage": 43.92, "elapsed_time": "10:08:50", "remaining_time": "12:57:15", "throughput": 661.18, "total_tokens": 24153328} {"current_steps": 17575, "total_steps": 40000, "loss": 0.7777, "lr": 2.9734669691932497e-05, "epoch": 0.5625440112668844, "percentage": 43.94, "elapsed_time": "10:08:52", "remaining_time": "12:56:53", "throughput": 661.33, "total_tokens": 24160048} {"current_steps": 17580, "total_steps": 40000, "loss": 0.8141, "lr": 2.9725029521230147e-05, "epoch": 0.5627040522373727, "percentage": 43.95, "elapsed_time": "10:08:54", "remaining_time": "12:56:32", "throughput": 661.49, "total_tokens": 24166992} {"current_steps": 17585, "total_steps": 40000, "loss": 0.9996, "lr": 2.9715388621868873e-05, "epoch": 0.5628640932078612, "percentage": 43.96, "elapsed_time": "10:08:55", "remaining_time": "12:56:11", "throughput": 661.65, "total_tokens": 24173840} {"current_steps": 17590, "total_steps": 40000, "loss": 0.8277, "lr": 2.970574699533541e-05, "epoch": 0.5630241341783496, "percentage": 43.97, "elapsed_time": "10:08:57", "remaining_time": "12:55:49", "throughput": 661.81, "total_tokens": 24180800} {"current_steps": 17595, "total_steps": 40000, "loss": 0.6262, "lr": 2.969610464311662e-05, "epoch": 0.5631841751488381, "percentage": 43.99, "elapsed_time": "10:08:59", "remaining_time": "12:55:28", "throughput": 661.97, "total_tokens": 24187824} {"current_steps": 17600, "total_steps": 40000, "loss": 0.7807, "lr": 2.9686461566699487e-05, "epoch": 0.5633442161193265, "percentage": 44.0, "elapsed_time": "10:09:01", "remaining_time": "12:55:06", "throughput": 662.12, "total_tokens": 24194480} {"current_steps": 17600, "total_steps": 40000, "eval_loss": 0.7514320015907288, "epoch": 0.5633442161193265, "percentage": 44.0, "elapsed_time": "10:14:48", "remaining_time": "13:02:29", "throughput": 655.88, "total_tokens": 24194480} {"current_steps": 17605, "total_steps": 40000, "loss": 0.8254, "lr": 2.9676817767571086e-05, "epoch": 0.563504257089815, "percentage": 44.01, "elapsed_time": "10:14:52", "remaining_time": "13:02:09", "throughput": 656.0, "total_tokens": 24201216} {"current_steps": 17610, "total_steps": 40000, "loss": 0.6697, "lr": 2.966717324721861e-05, "epoch": 0.5636642980603035, "percentage": 44.02, "elapsed_time": "10:14:53", "remaining_time": "13:01:48", "throughput": 656.16, "total_tokens": 24208272} {"current_steps": 17615, "total_steps": 40000, "loss": 0.8739, "lr": 2.9657528007129366e-05, "epoch": 0.5638243390307919, "percentage": 44.04, "elapsed_time": "10:14:55", "remaining_time": "13:01:26", "throughput": 656.31, "total_tokens": 24215040} {"current_steps": 17620, "total_steps": 40000, "loss": 0.6043, "lr": 2.9647882048790777e-05, "epoch": 0.5639843800012804, "percentage": 44.05, "elapsed_time": "10:14:57", "remaining_time": "13:01:04", "throughput": 656.48, "total_tokens": 24222224} {"current_steps": 17625, "total_steps": 40000, "loss": 0.5624, "lr": 2.963823537369037e-05, "epoch": 0.5641444209717688, "percentage": 44.06, "elapsed_time": "10:14:58", "remaining_time": "13:00:43", "throughput": 656.63, "total_tokens": 24228864} {"current_steps": 17630, "total_steps": 40000, "loss": 0.8724, "lr": 2.9628587983315775e-05, "epoch": 0.5643044619422573, "percentage": 44.07, "elapsed_time": "10:15:00", "remaining_time": "13:00:21", "throughput": 656.78, "total_tokens": 24235568} {"current_steps": 17635, "total_steps": 40000, "loss": 0.8132, "lr": 2.9618939879154746e-05, "epoch": 0.5644645029127456, "percentage": 44.09, "elapsed_time": "10:15:02", "remaining_time": "13:00:00", "throughput": 656.93, "total_tokens": 24242208} {"current_steps": 17640, "total_steps": 40000, "loss": 0.7689, "lr": 2.9609291062695143e-05, "epoch": 0.5646245438832341, "percentage": 44.1, "elapsed_time": "10:15:04", "remaining_time": "12:59:38", "throughput": 657.08, "total_tokens": 24249024} {"current_steps": 17645, "total_steps": 40000, "loss": 0.646, "lr": 2.9599641535424938e-05, "epoch": 0.5647845848537225, "percentage": 44.11, "elapsed_time": "10:15:05", "remaining_time": "12:59:17", "throughput": 657.23, "total_tokens": 24255744} {"current_steps": 17650, "total_steps": 40000, "loss": 0.8459, "lr": 2.9589991298832202e-05, "epoch": 0.564944625824211, "percentage": 44.12, "elapsed_time": "10:15:07", "remaining_time": "12:58:55", "throughput": 657.39, "total_tokens": 24262736} {"current_steps": 17655, "total_steps": 40000, "loss": 0.8876, "lr": 2.958034035440513e-05, "epoch": 0.5651046667946994, "percentage": 44.14, "elapsed_time": "10:15:09", "remaining_time": "12:58:34", "throughput": 657.55, "total_tokens": 24269776} {"current_steps": 17660, "total_steps": 40000, "loss": 0.7358, "lr": 2.957068870363201e-05, "epoch": 0.5652647077651879, "percentage": 44.15, "elapsed_time": "10:15:11", "remaining_time": "12:58:12", "throughput": 657.7, "total_tokens": 24276320} {"current_steps": 17665, "total_steps": 40000, "loss": 0.778, "lr": 2.956103634800126e-05, "epoch": 0.5654247487356764, "percentage": 44.16, "elapsed_time": "10:15:12", "remaining_time": "12:57:51", "throughput": 657.85, "total_tokens": 24283040} {"current_steps": 17670, "total_steps": 40000, "loss": 0.836, "lr": 2.9551383289001384e-05, "epoch": 0.5655847897061648, "percentage": 44.17, "elapsed_time": "10:15:14", "remaining_time": "12:57:29", "throughput": 658.0, "total_tokens": 24289904} {"current_steps": 17675, "total_steps": 40000, "loss": 0.555, "lr": 2.9541729528121005e-05, "epoch": 0.5657448306766533, "percentage": 44.19, "elapsed_time": "10:15:16", "remaining_time": "12:57:08", "throughput": 658.17, "total_tokens": 24297280} {"current_steps": 17680, "total_steps": 40000, "loss": 0.7138, "lr": 2.9532075066848856e-05, "epoch": 0.5659048716471416, "percentage": 44.2, "elapsed_time": "10:15:18", "remaining_time": "12:56:46", "throughput": 658.33, "total_tokens": 24304160} {"current_steps": 17685, "total_steps": 40000, "loss": 0.7213, "lr": 2.9522419906673786e-05, "epoch": 0.5660649126176301, "percentage": 44.21, "elapsed_time": "10:15:19", "remaining_time": "12:56:25", "throughput": 658.49, "total_tokens": 24311136} {"current_steps": 17690, "total_steps": 40000, "loss": 0.6182, "lr": 2.951276404908474e-05, "epoch": 0.5662249535881185, "percentage": 44.22, "elapsed_time": "10:15:21", "remaining_time": "12:56:04", "throughput": 658.65, "total_tokens": 24318336} {"current_steps": 17695, "total_steps": 40000, "loss": 0.7847, "lr": 2.9503107495570752e-05, "epoch": 0.566384994558607, "percentage": 44.24, "elapsed_time": "10:15:23", "remaining_time": "12:55:42", "throughput": 658.8, "total_tokens": 24325040} {"current_steps": 17700, "total_steps": 40000, "loss": 0.6807, "lr": 2.9493450247621003e-05, "epoch": 0.5665450355290954, "percentage": 44.25, "elapsed_time": "10:15:24", "remaining_time": "12:55:21", "throughput": 658.95, "total_tokens": 24331824} {"current_steps": 17705, "total_steps": 40000, "loss": 0.7409, "lr": 2.948379230672476e-05, "epoch": 0.5667050764995839, "percentage": 44.26, "elapsed_time": "10:15:26", "remaining_time": "12:54:59", "throughput": 659.12, "total_tokens": 24339024} {"current_steps": 17710, "total_steps": 40000, "loss": 0.5999, "lr": 2.9474133674371396e-05, "epoch": 0.5668651174700723, "percentage": 44.27, "elapsed_time": "10:15:28", "remaining_time": "12:54:38", "throughput": 659.27, "total_tokens": 24345920} {"current_steps": 17715, "total_steps": 40000, "loss": 0.752, "lr": 2.9464474352050387e-05, "epoch": 0.5670251584405608, "percentage": 44.29, "elapsed_time": "10:15:30", "remaining_time": "12:54:17", "throughput": 659.43, "total_tokens": 24352816} {"current_steps": 17720, "total_steps": 40000, "loss": 0.7905, "lr": 2.9454814341251336e-05, "epoch": 0.5671851994110493, "percentage": 44.3, "elapsed_time": "10:15:32", "remaining_time": "12:53:56", "throughput": 659.58, "total_tokens": 24359600} {"current_steps": 17725, "total_steps": 40000, "loss": 0.8502, "lr": 2.9445153643463942e-05, "epoch": 0.5673452403815377, "percentage": 44.31, "elapsed_time": "10:15:33", "remaining_time": "12:53:34", "throughput": 659.74, "total_tokens": 24366672} {"current_steps": 17730, "total_steps": 40000, "loss": 0.6531, "lr": 2.943549226017798e-05, "epoch": 0.5675052813520262, "percentage": 44.32, "elapsed_time": "10:15:35", "remaining_time": "12:53:13", "throughput": 659.89, "total_tokens": 24373456} {"current_steps": 17735, "total_steps": 40000, "loss": 0.8071, "lr": 2.942583019288337e-05, "epoch": 0.5676653223225145, "percentage": 44.34, "elapsed_time": "10:15:37", "remaining_time": "12:52:52", "throughput": 660.04, "total_tokens": 24380336} {"current_steps": 17740, "total_steps": 40000, "loss": 0.7401, "lr": 2.9416167443070132e-05, "epoch": 0.567825363293003, "percentage": 44.35, "elapsed_time": "10:15:39", "remaining_time": "12:52:30", "throughput": 660.19, "total_tokens": 24386896} {"current_steps": 17745, "total_steps": 40000, "loss": 0.727, "lr": 2.9406504012228375e-05, "epoch": 0.5679854042634914, "percentage": 44.36, "elapsed_time": "10:15:40", "remaining_time": "12:52:09", "throughput": 660.35, "total_tokens": 24393808} {"current_steps": 17750, "total_steps": 40000, "loss": 0.8175, "lr": 2.939683990184832e-05, "epoch": 0.5681454452339799, "percentage": 44.38, "elapsed_time": "10:15:42", "remaining_time": "12:51:48", "throughput": 660.5, "total_tokens": 24400432} {"current_steps": 17755, "total_steps": 40000, "loss": 0.6083, "lr": 2.93871751134203e-05, "epoch": 0.5683054862044683, "percentage": 44.39, "elapsed_time": "10:15:44", "remaining_time": "12:51:27", "throughput": 660.65, "total_tokens": 24407424} {"current_steps": 17760, "total_steps": 40000, "loss": 0.5837, "lr": 2.9377509648434752e-05, "epoch": 0.5684655271749568, "percentage": 44.4, "elapsed_time": "10:15:46", "remaining_time": "12:51:05", "throughput": 660.8, "total_tokens": 24413872} {"current_steps": 17765, "total_steps": 40000, "loss": 0.7373, "lr": 2.9367843508382203e-05, "epoch": 0.5686255681454452, "percentage": 44.41, "elapsed_time": "10:15:47", "remaining_time": "12:50:44", "throughput": 660.95, "total_tokens": 24420656} {"current_steps": 17770, "total_steps": 40000, "loss": 0.7523, "lr": 2.9358176694753293e-05, "epoch": 0.5687856091159337, "percentage": 44.42, "elapsed_time": "10:15:49", "remaining_time": "12:50:23", "throughput": 661.12, "total_tokens": 24428000} {"current_steps": 17775, "total_steps": 40000, "loss": 0.8347, "lr": 2.9348509209038766e-05, "epoch": 0.5689456500864222, "percentage": 44.44, "elapsed_time": "10:15:51", "remaining_time": "12:50:02", "throughput": 661.27, "total_tokens": 24434944} {"current_steps": 17780, "total_steps": 40000, "loss": 0.764, "lr": 2.933884105272947e-05, "epoch": 0.5691056910569106, "percentage": 44.45, "elapsed_time": "10:15:53", "remaining_time": "12:49:40", "throughput": 661.44, "total_tokens": 24442240} {"current_steps": 17785, "total_steps": 40000, "loss": 0.767, "lr": 2.9329172227316366e-05, "epoch": 0.569265732027399, "percentage": 44.46, "elapsed_time": "10:15:54", "remaining_time": "12:49:19", "throughput": 661.59, "total_tokens": 24449072} {"current_steps": 17790, "total_steps": 40000, "loss": 0.6547, "lr": 2.93195027342905e-05, "epoch": 0.5694257729978874, "percentage": 44.47, "elapsed_time": "10:15:56", "remaining_time": "12:48:58", "throughput": 661.74, "total_tokens": 24455568} {"current_steps": 17795, "total_steps": 40000, "loss": 0.7396, "lr": 2.9309832575143024e-05, "epoch": 0.5695858139683759, "percentage": 44.49, "elapsed_time": "10:15:58", "remaining_time": "12:48:37", "throughput": 661.89, "total_tokens": 24462272} {"current_steps": 17800, "total_steps": 40000, "loss": 0.7174, "lr": 2.930016175136521e-05, "epoch": 0.5697458549388643, "percentage": 44.5, "elapsed_time": "10:15:59", "remaining_time": "12:48:16", "throughput": 662.05, "total_tokens": 24469312} {"current_steps": 17800, "total_steps": 40000, "eval_loss": 0.7505316138267517, "epoch": 0.5697458549388643, "percentage": 44.5, "elapsed_time": "10:21:47", "remaining_time": "12:55:29", "throughput": 655.88, "total_tokens": 24469312} {"current_steps": 17805, "total_steps": 40000, "loss": 0.7002, "lr": 2.9290490264448412e-05, "epoch": 0.5699058959093528, "percentage": 44.51, "elapsed_time": "10:21:51", "remaining_time": "12:55:10", "throughput": 656.0, "total_tokens": 24476128} {"current_steps": 17810, "total_steps": 40000, "loss": 0.8619, "lr": 2.9280818115884094e-05, "epoch": 0.5700659368798412, "percentage": 44.52, "elapsed_time": "10:21:53", "remaining_time": "12:54:49", "throughput": 656.15, "total_tokens": 24483152} {"current_steps": 17815, "total_steps": 40000, "loss": 0.5961, "lr": 2.9271145307163828e-05, "epoch": 0.5702259778503297, "percentage": 44.54, "elapsed_time": "10:21:54", "remaining_time": "12:54:28", "throughput": 656.3, "total_tokens": 24489920} {"current_steps": 17820, "total_steps": 40000, "loss": 0.6175, "lr": 2.9261471839779287e-05, "epoch": 0.5703860188208181, "percentage": 44.55, "elapsed_time": "10:21:56", "remaining_time": "12:54:06", "throughput": 656.46, "total_tokens": 24496752} {"current_steps": 17825, "total_steps": 40000, "loss": 0.5511, "lr": 2.925179771522223e-05, "epoch": 0.5705460597913066, "percentage": 44.56, "elapsed_time": "10:21:58", "remaining_time": "12:53:45", "throughput": 656.59, "total_tokens": 24502912} {"current_steps": 17830, "total_steps": 40000, "loss": 0.7455, "lr": 2.9242122934984535e-05, "epoch": 0.5707061007617951, "percentage": 44.57, "elapsed_time": "10:22:00", "remaining_time": "12:53:24", "throughput": 656.74, "total_tokens": 24509568} {"current_steps": 17835, "total_steps": 40000, "loss": 0.5971, "lr": 2.9232447500558176e-05, "epoch": 0.5708661417322834, "percentage": 44.59, "elapsed_time": "10:22:01", "remaining_time": "12:53:02", "throughput": 656.9, "total_tokens": 24516784} {"current_steps": 17840, "total_steps": 40000, "loss": 0.6426, "lr": 2.9222771413435225e-05, "epoch": 0.571026182702772, "percentage": 44.6, "elapsed_time": "10:22:03", "remaining_time": "12:52:41", "throughput": 657.05, "total_tokens": 24523600} {"current_steps": 17845, "total_steps": 40000, "loss": 0.7562, "lr": 2.9213094675107848e-05, "epoch": 0.5711862236732603, "percentage": 44.61, "elapsed_time": "10:22:05", "remaining_time": "12:52:20", "throughput": 657.21, "total_tokens": 24530512} {"current_steps": 17850, "total_steps": 40000, "loss": 0.668, "lr": 2.9203417287068335e-05, "epoch": 0.5713462646437488, "percentage": 44.62, "elapsed_time": "10:22:07", "remaining_time": "12:51:58", "throughput": 657.36, "total_tokens": 24537312} {"current_steps": 17855, "total_steps": 40000, "loss": 0.5444, "lr": 2.9193739250809042e-05, "epoch": 0.5715063056142372, "percentage": 44.64, "elapsed_time": "10:22:08", "remaining_time": "12:51:37", "throughput": 657.51, "total_tokens": 24543920} {"current_steps": 17860, "total_steps": 40000, "loss": 0.7944, "lr": 2.9184060567822463e-05, "epoch": 0.5716663465847257, "percentage": 44.65, "elapsed_time": "10:22:10", "remaining_time": "12:51:16", "throughput": 657.66, "total_tokens": 24550688} {"current_steps": 17865, "total_steps": 40000, "loss": 0.6351, "lr": 2.9174381239601166e-05, "epoch": 0.5718263875552141, "percentage": 44.66, "elapsed_time": "10:22:12", "remaining_time": "12:50:55", "throughput": 657.82, "total_tokens": 24558048} {"current_steps": 17870, "total_steps": 40000, "loss": 0.6666, "lr": 2.916470126763783e-05, "epoch": 0.5719864285257026, "percentage": 44.67, "elapsed_time": "10:22:13", "remaining_time": "12:50:33", "throughput": 657.97, "total_tokens": 24564784} {"current_steps": 17875, "total_steps": 40000, "loss": 0.8462, "lr": 2.9155020653425203e-05, "epoch": 0.5721464694961911, "percentage": 44.69, "elapsed_time": "10:22:15", "remaining_time": "12:50:12", "throughput": 658.12, "total_tokens": 24571552} {"current_steps": 17880, "total_steps": 40000, "loss": 0.8137, "lr": 2.9145339398456184e-05, "epoch": 0.5723065104666795, "percentage": 44.7, "elapsed_time": "10:22:17", "remaining_time": "12:49:51", "throughput": 658.28, "total_tokens": 24578320} {"current_steps": 17885, "total_steps": 40000, "loss": 0.6956, "lr": 2.913565750422374e-05, "epoch": 0.572466551437168, "percentage": 44.71, "elapsed_time": "10:22:19", "remaining_time": "12:49:30", "throughput": 658.42, "total_tokens": 24585008} {"current_steps": 17890, "total_steps": 40000, "loss": 0.7423, "lr": 2.9125974972220938e-05, "epoch": 0.5726265924076563, "percentage": 44.73, "elapsed_time": "10:22:20", "remaining_time": "12:49:09", "throughput": 658.57, "total_tokens": 24591792} {"current_steps": 17895, "total_steps": 40000, "loss": 0.7861, "lr": 2.9116291803940932e-05, "epoch": 0.5727866333781448, "percentage": 44.74, "elapsed_time": "10:22:22", "remaining_time": "12:48:47", "throughput": 658.74, "total_tokens": 24598944} {"current_steps": 17900, "total_steps": 40000, "loss": 0.6952, "lr": 2.910660800087701e-05, "epoch": 0.5729466743486332, "percentage": 44.75, "elapsed_time": "10:22:24", "remaining_time": "12:48:26", "throughput": 658.88, "total_tokens": 24605520} {"current_steps": 17905, "total_steps": 40000, "loss": 0.8364, "lr": 2.909692356452254e-05, "epoch": 0.5731067153191217, "percentage": 44.76, "elapsed_time": "10:22:26", "remaining_time": "12:48:05", "throughput": 659.04, "total_tokens": 24612464} {"current_steps": 17910, "total_steps": 40000, "loss": 0.6886, "lr": 2.9087238496370962e-05, "epoch": 0.5732667562896101, "percentage": 44.77, "elapsed_time": "10:22:27", "remaining_time": "12:47:44", "throughput": 659.19, "total_tokens": 24619440} {"current_steps": 17915, "total_steps": 40000, "loss": 0.8449, "lr": 2.907755279791583e-05, "epoch": 0.5734267972600986, "percentage": 44.79, "elapsed_time": "10:22:29", "remaining_time": "12:47:23", "throughput": 659.35, "total_tokens": 24626384} {"current_steps": 17920, "total_steps": 40000, "loss": 0.8073, "lr": 2.906786647065083e-05, "epoch": 0.573586838230587, "percentage": 44.8, "elapsed_time": "10:22:31", "remaining_time": "12:47:02", "throughput": 659.51, "total_tokens": 24633392} {"current_steps": 17925, "total_steps": 40000, "loss": 0.8845, "lr": 2.9058179516069695e-05, "epoch": 0.5737468792010755, "percentage": 44.81, "elapsed_time": "10:22:33", "remaining_time": "12:46:41", "throughput": 659.66, "total_tokens": 24640192} {"current_steps": 17930, "total_steps": 40000, "loss": 0.5851, "lr": 2.9048491935666282e-05, "epoch": 0.573906920171564, "percentage": 44.82, "elapsed_time": "10:22:34", "remaining_time": "12:46:19", "throughput": 659.81, "total_tokens": 24647232} {"current_steps": 17935, "total_steps": 40000, "loss": 0.6143, "lr": 2.9038803730934534e-05, "epoch": 0.5740669611420524, "percentage": 44.84, "elapsed_time": "10:22:36", "remaining_time": "12:45:58", "throughput": 659.97, "total_tokens": 24654208} {"current_steps": 17940, "total_steps": 40000, "loss": 0.859, "lr": 2.9029114903368503e-05, "epoch": 0.5742270021125409, "percentage": 44.85, "elapsed_time": "10:22:38", "remaining_time": "12:45:37", "throughput": 660.13, "total_tokens": 24661200} {"current_steps": 17945, "total_steps": 40000, "loss": 0.8365, "lr": 2.9019425454462318e-05, "epoch": 0.5743870430830292, "percentage": 44.86, "elapsed_time": "10:22:40", "remaining_time": "12:45:16", "throughput": 660.28, "total_tokens": 24667888} {"current_steps": 17950, "total_steps": 40000, "loss": 0.6712, "lr": 2.9009735385710212e-05, "epoch": 0.5745470840535177, "percentage": 44.88, "elapsed_time": "10:22:41", "remaining_time": "12:44:55", "throughput": 660.45, "total_tokens": 24675472} {"current_steps": 17955, "total_steps": 40000, "loss": 0.8231, "lr": 2.900004469860652e-05, "epoch": 0.5747071250240061, "percentage": 44.89, "elapsed_time": "10:22:43", "remaining_time": "12:44:34", "throughput": 660.6, "total_tokens": 24682288} {"current_steps": 17960, "total_steps": 40000, "loss": 0.9536, "lr": 2.8990353394645668e-05, "epoch": 0.5748671659944946, "percentage": 44.9, "elapsed_time": "10:22:45", "remaining_time": "12:44:13", "throughput": 660.76, "total_tokens": 24689328} {"current_steps": 17965, "total_steps": 40000, "loss": 0.8061, "lr": 2.8980661475322186e-05, "epoch": 0.575027206964983, "percentage": 44.91, "elapsed_time": "10:22:46", "remaining_time": "12:43:52", "throughput": 660.9, "total_tokens": 24695680} {"current_steps": 17970, "total_steps": 40000, "loss": 0.8071, "lr": 2.897096894213067e-05, "epoch": 0.5751872479354715, "percentage": 44.92, "elapsed_time": "10:22:48", "remaining_time": "12:43:31", "throughput": 661.05, "total_tokens": 24702480} {"current_steps": 17975, "total_steps": 40000, "loss": 0.6737, "lr": 2.8961275796565845e-05, "epoch": 0.5753472889059599, "percentage": 44.94, "elapsed_time": "10:22:50", "remaining_time": "12:43:10", "throughput": 661.2, "total_tokens": 24709312} {"current_steps": 17980, "total_steps": 40000, "loss": 0.6563, "lr": 2.8951582040122517e-05, "epoch": 0.5755073298764484, "percentage": 44.95, "elapsed_time": "10:22:52", "remaining_time": "12:42:49", "throughput": 661.35, "total_tokens": 24715920} {"current_steps": 17985, "total_steps": 40000, "loss": 0.6111, "lr": 2.894188767429557e-05, "epoch": 0.5756673708469369, "percentage": 44.96, "elapsed_time": "10:22:53", "remaining_time": "12:42:28", "throughput": 661.49, "total_tokens": 24722464} {"current_steps": 17990, "total_steps": 40000, "loss": 0.7521, "lr": 2.8932192700580014e-05, "epoch": 0.5758274118174252, "percentage": 44.98, "elapsed_time": "10:22:55", "remaining_time": "12:42:07", "throughput": 661.65, "total_tokens": 24729392} {"current_steps": 17995, "total_steps": 40000, "loss": 0.6523, "lr": 2.8922497120470916e-05, "epoch": 0.5759874527879137, "percentage": 44.99, "elapsed_time": "10:22:57", "remaining_time": "12:41:46", "throughput": 661.8, "total_tokens": 24736496} {"current_steps": 18000, "total_steps": 40000, "loss": 0.7576, "lr": 2.891280093546348e-05, "epoch": 0.5761474937584021, "percentage": 45.0, "elapsed_time": "10:22:59", "remaining_time": "12:41:25", "throughput": 661.96, "total_tokens": 24743360} {"current_steps": 18000, "total_steps": 40000, "eval_loss": 0.750076949596405, "epoch": 0.5761474937584021, "percentage": 45.0, "elapsed_time": "10:28:46", "remaining_time": "12:48:30", "throughput": 655.85, "total_tokens": 24743360} {"current_steps": 18005, "total_steps": 40000, "loss": 0.5564, "lr": 2.890310414705297e-05, "epoch": 0.5763075347288906, "percentage": 45.01, "elapsed_time": "10:28:50", "remaining_time": "12:48:11", "throughput": 656.0, "total_tokens": 24750928} {"current_steps": 18010, "total_steps": 40000, "loss": 0.9775, "lr": 2.8893406756734742e-05, "epoch": 0.576467575699379, "percentage": 45.02, "elapsed_time": "10:28:52", "remaining_time": "12:47:50", "throughput": 656.15, "total_tokens": 24758096} {"current_steps": 18015, "total_steps": 40000, "loss": 0.7022, "lr": 2.888370876600427e-05, "epoch": 0.5766276166698675, "percentage": 45.04, "elapsed_time": "10:28:53", "remaining_time": "12:47:29", "throughput": 656.32, "total_tokens": 24765552} {"current_steps": 18020, "total_steps": 40000, "loss": 0.713, "lr": 2.8874010176357104e-05, "epoch": 0.5767876576403559, "percentage": 45.05, "elapsed_time": "10:28:55", "remaining_time": "12:47:08", "throughput": 656.49, "total_tokens": 24773040} {"current_steps": 18025, "total_steps": 40000, "loss": 0.8217, "lr": 2.886431098928888e-05, "epoch": 0.5769476986108444, "percentage": 45.06, "elapsed_time": "10:28:57", "remaining_time": "12:46:47", "throughput": 656.63, "total_tokens": 24779600} {"current_steps": 18030, "total_steps": 40000, "loss": 0.6155, "lr": 2.885461120629534e-05, "epoch": 0.5771077395813328, "percentage": 45.07, "elapsed_time": "10:28:59", "remaining_time": "12:46:25", "throughput": 656.78, "total_tokens": 24786368} {"current_steps": 18035, "total_steps": 40000, "loss": 0.7029, "lr": 2.8844910828872317e-05, "epoch": 0.5772677805518213, "percentage": 45.09, "elapsed_time": "10:29:00", "remaining_time": "12:46:04", "throughput": 656.95, "total_tokens": 24793920} {"current_steps": 18040, "total_steps": 40000, "loss": 0.7079, "lr": 2.8835209858515715e-05, "epoch": 0.5774278215223098, "percentage": 45.1, "elapsed_time": "10:29:02", "remaining_time": "12:45:43", "throughput": 657.12, "total_tokens": 24801232} {"current_steps": 18045, "total_steps": 40000, "loss": 0.8166, "lr": 2.8825508296721566e-05, "epoch": 0.5775878624927981, "percentage": 45.11, "elapsed_time": "10:29:04", "remaining_time": "12:45:22", "throughput": 657.27, "total_tokens": 24808176} {"current_steps": 18050, "total_steps": 40000, "loss": 0.6339, "lr": 2.881580614498596e-05, "epoch": 0.5777479034632866, "percentage": 45.12, "elapsed_time": "10:29:05", "remaining_time": "12:45:01", "throughput": 657.42, "total_tokens": 24814944} {"current_steps": 18055, "total_steps": 40000, "loss": 0.8591, "lr": 2.8806103404805103e-05, "epoch": 0.577907944433775, "percentage": 45.14, "elapsed_time": "10:29:07", "remaining_time": "12:44:40", "throughput": 657.56, "total_tokens": 24821552} {"current_steps": 18060, "total_steps": 40000, "loss": 0.7915, "lr": 2.8796400077675257e-05, "epoch": 0.5780679854042635, "percentage": 45.15, "elapsed_time": "10:29:09", "remaining_time": "12:44:19", "throughput": 657.72, "total_tokens": 24828432} {"current_steps": 18065, "total_steps": 40000, "loss": 0.6186, "lr": 2.8786696165092812e-05, "epoch": 0.5782280263747519, "percentage": 45.16, "elapsed_time": "10:29:11", "remaining_time": "12:43:58", "throughput": 657.86, "total_tokens": 24835152} {"current_steps": 18070, "total_steps": 40000, "loss": 0.6254, "lr": 2.8776991668554236e-05, "epoch": 0.5783880673452404, "percentage": 45.17, "elapsed_time": "10:29:12", "remaining_time": "12:43:37", "throughput": 658.02, "total_tokens": 24842224} {"current_steps": 18075, "total_steps": 40000, "loss": 0.6829, "lr": 2.876728658955608e-05, "epoch": 0.5785481083157288, "percentage": 45.19, "elapsed_time": "10:29:14", "remaining_time": "12:43:16", "throughput": 658.18, "total_tokens": 24849232} {"current_steps": 18080, "total_steps": 40000, "loss": 0.8361, "lr": 2.8757580929594986e-05, "epoch": 0.5787081492862173, "percentage": 45.2, "elapsed_time": "10:29:16", "remaining_time": "12:42:55", "throughput": 658.32, "total_tokens": 24855936} {"current_steps": 18085, "total_steps": 40000, "loss": 0.7624, "lr": 2.87478746901677e-05, "epoch": 0.5788681902567057, "percentage": 45.21, "elapsed_time": "10:29:18", "remaining_time": "12:42:34", "throughput": 658.48, "total_tokens": 24863024} {"current_steps": 18090, "total_steps": 40000, "loss": 0.6774, "lr": 2.873816787277103e-05, "epoch": 0.5790282312271942, "percentage": 45.23, "elapsed_time": "10:29:19", "remaining_time": "12:42:13", "throughput": 658.62, "total_tokens": 24869280} {"current_steps": 18095, "total_steps": 40000, "loss": 0.7534, "lr": 2.8728460478901903e-05, "epoch": 0.5791882721976827, "percentage": 45.24, "elapsed_time": "10:29:21", "remaining_time": "12:41:52", "throughput": 658.77, "total_tokens": 24876096} {"current_steps": 18100, "total_steps": 40000, "loss": 0.7932, "lr": 2.8718752510057307e-05, "epoch": 0.579348313168171, "percentage": 45.25, "elapsed_time": "10:29:23", "remaining_time": "12:41:31", "throughput": 658.92, "total_tokens": 24882928} {"current_steps": 18105, "total_steps": 40000, "loss": 0.5639, "lr": 2.870904396773435e-05, "epoch": 0.5795083541386595, "percentage": 45.26, "elapsed_time": "10:29:25", "remaining_time": "12:41:10", "throughput": 659.07, "total_tokens": 24889968} {"current_steps": 18110, "total_steps": 40000, "loss": 0.6356, "lr": 2.86993348534302e-05, "epoch": 0.5796683951091479, "percentage": 45.27, "elapsed_time": "10:29:26", "remaining_time": "12:40:49", "throughput": 659.22, "total_tokens": 24896432} {"current_steps": 18115, "total_steps": 40000, "loss": 0.7274, "lr": 2.868962516864212e-05, "epoch": 0.5798284360796364, "percentage": 45.29, "elapsed_time": "10:29:28", "remaining_time": "12:40:28", "throughput": 659.36, "total_tokens": 24902992} {"current_steps": 18120, "total_steps": 40000, "loss": 0.8901, "lr": 2.8679914914867477e-05, "epoch": 0.5799884770501248, "percentage": 45.3, "elapsed_time": "10:29:30", "remaining_time": "12:40:07", "throughput": 659.51, "total_tokens": 24909856} {"current_steps": 18125, "total_steps": 40000, "loss": 0.783, "lr": 2.8670204093603713e-05, "epoch": 0.5801485180206133, "percentage": 45.31, "elapsed_time": "10:29:31", "remaining_time": "12:39:46", "throughput": 659.66, "total_tokens": 24916800} {"current_steps": 18130, "total_steps": 40000, "loss": 0.6269, "lr": 2.8660492706348357e-05, "epoch": 0.5803085589911017, "percentage": 45.32, "elapsed_time": "10:29:33", "remaining_time": "12:39:25", "throughput": 659.82, "total_tokens": 24923712} {"current_steps": 18135, "total_steps": 40000, "loss": 0.7806, "lr": 2.8650780754599022e-05, "epoch": 0.5804685999615902, "percentage": 45.34, "elapsed_time": "10:29:35", "remaining_time": "12:39:05", "throughput": 659.96, "total_tokens": 24930256} {"current_steps": 18140, "total_steps": 40000, "loss": 0.68, "lr": 2.8641068239853407e-05, "epoch": 0.5806286409320787, "percentage": 45.35, "elapsed_time": "10:29:37", "remaining_time": "12:38:44", "throughput": 660.11, "total_tokens": 24936976} {"current_steps": 18145, "total_steps": 40000, "loss": 0.804, "lr": 2.863135516360932e-05, "epoch": 0.580788681902567, "percentage": 45.36, "elapsed_time": "10:29:38", "remaining_time": "12:38:23", "throughput": 660.26, "total_tokens": 24943712} {"current_steps": 18150, "total_steps": 40000, "loss": 0.8723, "lr": 2.8621641527364633e-05, "epoch": 0.5809487228730555, "percentage": 45.38, "elapsed_time": "10:29:40", "remaining_time": "12:38:02", "throughput": 660.4, "total_tokens": 24950432} {"current_steps": 18155, "total_steps": 40000, "loss": 0.7549, "lr": 2.8611927332617313e-05, "epoch": 0.5811087638435439, "percentage": 45.39, "elapsed_time": "10:29:42", "remaining_time": "12:37:41", "throughput": 660.56, "total_tokens": 24957360} {"current_steps": 18160, "total_steps": 40000, "loss": 0.9237, "lr": 2.8602212580865405e-05, "epoch": 0.5812688048140324, "percentage": 45.4, "elapsed_time": "10:29:44", "remaining_time": "12:37:20", "throughput": 660.72, "total_tokens": 24964768} {"current_steps": 18165, "total_steps": 40000, "loss": 0.8063, "lr": 2.859249727360705e-05, "epoch": 0.5814288457845208, "percentage": 45.41, "elapsed_time": "10:29:45", "remaining_time": "12:36:59", "throughput": 660.88, "total_tokens": 24971952} {"current_steps": 18170, "total_steps": 40000, "loss": 0.6009, "lr": 2.8582781412340465e-05, "epoch": 0.5815888867550093, "percentage": 45.42, "elapsed_time": "10:29:47", "remaining_time": "12:36:39", "throughput": 661.02, "total_tokens": 24978480} {"current_steps": 18175, "total_steps": 40000, "loss": 0.7797, "lr": 2.857306499856397e-05, "epoch": 0.5817489277254977, "percentage": 45.44, "elapsed_time": "10:29:49", "remaining_time": "12:36:18", "throughput": 661.19, "total_tokens": 24985760} {"current_steps": 18180, "total_steps": 40000, "loss": 0.5712, "lr": 2.856334803377594e-05, "epoch": 0.5819089686959862, "percentage": 45.45, "elapsed_time": "10:29:51", "remaining_time": "12:35:57", "throughput": 661.35, "total_tokens": 24993104} {"current_steps": 18185, "total_steps": 40000, "loss": 0.5999, "lr": 2.8553630519474867e-05, "epoch": 0.5820690096664746, "percentage": 45.46, "elapsed_time": "10:29:52", "remaining_time": "12:35:36", "throughput": 661.49, "total_tokens": 24999632} {"current_steps": 18190, "total_steps": 40000, "loss": 0.818, "lr": 2.8543912457159317e-05, "epoch": 0.5822290506369631, "percentage": 45.48, "elapsed_time": "10:29:54", "remaining_time": "12:35:15", "throughput": 661.64, "total_tokens": 25006512} {"current_steps": 18195, "total_steps": 40000, "loss": 0.6908, "lr": 2.853419384832792e-05, "epoch": 0.5823890916074516, "percentage": 45.49, "elapsed_time": "10:29:56", "remaining_time": "12:34:55", "throughput": 661.8, "total_tokens": 25013360} {"current_steps": 18200, "total_steps": 40000, "loss": 0.961, "lr": 2.8524474694479423e-05, "epoch": 0.5825491325779399, "percentage": 45.5, "elapsed_time": "10:29:57", "remaining_time": "12:34:34", "throughput": 661.95, "total_tokens": 25020352} {"current_steps": 18200, "total_steps": 40000, "eval_loss": 0.7496914267539978, "epoch": 0.5825491325779399, "percentage": 45.5, "elapsed_time": "10:35:45", "remaining_time": "12:41:30", "throughput": 655.92, "total_tokens": 25020352} {"current_steps": 18205, "total_steps": 40000, "loss": 0.6989, "lr": 2.851475499711264e-05, "epoch": 0.5827091735484284, "percentage": 45.51, "elapsed_time": "10:35:49", "remaining_time": "12:41:11", "throughput": 656.04, "total_tokens": 25027344} {"current_steps": 18210, "total_steps": 40000, "loss": 0.5761, "lr": 2.8505034757726468e-05, "epoch": 0.5828692145189168, "percentage": 45.52, "elapsed_time": "10:35:50", "remaining_time": "12:40:50", "throughput": 656.19, "total_tokens": 25034048} {"current_steps": 18215, "total_steps": 40000, "loss": 0.6794, "lr": 2.8495313977819886e-05, "epoch": 0.5830292554894053, "percentage": 45.54, "elapsed_time": "10:35:52", "remaining_time": "12:40:30", "throughput": 656.33, "total_tokens": 25040736} {"current_steps": 18220, "total_steps": 40000, "loss": 0.739, "lr": 2.8485592658891956e-05, "epoch": 0.5831892964598937, "percentage": 45.55, "elapsed_time": "10:35:54", "remaining_time": "12:40:09", "throughput": 656.49, "total_tokens": 25047776} {"current_steps": 18225, "total_steps": 40000, "loss": 0.7653, "lr": 2.8475870802441844e-05, "epoch": 0.5833493374303822, "percentage": 45.56, "elapsed_time": "10:35:55", "remaining_time": "12:39:48", "throughput": 656.65, "total_tokens": 25055280} {"current_steps": 18230, "total_steps": 40000, "loss": 0.6648, "lr": 2.8466148409968774e-05, "epoch": 0.5835093784008706, "percentage": 45.57, "elapsed_time": "10:35:57", "remaining_time": "12:39:27", "throughput": 656.8, "total_tokens": 25062064} {"current_steps": 18235, "total_steps": 40000, "loss": 0.6114, "lr": 2.8456425482972067e-05, "epoch": 0.5836694193713591, "percentage": 45.59, "elapsed_time": "10:35:59", "remaining_time": "12:39:06", "throughput": 656.95, "total_tokens": 25068864} {"current_steps": 18240, "total_steps": 40000, "loss": 0.721, "lr": 2.84467020229511e-05, "epoch": 0.5838294603418475, "percentage": 45.6, "elapsed_time": "10:36:01", "remaining_time": "12:38:45", "throughput": 657.1, "total_tokens": 25075872} {"current_steps": 18245, "total_steps": 40000, "loss": 0.5625, "lr": 2.8436978031405375e-05, "epoch": 0.583989501312336, "percentage": 45.61, "elapsed_time": "10:36:02", "remaining_time": "12:38:24", "throughput": 657.27, "total_tokens": 25083184} {"current_steps": 18250, "total_steps": 40000, "loss": 0.6452, "lr": 2.842725350983445e-05, "epoch": 0.5841495422828245, "percentage": 45.62, "elapsed_time": "10:36:04", "remaining_time": "12:38:03", "throughput": 657.42, "total_tokens": 25090000} {"current_steps": 18255, "total_steps": 40000, "loss": 0.7681, "lr": 2.8417528459737957e-05, "epoch": 0.5843095832533128, "percentage": 45.64, "elapsed_time": "10:36:06", "remaining_time": "12:37:43", "throughput": 657.56, "total_tokens": 25096544} {"current_steps": 18260, "total_steps": 40000, "loss": 0.6463, "lr": 2.8407802882615624e-05, "epoch": 0.5844696242238013, "percentage": 45.65, "elapsed_time": "10:36:08", "remaining_time": "12:37:22", "throughput": 657.7, "total_tokens": 25103056} {"current_steps": 18265, "total_steps": 40000, "loss": 0.9415, "lr": 2.8398076779967277e-05, "epoch": 0.5846296651942897, "percentage": 45.66, "elapsed_time": "10:36:09", "remaining_time": "12:37:01", "throughput": 657.85, "total_tokens": 25109920} {"current_steps": 18270, "total_steps": 40000, "loss": 0.7554, "lr": 2.8388350153292774e-05, "epoch": 0.5847897061647782, "percentage": 45.67, "elapsed_time": "10:36:11", "remaining_time": "12:36:40", "throughput": 657.99, "total_tokens": 25116368} {"current_steps": 18275, "total_steps": 40000, "loss": 0.8289, "lr": 2.8378623004092103e-05, "epoch": 0.5849497471352666, "percentage": 45.69, "elapsed_time": "10:36:13", "remaining_time": "12:36:19", "throughput": 658.14, "total_tokens": 25123232} {"current_steps": 18280, "total_steps": 40000, "loss": 0.5439, "lr": 2.8368895333865302e-05, "epoch": 0.5851097881057551, "percentage": 45.7, "elapsed_time": "10:36:15", "remaining_time": "12:35:58", "throughput": 658.28, "total_tokens": 25129936} {"current_steps": 18285, "total_steps": 40000, "loss": 0.7328, "lr": 2.835916714411251e-05, "epoch": 0.5852698290762435, "percentage": 45.71, "elapsed_time": "10:36:16", "remaining_time": "12:35:38", "throughput": 658.43, "total_tokens": 25136704} {"current_steps": 18290, "total_steps": 40000, "loss": 0.8135, "lr": 2.8349438436333926e-05, "epoch": 0.585429870046732, "percentage": 45.73, "elapsed_time": "10:36:18", "remaining_time": "12:35:17", "throughput": 658.57, "total_tokens": 25143136} {"current_steps": 18295, "total_steps": 40000, "loss": 0.9086, "lr": 2.833970921202984e-05, "epoch": 0.5855899110172204, "percentage": 45.74, "elapsed_time": "10:36:20", "remaining_time": "12:34:56", "throughput": 658.72, "total_tokens": 25150032} {"current_steps": 18300, "total_steps": 40000, "loss": 0.5983, "lr": 2.8329979472700628e-05, "epoch": 0.5857499519877089, "percentage": 45.75, "elapsed_time": "10:36:21", "remaining_time": "12:34:35", "throughput": 658.87, "total_tokens": 25156864} {"current_steps": 18305, "total_steps": 40000, "loss": 0.6229, "lr": 2.832024921984674e-05, "epoch": 0.5859099929581973, "percentage": 45.76, "elapsed_time": "10:36:23", "remaining_time": "12:34:15", "throughput": 659.02, "total_tokens": 25163920} {"current_steps": 18310, "total_steps": 40000, "loss": 0.832, "lr": 2.8310518454968693e-05, "epoch": 0.5860700339286857, "percentage": 45.77, "elapsed_time": "10:36:25", "remaining_time": "12:33:54", "throughput": 659.17, "total_tokens": 25170816} {"current_steps": 18315, "total_steps": 40000, "loss": 0.6582, "lr": 2.8300787179567095e-05, "epoch": 0.5862300748991742, "percentage": 45.79, "elapsed_time": "10:36:27", "remaining_time": "12:33:33", "throughput": 659.33, "total_tokens": 25177808} {"current_steps": 18320, "total_steps": 40000, "loss": 0.7135, "lr": 2.8291055395142636e-05, "epoch": 0.5863901158696626, "percentage": 45.8, "elapsed_time": "10:36:28", "remaining_time": "12:33:13", "throughput": 659.48, "total_tokens": 25184848} {"current_steps": 18325, "total_steps": 40000, "loss": 0.7689, "lr": 2.8281323103196073e-05, "epoch": 0.5865501568401511, "percentage": 45.81, "elapsed_time": "10:36:30", "remaining_time": "12:32:52", "throughput": 659.62, "total_tokens": 25191456} {"current_steps": 18330, "total_steps": 40000, "loss": 0.8356, "lr": 2.8271590305228256e-05, "epoch": 0.5867101978106395, "percentage": 45.82, "elapsed_time": "10:36:32", "remaining_time": "12:32:31", "throughput": 659.78, "total_tokens": 25198544} {"current_steps": 18335, "total_steps": 40000, "loss": 0.6681, "lr": 2.82618570027401e-05, "epoch": 0.586870238781128, "percentage": 45.84, "elapsed_time": "10:36:34", "remaining_time": "12:32:10", "throughput": 659.93, "total_tokens": 25205536} {"current_steps": 18340, "total_steps": 40000, "loss": 0.7362, "lr": 2.8252123197232604e-05, "epoch": 0.5870302797516164, "percentage": 45.85, "elapsed_time": "10:36:35", "remaining_time": "12:31:50", "throughput": 660.08, "total_tokens": 25212528} {"current_steps": 18345, "total_steps": 40000, "loss": 0.6466, "lr": 2.8242388890206843e-05, "epoch": 0.5871903207221049, "percentage": 45.86, "elapsed_time": "10:36:37", "remaining_time": "12:31:29", "throughput": 660.24, "total_tokens": 25219648} {"current_steps": 18350, "total_steps": 40000, "loss": 0.905, "lr": 2.8232654083163967e-05, "epoch": 0.5873503616925934, "percentage": 45.88, "elapsed_time": "10:36:39", "remaining_time": "12:31:09", "throughput": 660.39, "total_tokens": 25226624} {"current_steps": 18355, "total_steps": 40000, "loss": 0.7697, "lr": 2.822291877760521e-05, "epoch": 0.5875104026630817, "percentage": 45.89, "elapsed_time": "10:36:41", "remaining_time": "12:30:48", "throughput": 660.54, "total_tokens": 25233312} {"current_steps": 18360, "total_steps": 40000, "loss": 0.5748, "lr": 2.8213182975031864e-05, "epoch": 0.5876704436335702, "percentage": 45.9, "elapsed_time": "10:36:42", "remaining_time": "12:30:27", "throughput": 660.69, "total_tokens": 25240176} {"current_steps": 18365, "total_steps": 40000, "loss": 0.8185, "lr": 2.8203446676945337e-05, "epoch": 0.5878304846040586, "percentage": 45.91, "elapsed_time": "10:36:44", "remaining_time": "12:30:07", "throughput": 660.85, "total_tokens": 25247552} {"current_steps": 18370, "total_steps": 40000, "loss": 0.6914, "lr": 2.8193709884847075e-05, "epoch": 0.5879905255745471, "percentage": 45.92, "elapsed_time": "10:36:46", "remaining_time": "12:29:46", "throughput": 660.99, "total_tokens": 25253840} {"current_steps": 18375, "total_steps": 40000, "loss": 0.9035, "lr": 2.8183972600238605e-05, "epoch": 0.5881505665450355, "percentage": 45.94, "elapsed_time": "10:36:48", "remaining_time": "12:29:25", "throughput": 661.14, "total_tokens": 25260880} {"current_steps": 18380, "total_steps": 40000, "loss": 0.6551, "lr": 2.817423482462156e-05, "epoch": 0.588310607515524, "percentage": 45.95, "elapsed_time": "10:36:49", "remaining_time": "12:29:05", "throughput": 661.28, "total_tokens": 25267520} {"current_steps": 18385, "total_steps": 40000, "loss": 0.8263, "lr": 2.8164496559497605e-05, "epoch": 0.5884706484860124, "percentage": 45.96, "elapsed_time": "10:36:51", "remaining_time": "12:28:44", "throughput": 661.44, "total_tokens": 25274688} {"current_steps": 18390, "total_steps": 40000, "loss": 0.9251, "lr": 2.815475780636852e-05, "epoch": 0.5886306894565009, "percentage": 45.98, "elapsed_time": "10:36:53", "remaining_time": "12:28:24", "throughput": 661.6, "total_tokens": 25281712} {"current_steps": 18395, "total_steps": 40000, "loss": 0.6997, "lr": 2.814501856673613e-05, "epoch": 0.5887907304269893, "percentage": 45.99, "elapsed_time": "10:36:55", "remaining_time": "12:28:03", "throughput": 661.75, "total_tokens": 25288832} {"current_steps": 18400, "total_steps": 40000, "loss": 0.9696, "lr": 2.8135278842102353e-05, "epoch": 0.5889507713974778, "percentage": 46.0, "elapsed_time": "10:36:56", "remaining_time": "12:27:43", "throughput": 661.91, "total_tokens": 25295920} {"current_steps": 18400, "total_steps": 40000, "eval_loss": 0.74904465675354, "epoch": 0.5889507713974778, "percentage": 46.0, "elapsed_time": "10:42:44", "remaining_time": "12:34:30", "throughput": 655.95, "total_tokens": 25295920} {"current_steps": 18405, "total_steps": 40000, "loss": 0.5838, "lr": 2.8125538633969183e-05, "epoch": 0.5891108123679663, "percentage": 46.01, "elapsed_time": "10:42:47", "remaining_time": "12:34:12", "throughput": 656.06, "total_tokens": 25302784} {"current_steps": 18410, "total_steps": 40000, "loss": 0.6335, "lr": 2.8115797943838677e-05, "epoch": 0.5892708533384546, "percentage": 46.02, "elapsed_time": "10:42:49", "remaining_time": "12:33:51", "throughput": 656.2, "total_tokens": 25309408} {"current_steps": 18415, "total_steps": 40000, "loss": 0.6354, "lr": 2.810605677321298e-05, "epoch": 0.5894308943089431, "percentage": 46.04, "elapsed_time": "10:42:51", "remaining_time": "12:33:30", "throughput": 656.36, "total_tokens": 25316656} {"current_steps": 18420, "total_steps": 40000, "loss": 0.7084, "lr": 2.809631512359428e-05, "epoch": 0.5895909352794315, "percentage": 46.05, "elapsed_time": "10:42:52", "remaining_time": "12:33:10", "throughput": 656.51, "total_tokens": 25323376} {"current_steps": 18425, "total_steps": 40000, "loss": 0.5278, "lr": 2.8086572996484884e-05, "epoch": 0.58975097624992, "percentage": 46.06, "elapsed_time": "10:42:54", "remaining_time": "12:32:49", "throughput": 656.66, "total_tokens": 25330288} {"current_steps": 18430, "total_steps": 40000, "loss": 0.8291, "lr": 2.8076830393387143e-05, "epoch": 0.5899110172204084, "percentage": 46.08, "elapsed_time": "10:42:56", "remaining_time": "12:32:28", "throughput": 656.8, "total_tokens": 25336960} {"current_steps": 18435, "total_steps": 40000, "loss": 0.7687, "lr": 2.8067087315803497e-05, "epoch": 0.5900710581908969, "percentage": 46.09, "elapsed_time": "10:42:58", "remaining_time": "12:32:08", "throughput": 656.95, "total_tokens": 25343808} {"current_steps": 18440, "total_steps": 40000, "loss": 0.7695, "lr": 2.8057343765236433e-05, "epoch": 0.5902310991613853, "percentage": 46.1, "elapsed_time": "10:42:59", "remaining_time": "12:31:47", "throughput": 657.09, "total_tokens": 25350576} {"current_steps": 18445, "total_steps": 40000, "loss": 0.8036, "lr": 2.804759974318854e-05, "epoch": 0.5903911401318738, "percentage": 46.11, "elapsed_time": "10:43:01", "remaining_time": "12:31:26", "throughput": 657.26, "total_tokens": 25357952} {"current_steps": 18450, "total_steps": 40000, "loss": 0.6583, "lr": 2.8037855251162482e-05, "epoch": 0.5905511811023622, "percentage": 46.12, "elapsed_time": "10:43:03", "remaining_time": "12:31:06", "throughput": 657.41, "total_tokens": 25364880} {"current_steps": 18455, "total_steps": 40000, "loss": 0.6972, "lr": 2.802811029066096e-05, "epoch": 0.5907112220728507, "percentage": 46.14, "elapsed_time": "10:43:05", "remaining_time": "12:30:45", "throughput": 657.55, "total_tokens": 25371696} {"current_steps": 18460, "total_steps": 40000, "loss": 0.6855, "lr": 2.8018364863186764e-05, "epoch": 0.5908712630433391, "percentage": 46.15, "elapsed_time": "10:43:06", "remaining_time": "12:30:24", "throughput": 657.71, "total_tokens": 25379056} {"current_steps": 18465, "total_steps": 40000, "loss": 0.8136, "lr": 2.800861897024279e-05, "epoch": 0.5910313040138275, "percentage": 46.16, "elapsed_time": "10:43:08", "remaining_time": "12:30:04", "throughput": 657.86, "total_tokens": 25385888} {"current_steps": 18470, "total_steps": 40000, "loss": 0.5083, "lr": 2.799887261333196e-05, "epoch": 0.591191344984316, "percentage": 46.17, "elapsed_time": "10:43:10", "remaining_time": "12:29:43", "throughput": 658.01, "total_tokens": 25392768} {"current_steps": 18475, "total_steps": 40000, "loss": 0.867, "lr": 2.798912579395728e-05, "epoch": 0.5913513859548044, "percentage": 46.19, "elapsed_time": "10:43:11", "remaining_time": "12:29:23", "throughput": 658.16, "total_tokens": 25399744} {"current_steps": 18480, "total_steps": 40000, "loss": 0.9193, "lr": 2.797937851362185e-05, "epoch": 0.5915114269252929, "percentage": 46.2, "elapsed_time": "10:43:13", "remaining_time": "12:29:02", "throughput": 658.31, "total_tokens": 25406656} {"current_steps": 18485, "total_steps": 40000, "loss": 0.8031, "lr": 2.7969630773828802e-05, "epoch": 0.5916714678957813, "percentage": 46.21, "elapsed_time": "10:43:15", "remaining_time": "12:28:41", "throughput": 658.46, "total_tokens": 25413536} {"current_steps": 18490, "total_steps": 40000, "loss": 0.5306, "lr": 2.7959882576081382e-05, "epoch": 0.5918315088662698, "percentage": 46.23, "elapsed_time": "10:43:17", "remaining_time": "12:28:21", "throughput": 658.6, "total_tokens": 25420032} {"current_steps": 18495, "total_steps": 40000, "loss": 0.5596, "lr": 2.795013392188286e-05, "epoch": 0.5919915498367582, "percentage": 46.24, "elapsed_time": "10:43:18", "remaining_time": "12:28:00", "throughput": 658.74, "total_tokens": 25426624} {"current_steps": 18500, "total_steps": 40000, "loss": 0.8912, "lr": 2.7940384812736614e-05, "epoch": 0.5921515908072467, "percentage": 46.25, "elapsed_time": "10:43:20", "remaining_time": "12:27:40", "throughput": 658.89, "total_tokens": 25433728} {"current_steps": 18505, "total_steps": 40000, "loss": 0.6384, "lr": 2.7930635250146087e-05, "epoch": 0.592311631777735, "percentage": 46.26, "elapsed_time": "10:43:22", "remaining_time": "12:27:19", "throughput": 659.04, "total_tokens": 25440528} {"current_steps": 18510, "total_steps": 40000, "loss": 0.4413, "lr": 2.792088523561477e-05, "epoch": 0.5924716727482235, "percentage": 46.27, "elapsed_time": "10:43:24", "remaining_time": "12:26:59", "throughput": 659.19, "total_tokens": 25447328} {"current_steps": 18515, "total_steps": 40000, "loss": 0.6498, "lr": 2.7911134770646246e-05, "epoch": 0.592631713718712, "percentage": 46.29, "elapsed_time": "10:43:25", "remaining_time": "12:26:38", "throughput": 659.35, "total_tokens": 25454688} {"current_steps": 18520, "total_steps": 40000, "loss": 0.7328, "lr": 2.7901383856744157e-05, "epoch": 0.5927917546892004, "percentage": 46.3, "elapsed_time": "10:43:27", "remaining_time": "12:26:18", "throughput": 659.5, "total_tokens": 25461728} {"current_steps": 18525, "total_steps": 40000, "loss": 0.8962, "lr": 2.7891632495412217e-05, "epoch": 0.5929517956596889, "percentage": 46.31, "elapsed_time": "10:43:29", "remaining_time": "12:25:57", "throughput": 659.65, "total_tokens": 25468624} {"current_steps": 18530, "total_steps": 40000, "loss": 0.659, "lr": 2.7881880688154205e-05, "epoch": 0.5931118366301773, "percentage": 46.33, "elapsed_time": "10:43:31", "remaining_time": "12:25:37", "throughput": 659.79, "total_tokens": 25475360} {"current_steps": 18535, "total_steps": 40000, "loss": 0.6742, "lr": 2.7872128436473977e-05, "epoch": 0.5932718776006658, "percentage": 46.34, "elapsed_time": "10:43:32", "remaining_time": "12:25:16", "throughput": 659.94, "total_tokens": 25482224} {"current_steps": 18540, "total_steps": 40000, "loss": 0.6011, "lr": 2.7862375741875448e-05, "epoch": 0.5934319185711542, "percentage": 46.35, "elapsed_time": "10:43:34", "remaining_time": "12:24:56", "throughput": 660.08, "total_tokens": 25488848} {"current_steps": 18545, "total_steps": 40000, "loss": 0.9455, "lr": 2.785262260586261e-05, "epoch": 0.5935919595416427, "percentage": 46.36, "elapsed_time": "10:43:36", "remaining_time": "12:24:35", "throughput": 660.24, "total_tokens": 25495984} {"current_steps": 18550, "total_steps": 40000, "loss": 0.7501, "lr": 2.7842869029939517e-05, "epoch": 0.5937520005121311, "percentage": 46.38, "elapsed_time": "10:43:37", "remaining_time": "12:24:15", "throughput": 660.38, "total_tokens": 25502432} {"current_steps": 18555, "total_steps": 40000, "loss": 0.6607, "lr": 2.7833115015610296e-05, "epoch": 0.5939120414826196, "percentage": 46.39, "elapsed_time": "10:43:39", "remaining_time": "12:23:54", "throughput": 660.53, "total_tokens": 25509376} {"current_steps": 18560, "total_steps": 40000, "loss": 1.0187, "lr": 2.7823360564379136e-05, "epoch": 0.5940720824531079, "percentage": 46.4, "elapsed_time": "10:43:41", "remaining_time": "12:23:34", "throughput": 660.67, "total_tokens": 25515920} {"current_steps": 18565, "total_steps": 40000, "loss": 0.78, "lr": 2.7813605677750297e-05, "epoch": 0.5942321234235964, "percentage": 46.41, "elapsed_time": "10:43:43", "remaining_time": "12:23:14", "throughput": 660.81, "total_tokens": 25522720} {"current_steps": 18570, "total_steps": 40000, "loss": 0.8279, "lr": 2.7803850357228102e-05, "epoch": 0.5943921643940849, "percentage": 46.42, "elapsed_time": "10:43:44", "remaining_time": "12:22:53", "throughput": 660.96, "total_tokens": 25529376} {"current_steps": 18575, "total_steps": 40000, "loss": 0.7046, "lr": 2.779409460431695e-05, "epoch": 0.5945522053645733, "percentage": 46.44, "elapsed_time": "10:43:46", "remaining_time": "12:22:33", "throughput": 661.1, "total_tokens": 25536096} {"current_steps": 18580, "total_steps": 40000, "loss": 0.7454, "lr": 2.778433842052129e-05, "epoch": 0.5947122463350618, "percentage": 46.45, "elapsed_time": "10:43:48", "remaining_time": "12:22:12", "throughput": 661.25, "total_tokens": 25543216} {"current_steps": 18585, "total_steps": 40000, "loss": 0.7529, "lr": 2.7774581807345664e-05, "epoch": 0.5948722873055502, "percentage": 46.46, "elapsed_time": "10:43:50", "remaining_time": "12:21:52", "throughput": 661.42, "total_tokens": 25550656} {"current_steps": 18590, "total_steps": 40000, "loss": 0.9549, "lr": 2.776482476629465e-05, "epoch": 0.5950323282760387, "percentage": 46.48, "elapsed_time": "10:43:51", "remaining_time": "12:21:32", "throughput": 661.57, "total_tokens": 25557696} {"current_steps": 18595, "total_steps": 40000, "loss": 0.6914, "lr": 2.7755067298872924e-05, "epoch": 0.5951923692465271, "percentage": 46.49, "elapsed_time": "10:43:53", "remaining_time": "12:21:11", "throughput": 661.72, "total_tokens": 25564592} {"current_steps": 18600, "total_steps": 40000, "loss": 0.6775, "lr": 2.774530940658518e-05, "epoch": 0.5953524102170156, "percentage": 46.5, "elapsed_time": "10:43:55", "remaining_time": "12:20:51", "throughput": 661.86, "total_tokens": 25571232} {"current_steps": 18600, "total_steps": 40000, "eval_loss": 0.748390257358551, "epoch": 0.5953524102170156, "percentage": 46.5, "elapsed_time": "10:49:43", "remaining_time": "12:27:31", "throughput": 655.95, "total_tokens": 25571232} {"current_steps": 18605, "total_steps": 40000, "loss": 0.7722, "lr": 2.7735551090936236e-05, "epoch": 0.595512451187504, "percentage": 46.51, "elapsed_time": "10:49:47", "remaining_time": "12:27:13", "throughput": 656.07, "total_tokens": 25578400} {"current_steps": 18610, "total_steps": 40000, "loss": 0.6258, "lr": 2.7725792353430934e-05, "epoch": 0.5956724921579925, "percentage": 46.52, "elapsed_time": "10:49:48", "remaining_time": "12:26:52", "throughput": 656.21, "total_tokens": 25584960} {"current_steps": 18615, "total_steps": 40000, "loss": 0.5903, "lr": 2.77160331955742e-05, "epoch": 0.595832533128481, "percentage": 46.54, "elapsed_time": "10:49:50", "remaining_time": "12:26:32", "throughput": 656.37, "total_tokens": 25592144} {"current_steps": 18620, "total_steps": 40000, "loss": 0.7293, "lr": 2.7706273618871008e-05, "epoch": 0.5959925740989693, "percentage": 46.55, "elapsed_time": "10:49:52", "remaining_time": "12:26:11", "throughput": 656.52, "total_tokens": 25599040} {"current_steps": 18625, "total_steps": 40000, "loss": 0.7654, "lr": 2.769651362482642e-05, "epoch": 0.5961526150694578, "percentage": 46.56, "elapsed_time": "10:49:53", "remaining_time": "12:25:51", "throughput": 656.67, "total_tokens": 25606048} {"current_steps": 18630, "total_steps": 40000, "loss": 0.8664, "lr": 2.768675321494555e-05, "epoch": 0.5963126560399462, "percentage": 46.58, "elapsed_time": "10:49:55", "remaining_time": "12:25:30", "throughput": 656.82, "total_tokens": 25613200} {"current_steps": 18635, "total_steps": 40000, "loss": 0.7747, "lr": 2.7676992390733565e-05, "epoch": 0.5964726970104347, "percentage": 46.59, "elapsed_time": "10:49:57", "remaining_time": "12:25:10", "throughput": 656.96, "total_tokens": 25619888} {"current_steps": 18640, "total_steps": 40000, "loss": 0.6112, "lr": 2.766723115369571e-05, "epoch": 0.5966327379809231, "percentage": 46.6, "elapsed_time": "10:49:59", "remaining_time": "12:24:50", "throughput": 657.1, "total_tokens": 25626448} {"current_steps": 18645, "total_steps": 40000, "loss": 0.6582, "lr": 2.765746950533729e-05, "epoch": 0.5967927789514116, "percentage": 46.61, "elapsed_time": "10:50:00", "remaining_time": "12:24:29", "throughput": 657.25, "total_tokens": 25633216} {"current_steps": 18650, "total_steps": 40000, "loss": 0.5531, "lr": 2.7647707447163684e-05, "epoch": 0.5969528199219, "percentage": 46.62, "elapsed_time": "10:50:02", "remaining_time": "12:24:09", "throughput": 657.39, "total_tokens": 25639840} {"current_steps": 18655, "total_steps": 40000, "loss": 0.6345, "lr": 2.7637944980680315e-05, "epoch": 0.5971128608923885, "percentage": 46.64, "elapsed_time": "10:50:04", "remaining_time": "12:23:48", "throughput": 657.53, "total_tokens": 25646512} {"current_steps": 18660, "total_steps": 40000, "loss": 0.7539, "lr": 2.762818210739268e-05, "epoch": 0.5972729018628768, "percentage": 46.65, "elapsed_time": "10:50:06", "remaining_time": "12:23:28", "throughput": 657.67, "total_tokens": 25653152} {"current_steps": 18665, "total_steps": 40000, "loss": 0.6819, "lr": 2.7618418828806332e-05, "epoch": 0.5974329428333653, "percentage": 46.66, "elapsed_time": "10:50:07", "remaining_time": "12:23:07", "throughput": 657.82, "total_tokens": 25660016} {"current_steps": 18670, "total_steps": 40000, "loss": 1.0387, "lr": 2.76086551464269e-05, "epoch": 0.5975929838038538, "percentage": 46.67, "elapsed_time": "10:50:09", "remaining_time": "12:22:47", "throughput": 657.96, "total_tokens": 25666640} {"current_steps": 18675, "total_steps": 40000, "loss": 0.7121, "lr": 2.759889106176006e-05, "epoch": 0.5977530247743422, "percentage": 46.69, "elapsed_time": "10:50:11", "remaining_time": "12:22:27", "throughput": 658.11, "total_tokens": 25673712} {"current_steps": 18680, "total_steps": 40000, "loss": 0.6712, "lr": 2.758912657631156e-05, "epoch": 0.5979130657448307, "percentage": 46.7, "elapsed_time": "10:50:13", "remaining_time": "12:22:06", "throughput": 658.26, "total_tokens": 25680704} {"current_steps": 18685, "total_steps": 40000, "loss": 0.6474, "lr": 2.7579361691587198e-05, "epoch": 0.5980731067153191, "percentage": 46.71, "elapsed_time": "10:50:14", "remaining_time": "12:21:46", "throughput": 658.41, "total_tokens": 25687664} {"current_steps": 18690, "total_steps": 40000, "loss": 0.7433, "lr": 2.756959640909285e-05, "epoch": 0.5982331476858076, "percentage": 46.73, "elapsed_time": "10:50:16", "remaining_time": "12:21:25", "throughput": 658.55, "total_tokens": 25694448} {"current_steps": 18695, "total_steps": 40000, "loss": 0.6645, "lr": 2.7559830730334452e-05, "epoch": 0.598393188656296, "percentage": 46.74, "elapsed_time": "10:50:18", "remaining_time": "12:21:05", "throughput": 658.7, "total_tokens": 25701456} {"current_steps": 18700, "total_steps": 40000, "loss": 0.7208, "lr": 2.7550064656817988e-05, "epoch": 0.5985532296267845, "percentage": 46.75, "elapsed_time": "10:50:19", "remaining_time": "12:20:45", "throughput": 658.86, "total_tokens": 25708608} {"current_steps": 18705, "total_steps": 40000, "loss": 0.846, "lr": 2.7540298190049503e-05, "epoch": 0.5987132705972729, "percentage": 46.76, "elapsed_time": "10:50:21", "remaining_time": "12:20:24", "throughput": 659.0, "total_tokens": 25715264} {"current_steps": 18710, "total_steps": 40000, "loss": 0.7483, "lr": 2.7530531331535107e-05, "epoch": 0.5988733115677614, "percentage": 46.77, "elapsed_time": "10:50:23", "remaining_time": "12:20:04", "throughput": 659.14, "total_tokens": 25721936} {"current_steps": 18715, "total_steps": 40000, "loss": 0.5588, "lr": 2.752076408278099e-05, "epoch": 0.5990333525382497, "percentage": 46.79, "elapsed_time": "10:50:25", "remaining_time": "12:19:44", "throughput": 659.31, "total_tokens": 25729536} {"current_steps": 18720, "total_steps": 40000, "loss": 0.8023, "lr": 2.751099644529337e-05, "epoch": 0.5991933935087382, "percentage": 46.8, "elapsed_time": "10:50:26", "remaining_time": "12:19:23", "throughput": 659.46, "total_tokens": 25736576} {"current_steps": 18725, "total_steps": 40000, "loss": 0.732, "lr": 2.7501228420578533e-05, "epoch": 0.5993534344792267, "percentage": 46.81, "elapsed_time": "10:50:28", "remaining_time": "12:19:03", "throughput": 659.61, "total_tokens": 25743632} {"current_steps": 18730, "total_steps": 40000, "loss": 0.713, "lr": 2.7491460010142857e-05, "epoch": 0.5995134754497151, "percentage": 46.83, "elapsed_time": "10:50:30", "remaining_time": "12:18:43", "throughput": 659.75, "total_tokens": 25750352} {"current_steps": 18735, "total_steps": 40000, "loss": 0.6745, "lr": 2.7481691215492727e-05, "epoch": 0.5996735164202036, "percentage": 46.84, "elapsed_time": "10:50:32", "remaining_time": "12:18:23", "throughput": 659.9, "total_tokens": 25757344} {"current_steps": 18740, "total_steps": 40000, "loss": 0.8536, "lr": 2.747192203813463e-05, "epoch": 0.599833557390692, "percentage": 46.85, "elapsed_time": "10:50:33", "remaining_time": "12:18:02", "throughput": 660.05, "total_tokens": 25764176} {"current_steps": 18745, "total_steps": 40000, "loss": 0.7354, "lr": 2.7462152479575087e-05, "epoch": 0.5999935983611805, "percentage": 46.86, "elapsed_time": "10:50:35", "remaining_time": "12:17:42", "throughput": 660.19, "total_tokens": 25770768} {"current_steps": 18750, "total_steps": 40000, "loss": 0.6665, "lr": 2.7452382541320697e-05, "epoch": 0.6001536393316689, "percentage": 46.88, "elapsed_time": "10:50:37", "remaining_time": "12:17:22", "throughput": 660.33, "total_tokens": 25777712} {"current_steps": 18755, "total_steps": 40000, "loss": 0.6703, "lr": 2.7442612224878096e-05, "epoch": 0.6003136803021574, "percentage": 46.89, "elapsed_time": "10:50:39", "remaining_time": "12:17:02", "throughput": 660.48, "total_tokens": 25784512} {"current_steps": 18760, "total_steps": 40000, "loss": 0.7379, "lr": 2.7432841531753994e-05, "epoch": 0.6004737212726458, "percentage": 46.9, "elapsed_time": "10:50:40", "remaining_time": "12:16:41", "throughput": 660.63, "total_tokens": 25791504} {"current_steps": 18765, "total_steps": 40000, "loss": 0.6223, "lr": 2.7423070463455147e-05, "epoch": 0.6006337622431343, "percentage": 46.91, "elapsed_time": "10:50:42", "remaining_time": "12:16:21", "throughput": 660.78, "total_tokens": 25798512} {"current_steps": 18770, "total_steps": 40000, "loss": 0.7387, "lr": 2.7413299021488397e-05, "epoch": 0.6007938032136226, "percentage": 46.92, "elapsed_time": "10:50:44", "remaining_time": "12:16:01", "throughput": 660.92, "total_tokens": 25805152} {"current_steps": 18775, "total_steps": 40000, "loss": 0.8647, "lr": 2.7403527207360615e-05, "epoch": 0.6009538441841111, "percentage": 46.94, "elapsed_time": "10:50:46", "remaining_time": "12:15:41", "throughput": 661.07, "total_tokens": 25812240} {"current_steps": 18780, "total_steps": 40000, "loss": 0.796, "lr": 2.7393755022578722e-05, "epoch": 0.6011138851545996, "percentage": 46.95, "elapsed_time": "10:50:47", "remaining_time": "12:15:21", "throughput": 661.23, "total_tokens": 25819456} {"current_steps": 18785, "total_steps": 40000, "loss": 0.9878, "lr": 2.7383982468649714e-05, "epoch": 0.601273926125088, "percentage": 46.96, "elapsed_time": "10:50:49", "remaining_time": "12:15:00", "throughput": 661.39, "total_tokens": 25826768} {"current_steps": 18790, "total_steps": 40000, "loss": 0.7369, "lr": 2.7374209547080665e-05, "epoch": 0.6014339670955765, "percentage": 46.98, "elapsed_time": "10:50:51", "remaining_time": "12:14:40", "throughput": 661.55, "total_tokens": 25834304} {"current_steps": 18795, "total_steps": 40000, "loss": 0.8134, "lr": 2.7364436259378663e-05, "epoch": 0.6015940080660649, "percentage": 46.99, "elapsed_time": "10:50:52", "remaining_time": "12:14:20", "throughput": 661.69, "total_tokens": 25840784} {"current_steps": 18800, "total_steps": 40000, "loss": 0.8449, "lr": 2.735466260705088e-05, "epoch": 0.6017540490365534, "percentage": 47.0, "elapsed_time": "10:50:54", "remaining_time": "12:14:00", "throughput": 661.83, "total_tokens": 25847664} {"current_steps": 18800, "total_steps": 40000, "eval_loss": 0.7477852702140808, "epoch": 0.6017540490365534, "percentage": 47.0, "elapsed_time": "10:56:42", "remaining_time": "12:20:33", "throughput": 655.98, "total_tokens": 25847664} {"current_steps": 18805, "total_steps": 40000, "loss": 0.9535, "lr": 2.7344888591604524e-05, "epoch": 0.6019140900070418, "percentage": 47.01, "elapsed_time": "10:56:46", "remaining_time": "12:20:15", "throughput": 656.1, "total_tokens": 25854608} {"current_steps": 18810, "total_steps": 40000, "loss": 0.722, "lr": 2.7335114214546893e-05, "epoch": 0.6020741309775303, "percentage": 47.02, "elapsed_time": "10:56:48", "remaining_time": "12:19:54", "throughput": 656.24, "total_tokens": 25861472} {"current_steps": 18815, "total_steps": 40000, "loss": 0.6901, "lr": 2.7325339477385293e-05, "epoch": 0.6022341719480186, "percentage": 47.04, "elapsed_time": "10:56:50", "remaining_time": "12:19:34", "throughput": 656.38, "total_tokens": 25868288} {"current_steps": 18820, "total_steps": 40000, "loss": 0.7778, "lr": 2.7315564381627128e-05, "epoch": 0.6023942129185071, "percentage": 47.05, "elapsed_time": "10:56:52", "remaining_time": "12:19:14", "throughput": 656.53, "total_tokens": 25875264} {"current_steps": 18825, "total_steps": 40000, "loss": 0.7145, "lr": 2.7305788928779835e-05, "epoch": 0.6025542538889955, "percentage": 47.06, "elapsed_time": "10:56:53", "remaining_time": "12:18:53", "throughput": 656.68, "total_tokens": 25882096} {"current_steps": 18830, "total_steps": 40000, "loss": 0.8056, "lr": 2.729601312035091e-05, "epoch": 0.602714294859484, "percentage": 47.08, "elapsed_time": "10:56:55", "remaining_time": "12:18:33", "throughput": 656.82, "total_tokens": 25888848} {"current_steps": 18835, "total_steps": 40000, "loss": 0.79, "lr": 2.7286236957847915e-05, "epoch": 0.6028743358299725, "percentage": 47.09, "elapsed_time": "10:56:57", "remaining_time": "12:18:13", "throughput": 656.97, "total_tokens": 25895856} {"current_steps": 18840, "total_steps": 40000, "loss": 0.5457, "lr": 2.7276460442778446e-05, "epoch": 0.6030343768004609, "percentage": 47.1, "elapsed_time": "10:56:58", "remaining_time": "12:17:53", "throughput": 657.12, "total_tokens": 25903008} {"current_steps": 18845, "total_steps": 40000, "loss": 0.9639, "lr": 2.726668357665017e-05, "epoch": 0.6031944177709494, "percentage": 47.11, "elapsed_time": "10:57:00", "remaining_time": "12:17:32", "throughput": 657.27, "total_tokens": 25910160} {"current_steps": 18850, "total_steps": 40000, "loss": 0.8959, "lr": 2.7256906360970808e-05, "epoch": 0.6033544587414378, "percentage": 47.12, "elapsed_time": "10:57:02", "remaining_time": "12:17:12", "throughput": 657.41, "total_tokens": 25916768} {"current_steps": 18855, "total_steps": 40000, "loss": 0.7403, "lr": 2.7247128797248117e-05, "epoch": 0.6035144997119263, "percentage": 47.14, "elapsed_time": "10:57:04", "remaining_time": "12:16:52", "throughput": 657.56, "total_tokens": 25923696} {"current_steps": 18860, "total_steps": 40000, "loss": 0.8482, "lr": 2.7237350886989925e-05, "epoch": 0.6036745406824147, "percentage": 47.15, "elapsed_time": "10:57:05", "remaining_time": "12:16:32", "throughput": 657.72, "total_tokens": 25931008} {"current_steps": 18865, "total_steps": 40000, "loss": 0.6411, "lr": 2.7227572631704107e-05, "epoch": 0.6038345816529032, "percentage": 47.16, "elapsed_time": "10:57:07", "remaining_time": "12:16:11", "throughput": 657.86, "total_tokens": 25937920} {"current_steps": 18870, "total_steps": 40000, "loss": 0.8243, "lr": 2.7217794032898596e-05, "epoch": 0.6039946226233915, "percentage": 47.17, "elapsed_time": "10:57:09", "remaining_time": "12:15:51", "throughput": 658.01, "total_tokens": 25944816} {"current_steps": 18875, "total_steps": 40000, "loss": 0.7486, "lr": 2.7208015092081384e-05, "epoch": 0.60415466359388, "percentage": 47.19, "elapsed_time": "10:57:11", "remaining_time": "12:15:31", "throughput": 658.15, "total_tokens": 25951408} {"current_steps": 18880, "total_steps": 40000, "loss": 0.6286, "lr": 2.719823581076049e-05, "epoch": 0.6043147045643685, "percentage": 47.2, "elapsed_time": "10:57:12", "remaining_time": "12:15:11", "throughput": 658.29, "total_tokens": 25958256} {"current_steps": 18885, "total_steps": 40000, "loss": 0.7766, "lr": 2.718845619044401e-05, "epoch": 0.6044747455348569, "percentage": 47.21, "elapsed_time": "10:57:14", "remaining_time": "12:14:51", "throughput": 658.43, "total_tokens": 25965088} {"current_steps": 18890, "total_steps": 40000, "loss": 0.8863, "lr": 2.7178676232640088e-05, "epoch": 0.6046347865053454, "percentage": 47.23, "elapsed_time": "10:57:16", "remaining_time": "12:14:30", "throughput": 658.59, "total_tokens": 25972192} {"current_steps": 18895, "total_steps": 40000, "loss": 0.8706, "lr": 2.716889593885691e-05, "epoch": 0.6047948274758338, "percentage": 47.24, "elapsed_time": "10:57:18", "remaining_time": "12:14:10", "throughput": 658.74, "total_tokens": 25979344} {"current_steps": 18900, "total_steps": 40000, "loss": 0.7539, "lr": 2.7159115310602716e-05, "epoch": 0.6049548684463223, "percentage": 47.25, "elapsed_time": "10:57:19", "remaining_time": "12:13:50", "throughput": 658.9, "total_tokens": 25986720} {"current_steps": 18905, "total_steps": 40000, "loss": 0.5173, "lr": 2.7149334349385814e-05, "epoch": 0.6051149094168107, "percentage": 47.26, "elapsed_time": "10:57:21", "remaining_time": "12:13:30", "throughput": 659.04, "total_tokens": 25993584} {"current_steps": 18910, "total_steps": 40000, "loss": 0.7665, "lr": 2.713955305671454e-05, "epoch": 0.6052749503872992, "percentage": 47.27, "elapsed_time": "10:57:23", "remaining_time": "12:13:10", "throughput": 659.18, "total_tokens": 26000256} {"current_steps": 18915, "total_steps": 40000, "loss": 0.8295, "lr": 2.71297714340973e-05, "epoch": 0.6054349913577876, "percentage": 47.29, "elapsed_time": "10:57:24", "remaining_time": "12:12:50", "throughput": 659.33, "total_tokens": 26007088} {"current_steps": 18920, "total_steps": 40000, "loss": 1.0016, "lr": 2.7119989483042545e-05, "epoch": 0.605595032328276, "percentage": 47.3, "elapsed_time": "10:57:26", "remaining_time": "12:12:30", "throughput": 659.47, "total_tokens": 26013856} {"current_steps": 18925, "total_steps": 40000, "loss": 0.684, "lr": 2.7110207205058768e-05, "epoch": 0.6057550732987644, "percentage": 47.31, "elapsed_time": "10:57:28", "remaining_time": "12:12:10", "throughput": 659.62, "total_tokens": 26020848} {"current_steps": 18930, "total_steps": 40000, "loss": 0.5613, "lr": 2.7100424601654517e-05, "epoch": 0.6059151142692529, "percentage": 47.33, "elapsed_time": "10:57:30", "remaining_time": "12:11:49", "throughput": 659.76, "total_tokens": 26027696} {"current_steps": 18935, "total_steps": 40000, "loss": 0.6983, "lr": 2.7090641674338403e-05, "epoch": 0.6060751552397414, "percentage": 47.34, "elapsed_time": "10:57:31", "remaining_time": "12:11:29", "throughput": 659.91, "total_tokens": 26034624} {"current_steps": 18940, "total_steps": 40000, "loss": 0.6598, "lr": 2.7080858424619072e-05, "epoch": 0.6062351962102298, "percentage": 47.35, "elapsed_time": "10:57:33", "remaining_time": "12:11:09", "throughput": 660.06, "total_tokens": 26041600} {"current_steps": 18945, "total_steps": 40000, "loss": 0.8207, "lr": 2.707107485400521e-05, "epoch": 0.6063952371807183, "percentage": 47.36, "elapsed_time": "10:57:35", "remaining_time": "12:10:49", "throughput": 660.2, "total_tokens": 26048480} {"current_steps": 18950, "total_steps": 40000, "loss": 0.654, "lr": 2.7061290964005586e-05, "epoch": 0.6065552781512067, "percentage": 47.38, "elapsed_time": "10:57:37", "remaining_time": "12:10:29", "throughput": 660.34, "total_tokens": 26055328} {"current_steps": 18955, "total_steps": 40000, "loss": 0.6231, "lr": 2.7051506756129e-05, "epoch": 0.6067153191216952, "percentage": 47.39, "elapsed_time": "10:57:38", "remaining_time": "12:10:09", "throughput": 660.49, "total_tokens": 26062144} {"current_steps": 18960, "total_steps": 40000, "loss": 0.7839, "lr": 2.704172223188428e-05, "epoch": 0.6068753600921836, "percentage": 47.4, "elapsed_time": "10:57:40", "remaining_time": "12:09:49", "throughput": 660.65, "total_tokens": 26069648} {"current_steps": 18965, "total_steps": 40000, "loss": 0.8784, "lr": 2.7031937392780334e-05, "epoch": 0.6070354010626721, "percentage": 47.41, "elapsed_time": "10:57:42", "remaining_time": "12:09:29", "throughput": 660.79, "total_tokens": 26076464} {"current_steps": 18970, "total_steps": 40000, "loss": 0.8262, "lr": 2.702215224032611e-05, "epoch": 0.6071954420331604, "percentage": 47.42, "elapsed_time": "10:57:44", "remaining_time": "12:09:09", "throughput": 660.95, "total_tokens": 26083952} {"current_steps": 18975, "total_steps": 40000, "loss": 0.7847, "lr": 2.70123667760306e-05, "epoch": 0.6073554830036489, "percentage": 47.44, "elapsed_time": "10:57:45", "remaining_time": "12:08:49", "throughput": 661.1, "total_tokens": 26090848} {"current_steps": 18980, "total_steps": 40000, "loss": 0.73, "lr": 2.7002581001402845e-05, "epoch": 0.6075155239741373, "percentage": 47.45, "elapsed_time": "10:57:47", "remaining_time": "12:08:29", "throughput": 661.25, "total_tokens": 26098048} {"current_steps": 18985, "total_steps": 40000, "loss": 0.8488, "lr": 2.6992794917951923e-05, "epoch": 0.6076755649446258, "percentage": 47.46, "elapsed_time": "10:57:49", "remaining_time": "12:08:09", "throughput": 661.39, "total_tokens": 26104656} {"current_steps": 18990, "total_steps": 40000, "loss": 1.0961, "lr": 2.6983008527187e-05, "epoch": 0.6078356059151143, "percentage": 47.48, "elapsed_time": "10:57:51", "remaining_time": "12:07:49", "throughput": 661.54, "total_tokens": 26111792} {"current_steps": 18995, "total_steps": 40000, "loss": 0.7711, "lr": 2.697322183061723e-05, "epoch": 0.6079956468856027, "percentage": 47.49, "elapsed_time": "10:57:52", "remaining_time": "12:07:29", "throughput": 661.68, "total_tokens": 26118272} {"current_steps": 19000, "total_steps": 40000, "loss": 0.8842, "lr": 2.696343482975186e-05, "epoch": 0.6081556878560912, "percentage": 47.5, "elapsed_time": "10:57:54", "remaining_time": "12:07:09", "throughput": 661.83, "total_tokens": 26125328} {"current_steps": 19000, "total_steps": 40000, "eval_loss": 0.7478021383285522, "epoch": 0.6081556878560912, "percentage": 47.5, "elapsed_time": "11:03:42", "remaining_time": "12:13:34", "throughput": 656.05, "total_tokens": 26125328} {"current_steps": 19005, "total_steps": 40000, "loss": 0.6812, "lr": 2.695364752610016e-05, "epoch": 0.6083157288265796, "percentage": 47.51, "elapsed_time": "11:03:45", "remaining_time": "12:13:16", "throughput": 656.16, "total_tokens": 26131968} {"current_steps": 19010, "total_steps": 40000, "loss": 0.5705, "lr": 2.6943859921171467e-05, "epoch": 0.6084757697970681, "percentage": 47.52, "elapsed_time": "11:03:47", "remaining_time": "12:12:55", "throughput": 656.3, "total_tokens": 26138736} {"current_steps": 19015, "total_steps": 40000, "loss": 0.785, "lr": 2.6934072016475143e-05, "epoch": 0.6086358107675565, "percentage": 47.54, "elapsed_time": "11:03:49", "remaining_time": "12:12:35", "throughput": 656.46, "total_tokens": 26146352} {"current_steps": 19020, "total_steps": 40000, "loss": 0.7363, "lr": 2.6924283813520606e-05, "epoch": 0.608795851738045, "percentage": 47.55, "elapsed_time": "11:03:51", "remaining_time": "12:12:15", "throughput": 656.62, "total_tokens": 26153760} {"current_steps": 19025, "total_steps": 40000, "loss": 0.7111, "lr": 2.691449531381733e-05, "epoch": 0.6089558927085333, "percentage": 47.56, "elapsed_time": "11:03:52", "remaining_time": "12:11:55", "throughput": 656.76, "total_tokens": 26160640} {"current_steps": 19030, "total_steps": 40000, "loss": 0.9194, "lr": 2.6904706518874816e-05, "epoch": 0.6091159336790218, "percentage": 47.58, "elapsed_time": "11:03:54", "remaining_time": "12:11:35", "throughput": 656.9, "total_tokens": 26167424} {"current_steps": 19035, "total_steps": 40000, "loss": 0.5997, "lr": 2.6894917430202615e-05, "epoch": 0.6092759746495102, "percentage": 47.59, "elapsed_time": "11:03:56", "remaining_time": "12:11:15", "throughput": 657.05, "total_tokens": 26174304} {"current_steps": 19040, "total_steps": 40000, "loss": 0.8146, "lr": 2.6885128049310343e-05, "epoch": 0.6094360156199987, "percentage": 47.6, "elapsed_time": "11:03:58", "remaining_time": "12:10:55", "throughput": 657.19, "total_tokens": 26181120} {"current_steps": 19045, "total_steps": 40000, "loss": 0.5542, "lr": 2.687533837770762e-05, "epoch": 0.6095960565904872, "percentage": 47.61, "elapsed_time": "11:03:59", "remaining_time": "12:10:35", "throughput": 657.33, "total_tokens": 26187904} {"current_steps": 19050, "total_steps": 40000, "loss": 0.9672, "lr": 2.6865548416904162e-05, "epoch": 0.6097560975609756, "percentage": 47.62, "elapsed_time": "11:04:01", "remaining_time": "12:10:15", "throughput": 657.48, "total_tokens": 26194928} {"current_steps": 19055, "total_steps": 40000, "loss": 0.7633, "lr": 2.68557581684097e-05, "epoch": 0.6099161385314641, "percentage": 47.64, "elapsed_time": "11:04:03", "remaining_time": "12:09:55", "throughput": 657.62, "total_tokens": 26201792} {"current_steps": 19060, "total_steps": 40000, "loss": 0.7616, "lr": 2.6845967633733998e-05, "epoch": 0.6100761795019525, "percentage": 47.65, "elapsed_time": "11:04:05", "remaining_time": "12:09:35", "throughput": 657.76, "total_tokens": 26208592} {"current_steps": 19065, "total_steps": 40000, "loss": 0.5912, "lr": 2.683617681438689e-05, "epoch": 0.610236220472441, "percentage": 47.66, "elapsed_time": "11:04:06", "remaining_time": "12:09:15", "throughput": 657.9, "total_tokens": 26215312} {"current_steps": 19070, "total_steps": 40000, "loss": 0.7061, "lr": 2.682638571187825e-05, "epoch": 0.6103962614429294, "percentage": 47.67, "elapsed_time": "11:04:08", "remaining_time": "12:08:55", "throughput": 658.05, "total_tokens": 26222208} {"current_steps": 19075, "total_steps": 40000, "loss": 0.7676, "lr": 2.6816594327717976e-05, "epoch": 0.6105563024134179, "percentage": 47.69, "elapsed_time": "11:04:10", "remaining_time": "12:08:35", "throughput": 658.18, "total_tokens": 26228800} {"current_steps": 19080, "total_steps": 40000, "loss": 0.7076, "lr": 2.680680266341603e-05, "epoch": 0.6107163433839062, "percentage": 47.7, "elapsed_time": "11:04:11", "remaining_time": "12:08:15", "throughput": 658.33, "total_tokens": 26235632} {"current_steps": 19085, "total_steps": 40000, "loss": 0.6672, "lr": 2.67970107204824e-05, "epoch": 0.6108763843543947, "percentage": 47.71, "elapsed_time": "11:04:13", "remaining_time": "12:07:55", "throughput": 658.47, "total_tokens": 26242368} {"current_steps": 19090, "total_steps": 40000, "loss": 0.7516, "lr": 2.6787218500427142e-05, "epoch": 0.6110364253248832, "percentage": 47.73, "elapsed_time": "11:04:15", "remaining_time": "12:07:35", "throughput": 658.62, "total_tokens": 26249584} {"current_steps": 19095, "total_steps": 40000, "loss": 0.7662, "lr": 2.6777426004760332e-05, "epoch": 0.6111964662953716, "percentage": 47.74, "elapsed_time": "11:04:17", "remaining_time": "12:07:15", "throughput": 658.78, "total_tokens": 26256944} {"current_steps": 19100, "total_steps": 40000, "loss": 0.7149, "lr": 2.6767633234992094e-05, "epoch": 0.6113565072658601, "percentage": 47.75, "elapsed_time": "11:04:18", "remaining_time": "12:06:55", "throughput": 658.93, "total_tokens": 26264336} {"current_steps": 19105, "total_steps": 40000, "loss": 0.7848, "lr": 2.6757840192632598e-05, "epoch": 0.6115165482363485, "percentage": 47.76, "elapsed_time": "11:04:20", "remaining_time": "12:06:35", "throughput": 659.08, "total_tokens": 26271216} {"current_steps": 19110, "total_steps": 40000, "loss": 0.6581, "lr": 2.6748046879192052e-05, "epoch": 0.611676589206837, "percentage": 47.77, "elapsed_time": "11:04:22", "remaining_time": "12:06:15", "throughput": 659.22, "total_tokens": 26278064} {"current_steps": 19115, "total_steps": 40000, "loss": 0.7964, "lr": 2.673825329618071e-05, "epoch": 0.6118366301773254, "percentage": 47.79, "elapsed_time": "11:04:24", "remaining_time": "12:05:55", "throughput": 659.36, "total_tokens": 26284880} {"current_steps": 19120, "total_steps": 40000, "loss": 0.6025, "lr": 2.6728459445108866e-05, "epoch": 0.6119966711478139, "percentage": 47.8, "elapsed_time": "11:04:25", "remaining_time": "12:05:35", "throughput": 659.51, "total_tokens": 26291984} {"current_steps": 19125, "total_steps": 40000, "loss": 0.7925, "lr": 2.6718665327486854e-05, "epoch": 0.6121567121183022, "percentage": 47.81, "elapsed_time": "11:04:27", "remaining_time": "12:05:15", "throughput": 659.66, "total_tokens": 26299136} {"current_steps": 19130, "total_steps": 40000, "loss": 0.8493, "lr": 2.6708870944825048e-05, "epoch": 0.6123167530887907, "percentage": 47.83, "elapsed_time": "11:04:29", "remaining_time": "12:04:55", "throughput": 659.81, "total_tokens": 26306240} {"current_steps": 19135, "total_steps": 40000, "loss": 0.8282, "lr": 2.6699076298633874e-05, "epoch": 0.6124767940592791, "percentage": 47.84, "elapsed_time": "11:04:31", "remaining_time": "12:04:35", "throughput": 659.96, "total_tokens": 26313328} {"current_steps": 19140, "total_steps": 40000, "loss": 0.7231, "lr": 2.6689281390423788e-05, "epoch": 0.6126368350297676, "percentage": 47.85, "elapsed_time": "11:04:32", "remaining_time": "12:04:15", "throughput": 660.11, "total_tokens": 26320592} {"current_steps": 19145, "total_steps": 40000, "loss": 0.6647, "lr": 2.667948622170527e-05, "epoch": 0.6127968760002561, "percentage": 47.86, "elapsed_time": "11:04:34", "remaining_time": "12:03:56", "throughput": 660.26, "total_tokens": 26327648} {"current_steps": 19150, "total_steps": 40000, "loss": 0.94, "lr": 2.6669690793988873e-05, "epoch": 0.6129569169707445, "percentage": 47.88, "elapsed_time": "11:04:36", "remaining_time": "12:03:36", "throughput": 660.4, "total_tokens": 26334288} {"current_steps": 19155, "total_steps": 40000, "loss": 0.6911, "lr": 2.665989510878518e-05, "epoch": 0.613116957941233, "percentage": 47.89, "elapsed_time": "11:04:38", "remaining_time": "12:03:16", "throughput": 660.55, "total_tokens": 26341264} {"current_steps": 19160, "total_steps": 40000, "loss": 0.5837, "lr": 2.6650099167604793e-05, "epoch": 0.6132769989117214, "percentage": 47.9, "elapsed_time": "11:04:39", "remaining_time": "12:02:56", "throughput": 660.7, "total_tokens": 26348656} {"current_steps": 19165, "total_steps": 40000, "loss": 0.7596, "lr": 2.6640302971958376e-05, "epoch": 0.6134370398822099, "percentage": 47.91, "elapsed_time": "11:04:41", "remaining_time": "12:02:36", "throughput": 660.83, "total_tokens": 26355008} {"current_steps": 19170, "total_steps": 40000, "loss": 0.7221, "lr": 2.6630506523356635e-05, "epoch": 0.6135970808526983, "percentage": 47.93, "elapsed_time": "11:04:43", "remaining_time": "12:02:16", "throughput": 660.98, "total_tokens": 26361840} {"current_steps": 19175, "total_steps": 40000, "loss": 0.8688, "lr": 2.6620709823310297e-05, "epoch": 0.6137571218231868, "percentage": 47.94, "elapsed_time": "11:04:45", "remaining_time": "12:01:57", "throughput": 661.14, "total_tokens": 26369520} {"current_steps": 19180, "total_steps": 40000, "loss": 0.656, "lr": 2.661091287333014e-05, "epoch": 0.6139171627936751, "percentage": 47.95, "elapsed_time": "11:04:46", "remaining_time": "12:01:37", "throughput": 661.28, "total_tokens": 26376304} {"current_steps": 19185, "total_steps": 40000, "loss": 0.7719, "lr": 2.660111567492696e-05, "epoch": 0.6140772037641636, "percentage": 47.96, "elapsed_time": "11:04:48", "remaining_time": "12:01:17", "throughput": 661.43, "total_tokens": 26383344} {"current_steps": 19190, "total_steps": 40000, "loss": 0.6088, "lr": 2.6591318229611635e-05, "epoch": 0.614237244734652, "percentage": 47.98, "elapsed_time": "11:04:50", "remaining_time": "12:00:57", "throughput": 661.57, "total_tokens": 26390048} {"current_steps": 19195, "total_steps": 40000, "loss": 0.8344, "lr": 2.6581520538895037e-05, "epoch": 0.6143972857051405, "percentage": 47.99, "elapsed_time": "11:04:51", "remaining_time": "12:00:37", "throughput": 661.71, "total_tokens": 26397040} {"current_steps": 19200, "total_steps": 40000, "loss": 0.7932, "lr": 2.6571722604288102e-05, "epoch": 0.614557326675629, "percentage": 48.0, "elapsed_time": "11:04:53", "remaining_time": "12:00:18", "throughput": 661.86, "total_tokens": 26404064} {"current_steps": 19200, "total_steps": 40000, "eval_loss": 0.7467134594917297, "epoch": 0.614557326675629, "percentage": 48.0, "elapsed_time": "11:10:41", "remaining_time": "12:06:34", "throughput": 656.14, "total_tokens": 26404064} {"current_steps": 19205, "total_steps": 40000, "loss": 0.8047, "lr": 2.656192442730179e-05, "epoch": 0.6147173676461174, "percentage": 48.01, "elapsed_time": "11:10:44", "remaining_time": "12:06:16", "throughput": 656.26, "total_tokens": 26411024} {"current_steps": 19210, "total_steps": 40000, "loss": 0.6202, "lr": 2.6552126009447098e-05, "epoch": 0.6148774086166059, "percentage": 48.02, "elapsed_time": "11:10:46", "remaining_time": "12:05:56", "throughput": 656.4, "total_tokens": 26417920} {"current_steps": 19215, "total_steps": 40000, "loss": 0.6456, "lr": 2.654232735223507e-05, "epoch": 0.6150374495870943, "percentage": 48.04, "elapsed_time": "11:10:48", "remaining_time": "12:05:36", "throughput": 656.55, "total_tokens": 26424960} {"current_steps": 19220, "total_steps": 40000, "loss": 0.8273, "lr": 2.6532528457176787e-05, "epoch": 0.6151974905575828, "percentage": 48.05, "elapsed_time": "11:10:50", "remaining_time": "12:05:17", "throughput": 656.69, "total_tokens": 26431968} {"current_steps": 19225, "total_steps": 40000, "loss": 0.7689, "lr": 2.6522729325783348e-05, "epoch": 0.6153575315280712, "percentage": 48.06, "elapsed_time": "11:10:51", "remaining_time": "12:04:57", "throughput": 656.84, "total_tokens": 26438928} {"current_steps": 19230, "total_steps": 40000, "loss": 0.6307, "lr": 2.6512929959565914e-05, "epoch": 0.6155175724985597, "percentage": 48.08, "elapsed_time": "11:10:53", "remaining_time": "12:04:37", "throughput": 656.97, "total_tokens": 26445392} {"current_steps": 19235, "total_steps": 40000, "loss": 1.0154, "lr": 2.6503130360035673e-05, "epoch": 0.615677613469048, "percentage": 48.09, "elapsed_time": "11:10:55", "remaining_time": "12:04:17", "throughput": 657.11, "total_tokens": 26452016} {"current_steps": 19240, "total_steps": 40000, "loss": 0.7449, "lr": 2.6493330528703835e-05, "epoch": 0.6158376544395365, "percentage": 48.1, "elapsed_time": "11:10:57", "remaining_time": "12:03:57", "throughput": 657.24, "total_tokens": 26458624} {"current_steps": 19245, "total_steps": 40000, "loss": 0.7652, "lr": 2.648353046708167e-05, "epoch": 0.6159976954100249, "percentage": 48.11, "elapsed_time": "11:10:58", "remaining_time": "12:03:37", "throughput": 657.38, "total_tokens": 26465440} {"current_steps": 19250, "total_steps": 40000, "loss": 0.7661, "lr": 2.647373017668046e-05, "epoch": 0.6161577363805134, "percentage": 48.12, "elapsed_time": "11:11:00", "remaining_time": "12:03:17", "throughput": 657.52, "total_tokens": 26472080} {"current_steps": 19255, "total_steps": 40000, "loss": 0.8371, "lr": 2.6463929659011537e-05, "epoch": 0.6163177773510019, "percentage": 48.14, "elapsed_time": "11:11:02", "remaining_time": "12:02:57", "throughput": 657.66, "total_tokens": 26478976} {"current_steps": 19260, "total_steps": 40000, "loss": 1.0149, "lr": 2.6454128915586262e-05, "epoch": 0.6164778183214903, "percentage": 48.15, "elapsed_time": "11:11:03", "remaining_time": "12:02:38", "throughput": 657.8, "total_tokens": 26485776} {"current_steps": 19265, "total_steps": 40000, "loss": 0.8184, "lr": 2.6444327947916036e-05, "epoch": 0.6166378592919788, "percentage": 48.16, "elapsed_time": "11:11:05", "remaining_time": "12:02:18", "throughput": 657.95, "total_tokens": 26492816} {"current_steps": 19270, "total_steps": 40000, "loss": 0.7403, "lr": 2.6434526757512292e-05, "epoch": 0.6167979002624672, "percentage": 48.18, "elapsed_time": "11:11:07", "remaining_time": "12:01:58", "throughput": 658.09, "total_tokens": 26499488} {"current_steps": 19275, "total_steps": 40000, "loss": 0.6284, "lr": 2.6424725345886486e-05, "epoch": 0.6169579412329557, "percentage": 48.19, "elapsed_time": "11:11:09", "remaining_time": "12:01:38", "throughput": 658.23, "total_tokens": 26506288} {"current_steps": 19280, "total_steps": 40000, "loss": 0.7506, "lr": 2.641492371455014e-05, "epoch": 0.617117982203444, "percentage": 48.2, "elapsed_time": "11:11:10", "remaining_time": "12:01:18", "throughput": 658.38, "total_tokens": 26513424} {"current_steps": 19285, "total_steps": 40000, "loss": 0.7436, "lr": 2.640512186501477e-05, "epoch": 0.6172780231739325, "percentage": 48.21, "elapsed_time": "11:11:12", "remaining_time": "12:00:58", "throughput": 658.51, "total_tokens": 26519808} {"current_steps": 19290, "total_steps": 40000, "loss": 0.6521, "lr": 2.639531979879195e-05, "epoch": 0.6174380641444209, "percentage": 48.23, "elapsed_time": "11:11:14", "remaining_time": "12:00:39", "throughput": 658.64, "total_tokens": 26526480} {"current_steps": 19295, "total_steps": 40000, "loss": 0.8914, "lr": 2.638551751739328e-05, "epoch": 0.6175981051149094, "percentage": 48.24, "elapsed_time": "11:11:16", "remaining_time": "12:00:19", "throughput": 658.78, "total_tokens": 26533008} {"current_steps": 19300, "total_steps": 40000, "loss": 0.8203, "lr": 2.6375715022330404e-05, "epoch": 0.6177581460853978, "percentage": 48.25, "elapsed_time": "11:11:18", "remaining_time": "11:59:59", "throughput": 658.9, "total_tokens": 26539456} {"current_steps": 19305, "total_steps": 40000, "loss": 0.7502, "lr": 2.6365912315114976e-05, "epoch": 0.6179181870558863, "percentage": 48.26, "elapsed_time": "11:11:19", "remaining_time": "11:59:40", "throughput": 659.06, "total_tokens": 26546704} {"current_steps": 19310, "total_steps": 40000, "loss": 0.7486, "lr": 2.6356109397258704e-05, "epoch": 0.6180782280263748, "percentage": 48.27, "elapsed_time": "11:11:21", "remaining_time": "11:59:20", "throughput": 659.21, "total_tokens": 26554032} {"current_steps": 19315, "total_steps": 40000, "loss": 0.91, "lr": 2.6346306270273325e-05, "epoch": 0.6182382689968632, "percentage": 48.29, "elapsed_time": "11:11:23", "remaining_time": "11:59:00", "throughput": 659.37, "total_tokens": 26561472} {"current_steps": 19320, "total_steps": 40000, "loss": 0.6978, "lr": 2.6336502935670608e-05, "epoch": 0.6183983099673517, "percentage": 48.3, "elapsed_time": "11:11:25", "remaining_time": "11:58:40", "throughput": 659.52, "total_tokens": 26568624} {"current_steps": 19325, "total_steps": 40000, "loss": 0.9052, "lr": 2.6326699394962333e-05, "epoch": 0.6185583509378401, "percentage": 48.31, "elapsed_time": "11:11:26", "remaining_time": "11:58:21", "throughput": 659.66, "total_tokens": 26575792} {"current_steps": 19330, "total_steps": 40000, "loss": 0.8008, "lr": 2.6316895649660334e-05, "epoch": 0.6187183919083286, "percentage": 48.33, "elapsed_time": "11:11:28", "remaining_time": "11:58:01", "throughput": 659.81, "total_tokens": 26582704} {"current_steps": 19335, "total_steps": 40000, "loss": 0.7731, "lr": 2.6307091701276486e-05, "epoch": 0.6188784328788169, "percentage": 48.34, "elapsed_time": "11:11:30", "remaining_time": "11:57:41", "throughput": 659.96, "total_tokens": 26589968} {"current_steps": 19340, "total_steps": 40000, "loss": 0.8773, "lr": 2.629728755132267e-05, "epoch": 0.6190384738493054, "percentage": 48.35, "elapsed_time": "11:11:32", "remaining_time": "11:57:22", "throughput": 660.1, "total_tokens": 26596864} {"current_steps": 19345, "total_steps": 40000, "loss": 1.0543, "lr": 2.628748320131081e-05, "epoch": 0.6191985148197938, "percentage": 48.36, "elapsed_time": "11:11:33", "remaining_time": "11:57:02", "throughput": 660.25, "total_tokens": 26604048} {"current_steps": 19350, "total_steps": 40000, "loss": 0.7443, "lr": 2.6277678652752856e-05, "epoch": 0.6193585557902823, "percentage": 48.38, "elapsed_time": "11:11:35", "remaining_time": "11:56:42", "throughput": 660.4, "total_tokens": 26611216} {"current_steps": 19355, "total_steps": 40000, "loss": 0.6682, "lr": 2.6267873907160807e-05, "epoch": 0.6195185967607708, "percentage": 48.39, "elapsed_time": "11:11:37", "remaining_time": "11:56:23", "throughput": 660.54, "total_tokens": 26618032} {"current_steps": 19360, "total_steps": 40000, "loss": 0.7255, "lr": 2.6258068966046668e-05, "epoch": 0.6196786377312592, "percentage": 48.4, "elapsed_time": "11:11:38", "remaining_time": "11:56:03", "throughput": 660.68, "total_tokens": 26624704} {"current_steps": 19365, "total_steps": 40000, "loss": 0.746, "lr": 2.6248263830922475e-05, "epoch": 0.6198386787017477, "percentage": 48.41, "elapsed_time": "11:11:40", "remaining_time": "11:55:43", "throughput": 660.81, "total_tokens": 26631120} {"current_steps": 19370, "total_steps": 40000, "loss": 0.8041, "lr": 2.6238458503300318e-05, "epoch": 0.6199987196722361, "percentage": 48.43, "elapsed_time": "11:11:42", "remaining_time": "11:55:24", "throughput": 660.94, "total_tokens": 26637568} {"current_steps": 19375, "total_steps": 40000, "loss": 0.5927, "lr": 2.6228652984692292e-05, "epoch": 0.6201587606427246, "percentage": 48.44, "elapsed_time": "11:11:44", "remaining_time": "11:55:04", "throughput": 661.08, "total_tokens": 26644240} {"current_steps": 19380, "total_steps": 40000, "loss": 0.6955, "lr": 2.621884727661054e-05, "epoch": 0.620318801613213, "percentage": 48.45, "elapsed_time": "11:11:45", "remaining_time": "11:54:44", "throughput": 661.21, "total_tokens": 26650800} {"current_steps": 19385, "total_steps": 40000, "loss": 0.6099, "lr": 2.6209041380567222e-05, "epoch": 0.6204788425837015, "percentage": 48.46, "elapsed_time": "11:11:47", "remaining_time": "11:54:25", "throughput": 661.35, "total_tokens": 26657536} {"current_steps": 19390, "total_steps": 40000, "loss": 0.6748, "lr": 2.6199235298074527e-05, "epoch": 0.6206388835541898, "percentage": 48.48, "elapsed_time": "11:11:49", "remaining_time": "11:54:05", "throughput": 661.49, "total_tokens": 26664288} {"current_steps": 19395, "total_steps": 40000, "loss": 0.7776, "lr": 2.618942903064468e-05, "epoch": 0.6207989245246783, "percentage": 48.49, "elapsed_time": "11:11:51", "remaining_time": "11:53:45", "throughput": 661.62, "total_tokens": 26670816} {"current_steps": 19400, "total_steps": 40000, "loss": 0.6471, "lr": 2.6179622579789932e-05, "epoch": 0.6209589654951667, "percentage": 48.5, "elapsed_time": "11:11:52", "remaining_time": "11:53:26", "throughput": 661.76, "total_tokens": 26677504} {"current_steps": 19400, "total_steps": 40000, "eval_loss": 0.7465914487838745, "epoch": 0.6209589654951667, "percentage": 48.5, "elapsed_time": "11:17:40", "remaining_time": "11:59:35", "throughput": 656.11, "total_tokens": 26677504} {"current_steps": 19405, "total_steps": 40000, "loss": 0.664, "lr": 2.6169815947022553e-05, "epoch": 0.6211190064656552, "percentage": 48.51, "elapsed_time": "11:17:43", "remaining_time": "11:59:17", "throughput": 656.22, "total_tokens": 26684512} {"current_steps": 19410, "total_steps": 40000, "loss": 0.7715, "lr": 2.6160009133854853e-05, "epoch": 0.6212790474361437, "percentage": 48.52, "elapsed_time": "11:17:45", "remaining_time": "11:58:57", "throughput": 656.37, "total_tokens": 26691808} {"current_steps": 19415, "total_steps": 40000, "loss": 0.681, "lr": 2.6150202141799168e-05, "epoch": 0.6214390884066321, "percentage": 48.54, "elapsed_time": "11:17:47", "remaining_time": "11:58:38", "throughput": 656.51, "total_tokens": 26698560} {"current_steps": 19420, "total_steps": 40000, "loss": 0.798, "lr": 2.614039497236786e-05, "epoch": 0.6215991293771206, "percentage": 48.55, "elapsed_time": "11:17:49", "remaining_time": "11:58:18", "throughput": 656.65, "total_tokens": 26705376} {"current_steps": 19425, "total_steps": 40000, "loss": 0.5387, "lr": 2.6130587627073315e-05, "epoch": 0.621759170347609, "percentage": 48.56, "elapsed_time": "11:17:50", "remaining_time": "11:57:58", "throughput": 656.79, "total_tokens": 26712304} {"current_steps": 19430, "total_steps": 40000, "loss": 0.8577, "lr": 2.6120780107427956e-05, "epoch": 0.6219192113180975, "percentage": 48.58, "elapsed_time": "11:17:52", "remaining_time": "11:57:38", "throughput": 656.94, "total_tokens": 26719360} {"current_steps": 19435, "total_steps": 40000, "loss": 0.6778, "lr": 2.6110972414944214e-05, "epoch": 0.6220792522885858, "percentage": 48.59, "elapsed_time": "11:17:54", "remaining_time": "11:57:19", "throughput": 657.08, "total_tokens": 26726096} {"current_steps": 19440, "total_steps": 40000, "loss": 0.554, "lr": 2.6101164551134565e-05, "epoch": 0.6222392932590743, "percentage": 48.6, "elapsed_time": "11:17:55", "remaining_time": "11:56:59", "throughput": 657.21, "total_tokens": 26732832} {"current_steps": 19445, "total_steps": 40000, "loss": 0.6611, "lr": 2.6091356517511505e-05, "epoch": 0.6223993342295627, "percentage": 48.61, "elapsed_time": "11:17:57", "remaining_time": "11:56:39", "throughput": 657.35, "total_tokens": 26739360} {"current_steps": 19450, "total_steps": 40000, "loss": 0.5904, "lr": 2.608154831558755e-05, "epoch": 0.6225593752000512, "percentage": 48.62, "elapsed_time": "11:17:59", "remaining_time": "11:56:20", "throughput": 657.49, "total_tokens": 26746432} {"current_steps": 19455, "total_steps": 40000, "loss": 0.8656, "lr": 2.607173994687526e-05, "epoch": 0.6227194161705396, "percentage": 48.64, "elapsed_time": "11:18:01", "remaining_time": "11:56:00", "throughput": 657.63, "total_tokens": 26753344} {"current_steps": 19460, "total_steps": 40000, "loss": 0.6368, "lr": 2.6061931412887196e-05, "epoch": 0.6228794571410281, "percentage": 48.65, "elapsed_time": "11:18:02", "remaining_time": "11:55:40", "throughput": 657.77, "total_tokens": 26760000} {"current_steps": 19465, "total_steps": 40000, "loss": 0.6935, "lr": 2.6052122715135973e-05, "epoch": 0.6230394981115166, "percentage": 48.66, "elapsed_time": "11:18:04", "remaining_time": "11:55:21", "throughput": 657.92, "total_tokens": 26767088} {"current_steps": 19470, "total_steps": 40000, "loss": 0.5468, "lr": 2.60423138551342e-05, "epoch": 0.623199539082005, "percentage": 48.68, "elapsed_time": "11:18:06", "remaining_time": "11:55:01", "throughput": 658.06, "total_tokens": 26774064} {"current_steps": 19475, "total_steps": 40000, "loss": 0.8261, "lr": 2.6032504834394527e-05, "epoch": 0.6233595800524935, "percentage": 48.69, "elapsed_time": "11:18:08", "remaining_time": "11:54:41", "throughput": 658.2, "total_tokens": 26780976} {"current_steps": 19480, "total_steps": 40000, "loss": 0.7758, "lr": 2.602269565442964e-05, "epoch": 0.6235196210229819, "percentage": 48.7, "elapsed_time": "11:18:09", "remaining_time": "11:54:22", "throughput": 658.34, "total_tokens": 26787840} {"current_steps": 19485, "total_steps": 40000, "loss": 0.7631, "lr": 2.6012886316752227e-05, "epoch": 0.6236796619934704, "percentage": 48.71, "elapsed_time": "11:18:11", "remaining_time": "11:54:02", "throughput": 658.48, "total_tokens": 26794592} {"current_steps": 19490, "total_steps": 40000, "loss": 0.8654, "lr": 2.6003076822875018e-05, "epoch": 0.6238397029639587, "percentage": 48.73, "elapsed_time": "11:18:13", "remaining_time": "11:53:43", "throughput": 658.62, "total_tokens": 26801296} {"current_steps": 19495, "total_steps": 40000, "loss": 0.5405, "lr": 2.5993267174310755e-05, "epoch": 0.6239997439344472, "percentage": 48.74, "elapsed_time": "11:18:15", "remaining_time": "11:53:23", "throughput": 658.75, "total_tokens": 26807856} {"current_steps": 19500, "total_steps": 40000, "loss": 0.6201, "lr": 2.5983457372572218e-05, "epoch": 0.6241597849049356, "percentage": 48.75, "elapsed_time": "11:18:16", "remaining_time": "11:53:03", "throughput": 658.89, "total_tokens": 26814672} {"current_steps": 19505, "total_steps": 40000, "loss": 0.7018, "lr": 2.597364741917219e-05, "epoch": 0.6243198258754241, "percentage": 48.76, "elapsed_time": "11:18:18", "remaining_time": "11:52:44", "throughput": 659.03, "total_tokens": 26821680} {"current_steps": 19510, "total_steps": 40000, "loss": 0.7639, "lr": 2.5963837315623492e-05, "epoch": 0.6244798668459125, "percentage": 48.77, "elapsed_time": "11:18:20", "remaining_time": "11:52:24", "throughput": 659.16, "total_tokens": 26827952} {"current_steps": 19515, "total_steps": 40000, "loss": 0.4201, "lr": 2.595402706343897e-05, "epoch": 0.624639907816401, "percentage": 48.79, "elapsed_time": "11:18:22", "remaining_time": "11:52:05", "throughput": 659.31, "total_tokens": 26835072} {"current_steps": 19520, "total_steps": 40000, "loss": 0.9621, "lr": 2.594421666413148e-05, "epoch": 0.6247999487868895, "percentage": 48.8, "elapsed_time": "11:18:23", "remaining_time": "11:51:45", "throughput": 659.44, "total_tokens": 26841536} {"current_steps": 19525, "total_steps": 40000, "loss": 0.691, "lr": 2.5934406119213928e-05, "epoch": 0.6249599897573779, "percentage": 48.81, "elapsed_time": "11:18:25", "remaining_time": "11:51:26", "throughput": 659.59, "total_tokens": 26848832} {"current_steps": 19530, "total_steps": 40000, "loss": 0.679, "lr": 2.5924595430199193e-05, "epoch": 0.6251200307278664, "percentage": 48.83, "elapsed_time": "11:18:27", "remaining_time": "11:51:06", "throughput": 659.73, "total_tokens": 26855888} {"current_steps": 19535, "total_steps": 40000, "loss": 0.8162, "lr": 2.5914784598600238e-05, "epoch": 0.6252800716983548, "percentage": 48.84, "elapsed_time": "11:18:28", "remaining_time": "11:50:46", "throughput": 659.87, "total_tokens": 26862672} {"current_steps": 19540, "total_steps": 40000, "loss": 0.6272, "lr": 2.5904973625930002e-05, "epoch": 0.6254401126688433, "percentage": 48.85, "elapsed_time": "11:18:30", "remaining_time": "11:50:27", "throughput": 660.03, "total_tokens": 26870224} {"current_steps": 19545, "total_steps": 40000, "loss": 0.5353, "lr": 2.5895162513701456e-05, "epoch": 0.6256001536393316, "percentage": 48.86, "elapsed_time": "11:18:32", "remaining_time": "11:50:07", "throughput": 660.16, "total_tokens": 26876736} {"current_steps": 19550, "total_steps": 40000, "loss": 0.5105, "lr": 2.5885351263427593e-05, "epoch": 0.6257601946098201, "percentage": 48.88, "elapsed_time": "11:18:34", "remaining_time": "11:49:48", "throughput": 660.31, "total_tokens": 26883936} {"current_steps": 19555, "total_steps": 40000, "loss": 0.761, "lr": 2.5875539876621448e-05, "epoch": 0.6259202355803085, "percentage": 48.89, "elapsed_time": "11:18:35", "remaining_time": "11:49:29", "throughput": 660.45, "total_tokens": 26890912} {"current_steps": 19560, "total_steps": 40000, "loss": 0.8936, "lr": 2.586572835479605e-05, "epoch": 0.626080276550797, "percentage": 48.9, "elapsed_time": "11:18:37", "remaining_time": "11:49:09", "throughput": 660.58, "total_tokens": 26897456} {"current_steps": 19565, "total_steps": 40000, "loss": 0.8964, "lr": 2.585591669946446e-05, "epoch": 0.6262403175212854, "percentage": 48.91, "elapsed_time": "11:18:39", "remaining_time": "11:48:50", "throughput": 660.73, "total_tokens": 26904368} {"current_steps": 19570, "total_steps": 40000, "loss": 0.7557, "lr": 2.5846104912139756e-05, "epoch": 0.6264003584917739, "percentage": 48.93, "elapsed_time": "11:18:41", "remaining_time": "11:48:30", "throughput": 660.87, "total_tokens": 26911424} {"current_steps": 19575, "total_steps": 40000, "loss": 0.7093, "lr": 2.583629299433505e-05, "epoch": 0.6265603994622624, "percentage": 48.94, "elapsed_time": "11:18:42", "remaining_time": "11:48:11", "throughput": 661.01, "total_tokens": 26918192} {"current_steps": 19580, "total_steps": 40000, "loss": 0.7886, "lr": 2.582648094756345e-05, "epoch": 0.6267204404327508, "percentage": 48.95, "elapsed_time": "11:18:44", "remaining_time": "11:47:51", "throughput": 661.14, "total_tokens": 26924704} {"current_steps": 19585, "total_steps": 40000, "loss": 0.7722, "lr": 2.5816668773338098e-05, "epoch": 0.6268804814032393, "percentage": 48.96, "elapsed_time": "11:18:46", "remaining_time": "11:47:32", "throughput": 661.28, "total_tokens": 26931584} {"current_steps": 19590, "total_steps": 40000, "loss": 0.7782, "lr": 2.580685647317216e-05, "epoch": 0.6270405223737276, "percentage": 48.98, "elapsed_time": "11:18:48", "remaining_time": "11:47:12", "throughput": 661.43, "total_tokens": 26938640} {"current_steps": 19595, "total_steps": 40000, "loss": 0.7699, "lr": 2.5797044048578818e-05, "epoch": 0.6272005633442161, "percentage": 48.99, "elapsed_time": "11:18:49", "remaining_time": "11:46:53", "throughput": 661.57, "total_tokens": 26945568} {"current_steps": 19600, "total_steps": 40000, "loss": 0.8983, "lr": 2.5787231501071262e-05, "epoch": 0.6273606043147045, "percentage": 49.0, "elapsed_time": "11:18:51", "remaining_time": "11:46:34", "throughput": 661.71, "total_tokens": 26952544} {"current_steps": 19600, "total_steps": 40000, "eval_loss": 0.7469459772109985, "epoch": 0.6273606043147045, "percentage": 49.0, "elapsed_time": "11:24:39", "remaining_time": "11:52:35", "throughput": 656.11, "total_tokens": 26952544} {"current_steps": 19605, "total_steps": 40000, "loss": 0.8745, "lr": 2.577741883216272e-05, "epoch": 0.627520645285193, "percentage": 49.01, "elapsed_time": "11:24:43", "remaining_time": "11:52:18", "throughput": 656.21, "total_tokens": 26959328} {"current_steps": 19610, "total_steps": 40000, "loss": 0.8894, "lr": 2.576760604336642e-05, "epoch": 0.6276806862556814, "percentage": 49.02, "elapsed_time": "11:24:44", "remaining_time": "11:51:59", "throughput": 656.35, "total_tokens": 26965984} {"current_steps": 19615, "total_steps": 40000, "loss": 0.7099, "lr": 2.575779313619563e-05, "epoch": 0.6278407272261699, "percentage": 49.04, "elapsed_time": "11:24:46", "remaining_time": "11:51:39", "throughput": 656.48, "total_tokens": 26972480} {"current_steps": 19620, "total_steps": 40000, "loss": 0.5127, "lr": 2.5747980112163605e-05, "epoch": 0.6280007681966584, "percentage": 49.05, "elapsed_time": "11:24:48", "remaining_time": "11:51:19", "throughput": 656.61, "total_tokens": 26979200} {"current_steps": 19625, "total_steps": 40000, "loss": 0.9095, "lr": 2.5738166972783656e-05, "epoch": 0.6281608091671468, "percentage": 49.06, "elapsed_time": "11:24:50", "remaining_time": "11:51:00", "throughput": 656.75, "total_tokens": 26986000} {"current_steps": 19630, "total_steps": 40000, "loss": 0.8447, "lr": 2.5728353719569075e-05, "epoch": 0.6283208501376353, "percentage": 49.08, "elapsed_time": "11:24:51", "remaining_time": "11:50:40", "throughput": 656.9, "total_tokens": 26993088} {"current_steps": 19635, "total_steps": 40000, "loss": 0.632, "lr": 2.57185403540332e-05, "epoch": 0.6284808911081237, "percentage": 49.09, "elapsed_time": "11:24:53", "remaining_time": "11:50:21", "throughput": 657.04, "total_tokens": 26999904} {"current_steps": 19640, "total_steps": 40000, "loss": 0.8086, "lr": 2.5708726877689375e-05, "epoch": 0.6286409320786122, "percentage": 49.1, "elapsed_time": "11:24:55", "remaining_time": "11:50:01", "throughput": 657.17, "total_tokens": 27006576} {"current_steps": 19645, "total_steps": 40000, "loss": 0.7024, "lr": 2.5698913292050964e-05, "epoch": 0.6288009730491005, "percentage": 49.11, "elapsed_time": "11:24:56", "remaining_time": "11:49:42", "throughput": 657.31, "total_tokens": 27013296} {"current_steps": 19650, "total_steps": 40000, "loss": 0.7004, "lr": 2.568909959863133e-05, "epoch": 0.628961014019589, "percentage": 49.12, "elapsed_time": "11:24:58", "remaining_time": "11:49:22", "throughput": 657.44, "total_tokens": 27020096} {"current_steps": 19655, "total_steps": 40000, "loss": 0.8292, "lr": 2.5679285798943887e-05, "epoch": 0.6291210549900774, "percentage": 49.14, "elapsed_time": "11:25:00", "remaining_time": "11:49:03", "throughput": 657.59, "total_tokens": 27027072} {"current_steps": 19660, "total_steps": 40000, "loss": 0.8594, "lr": 2.5669471894502035e-05, "epoch": 0.6292810959605659, "percentage": 49.15, "elapsed_time": "11:25:02", "remaining_time": "11:48:43", "throughput": 657.71, "total_tokens": 27033392} {"current_steps": 19665, "total_steps": 40000, "loss": 0.9728, "lr": 2.56596578868192e-05, "epoch": 0.6294411369310543, "percentage": 49.16, "elapsed_time": "11:25:03", "remaining_time": "11:48:24", "throughput": 657.85, "total_tokens": 27040176} {"current_steps": 19670, "total_steps": 40000, "loss": 0.6267, "lr": 2.564984377740883e-05, "epoch": 0.6296011779015428, "percentage": 49.18, "elapsed_time": "11:25:05", "remaining_time": "11:48:04", "throughput": 657.99, "total_tokens": 27047312} {"current_steps": 19675, "total_steps": 40000, "loss": 0.7487, "lr": 2.564002956778438e-05, "epoch": 0.6297612188720313, "percentage": 49.19, "elapsed_time": "11:25:07", "remaining_time": "11:47:45", "throughput": 658.13, "total_tokens": 27054144} {"current_steps": 19680, "total_steps": 40000, "loss": 0.7296, "lr": 2.563021525945934e-05, "epoch": 0.6299212598425197, "percentage": 49.2, "elapsed_time": "11:25:09", "remaining_time": "11:47:26", "throughput": 658.26, "total_tokens": 27060608} {"current_steps": 19685, "total_steps": 40000, "loss": 0.7968, "lr": 2.562040085394718e-05, "epoch": 0.6300813008130082, "percentage": 49.21, "elapsed_time": "11:25:10", "remaining_time": "11:47:06", "throughput": 658.39, "total_tokens": 27067168} {"current_steps": 19690, "total_steps": 40000, "loss": 0.6896, "lr": 2.56105863527614e-05, "epoch": 0.6302413417834966, "percentage": 49.23, "elapsed_time": "11:25:12", "remaining_time": "11:46:47", "throughput": 658.54, "total_tokens": 27074112} {"current_steps": 19695, "total_steps": 40000, "loss": 0.7758, "lr": 2.5600771757415548e-05, "epoch": 0.630401382753985, "percentage": 49.24, "elapsed_time": "11:25:14", "remaining_time": "11:46:27", "throughput": 658.68, "total_tokens": 27081040} {"current_steps": 19700, "total_steps": 40000, "loss": 0.5943, "lr": 2.5590957069423134e-05, "epoch": 0.6305614237244734, "percentage": 49.25, "elapsed_time": "11:25:16", "remaining_time": "11:46:08", "throughput": 658.81, "total_tokens": 27087792} {"current_steps": 19705, "total_steps": 40000, "loss": 0.5442, "lr": 2.5581142290297716e-05, "epoch": 0.6307214646949619, "percentage": 49.26, "elapsed_time": "11:25:17", "remaining_time": "11:45:48", "throughput": 658.95, "total_tokens": 27094752} {"current_steps": 19710, "total_steps": 40000, "loss": 0.7472, "lr": 2.557132742155285e-05, "epoch": 0.6308815056654503, "percentage": 49.28, "elapsed_time": "11:25:19", "remaining_time": "11:45:29", "throughput": 659.09, "total_tokens": 27101392} {"current_steps": 19715, "total_steps": 40000, "loss": 0.9742, "lr": 2.556151246470212e-05, "epoch": 0.6310415466359388, "percentage": 49.29, "elapsed_time": "11:25:21", "remaining_time": "11:45:10", "throughput": 659.24, "total_tokens": 27108624} {"current_steps": 19720, "total_steps": 40000, "loss": 0.6037, "lr": 2.5551697421259114e-05, "epoch": 0.6312015876064272, "percentage": 49.3, "elapsed_time": "11:25:23", "remaining_time": "11:44:50", "throughput": 659.38, "total_tokens": 27115600} {"current_steps": 19725, "total_steps": 40000, "loss": 0.6899, "lr": 2.554188229273743e-05, "epoch": 0.6313616285769157, "percentage": 49.31, "elapsed_time": "11:25:24", "remaining_time": "11:44:31", "throughput": 659.52, "total_tokens": 27122432} {"current_steps": 19730, "total_steps": 40000, "loss": 0.8957, "lr": 2.5532067080650678e-05, "epoch": 0.6315216695474042, "percentage": 49.33, "elapsed_time": "11:25:26", "remaining_time": "11:44:12", "throughput": 659.66, "total_tokens": 27129360} {"current_steps": 19735, "total_steps": 40000, "loss": 0.768, "lr": 2.55222517865125e-05, "epoch": 0.6316817105178926, "percentage": 49.34, "elapsed_time": "11:25:28", "remaining_time": "11:43:52", "throughput": 659.8, "total_tokens": 27136432} {"current_steps": 19740, "total_steps": 40000, "loss": 0.4168, "lr": 2.5512436411836538e-05, "epoch": 0.6318417514883811, "percentage": 49.35, "elapsed_time": "11:25:29", "remaining_time": "11:43:33", "throughput": 659.96, "total_tokens": 27144176} {"current_steps": 19745, "total_steps": 40000, "loss": 0.8514, "lr": 2.5502620958136443e-05, "epoch": 0.6320017924588694, "percentage": 49.36, "elapsed_time": "11:25:31", "remaining_time": "11:43:14", "throughput": 660.1, "total_tokens": 27150848} {"current_steps": 19750, "total_steps": 40000, "loss": 0.7072, "lr": 2.5492805426925874e-05, "epoch": 0.6321618334293579, "percentage": 49.38, "elapsed_time": "11:25:33", "remaining_time": "11:42:54", "throughput": 660.23, "total_tokens": 27157504} {"current_steps": 19755, "total_steps": 40000, "loss": 0.8406, "lr": 2.5482989819718523e-05, "epoch": 0.6323218743998463, "percentage": 49.39, "elapsed_time": "11:25:35", "remaining_time": "11:42:35", "throughput": 660.38, "total_tokens": 27164816} {"current_steps": 19760, "total_steps": 40000, "loss": 0.7223, "lr": 2.5473174138028065e-05, "epoch": 0.6324819153703348, "percentage": 49.4, "elapsed_time": "11:25:36", "remaining_time": "11:42:16", "throughput": 660.52, "total_tokens": 27171696} {"current_steps": 19765, "total_steps": 40000, "loss": 0.8155, "lr": 2.5463358383368212e-05, "epoch": 0.6326419563408232, "percentage": 49.41, "elapsed_time": "11:25:38", "remaining_time": "11:41:56", "throughput": 660.65, "total_tokens": 27178288} {"current_steps": 19770, "total_steps": 40000, "loss": 0.5939, "lr": 2.545354255725267e-05, "epoch": 0.6328019973113117, "percentage": 49.43, "elapsed_time": "11:25:40", "remaining_time": "11:41:37", "throughput": 660.79, "total_tokens": 27185040} {"current_steps": 19775, "total_steps": 40000, "loss": 0.7557, "lr": 2.5443726661195165e-05, "epoch": 0.6329620382818001, "percentage": 49.44, "elapsed_time": "11:25:42", "remaining_time": "11:41:18", "throughput": 660.92, "total_tokens": 27191824} {"current_steps": 19780, "total_steps": 40000, "loss": 0.6251, "lr": 2.543391069670944e-05, "epoch": 0.6331220792522886, "percentage": 49.45, "elapsed_time": "11:25:43", "remaining_time": "11:40:59", "throughput": 661.07, "total_tokens": 27198832} {"current_steps": 19785, "total_steps": 40000, "loss": 0.849, "lr": 2.5424094665309228e-05, "epoch": 0.6332821202227771, "percentage": 49.46, "elapsed_time": "11:25:45", "remaining_time": "11:40:39", "throughput": 661.21, "total_tokens": 27205888} {"current_steps": 19790, "total_steps": 40000, "loss": 0.898, "lr": 2.5414278568508292e-05, "epoch": 0.6334421611932655, "percentage": 49.48, "elapsed_time": "11:25:47", "remaining_time": "11:40:20", "throughput": 661.36, "total_tokens": 27213088} {"current_steps": 19795, "total_steps": 40000, "loss": 0.6706, "lr": 2.540446240782039e-05, "epoch": 0.633602202163754, "percentage": 49.49, "elapsed_time": "11:25:49", "remaining_time": "11:40:01", "throughput": 661.5, "total_tokens": 27220128} {"current_steps": 19800, "total_steps": 40000, "loss": 0.7124, "lr": 2.5394646184759307e-05, "epoch": 0.6337622431342423, "percentage": 49.5, "elapsed_time": "11:25:50", "remaining_time": "11:39:42", "throughput": 661.64, "total_tokens": 27226896} {"current_steps": 19800, "total_steps": 40000, "eval_loss": 0.7465463876724243, "epoch": 0.6337622431342423, "percentage": 49.5, "elapsed_time": "11:31:38", "remaining_time": "11:45:37", "throughput": 656.09, "total_tokens": 27226896} {"current_steps": 19805, "total_steps": 40000, "loss": 0.7065, "lr": 2.538482990083882e-05, "epoch": 0.6339222841047308, "percentage": 49.51, "elapsed_time": "11:31:42", "remaining_time": "11:45:19", "throughput": 656.19, "total_tokens": 27233680} {"current_steps": 19810, "total_steps": 40000, "loss": 0.6704, "lr": 2.5375013557572725e-05, "epoch": 0.6340823250752192, "percentage": 49.53, "elapsed_time": "11:31:44", "remaining_time": "11:45:00", "throughput": 656.32, "total_tokens": 27240080} {"current_steps": 19815, "total_steps": 40000, "loss": 0.6125, "lr": 2.536519715647483e-05, "epoch": 0.6342423660457077, "percentage": 49.54, "elapsed_time": "11:31:46", "remaining_time": "11:44:41", "throughput": 656.46, "total_tokens": 27247072} {"current_steps": 19820, "total_steps": 40000, "loss": 0.7234, "lr": 2.535538069905894e-05, "epoch": 0.6344024070161961, "percentage": 49.55, "elapsed_time": "11:31:47", "remaining_time": "11:44:21", "throughput": 656.59, "total_tokens": 27253776} {"current_steps": 19825, "total_steps": 40000, "loss": 0.6793, "lr": 2.534556418683888e-05, "epoch": 0.6345624479866846, "percentage": 49.56, "elapsed_time": "11:31:49", "remaining_time": "11:44:02", "throughput": 656.72, "total_tokens": 27260224} {"current_steps": 19830, "total_steps": 40000, "loss": 0.7392, "lr": 2.5335747621328486e-05, "epoch": 0.634722488957173, "percentage": 49.58, "elapsed_time": "11:31:51", "remaining_time": "11:43:43", "throughput": 656.87, "total_tokens": 27267456} {"current_steps": 19835, "total_steps": 40000, "loss": 0.5343, "lr": 2.5325931004041586e-05, "epoch": 0.6348825299276615, "percentage": 49.59, "elapsed_time": "11:31:52", "remaining_time": "11:43:23", "throughput": 657.0, "total_tokens": 27274096} {"current_steps": 19840, "total_steps": 40000, "loss": 0.6724, "lr": 2.5316114336492032e-05, "epoch": 0.63504257089815, "percentage": 49.6, "elapsed_time": "11:31:54", "remaining_time": "11:43:04", "throughput": 657.13, "total_tokens": 27280560} {"current_steps": 19845, "total_steps": 40000, "loss": 0.8433, "lr": 2.530629762019367e-05, "epoch": 0.6352026118686384, "percentage": 49.61, "elapsed_time": "11:31:56", "remaining_time": "11:42:44", "throughput": 657.27, "total_tokens": 27287664} {"current_steps": 19850, "total_steps": 40000, "loss": 0.7615, "lr": 2.5296480856660364e-05, "epoch": 0.6353626528391269, "percentage": 49.62, "elapsed_time": "11:31:58", "remaining_time": "11:42:25", "throughput": 657.41, "total_tokens": 27294416} {"current_steps": 19855, "total_steps": 40000, "loss": 0.9719, "lr": 2.528666404740599e-05, "epoch": 0.6355226938096152, "percentage": 49.64, "elapsed_time": "11:31:59", "remaining_time": "11:42:06", "throughput": 657.55, "total_tokens": 27301376} {"current_steps": 19860, "total_steps": 40000, "loss": 0.4876, "lr": 2.527684719394442e-05, "epoch": 0.6356827347801037, "percentage": 49.65, "elapsed_time": "11:32:01", "remaining_time": "11:41:47", "throughput": 657.68, "total_tokens": 27307968} {"current_steps": 19865, "total_steps": 40000, "loss": 0.7762, "lr": 2.526703029778953e-05, "epoch": 0.6358427757505921, "percentage": 49.66, "elapsed_time": "11:32:03", "remaining_time": "11:41:27", "throughput": 657.83, "total_tokens": 27315472} {"current_steps": 19870, "total_steps": 40000, "loss": 0.6673, "lr": 2.5257213360455208e-05, "epoch": 0.6360028167210806, "percentage": 49.68, "elapsed_time": "11:32:05", "remaining_time": "11:41:08", "throughput": 657.96, "total_tokens": 27321936} {"current_steps": 19875, "total_steps": 40000, "loss": 0.7966, "lr": 2.5247396383455353e-05, "epoch": 0.636162857691569, "percentage": 49.69, "elapsed_time": "11:32:06", "remaining_time": "11:40:49", "throughput": 658.09, "total_tokens": 27328448} {"current_steps": 19880, "total_steps": 40000, "loss": 0.8187, "lr": 2.523757936830387e-05, "epoch": 0.6363228986620575, "percentage": 49.7, "elapsed_time": "11:32:08", "remaining_time": "11:40:29", "throughput": 658.23, "total_tokens": 27335376} {"current_steps": 19885, "total_steps": 40000, "loss": 0.6948, "lr": 2.5227762316514662e-05, "epoch": 0.636482939632546, "percentage": 49.71, "elapsed_time": "11:32:10", "remaining_time": "11:40:10", "throughput": 658.36, "total_tokens": 27342064} {"current_steps": 19890, "total_steps": 40000, "loss": 0.7428, "lr": 2.5217945229601648e-05, "epoch": 0.6366429806030344, "percentage": 49.73, "elapsed_time": "11:32:12", "remaining_time": "11:39:51", "throughput": 658.5, "total_tokens": 27348800} {"current_steps": 19895, "total_steps": 40000, "loss": 0.5524, "lr": 2.5208128109078738e-05, "epoch": 0.6368030215735229, "percentage": 49.74, "elapsed_time": "11:32:13", "remaining_time": "11:39:32", "throughput": 658.64, "total_tokens": 27355664} {"current_steps": 19900, "total_steps": 40000, "loss": 0.7922, "lr": 2.5198310956459853e-05, "epoch": 0.6369630625440112, "percentage": 49.75, "elapsed_time": "11:32:15", "remaining_time": "11:39:12", "throughput": 658.77, "total_tokens": 27362496} {"current_steps": 19905, "total_steps": 40000, "loss": 0.8208, "lr": 2.518849377325893e-05, "epoch": 0.6371231035144997, "percentage": 49.76, "elapsed_time": "11:32:17", "remaining_time": "11:38:53", "throughput": 658.91, "total_tokens": 27369424} {"current_steps": 19910, "total_steps": 40000, "loss": 1.0023, "lr": 2.51786765609899e-05, "epoch": 0.6372831444849881, "percentage": 49.78, "elapsed_time": "11:32:19", "remaining_time": "11:38:34", "throughput": 659.05, "total_tokens": 27376304} {"current_steps": 19915, "total_steps": 40000, "loss": 0.7016, "lr": 2.5168859321166694e-05, "epoch": 0.6374431854554766, "percentage": 49.79, "elapsed_time": "11:32:20", "remaining_time": "11:38:15", "throughput": 659.18, "total_tokens": 27383008} {"current_steps": 19920, "total_steps": 40000, "loss": 0.5966, "lr": 2.515904205530326e-05, "epoch": 0.637603226425965, "percentage": 49.8, "elapsed_time": "11:32:22", "remaining_time": "11:37:56", "throughput": 659.33, "total_tokens": 27390112} {"current_steps": 19925, "total_steps": 40000, "loss": 0.5544, "lr": 2.514922476491355e-05, "epoch": 0.6377632673964535, "percentage": 49.81, "elapsed_time": "11:32:24", "remaining_time": "11:37:36", "throughput": 659.46, "total_tokens": 27396768} {"current_steps": 19930, "total_steps": 40000, "loss": 0.7374, "lr": 2.51394074515115e-05, "epoch": 0.6379233083669419, "percentage": 49.83, "elapsed_time": "11:32:25", "remaining_time": "11:37:17", "throughput": 659.6, "total_tokens": 27403792} {"current_steps": 19935, "total_steps": 40000, "loss": 0.8911, "lr": 2.5129590116611067e-05, "epoch": 0.6380833493374304, "percentage": 49.84, "elapsed_time": "11:32:27", "remaining_time": "11:36:58", "throughput": 659.74, "total_tokens": 27410848} {"current_steps": 19940, "total_steps": 40000, "loss": 0.6687, "lr": 2.5119772761726212e-05, "epoch": 0.6382433903079189, "percentage": 49.85, "elapsed_time": "11:32:29", "remaining_time": "11:36:39", "throughput": 659.88, "total_tokens": 27417792} {"current_steps": 19945, "total_steps": 40000, "loss": 0.5505, "lr": 2.5109955388370893e-05, "epoch": 0.6384034312784073, "percentage": 49.86, "elapsed_time": "11:32:31", "remaining_time": "11:36:20", "throughput": 660.03, "total_tokens": 27425104} {"current_steps": 19950, "total_steps": 40000, "loss": 0.6876, "lr": 2.510013799805907e-05, "epoch": 0.6385634722488958, "percentage": 49.88, "elapsed_time": "11:32:32", "remaining_time": "11:36:01", "throughput": 660.17, "total_tokens": 27431888} {"current_steps": 19955, "total_steps": 40000, "loss": 0.7366, "lr": 2.5090320592304706e-05, "epoch": 0.6387235132193841, "percentage": 49.89, "elapsed_time": "11:32:34", "remaining_time": "11:35:42", "throughput": 660.31, "total_tokens": 27439072} {"current_steps": 19960, "total_steps": 40000, "loss": 0.8642, "lr": 2.5080503172621777e-05, "epoch": 0.6388835541898726, "percentage": 49.9, "elapsed_time": "11:32:36", "remaining_time": "11:35:22", "throughput": 660.45, "total_tokens": 27445712} {"current_steps": 19965, "total_steps": 40000, "loss": 0.6733, "lr": 2.5070685740524246e-05, "epoch": 0.639043595160361, "percentage": 49.91, "elapsed_time": "11:32:38", "remaining_time": "11:35:03", "throughput": 660.58, "total_tokens": 27452576} {"current_steps": 19970, "total_steps": 40000, "loss": 0.8969, "lr": 2.5060868297526084e-05, "epoch": 0.6392036361308495, "percentage": 49.93, "elapsed_time": "11:32:39", "remaining_time": "11:34:44", "throughput": 660.72, "total_tokens": 27459328} {"current_steps": 19975, "total_steps": 40000, "loss": 0.8271, "lr": 2.5051050845141267e-05, "epoch": 0.6393636771013379, "percentage": 49.94, "elapsed_time": "11:32:41", "remaining_time": "11:34:25", "throughput": 660.87, "total_tokens": 27466816} {"current_steps": 19980, "total_steps": 40000, "loss": 0.6275, "lr": 2.5041233384883765e-05, "epoch": 0.6395237180718264, "percentage": 49.95, "elapsed_time": "11:32:43", "remaining_time": "11:34:06", "throughput": 661.01, "total_tokens": 27473840} {"current_steps": 19985, "total_steps": 40000, "loss": 0.5391, "lr": 2.5031415918267564e-05, "epoch": 0.6396837590423148, "percentage": 49.96, "elapsed_time": "11:32:45", "remaining_time": "11:33:47", "throughput": 661.15, "total_tokens": 27480688} {"current_steps": 19990, "total_steps": 40000, "loss": 0.6704, "lr": 2.5021598446806626e-05, "epoch": 0.6398438000128033, "percentage": 49.98, "elapsed_time": "11:32:46", "remaining_time": "11:33:28", "throughput": 661.28, "total_tokens": 27487264} {"current_steps": 19995, "total_steps": 40000, "loss": 0.6506, "lr": 2.5011780972014937e-05, "epoch": 0.6400038409832918, "percentage": 49.99, "elapsed_time": "11:32:48", "remaining_time": "11:33:09", "throughput": 661.42, "total_tokens": 27494240} {"current_steps": 20000, "total_steps": 40000, "loss": 0.7017, "lr": 2.5001963495406478e-05, "epoch": 0.6401638819537802, "percentage": 50.0, "elapsed_time": "11:32:50", "remaining_time": "11:32:50", "throughput": 661.56, "total_tokens": 27501216} {"current_steps": 20000, "total_steps": 40000, "eval_loss": 0.746458888053894, "epoch": 0.6401638819537802, "percentage": 50.0, "elapsed_time": "11:38:37", "remaining_time": "11:38:37", "throughput": 656.07, "total_tokens": 27501216} {"current_steps": 20005, "total_steps": 40000, "loss": 0.8481, "lr": 2.499214601849522e-05, "epoch": 0.6403239229242687, "percentage": 50.01, "elapsed_time": "11:38:42", "remaining_time": "11:38:21", "throughput": 656.17, "total_tokens": 27508000} {"current_steps": 20010, "total_steps": 40000, "loss": 0.7617, "lr": 2.4982328542795148e-05, "epoch": 0.640483963894757, "percentage": 50.02, "elapsed_time": "11:38:43", "remaining_time": "11:38:02", "throughput": 656.3, "total_tokens": 27514640} {"current_steps": 20015, "total_steps": 40000, "loss": 0.7144, "lr": 2.497251106982024e-05, "epoch": 0.6406440048652455, "percentage": 50.04, "elapsed_time": "11:38:45", "remaining_time": "11:37:42", "throughput": 656.44, "total_tokens": 27521520} {"current_steps": 20020, "total_steps": 40000, "loss": 0.8711, "lr": 2.4962693601084458e-05, "epoch": 0.6408040458357339, "percentage": 50.05, "elapsed_time": "11:38:47", "remaining_time": "11:37:23", "throughput": 656.57, "total_tokens": 27528176} {"current_steps": 20025, "total_steps": 40000, "loss": 0.6552, "lr": 2.4952876138101794e-05, "epoch": 0.6409640868062224, "percentage": 50.06, "elapsed_time": "11:38:49", "remaining_time": "11:37:04", "throughput": 656.7, "total_tokens": 27534976} {"current_steps": 20030, "total_steps": 40000, "loss": 0.6949, "lr": 2.4943058682386233e-05, "epoch": 0.6411241277767108, "percentage": 50.08, "elapsed_time": "11:38:50", "remaining_time": "11:36:45", "throughput": 656.84, "total_tokens": 27541968} {"current_steps": 20035, "total_steps": 40000, "loss": 0.689, "lr": 2.493324123545173e-05, "epoch": 0.6412841687471993, "percentage": 50.09, "elapsed_time": "11:38:52", "remaining_time": "11:36:26", "throughput": 656.97, "total_tokens": 27548640} {"current_steps": 20040, "total_steps": 40000, "loss": 0.9365, "lr": 2.4923423798812272e-05, "epoch": 0.6414442097176877, "percentage": 50.1, "elapsed_time": "11:38:54", "remaining_time": "11:36:06", "throughput": 657.11, "total_tokens": 27555296} {"current_steps": 20045, "total_steps": 40000, "loss": 0.591, "lr": 2.4913606373981825e-05, "epoch": 0.6416042506881762, "percentage": 50.11, "elapsed_time": "11:38:56", "remaining_time": "11:35:47", "throughput": 657.24, "total_tokens": 27562272} {"current_steps": 20050, "total_steps": 40000, "loss": 0.8002, "lr": 2.4903788962474357e-05, "epoch": 0.6417642916586647, "percentage": 50.12, "elapsed_time": "11:38:57", "remaining_time": "11:35:28", "throughput": 657.38, "total_tokens": 27569072} {"current_steps": 20055, "total_steps": 40000, "loss": 0.5782, "lr": 2.489397156580385e-05, "epoch": 0.641924332629153, "percentage": 50.14, "elapsed_time": "11:38:59", "remaining_time": "11:35:09", "throughput": 657.51, "total_tokens": 27575888} {"current_steps": 20060, "total_steps": 40000, "loss": 0.7759, "lr": 2.4884154185484246e-05, "epoch": 0.6420843735996415, "percentage": 50.15, "elapsed_time": "11:39:01", "remaining_time": "11:34:50", "throughput": 657.64, "total_tokens": 27582480} {"current_steps": 20065, "total_steps": 40000, "loss": 1.0219, "lr": 2.4874336823029526e-05, "epoch": 0.6422444145701299, "percentage": 50.16, "elapsed_time": "11:39:03", "remaining_time": "11:34:31", "throughput": 657.79, "total_tokens": 27589696} {"current_steps": 20070, "total_steps": 40000, "loss": 0.6654, "lr": 2.4864519479953656e-05, "epoch": 0.6424044555406184, "percentage": 50.18, "elapsed_time": "11:39:04", "remaining_time": "11:34:12", "throughput": 657.92, "total_tokens": 27596512} {"current_steps": 20075, "total_steps": 40000, "loss": 0.6895, "lr": 2.485470215777058e-05, "epoch": 0.6425644965111068, "percentage": 50.19, "elapsed_time": "11:39:06", "remaining_time": "11:33:53", "throughput": 658.06, "total_tokens": 27603152} {"current_steps": 20080, "total_steps": 40000, "loss": 0.8809, "lr": 2.4844884857994258e-05, "epoch": 0.6427245374815953, "percentage": 50.2, "elapsed_time": "11:39:08", "remaining_time": "11:33:34", "throughput": 658.2, "total_tokens": 27610256} {"current_steps": 20085, "total_steps": 40000, "loss": 0.7903, "lr": 2.4835067582138638e-05, "epoch": 0.6428845784520837, "percentage": 50.21, "elapsed_time": "11:39:09", "remaining_time": "11:33:14", "throughput": 658.34, "total_tokens": 27617360} {"current_steps": 20090, "total_steps": 40000, "loss": 0.6717, "lr": 2.4825250331717666e-05, "epoch": 0.6430446194225722, "percentage": 50.22, "elapsed_time": "11:39:11", "remaining_time": "11:32:55", "throughput": 658.48, "total_tokens": 27624336} {"current_steps": 20095, "total_steps": 40000, "loss": 0.5902, "lr": 2.4815433108245298e-05, "epoch": 0.6432046603930607, "percentage": 50.24, "elapsed_time": "11:39:13", "remaining_time": "11:32:36", "throughput": 658.61, "total_tokens": 27631072} {"current_steps": 20100, "total_steps": 40000, "loss": 0.8438, "lr": 2.4805615913235456e-05, "epoch": 0.6433647013635491, "percentage": 50.25, "elapsed_time": "11:39:15", "remaining_time": "11:32:17", "throughput": 658.75, "total_tokens": 27637936} {"current_steps": 20105, "total_steps": 40000, "loss": 0.7644, "lr": 2.479579874820208e-05, "epoch": 0.6435247423340376, "percentage": 50.26, "elapsed_time": "11:39:16", "remaining_time": "11:31:58", "throughput": 658.88, "total_tokens": 27644704} {"current_steps": 20110, "total_steps": 40000, "loss": 1.0649, "lr": 2.4785981614659115e-05, "epoch": 0.6436847833045259, "percentage": 50.28, "elapsed_time": "11:39:18", "remaining_time": "11:31:39", "throughput": 659.01, "total_tokens": 27651184} {"current_steps": 20115, "total_steps": 40000, "loss": 0.738, "lr": 2.477616451412047e-05, "epoch": 0.6438448242750144, "percentage": 50.29, "elapsed_time": "11:39:20", "remaining_time": "11:31:20", "throughput": 659.17, "total_tokens": 27658896} {"current_steps": 20120, "total_steps": 40000, "loss": 0.6496, "lr": 2.476634744810007e-05, "epoch": 0.6440048652455028, "percentage": 50.3, "elapsed_time": "11:39:22", "remaining_time": "11:31:01", "throughput": 659.3, "total_tokens": 27665712} {"current_steps": 20125, "total_steps": 40000, "loss": 0.7875, "lr": 2.475653041811183e-05, "epoch": 0.6441649062159913, "percentage": 50.31, "elapsed_time": "11:39:23", "remaining_time": "11:30:42", "throughput": 659.44, "total_tokens": 27672512} {"current_steps": 20130, "total_steps": 40000, "loss": 0.6494, "lr": 2.4746713425669652e-05, "epoch": 0.6443249471864797, "percentage": 50.32, "elapsed_time": "11:39:25", "remaining_time": "11:30:23", "throughput": 659.59, "total_tokens": 27679968} {"current_steps": 20135, "total_steps": 40000, "loss": 0.7277, "lr": 2.4736896472287458e-05, "epoch": 0.6444849881569682, "percentage": 50.34, "elapsed_time": "11:39:27", "remaining_time": "11:30:04", "throughput": 659.72, "total_tokens": 27686672} {"current_steps": 20140, "total_steps": 40000, "loss": 0.7707, "lr": 2.4727079559479124e-05, "epoch": 0.6446450291274566, "percentage": 50.35, "elapsed_time": "11:39:29", "remaining_time": "11:29:45", "throughput": 659.87, "total_tokens": 27694128} {"current_steps": 20145, "total_steps": 40000, "loss": 0.7848, "lr": 2.4717262688758557e-05, "epoch": 0.6448050700979451, "percentage": 50.36, "elapsed_time": "11:39:30", "remaining_time": "11:29:26", "throughput": 660.01, "total_tokens": 27701152} {"current_steps": 20150, "total_steps": 40000, "loss": 0.8491, "lr": 2.4707445861639637e-05, "epoch": 0.6449651110684336, "percentage": 50.38, "elapsed_time": "11:39:32", "remaining_time": "11:29:07", "throughput": 660.15, "total_tokens": 27708048} {"current_steps": 20155, "total_steps": 40000, "loss": 0.7587, "lr": 2.4697629079636244e-05, "epoch": 0.645125152038922, "percentage": 50.39, "elapsed_time": "11:39:34", "remaining_time": "11:28:48", "throughput": 660.28, "total_tokens": 27714672} {"current_steps": 20160, "total_steps": 40000, "loss": 0.9801, "lr": 2.4687812344262244e-05, "epoch": 0.6452851930094105, "percentage": 50.4, "elapsed_time": "11:39:36", "remaining_time": "11:28:29", "throughput": 660.43, "total_tokens": 27722048} {"current_steps": 20165, "total_steps": 40000, "loss": 0.8011, "lr": 2.46779956570315e-05, "epoch": 0.6454452339798988, "percentage": 50.41, "elapsed_time": "11:39:37", "remaining_time": "11:28:10", "throughput": 660.56, "total_tokens": 27728960} {"current_steps": 20170, "total_steps": 40000, "loss": 0.6404, "lr": 2.466817901945787e-05, "epoch": 0.6456052749503873, "percentage": 50.42, "elapsed_time": "11:39:39", "remaining_time": "11:27:51", "throughput": 660.69, "total_tokens": 27735440} {"current_steps": 20175, "total_steps": 40000, "loss": 0.8723, "lr": 2.4658362433055217e-05, "epoch": 0.6457653159208757, "percentage": 50.44, "elapsed_time": "11:39:41", "remaining_time": "11:27:32", "throughput": 660.82, "total_tokens": 27741952} {"current_steps": 20180, "total_steps": 40000, "loss": 0.5616, "lr": 2.4648545899337356e-05, "epoch": 0.6459253568913642, "percentage": 50.45, "elapsed_time": "11:39:42", "remaining_time": "11:27:13", "throughput": 660.95, "total_tokens": 27748560} {"current_steps": 20185, "total_steps": 40000, "loss": 0.7756, "lr": 2.4638729419818143e-05, "epoch": 0.6460853978618526, "percentage": 50.46, "elapsed_time": "11:39:44", "remaining_time": "11:26:55", "throughput": 661.08, "total_tokens": 27755136} {"current_steps": 20190, "total_steps": 40000, "loss": 0.6353, "lr": 2.46289129960114e-05, "epoch": 0.6462454388323411, "percentage": 50.48, "elapsed_time": "11:39:46", "remaining_time": "11:26:36", "throughput": 661.22, "total_tokens": 27762064} {"current_steps": 20195, "total_steps": 40000, "loss": 0.8878, "lr": 2.4619096629430924e-05, "epoch": 0.6464054798028295, "percentage": 50.49, "elapsed_time": "11:39:48", "remaining_time": "11:26:17", "throughput": 661.37, "total_tokens": 27769568} {"current_steps": 20200, "total_steps": 40000, "loss": 0.6379, "lr": 2.4609280321590543e-05, "epoch": 0.646565520773318, "percentage": 50.5, "elapsed_time": "11:39:49", "remaining_time": "11:25:58", "throughput": 661.51, "total_tokens": 27776624} {"current_steps": 20200, "total_steps": 40000, "eval_loss": 0.7448143362998962, "epoch": 0.646565520773318, "percentage": 50.5, "elapsed_time": "11:45:37", "remaining_time": "11:31:39", "throughput": 656.08, "total_tokens": 27776624} {"current_steps": 20205, "total_steps": 40000, "loss": 0.8835, "lr": 2.4599464074004037e-05, "epoch": 0.6467255617438065, "percentage": 50.51, "elapsed_time": "11:45:41", "remaining_time": "11:31:21", "throughput": 656.18, "total_tokens": 27783584} {"current_steps": 20210, "total_steps": 40000, "loss": 0.7388, "lr": 2.4589647888185204e-05, "epoch": 0.6468856027142948, "percentage": 50.52, "elapsed_time": "11:45:42", "remaining_time": "11:31:02", "throughput": 656.33, "total_tokens": 27790848} {"current_steps": 20215, "total_steps": 40000, "loss": 0.787, "lr": 2.4579831765647836e-05, "epoch": 0.6470456436847833, "percentage": 50.54, "elapsed_time": "11:45:44", "remaining_time": "11:30:43", "throughput": 656.46, "total_tokens": 27797520} {"current_steps": 20220, "total_steps": 40000, "loss": 0.6143, "lr": 2.4570015707905676e-05, "epoch": 0.6472056846552717, "percentage": 50.55, "elapsed_time": "11:45:46", "remaining_time": "11:30:24", "throughput": 656.6, "total_tokens": 27804560} {"current_steps": 20225, "total_steps": 40000, "loss": 0.7078, "lr": 2.4560199716472508e-05, "epoch": 0.6473657256257602, "percentage": 50.56, "elapsed_time": "11:45:48", "remaining_time": "11:30:05", "throughput": 656.73, "total_tokens": 27811344} {"current_steps": 20230, "total_steps": 40000, "loss": 0.6944, "lr": 2.455038379286207e-05, "epoch": 0.6475257665962486, "percentage": 50.58, "elapsed_time": "11:45:49", "remaining_time": "11:29:46", "throughput": 656.87, "total_tokens": 27818320} {"current_steps": 20235, "total_steps": 40000, "loss": 0.7039, "lr": 2.4540567938588095e-05, "epoch": 0.6476858075667371, "percentage": 50.59, "elapsed_time": "11:45:51", "remaining_time": "11:29:27", "throughput": 657.01, "total_tokens": 27825200} {"current_steps": 20240, "total_steps": 40000, "loss": 0.9736, "lr": 2.4530752155164328e-05, "epoch": 0.6478458485372255, "percentage": 50.6, "elapsed_time": "11:45:53", "remaining_time": "11:29:08", "throughput": 657.15, "total_tokens": 27832416} {"current_steps": 20245, "total_steps": 40000, "loss": 0.8196, "lr": 2.4520936444104463e-05, "epoch": 0.648005889507714, "percentage": 50.61, "elapsed_time": "11:45:55", "remaining_time": "11:28:49", "throughput": 657.28, "total_tokens": 27838960} {"current_steps": 20250, "total_steps": 40000, "loss": 0.5941, "lr": 2.4511120806922218e-05, "epoch": 0.6481659304782024, "percentage": 50.62, "elapsed_time": "11:45:56", "remaining_time": "11:28:30", "throughput": 657.42, "total_tokens": 27846112} {"current_steps": 20255, "total_steps": 40000, "loss": 0.5083, "lr": 2.45013052451313e-05, "epoch": 0.6483259714486909, "percentage": 50.64, "elapsed_time": "11:45:58", "remaining_time": "11:28:11", "throughput": 657.56, "total_tokens": 27853056} {"current_steps": 20260, "total_steps": 40000, "loss": 0.6873, "lr": 2.4491489760245376e-05, "epoch": 0.6484860124191794, "percentage": 50.65, "elapsed_time": "11:46:00", "remaining_time": "11:27:53", "throughput": 657.7, "total_tokens": 27860128} {"current_steps": 20265, "total_steps": 40000, "loss": 0.8587, "lr": 2.4481674353778115e-05, "epoch": 0.6486460533896677, "percentage": 50.66, "elapsed_time": "11:46:01", "remaining_time": "11:27:34", "throughput": 657.83, "total_tokens": 27867024} {"current_steps": 20270, "total_steps": 40000, "loss": 0.6938, "lr": 2.447185902724319e-05, "epoch": 0.6488060943601562, "percentage": 50.68, "elapsed_time": "11:46:03", "remaining_time": "11:27:15", "throughput": 657.97, "total_tokens": 27874016} {"current_steps": 20275, "total_steps": 40000, "loss": 0.7091, "lr": 2.4462043782154233e-05, "epoch": 0.6489661353306446, "percentage": 50.69, "elapsed_time": "11:46:05", "remaining_time": "11:26:56", "throughput": 658.1, "total_tokens": 27880544} {"current_steps": 20280, "total_steps": 40000, "loss": 0.6598, "lr": 2.4452228620024895e-05, "epoch": 0.6491261763011331, "percentage": 50.7, "elapsed_time": "11:46:07", "remaining_time": "11:26:37", "throughput": 658.22, "total_tokens": 27887136} {"current_steps": 20285, "total_steps": 40000, "loss": 0.7487, "lr": 2.4442413542368776e-05, "epoch": 0.6492862172716215, "percentage": 50.71, "elapsed_time": "11:46:08", "remaining_time": "11:26:18", "throughput": 658.36, "total_tokens": 27893856} {"current_steps": 20290, "total_steps": 40000, "loss": 0.7286, "lr": 2.4432598550699502e-05, "epoch": 0.64944625824211, "percentage": 50.72, "elapsed_time": "11:46:10", "remaining_time": "11:25:59", "throughput": 658.5, "total_tokens": 27900912} {"current_steps": 20295, "total_steps": 40000, "loss": 0.7384, "lr": 2.4422783646530663e-05, "epoch": 0.6496062992125984, "percentage": 50.74, "elapsed_time": "11:46:12", "remaining_time": "11:25:40", "throughput": 658.63, "total_tokens": 27907760} {"current_steps": 20300, "total_steps": 40000, "loss": 0.929, "lr": 2.441296883137584e-05, "epoch": 0.6497663401830869, "percentage": 50.75, "elapsed_time": "11:46:14", "remaining_time": "11:25:21", "throughput": 658.76, "total_tokens": 27914560} {"current_steps": 20305, "total_steps": 40000, "loss": 0.7042, "lr": 2.4403154106748592e-05, "epoch": 0.6499263811535753, "percentage": 50.76, "elapsed_time": "11:46:15", "remaining_time": "11:25:02", "throughput": 658.9, "total_tokens": 27921328} {"current_steps": 20310, "total_steps": 40000, "loss": 0.7096, "lr": 2.4393339474162494e-05, "epoch": 0.6500864221240638, "percentage": 50.78, "elapsed_time": "11:46:17", "remaining_time": "11:24:43", "throughput": 659.04, "total_tokens": 27928368} {"current_steps": 20315, "total_steps": 40000, "loss": 0.6642, "lr": 2.4383524935131062e-05, "epoch": 0.6502464630945523, "percentage": 50.79, "elapsed_time": "11:46:19", "remaining_time": "11:24:25", "throughput": 659.18, "total_tokens": 27935552} {"current_steps": 20320, "total_steps": 40000, "loss": 0.9317, "lr": 2.437371049116784e-05, "epoch": 0.6504065040650406, "percentage": 50.8, "elapsed_time": "11:46:21", "remaining_time": "11:24:06", "throughput": 659.32, "total_tokens": 27942592} {"current_steps": 20325, "total_steps": 40000, "loss": 0.703, "lr": 2.436389614378632e-05, "epoch": 0.6505665450355291, "percentage": 50.81, "elapsed_time": "11:46:22", "remaining_time": "11:23:47", "throughput": 659.45, "total_tokens": 27949216} {"current_steps": 20330, "total_steps": 40000, "loss": 0.558, "lr": 2.435408189450002e-05, "epoch": 0.6507265860060175, "percentage": 50.82, "elapsed_time": "11:46:24", "remaining_time": "11:23:28", "throughput": 659.58, "total_tokens": 27955952} {"current_steps": 20335, "total_steps": 40000, "loss": 0.6119, "lr": 2.4344267744822406e-05, "epoch": 0.650886626976506, "percentage": 50.84, "elapsed_time": "11:46:26", "remaining_time": "11:23:09", "throughput": 659.72, "total_tokens": 27962896} {"current_steps": 20340, "total_steps": 40000, "loss": 0.8025, "lr": 2.4334453696266944e-05, "epoch": 0.6510466679469944, "percentage": 50.85, "elapsed_time": "11:46:28", "remaining_time": "11:22:50", "throughput": 659.84, "total_tokens": 27969376} {"current_steps": 20345, "total_steps": 40000, "loss": 0.5157, "lr": 2.432463975034708e-05, "epoch": 0.6512067089174829, "percentage": 50.86, "elapsed_time": "11:46:29", "remaining_time": "11:22:32", "throughput": 659.97, "total_tokens": 27976048} {"current_steps": 20350, "total_steps": 40000, "loss": 0.6788, "lr": 2.4314825908576265e-05, "epoch": 0.6513667498879713, "percentage": 50.88, "elapsed_time": "11:46:31", "remaining_time": "11:22:13", "throughput": 660.1, "total_tokens": 27982512} {"current_steps": 20355, "total_steps": 40000, "loss": 0.7972, "lr": 2.4305012172467897e-05, "epoch": 0.6515267908584598, "percentage": 50.89, "elapsed_time": "11:46:33", "remaining_time": "11:21:54", "throughput": 660.23, "total_tokens": 27989408} {"current_steps": 20360, "total_steps": 40000, "loss": 0.6929, "lr": 2.4295198543535393e-05, "epoch": 0.6516868318289483, "percentage": 50.9, "elapsed_time": "11:46:34", "remaining_time": "11:21:35", "throughput": 660.37, "total_tokens": 27996272} {"current_steps": 20365, "total_steps": 40000, "loss": 0.7367, "lr": 2.4285385023292124e-05, "epoch": 0.6518468727994366, "percentage": 50.91, "elapsed_time": "11:46:36", "remaining_time": "11:21:16", "throughput": 660.5, "total_tokens": 28003184} {"current_steps": 20370, "total_steps": 40000, "loss": 0.8836, "lr": 2.427557161325147e-05, "epoch": 0.6520069137699251, "percentage": 50.92, "elapsed_time": "11:46:38", "remaining_time": "11:20:58", "throughput": 660.64, "total_tokens": 28010256} {"current_steps": 20375, "total_steps": 40000, "loss": 0.632, "lr": 2.4265758314926778e-05, "epoch": 0.6521669547404135, "percentage": 50.94, "elapsed_time": "11:46:40", "remaining_time": "11:20:39", "throughput": 660.78, "total_tokens": 28017200} {"current_steps": 20380, "total_steps": 40000, "loss": 0.7476, "lr": 2.4255945129831373e-05, "epoch": 0.652326995710902, "percentage": 50.95, "elapsed_time": "11:46:41", "remaining_time": "11:20:20", "throughput": 660.92, "total_tokens": 28024096} {"current_steps": 20385, "total_steps": 40000, "loss": 0.851, "lr": 2.4246132059478578e-05, "epoch": 0.6524870366813904, "percentage": 50.96, "elapsed_time": "11:46:43", "remaining_time": "11:20:01", "throughput": 661.05, "total_tokens": 28030864} {"current_steps": 20390, "total_steps": 40000, "loss": 0.9745, "lr": 2.4236319105381706e-05, "epoch": 0.6526470776518789, "percentage": 50.98, "elapsed_time": "11:46:45", "remaining_time": "11:19:43", "throughput": 661.2, "total_tokens": 28038464} {"current_steps": 20395, "total_steps": 40000, "loss": 0.8529, "lr": 2.422650626905401e-05, "epoch": 0.6528071186223673, "percentage": 50.99, "elapsed_time": "11:46:47", "remaining_time": "11:19:24", "throughput": 661.34, "total_tokens": 28045552} {"current_steps": 20400, "total_steps": 40000, "loss": 0.6725, "lr": 2.4216693552008785e-05, "epoch": 0.6529671595928558, "percentage": 51.0, "elapsed_time": "11:46:48", "remaining_time": "11:19:05", "throughput": 661.46, "total_tokens": 28051872} {"current_steps": 20400, "total_steps": 40000, "eval_loss": 0.7442517280578613, "epoch": 0.6529671595928558, "percentage": 51.0, "elapsed_time": "11:52:36", "remaining_time": "11:24:40", "throughput": 656.08, "total_tokens": 28051872} {"current_steps": 20405, "total_steps": 40000, "loss": 0.8399, "lr": 2.4206880955759247e-05, "epoch": 0.6531272005633442, "percentage": 51.01, "elapsed_time": "11:52:40", "remaining_time": "11:24:22", "throughput": 656.19, "total_tokens": 28058624} {"current_steps": 20410, "total_steps": 40000, "loss": 0.73, "lr": 2.419706848181863e-05, "epoch": 0.6532872415338327, "percentage": 51.02, "elapsed_time": "11:52:41", "remaining_time": "11:24:03", "throughput": 656.32, "total_tokens": 28065472} {"current_steps": 20415, "total_steps": 40000, "loss": 0.5372, "lr": 2.4187256131700153e-05, "epoch": 0.6534472825043212, "percentage": 51.04, "elapsed_time": "11:52:43", "remaining_time": "11:23:44", "throughput": 656.46, "total_tokens": 28072576} {"current_steps": 20420, "total_steps": 40000, "loss": 0.9204, "lr": 2.4177443906916985e-05, "epoch": 0.6536073234748095, "percentage": 51.05, "elapsed_time": "11:52:45", "remaining_time": "11:23:26", "throughput": 656.62, "total_tokens": 28080464} {"current_steps": 20425, "total_steps": 40000, "loss": 0.8453, "lr": 2.4167631808982303e-05, "epoch": 0.653767364445298, "percentage": 51.06, "elapsed_time": "11:52:47", "remaining_time": "11:23:07", "throughput": 656.76, "total_tokens": 28087888} {"current_steps": 20430, "total_steps": 40000, "loss": 0.8409, "lr": 2.4157819839409264e-05, "epoch": 0.6539274054157864, "percentage": 51.08, "elapsed_time": "11:52:48", "remaining_time": "11:22:48", "throughput": 656.9, "total_tokens": 28094736} {"current_steps": 20435, "total_steps": 40000, "loss": 0.774, "lr": 2.414800799971098e-05, "epoch": 0.6540874463862749, "percentage": 51.09, "elapsed_time": "11:52:50", "remaining_time": "11:22:29", "throughput": 657.04, "total_tokens": 28101936} {"current_steps": 20440, "total_steps": 40000, "loss": 0.7388, "lr": 2.4138196291400582e-05, "epoch": 0.6542474873567633, "percentage": 51.1, "elapsed_time": "11:52:52", "remaining_time": "11:22:10", "throughput": 657.17, "total_tokens": 28108576} {"current_steps": 20445, "total_steps": 40000, "loss": 0.7499, "lr": 2.412838471599114e-05, "epoch": 0.6544075283272518, "percentage": 51.11, "elapsed_time": "11:52:54", "remaining_time": "11:21:52", "throughput": 657.31, "total_tokens": 28115680} {"current_steps": 20450, "total_steps": 40000, "loss": 0.8869, "lr": 2.411857327499572e-05, "epoch": 0.6545675692977402, "percentage": 51.12, "elapsed_time": "11:52:55", "remaining_time": "11:21:33", "throughput": 657.44, "total_tokens": 28122416} {"current_steps": 20455, "total_steps": 40000, "loss": 0.909, "lr": 2.410876196992739e-05, "epoch": 0.6547276102682287, "percentage": 51.14, "elapsed_time": "11:52:57", "remaining_time": "11:21:14", "throughput": 657.57, "total_tokens": 28129136} {"current_steps": 20460, "total_steps": 40000, "loss": 0.7613, "lr": 2.4098950802299156e-05, "epoch": 0.6548876512387171, "percentage": 51.15, "elapsed_time": "11:52:59", "remaining_time": "11:20:55", "throughput": 657.7, "total_tokens": 28136016} {"current_steps": 20465, "total_steps": 40000, "loss": 0.619, "lr": 2.4089139773624027e-05, "epoch": 0.6550476922092056, "percentage": 51.16, "elapsed_time": "11:53:00", "remaining_time": "11:20:36", "throughput": 657.83, "total_tokens": 28142640} {"current_steps": 20470, "total_steps": 40000, "loss": 0.6706, "lr": 2.4079328885415007e-05, "epoch": 0.655207733179694, "percentage": 51.18, "elapsed_time": "11:53:02", "remaining_time": "11:20:18", "throughput": 657.97, "total_tokens": 28149680} {"current_steps": 20475, "total_steps": 40000, "loss": 0.7591, "lr": 2.4069518139185036e-05, "epoch": 0.6553677741501824, "percentage": 51.19, "elapsed_time": "11:53:04", "remaining_time": "11:19:59", "throughput": 658.1, "total_tokens": 28156256} {"current_steps": 20480, "total_steps": 40000, "loss": 0.5895, "lr": 2.405970753644706e-05, "epoch": 0.6555278151206709, "percentage": 51.2, "elapsed_time": "11:53:06", "remaining_time": "11:19:40", "throughput": 658.23, "total_tokens": 28163024} {"current_steps": 20485, "total_steps": 40000, "loss": 0.635, "lr": 2.4049897078714e-05, "epoch": 0.6556878560911593, "percentage": 51.21, "elapsed_time": "11:53:07", "remaining_time": "11:19:21", "throughput": 658.37, "total_tokens": 28170112} {"current_steps": 20490, "total_steps": 40000, "loss": 0.7457, "lr": 2.404008676749874e-05, "epoch": 0.6558478970616478, "percentage": 51.23, "elapsed_time": "11:53:09", "remaining_time": "11:19:03", "throughput": 658.49, "total_tokens": 28176736} {"current_steps": 20495, "total_steps": 40000, "loss": 0.7981, "lr": 2.403027660431418e-05, "epoch": 0.6560079380321362, "percentage": 51.24, "elapsed_time": "11:53:11", "remaining_time": "11:18:44", "throughput": 658.62, "total_tokens": 28183328} {"current_steps": 20500, "total_steps": 40000, "loss": 0.9392, "lr": 2.402046659067314e-05, "epoch": 0.6561679790026247, "percentage": 51.25, "elapsed_time": "11:53:13", "remaining_time": "11:18:25", "throughput": 658.75, "total_tokens": 28190112} {"current_steps": 20505, "total_steps": 40000, "loss": 0.5327, "lr": 2.401065672808847e-05, "epoch": 0.6563280199731131, "percentage": 51.26, "elapsed_time": "11:53:14", "remaining_time": "11:18:06", "throughput": 658.88, "total_tokens": 28196640} {"current_steps": 20510, "total_steps": 40000, "loss": 0.6452, "lr": 2.400084701807296e-05, "epoch": 0.6564880609436016, "percentage": 51.28, "elapsed_time": "11:53:16", "remaining_time": "11:17:48", "throughput": 659.01, "total_tokens": 28203296} {"current_steps": 20515, "total_steps": 40000, "loss": 0.7553, "lr": 2.39910374621394e-05, "epoch": 0.65664810191409, "percentage": 51.29, "elapsed_time": "11:53:18", "remaining_time": "11:17:29", "throughput": 659.14, "total_tokens": 28210016} {"current_steps": 20520, "total_steps": 40000, "loss": 0.9109, "lr": 2.3981228061800544e-05, "epoch": 0.6568081428845784, "percentage": 51.3, "elapsed_time": "11:53:20", "remaining_time": "11:17:10", "throughput": 659.26, "total_tokens": 28216512} {"current_steps": 20525, "total_steps": 40000, "loss": 0.5702, "lr": 2.3971418818569115e-05, "epoch": 0.656968183855067, "percentage": 51.31, "elapsed_time": "11:53:21", "remaining_time": "11:16:52", "throughput": 659.39, "total_tokens": 28223248} {"current_steps": 20530, "total_steps": 40000, "loss": 0.5666, "lr": 2.3961609733957832e-05, "epoch": 0.6571282248255553, "percentage": 51.32, "elapsed_time": "11:53:23", "remaining_time": "11:16:33", "throughput": 659.52, "total_tokens": 28229968} {"current_steps": 20535, "total_steps": 40000, "loss": 0.6622, "lr": 2.395180080947939e-05, "epoch": 0.6572882657960438, "percentage": 51.34, "elapsed_time": "11:53:25", "remaining_time": "11:16:14", "throughput": 659.66, "total_tokens": 28236768} {"current_steps": 20540, "total_steps": 40000, "loss": 0.6263, "lr": 2.394199204664642e-05, "epoch": 0.6574483067665322, "percentage": 51.35, "elapsed_time": "11:53:26", "remaining_time": "11:15:56", "throughput": 659.79, "total_tokens": 28243424} {"current_steps": 20545, "total_steps": 40000, "loss": 0.8715, "lr": 2.3932183446971583e-05, "epoch": 0.6576083477370207, "percentage": 51.36, "elapsed_time": "11:53:28", "remaining_time": "11:15:37", "throughput": 659.92, "total_tokens": 28250464} {"current_steps": 20550, "total_steps": 40000, "loss": 0.76, "lr": 2.3922375011967473e-05, "epoch": 0.6577683887075091, "percentage": 51.38, "elapsed_time": "11:53:30", "remaining_time": "11:15:18", "throughput": 660.06, "total_tokens": 28257552} {"current_steps": 20555, "total_steps": 40000, "loss": 0.8468, "lr": 2.3912566743146676e-05, "epoch": 0.6579284296779976, "percentage": 51.39, "elapsed_time": "11:53:32", "remaining_time": "11:15:00", "throughput": 660.2, "total_tokens": 28264416} {"current_steps": 20560, "total_steps": 40000, "loss": 0.7663, "lr": 2.390275864202176e-05, "epoch": 0.658088470648486, "percentage": 51.4, "elapsed_time": "11:53:33", "remaining_time": "11:14:41", "throughput": 660.33, "total_tokens": 28271168} {"current_steps": 20565, "total_steps": 40000, "loss": 0.5543, "lr": 2.3892950710105243e-05, "epoch": 0.6582485116189745, "percentage": 51.41, "elapsed_time": "11:53:35", "remaining_time": "11:14:23", "throughput": 660.45, "total_tokens": 28277712} {"current_steps": 20570, "total_steps": 40000, "loss": 0.7902, "lr": 2.3883142948909635e-05, "epoch": 0.6584085525894628, "percentage": 51.42, "elapsed_time": "11:53:37", "remaining_time": "11:14:04", "throughput": 660.58, "total_tokens": 28284416} {"current_steps": 20575, "total_steps": 40000, "loss": 0.6632, "lr": 2.3873335359947433e-05, "epoch": 0.6585685935599513, "percentage": 51.44, "elapsed_time": "11:53:39", "remaining_time": "11:13:45", "throughput": 660.71, "total_tokens": 28291184} {"current_steps": 20580, "total_steps": 40000, "loss": 0.737, "lr": 2.3863527944731066e-05, "epoch": 0.6587286345304398, "percentage": 51.45, "elapsed_time": "11:53:40", "remaining_time": "11:13:27", "throughput": 660.85, "total_tokens": 28298048} {"current_steps": 20585, "total_steps": 40000, "loss": 0.848, "lr": 2.385372070477298e-05, "epoch": 0.6588886755009282, "percentage": 51.46, "elapsed_time": "11:53:42", "remaining_time": "11:13:08", "throughput": 660.98, "total_tokens": 28304704} {"current_steps": 20590, "total_steps": 40000, "loss": 0.7571, "lr": 2.384391364158556e-05, "epoch": 0.6590487164714167, "percentage": 51.48, "elapsed_time": "11:53:44", "remaining_time": "11:12:50", "throughput": 661.12, "total_tokens": 28311872} {"current_steps": 20595, "total_steps": 40000, "loss": 0.7425, "lr": 2.3834106756681185e-05, "epoch": 0.6592087574419051, "percentage": 51.49, "elapsed_time": "11:53:46", "remaining_time": "11:12:31", "throughput": 661.25, "total_tokens": 28318576} {"current_steps": 20600, "total_steps": 40000, "loss": 0.6149, "lr": 2.3824300051572206e-05, "epoch": 0.6593687984123936, "percentage": 51.5, "elapsed_time": "11:53:47", "remaining_time": "11:12:12", "throughput": 661.38, "total_tokens": 28325632} {"current_steps": 20600, "total_steps": 40000, "eval_loss": 0.7431187033653259, "epoch": 0.6593687984123936, "percentage": 51.5, "elapsed_time": "11:59:35", "remaining_time": "11:17:40", "throughput": 656.06, "total_tokens": 28325632} {"current_steps": 20605, "total_steps": 40000, "loss": 0.7798, "lr": 2.3814493527770923e-05, "epoch": 0.659528839382882, "percentage": 51.51, "elapsed_time": "11:59:38", "remaining_time": "11:17:23", "throughput": 656.17, "total_tokens": 28332336} {"current_steps": 20610, "total_steps": 40000, "loss": 0.5077, "lr": 2.3804687186789637e-05, "epoch": 0.6596888803533705, "percentage": 51.52, "elapsed_time": "11:59:40", "remaining_time": "11:17:04", "throughput": 656.3, "total_tokens": 28339344} {"current_steps": 20615, "total_steps": 40000, "loss": 0.615, "lr": 2.379488103014062e-05, "epoch": 0.6598489213238589, "percentage": 51.54, "elapsed_time": "11:59:42", "remaining_time": "11:16:45", "throughput": 656.43, "total_tokens": 28346208} {"current_steps": 20620, "total_steps": 40000, "loss": 0.5162, "lr": 2.3785075059336086e-05, "epoch": 0.6600089622943474, "percentage": 51.55, "elapsed_time": "11:59:43", "remaining_time": "11:16:26", "throughput": 656.57, "total_tokens": 28353312} {"current_steps": 20625, "total_steps": 40000, "loss": 0.6456, "lr": 2.3775269275888248e-05, "epoch": 0.6601690032648359, "percentage": 51.56, "elapsed_time": "11:59:45", "remaining_time": "11:16:08", "throughput": 656.71, "total_tokens": 28360304} {"current_steps": 20630, "total_steps": 40000, "loss": 0.8548, "lr": 2.3765463681309274e-05, "epoch": 0.6603290442353242, "percentage": 51.58, "elapsed_time": "11:59:47", "remaining_time": "11:15:49", "throughput": 656.84, "total_tokens": 28367184} {"current_steps": 20635, "total_steps": 40000, "loss": 0.8055, "lr": 2.3755658277111313e-05, "epoch": 0.6604890852058127, "percentage": 51.59, "elapsed_time": "11:59:49", "remaining_time": "11:15:30", "throughput": 656.97, "total_tokens": 28373968} {"current_steps": 20640, "total_steps": 40000, "loss": 1.0277, "lr": 2.374585306480649e-05, "epoch": 0.6606491261763011, "percentage": 51.6, "elapsed_time": "11:59:50", "remaining_time": "11:15:12", "throughput": 657.1, "total_tokens": 28380672} {"current_steps": 20645, "total_steps": 40000, "loss": 0.8509, "lr": 2.3736048045906877e-05, "epoch": 0.6608091671467896, "percentage": 51.61, "elapsed_time": "11:59:52", "remaining_time": "11:14:53", "throughput": 657.23, "total_tokens": 28387264} {"current_steps": 20650, "total_steps": 40000, "loss": 0.9293, "lr": 2.372624322192454e-05, "epoch": 0.660969208117278, "percentage": 51.62, "elapsed_time": "11:59:54", "remaining_time": "11:14:35", "throughput": 657.35, "total_tokens": 28393584} {"current_steps": 20655, "total_steps": 40000, "loss": 0.9067, "lr": 2.3716438594371516e-05, "epoch": 0.6611292490877665, "percentage": 51.64, "elapsed_time": "11:59:56", "remaining_time": "11:14:16", "throughput": 657.48, "total_tokens": 28400560} {"current_steps": 20660, "total_steps": 40000, "loss": 0.681, "lr": 2.3706634164759784e-05, "epoch": 0.6612892900582549, "percentage": 51.65, "elapsed_time": "11:59:57", "remaining_time": "11:13:57", "throughput": 657.61, "total_tokens": 28407232} {"current_steps": 20665, "total_steps": 40000, "loss": 0.658, "lr": 2.3696829934601323e-05, "epoch": 0.6614493310287434, "percentage": 51.66, "elapsed_time": "11:59:59", "remaining_time": "11:13:39", "throughput": 657.74, "total_tokens": 28413936} {"current_steps": 20670, "total_steps": 40000, "loss": 0.7719, "lr": 2.3687025905408053e-05, "epoch": 0.6616093719992318, "percentage": 51.68, "elapsed_time": "12:00:01", "remaining_time": "11:13:20", "throughput": 657.87, "total_tokens": 28420880} {"current_steps": 20675, "total_steps": 40000, "loss": 0.7724, "lr": 2.3677222078691886e-05, "epoch": 0.6617694129697202, "percentage": 51.69, "elapsed_time": "12:00:02", "remaining_time": "11:13:01", "throughput": 658.0, "total_tokens": 28427568} {"current_steps": 20680, "total_steps": 40000, "loss": 0.7781, "lr": 2.366741845596471e-05, "epoch": 0.6619294539402087, "percentage": 51.7, "elapsed_time": "12:00:04", "remaining_time": "11:12:43", "throughput": 658.13, "total_tokens": 28434400} {"current_steps": 20685, "total_steps": 40000, "loss": 0.9142, "lr": 2.3657615038738343e-05, "epoch": 0.6620894949106971, "percentage": 51.71, "elapsed_time": "12:00:06", "remaining_time": "11:12:24", "throughput": 658.27, "total_tokens": 28441360} {"current_steps": 20690, "total_steps": 40000, "loss": 0.8333, "lr": 2.3647811828524614e-05, "epoch": 0.6622495358811856, "percentage": 51.73, "elapsed_time": "12:00:08", "remaining_time": "11:12:06", "throughput": 658.4, "total_tokens": 28448160} {"current_steps": 20695, "total_steps": 40000, "loss": 0.6514, "lr": 2.363800882683529e-05, "epoch": 0.662409576851674, "percentage": 51.74, "elapsed_time": "12:00:09", "remaining_time": "11:11:47", "throughput": 658.53, "total_tokens": 28455152} {"current_steps": 20700, "total_steps": 40000, "loss": 0.5906, "lr": 2.3628206035182125e-05, "epoch": 0.6625696178221625, "percentage": 51.75, "elapsed_time": "12:00:11", "remaining_time": "11:11:29", "throughput": 658.66, "total_tokens": 28461760} {"current_steps": 20705, "total_steps": 40000, "loss": 0.8213, "lr": 2.361840345507683e-05, "epoch": 0.6627296587926509, "percentage": 51.76, "elapsed_time": "12:00:13", "remaining_time": "11:11:10", "throughput": 658.79, "total_tokens": 28468416} {"current_steps": 20710, "total_steps": 40000, "loss": 0.9582, "lr": 2.3608601088031073e-05, "epoch": 0.6628896997631394, "percentage": 51.78, "elapsed_time": "12:00:15", "remaining_time": "11:10:52", "throughput": 658.93, "total_tokens": 28475536} {"current_steps": 20715, "total_steps": 40000, "loss": 0.8175, "lr": 2.3598798935556516e-05, "epoch": 0.6630497407336278, "percentage": 51.79, "elapsed_time": "12:00:16", "remaining_time": "11:10:33", "throughput": 659.06, "total_tokens": 28482496} {"current_steps": 20720, "total_steps": 40000, "loss": 0.6457, "lr": 2.3588996999164784e-05, "epoch": 0.6632097817041163, "percentage": 51.8, "elapsed_time": "12:00:18", "remaining_time": "11:10:14", "throughput": 659.2, "total_tokens": 28489568} {"current_steps": 20725, "total_steps": 40000, "loss": 0.6804, "lr": 2.3579195280367434e-05, "epoch": 0.6633698226746046, "percentage": 51.81, "elapsed_time": "12:00:20", "remaining_time": "11:09:56", "throughput": 659.33, "total_tokens": 28496624} {"current_steps": 20730, "total_steps": 40000, "loss": 0.7577, "lr": 2.356939378067603e-05, "epoch": 0.6635298636450931, "percentage": 51.82, "elapsed_time": "12:00:22", "remaining_time": "11:09:37", "throughput": 659.47, "total_tokens": 28503696} {"current_steps": 20735, "total_steps": 40000, "loss": 0.8178, "lr": 2.3559592501602092e-05, "epoch": 0.6636899046155816, "percentage": 51.84, "elapsed_time": "12:00:23", "remaining_time": "11:09:19", "throughput": 659.6, "total_tokens": 28510480} {"current_steps": 20740, "total_steps": 40000, "loss": 0.595, "lr": 2.3549791444657076e-05, "epoch": 0.66384994558607, "percentage": 51.85, "elapsed_time": "12:00:25", "remaining_time": "11:09:00", "throughput": 659.73, "total_tokens": 28517136} {"current_steps": 20745, "total_steps": 40000, "loss": 0.7344, "lr": 2.353999061135246e-05, "epoch": 0.6640099865565585, "percentage": 51.86, "elapsed_time": "12:00:27", "remaining_time": "11:08:42", "throughput": 659.86, "total_tokens": 28524144} {"current_steps": 20750, "total_steps": 40000, "loss": 0.8677, "lr": 2.3530190003199626e-05, "epoch": 0.6641700275270469, "percentage": 51.88, "elapsed_time": "12:00:29", "remaining_time": "11:08:24", "throughput": 660.0, "total_tokens": 28530976} {"current_steps": 20755, "total_steps": 40000, "loss": 0.6325, "lr": 2.3520389621709965e-05, "epoch": 0.6643300684975354, "percentage": 51.89, "elapsed_time": "12:00:30", "remaining_time": "11:08:05", "throughput": 660.13, "total_tokens": 28537952} {"current_steps": 20760, "total_steps": 40000, "loss": 0.6637, "lr": 2.351058946839483e-05, "epoch": 0.6644901094680238, "percentage": 51.9, "elapsed_time": "12:00:32", "remaining_time": "11:07:47", "throughput": 660.26, "total_tokens": 28544816} {"current_steps": 20765, "total_steps": 40000, "loss": 0.8206, "lr": 2.350078954476551e-05, "epoch": 0.6646501504385123, "percentage": 51.91, "elapsed_time": "12:00:34", "remaining_time": "11:07:28", "throughput": 660.38, "total_tokens": 28551136} {"current_steps": 20770, "total_steps": 40000, "loss": 0.6519, "lr": 2.3490989852333272e-05, "epoch": 0.6648101914090007, "percentage": 51.92, "elapsed_time": "12:00:35", "remaining_time": "11:07:10", "throughput": 660.52, "total_tokens": 28558304} {"current_steps": 20775, "total_steps": 40000, "loss": 0.6693, "lr": 2.3481190392609377e-05, "epoch": 0.6649702323794892, "percentage": 51.94, "elapsed_time": "12:00:37", "remaining_time": "11:06:51", "throughput": 660.65, "total_tokens": 28564848} {"current_steps": 20780, "total_steps": 40000, "loss": 0.6255, "lr": 2.3471391167105e-05, "epoch": 0.6651302733499775, "percentage": 51.95, "elapsed_time": "12:00:39", "remaining_time": "11:06:33", "throughput": 660.79, "total_tokens": 28572032} {"current_steps": 20785, "total_steps": 40000, "loss": 0.8313, "lr": 2.3461592177331325e-05, "epoch": 0.665290314320466, "percentage": 51.96, "elapsed_time": "12:00:41", "remaining_time": "11:06:14", "throughput": 660.91, "total_tokens": 28578736} {"current_steps": 20790, "total_steps": 40000, "loss": 0.6484, "lr": 2.345179342479946e-05, "epoch": 0.6654503552909545, "percentage": 51.98, "elapsed_time": "12:00:42", "remaining_time": "11:05:56", "throughput": 661.04, "total_tokens": 28585456} {"current_steps": 20795, "total_steps": 40000, "loss": 0.7404, "lr": 2.3441994911020503e-05, "epoch": 0.6656103962614429, "percentage": 51.99, "elapsed_time": "12:00:44", "remaining_time": "11:05:38", "throughput": 661.18, "total_tokens": 28592432} {"current_steps": 20800, "total_steps": 40000, "loss": 0.9104, "lr": 2.3432196637505522e-05, "epoch": 0.6657704372319314, "percentage": 52.0, "elapsed_time": "12:00:46", "remaining_time": "11:05:19", "throughput": 661.3, "total_tokens": 28598784} {"current_steps": 20800, "total_steps": 40000, "eval_loss": 0.7430834770202637, "epoch": 0.6657704372319314, "percentage": 52.0, "elapsed_time": "12:06:34", "remaining_time": "11:10:41", "throughput": 656.01, "total_tokens": 28598784} {"current_steps": 20805, "total_steps": 40000, "loss": 0.8098, "lr": 2.3422398605765515e-05, "epoch": 0.6659304782024198, "percentage": 52.01, "elapsed_time": "12:06:38", "remaining_time": "11:10:24", "throughput": 656.12, "total_tokens": 28605568} {"current_steps": 20810, "total_steps": 40000, "loss": 0.9743, "lr": 2.3412600817311462e-05, "epoch": 0.6660905191729083, "percentage": 52.02, "elapsed_time": "12:06:39", "remaining_time": "11:10:05", "throughput": 656.27, "total_tokens": 28613184} {"current_steps": 20815, "total_steps": 40000, "loss": 0.7458, "lr": 2.3402803273654326e-05, "epoch": 0.6662505601433967, "percentage": 52.04, "elapsed_time": "12:06:41", "remaining_time": "11:09:47", "throughput": 656.39, "total_tokens": 28619872} {"current_steps": 20820, "total_steps": 40000, "loss": 0.5297, "lr": 2.3393005976304983e-05, "epoch": 0.6664106011138852, "percentage": 52.05, "elapsed_time": "12:06:43", "remaining_time": "11:09:28", "throughput": 656.53, "total_tokens": 28626960} {"current_steps": 20825, "total_steps": 40000, "loss": 0.7163, "lr": 2.338320892677432e-05, "epoch": 0.6665706420843736, "percentage": 52.06, "elapsed_time": "12:06:45", "remaining_time": "11:09:10", "throughput": 656.66, "total_tokens": 28633776} {"current_steps": 20830, "total_steps": 40000, "loss": 0.7826, "lr": 2.3373412126573155e-05, "epoch": 0.666730683054862, "percentage": 52.08, "elapsed_time": "12:06:46", "remaining_time": "11:08:51", "throughput": 656.79, "total_tokens": 28640576} {"current_steps": 20835, "total_steps": 40000, "loss": 0.745, "lr": 2.3363615577212285e-05, "epoch": 0.6668907240253504, "percentage": 52.09, "elapsed_time": "12:06:48", "remaining_time": "11:08:33", "throughput": 656.92, "total_tokens": 28647552} {"current_steps": 20840, "total_steps": 40000, "loss": 0.8165, "lr": 2.3353819280202455e-05, "epoch": 0.6670507649958389, "percentage": 52.1, "elapsed_time": "12:06:50", "remaining_time": "11:08:14", "throughput": 657.06, "total_tokens": 28654608} {"current_steps": 20845, "total_steps": 40000, "loss": 0.7215, "lr": 2.334402323705438e-05, "epoch": 0.6672108059663274, "percentage": 52.11, "elapsed_time": "12:06:52", "remaining_time": "11:07:56", "throughput": 657.19, "total_tokens": 28661520} {"current_steps": 20850, "total_steps": 40000, "loss": 0.6328, "lr": 2.3334227449278725e-05, "epoch": 0.6673708469368158, "percentage": 52.12, "elapsed_time": "12:06:53", "remaining_time": "11:07:37", "throughput": 657.32, "total_tokens": 28668304} {"current_steps": 20855, "total_steps": 40000, "loss": 0.9104, "lr": 2.3324431918386143e-05, "epoch": 0.6675308879073043, "percentage": 52.14, "elapsed_time": "12:06:55", "remaining_time": "11:07:19", "throughput": 657.46, "total_tokens": 28675328} {"current_steps": 20860, "total_steps": 40000, "loss": 0.9181, "lr": 2.3314636645887207e-05, "epoch": 0.6676909288777927, "percentage": 52.15, "elapsed_time": "12:06:57", "remaining_time": "11:07:00", "throughput": 657.59, "total_tokens": 28682432} {"current_steps": 20865, "total_steps": 40000, "loss": 0.7883, "lr": 2.3304841633292487e-05, "epoch": 0.6678509698482812, "percentage": 52.16, "elapsed_time": "12:06:59", "remaining_time": "11:06:42", "throughput": 657.72, "total_tokens": 28689008} {"current_steps": 20870, "total_steps": 40000, "loss": 0.6277, "lr": 2.329504688211248e-05, "epoch": 0.6680110108187696, "percentage": 52.18, "elapsed_time": "12:07:00", "remaining_time": "11:06:23", "throughput": 657.84, "total_tokens": 28695568} {"current_steps": 20875, "total_steps": 40000, "loss": 0.7047, "lr": 2.3285252393857677e-05, "epoch": 0.6681710517892581, "percentage": 52.19, "elapsed_time": "12:07:02", "remaining_time": "11:06:05", "throughput": 657.98, "total_tokens": 28702512} {"current_steps": 20880, "total_steps": 40000, "loss": 0.6852, "lr": 2.327545817003851e-05, "epoch": 0.6683310927597464, "percentage": 52.2, "elapsed_time": "12:07:04", "remaining_time": "11:05:47", "throughput": 658.1, "total_tokens": 28709168} {"current_steps": 20885, "total_steps": 40000, "loss": 0.809, "lr": 2.326566421216535e-05, "epoch": 0.6684911337302349, "percentage": 52.21, "elapsed_time": "12:07:05", "remaining_time": "11:05:28", "throughput": 658.23, "total_tokens": 28715888} {"current_steps": 20890, "total_steps": 40000, "loss": 0.6518, "lr": 2.3255870521748565e-05, "epoch": 0.6686511747007234, "percentage": 52.23, "elapsed_time": "12:07:07", "remaining_time": "11:05:10", "throughput": 658.36, "total_tokens": 28722672} {"current_steps": 20895, "total_steps": 40000, "loss": 0.6785, "lr": 2.3246077100298474e-05, "epoch": 0.6688112156712118, "percentage": 52.24, "elapsed_time": "12:07:09", "remaining_time": "11:04:51", "throughput": 658.49, "total_tokens": 28729456} {"current_steps": 20900, "total_steps": 40000, "loss": 0.7718, "lr": 2.3236283949325328e-05, "epoch": 0.6689712566417003, "percentage": 52.25, "elapsed_time": "12:07:11", "remaining_time": "11:04:33", "throughput": 658.61, "total_tokens": 28735904} {"current_steps": 20905, "total_steps": 40000, "loss": 0.7523, "lr": 2.3226491070339368e-05, "epoch": 0.6691312976121887, "percentage": 52.26, "elapsed_time": "12:07:12", "remaining_time": "11:04:15", "throughput": 658.75, "total_tokens": 28743024} {"current_steps": 20910, "total_steps": 40000, "loss": 0.5723, "lr": 2.3216698464850762e-05, "epoch": 0.6692913385826772, "percentage": 52.28, "elapsed_time": "12:07:14", "remaining_time": "11:03:56", "throughput": 658.88, "total_tokens": 28750112} {"current_steps": 20915, "total_steps": 40000, "loss": 0.7619, "lr": 2.320690613436967e-05, "epoch": 0.6694513795531656, "percentage": 52.29, "elapsed_time": "12:07:16", "remaining_time": "11:03:38", "throughput": 659.01, "total_tokens": 28756880} {"current_steps": 20920, "total_steps": 40000, "loss": 0.6753, "lr": 2.3197114080406192e-05, "epoch": 0.6696114205236541, "percentage": 52.3, "elapsed_time": "12:07:18", "remaining_time": "11:03:19", "throughput": 659.14, "total_tokens": 28763584} {"current_steps": 20925, "total_steps": 40000, "loss": 1.0951, "lr": 2.3187322304470365e-05, "epoch": 0.6697714614941425, "percentage": 52.31, "elapsed_time": "12:07:19", "remaining_time": "11:03:01", "throughput": 659.28, "total_tokens": 28770720} {"current_steps": 20930, "total_steps": 40000, "loss": 0.7597, "lr": 2.3177530808072222e-05, "epoch": 0.669931502464631, "percentage": 52.33, "elapsed_time": "12:07:21", "remaining_time": "11:02:43", "throughput": 659.41, "total_tokens": 28777648} {"current_steps": 20935, "total_steps": 40000, "loss": 0.762, "lr": 2.316773959272174e-05, "epoch": 0.6700915434351193, "percentage": 52.34, "elapsed_time": "12:07:23", "remaining_time": "11:02:24", "throughput": 659.54, "total_tokens": 28784576} {"current_steps": 20940, "total_steps": 40000, "loss": 0.7418, "lr": 2.3157948659928823e-05, "epoch": 0.6702515844056078, "percentage": 52.35, "elapsed_time": "12:07:25", "remaining_time": "11:02:06", "throughput": 659.67, "total_tokens": 28791376} {"current_steps": 20945, "total_steps": 40000, "loss": 0.5202, "lr": 2.3148158011203388e-05, "epoch": 0.6704116253760963, "percentage": 52.36, "elapsed_time": "12:07:26", "remaining_time": "11:01:48", "throughput": 659.8, "total_tokens": 28798144} {"current_steps": 20950, "total_steps": 40000, "loss": 0.904, "lr": 2.3138367648055253e-05, "epoch": 0.6705716663465847, "percentage": 52.38, "elapsed_time": "12:07:28", "remaining_time": "11:01:29", "throughput": 659.93, "total_tokens": 28805072} {"current_steps": 20955, "total_steps": 40000, "loss": 0.6441, "lr": 2.312857757199422e-05, "epoch": 0.6707317073170732, "percentage": 52.39, "elapsed_time": "12:07:30", "remaining_time": "11:01:11", "throughput": 660.07, "total_tokens": 28812064} {"current_steps": 20960, "total_steps": 40000, "loss": 0.8608, "lr": 2.3118787784530048e-05, "epoch": 0.6708917482875616, "percentage": 52.4, "elapsed_time": "12:07:31", "remaining_time": "11:00:53", "throughput": 660.2, "total_tokens": 28819040} {"current_steps": 20965, "total_steps": 40000, "loss": 0.7283, "lr": 2.310899828717243e-05, "epoch": 0.6710517892580501, "percentage": 52.41, "elapsed_time": "12:07:33", "remaining_time": "11:00:35", "throughput": 660.34, "total_tokens": 28826208} {"current_steps": 20970, "total_steps": 40000, "loss": 0.7952, "lr": 2.309920908143104e-05, "epoch": 0.6712118302285385, "percentage": 52.42, "elapsed_time": "12:07:35", "remaining_time": "11:00:16", "throughput": 660.47, "total_tokens": 28833216} {"current_steps": 20975, "total_steps": 40000, "loss": 0.8468, "lr": 2.308942016881551e-05, "epoch": 0.671371871199027, "percentage": 52.44, "elapsed_time": "12:07:37", "remaining_time": "10:59:58", "throughput": 660.6, "total_tokens": 28840112} {"current_steps": 20980, "total_steps": 40000, "loss": 0.8606, "lr": 2.307963155083539e-05, "epoch": 0.6715319121695154, "percentage": 52.45, "elapsed_time": "12:07:38", "remaining_time": "10:59:40", "throughput": 660.73, "total_tokens": 28846656} {"current_steps": 20985, "total_steps": 40000, "loss": 0.6108, "lr": 2.306984322900022e-05, "epoch": 0.6716919531400039, "percentage": 52.46, "elapsed_time": "12:07:40", "remaining_time": "10:59:21", "throughput": 660.87, "total_tokens": 28853872} {"current_steps": 20990, "total_steps": 40000, "loss": 0.5712, "lr": 2.3060055204819482e-05, "epoch": 0.6718519941104922, "percentage": 52.48, "elapsed_time": "12:07:42", "remaining_time": "10:59:03", "throughput": 661.0, "total_tokens": 28860816} {"current_steps": 20995, "total_steps": 40000, "loss": 0.554, "lr": 2.3050267479802604e-05, "epoch": 0.6720120350809807, "percentage": 52.49, "elapsed_time": "12:07:44", "remaining_time": "10:58:45", "throughput": 661.14, "total_tokens": 28868000} {"current_steps": 21000, "total_steps": 40000, "loss": 0.7189, "lr": 2.304048005545899e-05, "epoch": 0.6721720760514692, "percentage": 52.5, "elapsed_time": "12:07:45", "remaining_time": "10:58:27", "throughput": 661.27, "total_tokens": 28874800} {"current_steps": 21000, "total_steps": 40000, "eval_loss": 0.7426405549049377, "epoch": 0.6721720760514692, "percentage": 52.5, "elapsed_time": "12:13:33", "remaining_time": "11:03:41", "throughput": 656.05, "total_tokens": 28874800} {"current_steps": 21005, "total_steps": 40000, "loss": 0.6633, "lr": 2.3030692933297972e-05, "epoch": 0.6723321170219576, "percentage": 52.51, "elapsed_time": "12:13:36", "remaining_time": "11:03:24", "throughput": 656.16, "total_tokens": 28881904} {"current_steps": 21010, "total_steps": 40000, "loss": 0.7474, "lr": 2.3020906114828843e-05, "epoch": 0.6724921579924461, "percentage": 52.52, "elapsed_time": "12:13:38", "remaining_time": "11:03:06", "throughput": 656.29, "total_tokens": 28888784} {"current_steps": 21015, "total_steps": 40000, "loss": 0.5106, "lr": 2.301111960156088e-05, "epoch": 0.6726521989629345, "percentage": 52.54, "elapsed_time": "12:13:40", "remaining_time": "11:02:47", "throughput": 656.43, "total_tokens": 28896304} {"current_steps": 21020, "total_steps": 40000, "loss": 0.7771, "lr": 2.300133339500326e-05, "epoch": 0.672812239933423, "percentage": 52.55, "elapsed_time": "12:13:41", "remaining_time": "11:02:29", "throughput": 656.57, "total_tokens": 28903376} {"current_steps": 21025, "total_steps": 40000, "loss": 0.7286, "lr": 2.2991547496665148e-05, "epoch": 0.6729722809039114, "percentage": 52.56, "elapsed_time": "12:13:43", "remaining_time": "11:02:11", "throughput": 656.69, "total_tokens": 28909856} {"current_steps": 21030, "total_steps": 40000, "loss": 1.024, "lr": 2.298176190805565e-05, "epoch": 0.6731323218743999, "percentage": 52.58, "elapsed_time": "12:13:45", "remaining_time": "11:01:52", "throughput": 656.82, "total_tokens": 28916528} {"current_steps": 21035, "total_steps": 40000, "loss": 0.901, "lr": 2.2971976630683826e-05, "epoch": 0.6732923628448882, "percentage": 52.59, "elapsed_time": "12:13:47", "remaining_time": "11:01:34", "throughput": 656.95, "total_tokens": 28923536} {"current_steps": 21040, "total_steps": 40000, "loss": 0.7554, "lr": 2.29621916660587e-05, "epoch": 0.6734524038153767, "percentage": 52.6, "elapsed_time": "12:13:48", "remaining_time": "11:01:16", "throughput": 657.08, "total_tokens": 28930448} {"current_steps": 21045, "total_steps": 40000, "loss": 0.7272, "lr": 2.295240701568922e-05, "epoch": 0.6736124447858651, "percentage": 52.61, "elapsed_time": "12:13:50", "remaining_time": "11:00:57", "throughput": 657.21, "total_tokens": 28937296} {"current_steps": 21050, "total_steps": 40000, "loss": 0.6627, "lr": 2.2942622681084312e-05, "epoch": 0.6737724857563536, "percentage": 52.62, "elapsed_time": "12:13:52", "remaining_time": "11:00:39", "throughput": 657.34, "total_tokens": 28944336} {"current_steps": 21055, "total_steps": 40000, "loss": 0.6876, "lr": 2.293283866375284e-05, "epoch": 0.6739325267268421, "percentage": 52.64, "elapsed_time": "12:13:53", "remaining_time": "11:00:21", "throughput": 657.47, "total_tokens": 28950960} {"current_steps": 21060, "total_steps": 40000, "loss": 0.7818, "lr": 2.2923054965203627e-05, "epoch": 0.6740925676973305, "percentage": 52.65, "elapsed_time": "12:13:55", "remaining_time": "11:00:02", "throughput": 657.61, "total_tokens": 28958384} {"current_steps": 21065, "total_steps": 40000, "loss": 0.6659, "lr": 2.2913271586945443e-05, "epoch": 0.674252608667819, "percentage": 52.66, "elapsed_time": "12:13:57", "remaining_time": "10:59:44", "throughput": 657.73, "total_tokens": 28964896} {"current_steps": 21070, "total_steps": 40000, "loss": 0.767, "lr": 2.290348853048699e-05, "epoch": 0.6744126496383074, "percentage": 52.68, "elapsed_time": "12:13:59", "remaining_time": "10:59:26", "throughput": 657.87, "total_tokens": 28971952} {"current_steps": 21075, "total_steps": 40000, "loss": 0.8089, "lr": 2.2893705797336956e-05, "epoch": 0.6745726906087959, "percentage": 52.69, "elapsed_time": "12:14:00", "remaining_time": "10:59:07", "throughput": 658.0, "total_tokens": 28978912} {"current_steps": 21080, "total_steps": 40000, "loss": 0.8068, "lr": 2.288392338900397e-05, "epoch": 0.6747327315792843, "percentage": 52.7, "elapsed_time": "12:14:02", "remaining_time": "10:58:49", "throughput": 658.13, "total_tokens": 28985920} {"current_steps": 21085, "total_steps": 40000, "loss": 0.7156, "lr": 2.2874141306996576e-05, "epoch": 0.6748927725497728, "percentage": 52.71, "elapsed_time": "12:14:04", "remaining_time": "10:58:31", "throughput": 658.27, "total_tokens": 28993200} {"current_steps": 21090, "total_steps": 40000, "loss": 0.6158, "lr": 2.2864359552823312e-05, "epoch": 0.6750528135202611, "percentage": 52.73, "elapsed_time": "12:14:06", "remaining_time": "10:58:13", "throughput": 658.4, "total_tokens": 29000096} {"current_steps": 21095, "total_steps": 40000, "loss": 0.6829, "lr": 2.2854578127992648e-05, "epoch": 0.6752128544907496, "percentage": 52.74, "elapsed_time": "12:14:07", "remaining_time": "10:57:54", "throughput": 658.54, "total_tokens": 29007232} {"current_steps": 21100, "total_steps": 40000, "loss": 0.7016, "lr": 2.2844797034012988e-05, "epoch": 0.6753728954612381, "percentage": 52.75, "elapsed_time": "12:14:09", "remaining_time": "10:57:36", "throughput": 658.67, "total_tokens": 29013968} {"current_steps": 21105, "total_steps": 40000, "loss": 0.6798, "lr": 2.2835016272392722e-05, "epoch": 0.6755329364317265, "percentage": 52.76, "elapsed_time": "12:14:11", "remaining_time": "10:57:18", "throughput": 658.81, "total_tokens": 29021232} {"current_steps": 21110, "total_steps": 40000, "loss": 0.9797, "lr": 2.2825235844640142e-05, "epoch": 0.675692977402215, "percentage": 52.78, "elapsed_time": "12:14:13", "remaining_time": "10:57:00", "throughput": 658.93, "total_tokens": 29027744} {"current_steps": 21115, "total_steps": 40000, "loss": 0.7188, "lr": 2.2815455752263522e-05, "epoch": 0.6758530183727034, "percentage": 52.79, "elapsed_time": "12:14:14", "remaining_time": "10:56:42", "throughput": 659.06, "total_tokens": 29034880} {"current_steps": 21120, "total_steps": 40000, "loss": 0.85, "lr": 2.2805675996771092e-05, "epoch": 0.6760130593431919, "percentage": 52.8, "elapsed_time": "12:14:16", "remaining_time": "10:56:23", "throughput": 659.2, "total_tokens": 29041936} {"current_steps": 21125, "total_steps": 40000, "loss": 0.8886, "lr": 2.2795896579670987e-05, "epoch": 0.6761731003136803, "percentage": 52.81, "elapsed_time": "12:14:18", "remaining_time": "10:56:05", "throughput": 659.33, "total_tokens": 29048912} {"current_steps": 21130, "total_steps": 40000, "loss": 0.6122, "lr": 2.2786117502471337e-05, "epoch": 0.6763331412841688, "percentage": 52.83, "elapsed_time": "12:14:19", "remaining_time": "10:55:47", "throughput": 659.47, "total_tokens": 29056112} {"current_steps": 21135, "total_steps": 40000, "loss": 0.662, "lr": 2.2776338766680185e-05, "epoch": 0.6764931822546572, "percentage": 52.84, "elapsed_time": "12:14:21", "remaining_time": "10:55:29", "throughput": 659.59, "total_tokens": 29062816} {"current_steps": 21140, "total_steps": 40000, "loss": 1.0434, "lr": 2.2766560373805533e-05, "epoch": 0.6766532232251457, "percentage": 52.85, "elapsed_time": "12:14:23", "remaining_time": "10:55:11", "throughput": 659.72, "total_tokens": 29069664} {"current_steps": 21145, "total_steps": 40000, "loss": 0.6664, "lr": 2.2756782325355353e-05, "epoch": 0.676813264195634, "percentage": 52.86, "elapsed_time": "12:14:25", "remaining_time": "10:54:52", "throughput": 659.86, "total_tokens": 29076944} {"current_steps": 21150, "total_steps": 40000, "loss": 0.5828, "lr": 2.2747004622837514e-05, "epoch": 0.6769733051661225, "percentage": 52.88, "elapsed_time": "12:14:26", "remaining_time": "10:54:34", "throughput": 659.98, "total_tokens": 29083456} {"current_steps": 21155, "total_steps": 40000, "loss": 0.8362, "lr": 2.2737227267759878e-05, "epoch": 0.677133346136611, "percentage": 52.89, "elapsed_time": "12:14:28", "remaining_time": "10:54:16", "throughput": 660.11, "total_tokens": 29089952} {"current_steps": 21160, "total_steps": 40000, "loss": 0.9352, "lr": 2.272745026163024e-05, "epoch": 0.6772933871070994, "percentage": 52.9, "elapsed_time": "12:14:30", "remaining_time": "10:53:58", "throughput": 660.23, "total_tokens": 29096672} {"current_steps": 21165, "total_steps": 40000, "loss": 0.7611, "lr": 2.271767360595633e-05, "epoch": 0.6774534280775879, "percentage": 52.91, "elapsed_time": "12:14:32", "remaining_time": "10:53:40", "throughput": 660.35, "total_tokens": 29103184} {"current_steps": 21170, "total_steps": 40000, "loss": 0.7141, "lr": 2.270789730224583e-05, "epoch": 0.6776134690480763, "percentage": 52.92, "elapsed_time": "12:14:33", "remaining_time": "10:53:22", "throughput": 660.48, "total_tokens": 29109872} {"current_steps": 21175, "total_steps": 40000, "loss": 0.7275, "lr": 2.2698121352006367e-05, "epoch": 0.6777735100185648, "percentage": 52.94, "elapsed_time": "12:14:35", "remaining_time": "10:53:04", "throughput": 660.6, "total_tokens": 29116416} {"current_steps": 21180, "total_steps": 40000, "loss": 0.7978, "lr": 2.2688345756745517e-05, "epoch": 0.6779335509890532, "percentage": 52.95, "elapsed_time": "12:14:37", "remaining_time": "10:52:45", "throughput": 660.72, "total_tokens": 29122928} {"current_steps": 21185, "total_steps": 40000, "loss": 0.6879, "lr": 2.267857051797081e-05, "epoch": 0.6780935919595417, "percentage": 52.96, "elapsed_time": "12:14:39", "remaining_time": "10:52:27", "throughput": 660.86, "total_tokens": 29130160} {"current_steps": 21190, "total_steps": 40000, "loss": 0.6641, "lr": 2.2668795637189695e-05, "epoch": 0.67825363293003, "percentage": 52.98, "elapsed_time": "12:14:40", "remaining_time": "10:52:09", "throughput": 661.0, "total_tokens": 29137504} {"current_steps": 21195, "total_steps": 40000, "loss": 0.7803, "lr": 2.2659021115909586e-05, "epoch": 0.6784136739005185, "percentage": 52.99, "elapsed_time": "12:14:42", "remaining_time": "10:51:51", "throughput": 661.13, "total_tokens": 29144368} {"current_steps": 21200, "total_steps": 40000, "loss": 0.6754, "lr": 2.2649246955637847e-05, "epoch": 0.6785737148710069, "percentage": 53.0, "elapsed_time": "12:14:44", "remaining_time": "10:51:33", "throughput": 661.26, "total_tokens": 29151312} {"current_steps": 21200, "total_steps": 40000, "eval_loss": 0.7427748441696167, "epoch": 0.6785737148710069, "percentage": 53.0, "elapsed_time": "12:20:31", "remaining_time": "10:56:41", "throughput": 656.09, "total_tokens": 29151312} {"current_steps": 21205, "total_steps": 40000, "loss": 0.702, "lr": 2.2639473157881766e-05, "epoch": 0.6787337558414954, "percentage": 53.01, "elapsed_time": "12:20:35", "remaining_time": "10:56:25", "throughput": 656.19, "total_tokens": 29158000} {"current_steps": 21210, "total_steps": 40000, "loss": 0.9447, "lr": 2.2629699724148594e-05, "epoch": 0.6788937968119839, "percentage": 53.02, "elapsed_time": "12:20:36", "remaining_time": "10:56:06", "throughput": 656.32, "total_tokens": 29164800} {"current_steps": 21215, "total_steps": 40000, "loss": 0.8089, "lr": 2.26199266559455e-05, "epoch": 0.6790538377824723, "percentage": 53.04, "elapsed_time": "12:20:38", "remaining_time": "10:55:48", "throughput": 656.46, "total_tokens": 29172352} {"current_steps": 21220, "total_steps": 40000, "loss": 0.7352, "lr": 2.2610153954779625e-05, "epoch": 0.6792138787529608, "percentage": 53.05, "elapsed_time": "12:20:40", "remaining_time": "10:55:30", "throughput": 656.6, "total_tokens": 29179712} {"current_steps": 21225, "total_steps": 40000, "loss": 1.1539, "lr": 2.2600381622158056e-05, "epoch": 0.6793739197234492, "percentage": 53.06, "elapsed_time": "12:20:42", "remaining_time": "10:55:12", "throughput": 656.73, "total_tokens": 29186672} {"current_steps": 21230, "total_steps": 40000, "loss": 0.724, "lr": 2.2590609659587783e-05, "epoch": 0.6795339606939377, "percentage": 53.08, "elapsed_time": "12:20:43", "remaining_time": "10:54:53", "throughput": 656.87, "total_tokens": 29193632} {"current_steps": 21235, "total_steps": 40000, "loss": 0.7053, "lr": 2.2580838068575787e-05, "epoch": 0.6796940016644261, "percentage": 53.09, "elapsed_time": "12:20:45", "remaining_time": "10:54:35", "throughput": 656.99, "total_tokens": 29200512} {"current_steps": 21240, "total_steps": 40000, "loss": 0.5556, "lr": 2.257106685062896e-05, "epoch": 0.6798540426349146, "percentage": 53.1, "elapsed_time": "12:20:47", "remaining_time": "10:54:17", "throughput": 657.12, "total_tokens": 29207424} {"current_steps": 21245, "total_steps": 40000, "loss": 0.902, "lr": 2.256129600725415e-05, "epoch": 0.6800140836054029, "percentage": 53.11, "elapsed_time": "12:20:49", "remaining_time": "10:53:59", "throughput": 657.26, "total_tokens": 29214368} {"current_steps": 21250, "total_steps": 40000, "loss": 0.6227, "lr": 2.2551525539958145e-05, "epoch": 0.6801741245758914, "percentage": 53.12, "elapsed_time": "12:20:50", "remaining_time": "10:53:41", "throughput": 657.38, "total_tokens": 29221152} {"current_steps": 21255, "total_steps": 40000, "loss": 0.6756, "lr": 2.2541755450247663e-05, "epoch": 0.6803341655463798, "percentage": 53.14, "elapsed_time": "12:20:52", "remaining_time": "10:53:23", "throughput": 657.51, "total_tokens": 29228000} {"current_steps": 21260, "total_steps": 40000, "loss": 0.7779, "lr": 2.2531985739629382e-05, "epoch": 0.6804942065168683, "percentage": 53.15, "elapsed_time": "12:20:54", "remaining_time": "10:53:04", "throughput": 657.64, "total_tokens": 29234880} {"current_steps": 21265, "total_steps": 40000, "loss": 0.7724, "lr": 2.2522216409609924e-05, "epoch": 0.6806542474873568, "percentage": 53.16, "elapsed_time": "12:20:55", "remaining_time": "10:52:46", "throughput": 657.77, "total_tokens": 29241952} {"current_steps": 21270, "total_steps": 40000, "loss": 0.7111, "lr": 2.2512447461695826e-05, "epoch": 0.6808142884578452, "percentage": 53.17, "elapsed_time": "12:20:57", "remaining_time": "10:52:28", "throughput": 657.9, "total_tokens": 29248912} {"current_steps": 21275, "total_steps": 40000, "loss": 0.8003, "lr": 2.2502678897393593e-05, "epoch": 0.6809743294283337, "percentage": 53.19, "elapsed_time": "12:20:59", "remaining_time": "10:52:10", "throughput": 658.03, "total_tokens": 29255776} {"current_steps": 21280, "total_steps": 40000, "loss": 0.923, "lr": 2.2492910718209665e-05, "epoch": 0.6811343703988221, "percentage": 53.2, "elapsed_time": "12:21:01", "remaining_time": "10:51:52", "throughput": 658.16, "total_tokens": 29262672} {"current_steps": 21285, "total_steps": 40000, "loss": 0.7979, "lr": 2.2483142925650398e-05, "epoch": 0.6812944113693106, "percentage": 53.21, "elapsed_time": "12:21:02", "remaining_time": "10:51:34", "throughput": 658.29, "total_tokens": 29269424} {"current_steps": 21290, "total_steps": 40000, "loss": 0.6918, "lr": 2.247337552122213e-05, "epoch": 0.681454452339799, "percentage": 53.23, "elapsed_time": "12:21:04", "remaining_time": "10:51:16", "throughput": 658.41, "total_tokens": 29275808} {"current_steps": 21295, "total_steps": 40000, "loss": 0.6399, "lr": 2.24636085064311e-05, "epoch": 0.6816144933102875, "percentage": 53.24, "elapsed_time": "12:21:06", "remaining_time": "10:50:58", "throughput": 658.54, "total_tokens": 29282720} {"current_steps": 21300, "total_steps": 40000, "loss": 0.9384, "lr": 2.245384188278351e-05, "epoch": 0.6817745342807758, "percentage": 53.25, "elapsed_time": "12:21:08", "remaining_time": "10:50:40", "throughput": 658.66, "total_tokens": 29289360} {"current_steps": 21305, "total_steps": 40000, "loss": 0.6895, "lr": 2.2444075651785513e-05, "epoch": 0.6819345752512643, "percentage": 53.26, "elapsed_time": "12:21:09", "remaining_time": "10:50:22", "throughput": 658.78, "total_tokens": 29295824} {"current_steps": 21310, "total_steps": 40000, "loss": 0.8252, "lr": 2.243430981494316e-05, "epoch": 0.6820946162217527, "percentage": 53.27, "elapsed_time": "12:21:11", "remaining_time": "10:50:03", "throughput": 658.91, "total_tokens": 29302592} {"current_steps": 21315, "total_steps": 40000, "loss": 0.7848, "lr": 2.2424544373762475e-05, "epoch": 0.6822546571922412, "percentage": 53.29, "elapsed_time": "12:21:13", "remaining_time": "10:49:45", "throughput": 659.03, "total_tokens": 29309472} {"current_steps": 21320, "total_steps": 40000, "loss": 0.5841, "lr": 2.2414779329749418e-05, "epoch": 0.6824146981627297, "percentage": 53.3, "elapsed_time": "12:21:15", "remaining_time": "10:49:27", "throughput": 659.16, "total_tokens": 29316240} {"current_steps": 21325, "total_steps": 40000, "loss": 0.7133, "lr": 2.2405014684409873e-05, "epoch": 0.6825747391332181, "percentage": 53.31, "elapsed_time": "12:21:16", "remaining_time": "10:49:09", "throughput": 659.3, "total_tokens": 29323360} {"current_steps": 21330, "total_steps": 40000, "loss": 0.7365, "lr": 2.239525043924968e-05, "epoch": 0.6827347801037066, "percentage": 53.33, "elapsed_time": "12:21:18", "remaining_time": "10:48:51", "throughput": 659.42, "total_tokens": 29330096} {"current_steps": 21335, "total_steps": 40000, "loss": 0.579, "lr": 2.2385486595774592e-05, "epoch": 0.682894821074195, "percentage": 53.34, "elapsed_time": "12:21:20", "remaining_time": "10:48:33", "throughput": 659.55, "total_tokens": 29336928} {"current_steps": 21340, "total_steps": 40000, "loss": 0.9531, "lr": 2.237572315549033e-05, "epoch": 0.6830548620446835, "percentage": 53.35, "elapsed_time": "12:21:22", "remaining_time": "10:48:15", "throughput": 659.67, "total_tokens": 29343584} {"current_steps": 21345, "total_steps": 40000, "loss": 0.6177, "lr": 2.2365960119902545e-05, "epoch": 0.6832149030151718, "percentage": 53.36, "elapsed_time": "12:21:23", "remaining_time": "10:47:57", "throughput": 659.8, "total_tokens": 29350176} {"current_steps": 21350, "total_steps": 40000, "loss": 0.614, "lr": 2.2356197490516806e-05, "epoch": 0.6833749439856603, "percentage": 53.37, "elapsed_time": "12:21:25", "remaining_time": "10:47:39", "throughput": 659.92, "total_tokens": 29356912} {"current_steps": 21355, "total_steps": 40000, "loss": 0.4668, "lr": 2.234643526883863e-05, "epoch": 0.6835349849561487, "percentage": 53.39, "elapsed_time": "12:21:27", "remaining_time": "10:47:21", "throughput": 660.05, "total_tokens": 29363712} {"current_steps": 21360, "total_steps": 40000, "loss": 0.6247, "lr": 2.2336673456373497e-05, "epoch": 0.6836950259266372, "percentage": 53.4, "elapsed_time": "12:21:28", "remaining_time": "10:47:03", "throughput": 660.18, "total_tokens": 29370816} {"current_steps": 21365, "total_steps": 40000, "loss": 0.6583, "lr": 2.2326912054626772e-05, "epoch": 0.6838550668971257, "percentage": 53.41, "elapsed_time": "12:21:30", "remaining_time": "10:46:45", "throughput": 660.31, "total_tokens": 29377664} {"current_steps": 21370, "total_steps": 40000, "loss": 0.6469, "lr": 2.2317151065103813e-05, "epoch": 0.6840151078676141, "percentage": 53.42, "elapsed_time": "12:21:32", "remaining_time": "10:46:27", "throughput": 660.44, "total_tokens": 29384560} {"current_steps": 21375, "total_steps": 40000, "loss": 0.6882, "lr": 2.2307390489309865e-05, "epoch": 0.6841751488381026, "percentage": 53.44, "elapsed_time": "12:21:34", "remaining_time": "10:46:09", "throughput": 660.57, "total_tokens": 29391408} {"current_steps": 21380, "total_steps": 40000, "loss": 0.7283, "lr": 2.2297630328750146e-05, "epoch": 0.684335189808591, "percentage": 53.45, "elapsed_time": "12:21:35", "remaining_time": "10:45:51", "throughput": 660.7, "total_tokens": 29398544} {"current_steps": 21385, "total_steps": 40000, "loss": 0.5914, "lr": 2.228787058492979e-05, "epoch": 0.6844952307790795, "percentage": 53.46, "elapsed_time": "12:21:37", "remaining_time": "10:45:33", "throughput": 660.83, "total_tokens": 29405264} {"current_steps": 21390, "total_steps": 40000, "loss": 0.7515, "lr": 2.2278111259353875e-05, "epoch": 0.6846552717495679, "percentage": 53.47, "elapsed_time": "12:21:39", "remaining_time": "10:45:15", "throughput": 660.96, "total_tokens": 29412240} {"current_steps": 21395, "total_steps": 40000, "loss": 0.7355, "lr": 2.2268352353527395e-05, "epoch": 0.6848153127200564, "percentage": 53.49, "elapsed_time": "12:21:41", "remaining_time": "10:44:57", "throughput": 661.09, "total_tokens": 29419072} {"current_steps": 21400, "total_steps": 40000, "loss": 1.0405, "lr": 2.225859386895533e-05, "epoch": 0.6849753536905447, "percentage": 53.5, "elapsed_time": "12:21:42", "remaining_time": "10:44:40", "throughput": 661.21, "total_tokens": 29425936} {"current_steps": 21400, "total_steps": 40000, "eval_loss": 0.7422412037849426, "epoch": 0.6849753536905447, "percentage": 53.5, "elapsed_time": "12:27:31", "remaining_time": "10:49:42", "throughput": 656.08, "total_tokens": 29425936} {"current_steps": 21405, "total_steps": 40000, "loss": 0.6329, "lr": 2.2248835807142525e-05, "epoch": 0.6851353946610332, "percentage": 53.51, "elapsed_time": "12:27:36", "remaining_time": "10:49:27", "throughput": 656.17, "total_tokens": 29433248} {"current_steps": 21410, "total_steps": 40000, "loss": 0.8587, "lr": 2.2239078169593826e-05, "epoch": 0.6852954356315216, "percentage": 53.52, "elapsed_time": "12:27:37", "remaining_time": "10:49:09", "throughput": 656.3, "total_tokens": 29440336} {"current_steps": 21415, "total_steps": 40000, "loss": 0.8054, "lr": 2.222932095781396e-05, "epoch": 0.6854554766020101, "percentage": 53.54, "elapsed_time": "12:27:39", "remaining_time": "10:48:51", "throughput": 656.45, "total_tokens": 29447968} {"current_steps": 21420, "total_steps": 40000, "loss": 0.6574, "lr": 2.221956417330762e-05, "epoch": 0.6856155175724986, "percentage": 53.55, "elapsed_time": "12:27:41", "remaining_time": "10:48:33", "throughput": 656.57, "total_tokens": 29454800} {"current_steps": 21425, "total_steps": 40000, "loss": 0.6155, "lr": 2.2209807817579438e-05, "epoch": 0.685775558542987, "percentage": 53.56, "elapsed_time": "12:27:43", "remaining_time": "10:48:15", "throughput": 656.71, "total_tokens": 29462144} {"current_steps": 21430, "total_steps": 40000, "loss": 0.8009, "lr": 2.220005189213394e-05, "epoch": 0.6859355995134755, "percentage": 53.57, "elapsed_time": "12:27:44", "remaining_time": "10:47:57", "throughput": 656.83, "total_tokens": 29468816} {"current_steps": 21435, "total_steps": 40000, "loss": 0.6026, "lr": 2.2190296398475624e-05, "epoch": 0.6860956404839639, "percentage": 53.59, "elapsed_time": "12:27:46", "remaining_time": "10:47:39", "throughput": 656.96, "total_tokens": 29475792} {"current_steps": 21440, "total_steps": 40000, "loss": 0.6375, "lr": 2.2180541338108926e-05, "epoch": 0.6862556814544524, "percentage": 53.6, "elapsed_time": "12:27:48", "remaining_time": "10:47:21", "throughput": 657.09, "total_tokens": 29482512} {"current_steps": 21445, "total_steps": 40000, "loss": 0.747, "lr": 2.2170786712538176e-05, "epoch": 0.6864157224249408, "percentage": 53.61, "elapsed_time": "12:27:50", "remaining_time": "10:47:03", "throughput": 657.21, "total_tokens": 29489232} {"current_steps": 21450, "total_steps": 40000, "loss": 0.7238, "lr": 2.216103252326768e-05, "epoch": 0.6865757633954293, "percentage": 53.62, "elapsed_time": "12:27:51", "remaining_time": "10:46:45", "throughput": 657.34, "total_tokens": 29496288} {"current_steps": 21455, "total_steps": 40000, "loss": 0.8621, "lr": 2.2151278771801635e-05, "epoch": 0.6867358043659176, "percentage": 53.64, "elapsed_time": "12:27:53", "remaining_time": "10:46:27", "throughput": 657.47, "total_tokens": 29502992} {"current_steps": 21460, "total_steps": 40000, "loss": 0.5761, "lr": 2.21415254596442e-05, "epoch": 0.6868958453364061, "percentage": 53.65, "elapsed_time": "12:27:55", "remaining_time": "10:46:09", "throughput": 657.6, "total_tokens": 29510144} {"current_steps": 21465, "total_steps": 40000, "loss": 0.7872, "lr": 2.213177258829947e-05, "epoch": 0.6870558863068945, "percentage": 53.66, "elapsed_time": "12:27:57", "remaining_time": "10:45:51", "throughput": 657.73, "total_tokens": 29516976} {"current_steps": 21470, "total_steps": 40000, "loss": 0.7494, "lr": 2.2122020159271445e-05, "epoch": 0.687215927277383, "percentage": 53.67, "elapsed_time": "12:27:58", "remaining_time": "10:45:33", "throughput": 657.86, "total_tokens": 29524032} {"current_steps": 21475, "total_steps": 40000, "loss": 0.5109, "lr": 2.2112268174064075e-05, "epoch": 0.6873759682478715, "percentage": 53.69, "elapsed_time": "12:28:00", "remaining_time": "10:45:15", "throughput": 657.99, "total_tokens": 29530912} {"current_steps": 21480, "total_steps": 40000, "loss": 0.5324, "lr": 2.2102516634181253e-05, "epoch": 0.6875360092183599, "percentage": 53.7, "elapsed_time": "12:28:02", "remaining_time": "10:44:57", "throughput": 658.12, "total_tokens": 29537872} {"current_steps": 21485, "total_steps": 40000, "loss": 0.751, "lr": 2.209276554112677e-05, "epoch": 0.6876960501888484, "percentage": 53.71, "elapsed_time": "12:28:03", "remaining_time": "10:44:39", "throughput": 658.25, "total_tokens": 29544848} {"current_steps": 21490, "total_steps": 40000, "loss": 1.1239, "lr": 2.2083014896404384e-05, "epoch": 0.6878560911593368, "percentage": 53.73, "elapsed_time": "12:28:05", "remaining_time": "10:44:21", "throughput": 658.38, "total_tokens": 29551904} {"current_steps": 21495, "total_steps": 40000, "loss": 0.7589, "lr": 2.207326470151775e-05, "epoch": 0.6880161321298253, "percentage": 53.74, "elapsed_time": "12:28:07", "remaining_time": "10:44:03", "throughput": 658.5, "total_tokens": 29558512} {"current_steps": 21500, "total_steps": 40000, "loss": 0.7518, "lr": 2.2063514957970477e-05, "epoch": 0.6881761731003136, "percentage": 53.75, "elapsed_time": "12:28:09", "remaining_time": "10:43:45", "throughput": 658.63, "total_tokens": 29565232} {"current_steps": 21505, "total_steps": 40000, "loss": 1.0503, "lr": 2.205376566726611e-05, "epoch": 0.6883362140708021, "percentage": 53.76, "elapsed_time": "12:28:10", "remaining_time": "10:43:27", "throughput": 658.76, "total_tokens": 29572368} {"current_steps": 21510, "total_steps": 40000, "loss": 0.7652, "lr": 2.204401683090809e-05, "epoch": 0.6884962550412905, "percentage": 53.77, "elapsed_time": "12:28:12", "remaining_time": "10:43:09", "throughput": 658.89, "total_tokens": 29579152} {"current_steps": 21515, "total_steps": 40000, "loss": 0.8049, "lr": 2.203426845039982e-05, "epoch": 0.688656296011779, "percentage": 53.79, "elapsed_time": "12:28:14", "remaining_time": "10:42:51", "throughput": 659.01, "total_tokens": 29586032} {"current_steps": 21520, "total_steps": 40000, "loss": 0.7039, "lr": 2.202452052724464e-05, "epoch": 0.6888163369822674, "percentage": 53.8, "elapsed_time": "12:28:16", "remaining_time": "10:42:33", "throughput": 659.14, "total_tokens": 29592976} {"current_steps": 21525, "total_steps": 40000, "loss": 0.6911, "lr": 2.2014773062945777e-05, "epoch": 0.6889763779527559, "percentage": 53.81, "elapsed_time": "12:28:17", "remaining_time": "10:42:16", "throughput": 659.27, "total_tokens": 29599664} {"current_steps": 21530, "total_steps": 40000, "loss": 0.7346, "lr": 2.2005026059006427e-05, "epoch": 0.6891364189232444, "percentage": 53.83, "elapsed_time": "12:28:19", "remaining_time": "10:41:58", "throughput": 659.39, "total_tokens": 29606512} {"current_steps": 21535, "total_steps": 40000, "loss": 0.7409, "lr": 2.1995279516929695e-05, "epoch": 0.6892964598937328, "percentage": 53.84, "elapsed_time": "12:28:21", "remaining_time": "10:41:40", "throughput": 659.52, "total_tokens": 29613136} {"current_steps": 21540, "total_steps": 40000, "loss": 0.7695, "lr": 2.1985533438218613e-05, "epoch": 0.6894565008642213, "percentage": 53.85, "elapsed_time": "12:28:23", "remaining_time": "10:41:22", "throughput": 659.65, "total_tokens": 29620192} {"current_steps": 21545, "total_steps": 40000, "loss": 0.5264, "lr": 2.197578782437617e-05, "epoch": 0.6896165418347097, "percentage": 53.86, "elapsed_time": "12:28:24", "remaining_time": "10:41:04", "throughput": 659.77, "total_tokens": 29626960} {"current_steps": 21550, "total_steps": 40000, "loss": 0.893, "lr": 2.196604267690524e-05, "epoch": 0.6897765828051982, "percentage": 53.87, "elapsed_time": "12:28:26", "remaining_time": "10:40:46", "throughput": 659.89, "total_tokens": 29633440} {"current_steps": 21555, "total_steps": 40000, "loss": 0.8901, "lr": 2.195629799730865e-05, "epoch": 0.6899366237756865, "percentage": 53.89, "elapsed_time": "12:28:28", "remaining_time": "10:40:28", "throughput": 660.02, "total_tokens": 29640288} {"current_steps": 21560, "total_steps": 40000, "loss": 0.621, "lr": 2.1946553787089173e-05, "epoch": 0.690096664746175, "percentage": 53.9, "elapsed_time": "12:28:30", "remaining_time": "10:40:11", "throughput": 660.14, "total_tokens": 29646976} {"current_steps": 21565, "total_steps": 40000, "loss": 0.6479, "lr": 2.193681004774947e-05, "epoch": 0.6902567057166634, "percentage": 53.91, "elapsed_time": "12:28:31", "remaining_time": "10:39:53", "throughput": 660.27, "total_tokens": 29653904} {"current_steps": 21570, "total_steps": 40000, "loss": 0.8198, "lr": 2.1927066780792154e-05, "epoch": 0.6904167466871519, "percentage": 53.92, "elapsed_time": "12:28:33", "remaining_time": "10:39:35", "throughput": 660.41, "total_tokens": 29661136} {"current_steps": 21575, "total_steps": 40000, "loss": 0.6931, "lr": 2.191732398771975e-05, "epoch": 0.6905767876576403, "percentage": 53.94, "elapsed_time": "12:28:35", "remaining_time": "10:39:17", "throughput": 660.53, "total_tokens": 29668032} {"current_steps": 21580, "total_steps": 40000, "loss": 0.6982, "lr": 2.1907581670034725e-05, "epoch": 0.6907368286281288, "percentage": 53.95, "elapsed_time": "12:28:36", "remaining_time": "10:38:59", "throughput": 660.67, "total_tokens": 29675232} {"current_steps": 21585, "total_steps": 40000, "loss": 0.6754, "lr": 2.189783982923948e-05, "epoch": 0.6908968695986173, "percentage": 53.96, "elapsed_time": "12:28:38", "remaining_time": "10:38:41", "throughput": 660.8, "total_tokens": 29682160} {"current_steps": 21590, "total_steps": 40000, "loss": 0.7172, "lr": 2.1888098466836303e-05, "epoch": 0.6910569105691057, "percentage": 53.97, "elapsed_time": "12:28:40", "remaining_time": "10:38:24", "throughput": 660.92, "total_tokens": 29688976} {"current_steps": 21595, "total_steps": 40000, "loss": 0.6527, "lr": 2.1878357584327457e-05, "epoch": 0.6912169515395942, "percentage": 53.99, "elapsed_time": "12:28:42", "remaining_time": "10:38:06", "throughput": 661.05, "total_tokens": 29695808} {"current_steps": 21600, "total_steps": 40000, "loss": 0.8179, "lr": 2.1868617183215103e-05, "epoch": 0.6913769925100826, "percentage": 54.0, "elapsed_time": "12:28:43", "remaining_time": "10:37:48", "throughput": 661.18, "total_tokens": 29702784} {"current_steps": 21600, "total_steps": 40000, "eval_loss": 0.7416195273399353, "epoch": 0.6913769925100826, "percentage": 54.0, "elapsed_time": "12:34:31", "remaining_time": "10:42:44", "throughput": 656.1, "total_tokens": 29702784} {"current_steps": 21605, "total_steps": 40000, "loss": 0.6668, "lr": 2.1858877265001327e-05, "epoch": 0.691537033480571, "percentage": 54.01, "elapsed_time": "12:34:35", "remaining_time": "10:42:28", "throughput": 656.2, "total_tokens": 29709568} {"current_steps": 21610, "total_steps": 40000, "loss": 0.6653, "lr": 2.184913783118816e-05, "epoch": 0.6916970744510594, "percentage": 54.02, "elapsed_time": "12:34:36", "remaining_time": "10:42:10", "throughput": 656.32, "total_tokens": 29716304} {"current_steps": 21615, "total_steps": 40000, "loss": 0.6546, "lr": 2.1839398883277522e-05, "epoch": 0.6918571154215479, "percentage": 54.04, "elapsed_time": "12:34:38", "remaining_time": "10:41:52", "throughput": 656.45, "total_tokens": 29723104} {"current_steps": 21620, "total_steps": 40000, "loss": 0.7248, "lr": 2.182966042277129e-05, "epoch": 0.6920171563920363, "percentage": 54.05, "elapsed_time": "12:34:40", "remaining_time": "10:41:34", "throughput": 656.58, "total_tokens": 29730032} {"current_steps": 21625, "total_steps": 40000, "loss": 0.716, "lr": 2.181992245117128e-05, "epoch": 0.6921771973625248, "percentage": 54.06, "elapsed_time": "12:34:42", "remaining_time": "10:41:16", "throughput": 656.71, "total_tokens": 29737040} {"current_steps": 21630, "total_steps": 40000, "loss": 0.6502, "lr": 2.181018496997918e-05, "epoch": 0.6923372383330133, "percentage": 54.07, "elapsed_time": "12:34:43", "remaining_time": "10:40:58", "throughput": 656.84, "total_tokens": 29744080} {"current_steps": 21635, "total_steps": 40000, "loss": 0.5871, "lr": 2.1800447980696648e-05, "epoch": 0.6924972793035017, "percentage": 54.09, "elapsed_time": "12:34:45", "remaining_time": "10:40:40", "throughput": 656.96, "total_tokens": 29750768} {"current_steps": 21640, "total_steps": 40000, "loss": 0.7062, "lr": 2.1790711484825248e-05, "epoch": 0.6926573202739902, "percentage": 54.1, "elapsed_time": "12:34:47", "remaining_time": "10:40:22", "throughput": 657.09, "total_tokens": 29757744} {"current_steps": 21645, "total_steps": 40000, "loss": 0.7096, "lr": 2.178097548386646e-05, "epoch": 0.6928173612444786, "percentage": 54.11, "elapsed_time": "12:34:48", "remaining_time": "10:40:05", "throughput": 657.22, "total_tokens": 29764688} {"current_steps": 21650, "total_steps": 40000, "loss": 0.588, "lr": 2.1771239979321712e-05, "epoch": 0.6929774022149671, "percentage": 54.12, "elapsed_time": "12:34:50", "remaining_time": "10:39:47", "throughput": 657.34, "total_tokens": 29771536} {"current_steps": 21655, "total_steps": 40000, "loss": 0.7324, "lr": 2.1761504972692327e-05, "epoch": 0.6931374431854554, "percentage": 54.14, "elapsed_time": "12:34:52", "remaining_time": "10:39:29", "throughput": 657.47, "total_tokens": 29778512} {"current_steps": 21660, "total_steps": 40000, "loss": 0.5601, "lr": 2.1751770465479572e-05, "epoch": 0.6932974841559439, "percentage": 54.15, "elapsed_time": "12:34:54", "remaining_time": "10:39:11", "throughput": 657.6, "total_tokens": 29785552} {"current_steps": 21665, "total_steps": 40000, "loss": 0.7218, "lr": 2.174203645918464e-05, "epoch": 0.6934575251264323, "percentage": 54.16, "elapsed_time": "12:34:55", "remaining_time": "10:38:53", "throughput": 657.73, "total_tokens": 29792288} {"current_steps": 21670, "total_steps": 40000, "loss": 0.6008, "lr": 2.1732302955308624e-05, "epoch": 0.6936175660969208, "percentage": 54.17, "elapsed_time": "12:34:57", "remaining_time": "10:38:35", "throughput": 657.85, "total_tokens": 29799040} {"current_steps": 21675, "total_steps": 40000, "loss": 0.647, "lr": 2.172256995535255e-05, "epoch": 0.6937776070674092, "percentage": 54.19, "elapsed_time": "12:34:59", "remaining_time": "10:38:18", "throughput": 657.98, "total_tokens": 29806176} {"current_steps": 21680, "total_steps": 40000, "loss": 0.661, "lr": 2.171283746081739e-05, "epoch": 0.6939376480378977, "percentage": 54.2, "elapsed_time": "12:35:01", "remaining_time": "10:38:00", "throughput": 658.11, "total_tokens": 29813040} {"current_steps": 21685, "total_steps": 40000, "loss": 0.893, "lr": 2.1703105473203988e-05, "epoch": 0.6940976890083862, "percentage": 54.21, "elapsed_time": "12:35:02", "remaining_time": "10:37:42", "throughput": 658.23, "total_tokens": 29819728} {"current_steps": 21690, "total_steps": 40000, "loss": 0.7209, "lr": 2.1693373994013168e-05, "epoch": 0.6942577299788746, "percentage": 54.23, "elapsed_time": "12:35:04", "remaining_time": "10:37:24", "throughput": 658.36, "total_tokens": 29826752} {"current_steps": 21695, "total_steps": 40000, "loss": 0.6605, "lr": 2.168364302474562e-05, "epoch": 0.6944177709493631, "percentage": 54.24, "elapsed_time": "12:35:06", "remaining_time": "10:37:06", "throughput": 658.48, "total_tokens": 29833392} {"current_steps": 21700, "total_steps": 40000, "loss": 0.591, "lr": 2.167391256690199e-05, "epoch": 0.6945778119198515, "percentage": 54.25, "elapsed_time": "12:35:08", "remaining_time": "10:36:49", "throughput": 658.61, "total_tokens": 29840112} {"current_steps": 21705, "total_steps": 40000, "loss": 0.8327, "lr": 2.1664182621982855e-05, "epoch": 0.69473785289034, "percentage": 54.26, "elapsed_time": "12:35:09", "remaining_time": "10:36:31", "throughput": 658.73, "total_tokens": 29846848} {"current_steps": 21710, "total_steps": 40000, "loss": 0.795, "lr": 2.1654453191488673e-05, "epoch": 0.6948978938608283, "percentage": 54.27, "elapsed_time": "12:35:11", "remaining_time": "10:36:13", "throughput": 658.85, "total_tokens": 29853520} {"current_steps": 21715, "total_steps": 40000, "loss": 0.696, "lr": 2.1644724276919846e-05, "epoch": 0.6950579348313168, "percentage": 54.29, "elapsed_time": "12:35:13", "remaining_time": "10:35:55", "throughput": 658.97, "total_tokens": 29860176} {"current_steps": 21720, "total_steps": 40000, "loss": 0.7172, "lr": 2.1634995879776715e-05, "epoch": 0.6952179758018052, "percentage": 54.3, "elapsed_time": "12:35:14", "remaining_time": "10:35:38", "throughput": 659.09, "total_tokens": 29866816} {"current_steps": 21725, "total_steps": 40000, "loss": 0.8829, "lr": 2.162526800155949e-05, "epoch": 0.6953780167722937, "percentage": 54.31, "elapsed_time": "12:35:16", "remaining_time": "10:35:20", "throughput": 659.22, "total_tokens": 29873472} {"current_steps": 21730, "total_steps": 40000, "loss": 0.7583, "lr": 2.1615540643768363e-05, "epoch": 0.6955380577427821, "percentage": 54.33, "elapsed_time": "12:35:18", "remaining_time": "10:35:02", "throughput": 659.36, "total_tokens": 29881344} {"current_steps": 21735, "total_steps": 40000, "loss": 0.7574, "lr": 2.160581380790339e-05, "epoch": 0.6956980987132706, "percentage": 54.34, "elapsed_time": "12:35:20", "remaining_time": "10:34:44", "throughput": 659.5, "total_tokens": 29888592} {"current_steps": 21740, "total_steps": 40000, "loss": 0.7352, "lr": 2.1596087495464586e-05, "epoch": 0.6958581396837591, "percentage": 54.35, "elapsed_time": "12:35:21", "remaining_time": "10:34:27", "throughput": 659.64, "total_tokens": 29896000} {"current_steps": 21745, "total_steps": 40000, "loss": 0.6381, "lr": 2.1586361707951866e-05, "epoch": 0.6960181806542475, "percentage": 54.36, "elapsed_time": "12:35:23", "remaining_time": "10:34:09", "throughput": 659.77, "total_tokens": 29903248} {"current_steps": 21750, "total_steps": 40000, "loss": 0.9085, "lr": 2.157663644686507e-05, "epoch": 0.696178221624736, "percentage": 54.37, "elapsed_time": "12:35:25", "remaining_time": "10:33:51", "throughput": 659.9, "total_tokens": 29910048} {"current_steps": 21755, "total_steps": 40000, "loss": 0.6432, "lr": 2.156691171370396e-05, "epoch": 0.6963382625952244, "percentage": 54.39, "elapsed_time": "12:35:27", "remaining_time": "10:33:33", "throughput": 660.03, "total_tokens": 29917280} {"current_steps": 21760, "total_steps": 40000, "loss": 0.7542, "lr": 2.1557187509968195e-05, "epoch": 0.6964983035657129, "percentage": 54.4, "elapsed_time": "12:35:28", "remaining_time": "10:33:16", "throughput": 660.16, "total_tokens": 29924192} {"current_steps": 21765, "total_steps": 40000, "loss": 0.7776, "lr": 2.1547463837157382e-05, "epoch": 0.6966583445362012, "percentage": 54.41, "elapsed_time": "12:35:30", "remaining_time": "10:32:58", "throughput": 660.28, "total_tokens": 29930816} {"current_steps": 21770, "total_steps": 40000, "loss": 0.709, "lr": 2.1537740696771045e-05, "epoch": 0.6968183855066897, "percentage": 54.43, "elapsed_time": "12:35:32", "remaining_time": "10:32:40", "throughput": 660.41, "total_tokens": 29937824} {"current_steps": 21775, "total_steps": 40000, "loss": 0.7038, "lr": 2.1528018090308587e-05, "epoch": 0.6969784264771781, "percentage": 54.44, "elapsed_time": "12:35:34", "remaining_time": "10:32:23", "throughput": 660.54, "total_tokens": 29945120} {"current_steps": 21780, "total_steps": 40000, "loss": 0.9992, "lr": 2.151829601926938e-05, "epoch": 0.6971384674476666, "percentage": 54.45, "elapsed_time": "12:35:35", "remaining_time": "10:32:05", "throughput": 660.67, "total_tokens": 29951984} {"current_steps": 21785, "total_steps": 40000, "loss": 0.6563, "lr": 2.1508574485152684e-05, "epoch": 0.697298508418155, "percentage": 54.46, "elapsed_time": "12:35:37", "remaining_time": "10:31:47", "throughput": 660.79, "total_tokens": 29958720} {"current_steps": 21790, "total_steps": 40000, "loss": 0.8838, "lr": 2.1498853489457667e-05, "epoch": 0.6974585493886435, "percentage": 54.47, "elapsed_time": "12:35:39", "remaining_time": "10:31:30", "throughput": 660.92, "total_tokens": 29965472} {"current_steps": 21795, "total_steps": 40000, "loss": 0.5992, "lr": 2.1489133033683455e-05, "epoch": 0.697618590359132, "percentage": 54.49, "elapsed_time": "12:35:41", "remaining_time": "10:31:12", "throughput": 661.05, "total_tokens": 29972464} {"current_steps": 21800, "total_steps": 40000, "loss": 0.9606, "lr": 2.1479413119329038e-05, "epoch": 0.6977786313296204, "percentage": 54.5, "elapsed_time": "12:35:42", "remaining_time": "10:30:54", "throughput": 661.18, "total_tokens": 29979824} {"current_steps": 21800, "total_steps": 40000, "eval_loss": 0.7411177754402161, "epoch": 0.6977786313296204, "percentage": 54.5, "elapsed_time": "12:41:30", "remaining_time": "10:35:45", "throughput": 656.15, "total_tokens": 29979824} {"current_steps": 21805, "total_steps": 40000, "loss": 0.7615, "lr": 2.1469693747893355e-05, "epoch": 0.6979386723001089, "percentage": 54.51, "elapsed_time": "12:41:34", "remaining_time": "10:35:28", "throughput": 656.25, "total_tokens": 29986688} {"current_steps": 21810, "total_steps": 40000, "loss": 0.6662, "lr": 2.1459974920875274e-05, "epoch": 0.6980987132705972, "percentage": 54.52, "elapsed_time": "12:41:35", "remaining_time": "10:35:11", "throughput": 656.37, "total_tokens": 29993408} {"current_steps": 21815, "total_steps": 40000, "loss": 0.5265, "lr": 2.145025663977354e-05, "epoch": 0.6982587542410857, "percentage": 54.54, "elapsed_time": "12:41:37", "remaining_time": "10:34:53", "throughput": 656.5, "total_tokens": 30000272} {"current_steps": 21820, "total_steps": 40000, "loss": 0.8413, "lr": 2.1440538906086844e-05, "epoch": 0.6984187952115741, "percentage": 54.55, "elapsed_time": "12:41:39", "remaining_time": "10:34:35", "throughput": 656.61, "total_tokens": 30006704} {"current_steps": 21825, "total_steps": 40000, "loss": 0.6092, "lr": 2.1430821721313782e-05, "epoch": 0.6985788361820626, "percentage": 54.56, "elapsed_time": "12:41:40", "remaining_time": "10:34:17", "throughput": 656.74, "total_tokens": 30013680} {"current_steps": 21830, "total_steps": 40000, "loss": 0.7231, "lr": 2.142110508695286e-05, "epoch": 0.698738877152551, "percentage": 54.57, "elapsed_time": "12:41:42", "remaining_time": "10:34:00", "throughput": 656.88, "total_tokens": 30021008} {"current_steps": 21835, "total_steps": 40000, "loss": 0.7099, "lr": 2.1411389004502515e-05, "epoch": 0.6988989181230395, "percentage": 54.59, "elapsed_time": "12:41:44", "remaining_time": "10:33:42", "throughput": 657.0, "total_tokens": 30027936} {"current_steps": 21840, "total_steps": 40000, "loss": 0.8164, "lr": 2.140167347546107e-05, "epoch": 0.699058959093528, "percentage": 54.6, "elapsed_time": "12:41:46", "remaining_time": "10:33:24", "throughput": 657.13, "total_tokens": 30034704} {"current_steps": 21845, "total_steps": 40000, "loss": 0.8163, "lr": 2.1391958501326793e-05, "epoch": 0.6992190000640164, "percentage": 54.61, "elapsed_time": "12:41:47", "remaining_time": "10:33:07", "throughput": 657.25, "total_tokens": 30041728} {"current_steps": 21850, "total_steps": 40000, "loss": 0.5897, "lr": 2.1382244083597873e-05, "epoch": 0.6993790410345049, "percentage": 54.62, "elapsed_time": "12:41:49", "remaining_time": "10:32:49", "throughput": 657.37, "total_tokens": 30048160} {"current_steps": 21855, "total_steps": 40000, "loss": 0.5616, "lr": 2.137253022377237e-05, "epoch": 0.6995390820049933, "percentage": 54.64, "elapsed_time": "12:41:51", "remaining_time": "10:32:31", "throughput": 657.49, "total_tokens": 30054560} {"current_steps": 21860, "total_steps": 40000, "loss": 0.7018, "lr": 2.136281692334829e-05, "epoch": 0.6996991229754818, "percentage": 54.65, "elapsed_time": "12:41:53", "remaining_time": "10:32:13", "throughput": 657.63, "total_tokens": 30062160} {"current_steps": 21865, "total_steps": 40000, "loss": 0.7065, "lr": 2.135310418382356e-05, "epoch": 0.6998591639459701, "percentage": 54.66, "elapsed_time": "12:41:54", "remaining_time": "10:31:56", "throughput": 657.75, "total_tokens": 30069008} {"current_steps": 21870, "total_steps": 40000, "loss": 0.7876, "lr": 2.134339200669598e-05, "epoch": 0.7000192049164586, "percentage": 54.67, "elapsed_time": "12:41:56", "remaining_time": "10:31:38", "throughput": 657.88, "total_tokens": 30075856} {"current_steps": 21875, "total_steps": 40000, "loss": 0.7412, "lr": 2.133368039346331e-05, "epoch": 0.700179245886947, "percentage": 54.69, "elapsed_time": "12:41:58", "remaining_time": "10:31:20", "throughput": 658.01, "total_tokens": 30082976} {"current_steps": 21880, "total_steps": 40000, "loss": 0.658, "lr": 2.1323969345623195e-05, "epoch": 0.7003392868574355, "percentage": 54.7, "elapsed_time": "12:42:00", "remaining_time": "10:31:03", "throughput": 658.14, "total_tokens": 30090016} {"current_steps": 21885, "total_steps": 40000, "loss": 0.7065, "lr": 2.1314258864673207e-05, "epoch": 0.7004993278279239, "percentage": 54.71, "elapsed_time": "12:42:01", "remaining_time": "10:30:45", "throughput": 658.25, "total_tokens": 30096576} {"current_steps": 21890, "total_steps": 40000, "loss": 0.731, "lr": 2.130454895211082e-05, "epoch": 0.7006593687984124, "percentage": 54.73, "elapsed_time": "12:42:03", "remaining_time": "10:30:27", "throughput": 658.38, "total_tokens": 30103456} {"current_steps": 21895, "total_steps": 40000, "loss": 0.6699, "lr": 2.129483960943342e-05, "epoch": 0.7008194097689009, "percentage": 54.74, "elapsed_time": "12:42:05", "remaining_time": "10:30:10", "throughput": 658.51, "total_tokens": 30110384} {"current_steps": 21900, "total_steps": 40000, "loss": 0.8459, "lr": 2.128513083813831e-05, "epoch": 0.7009794507393893, "percentage": 54.75, "elapsed_time": "12:42:07", "remaining_time": "10:29:52", "throughput": 658.64, "total_tokens": 30117776} {"current_steps": 21905, "total_steps": 40000, "loss": 0.9385, "lr": 2.1275422639722724e-05, "epoch": 0.7011394917098778, "percentage": 54.76, "elapsed_time": "12:42:08", "remaining_time": "10:29:35", "throughput": 658.77, "total_tokens": 30124624} {"current_steps": 21910, "total_steps": 40000, "loss": 0.8826, "lr": 2.126571501568376e-05, "epoch": 0.7012995326803662, "percentage": 54.77, "elapsed_time": "12:42:10", "remaining_time": "10:29:17", "throughput": 658.9, "total_tokens": 30131872} {"current_steps": 21915, "total_steps": 40000, "loss": 0.7875, "lr": 2.1256007967518478e-05, "epoch": 0.7014595736508547, "percentage": 54.79, "elapsed_time": "12:42:12", "remaining_time": "10:28:59", "throughput": 659.03, "total_tokens": 30138736} {"current_steps": 21920, "total_steps": 40000, "loss": 0.8471, "lr": 2.124630149672381e-05, "epoch": 0.701619614621343, "percentage": 54.8, "elapsed_time": "12:42:13", "remaining_time": "10:28:42", "throughput": 659.16, "total_tokens": 30145840} {"current_steps": 21925, "total_steps": 40000, "loss": 0.7114, "lr": 2.1236595604796624e-05, "epoch": 0.7017796555918315, "percentage": 54.81, "elapsed_time": "12:42:15", "remaining_time": "10:28:24", "throughput": 659.28, "total_tokens": 30152672} {"current_steps": 21930, "total_steps": 40000, "loss": 0.7737, "lr": 2.1226890293233693e-05, "epoch": 0.7019396965623199, "percentage": 54.83, "elapsed_time": "12:42:17", "remaining_time": "10:28:06", "throughput": 659.4, "total_tokens": 30159136} {"current_steps": 21935, "total_steps": 40000, "loss": 0.8104, "lr": 2.1217185563531694e-05, "epoch": 0.7020997375328084, "percentage": 54.84, "elapsed_time": "12:42:19", "remaining_time": "10:27:49", "throughput": 659.51, "total_tokens": 30165344} {"current_steps": 21940, "total_steps": 40000, "loss": 0.8238, "lr": 2.120748141718721e-05, "epoch": 0.7022597785032968, "percentage": 54.85, "elapsed_time": "12:42:20", "remaining_time": "10:27:31", "throughput": 659.63, "total_tokens": 30172272} {"current_steps": 21945, "total_steps": 40000, "loss": 0.5938, "lr": 2.1197777855696765e-05, "epoch": 0.7024198194737853, "percentage": 54.86, "elapsed_time": "12:42:22", "remaining_time": "10:27:14", "throughput": 659.76, "total_tokens": 30179168} {"current_steps": 21950, "total_steps": 40000, "loss": 0.8498, "lr": 2.1188074880556746e-05, "epoch": 0.7025798604442738, "percentage": 54.87, "elapsed_time": "12:42:24", "remaining_time": "10:26:56", "throughput": 659.88, "total_tokens": 30185936} {"current_steps": 21955, "total_steps": 40000, "loss": 0.6351, "lr": 2.1178372493263495e-05, "epoch": 0.7027399014147622, "percentage": 54.89, "elapsed_time": "12:42:26", "remaining_time": "10:26:39", "throughput": 660.01, "total_tokens": 30192784} {"current_steps": 21960, "total_steps": 40000, "loss": 0.6932, "lr": 2.116867069531322e-05, "epoch": 0.7028999423852507, "percentage": 54.9, "elapsed_time": "12:42:27", "remaining_time": "10:26:21", "throughput": 660.14, "total_tokens": 30200000} {"current_steps": 21965, "total_steps": 40000, "loss": 0.7454, "lr": 2.1158969488202073e-05, "epoch": 0.703059983355739, "percentage": 54.91, "elapsed_time": "12:42:29", "remaining_time": "10:26:04", "throughput": 660.26, "total_tokens": 30206544} {"current_steps": 21970, "total_steps": 40000, "loss": 0.6908, "lr": 2.114926887342611e-05, "epoch": 0.7032200243262275, "percentage": 54.93, "elapsed_time": "12:42:31", "remaining_time": "10:25:46", "throughput": 660.38, "total_tokens": 30213328} {"current_steps": 21975, "total_steps": 40000, "loss": 0.8751, "lr": 2.113956885248127e-05, "epoch": 0.7033800652967159, "percentage": 54.94, "elapsed_time": "12:42:33", "remaining_time": "10:25:28", "throughput": 660.51, "total_tokens": 30220528} {"current_steps": 21980, "total_steps": 40000, "loss": 0.719, "lr": 2.112986942686342e-05, "epoch": 0.7035401062672044, "percentage": 54.95, "elapsed_time": "12:42:34", "remaining_time": "10:25:11", "throughput": 660.65, "total_tokens": 30228080} {"current_steps": 21985, "total_steps": 40000, "loss": 0.7394, "lr": 2.112017059806835e-05, "epoch": 0.7037001472376928, "percentage": 54.96, "elapsed_time": "12:42:36", "remaining_time": "10:24:53", "throughput": 660.78, "total_tokens": 30234848} {"current_steps": 21990, "total_steps": 40000, "loss": 0.7002, "lr": 2.1110472367591724e-05, "epoch": 0.7038601882081813, "percentage": 54.97, "elapsed_time": "12:42:38", "remaining_time": "10:24:36", "throughput": 660.9, "total_tokens": 30241840} {"current_steps": 21995, "total_steps": 40000, "loss": 0.7122, "lr": 2.1100774736929145e-05, "epoch": 0.7040202291786697, "percentage": 54.99, "elapsed_time": "12:42:40", "remaining_time": "10:24:18", "throughput": 661.03, "total_tokens": 30248752} {"current_steps": 22000, "total_steps": 40000, "loss": 0.7739, "lr": 2.10910777075761e-05, "epoch": 0.7041802701491582, "percentage": 55.0, "elapsed_time": "12:42:41", "remaining_time": "10:24:01", "throughput": 661.17, "total_tokens": 30256128} {"current_steps": 22000, "total_steps": 40000, "eval_loss": 0.7404069304466248, "epoch": 0.7041802701491582, "percentage": 55.0, "elapsed_time": "12:48:29", "remaining_time": "10:28:45", "throughput": 656.19, "total_tokens": 30256128} {"current_steps": 22005, "total_steps": 40000, "loss": 0.6461, "lr": 2.108138128102799e-05, "epoch": 0.7043403111196467, "percentage": 55.01, "elapsed_time": "12:48:32", "remaining_time": "10:28:29", "throughput": 656.28, "total_tokens": 30262960} {"current_steps": 22010, "total_steps": 40000, "loss": 0.7953, "lr": 2.107168545878014e-05, "epoch": 0.7045003520901351, "percentage": 55.02, "elapsed_time": "12:48:34", "remaining_time": "10:28:11", "throughput": 656.4, "total_tokens": 30269584} {"current_steps": 22015, "total_steps": 40000, "loss": 0.7276, "lr": 2.106199024232775e-05, "epoch": 0.7046603930606236, "percentage": 55.04, "elapsed_time": "12:48:36", "remaining_time": "10:27:54", "throughput": 656.53, "total_tokens": 30276624} {"current_steps": 22020, "total_steps": 40000, "loss": 0.7936, "lr": 2.105229563316595e-05, "epoch": 0.7048204340311119, "percentage": 55.05, "elapsed_time": "12:48:37", "remaining_time": "10:27:36", "throughput": 656.66, "total_tokens": 30283936} {"current_steps": 22025, "total_steps": 40000, "loss": 0.7713, "lr": 2.1042601632789784e-05, "epoch": 0.7049804750016004, "percentage": 55.06, "elapsed_time": "12:48:39", "remaining_time": "10:27:18", "throughput": 656.8, "total_tokens": 30291440} {"current_steps": 22030, "total_steps": 40000, "loss": 0.6614, "lr": 2.103290824269417e-05, "epoch": 0.7051405159720888, "percentage": 55.07, "elapsed_time": "12:48:41", "remaining_time": "10:27:01", "throughput": 656.93, "total_tokens": 30298224} {"current_steps": 22035, "total_steps": 40000, "loss": 0.7886, "lr": 2.1023215464373965e-05, "epoch": 0.7053005569425773, "percentage": 55.09, "elapsed_time": "12:48:42", "remaining_time": "10:26:43", "throughput": 657.04, "total_tokens": 30304848} {"current_steps": 22040, "total_steps": 40000, "loss": 0.6697, "lr": 2.1013523299323908e-05, "epoch": 0.7054605979130657, "percentage": 55.1, "elapsed_time": "12:48:44", "remaining_time": "10:26:26", "throughput": 657.15, "total_tokens": 30311040} {"current_steps": 22045, "total_steps": 40000, "loss": 0.7264, "lr": 2.1003831749038654e-05, "epoch": 0.7056206388835542, "percentage": 55.11, "elapsed_time": "12:48:46", "remaining_time": "10:26:08", "throughput": 657.28, "total_tokens": 30317984} {"current_steps": 22050, "total_steps": 40000, "loss": 0.8108, "lr": 2.099414081501277e-05, "epoch": 0.7057806798540426, "percentage": 55.12, "elapsed_time": "12:48:48", "remaining_time": "10:25:51", "throughput": 657.4, "total_tokens": 30324512} {"current_steps": 22055, "total_steps": 40000, "loss": 0.6447, "lr": 2.09844504987407e-05, "epoch": 0.7059407208245311, "percentage": 55.14, "elapsed_time": "12:48:49", "remaining_time": "10:25:33", "throughput": 657.53, "total_tokens": 30331648} {"current_steps": 22060, "total_steps": 40000, "loss": 0.5869, "lr": 2.097476080171683e-05, "epoch": 0.7061007617950196, "percentage": 55.15, "elapsed_time": "12:48:51", "remaining_time": "10:25:15", "throughput": 657.65, "total_tokens": 30338688} {"current_steps": 22065, "total_steps": 40000, "loss": 0.6651, "lr": 2.0965071725435436e-05, "epoch": 0.706260802765508, "percentage": 55.16, "elapsed_time": "12:48:53", "remaining_time": "10:24:58", "throughput": 657.77, "total_tokens": 30345216} {"current_steps": 22070, "total_steps": 40000, "loss": 0.7729, "lr": 2.0955383271390684e-05, "epoch": 0.7064208437359965, "percentage": 55.17, "elapsed_time": "12:48:55", "remaining_time": "10:24:40", "throughput": 657.9, "total_tokens": 30352480} {"current_steps": 22075, "total_steps": 40000, "loss": 0.7312, "lr": 2.094569544107666e-05, "epoch": 0.7065808847064848, "percentage": 55.19, "elapsed_time": "12:48:56", "remaining_time": "10:24:23", "throughput": 658.02, "total_tokens": 30359152} {"current_steps": 22080, "total_steps": 40000, "loss": 0.8555, "lr": 2.093600823598735e-05, "epoch": 0.7067409256769733, "percentage": 55.2, "elapsed_time": "12:48:58", "remaining_time": "10:24:05", "throughput": 658.15, "total_tokens": 30365984} {"current_steps": 22085, "total_steps": 40000, "loss": 0.9098, "lr": 2.092632165761663e-05, "epoch": 0.7069009666474617, "percentage": 55.21, "elapsed_time": "12:49:00", "remaining_time": "10:23:48", "throughput": 658.27, "total_tokens": 30372912} {"current_steps": 22090, "total_steps": 40000, "loss": 0.7278, "lr": 2.091663570745832e-05, "epoch": 0.7070610076179502, "percentage": 55.23, "elapsed_time": "12:49:02", "remaining_time": "10:23:30", "throughput": 658.41, "total_tokens": 30380528} {"current_steps": 22095, "total_steps": 40000, "loss": 0.7156, "lr": 2.0906950387006086e-05, "epoch": 0.7072210485884386, "percentage": 55.24, "elapsed_time": "12:49:03", "remaining_time": "10:23:13", "throughput": 658.54, "total_tokens": 30387376} {"current_steps": 22100, "total_steps": 40000, "loss": 0.5853, "lr": 2.0897265697753543e-05, "epoch": 0.7073810895589271, "percentage": 55.25, "elapsed_time": "12:49:05", "remaining_time": "10:22:55", "throughput": 658.66, "total_tokens": 30394240} {"current_steps": 22105, "total_steps": 40000, "loss": 0.601, "lr": 2.088758164119419e-05, "epoch": 0.7075411305294156, "percentage": 55.26, "elapsed_time": "12:49:07", "remaining_time": "10:22:38", "throughput": 658.78, "total_tokens": 30400784} {"current_steps": 22110, "total_steps": 40000, "loss": 0.4607, "lr": 2.0877898218821428e-05, "epoch": 0.707701171499904, "percentage": 55.27, "elapsed_time": "12:49:09", "remaining_time": "10:22:20", "throughput": 658.9, "total_tokens": 30407584} {"current_steps": 22115, "total_steps": 40000, "loss": 0.6842, "lr": 2.0868215432128565e-05, "epoch": 0.7078612124703925, "percentage": 55.29, "elapsed_time": "12:49:10", "remaining_time": "10:22:03", "throughput": 659.02, "total_tokens": 30414176} {"current_steps": 22120, "total_steps": 40000, "loss": 0.6319, "lr": 2.0858533282608796e-05, "epoch": 0.7080212534408808, "percentage": 55.3, "elapsed_time": "12:49:12", "remaining_time": "10:21:45", "throughput": 659.14, "total_tokens": 30420880} {"current_steps": 22125, "total_steps": 40000, "loss": 0.646, "lr": 2.084885177175524e-05, "epoch": 0.7081812944113693, "percentage": 55.31, "elapsed_time": "12:49:14", "remaining_time": "10:21:28", "throughput": 659.26, "total_tokens": 30427616} {"current_steps": 22130, "total_steps": 40000, "loss": 0.6467, "lr": 2.0839170901060917e-05, "epoch": 0.7083413353818577, "percentage": 55.33, "elapsed_time": "12:49:15", "remaining_time": "10:21:11", "throughput": 659.39, "total_tokens": 30434576} {"current_steps": 22135, "total_steps": 40000, "loss": 0.7061, "lr": 2.082949067201872e-05, "epoch": 0.7085013763523462, "percentage": 55.34, "elapsed_time": "12:49:17", "remaining_time": "10:20:53", "throughput": 659.51, "total_tokens": 30441312} {"current_steps": 22140, "total_steps": 40000, "loss": 0.6867, "lr": 2.0819811086121475e-05, "epoch": 0.7086614173228346, "percentage": 55.35, "elapsed_time": "12:49:19", "remaining_time": "10:20:36", "throughput": 659.63, "total_tokens": 30448000} {"current_steps": 22145, "total_steps": 40000, "loss": 0.6692, "lr": 2.08101321448619e-05, "epoch": 0.7088214582933231, "percentage": 55.36, "elapsed_time": "12:49:21", "remaining_time": "10:20:18", "throughput": 659.75, "total_tokens": 30454672} {"current_steps": 22150, "total_steps": 40000, "loss": 0.9696, "lr": 2.080045384973259e-05, "epoch": 0.7089814992638115, "percentage": 55.38, "elapsed_time": "12:49:22", "remaining_time": "10:20:01", "throughput": 659.87, "total_tokens": 30461296} {"current_steps": 22155, "total_steps": 40000, "loss": 0.7733, "lr": 2.0790776202226082e-05, "epoch": 0.7091415402343, "percentage": 55.39, "elapsed_time": "12:49:24", "remaining_time": "10:19:43", "throughput": 659.99, "total_tokens": 30468144} {"current_steps": 22160, "total_steps": 40000, "loss": 0.7557, "lr": 2.078109920383477e-05, "epoch": 0.7093015812047885, "percentage": 55.4, "elapsed_time": "12:49:26", "remaining_time": "10:19:26", "throughput": 660.11, "total_tokens": 30474784} {"current_steps": 22165, "total_steps": 40000, "loss": 0.7195, "lr": 2.0771422856050978e-05, "epoch": 0.7094616221752769, "percentage": 55.41, "elapsed_time": "12:49:28", "remaining_time": "10:19:09", "throughput": 660.24, "total_tokens": 30481920} {"current_steps": 22170, "total_steps": 40000, "loss": 0.557, "lr": 2.076174716036693e-05, "epoch": 0.7096216631457654, "percentage": 55.43, "elapsed_time": "12:49:29", "remaining_time": "10:18:51", "throughput": 660.35, "total_tokens": 30488416} {"current_steps": 22175, "total_steps": 40000, "loss": 0.6587, "lr": 2.075207211827472e-05, "epoch": 0.7097817041162537, "percentage": 55.44, "elapsed_time": "12:49:31", "remaining_time": "10:18:34", "throughput": 660.47, "total_tokens": 30495072} {"current_steps": 22180, "total_steps": 40000, "loss": 0.71, "lr": 2.074239773126638e-05, "epoch": 0.7099417450867422, "percentage": 55.45, "elapsed_time": "12:49:33", "remaining_time": "10:18:16", "throughput": 660.6, "total_tokens": 30502064} {"current_steps": 22185, "total_steps": 40000, "loss": 0.6927, "lr": 2.073272400083382e-05, "epoch": 0.7101017860572306, "percentage": 55.46, "elapsed_time": "12:49:35", "remaining_time": "10:17:59", "throughput": 660.72, "total_tokens": 30508672} {"current_steps": 22190, "total_steps": 40000, "loss": 0.8944, "lr": 2.072305092846883e-05, "epoch": 0.7102618270277191, "percentage": 55.47, "elapsed_time": "12:49:36", "remaining_time": "10:17:42", "throughput": 660.83, "total_tokens": 30515136} {"current_steps": 22195, "total_steps": 40000, "loss": 0.9201, "lr": 2.0713378515663152e-05, "epoch": 0.7104218679982075, "percentage": 55.49, "elapsed_time": "12:49:38", "remaining_time": "10:17:24", "throughput": 660.95, "total_tokens": 30521744} {"current_steps": 22200, "total_steps": 40000, "loss": 0.6248, "lr": 2.070370676390836e-05, "epoch": 0.710581908968696, "percentage": 55.5, "elapsed_time": "12:49:40", "remaining_time": "10:17:07", "throughput": 661.06, "total_tokens": 30528032} {"current_steps": 22200, "total_steps": 40000, "eval_loss": 0.7403197288513184, "epoch": 0.710581908968696, "percentage": 55.5, "elapsed_time": "12:55:28", "remaining_time": "10:21:46", "throughput": 656.12, "total_tokens": 30528032} {"current_steps": 22205, "total_steps": 40000, "loss": 0.5762, "lr": 2.0694035674695974e-05, "epoch": 0.7107419499391844, "percentage": 55.51, "elapsed_time": "12:55:31", "remaining_time": "10:21:30", "throughput": 656.22, "total_tokens": 30535056} {"current_steps": 22210, "total_steps": 40000, "loss": 0.6223, "lr": 2.0684365249517416e-05, "epoch": 0.7109019909096729, "percentage": 55.53, "elapsed_time": "12:55:33", "remaining_time": "10:21:13", "throughput": 656.33, "total_tokens": 30541520} {"current_steps": 22215, "total_steps": 40000, "loss": 0.6353, "lr": 2.067469548986396e-05, "epoch": 0.7110620318801614, "percentage": 55.54, "elapsed_time": "12:55:35", "remaining_time": "10:20:55", "throughput": 656.45, "total_tokens": 30548336} {"current_steps": 22220, "total_steps": 40000, "loss": 0.7441, "lr": 2.066502639722681e-05, "epoch": 0.7112220728506498, "percentage": 55.55, "elapsed_time": "12:55:37", "remaining_time": "10:20:38", "throughput": 656.57, "total_tokens": 30555152} {"current_steps": 22225, "total_steps": 40000, "loss": 0.9963, "lr": 2.065535797309708e-05, "epoch": 0.7113821138211383, "percentage": 55.56, "elapsed_time": "12:55:38", "remaining_time": "10:20:20", "throughput": 656.7, "total_tokens": 30562256} {"current_steps": 22230, "total_steps": 40000, "loss": 0.5935, "lr": 2.0645690218965736e-05, "epoch": 0.7115421547916266, "percentage": 55.57, "elapsed_time": "12:55:40", "remaining_time": "10:20:03", "throughput": 656.83, "total_tokens": 30569232} {"current_steps": 22235, "total_steps": 40000, "loss": 0.9009, "lr": 2.063602313632369e-05, "epoch": 0.7117021957621151, "percentage": 55.59, "elapsed_time": "12:55:42", "remaining_time": "10:19:45", "throughput": 656.95, "total_tokens": 30575904} {"current_steps": 22240, "total_steps": 40000, "loss": 0.6456, "lr": 2.0626356726661704e-05, "epoch": 0.7118622367326035, "percentage": 55.6, "elapsed_time": "12:55:44", "remaining_time": "10:19:28", "throughput": 657.08, "total_tokens": 30583312} {"current_steps": 22245, "total_steps": 40000, "loss": 0.7123, "lr": 2.0616690991470477e-05, "epoch": 0.712022277703092, "percentage": 55.61, "elapsed_time": "12:55:45", "remaining_time": "10:19:10", "throughput": 657.2, "total_tokens": 30589904} {"current_steps": 22250, "total_steps": 40000, "loss": 0.7736, "lr": 2.0607025932240595e-05, "epoch": 0.7121823186735804, "percentage": 55.62, "elapsed_time": "12:55:47", "remaining_time": "10:18:53", "throughput": 657.31, "total_tokens": 30596288} {"current_steps": 22255, "total_steps": 40000, "loss": 0.7021, "lr": 2.059736155046251e-05, "epoch": 0.7123423596440689, "percentage": 55.64, "elapsed_time": "12:55:49", "remaining_time": "10:18:36", "throughput": 657.44, "total_tokens": 30603248} {"current_steps": 22260, "total_steps": 40000, "loss": 0.6922, "lr": 2.0587697847626603e-05, "epoch": 0.7125024006145573, "percentage": 55.65, "elapsed_time": "12:55:51", "remaining_time": "10:18:18", "throughput": 657.55, "total_tokens": 30609904} {"current_steps": 22265, "total_steps": 40000, "loss": 0.6477, "lr": 2.057803482522314e-05, "epoch": 0.7126624415850458, "percentage": 55.66, "elapsed_time": "12:55:52", "remaining_time": "10:18:01", "throughput": 657.68, "total_tokens": 30616784} {"current_steps": 22270, "total_steps": 40000, "loss": 0.7317, "lr": 2.056837248474227e-05, "epoch": 0.7128224825555343, "percentage": 55.67, "elapsed_time": "12:55:54", "remaining_time": "10:17:43", "throughput": 657.81, "total_tokens": 30624176} {"current_steps": 22275, "total_steps": 40000, "loss": 0.8326, "lr": 2.0558710827674064e-05, "epoch": 0.7129825235260226, "percentage": 55.69, "elapsed_time": "12:55:56", "remaining_time": "10:17:26", "throughput": 657.93, "total_tokens": 30630864} {"current_steps": 22280, "total_steps": 40000, "loss": 0.7814, "lr": 2.054904985550845e-05, "epoch": 0.7131425644965111, "percentage": 55.7, "elapsed_time": "12:55:58", "remaining_time": "10:17:09", "throughput": 658.05, "total_tokens": 30637616} {"current_steps": 22285, "total_steps": 40000, "loss": 0.7508, "lr": 2.0539389569735287e-05, "epoch": 0.7133026054669995, "percentage": 55.71, "elapsed_time": "12:55:59", "remaining_time": "10:16:51", "throughput": 658.17, "total_tokens": 30644256} {"current_steps": 22290, "total_steps": 40000, "loss": 1.0196, "lr": 2.052972997184431e-05, "epoch": 0.713462646437488, "percentage": 55.73, "elapsed_time": "12:56:01", "remaining_time": "10:16:34", "throughput": 658.28, "total_tokens": 30650752} {"current_steps": 22295, "total_steps": 40000, "loss": 0.7736, "lr": 2.0520071063325146e-05, "epoch": 0.7136226874079764, "percentage": 55.74, "elapsed_time": "12:56:03", "remaining_time": "10:16:17", "throughput": 658.4, "total_tokens": 30657424} {"current_steps": 22300, "total_steps": 40000, "loss": 0.6331, "lr": 2.051041284566732e-05, "epoch": 0.7137827283784649, "percentage": 55.75, "elapsed_time": "12:56:05", "remaining_time": "10:15:59", "throughput": 658.52, "total_tokens": 30664192} {"current_steps": 22305, "total_steps": 40000, "loss": 0.7943, "lr": 2.050075532036026e-05, "epoch": 0.7139427693489533, "percentage": 55.76, "elapsed_time": "12:56:06", "remaining_time": "10:15:42", "throughput": 658.64, "total_tokens": 30670832} {"current_steps": 22310, "total_steps": 40000, "loss": 0.5776, "lr": 2.0491098488893264e-05, "epoch": 0.7141028103194418, "percentage": 55.77, "elapsed_time": "12:56:08", "remaining_time": "10:15:24", "throughput": 658.78, "total_tokens": 30678208} {"current_steps": 22315, "total_steps": 40000, "loss": 0.874, "lr": 2.0481442352755546e-05, "epoch": 0.7142628512899302, "percentage": 55.79, "elapsed_time": "12:56:10", "remaining_time": "10:15:07", "throughput": 658.9, "total_tokens": 30684976} {"current_steps": 22320, "total_steps": 40000, "loss": 0.7501, "lr": 2.0471786913436198e-05, "epoch": 0.7144228922604187, "percentage": 55.8, "elapsed_time": "12:56:11", "remaining_time": "10:14:50", "throughput": 659.02, "total_tokens": 30691952} {"current_steps": 22325, "total_steps": 40000, "loss": 0.6104, "lr": 2.0462132172424218e-05, "epoch": 0.7145829332309072, "percentage": 55.81, "elapsed_time": "12:56:13", "remaining_time": "10:14:33", "throughput": 659.15, "total_tokens": 30698912} {"current_steps": 22330, "total_steps": 40000, "loss": 0.624, "lr": 2.0452478131208484e-05, "epoch": 0.7147429742013955, "percentage": 55.83, "elapsed_time": "12:56:15", "remaining_time": "10:14:15", "throughput": 659.27, "total_tokens": 30705616} {"current_steps": 22335, "total_steps": 40000, "loss": 0.8611, "lr": 2.0442824791277765e-05, "epoch": 0.714903015171884, "percentage": 55.84, "elapsed_time": "12:56:17", "remaining_time": "10:13:58", "throughput": 659.38, "total_tokens": 30712272} {"current_steps": 22340, "total_steps": 40000, "loss": 0.7669, "lr": 2.0433172154120727e-05, "epoch": 0.7150630561423724, "percentage": 55.85, "elapsed_time": "12:56:18", "remaining_time": "10:13:41", "throughput": 659.52, "total_tokens": 30719632} {"current_steps": 22345, "total_steps": 40000, "loss": 0.658, "lr": 2.0423520221225947e-05, "epoch": 0.7152230971128609, "percentage": 55.86, "elapsed_time": "12:56:20", "remaining_time": "10:13:23", "throughput": 659.64, "total_tokens": 30726368} {"current_steps": 22350, "total_steps": 40000, "loss": 0.665, "lr": 2.0413868994081848e-05, "epoch": 0.7153831380833493, "percentage": 55.88, "elapsed_time": "12:56:22", "remaining_time": "10:13:06", "throughput": 659.76, "total_tokens": 30733392} {"current_steps": 22355, "total_steps": 40000, "loss": 0.746, "lr": 2.0404218474176795e-05, "epoch": 0.7155431790538378, "percentage": 55.89, "elapsed_time": "12:56:24", "remaining_time": "10:12:49", "throughput": 659.9, "total_tokens": 30740656} {"current_steps": 22360, "total_steps": 40000, "loss": 0.7467, "lr": 2.0394568662999002e-05, "epoch": 0.7157032200243262, "percentage": 55.9, "elapsed_time": "12:56:25", "remaining_time": "10:12:31", "throughput": 660.01, "total_tokens": 30747232} {"current_steps": 22365, "total_steps": 40000, "loss": 0.7188, "lr": 2.0384919562036593e-05, "epoch": 0.7158632609948147, "percentage": 55.91, "elapsed_time": "12:56:27", "remaining_time": "10:12:14", "throughput": 660.14, "total_tokens": 30754416} {"current_steps": 22370, "total_steps": 40000, "loss": 0.7707, "lr": 2.0375271172777593e-05, "epoch": 0.7160233019653032, "percentage": 55.93, "elapsed_time": "12:56:29", "remaining_time": "10:11:57", "throughput": 660.28, "total_tokens": 30761872} {"current_steps": 22375, "total_steps": 40000, "loss": 0.6778, "lr": 2.0365623496709885e-05, "epoch": 0.7161833429357916, "percentage": 55.94, "elapsed_time": "12:56:31", "remaining_time": "10:11:40", "throughput": 660.4, "total_tokens": 30768496} {"current_steps": 22380, "total_steps": 40000, "loss": 0.7898, "lr": 2.0355976535321283e-05, "epoch": 0.71634338390628, "percentage": 55.95, "elapsed_time": "12:56:32", "remaining_time": "10:11:22", "throughput": 660.52, "total_tokens": 30775616} {"current_steps": 22385, "total_steps": 40000, "loss": 0.6217, "lr": 2.034633029009945e-05, "epoch": 0.7165034248767684, "percentage": 55.96, "elapsed_time": "12:56:34", "remaining_time": "10:11:05", "throughput": 660.65, "total_tokens": 30782464} {"current_steps": 22390, "total_steps": 40000, "loss": 0.7929, "lr": 2.0336684762531972e-05, "epoch": 0.7166634658472569, "percentage": 55.97, "elapsed_time": "12:56:36", "remaining_time": "10:10:48", "throughput": 660.78, "total_tokens": 30789872} {"current_steps": 22395, "total_steps": 40000, "loss": 0.7722, "lr": 2.032703995410631e-05, "epoch": 0.7168235068177453, "percentage": 55.99, "elapsed_time": "12:56:38", "remaining_time": "10:10:31", "throughput": 660.91, "total_tokens": 30797072} {"current_steps": 22400, "total_steps": 40000, "loss": 0.7647, "lr": 2.031739586630981e-05, "epoch": 0.7169835477882338, "percentage": 56.0, "elapsed_time": "12:56:39", "remaining_time": "10:10:14", "throughput": 661.03, "total_tokens": 30803904} {"current_steps": 22400, "total_steps": 40000, "eval_loss": 0.7409636378288269, "epoch": 0.7169835477882338, "percentage": 56.0, "elapsed_time": "13:02:28", "remaining_time": "10:14:47", "throughput": 656.13, "total_tokens": 30803904} {"current_steps": 22405, "total_steps": 40000, "loss": 0.7273, "lr": 2.0307752500629707e-05, "epoch": 0.7171435887587222, "percentage": 56.01, "elapsed_time": "13:02:31", "remaining_time": "10:14:31", "throughput": 656.23, "total_tokens": 30810976} {"current_steps": 22410, "total_steps": 40000, "loss": 0.9042, "lr": 2.0298109858553144e-05, "epoch": 0.7173036297292107, "percentage": 56.03, "elapsed_time": "13:02:33", "remaining_time": "10:14:14", "throughput": 656.35, "total_tokens": 30817920} {"current_steps": 22415, "total_steps": 40000, "loss": 0.8847, "lr": 2.028846794156712e-05, "epoch": 0.7174636706996991, "percentage": 56.04, "elapsed_time": "13:02:34", "remaining_time": "10:13:57", "throughput": 656.49, "total_tokens": 30825328} {"current_steps": 22420, "total_steps": 40000, "loss": 0.7275, "lr": 2.027882675115856e-05, "epoch": 0.7176237116701876, "percentage": 56.05, "elapsed_time": "13:02:36", "remaining_time": "10:13:39", "throughput": 656.62, "total_tokens": 30832576} {"current_steps": 22425, "total_steps": 40000, "loss": 0.8189, "lr": 2.026918628881423e-05, "epoch": 0.7177837526406761, "percentage": 56.06, "elapsed_time": "13:02:38", "remaining_time": "10:13:22", "throughput": 656.74, "total_tokens": 30839648} {"current_steps": 22430, "total_steps": 40000, "loss": 0.7184, "lr": 2.0259546556020833e-05, "epoch": 0.7179437936111644, "percentage": 56.07, "elapsed_time": "13:02:40", "remaining_time": "10:13:05", "throughput": 656.86, "total_tokens": 30846336} {"current_steps": 22435, "total_steps": 40000, "loss": 0.7741, "lr": 2.024990755426493e-05, "epoch": 0.7181038345816529, "percentage": 56.09, "elapsed_time": "13:02:41", "remaining_time": "10:12:47", "throughput": 656.99, "total_tokens": 30853312} {"current_steps": 22440, "total_steps": 40000, "loss": 0.6425, "lr": 2.0240269285032975e-05, "epoch": 0.7182638755521413, "percentage": 56.1, "elapsed_time": "13:02:43", "remaining_time": "10:12:30", "throughput": 657.11, "total_tokens": 30860128} {"current_steps": 22445, "total_steps": 40000, "loss": 0.7833, "lr": 2.0230631749811306e-05, "epoch": 0.7184239165226298, "percentage": 56.11, "elapsed_time": "13:02:45", "remaining_time": "10:12:13", "throughput": 657.23, "total_tokens": 30867232} {"current_steps": 22450, "total_steps": 40000, "loss": 0.6656, "lr": 2.0220994950086162e-05, "epoch": 0.7185839574931182, "percentage": 56.12, "elapsed_time": "13:02:47", "remaining_time": "10:11:55", "throughput": 657.35, "total_tokens": 30874000} {"current_steps": 22455, "total_steps": 40000, "loss": 0.8172, "lr": 2.021135888734365e-05, "epoch": 0.7187439984636067, "percentage": 56.14, "elapsed_time": "13:02:48", "remaining_time": "10:11:38", "throughput": 657.48, "total_tokens": 30881008} {"current_steps": 22460, "total_steps": 40000, "loss": 0.6774, "lr": 2.0201723563069783e-05, "epoch": 0.7189040394340951, "percentage": 56.15, "elapsed_time": "13:02:50", "remaining_time": "10:11:21", "throughput": 657.6, "total_tokens": 30887648} {"current_steps": 22465, "total_steps": 40000, "loss": 0.698, "lr": 2.0192088978750433e-05, "epoch": 0.7190640804045836, "percentage": 56.16, "elapsed_time": "13:02:52", "remaining_time": "10:11:04", "throughput": 657.71, "total_tokens": 30894112} {"current_steps": 22470, "total_steps": 40000, "loss": 0.6364, "lr": 2.0182455135871385e-05, "epoch": 0.719224121375072, "percentage": 56.17, "elapsed_time": "13:02:54", "remaining_time": "10:10:46", "throughput": 657.83, "total_tokens": 30900816} {"current_steps": 22475, "total_steps": 40000, "loss": 0.6601, "lr": 2.0172822035918305e-05, "epoch": 0.7193841623455605, "percentage": 56.19, "elapsed_time": "13:02:55", "remaining_time": "10:10:29", "throughput": 657.95, "total_tokens": 30907712} {"current_steps": 22480, "total_steps": 40000, "loss": 0.7126, "lr": 2.016318968037671e-05, "epoch": 0.719544203316049, "percentage": 56.2, "elapsed_time": "13:02:57", "remaining_time": "10:10:12", "throughput": 658.07, "total_tokens": 30914432} {"current_steps": 22485, "total_steps": 40000, "loss": 0.8369, "lr": 2.015355807073206e-05, "epoch": 0.7197042442865373, "percentage": 56.21, "elapsed_time": "13:02:59", "remaining_time": "10:09:55", "throughput": 658.2, "total_tokens": 30921504} {"current_steps": 22490, "total_steps": 40000, "loss": 0.543, "lr": 2.0143927208469664e-05, "epoch": 0.7198642852570258, "percentage": 56.23, "elapsed_time": "13:03:00", "remaining_time": "10:09:37", "throughput": 658.31, "total_tokens": 30928032} {"current_steps": 22495, "total_steps": 40000, "loss": 0.6862, "lr": 2.0134297095074708e-05, "epoch": 0.7200243262275142, "percentage": 56.24, "elapsed_time": "13:03:02", "remaining_time": "10:09:20", "throughput": 658.43, "total_tokens": 30934944} {"current_steps": 22500, "total_steps": 40000, "loss": 0.8244, "lr": 2.0124667732032297e-05, "epoch": 0.7201843671980027, "percentage": 56.25, "elapsed_time": "13:03:04", "remaining_time": "10:09:03", "throughput": 658.56, "total_tokens": 30942000} {"current_steps": 22505, "total_steps": 40000, "loss": 0.8605, "lr": 2.011503912082738e-05, "epoch": 0.7203444081684911, "percentage": 56.26, "elapsed_time": "13:03:06", "remaining_time": "10:08:46", "throughput": 658.68, "total_tokens": 30948656} {"current_steps": 22510, "total_steps": 40000, "loss": 0.8818, "lr": 2.0105411262944823e-05, "epoch": 0.7205044491389796, "percentage": 56.27, "elapsed_time": "13:03:07", "remaining_time": "10:08:29", "throughput": 658.8, "total_tokens": 30955504} {"current_steps": 22515, "total_steps": 40000, "loss": 0.5738, "lr": 2.0095784159869366e-05, "epoch": 0.720664490109468, "percentage": 56.29, "elapsed_time": "13:03:09", "remaining_time": "10:08:11", "throughput": 658.91, "total_tokens": 30962000} {"current_steps": 22520, "total_steps": 40000, "loss": 0.7328, "lr": 2.0086157813085608e-05, "epoch": 0.7208245310799565, "percentage": 56.3, "elapsed_time": "13:03:11", "remaining_time": "10:07:54", "throughput": 659.03, "total_tokens": 30968848} {"current_steps": 22525, "total_steps": 40000, "loss": 0.7269, "lr": 2.0076532224078068e-05, "epoch": 0.7209845720504449, "percentage": 56.31, "elapsed_time": "13:03:13", "remaining_time": "10:07:37", "throughput": 659.15, "total_tokens": 30975584} {"current_steps": 22530, "total_steps": 40000, "loss": 0.9117, "lr": 2.0066907394331142e-05, "epoch": 0.7211446130209334, "percentage": 56.33, "elapsed_time": "13:03:14", "remaining_time": "10:07:20", "throughput": 659.27, "total_tokens": 30982464} {"current_steps": 22535, "total_steps": 40000, "loss": 0.7009, "lr": 2.0057283325329077e-05, "epoch": 0.7213046539914219, "percentage": 56.34, "elapsed_time": "13:03:16", "remaining_time": "10:07:03", "throughput": 659.39, "total_tokens": 30989120} {"current_steps": 22540, "total_steps": 40000, "loss": 0.7365, "lr": 2.0047660018556047e-05, "epoch": 0.7214646949619102, "percentage": 56.35, "elapsed_time": "13:03:18", "remaining_time": "10:06:45", "throughput": 659.5, "total_tokens": 30995632} {"current_steps": 22545, "total_steps": 40000, "loss": 0.7894, "lr": 2.0038037475496075e-05, "epoch": 0.7216247359323987, "percentage": 56.36, "elapsed_time": "13:03:20", "remaining_time": "10:06:28", "throughput": 659.63, "total_tokens": 31002448} {"current_steps": 22550, "total_steps": 40000, "loss": 0.6983, "lr": 2.0028415697633073e-05, "epoch": 0.7217847769028871, "percentage": 56.38, "elapsed_time": "13:03:21", "remaining_time": "10:06:11", "throughput": 659.74, "total_tokens": 31008880} {"current_steps": 22555, "total_steps": 40000, "loss": 0.8776, "lr": 2.0018794686450858e-05, "epoch": 0.7219448178733756, "percentage": 56.39, "elapsed_time": "13:03:23", "remaining_time": "10:05:54", "throughput": 659.85, "total_tokens": 31015232} {"current_steps": 22560, "total_steps": 40000, "loss": 0.6859, "lr": 2.0009174443433088e-05, "epoch": 0.722104858843864, "percentage": 56.4, "elapsed_time": "13:03:25", "remaining_time": "10:05:37", "throughput": 659.97, "total_tokens": 31022128} {"current_steps": 22565, "total_steps": 40000, "loss": 0.6498, "lr": 1.999955497006334e-05, "epoch": 0.7222648998143525, "percentage": 56.41, "elapsed_time": "13:03:27", "remaining_time": "10:05:20", "throughput": 660.1, "total_tokens": 31029120} {"current_steps": 22570, "total_steps": 40000, "loss": 0.6917, "lr": 1.9989936267825067e-05, "epoch": 0.7224249407848409, "percentage": 56.43, "elapsed_time": "13:03:28", "remaining_time": "10:05:03", "throughput": 660.22, "total_tokens": 31035984} {"current_steps": 22575, "total_steps": 40000, "loss": 0.8132, "lr": 1.9980318338201572e-05, "epoch": 0.7225849817553294, "percentage": 56.44, "elapsed_time": "13:03:30", "remaining_time": "10:04:46", "throughput": 660.35, "total_tokens": 31043344} {"current_steps": 22580, "total_steps": 40000, "loss": 0.6883, "lr": 1.997070118267607e-05, "epoch": 0.7227450227258178, "percentage": 56.45, "elapsed_time": "13:03:32", "remaining_time": "10:04:28", "throughput": 660.47, "total_tokens": 31050096} {"current_steps": 22585, "total_steps": 40000, "loss": 0.6272, "lr": 1.9961084802731654e-05, "epoch": 0.7229050636963062, "percentage": 56.46, "elapsed_time": "13:03:33", "remaining_time": "10:04:11", "throughput": 660.59, "total_tokens": 31057040} {"current_steps": 22590, "total_steps": 40000, "loss": 0.6716, "lr": 1.9951469199851273e-05, "epoch": 0.7230651046667947, "percentage": 56.47, "elapsed_time": "13:03:35", "remaining_time": "10:03:54", "throughput": 660.71, "total_tokens": 31063744} {"current_steps": 22595, "total_steps": 40000, "loss": 0.6436, "lr": 1.99418543755178e-05, "epoch": 0.7232251456372831, "percentage": 56.49, "elapsed_time": "13:03:37", "remaining_time": "10:03:37", "throughput": 660.83, "total_tokens": 31070688} {"current_steps": 22600, "total_steps": 40000, "loss": 0.828, "lr": 1.9932240331213936e-05, "epoch": 0.7233851866077716, "percentage": 56.5, "elapsed_time": "13:03:39", "remaining_time": "10:03:20", "throughput": 660.96, "total_tokens": 31077632} {"current_steps": 22600, "total_steps": 40000, "eval_loss": 0.7405943274497986, "epoch": 0.7233851866077716, "percentage": 56.5, "elapsed_time": "13:09:27", "remaining_time": "10:07:48", "throughput": 656.1, "total_tokens": 31077632} {"current_steps": 22605, "total_steps": 40000, "loss": 0.7729, "lr": 1.9922627068422297e-05, "epoch": 0.72354522757826, "percentage": 56.51, "elapsed_time": "13:09:30", "remaining_time": "10:07:32", "throughput": 656.2, "total_tokens": 31084560} {"current_steps": 22610, "total_steps": 40000, "loss": 0.5833, "lr": 1.991301458862538e-05, "epoch": 0.7237052685487485, "percentage": 56.53, "elapsed_time": "13:09:32", "remaining_time": "10:07:15", "throughput": 656.33, "total_tokens": 31091792} {"current_steps": 22615, "total_steps": 40000, "loss": 0.7392, "lr": 1.9903402893305536e-05, "epoch": 0.7238653095192369, "percentage": 56.54, "elapsed_time": "13:09:33", "remaining_time": "10:06:58", "throughput": 656.45, "total_tokens": 31098464} {"current_steps": 22620, "total_steps": 40000, "loss": 0.7579, "lr": 1.9893791983945016e-05, "epoch": 0.7240253504897254, "percentage": 56.55, "elapsed_time": "13:09:35", "remaining_time": "10:06:40", "throughput": 656.57, "total_tokens": 31105584} {"current_steps": 22625, "total_steps": 40000, "loss": 1.144, "lr": 1.988418186202594e-05, "epoch": 0.7241853914602138, "percentage": 56.56, "elapsed_time": "13:09:37", "remaining_time": "10:06:23", "throughput": 656.69, "total_tokens": 31112320} {"current_steps": 22630, "total_steps": 40000, "loss": 0.7772, "lr": 1.98745725290303e-05, "epoch": 0.7243454324307023, "percentage": 56.57, "elapsed_time": "13:09:39", "remaining_time": "10:06:06", "throughput": 656.81, "total_tokens": 31119184} {"current_steps": 22635, "total_steps": 40000, "loss": 0.5628, "lr": 1.986496398644e-05, "epoch": 0.7245054734011908, "percentage": 56.59, "elapsed_time": "13:09:40", "remaining_time": "10:05:49", "throughput": 656.94, "total_tokens": 31126192} {"current_steps": 22640, "total_steps": 40000, "loss": 0.7639, "lr": 1.9855356235736777e-05, "epoch": 0.7246655143716791, "percentage": 56.6, "elapsed_time": "13:09:42", "remaining_time": "10:05:32", "throughput": 657.07, "total_tokens": 31133552} {"current_steps": 22645, "total_steps": 40000, "loss": 0.661, "lr": 1.9845749278402277e-05, "epoch": 0.7248255553421676, "percentage": 56.61, "elapsed_time": "13:09:44", "remaining_time": "10:05:15", "throughput": 657.18, "total_tokens": 31140112} {"current_steps": 22650, "total_steps": 40000, "loss": 0.7518, "lr": 1.9836143115918006e-05, "epoch": 0.724985596312656, "percentage": 56.62, "elapsed_time": "13:09:46", "remaining_time": "10:04:57", "throughput": 657.31, "total_tokens": 31147136} {"current_steps": 22655, "total_steps": 40000, "loss": 0.7227, "lr": 1.9826537749765367e-05, "epoch": 0.7251456372831445, "percentage": 56.64, "elapsed_time": "13:09:47", "remaining_time": "10:04:40", "throughput": 657.43, "total_tokens": 31153984} {"current_steps": 22660, "total_steps": 40000, "loss": 0.6766, "lr": 1.9816933181425625e-05, "epoch": 0.7253056782536329, "percentage": 56.65, "elapsed_time": "13:09:49", "remaining_time": "10:04:23", "throughput": 657.54, "total_tokens": 31160624} {"current_steps": 22665, "total_steps": 40000, "loss": 0.7086, "lr": 1.9807329412379903e-05, "epoch": 0.7254657192241214, "percentage": 56.66, "elapsed_time": "13:09:51", "remaining_time": "10:04:06", "throughput": 657.66, "total_tokens": 31167424} {"current_steps": 22670, "total_steps": 40000, "loss": 0.6469, "lr": 1.9797726444109247e-05, "epoch": 0.7256257601946098, "percentage": 56.67, "elapsed_time": "13:09:52", "remaining_time": "10:03:49", "throughput": 657.78, "total_tokens": 31174208} {"current_steps": 22675, "total_steps": 40000, "loss": 0.6908, "lr": 1.9788124278094557e-05, "epoch": 0.7257858011650983, "percentage": 56.69, "elapsed_time": "13:09:54", "remaining_time": "10:03:32", "throughput": 657.9, "total_tokens": 31181040} {"current_steps": 22680, "total_steps": 40000, "loss": 0.626, "lr": 1.9778522915816594e-05, "epoch": 0.7259458421355867, "percentage": 56.7, "elapsed_time": "13:09:56", "remaining_time": "10:03:15", "throughput": 658.02, "total_tokens": 31187776} {"current_steps": 22685, "total_steps": 40000, "loss": 0.6899, "lr": 1.9768922358756014e-05, "epoch": 0.7261058831060752, "percentage": 56.71, "elapsed_time": "13:09:58", "remaining_time": "10:02:58", "throughput": 658.13, "total_tokens": 31194304} {"current_steps": 22690, "total_steps": 40000, "loss": 0.7716, "lr": 1.9759322608393353e-05, "epoch": 0.7262659240765637, "percentage": 56.73, "elapsed_time": "13:09:59", "remaining_time": "10:02:40", "throughput": 658.26, "total_tokens": 31201280} {"current_steps": 22695, "total_steps": 40000, "loss": 0.6103, "lr": 1.9749723666208992e-05, "epoch": 0.726425965047052, "percentage": 56.74, "elapsed_time": "13:10:01", "remaining_time": "10:02:23", "throughput": 658.38, "total_tokens": 31208160} {"current_steps": 22700, "total_steps": 40000, "loss": 0.9384, "lr": 1.9740125533683235e-05, "epoch": 0.7265860060175405, "percentage": 56.75, "elapsed_time": "13:10:03", "remaining_time": "10:02:06", "throughput": 658.5, "total_tokens": 31215056} {"current_steps": 22705, "total_steps": 40000, "loss": 0.7485, "lr": 1.9730528212296208e-05, "epoch": 0.7267460469880289, "percentage": 56.76, "elapsed_time": "13:10:05", "remaining_time": "10:01:49", "throughput": 658.62, "total_tokens": 31221856} {"current_steps": 22710, "total_steps": 40000, "loss": 0.7553, "lr": 1.9720931703527945e-05, "epoch": 0.7269060879585174, "percentage": 56.77, "elapsed_time": "13:10:06", "remaining_time": "10:01:32", "throughput": 658.74, "total_tokens": 31228688} {"current_steps": 22715, "total_steps": 40000, "loss": 0.665, "lr": 1.9711336008858373e-05, "epoch": 0.7270661289290058, "percentage": 56.79, "elapsed_time": "13:10:08", "remaining_time": "10:01:15", "throughput": 658.86, "total_tokens": 31235728} {"current_steps": 22720, "total_steps": 40000, "loss": 0.9428, "lr": 1.9701741129767233e-05, "epoch": 0.7272261698994943, "percentage": 56.8, "elapsed_time": "13:10:10", "remaining_time": "10:00:58", "throughput": 658.98, "total_tokens": 31242512} {"current_steps": 22725, "total_steps": 40000, "loss": 0.5811, "lr": 1.9692147067734202e-05, "epoch": 0.7273862108699827, "percentage": 56.81, "elapsed_time": "13:10:12", "remaining_time": "10:00:41", "throughput": 659.1, "total_tokens": 31249312} {"current_steps": 22730, "total_steps": 40000, "loss": 0.694, "lr": 1.96825538242388e-05, "epoch": 0.7275462518404712, "percentage": 56.83, "elapsed_time": "13:10:14", "remaining_time": "10:00:24", "throughput": 659.23, "total_tokens": 31256784} {"current_steps": 22735, "total_steps": 40000, "loss": 0.7819, "lr": 1.967296140076041e-05, "epoch": 0.7277062928109596, "percentage": 56.84, "elapsed_time": "13:10:15", "remaining_time": "10:00:07", "throughput": 659.36, "total_tokens": 31264048} {"current_steps": 22740, "total_steps": 40000, "loss": 0.709, "lr": 1.966336979877833e-05, "epoch": 0.727866333781448, "percentage": 56.85, "elapsed_time": "13:10:17", "remaining_time": "9:59:50", "throughput": 659.48, "total_tokens": 31270832} {"current_steps": 22745, "total_steps": 40000, "loss": 0.6073, "lr": 1.9653779019771678e-05, "epoch": 0.7280263747519365, "percentage": 56.86, "elapsed_time": "13:10:19", "remaining_time": "9:59:33", "throughput": 659.6, "total_tokens": 31277728} {"current_steps": 22750, "total_steps": 40000, "loss": 0.8426, "lr": 1.9644189065219488e-05, "epoch": 0.7281864157224249, "percentage": 56.88, "elapsed_time": "13:10:21", "remaining_time": "9:59:16", "throughput": 659.72, "total_tokens": 31284672} {"current_steps": 22755, "total_steps": 40000, "loss": 0.7639, "lr": 1.9634599936600655e-05, "epoch": 0.7283464566929134, "percentage": 56.89, "elapsed_time": "13:10:22", "remaining_time": "9:58:59", "throughput": 659.84, "total_tokens": 31291248} {"current_steps": 22760, "total_steps": 40000, "loss": 0.5476, "lr": 1.9625011635393935e-05, "epoch": 0.7285064976634018, "percentage": 56.9, "elapsed_time": "13:10:24", "remaining_time": "9:58:42", "throughput": 659.96, "total_tokens": 31298272} {"current_steps": 22765, "total_steps": 40000, "loss": 0.6157, "lr": 1.9615424163077963e-05, "epoch": 0.7286665386338903, "percentage": 56.91, "elapsed_time": "13:10:26", "remaining_time": "9:58:25", "throughput": 660.08, "total_tokens": 31304976} {"current_steps": 22770, "total_steps": 40000, "loss": 0.6729, "lr": 1.9605837521131263e-05, "epoch": 0.7288265796043787, "percentage": 56.93, "elapsed_time": "13:10:27", "remaining_time": "9:58:08", "throughput": 660.2, "total_tokens": 31312096} {"current_steps": 22775, "total_steps": 40000, "loss": 0.6661, "lr": 1.9596251711032192e-05, "epoch": 0.7289866205748672, "percentage": 56.94, "elapsed_time": "13:10:29", "remaining_time": "9:57:51", "throughput": 660.32, "total_tokens": 31318976} {"current_steps": 22780, "total_steps": 40000, "loss": 0.772, "lr": 1.958666673425903e-05, "epoch": 0.7291466615453556, "percentage": 56.95, "elapsed_time": "13:10:31", "remaining_time": "9:57:34", "throughput": 660.46, "total_tokens": 31326464} {"current_steps": 22785, "total_steps": 40000, "loss": 0.6089, "lr": 1.957708259228987e-05, "epoch": 0.7293067025158441, "percentage": 56.96, "elapsed_time": "13:10:33", "remaining_time": "9:57:17", "throughput": 660.58, "total_tokens": 31333232} {"current_steps": 22790, "total_steps": 40000, "loss": 0.6313, "lr": 1.956749928660273e-05, "epoch": 0.7294667434863324, "percentage": 56.97, "elapsed_time": "13:10:34", "remaining_time": "9:57:00", "throughput": 660.71, "total_tokens": 31340656} {"current_steps": 22795, "total_steps": 40000, "loss": 0.6803, "lr": 1.955791681867547e-05, "epoch": 0.7296267844568209, "percentage": 56.99, "elapsed_time": "13:10:36", "remaining_time": "9:56:43", "throughput": 660.83, "total_tokens": 31347664} {"current_steps": 22800, "total_steps": 40000, "loss": 1.0034, "lr": 1.9548335189985824e-05, "epoch": 0.7297868254273094, "percentage": 57.0, "elapsed_time": "13:10:38", "remaining_time": "9:56:26", "throughput": 660.95, "total_tokens": 31354544} {"current_steps": 22800, "total_steps": 40000, "eval_loss": 0.7402949929237366, "epoch": 0.7297868254273094, "percentage": 57.0, "elapsed_time": "13:16:25", "remaining_time": "10:00:49", "throughput": 656.15, "total_tokens": 31354544} {"current_steps": 22805, "total_steps": 40000, "loss": 0.5806, "lr": 1.9538754402011396e-05, "epoch": 0.7299468663977978, "percentage": 57.01, "elapsed_time": "13:16:30", "remaining_time": "10:00:33", "throughput": 656.23, "total_tokens": 31361424} {"current_steps": 22810, "total_steps": 40000, "loss": 0.8679, "lr": 1.952917445622968e-05, "epoch": 0.7301069073682863, "percentage": 57.03, "elapsed_time": "13:16:31", "remaining_time": "10:00:16", "throughput": 656.35, "total_tokens": 31368384} {"current_steps": 22815, "total_steps": 40000, "loss": 0.5962, "lr": 1.9519595354118005e-05, "epoch": 0.7302669483387747, "percentage": 57.04, "elapsed_time": "13:16:33", "remaining_time": "9:59:59", "throughput": 656.46, "total_tokens": 31374640} {"current_steps": 22820, "total_steps": 40000, "loss": 0.7059, "lr": 1.951001709715361e-05, "epoch": 0.7304269893092632, "percentage": 57.05, "elapsed_time": "13:16:35", "remaining_time": "9:59:42", "throughput": 656.57, "total_tokens": 31381104} {"current_steps": 22825, "total_steps": 40000, "loss": 0.6177, "lr": 1.9500439686813556e-05, "epoch": 0.7305870302797516, "percentage": 57.06, "elapsed_time": "13:16:37", "remaining_time": "9:59:25", "throughput": 656.68, "total_tokens": 31387536} {"current_steps": 22830, "total_steps": 40000, "loss": 0.7169, "lr": 1.949086312457482e-05, "epoch": 0.7307470712502401, "percentage": 57.07, "elapsed_time": "13:16:38", "remaining_time": "9:59:08", "throughput": 656.8, "total_tokens": 31394128} {"current_steps": 22835, "total_steps": 40000, "loss": 0.7676, "lr": 1.9481287411914223e-05, "epoch": 0.7309071122207285, "percentage": 57.09, "elapsed_time": "13:16:40", "remaining_time": "9:58:51", "throughput": 656.92, "total_tokens": 31400976} {"current_steps": 22840, "total_steps": 40000, "loss": 0.8508, "lr": 1.9471712550308457e-05, "epoch": 0.731067153191217, "percentage": 57.1, "elapsed_time": "13:16:42", "remaining_time": "9:58:34", "throughput": 657.04, "total_tokens": 31408000} {"current_steps": 22845, "total_steps": 40000, "loss": 0.6265, "lr": 1.946213854123409e-05, "epoch": 0.7312271941617055, "percentage": 57.11, "elapsed_time": "13:16:44", "remaining_time": "9:58:17", "throughput": 657.16, "total_tokens": 31415072} {"current_steps": 22850, "total_steps": 40000, "loss": 0.6894, "lr": 1.9452565386167554e-05, "epoch": 0.7313872351321938, "percentage": 57.12, "elapsed_time": "13:16:45", "remaining_time": "9:58:00", "throughput": 657.28, "total_tokens": 31421840} {"current_steps": 22855, "total_steps": 40000, "loss": 0.6733, "lr": 1.9442993086585142e-05, "epoch": 0.7315472761026823, "percentage": 57.14, "elapsed_time": "13:16:47", "remaining_time": "9:57:43", "throughput": 657.4, "total_tokens": 31428464} {"current_steps": 22860, "total_steps": 40000, "loss": 0.5766, "lr": 1.9433421643963043e-05, "epoch": 0.7317073170731707, "percentage": 57.15, "elapsed_time": "13:16:49", "remaining_time": "9:57:26", "throughput": 657.52, "total_tokens": 31435504} {"current_steps": 22865, "total_steps": 40000, "loss": 0.6683, "lr": 1.942385105977727e-05, "epoch": 0.7318673580436592, "percentage": 57.16, "elapsed_time": "13:16:50", "remaining_time": "9:57:09", "throughput": 657.64, "total_tokens": 31442208} {"current_steps": 22870, "total_steps": 40000, "loss": 0.7384, "lr": 1.9414281335503743e-05, "epoch": 0.7320273990141476, "percentage": 57.17, "elapsed_time": "13:16:52", "remaining_time": "9:56:52", "throughput": 657.75, "total_tokens": 31448944} {"current_steps": 22875, "total_steps": 40000, "loss": 0.6714, "lr": 1.9404712472618232e-05, "epoch": 0.7321874399846361, "percentage": 57.19, "elapsed_time": "13:16:54", "remaining_time": "9:56:35", "throughput": 657.87, "total_tokens": 31455888} {"current_steps": 22880, "total_steps": 40000, "loss": 0.6504, "lr": 1.939514447259636e-05, "epoch": 0.7323474809551245, "percentage": 57.2, "elapsed_time": "13:16:56", "remaining_time": "9:56:18", "throughput": 658.0, "total_tokens": 31462864} {"current_steps": 22885, "total_steps": 40000, "loss": 0.7167, "lr": 1.938557733691365e-05, "epoch": 0.732507521925613, "percentage": 57.21, "elapsed_time": "13:16:57", "remaining_time": "9:56:01", "throughput": 658.11, "total_tokens": 31469504} {"current_steps": 22890, "total_steps": 40000, "loss": 0.7978, "lr": 1.9376011067045476e-05, "epoch": 0.7326675628961014, "percentage": 57.23, "elapsed_time": "13:16:59", "remaining_time": "9:55:44", "throughput": 658.23, "total_tokens": 31476336} {"current_steps": 22895, "total_steps": 40000, "loss": 0.828, "lr": 1.9366445664467065e-05, "epoch": 0.7328276038665898, "percentage": 57.24, "elapsed_time": "13:17:01", "remaining_time": "9:55:27", "throughput": 658.35, "total_tokens": 31483168} {"current_steps": 22900, "total_steps": 40000, "loss": 1.0039, "lr": 1.9356881130653533e-05, "epoch": 0.7329876448370783, "percentage": 57.25, "elapsed_time": "13:17:03", "remaining_time": "9:55:10", "throughput": 658.47, "total_tokens": 31490272} {"current_steps": 22905, "total_steps": 40000, "loss": 0.708, "lr": 1.9347317467079846e-05, "epoch": 0.7331476858075667, "percentage": 57.26, "elapsed_time": "13:17:04", "remaining_time": "9:54:53", "throughput": 658.59, "total_tokens": 31496832} {"current_steps": 22910, "total_steps": 40000, "loss": 0.7368, "lr": 1.9337754675220836e-05, "epoch": 0.7333077267780552, "percentage": 57.27, "elapsed_time": "13:17:06", "remaining_time": "9:54:36", "throughput": 658.7, "total_tokens": 31503536} {"current_steps": 22915, "total_steps": 40000, "loss": 0.6767, "lr": 1.9328192756551218e-05, "epoch": 0.7334677677485436, "percentage": 57.29, "elapsed_time": "13:17:08", "remaining_time": "9:54:19", "throughput": 658.82, "total_tokens": 31510256} {"current_steps": 22920, "total_steps": 40000, "loss": 0.6653, "lr": 1.931863171254555e-05, "epoch": 0.7336278087190321, "percentage": 57.3, "elapsed_time": "13:17:10", "remaining_time": "9:54:02", "throughput": 658.94, "total_tokens": 31517296} {"current_steps": 22925, "total_steps": 40000, "loss": 0.8132, "lr": 1.930907154467826e-05, "epoch": 0.7337878496895205, "percentage": 57.31, "elapsed_time": "13:17:11", "remaining_time": "9:53:46", "throughput": 659.06, "total_tokens": 31524000} {"current_steps": 22930, "total_steps": 40000, "loss": 0.8429, "lr": 1.9299512254423673e-05, "epoch": 0.733947890660009, "percentage": 57.33, "elapsed_time": "13:17:13", "remaining_time": "9:53:29", "throughput": 659.18, "total_tokens": 31530912} {"current_steps": 22935, "total_steps": 40000, "loss": 0.6899, "lr": 1.9289953843255914e-05, "epoch": 0.7341079316304974, "percentage": 57.34, "elapsed_time": "13:17:15", "remaining_time": "9:53:12", "throughput": 659.3, "total_tokens": 31537808} {"current_steps": 22940, "total_steps": 40000, "loss": 0.8779, "lr": 1.9280396312649048e-05, "epoch": 0.7342679726009859, "percentage": 57.35, "elapsed_time": "13:17:16", "remaining_time": "9:52:55", "throughput": 659.42, "total_tokens": 31544816} {"current_steps": 22945, "total_steps": 40000, "loss": 0.7387, "lr": 1.9270839664076936e-05, "epoch": 0.7344280135714742, "percentage": 57.36, "elapsed_time": "13:17:18", "remaining_time": "9:52:38", "throughput": 659.54, "total_tokens": 31551584} {"current_steps": 22950, "total_steps": 40000, "loss": 0.6187, "lr": 1.9261283899013345e-05, "epoch": 0.7345880545419627, "percentage": 57.38, "elapsed_time": "13:17:20", "remaining_time": "9:52:21", "throughput": 659.66, "total_tokens": 31558544} {"current_steps": 22955, "total_steps": 40000, "loss": 0.7587, "lr": 1.92517290189319e-05, "epoch": 0.7347480955124512, "percentage": 57.39, "elapsed_time": "13:17:22", "remaining_time": "9:52:04", "throughput": 659.78, "total_tokens": 31565360} {"current_steps": 22960, "total_steps": 40000, "loss": 0.5886, "lr": 1.924217502530607e-05, "epoch": 0.7349081364829396, "percentage": 57.4, "elapsed_time": "13:17:23", "remaining_time": "9:51:47", "throughput": 659.89, "total_tokens": 31571888} {"current_steps": 22965, "total_steps": 40000, "loss": 0.7921, "lr": 1.9232621919609207e-05, "epoch": 0.7350681774534281, "percentage": 57.41, "elapsed_time": "13:17:25", "remaining_time": "9:51:30", "throughput": 660.01, "total_tokens": 31578576} {"current_steps": 22970, "total_steps": 40000, "loss": 0.7318, "lr": 1.9223069703314534e-05, "epoch": 0.7352282184239165, "percentage": 57.43, "elapsed_time": "13:17:27", "remaining_time": "9:51:14", "throughput": 660.13, "total_tokens": 31585264} {"current_steps": 22975, "total_steps": 40000, "loss": 0.708, "lr": 1.92135183778951e-05, "epoch": 0.735388259394405, "percentage": 57.44, "elapsed_time": "13:17:29", "remaining_time": "9:50:57", "throughput": 660.24, "total_tokens": 31592096} {"current_steps": 22980, "total_steps": 40000, "loss": 0.7559, "lr": 1.9203967944823857e-05, "epoch": 0.7355483003648934, "percentage": 57.45, "elapsed_time": "13:17:30", "remaining_time": "9:50:40", "throughput": 660.36, "total_tokens": 31598992} {"current_steps": 22985, "total_steps": 40000, "loss": 0.7935, "lr": 1.9194418405573588e-05, "epoch": 0.7357083413353819, "percentage": 57.46, "elapsed_time": "13:17:32", "remaining_time": "9:50:23", "throughput": 660.48, "total_tokens": 31605824} {"current_steps": 22990, "total_steps": 40000, "loss": 0.8032, "lr": 1.9184869761616954e-05, "epoch": 0.7358683823058703, "percentage": 57.48, "elapsed_time": "13:17:34", "remaining_time": "9:50:06", "throughput": 660.61, "total_tokens": 31612976} {"current_steps": 22995, "total_steps": 40000, "loss": 0.7199, "lr": 1.9175322014426495e-05, "epoch": 0.7360284232763588, "percentage": 57.49, "elapsed_time": "13:17:36", "remaining_time": "9:49:49", "throughput": 660.74, "total_tokens": 31620224} {"current_steps": 23000, "total_steps": 40000, "loss": 0.6809, "lr": 1.9165775165474565e-05, "epoch": 0.7361884642468471, "percentage": 57.5, "elapsed_time": "13:17:37", "remaining_time": "9:49:33", "throughput": 660.85, "total_tokens": 31626736} {"current_steps": 23000, "total_steps": 40000, "eval_loss": 0.7399948239326477, "epoch": 0.7361884642468471, "percentage": 57.5, "elapsed_time": "13:23:25", "remaining_time": "9:53:49", "throughput": 656.09, "total_tokens": 31626736} {"current_steps": 23005, "total_steps": 40000, "loss": 0.7464, "lr": 1.9156229216233434e-05, "epoch": 0.7363485052173356, "percentage": 57.51, "elapsed_time": "13:23:29", "remaining_time": "9:53:34", "throughput": 656.17, "total_tokens": 31633360} {"current_steps": 23010, "total_steps": 40000, "loss": 0.8055, "lr": 1.9146684168175184e-05, "epoch": 0.7365085461878241, "percentage": 57.53, "elapsed_time": "13:23:30", "remaining_time": "9:53:17", "throughput": 656.29, "total_tokens": 31640144} {"current_steps": 23015, "total_steps": 40000, "loss": 0.7751, "lr": 1.9137140022771796e-05, "epoch": 0.7366685871583125, "percentage": 57.54, "elapsed_time": "13:23:32", "remaining_time": "9:53:00", "throughput": 656.41, "total_tokens": 31647216} {"current_steps": 23020, "total_steps": 40000, "loss": 0.9271, "lr": 1.9127596781495103e-05, "epoch": 0.736828628128801, "percentage": 57.55, "elapsed_time": "13:23:34", "remaining_time": "9:52:43", "throughput": 656.53, "total_tokens": 31654416} {"current_steps": 23025, "total_steps": 40000, "loss": 0.9277, "lr": 1.9118054445816767e-05, "epoch": 0.7369886690992894, "percentage": 57.56, "elapsed_time": "13:23:36", "remaining_time": "9:52:26", "throughput": 656.66, "total_tokens": 31661600} {"current_steps": 23030, "total_steps": 40000, "loss": 0.7833, "lr": 1.9108513017208356e-05, "epoch": 0.7371487100697779, "percentage": 57.57, "elapsed_time": "13:23:37", "remaining_time": "9:52:10", "throughput": 656.77, "total_tokens": 31668176} {"current_steps": 23035, "total_steps": 40000, "loss": 0.7167, "lr": 1.9098972497141287e-05, "epoch": 0.7373087510402663, "percentage": 57.59, "elapsed_time": "13:23:39", "remaining_time": "9:51:53", "throughput": 656.92, "total_tokens": 31676336} {"current_steps": 23040, "total_steps": 40000, "loss": 0.5772, "lr": 1.9089432887086806e-05, "epoch": 0.7374687920107548, "percentage": 57.6, "elapsed_time": "13:23:41", "remaining_time": "9:51:36", "throughput": 657.03, "total_tokens": 31683072} {"current_steps": 23045, "total_steps": 40000, "loss": 0.8623, "lr": 1.9079894188516056e-05, "epoch": 0.7376288329812432, "percentage": 57.61, "elapsed_time": "13:23:43", "remaining_time": "9:51:19", "throughput": 657.16, "total_tokens": 31690352} {"current_steps": 23050, "total_steps": 40000, "loss": 0.5369, "lr": 1.907035640290002e-05, "epoch": 0.7377888739517316, "percentage": 57.63, "elapsed_time": "13:23:44", "remaining_time": "9:51:02", "throughput": 657.28, "total_tokens": 31697088} {"current_steps": 23055, "total_steps": 40000, "loss": 0.6044, "lr": 1.9060819531709534e-05, "epoch": 0.73794891492222, "percentage": 57.64, "elapsed_time": "13:23:46", "remaining_time": "9:50:45", "throughput": 657.39, "total_tokens": 31703648} {"current_steps": 23060, "total_steps": 40000, "loss": 0.8278, "lr": 1.9051283576415325e-05, "epoch": 0.7381089558927085, "percentage": 57.65, "elapsed_time": "13:23:48", "remaining_time": "9:50:28", "throughput": 657.5, "total_tokens": 31710304} {"current_steps": 23065, "total_steps": 40000, "loss": 0.755, "lr": 1.904174853848793e-05, "epoch": 0.738268996863197, "percentage": 57.66, "elapsed_time": "13:23:50", "remaining_time": "9:50:11", "throughput": 657.62, "total_tokens": 31717248} {"current_steps": 23070, "total_steps": 40000, "loss": 0.4901, "lr": 1.903221441939779e-05, "epoch": 0.7384290378336854, "percentage": 57.67, "elapsed_time": "13:23:51", "remaining_time": "9:49:55", "throughput": 657.74, "total_tokens": 31723856} {"current_steps": 23075, "total_steps": 40000, "loss": 0.679, "lr": 1.9022681220615194e-05, "epoch": 0.7385890788041739, "percentage": 57.69, "elapsed_time": "13:23:53", "remaining_time": "9:49:38", "throughput": 657.86, "total_tokens": 31730800} {"current_steps": 23080, "total_steps": 40000, "loss": 0.7672, "lr": 1.9013148943610255e-05, "epoch": 0.7387491197746623, "percentage": 57.7, "elapsed_time": "13:23:55", "remaining_time": "9:49:21", "throughput": 657.97, "total_tokens": 31737504} {"current_steps": 23085, "total_steps": 40000, "loss": 0.709, "lr": 1.9003617589852998e-05, "epoch": 0.7389091607451508, "percentage": 57.71, "elapsed_time": "13:23:56", "remaining_time": "9:49:04", "throughput": 658.09, "total_tokens": 31744288} {"current_steps": 23090, "total_steps": 40000, "loss": 0.7413, "lr": 1.899408716081326e-05, "epoch": 0.7390692017156392, "percentage": 57.73, "elapsed_time": "13:23:58", "remaining_time": "9:48:47", "throughput": 658.21, "total_tokens": 31751088} {"current_steps": 23095, "total_steps": 40000, "loss": 0.7705, "lr": 1.898455765796075e-05, "epoch": 0.7392292426861277, "percentage": 57.74, "elapsed_time": "13:24:00", "remaining_time": "9:48:30", "throughput": 658.33, "total_tokens": 31758288} {"current_steps": 23100, "total_steps": 40000, "loss": 0.9097, "lr": 1.8975029082765053e-05, "epoch": 0.739389283656616, "percentage": 57.75, "elapsed_time": "13:24:02", "remaining_time": "9:48:14", "throughput": 658.44, "total_tokens": 31764528} {"current_steps": 23105, "total_steps": 40000, "loss": 0.5906, "lr": 1.8965501436695577e-05, "epoch": 0.7395493246271045, "percentage": 57.76, "elapsed_time": "13:24:03", "remaining_time": "9:47:57", "throughput": 658.55, "total_tokens": 31771200} {"current_steps": 23110, "total_steps": 40000, "loss": 0.6235, "lr": 1.895597472122161e-05, "epoch": 0.739709365597593, "percentage": 57.77, "elapsed_time": "13:24:05", "remaining_time": "9:47:40", "throughput": 658.67, "total_tokens": 31777792} {"current_steps": 23115, "total_steps": 40000, "loss": 0.856, "lr": 1.894644893781231e-05, "epoch": 0.7398694065680814, "percentage": 57.79, "elapsed_time": "13:24:07", "remaining_time": "9:47:23", "throughput": 658.78, "total_tokens": 31784576} {"current_steps": 23120, "total_steps": 40000, "loss": 0.6718, "lr": 1.893692408793665e-05, "epoch": 0.7400294475385699, "percentage": 57.8, "elapsed_time": "13:24:09", "remaining_time": "9:47:06", "throughput": 658.9, "total_tokens": 31791136} {"current_steps": 23125, "total_steps": 40000, "loss": 0.684, "lr": 1.8927400173063493e-05, "epoch": 0.7401894885090583, "percentage": 57.81, "elapsed_time": "13:24:10", "remaining_time": "9:46:50", "throughput": 659.02, "total_tokens": 31798048} {"current_steps": 23130, "total_steps": 40000, "loss": 0.7421, "lr": 1.891787719466154e-05, "epoch": 0.7403495294795468, "percentage": 57.83, "elapsed_time": "13:24:12", "remaining_time": "9:46:33", "throughput": 659.13, "total_tokens": 31804752} {"current_steps": 23135, "total_steps": 40000, "loss": 0.6455, "lr": 1.8908355154199346e-05, "epoch": 0.7405095704500352, "percentage": 57.84, "elapsed_time": "13:24:14", "remaining_time": "9:46:16", "throughput": 659.25, "total_tokens": 31811696} {"current_steps": 23140, "total_steps": 40000, "loss": 0.6494, "lr": 1.8898834053145357e-05, "epoch": 0.7406696114205237, "percentage": 57.85, "elapsed_time": "13:24:16", "remaining_time": "9:45:59", "throughput": 659.37, "total_tokens": 31818704} {"current_steps": 23145, "total_steps": 40000, "loss": 0.8849, "lr": 1.8889313892967813e-05, "epoch": 0.7408296523910121, "percentage": 57.86, "elapsed_time": "13:24:17", "remaining_time": "9:45:43", "throughput": 659.49, "total_tokens": 31825552} {"current_steps": 23150, "total_steps": 40000, "loss": 0.7296, "lr": 1.8879794675134863e-05, "epoch": 0.7409896933615006, "percentage": 57.88, "elapsed_time": "13:24:19", "remaining_time": "9:45:26", "throughput": 659.61, "total_tokens": 31832592} {"current_steps": 23155, "total_steps": 40000, "loss": 0.6597, "lr": 1.8870276401114494e-05, "epoch": 0.7411497343319889, "percentage": 57.89, "elapsed_time": "13:24:21", "remaining_time": "9:45:09", "throughput": 659.73, "total_tokens": 31839296} {"current_steps": 23160, "total_steps": 40000, "loss": 0.6883, "lr": 1.886075907237453e-05, "epoch": 0.7413097753024774, "percentage": 57.9, "elapsed_time": "13:24:23", "remaining_time": "9:44:52", "throughput": 659.84, "total_tokens": 31845760} {"current_steps": 23165, "total_steps": 40000, "loss": 0.7921, "lr": 1.8851242690382672e-05, "epoch": 0.7414698162729659, "percentage": 57.91, "elapsed_time": "13:24:24", "remaining_time": "9:44:36", "throughput": 659.96, "total_tokens": 31852576} {"current_steps": 23170, "total_steps": 40000, "loss": 0.8592, "lr": 1.884172725660645e-05, "epoch": 0.7416298572434543, "percentage": 57.93, "elapsed_time": "13:24:26", "remaining_time": "9:44:19", "throughput": 660.08, "total_tokens": 31859760} {"current_steps": 23175, "total_steps": 40000, "loss": 0.5953, "lr": 1.8832212772513277e-05, "epoch": 0.7417898982139428, "percentage": 57.94, "elapsed_time": "13:24:28", "remaining_time": "9:44:02", "throughput": 660.2, "total_tokens": 31866496} {"current_steps": 23180, "total_steps": 40000, "loss": 0.7627, "lr": 1.8822699239570414e-05, "epoch": 0.7419499391844312, "percentage": 57.95, "elapsed_time": "13:24:29", "remaining_time": "9:43:45", "throughput": 660.32, "total_tokens": 31873616} {"current_steps": 23185, "total_steps": 40000, "loss": 0.7111, "lr": 1.8813186659244943e-05, "epoch": 0.7421099801549197, "percentage": 57.96, "elapsed_time": "13:24:31", "remaining_time": "9:43:29", "throughput": 660.44, "total_tokens": 31880608} {"current_steps": 23190, "total_steps": 40000, "loss": 0.8702, "lr": 1.880367503300385e-05, "epoch": 0.7422700211254081, "percentage": 57.98, "elapsed_time": "13:24:33", "remaining_time": "9:43:12", "throughput": 660.56, "total_tokens": 31887440} {"current_steps": 23195, "total_steps": 40000, "loss": 0.7907, "lr": 1.8794164362313927e-05, "epoch": 0.7424300620958966, "percentage": 57.99, "elapsed_time": "13:24:35", "remaining_time": "9:42:55", "throughput": 660.68, "total_tokens": 31894560} {"current_steps": 23200, "total_steps": 40000, "loss": 0.6563, "lr": 1.878465464864185e-05, "epoch": 0.742590103066385, "percentage": 58.0, "elapsed_time": "13:24:36", "remaining_time": "9:42:39", "throughput": 660.8, "total_tokens": 31901472} {"current_steps": 23200, "total_steps": 40000, "eval_loss": 0.7395905256271362, "epoch": 0.742590103066385, "percentage": 58.0, "elapsed_time": "13:30:24", "remaining_time": "9:46:50", "throughput": 656.08, "total_tokens": 31901472} {"current_steps": 23205, "total_steps": 40000, "loss": 0.8091, "lr": 1.877514589345414e-05, "epoch": 0.7427501440368734, "percentage": 58.01, "elapsed_time": "13:30:27", "remaining_time": "9:46:34", "throughput": 656.19, "total_tokens": 31908592} {"current_steps": 23210, "total_steps": 40000, "loss": 0.7393, "lr": 1.876563809821715e-05, "epoch": 0.7429101850073618, "percentage": 58.03, "elapsed_time": "13:30:29", "remaining_time": "9:46:18", "throughput": 656.3, "total_tokens": 31915488} {"current_steps": 23215, "total_steps": 40000, "loss": 0.7189, "lr": 1.8756131264397106e-05, "epoch": 0.7430702259778503, "percentage": 58.04, "elapsed_time": "13:30:30", "remaining_time": "9:46:01", "throughput": 656.42, "total_tokens": 31922336} {"current_steps": 23220, "total_steps": 40000, "loss": 0.852, "lr": 1.87466253934601e-05, "epoch": 0.7432302669483388, "percentage": 58.05, "elapsed_time": "13:30:32", "remaining_time": "9:45:44", "throughput": 656.55, "total_tokens": 31929504} {"current_steps": 23225, "total_steps": 40000, "loss": 0.7316, "lr": 1.8737120486872033e-05, "epoch": 0.7433903079188272, "percentage": 58.06, "elapsed_time": "13:30:34", "remaining_time": "9:45:27", "throughput": 656.67, "total_tokens": 31936608} {"current_steps": 23230, "total_steps": 40000, "loss": 0.6396, "lr": 1.8727616546098696e-05, "epoch": 0.7435503488893157, "percentage": 58.07, "elapsed_time": "13:30:36", "remaining_time": "9:45:10", "throughput": 656.78, "total_tokens": 31943216} {"current_steps": 23235, "total_steps": 40000, "loss": 0.9657, "lr": 1.8718113572605716e-05, "epoch": 0.7437103898598041, "percentage": 58.09, "elapsed_time": "13:30:37", "remaining_time": "9:44:54", "throughput": 656.9, "total_tokens": 31950240} {"current_steps": 23240, "total_steps": 40000, "loss": 0.7007, "lr": 1.8708611567858554e-05, "epoch": 0.7438704308302926, "percentage": 58.1, "elapsed_time": "13:30:39", "remaining_time": "9:44:37", "throughput": 657.02, "total_tokens": 31957040} {"current_steps": 23245, "total_steps": 40000, "loss": 0.8059, "lr": 1.8699110533322565e-05, "epoch": 0.744030471800781, "percentage": 58.11, "elapsed_time": "13:30:41", "remaining_time": "9:44:20", "throughput": 657.15, "total_tokens": 31964608} {"current_steps": 23250, "total_steps": 40000, "loss": 1.04, "lr": 1.8689610470462897e-05, "epoch": 0.7441905127712695, "percentage": 58.13, "elapsed_time": "13:30:43", "remaining_time": "9:44:03", "throughput": 657.27, "total_tokens": 31971584} {"current_steps": 23255, "total_steps": 40000, "loss": 0.7159, "lr": 1.8680111380744604e-05, "epoch": 0.7443505537417578, "percentage": 58.14, "elapsed_time": "13:30:44", "remaining_time": "9:43:47", "throughput": 657.39, "total_tokens": 31978352} {"current_steps": 23260, "total_steps": 40000, "loss": 0.8207, "lr": 1.8670613265632564e-05, "epoch": 0.7445105947122463, "percentage": 58.15, "elapsed_time": "13:30:46", "remaining_time": "9:43:30", "throughput": 657.49, "total_tokens": 31984672} {"current_steps": 23265, "total_steps": 40000, "loss": 0.6614, "lr": 1.866111612659149e-05, "epoch": 0.7446706356827347, "percentage": 58.16, "elapsed_time": "13:30:48", "remaining_time": "9:43:13", "throughput": 657.61, "total_tokens": 31991472} {"current_steps": 23270, "total_steps": 40000, "loss": 0.6816, "lr": 1.8651619965085967e-05, "epoch": 0.7448306766532232, "percentage": 58.17, "elapsed_time": "13:30:49", "remaining_time": "9:42:56", "throughput": 657.72, "total_tokens": 31998256} {"current_steps": 23275, "total_steps": 40000, "loss": 0.572, "lr": 1.8642124782580433e-05, "epoch": 0.7449907176237117, "percentage": 58.19, "elapsed_time": "13:30:51", "remaining_time": "9:42:40", "throughput": 657.85, "total_tokens": 32005424} {"current_steps": 23280, "total_steps": 40000, "loss": 0.7072, "lr": 1.8632630580539144e-05, "epoch": 0.7451507585942001, "percentage": 58.2, "elapsed_time": "13:30:53", "remaining_time": "9:42:23", "throughput": 657.97, "total_tokens": 32012480} {"current_steps": 23285, "total_steps": 40000, "loss": 0.7116, "lr": 1.862313736042625e-05, "epoch": 0.7453107995646886, "percentage": 58.21, "elapsed_time": "13:30:55", "remaining_time": "9:42:06", "throughput": 658.1, "total_tokens": 32019808} {"current_steps": 23290, "total_steps": 40000, "loss": 0.8262, "lr": 1.8613645123705703e-05, "epoch": 0.745470840535177, "percentage": 58.23, "elapsed_time": "13:30:56", "remaining_time": "9:41:50", "throughput": 658.21, "total_tokens": 32026496} {"current_steps": 23295, "total_steps": 40000, "loss": 0.9461, "lr": 1.8604153871841328e-05, "epoch": 0.7456308815056655, "percentage": 58.24, "elapsed_time": "13:30:58", "remaining_time": "9:41:33", "throughput": 658.33, "total_tokens": 32033360} {"current_steps": 23300, "total_steps": 40000, "loss": 0.6895, "lr": 1.859466360629682e-05, "epoch": 0.7457909224761539, "percentage": 58.25, "elapsed_time": "13:31:00", "remaining_time": "9:41:16", "throughput": 658.45, "total_tokens": 32040304} {"current_steps": 23305, "total_steps": 40000, "loss": 0.7728, "lr": 1.8585174328535666e-05, "epoch": 0.7459509634466424, "percentage": 58.26, "elapsed_time": "13:31:02", "remaining_time": "9:41:00", "throughput": 658.57, "total_tokens": 32047456} {"current_steps": 23310, "total_steps": 40000, "loss": 0.8774, "lr": 1.857568604002124e-05, "epoch": 0.7461110044171307, "percentage": 58.27, "elapsed_time": "13:31:03", "remaining_time": "9:40:43", "throughput": 658.7, "total_tokens": 32054688} {"current_steps": 23315, "total_steps": 40000, "loss": 0.5884, "lr": 1.8566198742216774e-05, "epoch": 0.7462710453876192, "percentage": 58.29, "elapsed_time": "13:31:05", "remaining_time": "9:40:26", "throughput": 658.81, "total_tokens": 32061584} {"current_steps": 23320, "total_steps": 40000, "loss": 0.5651, "lr": 1.85567124365853e-05, "epoch": 0.7464310863581076, "percentage": 58.3, "elapsed_time": "13:31:07", "remaining_time": "9:40:10", "throughput": 658.93, "total_tokens": 32068464} {"current_steps": 23325, "total_steps": 40000, "loss": 0.6789, "lr": 1.854722712458975e-05, "epoch": 0.7465911273285961, "percentage": 58.31, "elapsed_time": "13:31:09", "remaining_time": "9:39:53", "throughput": 659.05, "total_tokens": 32075424} {"current_steps": 23330, "total_steps": 40000, "loss": 0.7542, "lr": 1.853774280769286e-05, "epoch": 0.7467511682990846, "percentage": 58.33, "elapsed_time": "13:31:10", "remaining_time": "9:39:36", "throughput": 659.17, "total_tokens": 32082176} {"current_steps": 23335, "total_steps": 40000, "loss": 0.7771, "lr": 1.852825948735724e-05, "epoch": 0.746911209269573, "percentage": 58.34, "elapsed_time": "13:31:12", "remaining_time": "9:39:20", "throughput": 659.3, "total_tokens": 32089616} {"current_steps": 23340, "total_steps": 40000, "loss": 0.7588, "lr": 1.851877716504534e-05, "epoch": 0.7470712502400615, "percentage": 58.35, "elapsed_time": "13:31:14", "remaining_time": "9:39:03", "throughput": 659.42, "total_tokens": 32096800} {"current_steps": 23345, "total_steps": 40000, "loss": 0.7792, "lr": 1.8509295842219448e-05, "epoch": 0.7472312912105499, "percentage": 58.36, "elapsed_time": "13:31:15", "remaining_time": "9:38:46", "throughput": 659.53, "total_tokens": 32103200} {"current_steps": 23350, "total_steps": 40000, "loss": 0.8044, "lr": 1.8499815520341697e-05, "epoch": 0.7473913321810384, "percentage": 58.38, "elapsed_time": "13:31:17", "remaining_time": "9:38:30", "throughput": 659.65, "total_tokens": 32110384} {"current_steps": 23355, "total_steps": 40000, "loss": 0.7716, "lr": 1.8490336200874094e-05, "epoch": 0.7475513731515268, "percentage": 58.39, "elapsed_time": "13:31:19", "remaining_time": "9:38:13", "throughput": 659.76, "total_tokens": 32116960} {"current_steps": 23360, "total_steps": 40000, "loss": 0.7981, "lr": 1.848085788527844e-05, "epoch": 0.7477114141220152, "percentage": 58.4, "elapsed_time": "13:31:21", "remaining_time": "9:37:56", "throughput": 659.88, "total_tokens": 32123776} {"current_steps": 23365, "total_steps": 40000, "loss": 0.7294, "lr": 1.847138057501644e-05, "epoch": 0.7478714550925036, "percentage": 58.41, "elapsed_time": "13:31:22", "remaining_time": "9:37:40", "throughput": 659.99, "total_tokens": 32130384} {"current_steps": 23370, "total_steps": 40000, "loss": 0.7384, "lr": 1.8461904271549582e-05, "epoch": 0.7480314960629921, "percentage": 58.43, "elapsed_time": "13:31:24", "remaining_time": "9:37:23", "throughput": 660.12, "total_tokens": 32137664} {"current_steps": 23375, "total_steps": 40000, "loss": 0.9127, "lr": 1.845242897633926e-05, "epoch": 0.7481915370334806, "percentage": 58.44, "elapsed_time": "13:31:26", "remaining_time": "9:37:07", "throughput": 660.24, "total_tokens": 32144592} {"current_steps": 23380, "total_steps": 40000, "loss": 0.6615, "lr": 1.844295469084667e-05, "epoch": 0.748351578003969, "percentage": 58.45, "elapsed_time": "13:31:28", "remaining_time": "9:36:50", "throughput": 660.36, "total_tokens": 32151680} {"current_steps": 23385, "total_steps": 40000, "loss": 0.6714, "lr": 1.843348141653286e-05, "epoch": 0.7485116189744575, "percentage": 58.46, "elapsed_time": "13:31:29", "remaining_time": "9:36:34", "throughput": 660.48, "total_tokens": 32158640} {"current_steps": 23390, "total_steps": 40000, "loss": 0.7986, "lr": 1.842400915485874e-05, "epoch": 0.7486716599449459, "percentage": 58.48, "elapsed_time": "13:31:31", "remaining_time": "9:36:17", "throughput": 660.6, "total_tokens": 32165632} {"current_steps": 23395, "total_steps": 40000, "loss": 0.8255, "lr": 1.8414537907285053e-05, "epoch": 0.7488317009154344, "percentage": 58.49, "elapsed_time": "13:31:33", "remaining_time": "9:36:00", "throughput": 660.73, "total_tokens": 32172880} {"current_steps": 23400, "total_steps": 40000, "loss": 0.7809, "lr": 1.840506767527237e-05, "epoch": 0.7489917418859228, "percentage": 58.5, "elapsed_time": "13:31:35", "remaining_time": "9:35:44", "throughput": 660.85, "total_tokens": 32179968} {"current_steps": 23400, "total_steps": 40000, "eval_loss": 0.7390560507774353, "epoch": 0.7489917418859228, "percentage": 58.5, "elapsed_time": "13:37:22", "remaining_time": "9:39:50", "throughput": 656.16, "total_tokens": 32179968} {"current_steps": 23405, "total_steps": 40000, "loss": 0.8338, "lr": 1.8395598460281137e-05, "epoch": 0.7491517828564113, "percentage": 58.51, "elapsed_time": "13:37:25", "remaining_time": "9:39:35", "throughput": 656.26, "total_tokens": 32186928} {"current_steps": 23410, "total_steps": 40000, "loss": 0.7809, "lr": 1.838613026377161e-05, "epoch": 0.7493118238268996, "percentage": 58.53, "elapsed_time": "13:37:27", "remaining_time": "9:39:18", "throughput": 656.38, "total_tokens": 32193776} {"current_steps": 23415, "total_steps": 40000, "loss": 0.8281, "lr": 1.8376663087203917e-05, "epoch": 0.7494718647973881, "percentage": 58.54, "elapsed_time": "13:37:29", "remaining_time": "9:39:02", "throughput": 656.49, "total_tokens": 32200352} {"current_steps": 23420, "total_steps": 40000, "loss": 0.7995, "lr": 1.8367196932038014e-05, "epoch": 0.7496319057678765, "percentage": 58.55, "elapsed_time": "13:37:31", "remaining_time": "9:38:45", "throughput": 656.61, "total_tokens": 32207568} {"current_steps": 23425, "total_steps": 40000, "loss": 0.8967, "lr": 1.8357731799733686e-05, "epoch": 0.749791946738365, "percentage": 58.56, "elapsed_time": "13:37:32", "remaining_time": "9:38:28", "throughput": 656.73, "total_tokens": 32214480} {"current_steps": 23430, "total_steps": 40000, "loss": 0.811, "lr": 1.8348267691750586e-05, "epoch": 0.7499519877088535, "percentage": 58.58, "elapsed_time": "13:37:34", "remaining_time": "9:38:12", "throughput": 656.84, "total_tokens": 32221024} {"current_steps": 23435, "total_steps": 40000, "loss": 0.7749, "lr": 1.833880460954821e-05, "epoch": 0.7501120286793419, "percentage": 58.59, "elapsed_time": "13:37:36", "remaining_time": "9:37:55", "throughput": 656.95, "total_tokens": 32227840} {"current_steps": 23440, "total_steps": 40000, "loss": 0.6424, "lr": 1.8329342554585866e-05, "epoch": 0.7502720696498304, "percentage": 58.6, "elapsed_time": "13:37:38", "remaining_time": "9:37:38", "throughput": 657.07, "total_tokens": 32234752} {"current_steps": 23445, "total_steps": 40000, "loss": 0.6994, "lr": 1.8319881528322735e-05, "epoch": 0.7504321106203188, "percentage": 58.61, "elapsed_time": "13:37:39", "remaining_time": "9:37:22", "throughput": 657.19, "total_tokens": 32241552} {"current_steps": 23450, "total_steps": 40000, "loss": 0.7432, "lr": 1.8310421532217815e-05, "epoch": 0.7505921515908073, "percentage": 58.63, "elapsed_time": "13:37:41", "remaining_time": "9:37:05", "throughput": 657.3, "total_tokens": 32248368} {"current_steps": 23455, "total_steps": 40000, "loss": 0.8213, "lr": 1.8300962567729958e-05, "epoch": 0.7507521925612957, "percentage": 58.64, "elapsed_time": "13:37:43", "remaining_time": "9:36:48", "throughput": 657.43, "total_tokens": 32255664} {"current_steps": 23460, "total_steps": 40000, "loss": 0.7724, "lr": 1.8291504636317866e-05, "epoch": 0.7509122335317842, "percentage": 58.65, "elapsed_time": "13:37:45", "remaining_time": "9:36:32", "throughput": 657.54, "total_tokens": 32262048} {"current_steps": 23465, "total_steps": 40000, "loss": 0.8064, "lr": 1.8282047739440055e-05, "epoch": 0.7510722745022725, "percentage": 58.66, "elapsed_time": "13:37:46", "remaining_time": "9:36:15", "throughput": 657.66, "total_tokens": 32269216} {"current_steps": 23470, "total_steps": 40000, "loss": 0.7563, "lr": 1.8272591878554903e-05, "epoch": 0.751232315472761, "percentage": 58.67, "elapsed_time": "13:37:48", "remaining_time": "9:35:59", "throughput": 657.78, "total_tokens": 32276272} {"current_steps": 23475, "total_steps": 40000, "loss": 0.6159, "lr": 1.8263137055120638e-05, "epoch": 0.7513923564432494, "percentage": 58.69, "elapsed_time": "13:37:50", "remaining_time": "9:35:42", "throughput": 657.9, "total_tokens": 32283360} {"current_steps": 23480, "total_steps": 40000, "loss": 0.8284, "lr": 1.8253683270595295e-05, "epoch": 0.7515523974137379, "percentage": 58.7, "elapsed_time": "13:37:52", "remaining_time": "9:35:26", "throughput": 658.02, "total_tokens": 32290400} {"current_steps": 23485, "total_steps": 40000, "loss": 0.8676, "lr": 1.824423052643677e-05, "epoch": 0.7517124383842264, "percentage": 58.71, "elapsed_time": "13:37:53", "remaining_time": "9:35:09", "throughput": 658.14, "total_tokens": 32297200} {"current_steps": 23490, "total_steps": 40000, "loss": 0.6431, "lr": 1.82347788241028e-05, "epoch": 0.7518724793547148, "percentage": 58.73, "elapsed_time": "13:37:55", "remaining_time": "9:34:52", "throughput": 658.25, "total_tokens": 32304160} {"current_steps": 23495, "total_steps": 40000, "loss": 0.6926, "lr": 1.8225328165050942e-05, "epoch": 0.7520325203252033, "percentage": 58.74, "elapsed_time": "13:37:57", "remaining_time": "9:34:36", "throughput": 658.38, "total_tokens": 32311440} {"current_steps": 23500, "total_steps": 40000, "loss": 0.7834, "lr": 1.821587855073863e-05, "epoch": 0.7521925612956917, "percentage": 58.75, "elapsed_time": "13:37:59", "remaining_time": "9:34:19", "throughput": 658.51, "total_tokens": 32319072} {"current_steps": 23505, "total_steps": 40000, "loss": 0.835, "lr": 1.8206429982623086e-05, "epoch": 0.7523526022661802, "percentage": 58.76, "elapsed_time": "13:38:00", "remaining_time": "9:34:03", "throughput": 658.62, "total_tokens": 32325680} {"current_steps": 23510, "total_steps": 40000, "loss": 0.8051, "lr": 1.8196982462161416e-05, "epoch": 0.7525126432366686, "percentage": 58.77, "elapsed_time": "13:38:02", "remaining_time": "9:33:46", "throughput": 658.73, "total_tokens": 32332320} {"current_steps": 23515, "total_steps": 40000, "loss": 0.82, "lr": 1.818753599081055e-05, "epoch": 0.752672684207157, "percentage": 58.79, "elapsed_time": "13:38:04", "remaining_time": "9:33:30", "throughput": 658.85, "total_tokens": 32339216} {"current_steps": 23520, "total_steps": 40000, "loss": 0.8509, "lr": 1.817809057002724e-05, "epoch": 0.7528327251776454, "percentage": 58.8, "elapsed_time": "13:38:05", "remaining_time": "9:33:13", "throughput": 658.96, "total_tokens": 32345680} {"current_steps": 23525, "total_steps": 40000, "loss": 0.8288, "lr": 1.8168646201268096e-05, "epoch": 0.7529927661481339, "percentage": 58.81, "elapsed_time": "13:38:07", "remaining_time": "9:32:57", "throughput": 659.08, "total_tokens": 32352688} {"current_steps": 23530, "total_steps": 40000, "loss": 0.6705, "lr": 1.8159202885989557e-05, "epoch": 0.7531528071186223, "percentage": 58.83, "elapsed_time": "13:38:09", "remaining_time": "9:32:40", "throughput": 659.2, "total_tokens": 32359728} {"current_steps": 23535, "total_steps": 40000, "loss": 0.8305, "lr": 1.814976062564789e-05, "epoch": 0.7533128480891108, "percentage": 58.84, "elapsed_time": "13:38:11", "remaining_time": "9:32:24", "throughput": 659.33, "total_tokens": 32367360} {"current_steps": 23540, "total_steps": 40000, "loss": 0.6091, "lr": 1.8140319421699234e-05, "epoch": 0.7534728890595993, "percentage": 58.85, "elapsed_time": "13:38:12", "remaining_time": "9:32:07", "throughput": 659.45, "total_tokens": 32374512} {"current_steps": 23545, "total_steps": 40000, "loss": 0.6293, "lr": 1.8130879275599515e-05, "epoch": 0.7536329300300877, "percentage": 58.86, "elapsed_time": "13:38:14", "remaining_time": "9:31:50", "throughput": 659.57, "total_tokens": 32381408} {"current_steps": 23550, "total_steps": 40000, "loss": 0.751, "lr": 1.8121440188804544e-05, "epoch": 0.7537929710005762, "percentage": 58.88, "elapsed_time": "13:38:16", "remaining_time": "9:31:34", "throughput": 659.69, "total_tokens": 32388256} {"current_steps": 23555, "total_steps": 40000, "loss": 0.8045, "lr": 1.811200216276993e-05, "epoch": 0.7539530119710646, "percentage": 58.89, "elapsed_time": "13:38:18", "remaining_time": "9:31:18", "throughput": 659.81, "total_tokens": 32395536} {"current_steps": 23560, "total_steps": 40000, "loss": 0.6491, "lr": 1.810256519895115e-05, "epoch": 0.7541130529415531, "percentage": 58.9, "elapsed_time": "13:38:19", "remaining_time": "9:31:01", "throughput": 659.93, "total_tokens": 32402464} {"current_steps": 23565, "total_steps": 40000, "loss": 0.8091, "lr": 1.8093129298803494e-05, "epoch": 0.7542730939120414, "percentage": 58.91, "elapsed_time": "13:38:21", "remaining_time": "9:30:45", "throughput": 660.05, "total_tokens": 32409664} {"current_steps": 23570, "total_steps": 40000, "loss": 0.7757, "lr": 1.808369446378209e-05, "epoch": 0.7544331348825299, "percentage": 58.93, "elapsed_time": "13:38:23", "remaining_time": "9:30:28", "throughput": 660.17, "total_tokens": 32416704} {"current_steps": 23575, "total_steps": 40000, "loss": 0.7729, "lr": 1.8074260695341914e-05, "epoch": 0.7545931758530183, "percentage": 58.94, "elapsed_time": "13:38:25", "remaining_time": "9:30:12", "throughput": 660.29, "total_tokens": 32423568} {"current_steps": 23580, "total_steps": 40000, "loss": 1.0687, "lr": 1.8064827994937782e-05, "epoch": 0.7547532168235068, "percentage": 58.95, "elapsed_time": "13:38:26", "remaining_time": "9:29:55", "throughput": 660.4, "total_tokens": 32430368} {"current_steps": 23585, "total_steps": 40000, "loss": 0.8715, "lr": 1.8055396364024317e-05, "epoch": 0.7549132577939953, "percentage": 58.96, "elapsed_time": "13:38:28", "remaining_time": "9:29:39", "throughput": 660.52, "total_tokens": 32437088} {"current_steps": 23590, "total_steps": 40000, "loss": 0.7923, "lr": 1.804596580405601e-05, "epoch": 0.7550732987644837, "percentage": 58.98, "elapsed_time": "13:38:30", "remaining_time": "9:29:22", "throughput": 660.64, "total_tokens": 32444176} {"current_steps": 23595, "total_steps": 40000, "loss": 0.779, "lr": 1.8036536316487174e-05, "epoch": 0.7552333397349722, "percentage": 58.99, "elapsed_time": "13:38:31", "remaining_time": "9:29:06", "throughput": 660.75, "total_tokens": 32450704} {"current_steps": 23600, "total_steps": 40000, "loss": 0.8411, "lr": 1.802710790277193e-05, "epoch": 0.7553933807054606, "percentage": 59.0, "elapsed_time": "13:38:33", "remaining_time": "9:28:49", "throughput": 660.87, "total_tokens": 32457728} {"current_steps": 23600, "total_steps": 40000, "eval_loss": 0.7388349771499634, "epoch": 0.7553933807054606, "percentage": 59.0, "elapsed_time": "13:44:21", "remaining_time": "9:32:51", "throughput": 656.22, "total_tokens": 32457728} {"current_steps": 23605, "total_steps": 40000, "loss": 0.7383, "lr": 1.801768056436429e-05, "epoch": 0.7555534216759491, "percentage": 59.01, "elapsed_time": "13:44:24", "remaining_time": "9:32:36", "throughput": 656.31, "total_tokens": 32464224} {"current_steps": 23610, "total_steps": 40000, "loss": 1.1072, "lr": 1.8008254302718035e-05, "epoch": 0.7557134626464375, "percentage": 59.03, "elapsed_time": "13:44:26", "remaining_time": "9:32:19", "throughput": 656.43, "total_tokens": 32471312} {"current_steps": 23615, "total_steps": 40000, "loss": 0.7139, "lr": 1.7998829119286837e-05, "epoch": 0.755873503616926, "percentage": 59.04, "elapsed_time": "13:44:28", "remaining_time": "9:32:03", "throughput": 656.55, "total_tokens": 32478336} {"current_steps": 23620, "total_steps": 40000, "loss": 0.683, "lr": 1.798940501552418e-05, "epoch": 0.7560335445874143, "percentage": 59.05, "elapsed_time": "13:44:30", "remaining_time": "9:31:46", "throughput": 656.66, "total_tokens": 32485168} {"current_steps": 23625, "total_steps": 40000, "loss": 0.6428, "lr": 1.797998199288336e-05, "epoch": 0.7561935855579028, "percentage": 59.06, "elapsed_time": "13:44:31", "remaining_time": "9:31:30", "throughput": 656.77, "total_tokens": 32491424} {"current_steps": 23630, "total_steps": 40000, "loss": 0.8454, "lr": 1.7970560052817543e-05, "epoch": 0.7563536265283912, "percentage": 59.08, "elapsed_time": "13:44:33", "remaining_time": "9:31:13", "throughput": 656.89, "total_tokens": 32498832} {"current_steps": 23635, "total_steps": 40000, "loss": 0.5538, "lr": 1.7961139196779702e-05, "epoch": 0.7565136674988797, "percentage": 59.09, "elapsed_time": "13:44:35", "remaining_time": "9:30:56", "throughput": 657.0, "total_tokens": 32505520} {"current_steps": 23640, "total_steps": 40000, "loss": 0.6763, "lr": 1.7951719426222647e-05, "epoch": 0.7566737084693682, "percentage": 59.1, "elapsed_time": "13:44:37", "remaining_time": "9:30:40", "throughput": 657.12, "total_tokens": 32512384} {"current_steps": 23645, "total_steps": 40000, "loss": 0.8396, "lr": 1.794230074259904e-05, "epoch": 0.7568337494398566, "percentage": 59.11, "elapsed_time": "13:44:38", "remaining_time": "9:30:23", "throughput": 657.23, "total_tokens": 32519056} {"current_steps": 23650, "total_steps": 40000, "loss": 0.6406, "lr": 1.7932883147361336e-05, "epoch": 0.7569937904103451, "percentage": 59.13, "elapsed_time": "13:44:40", "remaining_time": "9:30:07", "throughput": 657.35, "total_tokens": 32525952} {"current_steps": 23655, "total_steps": 40000, "loss": 0.7858, "lr": 1.7923466641961865e-05, "epoch": 0.7571538313808335, "percentage": 59.14, "elapsed_time": "13:44:42", "remaining_time": "9:29:50", "throughput": 657.46, "total_tokens": 32532720} {"current_steps": 23660, "total_steps": 40000, "loss": 0.6173, "lr": 1.791405122785278e-05, "epoch": 0.757313872351322, "percentage": 59.15, "elapsed_time": "13:44:44", "remaining_time": "9:29:34", "throughput": 657.58, "total_tokens": 32539648} {"current_steps": 23665, "total_steps": 40000, "loss": 0.7858, "lr": 1.7904636906486037e-05, "epoch": 0.7574739133218104, "percentage": 59.16, "elapsed_time": "13:44:45", "remaining_time": "9:29:18", "throughput": 657.69, "total_tokens": 32546320} {"current_steps": 23670, "total_steps": 40000, "loss": 0.4698, "lr": 1.7895223679313448e-05, "epoch": 0.7576339542922989, "percentage": 59.17, "elapsed_time": "13:44:47", "remaining_time": "9:29:01", "throughput": 657.81, "total_tokens": 32553232} {"current_steps": 23675, "total_steps": 40000, "loss": 0.7754, "lr": 1.7885811547786653e-05, "epoch": 0.7577939952627872, "percentage": 59.19, "elapsed_time": "13:44:49", "remaining_time": "9:28:45", "throughput": 657.92, "total_tokens": 32559952} {"current_steps": 23680, "total_steps": 40000, "loss": 0.7416, "lr": 1.7876400513357115e-05, "epoch": 0.7579540362332757, "percentage": 59.2, "elapsed_time": "13:44:50", "remaining_time": "9:28:28", "throughput": 658.04, "total_tokens": 32566944} {"current_steps": 23685, "total_steps": 40000, "loss": 0.6504, "lr": 1.7866990577476146e-05, "epoch": 0.7581140772037641, "percentage": 59.21, "elapsed_time": "13:44:52", "remaining_time": "9:28:12", "throughput": 658.15, "total_tokens": 32573632} {"current_steps": 23690, "total_steps": 40000, "loss": 0.6583, "lr": 1.7857581741594863e-05, "epoch": 0.7582741181742526, "percentage": 59.23, "elapsed_time": "13:44:54", "remaining_time": "9:27:55", "throughput": 658.26, "total_tokens": 32580352} {"current_steps": 23695, "total_steps": 40000, "loss": 0.7659, "lr": 1.7848174007164237e-05, "epoch": 0.7584341591447411, "percentage": 59.24, "elapsed_time": "13:44:56", "remaining_time": "9:27:39", "throughput": 658.38, "total_tokens": 32587280} {"current_steps": 23700, "total_steps": 40000, "loss": 0.8031, "lr": 1.7838767375635052e-05, "epoch": 0.7585942001152295, "percentage": 59.25, "elapsed_time": "13:44:57", "remaining_time": "9:27:22", "throughput": 658.49, "total_tokens": 32594000} {"current_steps": 23705, "total_steps": 40000, "loss": 0.9274, "lr": 1.782936184845793e-05, "epoch": 0.758754241085718, "percentage": 59.26, "elapsed_time": "13:44:59", "remaining_time": "9:27:06", "throughput": 658.6, "total_tokens": 32600624} {"current_steps": 23710, "total_steps": 40000, "loss": 0.7119, "lr": 1.7819957427083334e-05, "epoch": 0.7589142820562064, "percentage": 59.27, "elapsed_time": "13:45:01", "remaining_time": "9:26:50", "throughput": 658.72, "total_tokens": 32607472} {"current_steps": 23715, "total_steps": 40000, "loss": 1.0465, "lr": 1.7810554112961516e-05, "epoch": 0.7590743230266949, "percentage": 59.29, "elapsed_time": "13:45:03", "remaining_time": "9:26:33", "throughput": 658.83, "total_tokens": 32614368} {"current_steps": 23720, "total_steps": 40000, "loss": 0.7471, "lr": 1.7801151907542607e-05, "epoch": 0.7592343639971832, "percentage": 59.3, "elapsed_time": "13:45:04", "remaining_time": "9:26:17", "throughput": 658.95, "total_tokens": 32620976} {"current_steps": 23725, "total_steps": 40000, "loss": 0.7076, "lr": 1.7791750812276547e-05, "epoch": 0.7593944049676717, "percentage": 59.31, "elapsed_time": "13:45:06", "remaining_time": "9:26:00", "throughput": 659.06, "total_tokens": 32627872} {"current_steps": 23730, "total_steps": 40000, "loss": 0.6599, "lr": 1.778235082861309e-05, "epoch": 0.7595544459381601, "percentage": 59.33, "elapsed_time": "13:45:08", "remaining_time": "9:25:44", "throughput": 659.18, "total_tokens": 32635120} {"current_steps": 23735, "total_steps": 40000, "loss": 0.6039, "lr": 1.777295195800184e-05, "epoch": 0.7597144869086486, "percentage": 59.34, "elapsed_time": "13:45:10", "remaining_time": "9:25:27", "throughput": 659.29, "total_tokens": 32641568} {"current_steps": 23740, "total_steps": 40000, "loss": 0.7604, "lr": 1.7763554201892215e-05, "epoch": 0.759874527879137, "percentage": 59.35, "elapsed_time": "13:45:11", "remaining_time": "9:25:11", "throughput": 659.41, "total_tokens": 32648528} {"current_steps": 23745, "total_steps": 40000, "loss": 0.6221, "lr": 1.7754157561733476e-05, "epoch": 0.7600345688496255, "percentage": 59.36, "elapsed_time": "13:45:13", "remaining_time": "9:24:55", "throughput": 659.53, "total_tokens": 32655552} {"current_steps": 23750, "total_steps": 40000, "loss": 0.7472, "lr": 1.7744762038974702e-05, "epoch": 0.760194609820114, "percentage": 59.38, "elapsed_time": "13:45:15", "remaining_time": "9:24:38", "throughput": 659.65, "total_tokens": 32662704} {"current_steps": 23755, "total_steps": 40000, "loss": 0.7332, "lr": 1.7735367635064788e-05, "epoch": 0.7603546507906024, "percentage": 59.39, "elapsed_time": "13:45:17", "remaining_time": "9:24:22", "throughput": 659.76, "total_tokens": 32669536} {"current_steps": 23760, "total_steps": 40000, "loss": 0.7557, "lr": 1.7725974351452474e-05, "epoch": 0.7605146917610909, "percentage": 59.4, "elapsed_time": "13:45:18", "remaining_time": "9:24:06", "throughput": 659.88, "total_tokens": 32676304} {"current_steps": 23765, "total_steps": 40000, "loss": 0.8703, "lr": 1.771658218958634e-05, "epoch": 0.7606747327315793, "percentage": 59.41, "elapsed_time": "13:45:20", "remaining_time": "9:23:49", "throughput": 660.0, "total_tokens": 32683296} {"current_steps": 23770, "total_steps": 40000, "loss": 0.7382, "lr": 1.770719115091475e-05, "epoch": 0.7608347737020678, "percentage": 59.42, "elapsed_time": "13:45:22", "remaining_time": "9:23:33", "throughput": 660.11, "total_tokens": 32690352} {"current_steps": 23775, "total_steps": 40000, "loss": 0.8512, "lr": 1.7697801236885935e-05, "epoch": 0.7609948146725561, "percentage": 59.44, "elapsed_time": "13:45:23", "remaining_time": "9:23:17", "throughput": 660.24, "total_tokens": 32697504} {"current_steps": 23780, "total_steps": 40000, "loss": 0.7442, "lr": 1.7688412448947944e-05, "epoch": 0.7611548556430446, "percentage": 59.45, "elapsed_time": "13:45:25", "remaining_time": "9:23:00", "throughput": 660.35, "total_tokens": 32704272} {"current_steps": 23785, "total_steps": 40000, "loss": 0.7337, "lr": 1.767902478854862e-05, "epoch": 0.761314896613533, "percentage": 59.46, "elapsed_time": "13:45:27", "remaining_time": "9:22:44", "throughput": 660.48, "total_tokens": 32711808} {"current_steps": 23790, "total_steps": 40000, "loss": 0.7129, "lr": 1.766963825713569e-05, "epoch": 0.7614749375840215, "percentage": 59.48, "elapsed_time": "13:45:29", "remaining_time": "9:22:28", "throughput": 660.59, "total_tokens": 32718512} {"current_steps": 23795, "total_steps": 40000, "loss": 0.725, "lr": 1.766025285615665e-05, "epoch": 0.7616349785545099, "percentage": 59.49, "elapsed_time": "13:45:30", "remaining_time": "9:22:11", "throughput": 660.71, "total_tokens": 32725360} {"current_steps": 23800, "total_steps": 40000, "loss": 0.7451, "lr": 1.7650868587058854e-05, "epoch": 0.7617950195249984, "percentage": 59.5, "elapsed_time": "13:45:32", "remaining_time": "9:21:55", "throughput": 660.82, "total_tokens": 32732288} {"current_steps": 23800, "total_steps": 40000, "eval_loss": 0.7381670475006104, "epoch": 0.7617950195249984, "percentage": 59.5, "elapsed_time": "13:51:20", "remaining_time": "9:25:52", "throughput": 656.21, "total_tokens": 32732288} {"current_steps": 23805, "total_steps": 40000, "loss": 0.8102, "lr": 1.7641485451289484e-05, "epoch": 0.7619550604954869, "percentage": 59.51, "elapsed_time": "13:51:24", "remaining_time": "9:25:37", "throughput": 656.31, "total_tokens": 32739216} {"current_steps": 23810, "total_steps": 40000, "loss": 1.0242, "lr": 1.7632103450295534e-05, "epoch": 0.7621151014659753, "percentage": 59.52, "elapsed_time": "13:51:25", "remaining_time": "9:25:20", "throughput": 656.43, "total_tokens": 32746448} {"current_steps": 23815, "total_steps": 40000, "loss": 0.8671, "lr": 1.762272258552381e-05, "epoch": 0.7622751424364638, "percentage": 59.54, "elapsed_time": "13:51:27", "remaining_time": "9:25:04", "throughput": 656.54, "total_tokens": 32753344} {"current_steps": 23820, "total_steps": 40000, "loss": 0.817, "lr": 1.7613342858420988e-05, "epoch": 0.7624351834069522, "percentage": 59.55, "elapsed_time": "13:51:29", "remaining_time": "9:24:47", "throughput": 656.66, "total_tokens": 32760096} {"current_steps": 23825, "total_steps": 40000, "loss": 0.6632, "lr": 1.760396427043351e-05, "epoch": 0.7625952243774407, "percentage": 59.56, "elapsed_time": "13:51:31", "remaining_time": "9:24:31", "throughput": 656.77, "total_tokens": 32766912} {"current_steps": 23830, "total_steps": 40000, "loss": 0.6351, "lr": 1.7594586823007696e-05, "epoch": 0.762755265347929, "percentage": 59.58, "elapsed_time": "13:51:32", "remaining_time": "9:24:15", "throughput": 656.88, "total_tokens": 32773376} {"current_steps": 23835, "total_steps": 40000, "loss": 1.0612, "lr": 1.7585210517589646e-05, "epoch": 0.7629153063184175, "percentage": 59.59, "elapsed_time": "13:51:34", "remaining_time": "9:23:58", "throughput": 657.0, "total_tokens": 32780560} {"current_steps": 23840, "total_steps": 40000, "loss": 0.6985, "lr": 1.7575835355625314e-05, "epoch": 0.7630753472889059, "percentage": 59.6, "elapsed_time": "13:51:36", "remaining_time": "9:23:42", "throughput": 657.12, "total_tokens": 32787904} {"current_steps": 23845, "total_steps": 40000, "loss": 0.8118, "lr": 1.756646133856048e-05, "epoch": 0.7632353882593944, "percentage": 59.61, "elapsed_time": "13:51:37", "remaining_time": "9:23:25", "throughput": 657.24, "total_tokens": 32794928} {"current_steps": 23850, "total_steps": 40000, "loss": 0.768, "lr": 1.7557088467840714e-05, "epoch": 0.7633954292298829, "percentage": 59.62, "elapsed_time": "13:51:39", "remaining_time": "9:23:09", "throughput": 657.36, "total_tokens": 32802208} {"current_steps": 23855, "total_steps": 40000, "loss": 0.635, "lr": 1.7547716744911438e-05, "epoch": 0.7635554702003713, "percentage": 59.64, "elapsed_time": "13:51:41", "remaining_time": "9:22:53", "throughput": 657.48, "total_tokens": 32809040} {"current_steps": 23860, "total_steps": 40000, "loss": 0.7127, "lr": 1.7538346171217902e-05, "epoch": 0.7637155111708598, "percentage": 59.65, "elapsed_time": "13:51:43", "remaining_time": "9:22:36", "throughput": 657.59, "total_tokens": 32815904} {"current_steps": 23865, "total_steps": 40000, "loss": 0.6677, "lr": 1.7528976748205146e-05, "epoch": 0.7638755521413482, "percentage": 59.66, "elapsed_time": "13:51:44", "remaining_time": "9:22:20", "throughput": 657.71, "total_tokens": 32822800} {"current_steps": 23870, "total_steps": 40000, "loss": 0.614, "lr": 1.751960847731807e-05, "epoch": 0.7640355931118367, "percentage": 59.67, "elapsed_time": "13:51:46", "remaining_time": "9:22:04", "throughput": 657.82, "total_tokens": 32829488} {"current_steps": 23875, "total_steps": 40000, "loss": 0.7995, "lr": 1.7510241360001362e-05, "epoch": 0.764195634082325, "percentage": 59.69, "elapsed_time": "13:51:48", "remaining_time": "9:21:47", "throughput": 657.93, "total_tokens": 32836112} {"current_steps": 23880, "total_steps": 40000, "loss": 0.6754, "lr": 1.7500875397699562e-05, "epoch": 0.7643556750528135, "percentage": 59.7, "elapsed_time": "13:51:50", "remaining_time": "9:21:31", "throughput": 658.04, "total_tokens": 32843008} {"current_steps": 23885, "total_steps": 40000, "loss": 0.5883, "lr": 1.7491510591857015e-05, "epoch": 0.7645157160233019, "percentage": 59.71, "elapsed_time": "13:51:51", "remaining_time": "9:21:15", "throughput": 658.16, "total_tokens": 32850128} {"current_steps": 23890, "total_steps": 40000, "loss": 0.7906, "lr": 1.7482146943917896e-05, "epoch": 0.7646757569937904, "percentage": 59.72, "elapsed_time": "13:51:53", "remaining_time": "9:20:58", "throughput": 658.29, "total_tokens": 32857488} {"current_steps": 23895, "total_steps": 40000, "loss": 0.7388, "lr": 1.7472784455326185e-05, "epoch": 0.7648357979642788, "percentage": 59.74, "elapsed_time": "13:51:55", "remaining_time": "9:20:42", "throughput": 658.4, "total_tokens": 32864288} {"current_steps": 23900, "total_steps": 40000, "loss": 0.5771, "lr": 1.746342312752572e-05, "epoch": 0.7649958389347673, "percentage": 59.75, "elapsed_time": "13:51:57", "remaining_time": "9:20:26", "throughput": 658.52, "total_tokens": 32871344} {"current_steps": 23905, "total_steps": 40000, "loss": 0.5787, "lr": 1.74540629619601e-05, "epoch": 0.7651558799052558, "percentage": 59.76, "elapsed_time": "13:51:58", "remaining_time": "9:20:09", "throughput": 658.63, "total_tokens": 32878256} {"current_steps": 23910, "total_steps": 40000, "loss": 1.0212, "lr": 1.7444703960072815e-05, "epoch": 0.7653159208757442, "percentage": 59.77, "elapsed_time": "13:52:00", "remaining_time": "9:19:53", "throughput": 658.74, "total_tokens": 32884896} {"current_steps": 23915, "total_steps": 40000, "loss": 0.9453, "lr": 1.7435346123307118e-05, "epoch": 0.7654759618462327, "percentage": 59.79, "elapsed_time": "13:52:02", "remaining_time": "9:19:37", "throughput": 658.86, "total_tokens": 32891632} {"current_steps": 23920, "total_steps": 40000, "loss": 0.5847, "lr": 1.742598945310611e-05, "epoch": 0.7656360028167211, "percentage": 59.8, "elapsed_time": "13:52:03", "remaining_time": "9:19:20", "throughput": 658.97, "total_tokens": 32898496} {"current_steps": 23925, "total_steps": 40000, "loss": 0.6326, "lr": 1.741663395091272e-05, "epoch": 0.7657960437872096, "percentage": 59.81, "elapsed_time": "13:52:05", "remaining_time": "9:19:04", "throughput": 659.08, "total_tokens": 32905024} {"current_steps": 23930, "total_steps": 40000, "loss": 0.9189, "lr": 1.7407279618169657e-05, "epoch": 0.7659560847576979, "percentage": 59.82, "elapsed_time": "13:52:07", "remaining_time": "9:18:48", "throughput": 659.19, "total_tokens": 32911712} {"current_steps": 23935, "total_steps": 40000, "loss": 0.8438, "lr": 1.73979264563195e-05, "epoch": 0.7661161257281864, "percentage": 59.84, "elapsed_time": "13:52:09", "remaining_time": "9:18:32", "throughput": 659.3, "total_tokens": 32918368} {"current_steps": 23940, "total_steps": 40000, "loss": 0.6991, "lr": 1.7388574466804625e-05, "epoch": 0.7662761666986748, "percentage": 59.85, "elapsed_time": "13:52:10", "remaining_time": "9:18:15", "throughput": 659.42, "total_tokens": 32925248} {"current_steps": 23945, "total_steps": 40000, "loss": 0.5932, "lr": 1.7379223651067207e-05, "epoch": 0.7664362076691633, "percentage": 59.86, "elapsed_time": "13:52:12", "remaining_time": "9:17:59", "throughput": 659.53, "total_tokens": 32932048} {"current_steps": 23950, "total_steps": 40000, "loss": 0.879, "lr": 1.736987401054928e-05, "epoch": 0.7665962486396517, "percentage": 59.88, "elapsed_time": "13:52:14", "remaining_time": "9:17:43", "throughput": 659.65, "total_tokens": 32939040} {"current_steps": 23955, "total_steps": 40000, "loss": 0.648, "lr": 1.736052554669266e-05, "epoch": 0.7667562896101402, "percentage": 59.89, "elapsed_time": "13:52:16", "remaining_time": "9:17:27", "throughput": 659.76, "total_tokens": 32945744} {"current_steps": 23960, "total_steps": 40000, "loss": 0.6987, "lr": 1.7351178260939007e-05, "epoch": 0.7669163305806287, "percentage": 59.9, "elapsed_time": "13:52:17", "remaining_time": "9:17:10", "throughput": 659.87, "total_tokens": 32952560} {"current_steps": 23965, "total_steps": 40000, "loss": 0.6813, "lr": 1.7341832154729794e-05, "epoch": 0.7670763715511171, "percentage": 59.91, "elapsed_time": "13:52:19", "remaining_time": "9:16:54", "throughput": 659.99, "total_tokens": 32959472} {"current_steps": 23970, "total_steps": 40000, "loss": 0.6123, "lr": 1.7332487229506286e-05, "epoch": 0.7672364125216056, "percentage": 59.92, "elapsed_time": "13:52:21", "remaining_time": "9:16:38", "throughput": 660.11, "total_tokens": 32966672} {"current_steps": 23975, "total_steps": 40000, "loss": 0.9244, "lr": 1.732314348670961e-05, "epoch": 0.767396453492094, "percentage": 59.94, "elapsed_time": "13:52:23", "remaining_time": "9:16:22", "throughput": 660.22, "total_tokens": 32973536} {"current_steps": 23980, "total_steps": 40000, "loss": 0.5894, "lr": 1.7313800927780686e-05, "epoch": 0.7675564944625825, "percentage": 59.95, "elapsed_time": "13:52:24", "remaining_time": "9:16:05", "throughput": 660.33, "total_tokens": 32980144} {"current_steps": 23985, "total_steps": 40000, "loss": 0.913, "lr": 1.7304459554160245e-05, "epoch": 0.7677165354330708, "percentage": 59.96, "elapsed_time": "13:52:26", "remaining_time": "9:15:49", "throughput": 660.45, "total_tokens": 32987264} {"current_steps": 23990, "total_steps": 40000, "loss": 0.6082, "lr": 1.7295119367288853e-05, "epoch": 0.7678765764035593, "percentage": 59.98, "elapsed_time": "13:52:28", "remaining_time": "9:15:33", "throughput": 660.56, "total_tokens": 32994032} {"current_steps": 23995, "total_steps": 40000, "loss": 0.832, "lr": 1.728578036860688e-05, "epoch": 0.7680366173740477, "percentage": 59.99, "elapsed_time": "13:52:30", "remaining_time": "9:15:17", "throughput": 660.68, "total_tokens": 33000768} {"current_steps": 24000, "total_steps": 40000, "loss": 0.7342, "lr": 1.7276442559554513e-05, "epoch": 0.7681966583445362, "percentage": 60.0, "elapsed_time": "13:52:31", "remaining_time": "9:15:01", "throughput": 660.79, "total_tokens": 33007504} {"current_steps": 24000, "total_steps": 40000, "eval_loss": 0.7381069660186768, "epoch": 0.7681966583445362, "percentage": 60.0, "elapsed_time": "13:58:19", "remaining_time": "9:18:53", "throughput": 656.22, "total_tokens": 33007504} {"current_steps": 24005, "total_steps": 40000, "loss": 0.6774, "lr": 1.726710594157177e-05, "epoch": 0.7683566993150246, "percentage": 60.01, "elapsed_time": "13:58:22", "remaining_time": "9:18:37", "throughput": 656.31, "total_tokens": 33014096} {"current_steps": 24010, "total_steps": 40000, "loss": 0.6334, "lr": 1.725777051609846e-05, "epoch": 0.7685167402855131, "percentage": 60.02, "elapsed_time": "13:58:24", "remaining_time": "9:18:21", "throughput": 656.42, "total_tokens": 33020880} {"current_steps": 24015, "total_steps": 40000, "loss": 0.7454, "lr": 1.7248436284574228e-05, "epoch": 0.7686767812560016, "percentage": 60.04, "elapsed_time": "13:58:26", "remaining_time": "9:18:05", "throughput": 656.53, "total_tokens": 33027696} {"current_steps": 24020, "total_steps": 40000, "loss": 0.6475, "lr": 1.723910324843855e-05, "epoch": 0.76883682222649, "percentage": 60.05, "elapsed_time": "13:58:28", "remaining_time": "9:17:48", "throughput": 656.65, "total_tokens": 33034768} {"current_steps": 24025, "total_steps": 40000, "loss": 0.8756, "lr": 1.722977140913067e-05, "epoch": 0.7689968631969785, "percentage": 60.06, "elapsed_time": "13:58:29", "remaining_time": "9:17:32", "throughput": 656.77, "total_tokens": 33041808} {"current_steps": 24030, "total_steps": 40000, "loss": 0.8666, "lr": 1.7220440768089688e-05, "epoch": 0.7691569041674668, "percentage": 60.08, "elapsed_time": "13:58:31", "remaining_time": "9:17:16", "throughput": 656.88, "total_tokens": 33048448} {"current_steps": 24035, "total_steps": 40000, "loss": 0.5671, "lr": 1.7211111326754505e-05, "epoch": 0.7693169451379553, "percentage": 60.09, "elapsed_time": "13:58:33", "remaining_time": "9:17:00", "throughput": 656.99, "total_tokens": 33055536} {"current_steps": 24040, "total_steps": 40000, "loss": 0.7576, "lr": 1.720178308656383e-05, "epoch": 0.7694769861084437, "percentage": 60.1, "elapsed_time": "13:58:35", "remaining_time": "9:16:43", "throughput": 657.1, "total_tokens": 33062032} {"current_steps": 24045, "total_steps": 40000, "loss": 0.4908, "lr": 1.719245604895621e-05, "epoch": 0.7696370270789322, "percentage": 60.11, "elapsed_time": "13:58:36", "remaining_time": "9:16:27", "throughput": 657.21, "total_tokens": 33068784} {"current_steps": 24050, "total_steps": 40000, "loss": 0.6889, "lr": 1.7183130215369972e-05, "epoch": 0.7697970680494206, "percentage": 60.12, "elapsed_time": "13:58:38", "remaining_time": "9:16:11", "throughput": 657.32, "total_tokens": 33075392} {"current_steps": 24055, "total_steps": 40000, "loss": 0.6106, "lr": 1.7173805587243292e-05, "epoch": 0.7699571090199091, "percentage": 60.14, "elapsed_time": "13:58:40", "remaining_time": "9:15:55", "throughput": 657.43, "total_tokens": 33082112} {"current_steps": 24060, "total_steps": 40000, "loss": 0.8858, "lr": 1.7164482166014147e-05, "epoch": 0.7701171499903975, "percentage": 60.15, "elapsed_time": "13:58:41", "remaining_time": "9:15:38", "throughput": 657.55, "total_tokens": 33089120} {"current_steps": 24065, "total_steps": 40000, "loss": 0.741, "lr": 1.7155159953120313e-05, "epoch": 0.770277190960886, "percentage": 60.16, "elapsed_time": "13:58:43", "remaining_time": "9:15:22", "throughput": 657.66, "total_tokens": 33095920} {"current_steps": 24070, "total_steps": 40000, "loss": 0.7174, "lr": 1.714583894999941e-05, "epoch": 0.7704372319313745, "percentage": 60.17, "elapsed_time": "13:58:45", "remaining_time": "9:15:06", "throughput": 657.77, "total_tokens": 33102672} {"current_steps": 24075, "total_steps": 40000, "loss": 0.732, "lr": 1.7136519158088826e-05, "epoch": 0.7705972729018629, "percentage": 60.19, "elapsed_time": "13:58:47", "remaining_time": "9:14:50", "throughput": 657.88, "total_tokens": 33109328} {"current_steps": 24080, "total_steps": 40000, "loss": 0.6125, "lr": 1.712720057882581e-05, "epoch": 0.7707573138723514, "percentage": 60.2, "elapsed_time": "13:58:48", "remaining_time": "9:14:33", "throughput": 657.99, "total_tokens": 33116048} {"current_steps": 24085, "total_steps": 40000, "loss": 0.8099, "lr": 1.7117883213647413e-05, "epoch": 0.7709173548428397, "percentage": 60.21, "elapsed_time": "13:58:50", "remaining_time": "9:14:17", "throughput": 658.1, "total_tokens": 33122736} {"current_steps": 24090, "total_steps": 40000, "loss": 0.7179, "lr": 1.710856706399046e-05, "epoch": 0.7710773958133282, "percentage": 60.22, "elapsed_time": "13:58:52", "remaining_time": "9:14:01", "throughput": 658.22, "total_tokens": 33129776} {"current_steps": 24095, "total_steps": 40000, "loss": 0.8718, "lr": 1.7099252131291648e-05, "epoch": 0.7712374367838166, "percentage": 60.24, "elapsed_time": "13:58:54", "remaining_time": "9:13:45", "throughput": 658.34, "total_tokens": 33136816} {"current_steps": 24100, "total_steps": 40000, "loss": 0.8011, "lr": 1.708993841698744e-05, "epoch": 0.7713974777543051, "percentage": 60.25, "elapsed_time": "13:58:55", "remaining_time": "9:13:29", "throughput": 658.44, "total_tokens": 33143376} {"current_steps": 24105, "total_steps": 40000, "loss": 0.9433, "lr": 1.7080625922514132e-05, "epoch": 0.7715575187247935, "percentage": 60.26, "elapsed_time": "13:58:57", "remaining_time": "9:13:12", "throughput": 658.56, "total_tokens": 33150256} {"current_steps": 24110, "total_steps": 40000, "loss": 0.6293, "lr": 1.7071314649307836e-05, "epoch": 0.771717559695282, "percentage": 60.27, "elapsed_time": "13:58:59", "remaining_time": "9:12:56", "throughput": 658.67, "total_tokens": 33156816} {"current_steps": 24115, "total_steps": 40000, "loss": 0.5935, "lr": 1.7062004598804448e-05, "epoch": 0.7718776006657705, "percentage": 60.29, "elapsed_time": "13:59:01", "remaining_time": "9:12:40", "throughput": 658.78, "total_tokens": 33163920} {"current_steps": 24120, "total_steps": 40000, "loss": 0.7174, "lr": 1.7052695772439702e-05, "epoch": 0.7720376416362589, "percentage": 60.3, "elapsed_time": "13:59:02", "remaining_time": "9:12:24", "throughput": 658.9, "total_tokens": 33170928} {"current_steps": 24125, "total_steps": 40000, "loss": 0.674, "lr": 1.7043388171649154e-05, "epoch": 0.7721976826067474, "percentage": 60.31, "elapsed_time": "13:59:04", "remaining_time": "9:12:08", "throughput": 659.01, "total_tokens": 33177712} {"current_steps": 24130, "total_steps": 40000, "loss": 0.6646, "lr": 1.7034081797868127e-05, "epoch": 0.7723577235772358, "percentage": 60.32, "elapsed_time": "13:59:06", "remaining_time": "9:11:52", "throughput": 659.14, "total_tokens": 33185344} {"current_steps": 24135, "total_steps": 40000, "loss": 0.7331, "lr": 1.70247766525318e-05, "epoch": 0.7725177645477243, "percentage": 60.34, "elapsed_time": "13:59:08", "remaining_time": "9:11:35", "throughput": 659.26, "total_tokens": 33192400} {"current_steps": 24140, "total_steps": 40000, "loss": 0.9374, "lr": 1.701547273707514e-05, "epoch": 0.7726778055182126, "percentage": 60.35, "elapsed_time": "13:59:09", "remaining_time": "9:11:19", "throughput": 659.38, "total_tokens": 33199392} {"current_steps": 24145, "total_steps": 40000, "loss": 0.8593, "lr": 1.7006170052932916e-05, "epoch": 0.7728378464887011, "percentage": 60.36, "elapsed_time": "13:59:11", "remaining_time": "9:11:03", "throughput": 659.49, "total_tokens": 33206512} {"current_steps": 24150, "total_steps": 40000, "loss": 0.7882, "lr": 1.6996868601539735e-05, "epoch": 0.7729978874591895, "percentage": 60.38, "elapsed_time": "13:59:13", "remaining_time": "9:10:47", "throughput": 659.6, "total_tokens": 33213104} {"current_steps": 24155, "total_steps": 40000, "loss": 0.6954, "lr": 1.6987568384329977e-05, "epoch": 0.773157928429678, "percentage": 60.39, "elapsed_time": "13:59:14", "remaining_time": "9:10:31", "throughput": 659.72, "total_tokens": 33220176} {"current_steps": 24160, "total_steps": 40000, "loss": 0.8333, "lr": 1.6978269402737866e-05, "epoch": 0.7733179694001664, "percentage": 60.4, "elapsed_time": "13:59:16", "remaining_time": "9:10:15", "throughput": 659.83, "total_tokens": 33226688} {"current_steps": 24165, "total_steps": 40000, "loss": 0.7234, "lr": 1.696897165819743e-05, "epoch": 0.7734780103706549, "percentage": 60.41, "elapsed_time": "13:59:18", "remaining_time": "9:09:59", "throughput": 659.94, "total_tokens": 33233616} {"current_steps": 24170, "total_steps": 40000, "loss": 0.7948, "lr": 1.6959675152142487e-05, "epoch": 0.7736380513411434, "percentage": 60.42, "elapsed_time": "13:59:20", "remaining_time": "9:09:43", "throughput": 660.05, "total_tokens": 33240480} {"current_steps": 24175, "total_steps": 40000, "loss": 0.6618, "lr": 1.6950379886006667e-05, "epoch": 0.7737980923116318, "percentage": 60.44, "elapsed_time": "13:59:21", "remaining_time": "9:09:27", "throughput": 660.16, "total_tokens": 33246992} {"current_steps": 24180, "total_steps": 40000, "loss": 0.7305, "lr": 1.6941085861223438e-05, "epoch": 0.7739581332821203, "percentage": 60.45, "elapsed_time": "13:59:23", "remaining_time": "9:09:10", "throughput": 660.28, "total_tokens": 33253936} {"current_steps": 24185, "total_steps": 40000, "loss": 0.5705, "lr": 1.6931793079226034e-05, "epoch": 0.7741181742526086, "percentage": 60.46, "elapsed_time": "13:59:25", "remaining_time": "9:08:54", "throughput": 660.4, "total_tokens": 33261408} {"current_steps": 24190, "total_steps": 40000, "loss": 0.5672, "lr": 1.692250154144754e-05, "epoch": 0.7742782152230971, "percentage": 60.48, "elapsed_time": "13:59:27", "remaining_time": "9:08:38", "throughput": 660.51, "total_tokens": 33267856} {"current_steps": 24195, "total_steps": 40000, "loss": 0.637, "lr": 1.6913211249320807e-05, "epoch": 0.7744382561935855, "percentage": 60.49, "elapsed_time": "13:59:28", "remaining_time": "9:08:22", "throughput": 660.62, "total_tokens": 33274912} {"current_steps": 24200, "total_steps": 40000, "loss": 0.7153, "lr": 1.6903922204278522e-05, "epoch": 0.774598297164074, "percentage": 60.5, "elapsed_time": "13:59:30", "remaining_time": "9:08:06", "throughput": 660.74, "total_tokens": 33281968} {"current_steps": 24200, "total_steps": 40000, "eval_loss": 0.7375113368034363, "epoch": 0.774598297164074, "percentage": 60.5, "elapsed_time": "14:05:18", "remaining_time": "9:11:53", "throughput": 656.21, "total_tokens": 33281968} {"current_steps": 24205, "total_steps": 40000, "loss": 0.8142, "lr": 1.6894634407753186e-05, "epoch": 0.7747583381345624, "percentage": 60.51, "elapsed_time": "14:05:21", "remaining_time": "9:11:38", "throughput": 656.3, "total_tokens": 33288800} {"current_steps": 24210, "total_steps": 40000, "loss": 0.8902, "lr": 1.6885347861177077e-05, "epoch": 0.7749183791050509, "percentage": 60.52, "elapsed_time": "14:05:23", "remaining_time": "9:11:22", "throughput": 656.42, "total_tokens": 33295984} {"current_steps": 24215, "total_steps": 40000, "loss": 0.6434, "lr": 1.6876062565982298e-05, "epoch": 0.7750784200755393, "percentage": 60.54, "elapsed_time": "14:05:25", "remaining_time": "9:11:06", "throughput": 656.53, "total_tokens": 33302560} {"current_steps": 24220, "total_steps": 40000, "loss": 0.7128, "lr": 1.6866778523600774e-05, "epoch": 0.7752384610460278, "percentage": 60.55, "elapsed_time": "14:05:26", "remaining_time": "9:10:49", "throughput": 656.64, "total_tokens": 33309312} {"current_steps": 24225, "total_steps": 40000, "loss": 0.7842, "lr": 1.6857495735464195e-05, "epoch": 0.7753985020165163, "percentage": 60.56, "elapsed_time": "14:05:28", "remaining_time": "9:10:33", "throughput": 656.75, "total_tokens": 33316032} {"current_steps": 24230, "total_steps": 40000, "loss": 0.6646, "lr": 1.6848214203004115e-05, "epoch": 0.7755585429870047, "percentage": 60.58, "elapsed_time": "14:05:30", "remaining_time": "9:10:17", "throughput": 656.86, "total_tokens": 33322752} {"current_steps": 24235, "total_steps": 40000, "loss": 0.7542, "lr": 1.6838933927651835e-05, "epoch": 0.7757185839574932, "percentage": 60.59, "elapsed_time": "14:05:32", "remaining_time": "9:10:01", "throughput": 656.98, "total_tokens": 33329808} {"current_steps": 24240, "total_steps": 40000, "loss": 0.8656, "lr": 1.6829654910838506e-05, "epoch": 0.7758786249279815, "percentage": 60.6, "elapsed_time": "14:05:33", "remaining_time": "9:09:45", "throughput": 657.09, "total_tokens": 33336880} {"current_steps": 24245, "total_steps": 40000, "loss": 0.5363, "lr": 1.6820377153995065e-05, "epoch": 0.77603866589847, "percentage": 60.61, "elapsed_time": "14:05:35", "remaining_time": "9:09:29", "throughput": 657.21, "total_tokens": 33343728} {"current_steps": 24250, "total_steps": 40000, "loss": 0.8682, "lr": 1.681110065855226e-05, "epoch": 0.7761987068689584, "percentage": 60.62, "elapsed_time": "14:05:37", "remaining_time": "9:09:13", "throughput": 657.32, "total_tokens": 33350384} {"current_steps": 24255, "total_steps": 40000, "loss": 0.6507, "lr": 1.6801825425940642e-05, "epoch": 0.7763587478394469, "percentage": 60.64, "elapsed_time": "14:05:38", "remaining_time": "9:08:56", "throughput": 657.42, "total_tokens": 33357024} {"current_steps": 24260, "total_steps": 40000, "loss": 0.5733, "lr": 1.679255145759056e-05, "epoch": 0.7765187888099353, "percentage": 60.65, "elapsed_time": "14:05:40", "remaining_time": "9:08:40", "throughput": 657.55, "total_tokens": 33364496} {"current_steps": 24265, "total_steps": 40000, "loss": 0.7122, "lr": 1.6783278754932187e-05, "epoch": 0.7766788297804238, "percentage": 60.66, "elapsed_time": "14:05:42", "remaining_time": "9:08:24", "throughput": 657.67, "total_tokens": 33371680} {"current_steps": 24270, "total_steps": 40000, "loss": 0.8238, "lr": 1.6774007319395496e-05, "epoch": 0.7768388707509122, "percentage": 60.68, "elapsed_time": "14:05:44", "remaining_time": "9:08:08", "throughput": 657.79, "total_tokens": 33378848} {"current_steps": 24275, "total_steps": 40000, "loss": 0.6702, "lr": 1.6764737152410243e-05, "epoch": 0.7769989117214007, "percentage": 60.69, "elapsed_time": "14:05:45", "remaining_time": "9:07:52", "throughput": 657.9, "total_tokens": 33385952} {"current_steps": 24280, "total_steps": 40000, "loss": 0.5647, "lr": 1.6755468255406016e-05, "epoch": 0.7771589526918892, "percentage": 60.7, "elapsed_time": "14:05:47", "remaining_time": "9:07:36", "throughput": 658.01, "total_tokens": 33392528} {"current_steps": 24285, "total_steps": 40000, "loss": 0.8436, "lr": 1.674620062981219e-05, "epoch": 0.7773189936623776, "percentage": 60.71, "elapsed_time": "14:05:49", "remaining_time": "9:07:20", "throughput": 658.13, "total_tokens": 33399488} {"current_steps": 24290, "total_steps": 40000, "loss": 0.7729, "lr": 1.6736934277057947e-05, "epoch": 0.777479034632866, "percentage": 60.72, "elapsed_time": "14:05:51", "remaining_time": "9:07:04", "throughput": 658.24, "total_tokens": 33406208} {"current_steps": 24295, "total_steps": 40000, "loss": 0.561, "lr": 1.6727669198572286e-05, "epoch": 0.7776390756033544, "percentage": 60.74, "elapsed_time": "14:05:52", "remaining_time": "9:06:48", "throughput": 658.35, "total_tokens": 33413136} {"current_steps": 24300, "total_steps": 40000, "loss": 0.9281, "lr": 1.6718405395783984e-05, "epoch": 0.7777991165738429, "percentage": 60.75, "elapsed_time": "14:05:54", "remaining_time": "9:06:32", "throughput": 658.46, "total_tokens": 33420048} {"current_steps": 24305, "total_steps": 40000, "loss": 0.5823, "lr": 1.6709142870121643e-05, "epoch": 0.7779591575443313, "percentage": 60.76, "elapsed_time": "14:05:56", "remaining_time": "9:06:15", "throughput": 658.57, "total_tokens": 33426784} {"current_steps": 24310, "total_steps": 40000, "loss": 0.7076, "lr": 1.669988162301367e-05, "epoch": 0.7781191985148198, "percentage": 60.77, "elapsed_time": "14:05:58", "remaining_time": "9:05:59", "throughput": 658.69, "total_tokens": 33433680} {"current_steps": 24315, "total_steps": 40000, "loss": 0.8928, "lr": 1.6690621655888243e-05, "epoch": 0.7782792394853082, "percentage": 60.79, "elapsed_time": "14:05:59", "remaining_time": "9:05:43", "throughput": 658.81, "total_tokens": 33441088} {"current_steps": 24320, "total_steps": 40000, "loss": 0.5658, "lr": 1.6681362970173386e-05, "epoch": 0.7784392804557967, "percentage": 60.8, "elapsed_time": "14:06:01", "remaining_time": "9:05:27", "throughput": 658.92, "total_tokens": 33447840} {"current_steps": 24325, "total_steps": 40000, "loss": 0.7164, "lr": 1.6672105567296904e-05, "epoch": 0.7785993214262851, "percentage": 60.81, "elapsed_time": "14:06:03", "remaining_time": "9:05:11", "throughput": 659.04, "total_tokens": 33454992} {"current_steps": 24330, "total_steps": 40000, "loss": 0.5439, "lr": 1.666284944868639e-05, "epoch": 0.7787593623967736, "percentage": 60.82, "elapsed_time": "14:06:05", "remaining_time": "9:04:55", "throughput": 659.15, "total_tokens": 33461840} {"current_steps": 24335, "total_steps": 40000, "loss": 0.5152, "lr": 1.665359461576927e-05, "epoch": 0.7789194033672621, "percentage": 60.84, "elapsed_time": "14:06:06", "remaining_time": "9:04:39", "throughput": 659.26, "total_tokens": 33468416} {"current_steps": 24340, "total_steps": 40000, "loss": 0.692, "lr": 1.6644341069972736e-05, "epoch": 0.7790794443377504, "percentage": 60.85, "elapsed_time": "14:06:08", "remaining_time": "9:04:23", "throughput": 659.38, "total_tokens": 33475856} {"current_steps": 24345, "total_steps": 40000, "loss": 0.6758, "lr": 1.6635088812723813e-05, "epoch": 0.7792394853082389, "percentage": 60.86, "elapsed_time": "14:06:10", "remaining_time": "9:04:07", "throughput": 659.49, "total_tokens": 33482624} {"current_steps": 24350, "total_steps": 40000, "loss": 0.8924, "lr": 1.6625837845449328e-05, "epoch": 0.7793995262787273, "percentage": 60.88, "elapsed_time": "14:06:11", "remaining_time": "9:03:51", "throughput": 659.6, "total_tokens": 33489376} {"current_steps": 24355, "total_steps": 40000, "loss": 0.5952, "lr": 1.6616588169575874e-05, "epoch": 0.7795595672492158, "percentage": 60.89, "elapsed_time": "14:06:13", "remaining_time": "9:03:35", "throughput": 659.71, "total_tokens": 33496112} {"current_steps": 24360, "total_steps": 40000, "loss": 0.6662, "lr": 1.6607339786529878e-05, "epoch": 0.7797196082197042, "percentage": 60.9, "elapsed_time": "14:06:15", "remaining_time": "9:03:19", "throughput": 659.82, "total_tokens": 33502544} {"current_steps": 24365, "total_steps": 40000, "loss": 0.9272, "lr": 1.659809269773756e-05, "epoch": 0.7798796491901927, "percentage": 60.91, "elapsed_time": "14:06:17", "remaining_time": "9:03:03", "throughput": 659.94, "total_tokens": 33510032} {"current_steps": 24370, "total_steps": 40000, "loss": 0.7281, "lr": 1.658884690462493e-05, "epoch": 0.7800396901606811, "percentage": 60.92, "elapsed_time": "14:06:18", "remaining_time": "9:02:47", "throughput": 660.05, "total_tokens": 33516768} {"current_steps": 24375, "total_steps": 40000, "loss": 0.7725, "lr": 1.6579602408617813e-05, "epoch": 0.7801997311311696, "percentage": 60.94, "elapsed_time": "14:06:20", "remaining_time": "9:02:31", "throughput": 660.16, "total_tokens": 33523520} {"current_steps": 24380, "total_steps": 40000, "loss": 0.7639, "lr": 1.657035921114181e-05, "epoch": 0.7803597721016581, "percentage": 60.95, "elapsed_time": "14:06:22", "remaining_time": "9:02:15", "throughput": 660.29, "total_tokens": 33530896} {"current_steps": 24385, "total_steps": 40000, "loss": 0.597, "lr": 1.656111731362236e-05, "epoch": 0.7805198130721465, "percentage": 60.96, "elapsed_time": "14:06:24", "remaining_time": "9:01:59", "throughput": 660.4, "total_tokens": 33538032} {"current_steps": 24390, "total_steps": 40000, "loss": 0.6391, "lr": 1.6551876717484666e-05, "epoch": 0.780679854042635, "percentage": 60.98, "elapsed_time": "14:06:25", "remaining_time": "9:01:43", "throughput": 660.51, "total_tokens": 33544768} {"current_steps": 24395, "total_steps": 40000, "loss": 0.5202, "lr": 1.6542637424153752e-05, "epoch": 0.7808398950131233, "percentage": 60.99, "elapsed_time": "14:06:27", "remaining_time": "9:01:27", "throughput": 660.63, "total_tokens": 33551760} {"current_steps": 24400, "total_steps": 40000, "loss": 0.7706, "lr": 1.6533399435054418e-05, "epoch": 0.7809999359836118, "percentage": 61.0, "elapsed_time": "14:06:29", "remaining_time": "9:01:11", "throughput": 660.74, "total_tokens": 33558736} {"current_steps": 24400, "total_steps": 40000, "eval_loss": 0.7380651831626892, "epoch": 0.7809999359836118, "percentage": 61.0, "elapsed_time": "14:12:16", "remaining_time": "9:04:53", "throughput": 656.26, "total_tokens": 33558736} {"current_steps": 24405, "total_steps": 40000, "loss": 0.6949, "lr": 1.6524162751611304e-05, "epoch": 0.7811599769541002, "percentage": 61.01, "elapsed_time": "14:12:20", "remaining_time": "9:04:39", "throughput": 656.33, "total_tokens": 33564992} {"current_steps": 24410, "total_steps": 40000, "loss": 0.7041, "lr": 1.6514927375248796e-05, "epoch": 0.7813200179245887, "percentage": 61.02, "elapsed_time": "14:12:21", "remaining_time": "9:04:22", "throughput": 656.44, "total_tokens": 33571600} {"current_steps": 24415, "total_steps": 40000, "loss": 0.5514, "lr": 1.6505693307391127e-05, "epoch": 0.7814800588950771, "percentage": 61.04, "elapsed_time": "14:12:23", "remaining_time": "9:04:06", "throughput": 656.55, "total_tokens": 33578384} {"current_steps": 24420, "total_steps": 40000, "loss": 0.7452, "lr": 1.6496460549462288e-05, "epoch": 0.7816400998655656, "percentage": 61.05, "elapsed_time": "14:12:25", "remaining_time": "9:03:50", "throughput": 656.66, "total_tokens": 33585152} {"current_steps": 24425, "total_steps": 40000, "loss": 0.7874, "lr": 1.6487229102886097e-05, "epoch": 0.781800140836054, "percentage": 61.06, "elapsed_time": "14:12:27", "remaining_time": "9:03:34", "throughput": 656.77, "total_tokens": 33592144} {"current_steps": 24430, "total_steps": 40000, "loss": 0.6297, "lr": 1.6477998969086155e-05, "epoch": 0.7819601818065425, "percentage": 61.08, "elapsed_time": "14:12:28", "remaining_time": "9:03:18", "throughput": 656.89, "total_tokens": 33599056} {"current_steps": 24435, "total_steps": 40000, "loss": 0.6121, "lr": 1.646877014948587e-05, "epoch": 0.782120222777031, "percentage": 61.09, "elapsed_time": "14:12:30", "remaining_time": "9:03:02", "throughput": 657.01, "total_tokens": 33606256} {"current_steps": 24440, "total_steps": 40000, "loss": 0.7181, "lr": 1.6459542645508433e-05, "epoch": 0.7822802637475194, "percentage": 61.1, "elapsed_time": "14:12:32", "remaining_time": "9:02:46", "throughput": 657.12, "total_tokens": 33613040} {"current_steps": 24445, "total_steps": 40000, "loss": 0.7159, "lr": 1.6450316458576852e-05, "epoch": 0.7824403047180079, "percentage": 61.11, "elapsed_time": "14:12:34", "remaining_time": "9:02:30", "throughput": 657.22, "total_tokens": 33619552} {"current_steps": 24450, "total_steps": 40000, "loss": 0.6913, "lr": 1.6441091590113912e-05, "epoch": 0.7826003456884962, "percentage": 61.12, "elapsed_time": "14:12:35", "remaining_time": "9:02:14", "throughput": 657.33, "total_tokens": 33626352} {"current_steps": 24455, "total_steps": 40000, "loss": 0.6855, "lr": 1.6431868041542213e-05, "epoch": 0.7827603866589847, "percentage": 61.14, "elapsed_time": "14:12:37", "remaining_time": "9:01:58", "throughput": 657.45, "total_tokens": 33633344} {"current_steps": 24460, "total_steps": 40000, "loss": 0.821, "lr": 1.6422645814284123e-05, "epoch": 0.7829204276294731, "percentage": 61.15, "elapsed_time": "14:12:39", "remaining_time": "9:01:42", "throughput": 657.56, "total_tokens": 33640288} {"current_steps": 24465, "total_steps": 40000, "loss": 0.613, "lr": 1.6413424909761846e-05, "epoch": 0.7830804685999616, "percentage": 61.16, "elapsed_time": "14:12:41", "remaining_time": "9:01:26", "throughput": 657.67, "total_tokens": 33647056} {"current_steps": 24470, "total_steps": 40000, "loss": 0.6598, "lr": 1.640420532939736e-05, "epoch": 0.78324050957045, "percentage": 61.18, "elapsed_time": "14:12:42", "remaining_time": "9:01:10", "throughput": 657.78, "total_tokens": 33653920} {"current_steps": 24475, "total_steps": 40000, "loss": 0.5437, "lr": 1.639498707461242e-05, "epoch": 0.7834005505409385, "percentage": 61.19, "elapsed_time": "14:12:44", "remaining_time": "9:00:54", "throughput": 657.89, "total_tokens": 33660832} {"current_steps": 24480, "total_steps": 40000, "loss": 0.5659, "lr": 1.6385770146828614e-05, "epoch": 0.7835605915114269, "percentage": 61.2, "elapsed_time": "14:12:46", "remaining_time": "9:00:38", "throughput": 658.01, "total_tokens": 33667776} {"current_steps": 24485, "total_steps": 40000, "loss": 0.9136, "lr": 1.637655454746731e-05, "epoch": 0.7837206324819154, "percentage": 61.21, "elapsed_time": "14:12:48", "remaining_time": "9:00:22", "throughput": 658.13, "total_tokens": 33675280} {"current_steps": 24490, "total_steps": 40000, "loss": 0.6699, "lr": 1.6367340277949658e-05, "epoch": 0.7838806734524039, "percentage": 61.22, "elapsed_time": "14:12:49", "remaining_time": "9:00:06", "throughput": 658.25, "total_tokens": 33682416} {"current_steps": 24495, "total_steps": 40000, "loss": 0.6765, "lr": 1.635812733969663e-05, "epoch": 0.7840407144228922, "percentage": 61.24, "elapsed_time": "14:12:51", "remaining_time": "8:59:50", "throughput": 658.36, "total_tokens": 33689392} {"current_steps": 24500, "total_steps": 40000, "loss": 0.745, "lr": 1.634891573412896e-05, "epoch": 0.7842007553933807, "percentage": 61.25, "elapsed_time": "14:12:53", "remaining_time": "8:59:34", "throughput": 658.47, "total_tokens": 33696144} {"current_steps": 24505, "total_steps": 40000, "loss": 0.5656, "lr": 1.6339705462667196e-05, "epoch": 0.7843607963638691, "percentage": 61.26, "elapsed_time": "14:12:54", "remaining_time": "8:59:18", "throughput": 658.58, "total_tokens": 33702624} {"current_steps": 24510, "total_steps": 40000, "loss": 0.687, "lr": 1.633049652673169e-05, "epoch": 0.7845208373343576, "percentage": 61.27, "elapsed_time": "14:12:56", "remaining_time": "8:59:02", "throughput": 658.68, "total_tokens": 33709280} {"current_steps": 24515, "total_steps": 40000, "loss": 0.6831, "lr": 1.632128892774256e-05, "epoch": 0.784680878304846, "percentage": 61.29, "elapsed_time": "14:12:58", "remaining_time": "8:58:47", "throughput": 658.8, "total_tokens": 33716144} {"current_steps": 24520, "total_steps": 40000, "loss": 0.5818, "lr": 1.6312082667119737e-05, "epoch": 0.7848409192753345, "percentage": 61.3, "elapsed_time": "14:13:00", "remaining_time": "8:58:31", "throughput": 658.91, "total_tokens": 33722944} {"current_steps": 24525, "total_steps": 40000, "loss": 0.5649, "lr": 1.630287774628296e-05, "epoch": 0.7850009602458229, "percentage": 61.31, "elapsed_time": "14:13:01", "remaining_time": "8:58:15", "throughput": 659.02, "total_tokens": 33729760} {"current_steps": 24530, "total_steps": 40000, "loss": 0.6247, "lr": 1.6293674166651718e-05, "epoch": 0.7851610012163114, "percentage": 61.32, "elapsed_time": "14:13:03", "remaining_time": "8:57:59", "throughput": 659.14, "total_tokens": 33737008} {"current_steps": 24535, "total_steps": 40000, "loss": 0.5206, "lr": 1.6284471929645338e-05, "epoch": 0.7853210421867998, "percentage": 61.34, "elapsed_time": "14:13:05", "remaining_time": "8:57:43", "throughput": 659.25, "total_tokens": 33743968} {"current_steps": 24540, "total_steps": 40000, "loss": 0.764, "lr": 1.627527103668291e-05, "epoch": 0.7854810831572883, "percentage": 61.35, "elapsed_time": "14:13:07", "remaining_time": "8:57:27", "throughput": 659.36, "total_tokens": 33750864} {"current_steps": 24545, "total_steps": 40000, "loss": 0.9574, "lr": 1.6266071489183327e-05, "epoch": 0.7856411241277768, "percentage": 61.36, "elapsed_time": "14:13:08", "remaining_time": "8:57:11", "throughput": 659.47, "total_tokens": 33757264} {"current_steps": 24550, "total_steps": 40000, "loss": 0.6516, "lr": 1.6256873288565283e-05, "epoch": 0.7858011650982651, "percentage": 61.38, "elapsed_time": "14:13:10", "remaining_time": "8:56:55", "throughput": 659.57, "total_tokens": 33763904} {"current_steps": 24555, "total_steps": 40000, "loss": 0.7008, "lr": 1.6247676436247245e-05, "epoch": 0.7859612060687536, "percentage": 61.39, "elapsed_time": "14:13:12", "remaining_time": "8:56:39", "throughput": 659.68, "total_tokens": 33770464} {"current_steps": 24560, "total_steps": 40000, "loss": 0.7936, "lr": 1.6238480933647486e-05, "epoch": 0.786121247039242, "percentage": 61.4, "elapsed_time": "14:13:13", "remaining_time": "8:56:23", "throughput": 659.79, "total_tokens": 33777168} {"current_steps": 24565, "total_steps": 40000, "loss": 0.5416, "lr": 1.6229286782184083e-05, "epoch": 0.7862812880097305, "percentage": 61.41, "elapsed_time": "14:13:15", "remaining_time": "8:56:07", "throughput": 659.9, "total_tokens": 33783808} {"current_steps": 24570, "total_steps": 40000, "loss": 0.6462, "lr": 1.622009398327487e-05, "epoch": 0.7864413289802189, "percentage": 61.42, "elapsed_time": "14:13:17", "remaining_time": "8:55:52", "throughput": 660.0, "total_tokens": 33790272} {"current_steps": 24575, "total_steps": 40000, "loss": 0.6938, "lr": 1.6210902538337502e-05, "epoch": 0.7866013699507074, "percentage": 61.44, "elapsed_time": "14:13:19", "remaining_time": "8:55:36", "throughput": 660.12, "total_tokens": 33797632} {"current_steps": 24580, "total_steps": 40000, "loss": 0.6734, "lr": 1.6201712448789413e-05, "epoch": 0.7867614109211958, "percentage": 61.45, "elapsed_time": "14:13:20", "remaining_time": "8:55:20", "throughput": 660.23, "total_tokens": 33804176} {"current_steps": 24585, "total_steps": 40000, "loss": 0.7667, "lr": 1.6192523716047827e-05, "epoch": 0.7869214518916843, "percentage": 61.46, "elapsed_time": "14:13:22", "remaining_time": "8:55:04", "throughput": 660.33, "total_tokens": 33810576} {"current_steps": 24590, "total_steps": 40000, "loss": 0.8101, "lr": 1.6183336341529776e-05, "epoch": 0.7870814928621728, "percentage": 61.48, "elapsed_time": "14:13:24", "remaining_time": "8:54:48", "throughput": 660.44, "total_tokens": 33817280} {"current_steps": 24595, "total_steps": 40000, "loss": 0.6997, "lr": 1.6174150326652047e-05, "epoch": 0.7872415338326612, "percentage": 61.49, "elapsed_time": "14:13:26", "remaining_time": "8:54:32", "throughput": 660.55, "total_tokens": 33824144} {"current_steps": 24600, "total_steps": 40000, "loss": 0.7155, "lr": 1.6164965672831256e-05, "epoch": 0.7874015748031497, "percentage": 61.5, "elapsed_time": "14:13:27", "remaining_time": "8:54:16", "throughput": 660.66, "total_tokens": 33830832} {"current_steps": 24600, "total_steps": 40000, "eval_loss": 0.737598180770874, "epoch": 0.7874015748031497, "percentage": 61.5, "elapsed_time": "14:19:16", "remaining_time": "8:57:55", "throughput": 656.19, "total_tokens": 33830832} {"current_steps": 24605, "total_steps": 40000, "loss": 0.5235, "lr": 1.6155782381483784e-05, "epoch": 0.787561615773638, "percentage": 61.51, "elapsed_time": "14:19:19", "remaining_time": "8:57:40", "throughput": 656.28, "total_tokens": 33837600} {"current_steps": 24610, "total_steps": 40000, "loss": 0.7377, "lr": 1.6146600454025813e-05, "epoch": 0.7877216567441265, "percentage": 61.52, "elapsed_time": "14:19:21", "remaining_time": "8:57:24", "throughput": 656.4, "total_tokens": 33844992} {"current_steps": 24615, "total_steps": 40000, "loss": 0.6364, "lr": 1.6137419891873317e-05, "epoch": 0.7878816977146149, "percentage": 61.54, "elapsed_time": "14:19:23", "remaining_time": "8:57:08", "throughput": 656.52, "total_tokens": 33852160} {"current_steps": 24620, "total_steps": 40000, "loss": 0.5209, "lr": 1.6128240696442038e-05, "epoch": 0.7880417386851034, "percentage": 61.55, "elapsed_time": "14:19:24", "remaining_time": "8:56:52", "throughput": 656.62, "total_tokens": 33858688} {"current_steps": 24625, "total_steps": 40000, "loss": 0.9236, "lr": 1.611906286914753e-05, "epoch": 0.7882017796555918, "percentage": 61.56, "elapsed_time": "14:19:26", "remaining_time": "8:56:36", "throughput": 656.74, "total_tokens": 33865792} {"current_steps": 24630, "total_steps": 40000, "loss": 0.777, "lr": 1.6109886411405144e-05, "epoch": 0.7883618206260803, "percentage": 61.58, "elapsed_time": "14:19:28", "remaining_time": "8:56:20", "throughput": 656.86, "total_tokens": 33872960} {"current_steps": 24635, "total_steps": 40000, "loss": 0.7209, "lr": 1.6100711324629985e-05, "epoch": 0.7885218615965687, "percentage": 61.59, "elapsed_time": "14:19:30", "remaining_time": "8:56:04", "throughput": 656.97, "total_tokens": 33879808} {"current_steps": 24640, "total_steps": 40000, "loss": 0.8014, "lr": 1.609153761023698e-05, "epoch": 0.7886819025670572, "percentage": 61.6, "elapsed_time": "14:19:31", "remaining_time": "8:55:48", "throughput": 657.08, "total_tokens": 33886560} {"current_steps": 24645, "total_steps": 40000, "loss": 0.8707, "lr": 1.608236526964083e-05, "epoch": 0.7888419435375457, "percentage": 61.61, "elapsed_time": "14:19:33", "remaining_time": "8:55:32", "throughput": 657.18, "total_tokens": 33893232} {"current_steps": 24650, "total_steps": 40000, "loss": 0.871, "lr": 1.607319430425601e-05, "epoch": 0.789001984508034, "percentage": 61.62, "elapsed_time": "14:19:35", "remaining_time": "8:55:16", "throughput": 657.3, "total_tokens": 33900304} {"current_steps": 24655, "total_steps": 40000, "loss": 0.5844, "lr": 1.606402471549682e-05, "epoch": 0.7891620254785225, "percentage": 61.64, "elapsed_time": "14:19:36", "remaining_time": "8:55:00", "throughput": 657.41, "total_tokens": 33907296} {"current_steps": 24660, "total_steps": 40000, "loss": 0.7395, "lr": 1.6054856504777312e-05, "epoch": 0.7893220664490109, "percentage": 61.65, "elapsed_time": "14:19:38", "remaining_time": "8:54:45", "throughput": 657.52, "total_tokens": 33914032} {"current_steps": 24665, "total_steps": 40000, "loss": 0.5936, "lr": 1.6045689673511334e-05, "epoch": 0.7894821074194994, "percentage": 61.66, "elapsed_time": "14:19:40", "remaining_time": "8:54:29", "throughput": 657.63, "total_tokens": 33920608} {"current_steps": 24670, "total_steps": 40000, "loss": 0.857, "lr": 1.6036524223112548e-05, "epoch": 0.7896421483899878, "percentage": 61.68, "elapsed_time": "14:19:42", "remaining_time": "8:54:13", "throughput": 657.73, "total_tokens": 33927248} {"current_steps": 24675, "total_steps": 40000, "loss": 0.6997, "lr": 1.602736015499436e-05, "epoch": 0.7898021893604763, "percentage": 61.69, "elapsed_time": "14:19:43", "remaining_time": "8:53:57", "throughput": 657.84, "total_tokens": 33934016} {"current_steps": 24680, "total_steps": 40000, "loss": 0.6724, "lr": 1.601819747057e-05, "epoch": 0.7899622303309647, "percentage": 61.7, "elapsed_time": "14:19:45", "remaining_time": "8:53:41", "throughput": 657.95, "total_tokens": 33940720} {"current_steps": 24685, "total_steps": 40000, "loss": 0.8434, "lr": 1.6009036171252465e-05, "epoch": 0.7901222713014532, "percentage": 61.71, "elapsed_time": "14:19:47", "remaining_time": "8:53:25", "throughput": 658.06, "total_tokens": 33947424} {"current_steps": 24690, "total_steps": 40000, "loss": 0.6539, "lr": 1.599987625845453e-05, "epoch": 0.7902823122719416, "percentage": 61.72, "elapsed_time": "14:19:49", "remaining_time": "8:53:09", "throughput": 658.16, "total_tokens": 33954128} {"current_steps": 24695, "total_steps": 40000, "loss": 0.8456, "lr": 1.599071773358879e-05, "epoch": 0.7904423532424301, "percentage": 61.74, "elapsed_time": "14:19:50", "remaining_time": "8:52:54", "throughput": 658.28, "total_tokens": 33961376} {"current_steps": 24700, "total_steps": 40000, "loss": 0.6713, "lr": 1.598156059806758e-05, "epoch": 0.7906023942129186, "percentage": 61.75, "elapsed_time": "14:19:52", "remaining_time": "8:52:38", "throughput": 658.4, "total_tokens": 33968576} {"current_steps": 24705, "total_steps": 40000, "loss": 0.7881, "lr": 1.5972404853303062e-05, "epoch": 0.7907624351834069, "percentage": 61.76, "elapsed_time": "14:19:54", "remaining_time": "8:52:22", "throughput": 658.51, "total_tokens": 33975392} {"current_steps": 24710, "total_steps": 40000, "loss": 0.7913, "lr": 1.5963250500707172e-05, "epoch": 0.7909224761538954, "percentage": 61.78, "elapsed_time": "14:19:56", "remaining_time": "8:52:06", "throughput": 658.62, "total_tokens": 33982112} {"current_steps": 24715, "total_steps": 40000, "loss": 0.6929, "lr": 1.5954097541691612e-05, "epoch": 0.7910825171243838, "percentage": 61.79, "elapsed_time": "14:19:57", "remaining_time": "8:51:50", "throughput": 658.73, "total_tokens": 33989040} {"current_steps": 24720, "total_steps": 40000, "loss": 0.7943, "lr": 1.5944945977667884e-05, "epoch": 0.7912425580948723, "percentage": 61.8, "elapsed_time": "14:19:59", "remaining_time": "8:51:34", "throughput": 658.84, "total_tokens": 33995728} {"current_steps": 24725, "total_steps": 40000, "loss": 0.5947, "lr": 1.593579581004729e-05, "epoch": 0.7914025990653607, "percentage": 61.81, "elapsed_time": "14:20:01", "remaining_time": "8:51:19", "throughput": 658.95, "total_tokens": 34002736} {"current_steps": 24730, "total_steps": 40000, "loss": 0.6039, "lr": 1.592664704024088e-05, "epoch": 0.7915626400358492, "percentage": 61.82, "elapsed_time": "14:20:02", "remaining_time": "8:51:03", "throughput": 659.05, "total_tokens": 34009104} {"current_steps": 24735, "total_steps": 40000, "loss": 0.8008, "lr": 1.591749966965953e-05, "epoch": 0.7917226810063376, "percentage": 61.84, "elapsed_time": "14:20:04", "remaining_time": "8:50:47", "throughput": 659.17, "total_tokens": 34016192} {"current_steps": 24740, "total_steps": 40000, "loss": 0.5717, "lr": 1.5908353699713856e-05, "epoch": 0.7918827219768261, "percentage": 61.85, "elapsed_time": "14:20:06", "remaining_time": "8:50:31", "throughput": 659.28, "total_tokens": 34023152} {"current_steps": 24745, "total_steps": 40000, "loss": 0.7236, "lr": 1.5899209131814298e-05, "epoch": 0.7920427629473145, "percentage": 61.86, "elapsed_time": "14:20:08", "remaining_time": "8:50:15", "throughput": 659.39, "total_tokens": 34030016} {"current_steps": 24750, "total_steps": 40000, "loss": 0.5253, "lr": 1.5890065967371067e-05, "epoch": 0.792202803917803, "percentage": 61.88, "elapsed_time": "14:20:09", "remaining_time": "8:50:00", "throughput": 659.5, "total_tokens": 34036976} {"current_steps": 24755, "total_steps": 40000, "loss": 0.7372, "lr": 1.5880924207794144e-05, "epoch": 0.7923628448882915, "percentage": 61.89, "elapsed_time": "14:20:11", "remaining_time": "8:49:44", "throughput": 659.62, "total_tokens": 34044032} {"current_steps": 24760, "total_steps": 40000, "loss": 0.7866, "lr": 1.5871783854493298e-05, "epoch": 0.7925228858587798, "percentage": 61.9, "elapsed_time": "14:20:13", "remaining_time": "8:49:28", "throughput": 659.73, "total_tokens": 34050720} {"current_steps": 24765, "total_steps": 40000, "loss": 0.6339, "lr": 1.5862644908878106e-05, "epoch": 0.7926829268292683, "percentage": 61.91, "elapsed_time": "14:20:15", "remaining_time": "8:49:12", "throughput": 659.84, "total_tokens": 34057648} {"current_steps": 24770, "total_steps": 40000, "loss": 0.6824, "lr": 1.5853507372357885e-05, "epoch": 0.7928429677997567, "percentage": 61.92, "elapsed_time": "14:20:16", "remaining_time": "8:48:56", "throughput": 659.95, "total_tokens": 34064704} {"current_steps": 24775, "total_steps": 40000, "loss": 0.8082, "lr": 1.5844371246341776e-05, "epoch": 0.7930030087702452, "percentage": 61.94, "elapsed_time": "14:20:18", "remaining_time": "8:48:41", "throughput": 660.06, "total_tokens": 34071200} {"current_steps": 24780, "total_steps": 40000, "loss": 0.7154, "lr": 1.5835236532238674e-05, "epoch": 0.7931630497407336, "percentage": 61.95, "elapsed_time": "14:20:20", "remaining_time": "8:48:25", "throughput": 660.16, "total_tokens": 34077792} {"current_steps": 24785, "total_steps": 40000, "loss": 0.6623, "lr": 1.582610323145727e-05, "epoch": 0.7933230907112221, "percentage": 61.96, "elapsed_time": "14:20:22", "remaining_time": "8:48:09", "throughput": 660.27, "total_tokens": 34084432} {"current_steps": 24790, "total_steps": 40000, "loss": 0.6736, "lr": 1.5816971345406035e-05, "epoch": 0.7934831316817105, "percentage": 61.98, "elapsed_time": "14:20:23", "remaining_time": "8:47:54", "throughput": 660.38, "total_tokens": 34091232} {"current_steps": 24795, "total_steps": 40000, "loss": 0.8188, "lr": 1.5807840875493225e-05, "epoch": 0.793643172652199, "percentage": 61.99, "elapsed_time": "14:20:25", "remaining_time": "8:47:38", "throughput": 660.49, "total_tokens": 34098256} {"current_steps": 24800, "total_steps": 40000, "loss": 0.9201, "lr": 1.5798711823126854e-05, "epoch": 0.7938032136226874, "percentage": 62.0, "elapsed_time": "14:20:27", "remaining_time": "8:47:22", "throughput": 660.6, "total_tokens": 34104944} {"current_steps": 24800, "total_steps": 40000, "eval_loss": 0.7376317381858826, "epoch": 0.7938032136226874, "percentage": 62.0, "elapsed_time": "14:26:15", "remaining_time": "8:50:55", "throughput": 656.18, "total_tokens": 34104944} {"current_steps": 24805, "total_steps": 40000, "loss": 0.6794, "lr": 1.578958418971477e-05, "epoch": 0.7939632545931758, "percentage": 62.01, "elapsed_time": "14:26:19", "remaining_time": "8:50:41", "throughput": 656.26, "total_tokens": 34111952} {"current_steps": 24810, "total_steps": 40000, "loss": 0.738, "lr": 1.578045797666453e-05, "epoch": 0.7941232955636643, "percentage": 62.02, "elapsed_time": "14:26:21", "remaining_time": "8:50:25", "throughput": 656.36, "total_tokens": 34118464} {"current_steps": 24815, "total_steps": 40000, "loss": 0.8695, "lr": 1.5771333185383548e-05, "epoch": 0.7942833365341527, "percentage": 62.04, "elapsed_time": "14:26:23", "remaining_time": "8:50:09", "throughput": 656.47, "total_tokens": 34125136} {"current_steps": 24820, "total_steps": 40000, "loss": 0.7556, "lr": 1.576220981727895e-05, "epoch": 0.7944433775046412, "percentage": 62.05, "elapsed_time": "14:26:24", "remaining_time": "8:49:54", "throughput": 656.58, "total_tokens": 34132256} {"current_steps": 24825, "total_steps": 40000, "loss": 1.0663, "lr": 1.575308787375769e-05, "epoch": 0.7946034184751296, "percentage": 62.06, "elapsed_time": "14:26:26", "remaining_time": "8:49:38", "throughput": 656.69, "total_tokens": 34139040} {"current_steps": 24830, "total_steps": 40000, "loss": 0.899, "lr": 1.5743967356226492e-05, "epoch": 0.7947634594456181, "percentage": 62.08, "elapsed_time": "14:26:28", "remaining_time": "8:49:22", "throughput": 656.81, "total_tokens": 34146336} {"current_steps": 24835, "total_steps": 40000, "loss": 1.0127, "lr": 1.5734848266091835e-05, "epoch": 0.7949235004161065, "percentage": 62.09, "elapsed_time": "14:26:30", "remaining_time": "8:49:06", "throughput": 656.92, "total_tokens": 34153200} {"current_steps": 24840, "total_steps": 40000, "loss": 0.9727, "lr": 1.572573060476001e-05, "epoch": 0.795083541386595, "percentage": 62.1, "elapsed_time": "14:26:31", "remaining_time": "8:48:50", "throughput": 657.03, "total_tokens": 34160096} {"current_steps": 24845, "total_steps": 40000, "loss": 0.7162, "lr": 1.5716614373637085e-05, "epoch": 0.7952435823570834, "percentage": 62.11, "elapsed_time": "14:26:33", "remaining_time": "8:48:35", "throughput": 657.14, "total_tokens": 34167120} {"current_steps": 24850, "total_steps": 40000, "loss": 0.7755, "lr": 1.570749957412887e-05, "epoch": 0.7954036233275719, "percentage": 62.12, "elapsed_time": "14:26:35", "remaining_time": "8:48:19", "throughput": 657.26, "total_tokens": 34174288} {"current_steps": 24855, "total_steps": 40000, "loss": 0.7755, "lr": 1.5698386207641013e-05, "epoch": 0.7955636642980604, "percentage": 62.14, "elapsed_time": "14:26:37", "remaining_time": "8:48:03", "throughput": 657.36, "total_tokens": 34180816} {"current_steps": 24860, "total_steps": 40000, "loss": 0.5798, "lr": 1.5689274275578884e-05, "epoch": 0.7957237052685487, "percentage": 62.15, "elapsed_time": "14:26:38", "remaining_time": "8:47:47", "throughput": 657.48, "total_tokens": 34188048} {"current_steps": 24865, "total_steps": 40000, "loss": 0.7034, "lr": 1.5680163779347667e-05, "epoch": 0.7958837462390372, "percentage": 62.16, "elapsed_time": "14:26:40", "remaining_time": "8:47:32", "throughput": 657.59, "total_tokens": 34195168} {"current_steps": 24870, "total_steps": 40000, "loss": 0.8263, "lr": 1.5671054720352327e-05, "epoch": 0.7960437872095256, "percentage": 62.18, "elapsed_time": "14:26:42", "remaining_time": "8:47:16", "throughput": 657.71, "total_tokens": 34202336} {"current_steps": 24875, "total_steps": 40000, "loss": 0.6537, "lr": 1.566194709999757e-05, "epoch": 0.7962038281800141, "percentage": 62.19, "elapsed_time": "14:26:43", "remaining_time": "8:47:00", "throughput": 657.82, "total_tokens": 34209024} {"current_steps": 24880, "total_steps": 40000, "loss": 0.7425, "lr": 1.5652840919687933e-05, "epoch": 0.7963638691505025, "percentage": 62.2, "elapsed_time": "14:26:45", "remaining_time": "8:46:44", "throughput": 657.92, "total_tokens": 34215760} {"current_steps": 24885, "total_steps": 40000, "loss": 0.641, "lr": 1.5643736180827676e-05, "epoch": 0.796523910120991, "percentage": 62.21, "elapsed_time": "14:26:47", "remaining_time": "8:46:29", "throughput": 658.03, "total_tokens": 34222608} {"current_steps": 24890, "total_steps": 40000, "loss": 0.8038, "lr": 1.5634632884820878e-05, "epoch": 0.7966839510914794, "percentage": 62.22, "elapsed_time": "14:26:49", "remaining_time": "8:46:13", "throughput": 658.15, "total_tokens": 34229712} {"current_steps": 24895, "total_steps": 40000, "loss": 0.6376, "lr": 1.5625531033071395e-05, "epoch": 0.7968439920619679, "percentage": 62.24, "elapsed_time": "14:26:50", "remaining_time": "8:45:57", "throughput": 658.26, "total_tokens": 34236512} {"current_steps": 24900, "total_steps": 40000, "loss": 0.6418, "lr": 1.5616430626982828e-05, "epoch": 0.7970040330324563, "percentage": 62.25, "elapsed_time": "14:26:52", "remaining_time": "8:45:41", "throughput": 658.36, "total_tokens": 34243120} {"current_steps": 24905, "total_steps": 40000, "loss": 0.653, "lr": 1.5607331667958575e-05, "epoch": 0.7971640740029448, "percentage": 62.26, "elapsed_time": "14:26:54", "remaining_time": "8:45:26", "throughput": 658.48, "total_tokens": 34250208} {"current_steps": 24910, "total_steps": 40000, "loss": 0.8127, "lr": 1.5598234157401824e-05, "epoch": 0.7973241149734333, "percentage": 62.28, "elapsed_time": "14:26:56", "remaining_time": "8:45:10", "throughput": 658.58, "total_tokens": 34256800} {"current_steps": 24915, "total_steps": 40000, "loss": 0.7399, "lr": 1.5589138096715503e-05, "epoch": 0.7974841559439216, "percentage": 62.29, "elapsed_time": "14:26:57", "remaining_time": "8:44:54", "throughput": 658.69, "total_tokens": 34263664} {"current_steps": 24920, "total_steps": 40000, "loss": 0.8832, "lr": 1.5580043487302365e-05, "epoch": 0.7976441969144101, "percentage": 62.3, "elapsed_time": "14:26:59", "remaining_time": "8:44:38", "throughput": 658.8, "total_tokens": 34270592} {"current_steps": 24925, "total_steps": 40000, "loss": 0.8439, "lr": 1.5570950330564888e-05, "epoch": 0.7978042378848985, "percentage": 62.31, "elapsed_time": "14:27:01", "remaining_time": "8:44:23", "throughput": 658.91, "total_tokens": 34277504} {"current_steps": 24930, "total_steps": 40000, "loss": 0.6356, "lr": 1.5561858627905367e-05, "epoch": 0.797964278855387, "percentage": 62.32, "elapsed_time": "14:27:03", "remaining_time": "8:44:07", "throughput": 659.03, "total_tokens": 34284720} {"current_steps": 24935, "total_steps": 40000, "loss": 0.6115, "lr": 1.5552768380725857e-05, "epoch": 0.7981243198258754, "percentage": 62.34, "elapsed_time": "14:27:04", "remaining_time": "8:43:51", "throughput": 659.14, "total_tokens": 34291792} {"current_steps": 24940, "total_steps": 40000, "loss": 0.7459, "lr": 1.5543679590428183e-05, "epoch": 0.7982843607963639, "percentage": 62.35, "elapsed_time": "14:27:06", "remaining_time": "8:43:36", "throughput": 659.27, "total_tokens": 34299632} {"current_steps": 24945, "total_steps": 40000, "loss": 0.5684, "lr": 1.5534592258413943e-05, "epoch": 0.7984444017668523, "percentage": 62.36, "elapsed_time": "14:27:08", "remaining_time": "8:43:20", "throughput": 659.38, "total_tokens": 34306336} {"current_steps": 24950, "total_steps": 40000, "loss": 0.7718, "lr": 1.5525506386084538e-05, "epoch": 0.7986044427373408, "percentage": 62.38, "elapsed_time": "14:27:09", "remaining_time": "8:43:04", "throughput": 659.49, "total_tokens": 34313120} {"current_steps": 24955, "total_steps": 40000, "loss": 0.7623, "lr": 1.55164219748411e-05, "epoch": 0.7987644837078292, "percentage": 62.39, "elapsed_time": "14:27:11", "remaining_time": "8:42:49", "throughput": 659.59, "total_tokens": 34319840} {"current_steps": 24960, "total_steps": 40000, "loss": 0.6703, "lr": 1.550733902608459e-05, "epoch": 0.7989245246783176, "percentage": 62.4, "elapsed_time": "14:27:13", "remaining_time": "8:42:33", "throughput": 659.7, "total_tokens": 34326544} {"current_steps": 24965, "total_steps": 40000, "loss": 0.782, "lr": 1.549825754121568e-05, "epoch": 0.7990845656488061, "percentage": 62.41, "elapsed_time": "14:27:15", "remaining_time": "8:42:17", "throughput": 659.82, "total_tokens": 34333616} {"current_steps": 24970, "total_steps": 40000, "loss": 0.6428, "lr": 1.5489177521634864e-05, "epoch": 0.7992446066192945, "percentage": 62.42, "elapsed_time": "14:27:16", "remaining_time": "8:42:02", "throughput": 659.93, "total_tokens": 34340496} {"current_steps": 24975, "total_steps": 40000, "loss": 0.8444, "lr": 1.5480098968742402e-05, "epoch": 0.799404647589783, "percentage": 62.44, "elapsed_time": "14:27:18", "remaining_time": "8:41:46", "throughput": 660.04, "total_tokens": 34347424} {"current_steps": 24980, "total_steps": 40000, "loss": 0.774, "lr": 1.5471021883938304e-05, "epoch": 0.7995646885602714, "percentage": 62.45, "elapsed_time": "14:27:20", "remaining_time": "8:41:30", "throughput": 660.15, "total_tokens": 34354464} {"current_steps": 24985, "total_steps": 40000, "loss": 0.5936, "lr": 1.546194626862238e-05, "epoch": 0.7997247295307599, "percentage": 62.46, "elapsed_time": "14:27:22", "remaining_time": "8:41:15", "throughput": 660.26, "total_tokens": 34361152} {"current_steps": 24990, "total_steps": 40000, "loss": 0.9052, "lr": 1.5452872124194216e-05, "epoch": 0.7998847705012483, "percentage": 62.48, "elapsed_time": "14:27:23", "remaining_time": "8:40:59", "throughput": 660.37, "total_tokens": 34368096} {"current_steps": 24995, "total_steps": 40000, "loss": 0.7545, "lr": 1.5443799452053136e-05, "epoch": 0.8000448114717368, "percentage": 62.49, "elapsed_time": "14:27:25", "remaining_time": "8:40:44", "throughput": 660.48, "total_tokens": 34374880} {"current_steps": 25000, "total_steps": 40000, "loss": 0.7624, "lr": 1.543472825359828e-05, "epoch": 0.8002048524422252, "percentage": 62.5, "elapsed_time": "14:27:27", "remaining_time": "8:40:28", "throughput": 660.58, "total_tokens": 34381536} {"current_steps": 25000, "total_steps": 40000, "eval_loss": 0.7367694973945618, "epoch": 0.8002048524422252, "percentage": 62.5, "elapsed_time": "14:33:14", "remaining_time": "8:43:56", "throughput": 656.2, "total_tokens": 34381536} {"current_steps": 25005, "total_steps": 40000, "loss": 0.7152, "lr": 1.5425658530228522e-05, "epoch": 0.8003648934127137, "percentage": 62.51, "elapsed_time": "14:33:19", "remaining_time": "8:43:42", "throughput": 656.29, "total_tokens": 34388816} {"current_steps": 25010, "total_steps": 40000, "loss": 0.5489, "lr": 1.5416590283342546e-05, "epoch": 0.800524934383202, "percentage": 62.52, "elapsed_time": "14:33:20", "remaining_time": "8:43:26", "throughput": 656.4, "total_tokens": 34395680} {"current_steps": 25015, "total_steps": 40000, "loss": 0.8134, "lr": 1.5407523514338783e-05, "epoch": 0.8006849753536905, "percentage": 62.54, "elapsed_time": "14:33:22", "remaining_time": "8:43:11", "throughput": 656.51, "total_tokens": 34402512} {"current_steps": 25020, "total_steps": 40000, "loss": 0.5621, "lr": 1.539845822461543e-05, "epoch": 0.800845016324179, "percentage": 62.55, "elapsed_time": "14:33:24", "remaining_time": "8:42:55", "throughput": 656.62, "total_tokens": 34409424} {"current_steps": 25025, "total_steps": 40000, "loss": 0.7532, "lr": 1.538939441557048e-05, "epoch": 0.8010050572946674, "percentage": 62.56, "elapsed_time": "14:33:25", "remaining_time": "8:42:39", "throughput": 656.72, "total_tokens": 34416192} {"current_steps": 25030, "total_steps": 40000, "loss": 0.8481, "lr": 1.5380332088601696e-05, "epoch": 0.8011650982651559, "percentage": 62.58, "elapsed_time": "14:33:27", "remaining_time": "8:42:24", "throughput": 656.84, "total_tokens": 34423440} {"current_steps": 25035, "total_steps": 40000, "loss": 0.5249, "lr": 1.537127124510658e-05, "epoch": 0.8013251392356443, "percentage": 62.59, "elapsed_time": "14:33:29", "remaining_time": "8:42:08", "throughput": 656.95, "total_tokens": 34430176} {"current_steps": 25040, "total_steps": 40000, "loss": 0.7988, "lr": 1.5362211886482457e-05, "epoch": 0.8014851802061328, "percentage": 62.6, "elapsed_time": "14:33:31", "remaining_time": "8:41:52", "throughput": 657.06, "total_tokens": 34437136} {"current_steps": 25045, "total_steps": 40000, "loss": 0.7266, "lr": 1.5353154014126363e-05, "epoch": 0.8016452211766212, "percentage": 62.61, "elapsed_time": "14:33:32", "remaining_time": "8:41:37", "throughput": 657.17, "total_tokens": 34444048} {"current_steps": 25050, "total_steps": 40000, "loss": 0.5549, "lr": 1.534409762943515e-05, "epoch": 0.8018052621471097, "percentage": 62.62, "elapsed_time": "14:33:34", "remaining_time": "8:41:21", "throughput": 657.27, "total_tokens": 34450496} {"current_steps": 25055, "total_steps": 40000, "loss": 0.8704, "lr": 1.5335042733805438e-05, "epoch": 0.8019653031175981, "percentage": 62.64, "elapsed_time": "14:33:36", "remaining_time": "8:41:05", "throughput": 657.37, "total_tokens": 34456976} {"current_steps": 25060, "total_steps": 40000, "loss": 0.7892, "lr": 1.532598932863358e-05, "epoch": 0.8021253440880866, "percentage": 62.65, "elapsed_time": "14:33:38", "remaining_time": "8:40:50", "throughput": 657.48, "total_tokens": 34463968} {"current_steps": 25065, "total_steps": 40000, "loss": 0.8459, "lr": 1.531693741531574e-05, "epoch": 0.8022853850585749, "percentage": 62.66, "elapsed_time": "14:33:39", "remaining_time": "8:40:34", "throughput": 657.6, "total_tokens": 34471248} {"current_steps": 25070, "total_steps": 40000, "loss": 0.6562, "lr": 1.5307886995247844e-05, "epoch": 0.8024454260290634, "percentage": 62.68, "elapsed_time": "14:33:41", "remaining_time": "8:40:18", "throughput": 657.7, "total_tokens": 34477744} {"current_steps": 25075, "total_steps": 40000, "loss": 0.6459, "lr": 1.529883806982557e-05, "epoch": 0.8026054669995519, "percentage": 62.69, "elapsed_time": "14:33:43", "remaining_time": "8:40:03", "throughput": 657.8, "total_tokens": 34484112} {"current_steps": 25080, "total_steps": 40000, "loss": 0.6935, "lr": 1.5289790640444376e-05, "epoch": 0.8027655079700403, "percentage": 62.7, "elapsed_time": "14:33:45", "remaining_time": "8:39:47", "throughput": 657.91, "total_tokens": 34490896} {"current_steps": 25085, "total_steps": 40000, "loss": 0.7718, "lr": 1.5280744708499494e-05, "epoch": 0.8029255489405288, "percentage": 62.71, "elapsed_time": "14:33:46", "remaining_time": "8:39:31", "throughput": 658.02, "total_tokens": 34497776} {"current_steps": 25090, "total_steps": 40000, "loss": 0.4825, "lr": 1.527170027538591e-05, "epoch": 0.8030855899110172, "percentage": 62.72, "elapsed_time": "14:33:48", "remaining_time": "8:39:16", "throughput": 658.13, "total_tokens": 34504720} {"current_steps": 25095, "total_steps": 40000, "loss": 0.7905, "lr": 1.5262657342498407e-05, "epoch": 0.8032456308815057, "percentage": 62.74, "elapsed_time": "14:33:50", "remaining_time": "8:39:00", "throughput": 658.23, "total_tokens": 34511152} {"current_steps": 25100, "total_steps": 40000, "loss": 0.6342, "lr": 1.52536159112315e-05, "epoch": 0.8034056718519941, "percentage": 62.75, "elapsed_time": "14:33:52", "remaining_time": "8:38:45", "throughput": 658.34, "total_tokens": 34518080} {"current_steps": 25105, "total_steps": 40000, "loss": 0.7908, "lr": 1.5244575982979497e-05, "epoch": 0.8035657128224826, "percentage": 62.76, "elapsed_time": "14:33:53", "remaining_time": "8:38:29", "throughput": 658.44, "total_tokens": 34524544} {"current_steps": 25110, "total_steps": 40000, "loss": 0.6215, "lr": 1.5235537559136487e-05, "epoch": 0.803725753792971, "percentage": 62.78, "elapsed_time": "14:33:55", "remaining_time": "8:38:13", "throughput": 658.55, "total_tokens": 34531664} {"current_steps": 25115, "total_steps": 40000, "loss": 0.6313, "lr": 1.5226500641096286e-05, "epoch": 0.8038857947634594, "percentage": 62.79, "elapsed_time": "14:33:57", "remaining_time": "8:37:58", "throughput": 658.66, "total_tokens": 34538384} {"current_steps": 25120, "total_steps": 40000, "loss": 0.7351, "lr": 1.5217465230252509e-05, "epoch": 0.804045835733948, "percentage": 62.8, "elapsed_time": "14:33:58", "remaining_time": "8:37:42", "throughput": 658.77, "total_tokens": 34545040} {"current_steps": 25125, "total_steps": 40000, "loss": 0.743, "lr": 1.5208431327998523e-05, "epoch": 0.8042058767044363, "percentage": 62.81, "elapsed_time": "14:34:00", "remaining_time": "8:37:27", "throughput": 658.87, "total_tokens": 34551872} {"current_steps": 25130, "total_steps": 40000, "loss": 0.875, "lr": 1.5199398935727477e-05, "epoch": 0.8043659176749248, "percentage": 62.82, "elapsed_time": "14:34:02", "remaining_time": "8:37:11", "throughput": 658.98, "total_tokens": 34558752} {"current_steps": 25135, "total_steps": 40000, "loss": 0.7288, "lr": 1.5190368054832282e-05, "epoch": 0.8045259586454132, "percentage": 62.84, "elapsed_time": "14:34:04", "remaining_time": "8:36:55", "throughput": 659.09, "total_tokens": 34565280} {"current_steps": 25140, "total_steps": 40000, "loss": 0.8422, "lr": 1.5181338686705601e-05, "epoch": 0.8046859996159017, "percentage": 62.85, "elapsed_time": "14:34:05", "remaining_time": "8:36:40", "throughput": 659.2, "total_tokens": 34572320} {"current_steps": 25145, "total_steps": 40000, "loss": 0.705, "lr": 1.5172310832739889e-05, "epoch": 0.8048460405863901, "percentage": 62.86, "elapsed_time": "14:34:07", "remaining_time": "8:36:24", "throughput": 659.31, "total_tokens": 34579184} {"current_steps": 25150, "total_steps": 40000, "loss": 0.7624, "lr": 1.5163284494327346e-05, "epoch": 0.8050060815568786, "percentage": 62.88, "elapsed_time": "14:34:09", "remaining_time": "8:36:09", "throughput": 659.41, "total_tokens": 34585888} {"current_steps": 25155, "total_steps": 40000, "loss": 0.6759, "lr": 1.5154259672859952e-05, "epoch": 0.805166122527367, "percentage": 62.89, "elapsed_time": "14:34:11", "remaining_time": "8:35:53", "throughput": 659.53, "total_tokens": 34593040} {"current_steps": 25160, "total_steps": 40000, "loss": 0.6785, "lr": 1.5145236369729452e-05, "epoch": 0.8053261634978555, "percentage": 62.9, "elapsed_time": "14:34:12", "remaining_time": "8:35:38", "throughput": 659.64, "total_tokens": 34599872} {"current_steps": 25165, "total_steps": 40000, "loss": 0.5868, "lr": 1.5136214586327335e-05, "epoch": 0.8054862044683438, "percentage": 62.91, "elapsed_time": "14:34:14", "remaining_time": "8:35:22", "throughput": 659.75, "total_tokens": 34606800} {"current_steps": 25170, "total_steps": 40000, "loss": 0.7755, "lr": 1.5127194324044885e-05, "epoch": 0.8056462454388323, "percentage": 62.92, "elapsed_time": "14:34:16", "remaining_time": "8:35:06", "throughput": 659.86, "total_tokens": 34613808} {"current_steps": 25175, "total_steps": 40000, "loss": 0.7603, "lr": 1.5118175584273148e-05, "epoch": 0.8058062864093208, "percentage": 62.94, "elapsed_time": "14:34:18", "remaining_time": "8:34:51", "throughput": 659.97, "total_tokens": 34620752} {"current_steps": 25180, "total_steps": 40000, "loss": 1.0728, "lr": 1.5109158368402909e-05, "epoch": 0.8059663273798092, "percentage": 62.95, "elapsed_time": "14:34:19", "remaining_time": "8:34:35", "throughput": 660.08, "total_tokens": 34627456} {"current_steps": 25185, "total_steps": 40000, "loss": 0.7926, "lr": 1.5100142677824753e-05, "epoch": 0.8061263683502977, "percentage": 62.96, "elapsed_time": "14:34:21", "remaining_time": "8:34:20", "throughput": 660.18, "total_tokens": 34634288} {"current_steps": 25190, "total_steps": 40000, "loss": 0.6236, "lr": 1.509112851392901e-05, "epoch": 0.8062864093207861, "percentage": 62.98, "elapsed_time": "14:34:23", "remaining_time": "8:34:04", "throughput": 660.29, "total_tokens": 34641008} {"current_steps": 25195, "total_steps": 40000, "loss": 0.6522, "lr": 1.5082115878105763e-05, "epoch": 0.8064464502912746, "percentage": 62.99, "elapsed_time": "14:34:25", "remaining_time": "8:33:49", "throughput": 660.39, "total_tokens": 34647600} {"current_steps": 25200, "total_steps": 40000, "loss": 0.6255, "lr": 1.5073104771744892e-05, "epoch": 0.806606491261763, "percentage": 63.0, "elapsed_time": "14:34:26", "remaining_time": "8:33:33", "throughput": 660.51, "total_tokens": 34654672} {"current_steps": 25200, "total_steps": 40000, "eval_loss": 0.7362045049667358, "epoch": 0.806606491261763, "percentage": 63.0, "elapsed_time": "14:40:14", "remaining_time": "8:36:57", "throughput": 656.16, "total_tokens": 34654672} {"current_steps": 25205, "total_steps": 40000, "loss": 0.634, "lr": 1.5064095196236006e-05, "epoch": 0.8067665322322515, "percentage": 63.01, "elapsed_time": "14:40:17", "remaining_time": "8:36:43", "throughput": 656.25, "total_tokens": 34661312} {"current_steps": 25210, "total_steps": 40000, "loss": 0.5986, "lr": 1.50550871529685e-05, "epoch": 0.8069265732027399, "percentage": 63.02, "elapsed_time": "14:40:19", "remaining_time": "8:36:27", "throughput": 656.36, "total_tokens": 34668176} {"current_steps": 25215, "total_steps": 40000, "loss": 0.798, "lr": 1.5046080643331546e-05, "epoch": 0.8070866141732284, "percentage": 63.04, "elapsed_time": "14:40:20", "remaining_time": "8:36:11", "throughput": 656.47, "total_tokens": 34675344} {"current_steps": 25220, "total_steps": 40000, "loss": 0.7219, "lr": 1.5037075668714028e-05, "epoch": 0.8072466551437167, "percentage": 63.05, "elapsed_time": "14:40:22", "remaining_time": "8:35:56", "throughput": 656.58, "total_tokens": 34682560} {"current_steps": 25225, "total_steps": 40000, "loss": 0.8945, "lr": 1.5028072230504656e-05, "epoch": 0.8074066961142052, "percentage": 63.06, "elapsed_time": "14:40:24", "remaining_time": "8:35:40", "throughput": 656.69, "total_tokens": 34689216} {"current_steps": 25230, "total_steps": 40000, "loss": 0.6755, "lr": 1.5019070330091861e-05, "epoch": 0.8075667370846937, "percentage": 63.08, "elapsed_time": "14:40:26", "remaining_time": "8:35:25", "throughput": 656.8, "total_tokens": 34696096} {"current_steps": 25235, "total_steps": 40000, "loss": 0.8563, "lr": 1.5010069968863843e-05, "epoch": 0.8077267780551821, "percentage": 63.09, "elapsed_time": "14:40:27", "remaining_time": "8:35:09", "throughput": 656.91, "total_tokens": 34702912} {"current_steps": 25240, "total_steps": 40000, "loss": 0.8952, "lr": 1.5001071148208584e-05, "epoch": 0.8078868190256706, "percentage": 63.1, "elapsed_time": "14:40:29", "remaining_time": "8:34:54", "throughput": 657.01, "total_tokens": 34709728} {"current_steps": 25245, "total_steps": 40000, "loss": 0.6964, "lr": 1.49920738695138e-05, "epoch": 0.808046859996159, "percentage": 63.11, "elapsed_time": "14:40:31", "remaining_time": "8:34:38", "throughput": 657.13, "total_tokens": 34716944} {"current_steps": 25250, "total_steps": 40000, "loss": 0.6408, "lr": 1.4983078134166995e-05, "epoch": 0.8082069009666475, "percentage": 63.12, "elapsed_time": "14:40:33", "remaining_time": "8:34:22", "throughput": 657.23, "total_tokens": 34723616} {"current_steps": 25255, "total_steps": 40000, "loss": 0.4879, "lr": 1.4974083943555428e-05, "epoch": 0.8083669419371359, "percentage": 63.14, "elapsed_time": "14:40:34", "remaining_time": "8:34:07", "throughput": 657.34, "total_tokens": 34730480} {"current_steps": 25260, "total_steps": 40000, "loss": 0.6198, "lr": 1.496509129906611e-05, "epoch": 0.8085269829076244, "percentage": 63.15, "elapsed_time": "14:40:36", "remaining_time": "8:33:51", "throughput": 657.45, "total_tokens": 34737616} {"current_steps": 25265, "total_steps": 40000, "loss": 0.578, "lr": 1.4956100202085809e-05, "epoch": 0.8086870238781128, "percentage": 63.16, "elapsed_time": "14:40:38", "remaining_time": "8:33:36", "throughput": 657.56, "total_tokens": 34744368} {"current_steps": 25270, "total_steps": 40000, "loss": 0.8222, "lr": 1.4947110654001093e-05, "epoch": 0.8088470648486012, "percentage": 63.18, "elapsed_time": "14:40:40", "remaining_time": "8:33:20", "throughput": 657.66, "total_tokens": 34750992} {"current_steps": 25275, "total_steps": 40000, "loss": 0.6774, "lr": 1.4938122656198234e-05, "epoch": 0.8090071058190896, "percentage": 63.19, "elapsed_time": "14:40:41", "remaining_time": "8:33:05", "throughput": 657.79, "total_tokens": 34758672} {"current_steps": 25280, "total_steps": 40000, "loss": 0.8045, "lr": 1.4929136210063316e-05, "epoch": 0.8091671467895781, "percentage": 63.2, "elapsed_time": "14:40:43", "remaining_time": "8:32:49", "throughput": 657.9, "total_tokens": 34765808} {"current_steps": 25285, "total_steps": 40000, "loss": 0.5941, "lr": 1.4920151316982146e-05, "epoch": 0.8093271877600666, "percentage": 63.21, "elapsed_time": "14:40:45", "remaining_time": "8:32:34", "throughput": 658.01, "total_tokens": 34772832} {"current_steps": 25290, "total_steps": 40000, "loss": 0.8247, "lr": 1.4911167978340312e-05, "epoch": 0.809487228730555, "percentage": 63.22, "elapsed_time": "14:40:46", "remaining_time": "8:32:18", "throughput": 658.12, "total_tokens": 34779760} {"current_steps": 25295, "total_steps": 40000, "loss": 0.6343, "lr": 1.4902186195523166e-05, "epoch": 0.8096472697010435, "percentage": 63.24, "elapsed_time": "14:40:48", "remaining_time": "8:32:03", "throughput": 658.22, "total_tokens": 34786224} {"current_steps": 25300, "total_steps": 40000, "loss": 0.5734, "lr": 1.4893205969915805e-05, "epoch": 0.8098073106715319, "percentage": 63.25, "elapsed_time": "14:40:50", "remaining_time": "8:31:47", "throughput": 658.32, "total_tokens": 34792768} {"current_steps": 25305, "total_steps": 40000, "loss": 0.768, "lr": 1.4884227302903086e-05, "epoch": 0.8099673516420204, "percentage": 63.26, "elapsed_time": "14:40:52", "remaining_time": "8:31:32", "throughput": 658.43, "total_tokens": 34799408} {"current_steps": 25310, "total_steps": 40000, "loss": 0.7817, "lr": 1.4875250195869653e-05, "epoch": 0.8101273926125088, "percentage": 63.28, "elapsed_time": "14:40:53", "remaining_time": "8:31:16", "throughput": 658.53, "total_tokens": 34806160} {"current_steps": 25315, "total_steps": 40000, "loss": 0.7193, "lr": 1.4866274650199862e-05, "epoch": 0.8102874335829973, "percentage": 63.29, "elapsed_time": "14:40:55", "remaining_time": "8:31:01", "throughput": 658.64, "total_tokens": 34812896} {"current_steps": 25320, "total_steps": 40000, "loss": 0.6528, "lr": 1.485730066727788e-05, "epoch": 0.8104474745534856, "percentage": 63.3, "elapsed_time": "14:40:57", "remaining_time": "8:30:45", "throughput": 658.75, "total_tokens": 34819664} {"current_steps": 25325, "total_steps": 40000, "loss": 0.6611, "lr": 1.4848328248487586e-05, "epoch": 0.8106075155239741, "percentage": 63.31, "elapsed_time": "14:40:59", "remaining_time": "8:30:30", "throughput": 658.85, "total_tokens": 34826368} {"current_steps": 25330, "total_steps": 40000, "loss": 0.8784, "lr": 1.4839357395212656e-05, "epoch": 0.8107675564944626, "percentage": 63.32, "elapsed_time": "14:41:00", "remaining_time": "8:30:14", "throughput": 658.96, "total_tokens": 34833408} {"current_steps": 25335, "total_steps": 40000, "loss": 0.755, "lr": 1.4830388108836502e-05, "epoch": 0.810927597464951, "percentage": 63.34, "elapsed_time": "14:41:02", "remaining_time": "8:29:59", "throughput": 659.08, "total_tokens": 34840432} {"current_steps": 25340, "total_steps": 40000, "loss": 0.9262, "lr": 1.4821420390742299e-05, "epoch": 0.8110876384354395, "percentage": 63.35, "elapsed_time": "14:41:04", "remaining_time": "8:29:43", "throughput": 659.19, "total_tokens": 34847440} {"current_steps": 25345, "total_steps": 40000, "loss": 0.6313, "lr": 1.4812454242312979e-05, "epoch": 0.8112476794059279, "percentage": 63.36, "elapsed_time": "14:41:06", "remaining_time": "8:29:28", "throughput": 659.29, "total_tokens": 34854224} {"current_steps": 25350, "total_steps": 40000, "loss": 0.697, "lr": 1.4803489664931253e-05, "epoch": 0.8114077203764164, "percentage": 63.38, "elapsed_time": "14:41:07", "remaining_time": "8:29:12", "throughput": 659.4, "total_tokens": 34861040} {"current_steps": 25355, "total_steps": 40000, "loss": 0.7515, "lr": 1.4794526659979544e-05, "epoch": 0.8115677613469048, "percentage": 63.39, "elapsed_time": "14:41:09", "remaining_time": "8:28:57", "throughput": 659.51, "total_tokens": 34867984} {"current_steps": 25360, "total_steps": 40000, "loss": 0.681, "lr": 1.4785565228840086e-05, "epoch": 0.8117278023173933, "percentage": 63.4, "elapsed_time": "14:41:11", "remaining_time": "8:28:41", "throughput": 659.62, "total_tokens": 34875056} {"current_steps": 25365, "total_steps": 40000, "loss": 0.8222, "lr": 1.4776605372894819e-05, "epoch": 0.8118878432878817, "percentage": 63.41, "elapsed_time": "14:41:13", "remaining_time": "8:28:26", "throughput": 659.74, "total_tokens": 34882336} {"current_steps": 25370, "total_steps": 40000, "loss": 0.6967, "lr": 1.4767647093525488e-05, "epoch": 0.8120478842583702, "percentage": 63.42, "elapsed_time": "14:41:14", "remaining_time": "8:28:11", "throughput": 659.84, "total_tokens": 34888912} {"current_steps": 25375, "total_steps": 40000, "loss": 0.6288, "lr": 1.4758690392113566e-05, "epoch": 0.8122079252288585, "percentage": 63.44, "elapsed_time": "14:41:16", "remaining_time": "8:27:55", "throughput": 659.96, "total_tokens": 34896272} {"current_steps": 25380, "total_steps": 40000, "loss": 0.6536, "lr": 1.4749735270040276e-05, "epoch": 0.812367966199347, "percentage": 63.45, "elapsed_time": "14:41:18", "remaining_time": "8:27:40", "throughput": 660.07, "total_tokens": 34903232} {"current_steps": 25385, "total_steps": 40000, "loss": 0.663, "lr": 1.4740781728686623e-05, "epoch": 0.8125280071698355, "percentage": 63.46, "elapsed_time": "14:41:20", "remaining_time": "8:27:24", "throughput": 660.17, "total_tokens": 34909888} {"current_steps": 25390, "total_steps": 40000, "loss": 0.7604, "lr": 1.4731829769433358e-05, "epoch": 0.8126880481403239, "percentage": 63.48, "elapsed_time": "14:41:21", "remaining_time": "8:27:09", "throughput": 660.29, "total_tokens": 34917104} {"current_steps": 25395, "total_steps": 40000, "loss": 0.8351, "lr": 1.4722879393660976e-05, "epoch": 0.8128480891108124, "percentage": 63.49, "elapsed_time": "14:41:23", "remaining_time": "8:26:53", "throughput": 660.4, "total_tokens": 34924128} {"current_steps": 25400, "total_steps": 40000, "loss": 0.7843, "lr": 1.4713930602749748e-05, "epoch": 0.8130081300813008, "percentage": 63.5, "elapsed_time": "14:41:25", "remaining_time": "8:26:38", "throughput": 660.52, "total_tokens": 34931520} {"current_steps": 25400, "total_steps": 40000, "eval_loss": 0.7355203032493591, "epoch": 0.8130081300813008, "percentage": 63.5, "elapsed_time": "14:47:13", "remaining_time": "8:29:58", "throughput": 656.19, "total_tokens": 34931520} {"current_steps": 25405, "total_steps": 40000, "loss": 0.7631, "lr": 1.470498339807968e-05, "epoch": 0.8131681710517893, "percentage": 63.51, "elapsed_time": "14:47:16", "remaining_time": "8:29:44", "throughput": 656.28, "total_tokens": 34938432} {"current_steps": 25410, "total_steps": 40000, "loss": 0.8242, "lr": 1.4696037781030542e-05, "epoch": 0.8133282120222777, "percentage": 63.52, "elapsed_time": "14:47:18", "remaining_time": "8:29:28", "throughput": 656.39, "total_tokens": 34945296} {"current_steps": 25415, "total_steps": 40000, "loss": 0.8366, "lr": 1.4687093752981876e-05, "epoch": 0.8134882529927662, "percentage": 63.54, "elapsed_time": "14:47:20", "remaining_time": "8:29:13", "throughput": 656.5, "total_tokens": 34952256} {"current_steps": 25420, "total_steps": 40000, "loss": 0.62, "lr": 1.4678151315312943e-05, "epoch": 0.8136482939632546, "percentage": 63.55, "elapsed_time": "14:47:22", "remaining_time": "8:28:57", "throughput": 656.61, "total_tokens": 34959232} {"current_steps": 25425, "total_steps": 40000, "loss": 0.7666, "lr": 1.4669210469402789e-05, "epoch": 0.813808334933743, "percentage": 63.56, "elapsed_time": "14:47:23", "remaining_time": "8:28:42", "throughput": 656.72, "total_tokens": 34966208} {"current_steps": 25430, "total_steps": 40000, "loss": 0.8631, "lr": 1.4660271216630218e-05, "epoch": 0.8139683759042314, "percentage": 63.58, "elapsed_time": "14:47:25", "remaining_time": "8:28:26", "throughput": 656.84, "total_tokens": 34973584} {"current_steps": 25435, "total_steps": 40000, "loss": 0.6507, "lr": 1.4651333558373748e-05, "epoch": 0.8141284168747199, "percentage": 63.59, "elapsed_time": "14:47:27", "remaining_time": "8:28:11", "throughput": 656.95, "total_tokens": 34980656} {"current_steps": 25440, "total_steps": 40000, "loss": 0.7269, "lr": 1.4642397496011707e-05, "epoch": 0.8142884578452084, "percentage": 63.6, "elapsed_time": "14:47:29", "remaining_time": "8:27:55", "throughput": 657.06, "total_tokens": 34987616} {"current_steps": 25445, "total_steps": 40000, "loss": 0.7872, "lr": 1.4633463030922129e-05, "epoch": 0.8144484988156968, "percentage": 63.61, "elapsed_time": "14:47:30", "remaining_time": "8:27:40", "throughput": 657.16, "total_tokens": 34994304} {"current_steps": 25450, "total_steps": 40000, "loss": 0.6504, "lr": 1.462453016448282e-05, "epoch": 0.8146085397861853, "percentage": 63.62, "elapsed_time": "14:47:32", "remaining_time": "8:27:24", "throughput": 657.27, "total_tokens": 35001408} {"current_steps": 25455, "total_steps": 40000, "loss": 0.6961, "lr": 1.4615598898071354e-05, "epoch": 0.8147685807566737, "percentage": 63.64, "elapsed_time": "14:47:34", "remaining_time": "8:27:09", "throughput": 657.38, "total_tokens": 35008224} {"current_steps": 25460, "total_steps": 40000, "loss": 0.7693, "lr": 1.4606669233065026e-05, "epoch": 0.8149286217271622, "percentage": 63.65, "elapsed_time": "14:47:36", "remaining_time": "8:26:54", "throughput": 657.49, "total_tokens": 35015200} {"current_steps": 25465, "total_steps": 40000, "loss": 0.4848, "lr": 1.4597741170840914e-05, "epoch": 0.8150886626976506, "percentage": 63.66, "elapsed_time": "14:47:37", "remaining_time": "8:26:38", "throughput": 657.59, "total_tokens": 35022000} {"current_steps": 25470, "total_steps": 40000, "loss": 0.8024, "lr": 1.4588814712775853e-05, "epoch": 0.8152487036681391, "percentage": 63.68, "elapsed_time": "14:47:39", "remaining_time": "8:26:23", "throughput": 657.7, "total_tokens": 35028928} {"current_steps": 25475, "total_steps": 40000, "loss": 0.6481, "lr": 1.4579889860246382e-05, "epoch": 0.8154087446386274, "percentage": 63.69, "elapsed_time": "14:47:41", "remaining_time": "8:26:07", "throughput": 657.81, "total_tokens": 35035760} {"current_steps": 25480, "total_steps": 40000, "loss": 0.7289, "lr": 1.457096661462885e-05, "epoch": 0.8155687856091159, "percentage": 63.7, "elapsed_time": "14:47:42", "remaining_time": "8:25:52", "throughput": 657.91, "total_tokens": 35042240} {"current_steps": 25485, "total_steps": 40000, "loss": 0.856, "lr": 1.4562044977299322e-05, "epoch": 0.8157288265796043, "percentage": 63.71, "elapsed_time": "14:47:44", "remaining_time": "8:25:36", "throughput": 658.02, "total_tokens": 35049024} {"current_steps": 25490, "total_steps": 40000, "loss": 0.7554, "lr": 1.4553124949633623e-05, "epoch": 0.8158888675500928, "percentage": 63.73, "elapsed_time": "14:47:46", "remaining_time": "8:25:21", "throughput": 658.12, "total_tokens": 35055984} {"current_steps": 25495, "total_steps": 40000, "loss": 0.826, "lr": 1.4544206533007354e-05, "epoch": 0.8160489085205813, "percentage": 63.74, "elapsed_time": "14:47:48", "remaining_time": "8:25:06", "throughput": 658.23, "total_tokens": 35062688} {"current_steps": 25500, "total_steps": 40000, "loss": 0.6938, "lr": 1.4535289728795821e-05, "epoch": 0.8162089494910697, "percentage": 63.75, "elapsed_time": "14:47:49", "remaining_time": "8:24:50", "throughput": 658.34, "total_tokens": 35069872} {"current_steps": 25505, "total_steps": 40000, "loss": 0.6599, "lr": 1.4526374538374132e-05, "epoch": 0.8163689904615582, "percentage": 63.76, "elapsed_time": "14:47:51", "remaining_time": "8:24:35", "throughput": 658.45, "total_tokens": 35076496} {"current_steps": 25510, "total_steps": 40000, "loss": 0.8119, "lr": 1.4517460963117097e-05, "epoch": 0.8165290314320466, "percentage": 63.78, "elapsed_time": "14:47:53", "remaining_time": "8:24:19", "throughput": 658.56, "total_tokens": 35083632} {"current_steps": 25515, "total_steps": 40000, "loss": 0.8419, "lr": 1.4508549004399314e-05, "epoch": 0.8166890724025351, "percentage": 63.79, "elapsed_time": "14:47:55", "remaining_time": "8:24:04", "throughput": 658.66, "total_tokens": 35090352} {"current_steps": 25520, "total_steps": 40000, "loss": 0.7539, "lr": 1.449963866359513e-05, "epoch": 0.8168491133730235, "percentage": 63.8, "elapsed_time": "14:47:56", "remaining_time": "8:23:49", "throughput": 658.77, "total_tokens": 35097280} {"current_steps": 25525, "total_steps": 40000, "loss": 0.7104, "lr": 1.4490729942078607e-05, "epoch": 0.817009154343512, "percentage": 63.81, "elapsed_time": "14:47:58", "remaining_time": "8:23:33", "throughput": 658.87, "total_tokens": 35103888} {"current_steps": 25530, "total_steps": 40000, "loss": 0.5745, "lr": 1.4481822841223608e-05, "epoch": 0.8171691953140003, "percentage": 63.82, "elapsed_time": "14:48:00", "remaining_time": "8:23:18", "throughput": 658.97, "total_tokens": 35110272} {"current_steps": 25535, "total_steps": 40000, "loss": 0.5874, "lr": 1.4472917362403704e-05, "epoch": 0.8173292362844888, "percentage": 63.84, "elapsed_time": "14:48:02", "remaining_time": "8:23:03", "throughput": 659.08, "total_tokens": 35116928} {"current_steps": 25540, "total_steps": 40000, "loss": 0.7092, "lr": 1.4464013506992224e-05, "epoch": 0.8174892772549772, "percentage": 63.85, "elapsed_time": "14:48:03", "remaining_time": "8:22:47", "throughput": 659.18, "total_tokens": 35123904} {"current_steps": 25545, "total_steps": 40000, "loss": 0.6675, "lr": 1.4455111276362277e-05, "epoch": 0.8176493182254657, "percentage": 63.86, "elapsed_time": "14:48:05", "remaining_time": "8:22:32", "throughput": 659.3, "total_tokens": 35131152} {"current_steps": 25550, "total_steps": 40000, "loss": 0.8037, "lr": 1.4446210671886676e-05, "epoch": 0.8178093591959542, "percentage": 63.88, "elapsed_time": "14:48:07", "remaining_time": "8:22:17", "throughput": 659.41, "total_tokens": 35138064} {"current_steps": 25555, "total_steps": 40000, "loss": 0.7809, "lr": 1.4437311694938015e-05, "epoch": 0.8179694001664426, "percentage": 63.89, "elapsed_time": "14:48:09", "remaining_time": "8:22:01", "throughput": 659.51, "total_tokens": 35144720} {"current_steps": 25560, "total_steps": 40000, "loss": 0.7214, "lr": 1.442841434688864e-05, "epoch": 0.8181294411369311, "percentage": 63.9, "elapsed_time": "14:48:10", "remaining_time": "8:21:46", "throughput": 659.61, "total_tokens": 35151344} {"current_steps": 25565, "total_steps": 40000, "loss": 0.6398, "lr": 1.4419518629110615e-05, "epoch": 0.8182894821074195, "percentage": 63.91, "elapsed_time": "14:48:12", "remaining_time": "8:21:31", "throughput": 659.72, "total_tokens": 35158080} {"current_steps": 25570, "total_steps": 40000, "loss": 0.8352, "lr": 1.4410624542975778e-05, "epoch": 0.818449523077908, "percentage": 63.92, "elapsed_time": "14:48:14", "remaining_time": "8:21:15", "throughput": 659.84, "total_tokens": 35165616} {"current_steps": 25575, "total_steps": 40000, "loss": 0.7881, "lr": 1.4401732089855724e-05, "epoch": 0.8186095640483964, "percentage": 63.94, "elapsed_time": "14:48:16", "remaining_time": "8:21:00", "throughput": 659.94, "total_tokens": 35172192} {"current_steps": 25580, "total_steps": 40000, "loss": 0.738, "lr": 1.4392841271121754e-05, "epoch": 0.8187696050188848, "percentage": 63.95, "elapsed_time": "14:48:17", "remaining_time": "8:20:45", "throughput": 660.04, "total_tokens": 35178784} {"current_steps": 25585, "total_steps": 40000, "loss": 0.7351, "lr": 1.438395208814497e-05, "epoch": 0.8189296459893732, "percentage": 63.96, "elapsed_time": "14:48:19", "remaining_time": "8:20:29", "throughput": 660.16, "total_tokens": 35186016} {"current_steps": 25590, "total_steps": 40000, "loss": 0.635, "lr": 1.4375064542296174e-05, "epoch": 0.8190896869598617, "percentage": 63.98, "elapsed_time": "14:48:21", "remaining_time": "8:20:14", "throughput": 660.26, "total_tokens": 35192656} {"current_steps": 25595, "total_steps": 40000, "loss": 0.7643, "lr": 1.4366178634945946e-05, "epoch": 0.8192497279303502, "percentage": 63.99, "elapsed_time": "14:48:22", "remaining_time": "8:19:59", "throughput": 660.36, "total_tokens": 35199344} {"current_steps": 25600, "total_steps": 40000, "loss": 0.6743, "lr": 1.4357294367464616e-05, "epoch": 0.8194097689008386, "percentage": 64.0, "elapsed_time": "14:48:24", "remaining_time": "8:19:43", "throughput": 660.48, "total_tokens": 35206448} {"current_steps": 25600, "total_steps": 40000, "eval_loss": 0.7353746891021729, "epoch": 0.8194097689008386, "percentage": 64.0, "elapsed_time": "14:54:12", "remaining_time": "8:22:59", "throughput": 656.19, "total_tokens": 35206448} {"current_steps": 25605, "total_steps": 40000, "loss": 0.944, "lr": 1.434841174122224e-05, "epoch": 0.8195698098713271, "percentage": 64.01, "elapsed_time": "14:54:15", "remaining_time": "8:22:45", "throughput": 656.28, "total_tokens": 35213584} {"current_steps": 25610, "total_steps": 40000, "loss": 0.8115, "lr": 1.4339530757588615e-05, "epoch": 0.8197298508418155, "percentage": 64.03, "elapsed_time": "14:54:17", "remaining_time": "8:22:29", "throughput": 656.4, "total_tokens": 35220928} {"current_steps": 25615, "total_steps": 40000, "loss": 0.8773, "lr": 1.433065141793333e-05, "epoch": 0.819889891812304, "percentage": 64.04, "elapsed_time": "14:54:19", "remaining_time": "8:22:14", "throughput": 656.51, "total_tokens": 35227936} {"current_steps": 25620, "total_steps": 40000, "loss": 0.8294, "lr": 1.4321773723625665e-05, "epoch": 0.8200499327827924, "percentage": 64.05, "elapsed_time": "14:54:21", "remaining_time": "8:21:58", "throughput": 656.61, "total_tokens": 35234352} {"current_steps": 25625, "total_steps": 40000, "loss": 0.7035, "lr": 1.4312897676034693e-05, "epoch": 0.8202099737532809, "percentage": 64.06, "elapsed_time": "14:54:22", "remaining_time": "8:21:43", "throughput": 656.71, "total_tokens": 35241040} {"current_steps": 25630, "total_steps": 40000, "loss": 0.5603, "lr": 1.4304023276529188e-05, "epoch": 0.8203700147237692, "percentage": 64.08, "elapsed_time": "14:54:24", "remaining_time": "8:21:28", "throughput": 656.82, "total_tokens": 35247824} {"current_steps": 25635, "total_steps": 40000, "loss": 0.5654, "lr": 1.4295150526477712e-05, "epoch": 0.8205300556942577, "percentage": 64.09, "elapsed_time": "14:54:26", "remaining_time": "8:21:12", "throughput": 656.93, "total_tokens": 35254816} {"current_steps": 25640, "total_steps": 40000, "loss": 0.7787, "lr": 1.4286279427248562e-05, "epoch": 0.8206900966647461, "percentage": 64.1, "elapsed_time": "14:54:28", "remaining_time": "8:20:57", "throughput": 657.04, "total_tokens": 35261904} {"current_steps": 25645, "total_steps": 40000, "loss": 0.7349, "lr": 1.4277409980209747e-05, "epoch": 0.8208501376352346, "percentage": 64.11, "elapsed_time": "14:54:29", "remaining_time": "8:20:42", "throughput": 657.15, "total_tokens": 35269248} {"current_steps": 25650, "total_steps": 40000, "loss": 0.9265, "lr": 1.4268542186729061e-05, "epoch": 0.8210101786057231, "percentage": 64.12, "elapsed_time": "14:54:31", "remaining_time": "8:20:26", "throughput": 657.26, "total_tokens": 35276064} {"current_steps": 25655, "total_steps": 40000, "loss": 0.8405, "lr": 1.4259676048174043e-05, "epoch": 0.8211702195762115, "percentage": 64.14, "elapsed_time": "14:54:33", "remaining_time": "8:20:11", "throughput": 657.36, "total_tokens": 35282640} {"current_steps": 25660, "total_steps": 40000, "loss": 0.7548, "lr": 1.4250811565911937e-05, "epoch": 0.8213302605467, "percentage": 64.15, "elapsed_time": "14:54:35", "remaining_time": "8:19:56", "throughput": 657.46, "total_tokens": 35289216} {"current_steps": 25665, "total_steps": 40000, "loss": 0.7811, "lr": 1.4241948741309782e-05, "epoch": 0.8214903015171884, "percentage": 64.16, "elapsed_time": "14:54:36", "remaining_time": "8:19:40", "throughput": 657.57, "total_tokens": 35296112} {"current_steps": 25670, "total_steps": 40000, "loss": 0.6113, "lr": 1.4233087575734317e-05, "epoch": 0.8216503424876769, "percentage": 64.18, "elapsed_time": "14:54:38", "remaining_time": "8:19:25", "throughput": 657.67, "total_tokens": 35302624} {"current_steps": 25675, "total_steps": 40000, "loss": 0.5193, "lr": 1.422422807055206e-05, "epoch": 0.8218103834581653, "percentage": 64.19, "elapsed_time": "14:54:40", "remaining_time": "8:19:10", "throughput": 657.78, "total_tokens": 35309632} {"current_steps": 25680, "total_steps": 40000, "loss": 0.6851, "lr": 1.4215370227129243e-05, "epoch": 0.8219704244286538, "percentage": 64.2, "elapsed_time": "14:54:42", "remaining_time": "8:18:54", "throughput": 657.88, "total_tokens": 35316592} {"current_steps": 25685, "total_steps": 40000, "loss": 0.6811, "lr": 1.4206514046831876e-05, "epoch": 0.8221304653991421, "percentage": 64.21, "elapsed_time": "14:54:43", "remaining_time": "8:18:39", "throughput": 657.99, "total_tokens": 35323520} {"current_steps": 25690, "total_steps": 40000, "loss": 0.6956, "lr": 1.419765953102567e-05, "epoch": 0.8222905063696306, "percentage": 64.22, "elapsed_time": "14:54:45", "remaining_time": "8:18:24", "throughput": 658.1, "total_tokens": 35330304} {"current_steps": 25695, "total_steps": 40000, "loss": 0.6432, "lr": 1.4188806681076125e-05, "epoch": 0.822450547340119, "percentage": 64.24, "elapsed_time": "14:54:47", "remaining_time": "8:18:08", "throughput": 658.2, "total_tokens": 35337072} {"current_steps": 25700, "total_steps": 40000, "loss": 0.768, "lr": 1.4179955498348443e-05, "epoch": 0.8226105883106075, "percentage": 64.25, "elapsed_time": "14:54:48", "remaining_time": "8:17:53", "throughput": 658.31, "total_tokens": 35343728} {"current_steps": 25705, "total_steps": 40000, "loss": 0.9277, "lr": 1.4171105984207605e-05, "epoch": 0.822770629281096, "percentage": 64.26, "elapsed_time": "14:54:50", "remaining_time": "8:17:38", "throughput": 658.41, "total_tokens": 35350592} {"current_steps": 25710, "total_steps": 40000, "loss": 0.673, "lr": 1.4162258140018304e-05, "epoch": 0.8229306702515844, "percentage": 64.28, "elapsed_time": "14:54:52", "remaining_time": "8:17:23", "throughput": 658.52, "total_tokens": 35357568} {"current_steps": 25715, "total_steps": 40000, "loss": 0.6874, "lr": 1.4153411967144986e-05, "epoch": 0.8230907112220729, "percentage": 64.29, "elapsed_time": "14:54:54", "remaining_time": "8:17:07", "throughput": 658.63, "total_tokens": 35364720} {"current_steps": 25720, "total_steps": 40000, "loss": 0.7682, "lr": 1.4144567466951864e-05, "epoch": 0.8232507521925613, "percentage": 64.3, "elapsed_time": "14:54:55", "remaining_time": "8:16:52", "throughput": 658.73, "total_tokens": 35371280} {"current_steps": 25725, "total_steps": 40000, "loss": 0.8086, "lr": 1.4135724640802844e-05, "epoch": 0.8234107931630498, "percentage": 64.31, "elapsed_time": "14:54:57", "remaining_time": "8:16:37", "throughput": 658.85, "total_tokens": 35378432} {"current_steps": 25730, "total_steps": 40000, "loss": 0.7725, "lr": 1.4126883490061615e-05, "epoch": 0.8235708341335382, "percentage": 64.33, "elapsed_time": "14:54:59", "remaining_time": "8:16:21", "throughput": 658.95, "total_tokens": 35385216} {"current_steps": 25735, "total_steps": 40000, "loss": 0.7191, "lr": 1.4118044016091603e-05, "epoch": 0.8237308751040266, "percentage": 64.34, "elapsed_time": "14:55:01", "remaining_time": "8:16:06", "throughput": 659.05, "total_tokens": 35391728} {"current_steps": 25740, "total_steps": 40000, "loss": 0.8354, "lr": 1.410920622025594e-05, "epoch": 0.823890916074515, "percentage": 64.35, "elapsed_time": "14:55:02", "remaining_time": "8:15:51", "throughput": 659.16, "total_tokens": 35398608} {"current_steps": 25745, "total_steps": 40000, "loss": 0.6402, "lr": 1.4100370103917554e-05, "epoch": 0.8240509570450035, "percentage": 64.36, "elapsed_time": "14:55:04", "remaining_time": "8:15:36", "throughput": 659.27, "total_tokens": 35405664} {"current_steps": 25750, "total_steps": 40000, "loss": 0.5859, "lr": 1.409153566843907e-05, "epoch": 0.8242109980154919, "percentage": 64.38, "elapsed_time": "14:55:06", "remaining_time": "8:15:20", "throughput": 659.37, "total_tokens": 35412368} {"current_steps": 25755, "total_steps": 40000, "loss": 0.7549, "lr": 1.408270291518286e-05, "epoch": 0.8243710389859804, "percentage": 64.39, "elapsed_time": "14:55:08", "remaining_time": "8:15:05", "throughput": 659.48, "total_tokens": 35419536} {"current_steps": 25760, "total_steps": 40000, "loss": 0.945, "lr": 1.407387184551107e-05, "epoch": 0.8245310799564689, "percentage": 64.4, "elapsed_time": "14:55:09", "remaining_time": "8:14:50", "throughput": 659.59, "total_tokens": 35426288} {"current_steps": 25765, "total_steps": 40000, "loss": 0.7073, "lr": 1.4065042460785532e-05, "epoch": 0.8246911209269573, "percentage": 64.41, "elapsed_time": "14:55:11", "remaining_time": "8:14:35", "throughput": 659.7, "total_tokens": 35433392} {"current_steps": 25770, "total_steps": 40000, "loss": 0.7292, "lr": 1.405621476236787e-05, "epoch": 0.8248511618974458, "percentage": 64.42, "elapsed_time": "14:55:13", "remaining_time": "8:14:20", "throughput": 659.81, "total_tokens": 35440448} {"current_steps": 25775, "total_steps": 40000, "loss": 0.7239, "lr": 1.4047388751619423e-05, "epoch": 0.8250112028679342, "percentage": 64.44, "elapsed_time": "14:55:15", "remaining_time": "8:14:04", "throughput": 659.91, "total_tokens": 35447056} {"current_steps": 25780, "total_steps": 40000, "loss": 0.5277, "lr": 1.4038564429901264e-05, "epoch": 0.8251712438384227, "percentage": 64.45, "elapsed_time": "14:55:16", "remaining_time": "8:13:49", "throughput": 660.01, "total_tokens": 35453872} {"current_steps": 25785, "total_steps": 40000, "loss": 0.6981, "lr": 1.4029741798574227e-05, "epoch": 0.825331284808911, "percentage": 64.46, "elapsed_time": "14:55:18", "remaining_time": "8:13:34", "throughput": 660.13, "total_tokens": 35460992} {"current_steps": 25790, "total_steps": 40000, "loss": 0.5664, "lr": 1.402092085899886e-05, "epoch": 0.8254913257793995, "percentage": 64.48, "elapsed_time": "14:55:20", "remaining_time": "8:13:19", "throughput": 660.23, "total_tokens": 35467856} {"current_steps": 25795, "total_steps": 40000, "loss": 0.7807, "lr": 1.4012101612535464e-05, "epoch": 0.8256513667498879, "percentage": 64.49, "elapsed_time": "14:55:21", "remaining_time": "8:13:04", "throughput": 660.35, "total_tokens": 35475088} {"current_steps": 25800, "total_steps": 40000, "loss": 0.632, "lr": 1.4003284060544092e-05, "epoch": 0.8258114077203764, "percentage": 64.5, "elapsed_time": "14:55:23", "remaining_time": "8:12:48", "throughput": 660.47, "total_tokens": 35482800} {"current_steps": 25800, "total_steps": 40000, "eval_loss": 0.7356077432632446, "epoch": 0.8258114077203764, "percentage": 64.5, "elapsed_time": "15:01:11", "remaining_time": "8:16:00", "throughput": 656.22, "total_tokens": 35482800} {"current_steps": 25805, "total_steps": 40000, "loss": 0.8366, "lr": 1.3994468204384504e-05, "epoch": 0.8259714486908648, "percentage": 64.51, "elapsed_time": "15:01:15", "remaining_time": "8:15:46", "throughput": 656.3, "total_tokens": 35489520} {"current_steps": 25810, "total_steps": 40000, "loss": 0.6433, "lr": 1.398565404541622e-05, "epoch": 0.8261314896613533, "percentage": 64.53, "elapsed_time": "15:01:17", "remaining_time": "8:15:30", "throughput": 656.4, "total_tokens": 35496304} {"current_steps": 25815, "total_steps": 40000, "loss": 0.9142, "lr": 1.3976841584998513e-05, "epoch": 0.8262915306318418, "percentage": 64.54, "elapsed_time": "15:01:18", "remaining_time": "8:15:15", "throughput": 656.5, "total_tokens": 35502928} {"current_steps": 25820, "total_steps": 40000, "loss": 0.7613, "lr": 1.3968030824490352e-05, "epoch": 0.8264515716023302, "percentage": 64.55, "elapsed_time": "15:01:20", "remaining_time": "8:15:00", "throughput": 656.61, "total_tokens": 35509664} {"current_steps": 25825, "total_steps": 40000, "loss": 0.6986, "lr": 1.3959221765250469e-05, "epoch": 0.8266116125728187, "percentage": 64.56, "elapsed_time": "15:01:22", "remaining_time": "8:14:45", "throughput": 656.71, "total_tokens": 35516336} {"current_steps": 25830, "total_steps": 40000, "loss": 0.7817, "lr": 1.3950414408637343e-05, "epoch": 0.8267716535433071, "percentage": 64.58, "elapsed_time": "15:01:24", "remaining_time": "8:14:29", "throughput": 656.82, "total_tokens": 35523456} {"current_steps": 25835, "total_steps": 40000, "loss": 0.7718, "lr": 1.3941608756009166e-05, "epoch": 0.8269316945137956, "percentage": 64.59, "elapsed_time": "15:01:25", "remaining_time": "8:14:14", "throughput": 656.91, "total_tokens": 35529808} {"current_steps": 25840, "total_steps": 40000, "loss": 0.7787, "lr": 1.3932804808723898e-05, "epoch": 0.8270917354842839, "percentage": 64.6, "elapsed_time": "15:01:27", "remaining_time": "8:13:59", "throughput": 657.02, "total_tokens": 35536448} {"current_steps": 25845, "total_steps": 40000, "loss": 0.7591, "lr": 1.3924002568139194e-05, "epoch": 0.8272517764547724, "percentage": 64.61, "elapsed_time": "15:01:29", "remaining_time": "8:13:44", "throughput": 657.11, "total_tokens": 35542784} {"current_steps": 25850, "total_steps": 40000, "loss": 0.859, "lr": 1.3915202035612485e-05, "epoch": 0.8274118174252608, "percentage": 64.62, "elapsed_time": "15:01:31", "remaining_time": "8:13:28", "throughput": 657.22, "total_tokens": 35549520} {"current_steps": 25855, "total_steps": 40000, "loss": 0.7731, "lr": 1.3906403212500935e-05, "epoch": 0.8275718583957493, "percentage": 64.64, "elapsed_time": "15:01:32", "remaining_time": "8:13:13", "throughput": 657.32, "total_tokens": 35556320} {"current_steps": 25860, "total_steps": 40000, "loss": 0.6843, "lr": 1.3897606100161409e-05, "epoch": 0.8277318993662378, "percentage": 64.65, "elapsed_time": "15:01:34", "remaining_time": "8:12:58", "throughput": 657.43, "total_tokens": 35563168} {"current_steps": 25865, "total_steps": 40000, "loss": 0.737, "lr": 1.388881069995055e-05, "epoch": 0.8278919403367262, "percentage": 64.66, "elapsed_time": "15:01:36", "remaining_time": "8:12:43", "throughput": 657.53, "total_tokens": 35570192} {"current_steps": 25870, "total_steps": 40000, "loss": 0.9333, "lr": 1.3880017013224708e-05, "epoch": 0.8280519813072147, "percentage": 64.68, "elapsed_time": "15:01:38", "remaining_time": "8:12:27", "throughput": 657.66, "total_tokens": 35577936} {"current_steps": 25875, "total_steps": 40000, "loss": 0.838, "lr": 1.3871225041339984e-05, "epoch": 0.8282120222777031, "percentage": 64.69, "elapsed_time": "15:01:39", "remaining_time": "8:12:12", "throughput": 657.77, "total_tokens": 35585168} {"current_steps": 25880, "total_steps": 40000, "loss": 0.662, "lr": 1.386243478565222e-05, "epoch": 0.8283720632481916, "percentage": 64.7, "elapsed_time": "15:01:41", "remaining_time": "8:11:57", "throughput": 657.86, "total_tokens": 35591248} {"current_steps": 25885, "total_steps": 40000, "loss": 0.5765, "lr": 1.3853646247516966e-05, "epoch": 0.82853210421868, "percentage": 64.71, "elapsed_time": "15:01:43", "remaining_time": "8:11:42", "throughput": 657.97, "total_tokens": 35598448} {"current_steps": 25890, "total_steps": 40000, "loss": 0.7121, "lr": 1.3844859428289545e-05, "epoch": 0.8286921451891684, "percentage": 64.72, "elapsed_time": "15:01:44", "remaining_time": "8:11:27", "throughput": 658.08, "total_tokens": 35605632} {"current_steps": 25895, "total_steps": 40000, "loss": 0.4407, "lr": 1.3836074329324984e-05, "epoch": 0.8288521861596568, "percentage": 64.74, "elapsed_time": "15:01:46", "remaining_time": "8:11:11", "throughput": 658.18, "total_tokens": 35612096} {"current_steps": 25900, "total_steps": 40000, "loss": 0.8338, "lr": 1.3827290951978044e-05, "epoch": 0.8290122271301453, "percentage": 64.75, "elapsed_time": "15:01:48", "remaining_time": "8:10:56", "throughput": 658.29, "total_tokens": 35618864} {"current_steps": 25905, "total_steps": 40000, "loss": 0.676, "lr": 1.381850929760326e-05, "epoch": 0.8291722681006337, "percentage": 64.76, "elapsed_time": "15:01:50", "remaining_time": "8:10:41", "throughput": 658.4, "total_tokens": 35626160} {"current_steps": 25910, "total_steps": 40000, "loss": 0.5443, "lr": 1.3809729367554842e-05, "epoch": 0.8293323090711222, "percentage": 64.78, "elapsed_time": "15:01:51", "remaining_time": "8:10:26", "throughput": 658.51, "total_tokens": 35633312} {"current_steps": 25915, "total_steps": 40000, "loss": 0.7452, "lr": 1.3800951163186784e-05, "epoch": 0.8294923500416107, "percentage": 64.79, "elapsed_time": "15:01:53", "remaining_time": "8:10:11", "throughput": 658.62, "total_tokens": 35640192} {"current_steps": 25920, "total_steps": 40000, "loss": 0.4992, "lr": 1.3792174685852801e-05, "epoch": 0.8296523910120991, "percentage": 64.8, "elapsed_time": "15:01:55", "remaining_time": "8:09:56", "throughput": 658.72, "total_tokens": 35647104} {"current_steps": 25925, "total_steps": 40000, "loss": 0.8708, "lr": 1.378339993690632e-05, "epoch": 0.8298124319825876, "percentage": 64.81, "elapsed_time": "15:01:57", "remaining_time": "8:09:40", "throughput": 658.83, "total_tokens": 35653808} {"current_steps": 25930, "total_steps": 40000, "loss": 0.6861, "lr": 1.3774626917700523e-05, "epoch": 0.829972472953076, "percentage": 64.83, "elapsed_time": "15:01:58", "remaining_time": "8:09:25", "throughput": 658.93, "total_tokens": 35660736} {"current_steps": 25935, "total_steps": 40000, "loss": 0.6804, "lr": 1.3765855629588334e-05, "epoch": 0.8301325139235645, "percentage": 64.84, "elapsed_time": "15:02:00", "remaining_time": "8:09:10", "throughput": 659.03, "total_tokens": 35667344} {"current_steps": 25940, "total_steps": 40000, "loss": 0.7885, "lr": 1.3757086073922374e-05, "epoch": 0.8302925548940528, "percentage": 64.85, "elapsed_time": "15:02:02", "remaining_time": "8:08:55", "throughput": 659.14, "total_tokens": 35674240} {"current_steps": 25945, "total_steps": 40000, "loss": 0.6994, "lr": 1.3748318252055038e-05, "epoch": 0.8304525958645413, "percentage": 64.86, "elapsed_time": "15:02:04", "remaining_time": "8:08:40", "throughput": 659.26, "total_tokens": 35681680} {"current_steps": 25950, "total_steps": 40000, "loss": 0.5492, "lr": 1.3739552165338416e-05, "epoch": 0.8306126368350297, "percentage": 64.88, "elapsed_time": "15:02:05", "remaining_time": "8:08:25", "throughput": 659.35, "total_tokens": 35688160} {"current_steps": 25955, "total_steps": 40000, "loss": 0.821, "lr": 1.3730787815124354e-05, "epoch": 0.8307726778055182, "percentage": 64.89, "elapsed_time": "15:02:07", "remaining_time": "8:08:10", "throughput": 659.46, "total_tokens": 35694960} {"current_steps": 25960, "total_steps": 40000, "loss": 0.7389, "lr": 1.3722025202764443e-05, "epoch": 0.8309327187760066, "percentage": 64.9, "elapsed_time": "15:02:09", "remaining_time": "8:07:54", "throughput": 659.57, "total_tokens": 35702368} {"current_steps": 25965, "total_steps": 40000, "loss": 0.8163, "lr": 1.371326432960997e-05, "epoch": 0.8310927597464951, "percentage": 64.91, "elapsed_time": "15:02:11", "remaining_time": "8:07:39", "throughput": 659.68, "total_tokens": 35709136} {"current_steps": 25970, "total_steps": 40000, "loss": 0.9922, "lr": 1.3704505197011969e-05, "epoch": 0.8312528007169836, "percentage": 64.92, "elapsed_time": "15:02:12", "remaining_time": "8:07:24", "throughput": 659.79, "total_tokens": 35716096} {"current_steps": 25975, "total_steps": 40000, "loss": 0.6591, "lr": 1.3695747806321224e-05, "epoch": 0.831412841687472, "percentage": 64.94, "elapsed_time": "15:02:14", "remaining_time": "8:07:09", "throughput": 659.89, "total_tokens": 35722960} {"current_steps": 25980, "total_steps": 40000, "loss": 0.6469, "lr": 1.3686992158888212e-05, "epoch": 0.8315728826579605, "percentage": 64.95, "elapsed_time": "15:02:16", "remaining_time": "8:06:54", "throughput": 660.0, "total_tokens": 35729904} {"current_steps": 25985, "total_steps": 40000, "loss": 0.9301, "lr": 1.367823825606319e-05, "epoch": 0.8317329236284489, "percentage": 64.96, "elapsed_time": "15:02:18", "remaining_time": "8:06:39", "throughput": 660.1, "total_tokens": 35736640} {"current_steps": 25990, "total_steps": 40000, "loss": 0.7804, "lr": 1.36694860991961e-05, "epoch": 0.8318929645989374, "percentage": 64.98, "elapsed_time": "15:02:19", "remaining_time": "8:06:24", "throughput": 660.21, "total_tokens": 35743696} {"current_steps": 25995, "total_steps": 40000, "loss": 0.6452, "lr": 1.3660735689636636e-05, "epoch": 0.8320530055694257, "percentage": 64.99, "elapsed_time": "15:02:21", "remaining_time": "8:06:09", "throughput": 660.31, "total_tokens": 35750416} {"current_steps": 26000, "total_steps": 40000, "loss": 0.8752, "lr": 1.365198702873424e-05, "epoch": 0.8322130465399142, "percentage": 65.0, "elapsed_time": "15:02:23", "remaining_time": "8:05:54", "throughput": 660.41, "total_tokens": 35756816} {"current_steps": 26000, "total_steps": 40000, "eval_loss": 0.7352335453033447, "epoch": 0.8322130465399142, "percentage": 65.0, "elapsed_time": "15:08:10", "remaining_time": "8:09:01", "throughput": 656.2, "total_tokens": 35756816} {"current_steps": 26005, "total_steps": 40000, "loss": 0.559, "lr": 1.364324011783804e-05, "epoch": 0.8323730875104026, "percentage": 65.01, "elapsed_time": "15:08:15", "remaining_time": "8:08:47", "throughput": 656.26, "total_tokens": 35763136} {"current_steps": 26010, "total_steps": 40000, "loss": 0.6852, "lr": 1.3634494958296934e-05, "epoch": 0.8325331284808911, "percentage": 65.03, "elapsed_time": "15:08:16", "remaining_time": "8:08:32", "throughput": 656.36, "total_tokens": 35769632} {"current_steps": 26015, "total_steps": 40000, "loss": 0.6706, "lr": 1.3625751551459542e-05, "epoch": 0.8326931694513795, "percentage": 65.04, "elapsed_time": "15:08:18", "remaining_time": "8:08:17", "throughput": 656.47, "total_tokens": 35776496} {"current_steps": 26020, "total_steps": 40000, "loss": 0.7136, "lr": 1.3617009898674188e-05, "epoch": 0.832853210421868, "percentage": 65.05, "elapsed_time": "15:08:20", "remaining_time": "8:08:01", "throughput": 656.57, "total_tokens": 35783328} {"current_steps": 26025, "total_steps": 40000, "loss": 0.6774, "lr": 1.3608270001288967e-05, "epoch": 0.8330132513923565, "percentage": 65.06, "elapsed_time": "15:08:22", "remaining_time": "8:07:46", "throughput": 656.68, "total_tokens": 35790336} {"current_steps": 26030, "total_steps": 40000, "loss": 0.7132, "lr": 1.359953186065166e-05, "epoch": 0.8331732923628449, "percentage": 65.08, "elapsed_time": "15:08:23", "remaining_time": "8:07:31", "throughput": 656.79, "total_tokens": 35797344} {"current_steps": 26035, "total_steps": 40000, "loss": 0.6254, "lr": 1.3590795478109814e-05, "epoch": 0.8333333333333334, "percentage": 65.09, "elapsed_time": "15:08:25", "remaining_time": "8:07:16", "throughput": 656.89, "total_tokens": 35804048} {"current_steps": 26040, "total_steps": 40000, "loss": 0.6769, "lr": 1.3582060855010675e-05, "epoch": 0.8334933743038218, "percentage": 65.1, "elapsed_time": "15:08:27", "remaining_time": "8:07:01", "throughput": 657.0, "total_tokens": 35811120} {"current_steps": 26045, "total_steps": 40000, "loss": 0.5679, "lr": 1.3573327992701245e-05, "epoch": 0.8336534152743102, "percentage": 65.11, "elapsed_time": "15:08:28", "remaining_time": "8:06:46", "throughput": 657.1, "total_tokens": 35817616} {"current_steps": 26050, "total_steps": 40000, "loss": 0.5624, "lr": 1.356459689252823e-05, "epoch": 0.8338134562447986, "percentage": 65.12, "elapsed_time": "15:08:30", "remaining_time": "8:06:30", "throughput": 657.2, "total_tokens": 35824384} {"current_steps": 26055, "total_steps": 40000, "loss": 0.7867, "lr": 1.3555867555838087e-05, "epoch": 0.8339734972152871, "percentage": 65.14, "elapsed_time": "15:08:32", "remaining_time": "8:06:15", "throughput": 657.3, "total_tokens": 35831216} {"current_steps": 26060, "total_steps": 40000, "loss": 0.6475, "lr": 1.3547139983976975e-05, "epoch": 0.8341335381857755, "percentage": 65.15, "elapsed_time": "15:08:34", "remaining_time": "8:06:00", "throughput": 657.41, "total_tokens": 35838416} {"current_steps": 26065, "total_steps": 40000, "loss": 0.7291, "lr": 1.3538414178290815e-05, "epoch": 0.834293579156264, "percentage": 65.16, "elapsed_time": "15:08:35", "remaining_time": "8:05:45", "throughput": 657.52, "total_tokens": 35845472} {"current_steps": 26070, "total_steps": 40000, "loss": 0.7968, "lr": 1.3529690140125209e-05, "epoch": 0.8344536201267524, "percentage": 65.18, "elapsed_time": "15:08:37", "remaining_time": "8:05:30", "throughput": 657.62, "total_tokens": 35852160} {"current_steps": 26075, "total_steps": 40000, "loss": 0.8029, "lr": 1.352096787082553e-05, "epoch": 0.8346136610972409, "percentage": 65.19, "elapsed_time": "15:08:39", "remaining_time": "8:05:15", "throughput": 657.73, "total_tokens": 35859056} {"current_steps": 26080, "total_steps": 40000, "loss": 0.8585, "lr": 1.3512247371736871e-05, "epoch": 0.8347737020677294, "percentage": 65.2, "elapsed_time": "15:08:41", "remaining_time": "8:05:00", "throughput": 657.84, "total_tokens": 35866208} {"current_steps": 26085, "total_steps": 40000, "loss": 0.6561, "lr": 1.3503528644204022e-05, "epoch": 0.8349337430382178, "percentage": 65.21, "elapsed_time": "15:08:42", "remaining_time": "8:04:45", "throughput": 657.94, "total_tokens": 35872832} {"current_steps": 26090, "total_steps": 40000, "loss": 0.6946, "lr": 1.349481168957153e-05, "epoch": 0.8350937840087063, "percentage": 65.22, "elapsed_time": "15:08:44", "remaining_time": "8:04:30", "throughput": 658.05, "total_tokens": 35879952} {"current_steps": 26095, "total_steps": 40000, "loss": 0.8629, "lr": 1.3486096509183665e-05, "epoch": 0.8352538249791946, "percentage": 65.24, "elapsed_time": "15:08:46", "remaining_time": "8:04:14", "throughput": 658.15, "total_tokens": 35886480} {"current_steps": 26100, "total_steps": 40000, "loss": 0.6551, "lr": 1.3477383104384406e-05, "epoch": 0.8354138659496831, "percentage": 65.25, "elapsed_time": "15:08:48", "remaining_time": "8:03:59", "throughput": 658.26, "total_tokens": 35893824} {"current_steps": 26105, "total_steps": 40000, "loss": 0.5615, "lr": 1.3468671476517481e-05, "epoch": 0.8355739069201715, "percentage": 65.26, "elapsed_time": "15:08:49", "remaining_time": "8:03:44", "throughput": 658.37, "total_tokens": 35900944} {"current_steps": 26110, "total_steps": 40000, "loss": 0.6472, "lr": 1.3459961626926326e-05, "epoch": 0.83573394789066, "percentage": 65.28, "elapsed_time": "15:08:51", "remaining_time": "8:03:29", "throughput": 658.48, "total_tokens": 35907744} {"current_steps": 26115, "total_steps": 40000, "loss": 0.7101, "lr": 1.3451253556954101e-05, "epoch": 0.8358939888611484, "percentage": 65.29, "elapsed_time": "15:08:53", "remaining_time": "8:03:14", "throughput": 658.59, "total_tokens": 35915232} {"current_steps": 26120, "total_steps": 40000, "loss": 0.6787, "lr": 1.3442547267943717e-05, "epoch": 0.8360540298316369, "percentage": 65.3, "elapsed_time": "15:08:55", "remaining_time": "8:02:59", "throughput": 658.7, "total_tokens": 35922064} {"current_steps": 26125, "total_steps": 40000, "loss": 0.6167, "lr": 1.3433842761237774e-05, "epoch": 0.8362140708021254, "percentage": 65.31, "elapsed_time": "15:08:56", "remaining_time": "8:02:44", "throughput": 658.8, "total_tokens": 35929040} {"current_steps": 26130, "total_steps": 40000, "loss": 0.7292, "lr": 1.3425140038178639e-05, "epoch": 0.8363741117726138, "percentage": 65.33, "elapsed_time": "15:08:58", "remaining_time": "8:02:29", "throughput": 658.91, "total_tokens": 35935728} {"current_steps": 26135, "total_steps": 40000, "loss": 0.7555, "lr": 1.3416439100108358e-05, "epoch": 0.8365341527431023, "percentage": 65.34, "elapsed_time": "15:09:00", "remaining_time": "8:02:14", "throughput": 659.0, "total_tokens": 35942208} {"current_steps": 26140, "total_steps": 40000, "loss": 0.6785, "lr": 1.3407739948368734e-05, "epoch": 0.8366941937135907, "percentage": 65.35, "elapsed_time": "15:09:02", "remaining_time": "8:01:59", "throughput": 659.11, "total_tokens": 35949184} {"current_steps": 26145, "total_steps": 40000, "loss": 0.573, "lr": 1.3399042584301298e-05, "epoch": 0.8368542346840792, "percentage": 65.36, "elapsed_time": "15:09:03", "remaining_time": "8:01:44", "throughput": 659.21, "total_tokens": 35956032} {"current_steps": 26150, "total_steps": 40000, "loss": 0.7173, "lr": 1.3390347009247272e-05, "epoch": 0.8370142756545675, "percentage": 65.38, "elapsed_time": "15:09:05", "remaining_time": "8:01:29", "throughput": 659.31, "total_tokens": 35962608} {"current_steps": 26155, "total_steps": 40000, "loss": 0.8261, "lr": 1.3381653224547635e-05, "epoch": 0.837174316625056, "percentage": 65.39, "elapsed_time": "15:09:07", "remaining_time": "8:01:14", "throughput": 659.43, "total_tokens": 35970352} {"current_steps": 26160, "total_steps": 40000, "loss": 0.6368, "lr": 1.3372961231543086e-05, "epoch": 0.8373343575955444, "percentage": 65.4, "elapsed_time": "15:09:09", "remaining_time": "8:00:59", "throughput": 659.53, "total_tokens": 35976784} {"current_steps": 26165, "total_steps": 40000, "loss": 0.7885, "lr": 1.3364271031574016e-05, "epoch": 0.8374943985660329, "percentage": 65.41, "elapsed_time": "15:09:10", "remaining_time": "8:00:44", "throughput": 659.64, "total_tokens": 35983712} {"current_steps": 26170, "total_steps": 40000, "loss": 0.7957, "lr": 1.335558262598059e-05, "epoch": 0.8376544395365213, "percentage": 65.42, "elapsed_time": "15:09:12", "remaining_time": "8:00:29", "throughput": 659.74, "total_tokens": 35990560} {"current_steps": 26175, "total_steps": 40000, "loss": 0.8822, "lr": 1.3346896016102645e-05, "epoch": 0.8378144805070098, "percentage": 65.44, "elapsed_time": "15:09:14", "remaining_time": "8:00:14", "throughput": 659.85, "total_tokens": 35997520} {"current_steps": 26180, "total_steps": 40000, "loss": 0.6134, "lr": 1.3338211203279788e-05, "epoch": 0.8379745214774983, "percentage": 65.45, "elapsed_time": "15:09:16", "remaining_time": "7:59:59", "throughput": 659.95, "total_tokens": 36004064} {"current_steps": 26185, "total_steps": 40000, "loss": 0.7553, "lr": 1.3329528188851303e-05, "epoch": 0.8381345624479867, "percentage": 65.46, "elapsed_time": "15:09:17", "remaining_time": "7:59:44", "throughput": 660.05, "total_tokens": 36010944} {"current_steps": 26190, "total_steps": 40000, "loss": 0.7201, "lr": 1.3320846974156242e-05, "epoch": 0.8382946034184752, "percentage": 65.48, "elapsed_time": "15:09:19", "remaining_time": "7:59:29", "throughput": 660.15, "total_tokens": 36017488} {"current_steps": 26195, "total_steps": 40000, "loss": 0.753, "lr": 1.3312167560533337e-05, "epoch": 0.8384546443889636, "percentage": 65.49, "elapsed_time": "15:09:21", "remaining_time": "7:59:14", "throughput": 660.26, "total_tokens": 36024416} {"current_steps": 26200, "total_steps": 40000, "loss": 0.6129, "lr": 1.3303489949321082e-05, "epoch": 0.838614685359452, "percentage": 65.5, "elapsed_time": "15:09:23", "remaining_time": "7:58:59", "throughput": 660.36, "total_tokens": 36031296} {"current_steps": 26200, "total_steps": 40000, "eval_loss": 0.7355942130088806, "epoch": 0.838614685359452, "percentage": 65.5, "elapsed_time": "15:15:10", "remaining_time": "8:02:02", "throughput": 656.18, "total_tokens": 36031296} {"current_steps": 26205, "total_steps": 40000, "loss": 0.5848, "lr": 1.3294814141857653e-05, "epoch": 0.8387747263299404, "percentage": 65.51, "elapsed_time": "15:15:14", "remaining_time": "8:01:48", "throughput": 656.26, "total_tokens": 36038224} {"current_steps": 26210, "total_steps": 40000, "loss": 0.5928, "lr": 1.3286140139480992e-05, "epoch": 0.8389347673004289, "percentage": 65.53, "elapsed_time": "15:15:16", "remaining_time": "8:01:33", "throughput": 656.37, "total_tokens": 36045344} {"current_steps": 26215, "total_steps": 40000, "loss": 0.6589, "lr": 1.3277467943528719e-05, "epoch": 0.8390948082709173, "percentage": 65.54, "elapsed_time": "15:15:17", "remaining_time": "8:01:18", "throughput": 656.47, "total_tokens": 36052096} {"current_steps": 26220, "total_steps": 40000, "loss": 0.8015, "lr": 1.3268797555338203e-05, "epoch": 0.8392548492414058, "percentage": 65.55, "elapsed_time": "15:15:19", "remaining_time": "8:01:03", "throughput": 656.58, "total_tokens": 36059152} {"current_steps": 26225, "total_steps": 40000, "loss": 0.7381, "lr": 1.3260128976246533e-05, "epoch": 0.8394148902118942, "percentage": 65.56, "elapsed_time": "15:15:21", "remaining_time": "8:00:48", "throughput": 656.68, "total_tokens": 36065840} {"current_steps": 26230, "total_steps": 40000, "loss": 0.8569, "lr": 1.32514622075905e-05, "epoch": 0.8395749311823827, "percentage": 65.58, "elapsed_time": "15:15:23", "remaining_time": "8:00:33", "throughput": 656.79, "total_tokens": 36073024} {"current_steps": 26235, "total_steps": 40000, "loss": 0.8127, "lr": 1.3242797250706638e-05, "epoch": 0.8397349721528712, "percentage": 65.59, "elapsed_time": "15:15:24", "remaining_time": "8:00:18", "throughput": 656.89, "total_tokens": 36079808} {"current_steps": 26240, "total_steps": 40000, "loss": 0.77, "lr": 1.3234134106931195e-05, "epoch": 0.8398950131233596, "percentage": 65.6, "elapsed_time": "15:15:26", "remaining_time": "8:00:02", "throughput": 656.99, "total_tokens": 36086400} {"current_steps": 26245, "total_steps": 40000, "loss": 0.8004, "lr": 1.322547277760013e-05, "epoch": 0.8400550540938481, "percentage": 65.61, "elapsed_time": "15:15:28", "remaining_time": "7:59:47", "throughput": 657.1, "total_tokens": 36093584} {"current_steps": 26250, "total_steps": 40000, "loss": 0.6531, "lr": 1.3216813264049132e-05, "epoch": 0.8402150950643364, "percentage": 65.62, "elapsed_time": "15:15:30", "remaining_time": "7:59:32", "throughput": 657.21, "total_tokens": 36100368} {"current_steps": 26255, "total_steps": 40000, "loss": 0.8272, "lr": 1.32081555676136e-05, "epoch": 0.8403751360348249, "percentage": 65.64, "elapsed_time": "15:15:31", "remaining_time": "7:59:17", "throughput": 657.31, "total_tokens": 36107200} {"current_steps": 26260, "total_steps": 40000, "loss": 0.584, "lr": 1.3199499689628674e-05, "epoch": 0.8405351770053133, "percentage": 65.65, "elapsed_time": "15:15:33", "remaining_time": "7:59:02", "throughput": 657.41, "total_tokens": 36114048} {"current_steps": 26265, "total_steps": 40000, "loss": 0.84, "lr": 1.3190845631429192e-05, "epoch": 0.8406952179758018, "percentage": 65.66, "elapsed_time": "15:15:35", "remaining_time": "7:58:47", "throughput": 657.53, "total_tokens": 36121600} {"current_steps": 26270, "total_steps": 40000, "loss": 0.4229, "lr": 1.3182193394349704e-05, "epoch": 0.8408552589462902, "percentage": 65.67, "elapsed_time": "15:15:37", "remaining_time": "7:58:32", "throughput": 657.63, "total_tokens": 36128288} {"current_steps": 26275, "total_steps": 40000, "loss": 0.5755, "lr": 1.3173542979724507e-05, "epoch": 0.8410152999167787, "percentage": 65.69, "elapsed_time": "15:15:38", "remaining_time": "7:58:17", "throughput": 657.74, "total_tokens": 36135264} {"current_steps": 26280, "total_steps": 40000, "loss": 0.5945, "lr": 1.3164894388887617e-05, "epoch": 0.8411753408872671, "percentage": 65.7, "elapsed_time": "15:15:40", "remaining_time": "7:58:02", "throughput": 657.84, "total_tokens": 36142224} {"current_steps": 26285, "total_steps": 40000, "loss": 0.5772, "lr": 1.3156247623172727e-05, "epoch": 0.8413353818577556, "percentage": 65.71, "elapsed_time": "15:15:42", "remaining_time": "7:57:47", "throughput": 657.94, "total_tokens": 36148752} {"current_steps": 26290, "total_steps": 40000, "loss": 0.8, "lr": 1.3147602683913302e-05, "epoch": 0.8414954228282441, "percentage": 65.72, "elapsed_time": "15:15:43", "remaining_time": "7:57:32", "throughput": 658.04, "total_tokens": 36155344} {"current_steps": 26295, "total_steps": 40000, "loss": 0.5845, "lr": 1.3138959572442481e-05, "epoch": 0.8416554637987325, "percentage": 65.74, "elapsed_time": "15:15:45", "remaining_time": "7:57:17", "throughput": 658.14, "total_tokens": 36162016} {"current_steps": 26300, "total_steps": 40000, "loss": 0.6773, "lr": 1.3130318290093146e-05, "epoch": 0.841815504769221, "percentage": 65.75, "elapsed_time": "15:15:47", "remaining_time": "7:57:02", "throughput": 658.25, "total_tokens": 36168912} {"current_steps": 26305, "total_steps": 40000, "loss": 0.8721, "lr": 1.3121678838197909e-05, "epoch": 0.8419755457397093, "percentage": 65.76, "elapsed_time": "15:15:49", "remaining_time": "7:56:47", "throughput": 658.35, "total_tokens": 36175584} {"current_steps": 26310, "total_steps": 40000, "loss": 0.747, "lr": 1.3113041218089056e-05, "epoch": 0.8421355867101978, "percentage": 65.77, "elapsed_time": "15:15:50", "remaining_time": "7:56:32", "throughput": 658.46, "total_tokens": 36182720} {"current_steps": 26315, "total_steps": 40000, "loss": 0.9302, "lr": 1.3104405431098626e-05, "epoch": 0.8422956276806862, "percentage": 65.79, "elapsed_time": "15:15:52", "remaining_time": "7:56:17", "throughput": 658.56, "total_tokens": 36189520} {"current_steps": 26320, "total_steps": 40000, "loss": 0.6439, "lr": 1.3095771478558377e-05, "epoch": 0.8424556686511747, "percentage": 65.8, "elapsed_time": "15:15:54", "remaining_time": "7:56:02", "throughput": 658.66, "total_tokens": 36196288} {"current_steps": 26325, "total_steps": 40000, "loss": 0.7172, "lr": 1.3087139361799766e-05, "epoch": 0.8426157096216631, "percentage": 65.81, "elapsed_time": "15:15:56", "remaining_time": "7:55:47", "throughput": 658.77, "total_tokens": 36203168} {"current_steps": 26330, "total_steps": 40000, "loss": 0.8435, "lr": 1.3078509082153964e-05, "epoch": 0.8427757505921516, "percentage": 65.83, "elapsed_time": "15:15:57", "remaining_time": "7:55:32", "throughput": 658.87, "total_tokens": 36210256} {"current_steps": 26335, "total_steps": 40000, "loss": 0.9618, "lr": 1.3069880640951885e-05, "epoch": 0.8429357915626401, "percentage": 65.84, "elapsed_time": "15:15:59", "remaining_time": "7:55:18", "throughput": 658.98, "total_tokens": 36216992} {"current_steps": 26340, "total_steps": 40000, "loss": 0.6439, "lr": 1.3061254039524123e-05, "epoch": 0.8430958325331285, "percentage": 65.85, "elapsed_time": "15:16:01", "remaining_time": "7:55:03", "throughput": 659.08, "total_tokens": 36223648} {"current_steps": 26345, "total_steps": 40000, "loss": 0.7178, "lr": 1.3052629279201028e-05, "epoch": 0.843255873503617, "percentage": 65.86, "elapsed_time": "15:16:03", "remaining_time": "7:54:48", "throughput": 659.18, "total_tokens": 36230640} {"current_steps": 26350, "total_steps": 40000, "loss": 0.6623, "lr": 1.3044006361312633e-05, "epoch": 0.8434159144741054, "percentage": 65.88, "elapsed_time": "15:16:04", "remaining_time": "7:54:33", "throughput": 659.29, "total_tokens": 36237568} {"current_steps": 26355, "total_steps": 40000, "loss": 0.8621, "lr": 1.30353852871887e-05, "epoch": 0.8435759554445939, "percentage": 65.89, "elapsed_time": "15:16:06", "remaining_time": "7:54:18", "throughput": 659.39, "total_tokens": 36244432} {"current_steps": 26360, "total_steps": 40000, "loss": 0.7398, "lr": 1.302676605815873e-05, "epoch": 0.8437359964150822, "percentage": 65.9, "elapsed_time": "15:16:08", "remaining_time": "7:54:03", "throughput": 659.5, "total_tokens": 36251344} {"current_steps": 26365, "total_steps": 40000, "loss": 0.6942, "lr": 1.3018148675551884e-05, "epoch": 0.8438960373855707, "percentage": 65.91, "elapsed_time": "15:16:09", "remaining_time": "7:53:48", "throughput": 659.62, "total_tokens": 36259216} {"current_steps": 26370, "total_steps": 40000, "loss": 0.6903, "lr": 1.3009533140697094e-05, "epoch": 0.8440560783560591, "percentage": 65.92, "elapsed_time": "15:16:11", "remaining_time": "7:53:33", "throughput": 659.73, "total_tokens": 36266368} {"current_steps": 26375, "total_steps": 40000, "loss": 0.7811, "lr": 1.3000919454922966e-05, "epoch": 0.8442161193265476, "percentage": 65.94, "elapsed_time": "15:16:13", "remaining_time": "7:53:18", "throughput": 659.83, "total_tokens": 36273136} {"current_steps": 26380, "total_steps": 40000, "loss": 0.7203, "lr": 1.299230761955785e-05, "epoch": 0.844376160297036, "percentage": 65.95, "elapsed_time": "15:16:15", "remaining_time": "7:53:03", "throughput": 659.94, "total_tokens": 36280336} {"current_steps": 26385, "total_steps": 40000, "loss": 0.6969, "lr": 1.2983697635929807e-05, "epoch": 0.8445362012675245, "percentage": 65.96, "elapsed_time": "15:16:16", "remaining_time": "7:52:48", "throughput": 660.05, "total_tokens": 36287488} {"current_steps": 26390, "total_steps": 40000, "loss": 0.7381, "lr": 1.2975089505366584e-05, "epoch": 0.844696242238013, "percentage": 65.97, "elapsed_time": "15:16:18", "remaining_time": "7:52:33", "throughput": 660.16, "total_tokens": 36294656} {"current_steps": 26395, "total_steps": 40000, "loss": 0.9801, "lr": 1.2966483229195683e-05, "epoch": 0.8448562832085014, "percentage": 65.99, "elapsed_time": "15:16:20", "remaining_time": "7:52:19", "throughput": 660.26, "total_tokens": 36301440} {"current_steps": 26400, "total_steps": 40000, "loss": 0.7504, "lr": 1.2957878808744283e-05, "epoch": 0.8450163241789899, "percentage": 66.0, "elapsed_time": "15:16:22", "remaining_time": "7:52:04", "throughput": 660.36, "total_tokens": 36307968} {"current_steps": 26400, "total_steps": 40000, "eval_loss": 0.7347632646560669, "epoch": 0.8450163241789899, "percentage": 66.0, "elapsed_time": "15:22:09", "remaining_time": "7:55:03", "throughput": 656.21, "total_tokens": 36307968} {"current_steps": 26405, "total_steps": 40000, "loss": 0.7827, "lr": 1.294927624533931e-05, "epoch": 0.8451763651494782, "percentage": 66.01, "elapsed_time": "15:22:13", "remaining_time": "7:54:49", "throughput": 656.29, "total_tokens": 36314560} {"current_steps": 26410, "total_steps": 40000, "loss": 0.6898, "lr": 1.2940675540307378e-05, "epoch": 0.8453364061199667, "percentage": 66.03, "elapsed_time": "15:22:15", "remaining_time": "7:54:34", "throughput": 656.39, "total_tokens": 36321168} {"current_steps": 26415, "total_steps": 40000, "loss": 0.7393, "lr": 1.2932076694974814e-05, "epoch": 0.8454964470904551, "percentage": 66.04, "elapsed_time": "15:22:16", "remaining_time": "7:54:19", "throughput": 656.49, "total_tokens": 36328304} {"current_steps": 26420, "total_steps": 40000, "loss": 0.894, "lr": 1.2923479710667682e-05, "epoch": 0.8456564880609436, "percentage": 66.05, "elapsed_time": "15:22:18", "remaining_time": "7:54:04", "throughput": 656.6, "total_tokens": 36335072} {"current_steps": 26425, "total_steps": 40000, "loss": 0.5709, "lr": 1.2914884588711751e-05, "epoch": 0.845816529031432, "percentage": 66.06, "elapsed_time": "15:22:20", "remaining_time": "7:53:49", "throughput": 656.7, "total_tokens": 36341808} {"current_steps": 26430, "total_steps": 40000, "loss": 0.8621, "lr": 1.2906291330432475e-05, "epoch": 0.8459765700019205, "percentage": 66.07, "elapsed_time": "15:22:22", "remaining_time": "7:53:34", "throughput": 656.79, "total_tokens": 36348224} {"current_steps": 26435, "total_steps": 40000, "loss": 0.8539, "lr": 1.2897699937155055e-05, "epoch": 0.8461366109724089, "percentage": 66.09, "elapsed_time": "15:22:23", "remaining_time": "7:53:19", "throughput": 656.89, "total_tokens": 36354896} {"current_steps": 26440, "total_steps": 40000, "loss": 0.5503, "lr": 1.2889110410204403e-05, "epoch": 0.8462966519428974, "percentage": 66.1, "elapsed_time": "15:22:25", "remaining_time": "7:53:04", "throughput": 657.0, "total_tokens": 36361792} {"current_steps": 26445, "total_steps": 40000, "loss": 0.9668, "lr": 1.2880522750905111e-05, "epoch": 0.8464566929133859, "percentage": 66.11, "elapsed_time": "15:22:27", "remaining_time": "7:52:49", "throughput": 657.1, "total_tokens": 36368832} {"current_steps": 26450, "total_steps": 40000, "loss": 0.7821, "lr": 1.2871936960581523e-05, "epoch": 0.8466167338838743, "percentage": 66.12, "elapsed_time": "15:22:28", "remaining_time": "7:52:34", "throughput": 657.2, "total_tokens": 36375536} {"current_steps": 26455, "total_steps": 40000, "loss": 0.7394, "lr": 1.2863353040557658e-05, "epoch": 0.8467767748543628, "percentage": 66.14, "elapsed_time": "15:22:30", "remaining_time": "7:52:19", "throughput": 657.3, "total_tokens": 36381968} {"current_steps": 26460, "total_steps": 40000, "loss": 1.1803, "lr": 1.2854770992157273e-05, "epoch": 0.8469368158248511, "percentage": 66.15, "elapsed_time": "15:22:32", "remaining_time": "7:52:04", "throughput": 657.4, "total_tokens": 36388704} {"current_steps": 26465, "total_steps": 40000, "loss": 0.9022, "lr": 1.2846190816703835e-05, "epoch": 0.8470968567953396, "percentage": 66.16, "elapsed_time": "15:22:34", "remaining_time": "7:51:49", "throughput": 657.5, "total_tokens": 36395216} {"current_steps": 26470, "total_steps": 40000, "loss": 0.6397, "lr": 1.2837612515520498e-05, "epoch": 0.847256897765828, "percentage": 66.17, "elapsed_time": "15:22:35", "remaining_time": "7:51:34", "throughput": 657.6, "total_tokens": 36401792} {"current_steps": 26475, "total_steps": 40000, "loss": 0.7578, "lr": 1.2829036089930163e-05, "epoch": 0.8474169387363165, "percentage": 66.19, "elapsed_time": "15:22:37", "remaining_time": "7:51:19", "throughput": 657.71, "total_tokens": 36409232} {"current_steps": 26480, "total_steps": 40000, "loss": 0.807, "lr": 1.2820461541255412e-05, "epoch": 0.8475769797068049, "percentage": 66.2, "elapsed_time": "15:22:39", "remaining_time": "7:51:05", "throughput": 657.81, "total_tokens": 36416128} {"current_steps": 26485, "total_steps": 40000, "loss": 0.8162, "lr": 1.2811888870818543e-05, "epoch": 0.8477370206772934, "percentage": 66.21, "elapsed_time": "15:22:41", "remaining_time": "7:50:50", "throughput": 657.92, "total_tokens": 36422976} {"current_steps": 26490, "total_steps": 40000, "loss": 0.6996, "lr": 1.2803318079941581e-05, "epoch": 0.8478970616477818, "percentage": 66.22, "elapsed_time": "15:22:42", "remaining_time": "7:50:35", "throughput": 658.02, "total_tokens": 36429792} {"current_steps": 26495, "total_steps": 40000, "loss": 0.8045, "lr": 1.2794749169946235e-05, "epoch": 0.8480571026182703, "percentage": 66.24, "elapsed_time": "15:22:44", "remaining_time": "7:50:20", "throughput": 658.12, "total_tokens": 36436528} {"current_steps": 26500, "total_steps": 40000, "loss": 0.743, "lr": 1.2786182142153952e-05, "epoch": 0.8482171435887588, "percentage": 66.25, "elapsed_time": "15:22:46", "remaining_time": "7:50:05", "throughput": 658.22, "total_tokens": 36443120} {"current_steps": 26505, "total_steps": 40000, "loss": 0.5607, "lr": 1.2777616997885878e-05, "epoch": 0.8483771845592472, "percentage": 66.26, "elapsed_time": "15:22:48", "remaining_time": "7:49:50", "throughput": 658.32, "total_tokens": 36450016} {"current_steps": 26510, "total_steps": 40000, "loss": 0.8439, "lr": 1.2769053738462847e-05, "epoch": 0.8485372255297357, "percentage": 66.27, "elapsed_time": "15:22:49", "remaining_time": "7:49:35", "throughput": 658.43, "total_tokens": 36457104} {"current_steps": 26515, "total_steps": 40000, "loss": 0.861, "lr": 1.2760492365205434e-05, "epoch": 0.848697266500224, "percentage": 66.29, "elapsed_time": "15:22:51", "remaining_time": "7:49:20", "throughput": 658.53, "total_tokens": 36463952} {"current_steps": 26520, "total_steps": 40000, "loss": 0.8294, "lr": 1.2751932879433919e-05, "epoch": 0.8488573074707125, "percentage": 66.3, "elapsed_time": "15:22:53", "remaining_time": "7:49:06", "throughput": 658.63, "total_tokens": 36470688} {"current_steps": 26525, "total_steps": 40000, "loss": 0.8078, "lr": 1.2743375282468267e-05, "epoch": 0.8490173484412009, "percentage": 66.31, "elapsed_time": "15:22:55", "remaining_time": "7:48:51", "throughput": 658.74, "total_tokens": 36477584} {"current_steps": 26530, "total_steps": 40000, "loss": 0.7744, "lr": 1.2734819575628182e-05, "epoch": 0.8491773894116894, "percentage": 66.33, "elapsed_time": "15:22:56", "remaining_time": "7:48:36", "throughput": 658.84, "total_tokens": 36484208} {"current_steps": 26535, "total_steps": 40000, "loss": 0.7098, "lr": 1.2726265760233039e-05, "epoch": 0.8493374303821778, "percentage": 66.34, "elapsed_time": "15:22:58", "remaining_time": "7:48:21", "throughput": 658.94, "total_tokens": 36491024} {"current_steps": 26540, "total_steps": 40000, "loss": 0.6912, "lr": 1.271771383760197e-05, "epoch": 0.8494974713526663, "percentage": 66.35, "elapsed_time": "15:23:00", "remaining_time": "7:48:06", "throughput": 659.05, "total_tokens": 36498080} {"current_steps": 26545, "total_steps": 40000, "loss": 0.7809, "lr": 1.2709163809053764e-05, "epoch": 0.8496575123231547, "percentage": 66.36, "elapsed_time": "15:23:01", "remaining_time": "7:47:51", "throughput": 659.15, "total_tokens": 36504928} {"current_steps": 26550, "total_steps": 40000, "loss": 0.5106, "lr": 1.2700615675906963e-05, "epoch": 0.8498175532936432, "percentage": 66.38, "elapsed_time": "15:23:03", "remaining_time": "7:47:36", "throughput": 659.26, "total_tokens": 36512112} {"current_steps": 26555, "total_steps": 40000, "loss": 0.7935, "lr": 1.269206943947978e-05, "epoch": 0.8499775942641317, "percentage": 66.39, "elapsed_time": "15:23:05", "remaining_time": "7:47:22", "throughput": 659.36, "total_tokens": 36519056} {"current_steps": 26560, "total_steps": 40000, "loss": 0.7162, "lr": 1.2683525101090177e-05, "epoch": 0.85013763523462, "percentage": 66.4, "elapsed_time": "15:23:07", "remaining_time": "7:47:07", "throughput": 659.46, "total_tokens": 36525712} {"current_steps": 26565, "total_steps": 40000, "loss": 0.6911, "lr": 1.2674982662055765e-05, "epoch": 0.8502976762051085, "percentage": 66.41, "elapsed_time": "15:23:08", "remaining_time": "7:46:52", "throughput": 659.57, "total_tokens": 36532800} {"current_steps": 26570, "total_steps": 40000, "loss": 0.8847, "lr": 1.2666442123693922e-05, "epoch": 0.8504577171755969, "percentage": 66.42, "elapsed_time": "15:23:10", "remaining_time": "7:46:37", "throughput": 659.67, "total_tokens": 36539504} {"current_steps": 26575, "total_steps": 40000, "loss": 0.7718, "lr": 1.265790348732169e-05, "epoch": 0.8506177581460854, "percentage": 66.44, "elapsed_time": "15:23:12", "remaining_time": "7:46:22", "throughput": 659.78, "total_tokens": 36546640} {"current_steps": 26580, "total_steps": 40000, "loss": 0.6547, "lr": 1.264936675425584e-05, "epoch": 0.8507777991165738, "percentage": 66.45, "elapsed_time": "15:23:14", "remaining_time": "7:46:07", "throughput": 659.87, "total_tokens": 36553136} {"current_steps": 26585, "total_steps": 40000, "loss": 0.8146, "lr": 1.2640831925812852e-05, "epoch": 0.8509378400870623, "percentage": 66.46, "elapsed_time": "15:23:15", "remaining_time": "7:45:53", "throughput": 659.98, "total_tokens": 36559952} {"current_steps": 26590, "total_steps": 40000, "loss": 0.9387, "lr": 1.263229900330889e-05, "epoch": 0.8510978810575507, "percentage": 66.47, "elapsed_time": "15:23:17", "remaining_time": "7:45:38", "throughput": 660.08, "total_tokens": 36566800} {"current_steps": 26595, "total_steps": 40000, "loss": 0.5242, "lr": 1.2623767988059843e-05, "epoch": 0.8512579220280392, "percentage": 66.49, "elapsed_time": "15:23:19", "remaining_time": "7:45:23", "throughput": 660.18, "total_tokens": 36573504} {"current_steps": 26600, "total_steps": 40000, "loss": 0.9538, "lr": 1.2615238881381309e-05, "epoch": 0.8514179629985277, "percentage": 66.5, "elapsed_time": "15:23:21", "remaining_time": "7:45:08", "throughput": 660.28, "total_tokens": 36580432} {"current_steps": 26600, "total_steps": 40000, "eval_loss": 0.7344503998756409, "epoch": 0.8514179629985277, "percentage": 66.5, "elapsed_time": "15:29:09", "remaining_time": "7:48:04", "throughput": 656.16, "total_tokens": 36580432} {"current_steps": 26605, "total_steps": 40000, "loss": 0.7764, "lr": 1.2606711684588568e-05, "epoch": 0.8515780039690161, "percentage": 66.51, "elapsed_time": "15:29:12", "remaining_time": "7:47:50", "throughput": 656.24, "total_tokens": 36587424} {"current_steps": 26610, "total_steps": 40000, "loss": 0.6289, "lr": 1.2598186398996636e-05, "epoch": 0.8517380449395046, "percentage": 66.53, "elapsed_time": "15:29:14", "remaining_time": "7:47:35", "throughput": 656.34, "total_tokens": 36594048} {"current_steps": 26615, "total_steps": 40000, "loss": 0.9257, "lr": 1.2589663025920207e-05, "epoch": 0.8518980859099929, "percentage": 66.54, "elapsed_time": "15:29:16", "remaining_time": "7:47:20", "throughput": 656.44, "total_tokens": 36600640} {"current_steps": 26620, "total_steps": 40000, "loss": 0.883, "lr": 1.2581141566673705e-05, "epoch": 0.8520581268804814, "percentage": 66.55, "elapsed_time": "15:29:18", "remaining_time": "7:47:05", "throughput": 656.54, "total_tokens": 36607376} {"current_steps": 26625, "total_steps": 40000, "loss": 0.7315, "lr": 1.257262202257124e-05, "epoch": 0.8522181678509698, "percentage": 66.56, "elapsed_time": "15:29:19", "remaining_time": "7:46:50", "throughput": 656.64, "total_tokens": 36614288} {"current_steps": 26630, "total_steps": 40000, "loss": 0.8835, "lr": 1.2564104394926618e-05, "epoch": 0.8523782088214583, "percentage": 66.57, "elapsed_time": "15:29:21", "remaining_time": "7:46:36", "throughput": 656.75, "total_tokens": 36621600} {"current_steps": 26635, "total_steps": 40000, "loss": 1.165, "lr": 1.2555588685053383e-05, "epoch": 0.8525382497919467, "percentage": 66.59, "elapsed_time": "15:29:23", "remaining_time": "7:46:21", "throughput": 656.85, "total_tokens": 36628368} {"current_steps": 26640, "total_steps": 40000, "loss": 0.7789, "lr": 1.2547074894264762e-05, "epoch": 0.8526982907624352, "percentage": 66.6, "elapsed_time": "15:29:25", "remaining_time": "7:46:06", "throughput": 656.97, "total_tokens": 36635840} {"current_steps": 26645, "total_steps": 40000, "loss": 0.7784, "lr": 1.2538563023873679e-05, "epoch": 0.8528583317329236, "percentage": 66.61, "elapsed_time": "15:29:26", "remaining_time": "7:45:51", "throughput": 657.07, "total_tokens": 36642688} {"current_steps": 26650, "total_steps": 40000, "loss": 0.7641, "lr": 1.2530053075192789e-05, "epoch": 0.8530183727034121, "percentage": 66.62, "elapsed_time": "15:29:28", "remaining_time": "7:45:36", "throughput": 657.17, "total_tokens": 36649600} {"current_steps": 26655, "total_steps": 40000, "loss": 1.1285, "lr": 1.252154504953441e-05, "epoch": 0.8531784136739006, "percentage": 66.64, "elapsed_time": "15:29:30", "remaining_time": "7:45:21", "throughput": 657.27, "total_tokens": 36656432} {"current_steps": 26660, "total_steps": 40000, "loss": 0.6934, "lr": 1.25130389482106e-05, "epoch": 0.853338454644389, "percentage": 66.65, "elapsed_time": "15:29:32", "remaining_time": "7:45:06", "throughput": 657.38, "total_tokens": 36663360} {"current_steps": 26665, "total_steps": 40000, "loss": 0.677, "lr": 1.2504534772533116e-05, "epoch": 0.8534984956148775, "percentage": 66.66, "elapsed_time": "15:29:33", "remaining_time": "7:44:52", "throughput": 657.48, "total_tokens": 36670032} {"current_steps": 26670, "total_steps": 40000, "loss": 0.6801, "lr": 1.2496032523813387e-05, "epoch": 0.8536585365853658, "percentage": 66.67, "elapsed_time": "15:29:35", "remaining_time": "7:44:37", "throughput": 657.58, "total_tokens": 36676704} {"current_steps": 26675, "total_steps": 40000, "loss": 1.1558, "lr": 1.2487532203362576e-05, "epoch": 0.8538185775558543, "percentage": 66.69, "elapsed_time": "15:29:37", "remaining_time": "7:44:22", "throughput": 657.68, "total_tokens": 36683472} {"current_steps": 26680, "total_steps": 40000, "loss": 0.7227, "lr": 1.247903381249155e-05, "epoch": 0.8539786185263427, "percentage": 66.7, "elapsed_time": "15:29:39", "remaining_time": "7:44:07", "throughput": 657.78, "total_tokens": 36690496} {"current_steps": 26685, "total_steps": 40000, "loss": 0.7662, "lr": 1.2470537352510853e-05, "epoch": 0.8541386594968312, "percentage": 66.71, "elapsed_time": "15:29:40", "remaining_time": "7:43:52", "throughput": 657.89, "total_tokens": 36697696} {"current_steps": 26690, "total_steps": 40000, "loss": 0.7121, "lr": 1.2462042824730758e-05, "epoch": 0.8542987004673196, "percentage": 66.72, "elapsed_time": "15:29:42", "remaining_time": "7:43:38", "throughput": 657.99, "total_tokens": 36704384} {"current_steps": 26695, "total_steps": 40000, "loss": 0.7547, "lr": 1.245355023046122e-05, "epoch": 0.8544587414378081, "percentage": 66.74, "elapsed_time": "15:29:44", "remaining_time": "7:43:23", "throughput": 658.1, "total_tokens": 36711424} {"current_steps": 26700, "total_steps": 40000, "loss": 0.5914, "lr": 1.2445059571011896e-05, "epoch": 0.8546187824082965, "percentage": 66.75, "elapsed_time": "15:29:46", "remaining_time": "7:43:08", "throughput": 658.2, "total_tokens": 36718304} {"current_steps": 26705, "total_steps": 40000, "loss": 0.6629, "lr": 1.2436570847692173e-05, "epoch": 0.854778823378785, "percentage": 66.76, "elapsed_time": "15:29:47", "remaining_time": "7:42:53", "throughput": 658.3, "total_tokens": 36725104} {"current_steps": 26710, "total_steps": 40000, "loss": 0.7383, "lr": 1.2428084061811096e-05, "epoch": 0.8549388643492735, "percentage": 66.77, "elapsed_time": "15:29:49", "remaining_time": "7:42:38", "throughput": 658.4, "total_tokens": 36731712} {"current_steps": 26715, "total_steps": 40000, "loss": 0.6307, "lr": 1.2419599214677447e-05, "epoch": 0.8550989053197618, "percentage": 66.79, "elapsed_time": "15:29:51", "remaining_time": "7:42:24", "throughput": 658.5, "total_tokens": 36738640} {"current_steps": 26720, "total_steps": 40000, "loss": 0.7289, "lr": 1.2411116307599702e-05, "epoch": 0.8552589462902503, "percentage": 66.8, "elapsed_time": "15:29:52", "remaining_time": "7:42:09", "throughput": 658.6, "total_tokens": 36745232} {"current_steps": 26725, "total_steps": 40000, "loss": 0.9511, "lr": 1.2402635341886016e-05, "epoch": 0.8554189872607387, "percentage": 66.81, "elapsed_time": "15:29:54", "remaining_time": "7:41:54", "throughput": 658.71, "total_tokens": 36752432} {"current_steps": 26730, "total_steps": 40000, "loss": 0.6986, "lr": 1.2394156318844278e-05, "epoch": 0.8555790282312272, "percentage": 66.83, "elapsed_time": "15:29:56", "remaining_time": "7:41:39", "throughput": 658.81, "total_tokens": 36759328} {"current_steps": 26735, "total_steps": 40000, "loss": 0.5952, "lr": 1.2385679239782039e-05, "epoch": 0.8557390692017156, "percentage": 66.84, "elapsed_time": "15:29:58", "remaining_time": "7:41:25", "throughput": 658.91, "total_tokens": 36765696} {"current_steps": 26740, "total_steps": 40000, "loss": 0.7593, "lr": 1.2377204106006585e-05, "epoch": 0.8558991101722041, "percentage": 66.85, "elapsed_time": "15:29:59", "remaining_time": "7:41:10", "throughput": 659.01, "total_tokens": 36772752} {"current_steps": 26745, "total_steps": 40000, "loss": 0.6498, "lr": 1.2368730918824891e-05, "epoch": 0.8560591511426925, "percentage": 66.86, "elapsed_time": "15:30:01", "remaining_time": "7:40:55", "throughput": 659.11, "total_tokens": 36779568} {"current_steps": 26750, "total_steps": 40000, "loss": 0.6743, "lr": 1.236025967954362e-05, "epoch": 0.856219192113181, "percentage": 66.88, "elapsed_time": "15:30:03", "remaining_time": "7:40:40", "throughput": 659.23, "total_tokens": 36787040} {"current_steps": 26755, "total_steps": 40000, "loss": 0.6349, "lr": 1.2351790389469153e-05, "epoch": 0.8563792330836694, "percentage": 66.89, "elapsed_time": "15:30:05", "remaining_time": "7:40:26", "throughput": 659.32, "total_tokens": 36793632} {"current_steps": 26760, "total_steps": 40000, "loss": 0.6074, "lr": 1.234332304990755e-05, "epoch": 0.8565392740541579, "percentage": 66.9, "elapsed_time": "15:30:06", "remaining_time": "7:40:11", "throughput": 659.42, "total_tokens": 36800032} {"current_steps": 26765, "total_steps": 40000, "loss": 0.8365, "lr": 1.2334857662164593e-05, "epoch": 0.8566993150246464, "percentage": 66.91, "elapsed_time": "15:30:08", "remaining_time": "7:39:56", "throughput": 659.52, "total_tokens": 36807024} {"current_steps": 26770, "total_steps": 40000, "loss": 0.8174, "lr": 1.2326394227545743e-05, "epoch": 0.8568593559951347, "percentage": 66.92, "elapsed_time": "15:30:10", "remaining_time": "7:39:42", "throughput": 659.62, "total_tokens": 36813696} {"current_steps": 26775, "total_steps": 40000, "loss": 0.795, "lr": 1.2317932747356162e-05, "epoch": 0.8570193969656232, "percentage": 66.94, "elapsed_time": "15:30:12", "remaining_time": "7:39:27", "throughput": 659.73, "total_tokens": 36820752} {"current_steps": 26780, "total_steps": 40000, "loss": 0.7358, "lr": 1.2309473222900726e-05, "epoch": 0.8571794379361116, "percentage": 66.95, "elapsed_time": "15:30:13", "remaining_time": "7:39:12", "throughput": 659.83, "total_tokens": 36827648} {"current_steps": 26785, "total_steps": 40000, "loss": 0.6386, "lr": 1.2301015655484006e-05, "epoch": 0.8573394789066001, "percentage": 66.96, "elapsed_time": "15:30:15", "remaining_time": "7:38:57", "throughput": 659.93, "total_tokens": 36834320} {"current_steps": 26790, "total_steps": 40000, "loss": 0.4963, "lr": 1.2292560046410245e-05, "epoch": 0.8574995198770885, "percentage": 66.97, "elapsed_time": "15:30:17", "remaining_time": "7:38:43", "throughput": 660.04, "total_tokens": 36841600} {"current_steps": 26795, "total_steps": 40000, "loss": 0.6396, "lr": 1.228410639698343e-05, "epoch": 0.857659560847577, "percentage": 66.99, "elapsed_time": "15:30:19", "remaining_time": "7:38:28", "throughput": 660.14, "total_tokens": 36848608} {"current_steps": 26800, "total_steps": 40000, "loss": 0.7165, "lr": 1.2275654708507195e-05, "epoch": 0.8578196018180654, "percentage": 67.0, "elapsed_time": "15:30:20", "remaining_time": "7:38:13", "throughput": 660.24, "total_tokens": 36855328} {"current_steps": 26800, "total_steps": 40000, "eval_loss": 0.7340035438537598, "epoch": 0.8578196018180654, "percentage": 67.0, "elapsed_time": "15:36:08", "remaining_time": "7:41:05", "throughput": 656.15, "total_tokens": 36855328} {"current_steps": 26805, "total_steps": 40000, "loss": 0.7468, "lr": 1.2267204982284908e-05, "epoch": 0.8579796427885539, "percentage": 67.01, "elapsed_time": "15:36:12", "remaining_time": "7:40:51", "throughput": 656.23, "total_tokens": 36861984} {"current_steps": 26810, "total_steps": 40000, "loss": 0.8203, "lr": 1.2258757219619635e-05, "epoch": 0.8581396837590423, "percentage": 67.03, "elapsed_time": "15:36:13", "remaining_time": "7:40:36", "throughput": 656.33, "total_tokens": 36868848} {"current_steps": 26815, "total_steps": 40000, "loss": 0.8671, "lr": 1.2250311421814104e-05, "epoch": 0.8582997247295308, "percentage": 67.04, "elapsed_time": "15:36:15", "remaining_time": "7:40:21", "throughput": 656.44, "total_tokens": 36876192} {"current_steps": 26820, "total_steps": 40000, "loss": 0.7275, "lr": 1.2241867590170772e-05, "epoch": 0.8584597657000193, "percentage": 67.05, "elapsed_time": "15:36:17", "remaining_time": "7:40:06", "throughput": 656.55, "total_tokens": 36883024} {"current_steps": 26825, "total_steps": 40000, "loss": 0.8516, "lr": 1.2233425725991799e-05, "epoch": 0.8586198066705076, "percentage": 67.06, "elapsed_time": "15:36:19", "remaining_time": "7:39:52", "throughput": 656.65, "total_tokens": 36890208} {"current_steps": 26830, "total_steps": 40000, "loss": 0.7746, "lr": 1.2224985830579003e-05, "epoch": 0.8587798476409961, "percentage": 67.07, "elapsed_time": "15:36:20", "remaining_time": "7:39:37", "throughput": 656.75, "total_tokens": 36897056} {"current_steps": 26835, "total_steps": 40000, "loss": 0.9902, "lr": 1.2216547905233944e-05, "epoch": 0.8589398886114845, "percentage": 67.09, "elapsed_time": "15:36:22", "remaining_time": "7:39:22", "throughput": 656.85, "total_tokens": 36903712} {"current_steps": 26840, "total_steps": 40000, "loss": 0.5985, "lr": 1.2208111951257842e-05, "epoch": 0.859099929581973, "percentage": 67.1, "elapsed_time": "15:36:24", "remaining_time": "7:39:07", "throughput": 656.96, "total_tokens": 36910848} {"current_steps": 26845, "total_steps": 40000, "loss": 0.8467, "lr": 1.2199677969951622e-05, "epoch": 0.8592599705524614, "percentage": 67.11, "elapsed_time": "15:36:26", "remaining_time": "7:38:53", "throughput": 657.07, "total_tokens": 36918192} {"current_steps": 26850, "total_steps": 40000, "loss": 0.7432, "lr": 1.2191245962615927e-05, "epoch": 0.8594200115229499, "percentage": 67.12, "elapsed_time": "15:36:27", "remaining_time": "7:38:38", "throughput": 657.17, "total_tokens": 36925056} {"current_steps": 26855, "total_steps": 40000, "loss": 0.6584, "lr": 1.218281593055106e-05, "epoch": 0.8595800524934383, "percentage": 67.14, "elapsed_time": "15:36:29", "remaining_time": "7:38:23", "throughput": 657.28, "total_tokens": 36932064} {"current_steps": 26860, "total_steps": 40000, "loss": 0.6589, "lr": 1.217438787505705e-05, "epoch": 0.8597400934639268, "percentage": 67.15, "elapsed_time": "15:36:31", "remaining_time": "7:38:08", "throughput": 657.37, "total_tokens": 36938592} {"current_steps": 26865, "total_steps": 40000, "loss": 0.7362, "lr": 1.2165961797433615e-05, "epoch": 0.8599001344344153, "percentage": 67.16, "elapsed_time": "15:36:33", "remaining_time": "7:37:54", "throughput": 657.48, "total_tokens": 36945600} {"current_steps": 26870, "total_steps": 40000, "loss": 0.8338, "lr": 1.215753769898014e-05, "epoch": 0.8600601754049036, "percentage": 67.17, "elapsed_time": "15:36:34", "remaining_time": "7:37:39", "throughput": 657.57, "total_tokens": 36952144} {"current_steps": 26875, "total_steps": 40000, "loss": 0.7306, "lr": 1.2149115580995755e-05, "epoch": 0.8602202163753921, "percentage": 67.19, "elapsed_time": "15:36:36", "remaining_time": "7:37:24", "throughput": 657.67, "total_tokens": 36958928} {"current_steps": 26880, "total_steps": 40000, "loss": 0.7889, "lr": 1.2140695444779227e-05, "epoch": 0.8603802573458805, "percentage": 67.2, "elapsed_time": "15:36:38", "remaining_time": "7:37:10", "throughput": 657.78, "total_tokens": 36965952} {"current_steps": 26885, "total_steps": 40000, "loss": 0.7076, "lr": 1.2132277291629066e-05, "epoch": 0.860540298316369, "percentage": 67.21, "elapsed_time": "15:36:39", "remaining_time": "7:36:55", "throughput": 657.89, "total_tokens": 36973152} {"current_steps": 26890, "total_steps": 40000, "loss": 0.8631, "lr": 1.2123861122843458e-05, "epoch": 0.8607003392868574, "percentage": 67.22, "elapsed_time": "15:36:41", "remaining_time": "7:36:40", "throughput": 657.99, "total_tokens": 36980192} {"current_steps": 26895, "total_steps": 40000, "loss": 0.7732, "lr": 1.2115446939720271e-05, "epoch": 0.8608603802573459, "percentage": 67.24, "elapsed_time": "15:36:43", "remaining_time": "7:36:25", "throughput": 658.1, "total_tokens": 36987392} {"current_steps": 26900, "total_steps": 40000, "loss": 0.6389, "lr": 1.210703474355708e-05, "epoch": 0.8610204212278343, "percentage": 67.25, "elapsed_time": "15:36:45", "remaining_time": "7:36:11", "throughput": 658.2, "total_tokens": 36994176} {"current_steps": 26905, "total_steps": 40000, "loss": 0.6547, "lr": 1.2098624535651164e-05, "epoch": 0.8611804621983228, "percentage": 67.26, "elapsed_time": "15:36:46", "remaining_time": "7:35:56", "throughput": 658.3, "total_tokens": 37000784} {"current_steps": 26910, "total_steps": 40000, "loss": 0.7877, "lr": 1.2090216317299477e-05, "epoch": 0.8613405031688112, "percentage": 67.27, "elapsed_time": "15:36:48", "remaining_time": "7:35:41", "throughput": 658.4, "total_tokens": 37007680} {"current_steps": 26915, "total_steps": 40000, "loss": 0.9205, "lr": 1.2081810089798668e-05, "epoch": 0.8615005441392997, "percentage": 67.29, "elapsed_time": "15:36:50", "remaining_time": "7:35:27", "throughput": 658.5, "total_tokens": 37014384} {"current_steps": 26920, "total_steps": 40000, "loss": 0.6852, "lr": 1.2073405854445072e-05, "epoch": 0.8616605851097882, "percentage": 67.3, "elapsed_time": "15:36:52", "remaining_time": "7:35:12", "throughput": 658.6, "total_tokens": 37021408} {"current_steps": 26925, "total_steps": 40000, "loss": 0.5312, "lr": 1.206500361253474e-05, "epoch": 0.8618206260802765, "percentage": 67.31, "elapsed_time": "15:36:53", "remaining_time": "7:34:57", "throughput": 658.7, "total_tokens": 37028176} {"current_steps": 26930, "total_steps": 40000, "loss": 0.8346, "lr": 1.2056603365363409e-05, "epoch": 0.861980667050765, "percentage": 67.33, "elapsed_time": "15:36:55", "remaining_time": "7:34:43", "throughput": 658.8, "total_tokens": 37034848} {"current_steps": 26935, "total_steps": 40000, "loss": 0.7169, "lr": 1.2048205114226487e-05, "epoch": 0.8621407080212534, "percentage": 67.34, "elapsed_time": "15:36:57", "remaining_time": "7:34:28", "throughput": 658.91, "total_tokens": 37042080} {"current_steps": 26940, "total_steps": 40000, "loss": 0.7188, "lr": 1.2039808860419102e-05, "epoch": 0.8623007489917419, "percentage": 67.35, "elapsed_time": "15:36:59", "remaining_time": "7:34:13", "throughput": 659.02, "total_tokens": 37049376} {"current_steps": 26945, "total_steps": 40000, "loss": 0.7939, "lr": 1.2031414605236066e-05, "epoch": 0.8624607899622303, "percentage": 67.36, "elapsed_time": "15:37:00", "remaining_time": "7:33:59", "throughput": 659.13, "total_tokens": 37056576} {"current_steps": 26950, "total_steps": 40000, "loss": 0.7405, "lr": 1.2023022349971862e-05, "epoch": 0.8626208309327188, "percentage": 67.38, "elapsed_time": "15:37:02", "remaining_time": "7:33:44", "throughput": 659.23, "total_tokens": 37063520} {"current_steps": 26955, "total_steps": 40000, "loss": 0.8538, "lr": 1.20146320959207e-05, "epoch": 0.8627808719032072, "percentage": 67.39, "elapsed_time": "15:37:04", "remaining_time": "7:33:30", "throughput": 659.33, "total_tokens": 37070560} {"current_steps": 26960, "total_steps": 40000, "loss": 0.8439, "lr": 1.2006243844376445e-05, "epoch": 0.8629409128736957, "percentage": 67.4, "elapsed_time": "15:37:06", "remaining_time": "7:33:15", "throughput": 659.43, "total_tokens": 37077200} {"current_steps": 26965, "total_steps": 40000, "loss": 0.544, "lr": 1.1997857596632678e-05, "epoch": 0.8631009538441841, "percentage": 67.41, "elapsed_time": "15:37:07", "remaining_time": "7:33:00", "throughput": 659.54, "total_tokens": 37084272} {"current_steps": 26970, "total_steps": 40000, "loss": 0.5522, "lr": 1.1989473353982672e-05, "epoch": 0.8632609948146726, "percentage": 67.42, "elapsed_time": "15:37:09", "remaining_time": "7:32:46", "throughput": 659.63, "total_tokens": 37090864} {"current_steps": 26975, "total_steps": 40000, "loss": 0.7542, "lr": 1.198109111771937e-05, "epoch": 0.863421035785161, "percentage": 67.44, "elapsed_time": "15:37:11", "remaining_time": "7:32:31", "throughput": 659.73, "total_tokens": 37097712} {"current_steps": 26980, "total_steps": 40000, "loss": 0.6915, "lr": 1.197271088913543e-05, "epoch": 0.8635810767556494, "percentage": 67.45, "elapsed_time": "15:37:13", "remaining_time": "7:32:16", "throughput": 659.84, "total_tokens": 37104736} {"current_steps": 26985, "total_steps": 40000, "loss": 0.7273, "lr": 1.1964332669523182e-05, "epoch": 0.8637411177261379, "percentage": 67.46, "elapsed_time": "15:37:14", "remaining_time": "7:32:02", "throughput": 659.95, "total_tokens": 37112064} {"current_steps": 26990, "total_steps": 40000, "loss": 0.7011, "lr": 1.1955956460174645e-05, "epoch": 0.8639011586966263, "percentage": 67.47, "elapsed_time": "15:37:16", "remaining_time": "7:31:47", "throughput": 660.05, "total_tokens": 37118976} {"current_steps": 26995, "total_steps": 40000, "loss": 0.6595, "lr": 1.1947582262381552e-05, "epoch": 0.8640611996671148, "percentage": 67.49, "elapsed_time": "15:37:18", "remaining_time": "7:31:33", "throughput": 660.15, "total_tokens": 37125920} {"current_steps": 27000, "total_steps": 40000, "loss": 0.8094, "lr": 1.1939210077435293e-05, "epoch": 0.8642212406376032, "percentage": 67.5, "elapsed_time": "15:37:19", "remaining_time": "7:31:18", "throughput": 660.26, "total_tokens": 37133072} {"current_steps": 27000, "total_steps": 40000, "eval_loss": 0.7338866591453552, "epoch": 0.8642212406376032, "percentage": 67.5, "elapsed_time": "15:43:08", "remaining_time": "7:34:06", "throughput": 656.2, "total_tokens": 37133072} {"current_steps": 27005, "total_steps": 40000, "loss": 0.7357, "lr": 1.193083990662697e-05, "epoch": 0.8643812816080917, "percentage": 67.51, "elapsed_time": "15:43:11", "remaining_time": "7:33:52", "throughput": 656.27, "total_tokens": 37139632} {"current_steps": 27010, "total_steps": 40000, "loss": 0.8032, "lr": 1.192247175124738e-05, "epoch": 0.8645413225785801, "percentage": 67.53, "elapsed_time": "15:43:13", "remaining_time": "7:33:37", "throughput": 656.37, "total_tokens": 37146080} {"current_steps": 27015, "total_steps": 40000, "loss": 0.6006, "lr": 1.191410561258698e-05, "epoch": 0.8647013635490686, "percentage": 67.54, "elapsed_time": "15:43:15", "remaining_time": "7:33:22", "throughput": 656.46, "total_tokens": 37152576} {"current_steps": 27020, "total_steps": 40000, "loss": 0.684, "lr": 1.1905741491935944e-05, "epoch": 0.864861404519557, "percentage": 67.55, "elapsed_time": "15:43:16", "remaining_time": "7:33:08", "throughput": 656.56, "total_tokens": 37159408} {"current_steps": 27025, "total_steps": 40000, "loss": 0.6347, "lr": 1.1897379390584129e-05, "epoch": 0.8650214454900454, "percentage": 67.56, "elapsed_time": "15:43:18", "remaining_time": "7:32:53", "throughput": 656.67, "total_tokens": 37166432} {"current_steps": 27030, "total_steps": 40000, "loss": 0.6211, "lr": 1.1889019309821062e-05, "epoch": 0.8651814864605339, "percentage": 67.58, "elapsed_time": "15:43:20", "remaining_time": "7:32:38", "throughput": 656.77, "total_tokens": 37173392} {"current_steps": 27035, "total_steps": 40000, "loss": 0.5841, "lr": 1.188066125093599e-05, "epoch": 0.8653415274310223, "percentage": 67.59, "elapsed_time": "15:43:22", "remaining_time": "7:32:24", "throughput": 656.87, "total_tokens": 37180320} {"current_steps": 27040, "total_steps": 40000, "loss": 0.828, "lr": 1.1872305215217811e-05, "epoch": 0.8655015684015108, "percentage": 67.6, "elapsed_time": "15:43:23", "remaining_time": "7:32:09", "throughput": 656.97, "total_tokens": 37186816} {"current_steps": 27045, "total_steps": 40000, "loss": 0.6545, "lr": 1.186395120395514e-05, "epoch": 0.8656616093719992, "percentage": 67.61, "elapsed_time": "15:43:25", "remaining_time": "7:31:54", "throughput": 657.07, "total_tokens": 37193600} {"current_steps": 27050, "total_steps": 40000, "loss": 0.5982, "lr": 1.1855599218436283e-05, "epoch": 0.8658216503424877, "percentage": 67.62, "elapsed_time": "15:43:27", "remaining_time": "7:31:40", "throughput": 657.17, "total_tokens": 37200656} {"current_steps": 27055, "total_steps": 40000, "loss": 0.7578, "lr": 1.1847249259949209e-05, "epoch": 0.8659816913129761, "percentage": 67.64, "elapsed_time": "15:43:28", "remaining_time": "7:31:25", "throughput": 657.27, "total_tokens": 37207424} {"current_steps": 27060, "total_steps": 40000, "loss": 0.6971, "lr": 1.1838901329781574e-05, "epoch": 0.8661417322834646, "percentage": 67.65, "elapsed_time": "15:43:30", "remaining_time": "7:31:11", "throughput": 657.37, "total_tokens": 37214208} {"current_steps": 27065, "total_steps": 40000, "loss": 0.8022, "lr": 1.1830555429220758e-05, "epoch": 0.866301773253953, "percentage": 67.66, "elapsed_time": "15:43:32", "remaining_time": "7:30:56", "throughput": 657.47, "total_tokens": 37220752} {"current_steps": 27070, "total_steps": 40000, "loss": 0.6402, "lr": 1.1822211559553784e-05, "epoch": 0.8664618142244415, "percentage": 67.67, "elapsed_time": "15:43:34", "remaining_time": "7:30:41", "throughput": 657.56, "total_tokens": 37227424} {"current_steps": 27075, "total_steps": 40000, "loss": 0.587, "lr": 1.18138697220674e-05, "epoch": 0.86662185519493, "percentage": 67.69, "elapsed_time": "15:43:35", "remaining_time": "7:30:27", "throughput": 657.67, "total_tokens": 37234336} {"current_steps": 27080, "total_steps": 40000, "loss": 0.8268, "lr": 1.1805529918048e-05, "epoch": 0.8667818961654183, "percentage": 67.7, "elapsed_time": "15:43:37", "remaining_time": "7:30:12", "throughput": 657.76, "total_tokens": 37241024} {"current_steps": 27085, "total_steps": 40000, "loss": 0.7362, "lr": 1.1797192148781702e-05, "epoch": 0.8669419371359068, "percentage": 67.71, "elapsed_time": "15:43:39", "remaining_time": "7:29:57", "throughput": 657.86, "total_tokens": 37247632} {"current_steps": 27090, "total_steps": 40000, "loss": 0.5278, "lr": 1.1788856415554297e-05, "epoch": 0.8671019781063952, "percentage": 67.73, "elapsed_time": "15:43:41", "remaining_time": "7:29:43", "throughput": 657.96, "total_tokens": 37254320} {"current_steps": 27095, "total_steps": 40000, "loss": 0.8193, "lr": 1.1780522719651249e-05, "epoch": 0.8672620190768837, "percentage": 67.74, "elapsed_time": "15:43:42", "remaining_time": "7:29:28", "throughput": 658.07, "total_tokens": 37261712} {"current_steps": 27100, "total_steps": 40000, "loss": 0.702, "lr": 1.1772191062357721e-05, "epoch": 0.8674220600473721, "percentage": 67.75, "elapsed_time": "15:43:44", "remaining_time": "7:29:14", "throughput": 658.16, "total_tokens": 37268320} {"current_steps": 27105, "total_steps": 40000, "loss": 0.686, "lr": 1.1763861444958573e-05, "epoch": 0.8675821010178606, "percentage": 67.76, "elapsed_time": "15:43:46", "remaining_time": "7:28:59", "throughput": 658.26, "total_tokens": 37274896} {"current_steps": 27110, "total_steps": 40000, "loss": 0.827, "lr": 1.1755533868738317e-05, "epoch": 0.867742141988349, "percentage": 67.77, "elapsed_time": "15:43:48", "remaining_time": "7:28:44", "throughput": 658.37, "total_tokens": 37281984} {"current_steps": 27115, "total_steps": 40000, "loss": 0.7197, "lr": 1.1747208334981185e-05, "epoch": 0.8679021829588375, "percentage": 67.79, "elapsed_time": "15:43:49", "remaining_time": "7:28:30", "throughput": 658.47, "total_tokens": 37288800} {"current_steps": 27120, "total_steps": 40000, "loss": 0.861, "lr": 1.1738884844971067e-05, "epoch": 0.8680622239293259, "percentage": 67.8, "elapsed_time": "15:43:51", "remaining_time": "7:28:15", "throughput": 658.56, "total_tokens": 37295520} {"current_steps": 27125, "total_steps": 40000, "loss": 0.8511, "lr": 1.1730563399991563e-05, "epoch": 0.8682222648998144, "percentage": 67.81, "elapsed_time": "15:43:53", "remaining_time": "7:28:01", "throughput": 658.67, "total_tokens": 37302384} {"current_steps": 27130, "total_steps": 40000, "loss": 0.7381, "lr": 1.1722244001325938e-05, "epoch": 0.8683823058703029, "percentage": 67.83, "elapsed_time": "15:43:55", "remaining_time": "7:27:46", "throughput": 658.77, "total_tokens": 37309680} {"current_steps": 27135, "total_steps": 40000, "loss": 0.5025, "lr": 1.1713926650257137e-05, "epoch": 0.8685423468407912, "percentage": 67.84, "elapsed_time": "15:43:56", "remaining_time": "7:27:32", "throughput": 658.87, "total_tokens": 37316000} {"current_steps": 27140, "total_steps": 40000, "loss": 0.7055, "lr": 1.170561134806781e-05, "epoch": 0.8687023878112797, "percentage": 67.85, "elapsed_time": "15:43:58", "remaining_time": "7:27:17", "throughput": 658.97, "total_tokens": 37323184} {"current_steps": 27145, "total_steps": 40000, "loss": 0.5904, "lr": 1.1697298096040287e-05, "epoch": 0.8688624287817681, "percentage": 67.86, "elapsed_time": "15:44:00", "remaining_time": "7:27:02", "throughput": 659.07, "total_tokens": 37329920} {"current_steps": 27150, "total_steps": 40000, "loss": 0.7027, "lr": 1.1688986895456567e-05, "epoch": 0.8690224697522566, "percentage": 67.88, "elapsed_time": "15:44:01", "remaining_time": "7:26:48", "throughput": 659.17, "total_tokens": 37336736} {"current_steps": 27155, "total_steps": 40000, "loss": 0.7463, "lr": 1.1680677747598349e-05, "epoch": 0.869182510722745, "percentage": 67.89, "elapsed_time": "15:44:03", "remaining_time": "7:26:33", "throughput": 659.27, "total_tokens": 37343488} {"current_steps": 27160, "total_steps": 40000, "loss": 0.6147, "lr": 1.1672370653746995e-05, "epoch": 0.8693425516932335, "percentage": 67.9, "elapsed_time": "15:44:05", "remaining_time": "7:26:19", "throughput": 659.38, "total_tokens": 37350608} {"current_steps": 27165, "total_steps": 40000, "loss": 0.6154, "lr": 1.166406561518357e-05, "epoch": 0.8695025926637219, "percentage": 67.91, "elapsed_time": "15:44:07", "remaining_time": "7:26:04", "throughput": 659.47, "total_tokens": 37357056} {"current_steps": 27170, "total_steps": 40000, "loss": 0.957, "lr": 1.1655762633188826e-05, "epoch": 0.8696626336342104, "percentage": 67.92, "elapsed_time": "15:44:08", "remaining_time": "7:25:50", "throughput": 659.56, "total_tokens": 37363632} {"current_steps": 27175, "total_steps": 40000, "loss": 0.6603, "lr": 1.1647461709043172e-05, "epoch": 0.8698226746046988, "percentage": 67.94, "elapsed_time": "15:44:10", "remaining_time": "7:25:35", "throughput": 659.67, "total_tokens": 37370832} {"current_steps": 27180, "total_steps": 40000, "loss": 0.6533, "lr": 1.1639162844026722e-05, "epoch": 0.8699827155751872, "percentage": 67.95, "elapsed_time": "15:44:12", "remaining_time": "7:25:21", "throughput": 659.77, "total_tokens": 37377776} {"current_steps": 27185, "total_steps": 40000, "loss": 0.6687, "lr": 1.163086603941927e-05, "epoch": 0.8701427565456757, "percentage": 67.96, "elapsed_time": "15:44:14", "remaining_time": "7:25:06", "throughput": 659.87, "total_tokens": 37384288} {"current_steps": 27190, "total_steps": 40000, "loss": 0.7222, "lr": 1.1622571296500273e-05, "epoch": 0.8703027975161641, "percentage": 67.97, "elapsed_time": "15:44:15", "remaining_time": "7:24:52", "throughput": 659.97, "total_tokens": 37391056} {"current_steps": 27195, "total_steps": 40000, "loss": 0.5707, "lr": 1.1614278616548904e-05, "epoch": 0.8704628384866526, "percentage": 67.99, "elapsed_time": "15:44:17", "remaining_time": "7:24:37", "throughput": 660.07, "total_tokens": 37397792} {"current_steps": 27200, "total_steps": 40000, "loss": 0.7163, "lr": 1.1605988000843986e-05, "epoch": 0.870622879457141, "percentage": 68.0, "elapsed_time": "15:44:19", "remaining_time": "7:24:23", "throughput": 660.16, "total_tokens": 37404464} {"current_steps": 27200, "total_steps": 40000, "eval_loss": 0.7339644432067871, "epoch": 0.870622879457141, "percentage": 68.0, "elapsed_time": "15:50:06", "remaining_time": "7:27:06", "throughput": 656.14, "total_tokens": 37404464} {"current_steps": 27205, "total_steps": 40000, "loss": 0.695, "lr": 1.1597699450664028e-05, "epoch": 0.8707829204276295, "percentage": 68.01, "elapsed_time": "15:50:09", "remaining_time": "7:26:52", "throughput": 656.22, "total_tokens": 37411152} {"current_steps": 27210, "total_steps": 40000, "loss": 0.6697, "lr": 1.1589412967287252e-05, "epoch": 0.8709429613981179, "percentage": 68.03, "elapsed_time": "15:50:11", "remaining_time": "7:26:38", "throughput": 656.32, "total_tokens": 37418016} {"current_steps": 27215, "total_steps": 40000, "loss": 0.5831, "lr": 1.1581128551991514e-05, "epoch": 0.8711030023686064, "percentage": 68.04, "elapsed_time": "15:50:13", "remaining_time": "7:26:23", "throughput": 656.43, "total_tokens": 37425024} {"current_steps": 27220, "total_steps": 40000, "loss": 0.673, "lr": 1.1572846206054383e-05, "epoch": 0.8712630433390948, "percentage": 68.05, "elapsed_time": "15:50:15", "remaining_time": "7:26:09", "throughput": 656.53, "total_tokens": 37432144} {"current_steps": 27225, "total_steps": 40000, "loss": 0.7137, "lr": 1.1564565930753113e-05, "epoch": 0.8714230843095833, "percentage": 68.06, "elapsed_time": "15:50:16", "remaining_time": "7:25:54", "throughput": 656.62, "total_tokens": 37438640} {"current_steps": 27230, "total_steps": 40000, "loss": 0.5839, "lr": 1.1556287727364606e-05, "epoch": 0.8715831252800716, "percentage": 68.08, "elapsed_time": "15:50:18", "remaining_time": "7:25:39", "throughput": 656.73, "total_tokens": 37445808} {"current_steps": 27235, "total_steps": 40000, "loss": 0.7309, "lr": 1.1548011597165489e-05, "epoch": 0.8717431662505601, "percentage": 68.09, "elapsed_time": "15:50:20", "remaining_time": "7:25:25", "throughput": 656.84, "total_tokens": 37453040} {"current_steps": 27240, "total_steps": 40000, "loss": 0.5679, "lr": 1.1539737541432019e-05, "epoch": 0.8719032072210486, "percentage": 68.1, "elapsed_time": "15:50:22", "remaining_time": "7:25:10", "throughput": 656.94, "total_tokens": 37459920} {"current_steps": 27245, "total_steps": 40000, "loss": 0.6493, "lr": 1.1531465561440174e-05, "epoch": 0.872063248191537, "percentage": 68.11, "elapsed_time": "15:50:23", "remaining_time": "7:24:56", "throughput": 657.04, "total_tokens": 37466720} {"current_steps": 27250, "total_steps": 40000, "loss": 0.6388, "lr": 1.1523195658465605e-05, "epoch": 0.8722232891620255, "percentage": 68.12, "elapsed_time": "15:50:25", "remaining_time": "7:24:41", "throughput": 657.13, "total_tokens": 37473296} {"current_steps": 27255, "total_steps": 40000, "loss": 0.7813, "lr": 1.1514927833783618e-05, "epoch": 0.8723833301325139, "percentage": 68.14, "elapsed_time": "15:50:27", "remaining_time": "7:24:27", "throughput": 657.23, "total_tokens": 37479856} {"current_steps": 27260, "total_steps": 40000, "loss": 0.8589, "lr": 1.150666208866922e-05, "epoch": 0.8725433711030024, "percentage": 68.15, "elapsed_time": "15:50:29", "remaining_time": "7:24:12", "throughput": 657.33, "total_tokens": 37486624} {"current_steps": 27265, "total_steps": 40000, "loss": 0.6402, "lr": 1.1498398424397106e-05, "epoch": 0.8727034120734908, "percentage": 68.16, "elapsed_time": "15:50:30", "remaining_time": "7:23:58", "throughput": 657.42, "total_tokens": 37493200} {"current_steps": 27270, "total_steps": 40000, "loss": 0.8626, "lr": 1.1490136842241628e-05, "epoch": 0.8728634530439793, "percentage": 68.17, "elapsed_time": "15:50:32", "remaining_time": "7:23:43", "throughput": 657.52, "total_tokens": 37499872} {"current_steps": 27275, "total_steps": 40000, "loss": 0.72, "lr": 1.1481877343476813e-05, "epoch": 0.8730234940144677, "percentage": 68.19, "elapsed_time": "15:50:34", "remaining_time": "7:23:29", "throughput": 657.62, "total_tokens": 37506768} {"current_steps": 27280, "total_steps": 40000, "loss": 0.7233, "lr": 1.14736199293764e-05, "epoch": 0.8731835349849562, "percentage": 68.2, "elapsed_time": "15:50:35", "remaining_time": "7:23:14", "throughput": 657.72, "total_tokens": 37513712} {"current_steps": 27285, "total_steps": 40000, "loss": 0.9112, "lr": 1.1465364601213771e-05, "epoch": 0.8733435759554445, "percentage": 68.21, "elapsed_time": "15:50:37", "remaining_time": "7:22:59", "throughput": 657.82, "total_tokens": 37520560} {"current_steps": 27290, "total_steps": 40000, "loss": 0.6918, "lr": 1.1457111360262012e-05, "epoch": 0.873503616925933, "percentage": 68.23, "elapsed_time": "15:50:39", "remaining_time": "7:22:45", "throughput": 657.92, "total_tokens": 37527184} {"current_steps": 27295, "total_steps": 40000, "loss": 0.7845, "lr": 1.1448860207793869e-05, "epoch": 0.8736636578964215, "percentage": 68.24, "elapsed_time": "15:50:41", "remaining_time": "7:22:30", "throughput": 658.01, "total_tokens": 37533840} {"current_steps": 27300, "total_steps": 40000, "loss": 0.7328, "lr": 1.144061114508177e-05, "epoch": 0.8738236988669099, "percentage": 68.25, "elapsed_time": "15:50:42", "remaining_time": "7:22:16", "throughput": 658.11, "total_tokens": 37540736} {"current_steps": 27305, "total_steps": 40000, "loss": 0.9245, "lr": 1.1432364173397842e-05, "epoch": 0.8739837398373984, "percentage": 68.26, "elapsed_time": "15:50:44", "remaining_time": "7:22:01", "throughput": 658.21, "total_tokens": 37547616} {"current_steps": 27310, "total_steps": 40000, "loss": 0.7847, "lr": 1.1424119294013852e-05, "epoch": 0.8741437808078868, "percentage": 68.27, "elapsed_time": "15:50:46", "remaining_time": "7:21:47", "throughput": 658.31, "total_tokens": 37554336} {"current_steps": 27315, "total_steps": 40000, "loss": 0.8601, "lr": 1.1415876508201279e-05, "epoch": 0.8743038217783753, "percentage": 68.29, "elapsed_time": "15:50:48", "remaining_time": "7:21:32", "throughput": 658.41, "total_tokens": 37561104} {"current_steps": 27320, "total_steps": 40000, "loss": 0.7319, "lr": 1.140763581723125e-05, "epoch": 0.8744638627488637, "percentage": 68.3, "elapsed_time": "15:50:49", "remaining_time": "7:21:18", "throughput": 658.51, "total_tokens": 37568016} {"current_steps": 27325, "total_steps": 40000, "loss": 0.7765, "lr": 1.1399397222374588e-05, "epoch": 0.8746239037193522, "percentage": 68.31, "elapsed_time": "15:50:51", "remaining_time": "7:21:04", "throughput": 658.62, "total_tokens": 37575152} {"current_steps": 27330, "total_steps": 40000, "loss": 0.5927, "lr": 1.1391160724901804e-05, "epoch": 0.8747839446898406, "percentage": 68.33, "elapsed_time": "15:50:53", "remaining_time": "7:20:49", "throughput": 658.71, "total_tokens": 37581664} {"current_steps": 27335, "total_steps": 40000, "loss": 0.6218, "lr": 1.138292632608304e-05, "epoch": 0.874943985660329, "percentage": 68.34, "elapsed_time": "15:50:55", "remaining_time": "7:20:35", "throughput": 658.81, "total_tokens": 37588304} {"current_steps": 27340, "total_steps": 40000, "loss": 0.6287, "lr": 1.1374694027188174e-05, "epoch": 0.8751040266308175, "percentage": 68.35, "elapsed_time": "15:50:56", "remaining_time": "7:20:20", "throughput": 658.91, "total_tokens": 37595200} {"current_steps": 27345, "total_steps": 40000, "loss": 0.7593, "lr": 1.1366463829486711e-05, "epoch": 0.8752640676013059, "percentage": 68.36, "elapsed_time": "15:50:58", "remaining_time": "7:20:06", "throughput": 659.0, "total_tokens": 37601792} {"current_steps": 27350, "total_steps": 40000, "loss": 0.6452, "lr": 1.1358235734247849e-05, "epoch": 0.8754241085717944, "percentage": 68.38, "elapsed_time": "15:51:00", "remaining_time": "7:19:51", "throughput": 659.1, "total_tokens": 37608544} {"current_steps": 27355, "total_steps": 40000, "loss": 0.7102, "lr": 1.1350009742740478e-05, "epoch": 0.8755841495422828, "percentage": 68.39, "elapsed_time": "15:51:02", "remaining_time": "7:19:37", "throughput": 659.2, "total_tokens": 37615264} {"current_steps": 27360, "total_steps": 40000, "loss": 0.9314, "lr": 1.134178585623313e-05, "epoch": 0.8757441905127713, "percentage": 68.4, "elapsed_time": "15:51:03", "remaining_time": "7:19:22", "throughput": 659.29, "total_tokens": 37621808} {"current_steps": 27365, "total_steps": 40000, "loss": 0.6859, "lr": 1.1333564075994047e-05, "epoch": 0.8759042314832597, "percentage": 68.41, "elapsed_time": "15:51:05", "remaining_time": "7:19:08", "throughput": 659.39, "total_tokens": 37628368} {"current_steps": 27370, "total_steps": 40000, "loss": 0.7265, "lr": 1.1325344403291133e-05, "epoch": 0.8760642724537482, "percentage": 68.42, "elapsed_time": "15:51:07", "remaining_time": "7:18:53", "throughput": 659.49, "total_tokens": 37635200} {"current_steps": 27375, "total_steps": 40000, "loss": 0.7233, "lr": 1.1317126839391951e-05, "epoch": 0.8762243134242366, "percentage": 68.44, "elapsed_time": "15:51:08", "remaining_time": "7:18:39", "throughput": 659.58, "total_tokens": 37641648} {"current_steps": 27380, "total_steps": 40000, "loss": 0.7591, "lr": 1.1308911385563766e-05, "epoch": 0.8763843543947251, "percentage": 68.45, "elapsed_time": "15:51:10", "remaining_time": "7:18:25", "throughput": 659.68, "total_tokens": 37648640} {"current_steps": 27385, "total_steps": 40000, "loss": 0.8085, "lr": 1.1300698043073494e-05, "epoch": 0.8765443953652134, "percentage": 68.46, "elapsed_time": "15:51:12", "remaining_time": "7:18:10", "throughput": 659.78, "total_tokens": 37655296} {"current_steps": 27390, "total_steps": 40000, "loss": 0.791, "lr": 1.1292486813187736e-05, "epoch": 0.8767044363357019, "percentage": 68.47, "elapsed_time": "15:51:14", "remaining_time": "7:17:56", "throughput": 659.88, "total_tokens": 37662032} {"current_steps": 27395, "total_steps": 40000, "loss": 0.7463, "lr": 1.1284277697172782e-05, "epoch": 0.8768644773061904, "percentage": 68.49, "elapsed_time": "15:51:15", "remaining_time": "7:17:41", "throughput": 659.97, "total_tokens": 37668672} {"current_steps": 27400, "total_steps": 40000, "loss": 0.7094, "lr": 1.127607069629456e-05, "epoch": 0.8770245182766788, "percentage": 68.5, "elapsed_time": "15:51:17", "remaining_time": "7:17:27", "throughput": 660.07, "total_tokens": 37675456} {"current_steps": 27400, "total_steps": 40000, "eval_loss": 0.7335285544395447, "epoch": 0.8770245182766788, "percentage": 68.5, "elapsed_time": "15:57:05", "remaining_time": "7:20:07", "throughput": 656.07, "total_tokens": 37675456} {"current_steps": 27405, "total_steps": 40000, "loss": 0.662, "lr": 1.1267865811818701e-05, "epoch": 0.8771845592471673, "percentage": 68.51, "elapsed_time": "15:57:09", "remaining_time": "7:19:53", "throughput": 656.15, "total_tokens": 37682624} {"current_steps": 27410, "total_steps": 40000, "loss": 1.0009, "lr": 1.1259663045010513e-05, "epoch": 0.8773446002176557, "percentage": 68.53, "elapsed_time": "15:57:11", "remaining_time": "7:19:39", "throughput": 656.26, "total_tokens": 37689552} {"current_steps": 27415, "total_steps": 40000, "loss": 0.7114, "lr": 1.1251462397134957e-05, "epoch": 0.8775046411881442, "percentage": 68.54, "elapsed_time": "15:57:12", "remaining_time": "7:19:24", "throughput": 656.35, "total_tokens": 37696400} {"current_steps": 27420, "total_steps": 40000, "loss": 0.9435, "lr": 1.1243263869456664e-05, "epoch": 0.8776646821586326, "percentage": 68.55, "elapsed_time": "15:57:14", "remaining_time": "7:19:10", "throughput": 656.45, "total_tokens": 37703168} {"current_steps": 27425, "total_steps": 40000, "loss": 0.6433, "lr": 1.1235067463239967e-05, "epoch": 0.8778247231291211, "percentage": 68.56, "elapsed_time": "15:57:16", "remaining_time": "7:18:55", "throughput": 656.55, "total_tokens": 37710160} {"current_steps": 27430, "total_steps": 40000, "loss": 0.8542, "lr": 1.122687317974884e-05, "epoch": 0.8779847640996095, "percentage": 68.58, "elapsed_time": "15:57:18", "remaining_time": "7:18:41", "throughput": 656.66, "total_tokens": 37717200} {"current_steps": 27435, "total_steps": 40000, "loss": 0.6574, "lr": 1.1218681020246963e-05, "epoch": 0.878144805070098, "percentage": 68.59, "elapsed_time": "15:57:19", "remaining_time": "7:18:27", "throughput": 656.76, "total_tokens": 37724240} {"current_steps": 27440, "total_steps": 40000, "loss": 0.7972, "lr": 1.1210490985997652e-05, "epoch": 0.8783048460405863, "percentage": 68.6, "elapsed_time": "15:57:21", "remaining_time": "7:18:12", "throughput": 656.86, "total_tokens": 37731376} {"current_steps": 27445, "total_steps": 40000, "loss": 0.7167, "lr": 1.1202303078263917e-05, "epoch": 0.8784648870110748, "percentage": 68.61, "elapsed_time": "15:57:23", "remaining_time": "7:17:58", "throughput": 656.97, "total_tokens": 37738384} {"current_steps": 27450, "total_steps": 40000, "loss": 0.659, "lr": 1.1194117298308451e-05, "epoch": 0.8786249279815633, "percentage": 68.62, "elapsed_time": "15:57:25", "remaining_time": "7:17:43", "throughput": 657.06, "total_tokens": 37745136} {"current_steps": 27455, "total_steps": 40000, "loss": 0.6989, "lr": 1.1185933647393585e-05, "epoch": 0.8787849689520517, "percentage": 68.64, "elapsed_time": "15:57:26", "remaining_time": "7:17:29", "throughput": 657.16, "total_tokens": 37752064} {"current_steps": 27460, "total_steps": 40000, "loss": 0.8524, "lr": 1.1177752126781354e-05, "epoch": 0.8789450099225402, "percentage": 68.65, "elapsed_time": "15:57:28", "remaining_time": "7:17:14", "throughput": 657.26, "total_tokens": 37758848} {"current_steps": 27465, "total_steps": 40000, "loss": 0.7852, "lr": 1.1169572737733441e-05, "epoch": 0.8791050508930286, "percentage": 68.66, "elapsed_time": "15:57:30", "remaining_time": "7:17:00", "throughput": 657.37, "total_tokens": 37765904} {"current_steps": 27470, "total_steps": 40000, "loss": 0.6252, "lr": 1.1161395481511216e-05, "epoch": 0.8792650918635171, "percentage": 68.67, "elapsed_time": "15:57:32", "remaining_time": "7:16:45", "throughput": 657.46, "total_tokens": 37772608} {"current_steps": 27475, "total_steps": 40000, "loss": 0.8359, "lr": 1.1153220359375722e-05, "epoch": 0.8794251328340055, "percentage": 68.69, "elapsed_time": "15:57:33", "remaining_time": "7:16:31", "throughput": 657.57, "total_tokens": 37779792} {"current_steps": 27480, "total_steps": 40000, "loss": 0.8459, "lr": 1.114504737258765e-05, "epoch": 0.879585173804494, "percentage": 68.7, "elapsed_time": "15:57:35", "remaining_time": "7:16:17", "throughput": 657.67, "total_tokens": 37786864} {"current_steps": 27485, "total_steps": 40000, "loss": 0.7337, "lr": 1.1136876522407393e-05, "epoch": 0.8797452147749824, "percentage": 68.71, "elapsed_time": "15:57:37", "remaining_time": "7:16:02", "throughput": 657.77, "total_tokens": 37793680} {"current_steps": 27490, "total_steps": 40000, "loss": 0.8244, "lr": 1.1128707810094985e-05, "epoch": 0.8799052557454708, "percentage": 68.73, "elapsed_time": "15:57:39", "remaining_time": "7:15:48", "throughput": 657.86, "total_tokens": 37800192} {"current_steps": 27495, "total_steps": 40000, "loss": 0.6632, "lr": 1.1120541236910157e-05, "epoch": 0.8800652967159592, "percentage": 68.74, "elapsed_time": "15:57:40", "remaining_time": "7:15:33", "throughput": 657.96, "total_tokens": 37806736} {"current_steps": 27500, "total_steps": 40000, "loss": 0.6789, "lr": 1.111237680411229e-05, "epoch": 0.8802253376864477, "percentage": 68.75, "elapsed_time": "15:57:42", "remaining_time": "7:15:19", "throughput": 658.05, "total_tokens": 37813168} {"current_steps": 27505, "total_steps": 40000, "loss": 0.672, "lr": 1.1104214512960433e-05, "epoch": 0.8803853786569362, "percentage": 68.76, "elapsed_time": "15:57:44", "remaining_time": "7:15:04", "throughput": 658.15, "total_tokens": 37820352} {"current_steps": 27510, "total_steps": 40000, "loss": 0.6771, "lr": 1.1096054364713327e-05, "epoch": 0.8805454196274246, "percentage": 68.77, "elapsed_time": "15:57:46", "remaining_time": "7:14:50", "throughput": 658.25, "total_tokens": 37827184} {"current_steps": 27515, "total_steps": 40000, "loss": 0.7214, "lr": 1.1087896360629371e-05, "epoch": 0.8807054605979131, "percentage": 68.79, "elapsed_time": "15:57:47", "remaining_time": "7:14:36", "throughput": 658.36, "total_tokens": 37834208} {"current_steps": 27520, "total_steps": 40000, "loss": 0.6515, "lr": 1.107974050196662e-05, "epoch": 0.8808655015684015, "percentage": 68.8, "elapsed_time": "15:57:49", "remaining_time": "7:14:21", "throughput": 658.45, "total_tokens": 37840928} {"current_steps": 27525, "total_steps": 40000, "loss": 0.6879, "lr": 1.1071586789982816e-05, "epoch": 0.88102554253889, "percentage": 68.81, "elapsed_time": "15:57:51", "remaining_time": "7:14:07", "throughput": 658.55, "total_tokens": 37847696} {"current_steps": 27530, "total_steps": 40000, "loss": 0.5399, "lr": 1.1063435225935373e-05, "epoch": 0.8811855835093784, "percentage": 68.83, "elapsed_time": "15:57:52", "remaining_time": "7:13:52", "throughput": 658.65, "total_tokens": 37854656} {"current_steps": 27535, "total_steps": 40000, "loss": 0.7566, "lr": 1.1055285811081348e-05, "epoch": 0.8813456244798669, "percentage": 68.84, "elapsed_time": "15:57:54", "remaining_time": "7:13:38", "throughput": 658.75, "total_tokens": 37861360} {"current_steps": 27540, "total_steps": 40000, "loss": 0.7574, "lr": 1.1047138546677499e-05, "epoch": 0.8815056654503552, "percentage": 68.85, "elapsed_time": "15:57:56", "remaining_time": "7:13:24", "throughput": 658.87, "total_tokens": 37869264} {"current_steps": 27545, "total_steps": 40000, "loss": 0.7509, "lr": 1.1038993433980219e-05, "epoch": 0.8816657064208437, "percentage": 68.86, "elapsed_time": "15:57:58", "remaining_time": "7:13:09", "throughput": 658.97, "total_tokens": 37876128} {"current_steps": 27550, "total_steps": 40000, "loss": 0.7138, "lr": 1.1030850474245597e-05, "epoch": 0.8818257473913321, "percentage": 68.88, "elapsed_time": "15:57:59", "remaining_time": "7:12:55", "throughput": 659.06, "total_tokens": 37882592} {"current_steps": 27555, "total_steps": 40000, "loss": 0.6388, "lr": 1.102270966872939e-05, "epoch": 0.8819857883618206, "percentage": 68.89, "elapsed_time": "15:58:01", "remaining_time": "7:12:41", "throughput": 659.16, "total_tokens": 37889664} {"current_steps": 27560, "total_steps": 40000, "loss": 0.7333, "lr": 1.1014571018687e-05, "epoch": 0.8821458293323091, "percentage": 68.9, "elapsed_time": "15:58:03", "remaining_time": "7:12:26", "throughput": 659.26, "total_tokens": 37896464} {"current_steps": 27565, "total_steps": 40000, "loss": 0.588, "lr": 1.1006434525373502e-05, "epoch": 0.8823058703027975, "percentage": 68.91, "elapsed_time": "15:58:05", "remaining_time": "7:12:12", "throughput": 659.37, "total_tokens": 37903712} {"current_steps": 27570, "total_steps": 40000, "loss": 0.908, "lr": 1.0998300190043664e-05, "epoch": 0.882465911273286, "percentage": 68.92, "elapsed_time": "15:58:06", "remaining_time": "7:11:58", "throughput": 659.47, "total_tokens": 37910640} {"current_steps": 27575, "total_steps": 40000, "loss": 0.8176, "lr": 1.0990168013951882e-05, "epoch": 0.8826259522437744, "percentage": 68.94, "elapsed_time": "15:58:08", "remaining_time": "7:11:43", "throughput": 659.57, "total_tokens": 37917536} {"current_steps": 27580, "total_steps": 40000, "loss": 0.7293, "lr": 1.0982037998352263e-05, "epoch": 0.8827859932142629, "percentage": 68.95, "elapsed_time": "15:58:10", "remaining_time": "7:11:29", "throughput": 659.66, "total_tokens": 37924128} {"current_steps": 27585, "total_steps": 40000, "loss": 0.8076, "lr": 1.0973910144498534e-05, "epoch": 0.8829460341847513, "percentage": 68.96, "elapsed_time": "15:58:12", "remaining_time": "7:11:15", "throughput": 659.76, "total_tokens": 37930848} {"current_steps": 27590, "total_steps": 40000, "loss": 0.7581, "lr": 1.0965784453644123e-05, "epoch": 0.8831060751552398, "percentage": 68.97, "elapsed_time": "15:58:13", "remaining_time": "7:11:00", "throughput": 659.86, "total_tokens": 37937792} {"current_steps": 27595, "total_steps": 40000, "loss": 0.6976, "lr": 1.0957660927042127e-05, "epoch": 0.8832661161257281, "percentage": 68.99, "elapsed_time": "15:58:15", "remaining_time": "7:10:46", "throughput": 659.96, "total_tokens": 37944720} {"current_steps": 27600, "total_steps": 40000, "loss": 0.6543, "lr": 1.094953956594527e-05, "epoch": 0.8834261570962166, "percentage": 69.0, "elapsed_time": "15:58:17", "remaining_time": "7:10:32", "throughput": 660.06, "total_tokens": 37951616} {"current_steps": 27600, "total_steps": 40000, "eval_loss": 0.733181893825531, "epoch": 0.8834261570962166, "percentage": 69.0, "elapsed_time": "16:04:05", "remaining_time": "7:13:08", "throughput": 656.09, "total_tokens": 37951616} {"current_steps": 27605, "total_steps": 40000, "loss": 0.8848, "lr": 1.0941420371605981e-05, "epoch": 0.8835861980667051, "percentage": 69.01, "elapsed_time": "16:04:08", "remaining_time": "7:12:54", "throughput": 656.17, "total_tokens": 37958592} {"current_steps": 27610, "total_steps": 40000, "loss": 0.8343, "lr": 1.0933303345276354e-05, "epoch": 0.8837462390371935, "percentage": 69.03, "elapsed_time": "16:04:10", "remaining_time": "7:12:40", "throughput": 656.27, "total_tokens": 37965488} {"current_steps": 27615, "total_steps": 40000, "loss": 0.6337, "lr": 1.0925188488208112e-05, "epoch": 0.883906280007682, "percentage": 69.04, "elapsed_time": "16:04:12", "remaining_time": "7:12:26", "throughput": 656.36, "total_tokens": 37972304} {"current_steps": 27620, "total_steps": 40000, "loss": 0.69, "lr": 1.0917075801652694e-05, "epoch": 0.8840663209781704, "percentage": 69.05, "elapsed_time": "16:04:14", "remaining_time": "7:12:11", "throughput": 656.47, "total_tokens": 37979328} {"current_steps": 27625, "total_steps": 40000, "loss": 0.6623, "lr": 1.0908965286861151e-05, "epoch": 0.8842263619486589, "percentage": 69.06, "elapsed_time": "16:04:15", "remaining_time": "7:11:57", "throughput": 656.56, "total_tokens": 37985696} {"current_steps": 27630, "total_steps": 40000, "loss": 0.6335, "lr": 1.090085694508425e-05, "epoch": 0.8843864029191473, "percentage": 69.08, "elapsed_time": "16:04:17", "remaining_time": "7:11:42", "throughput": 656.66, "total_tokens": 37992592} {"current_steps": 27635, "total_steps": 40000, "loss": 0.7115, "lr": 1.089275077757238e-05, "epoch": 0.8845464438896358, "percentage": 69.09, "elapsed_time": "16:04:19", "remaining_time": "7:11:28", "throughput": 656.74, "total_tokens": 37998720} {"current_steps": 27640, "total_steps": 40000, "loss": 0.7293, "lr": 1.0884646785575633e-05, "epoch": 0.8847064848601242, "percentage": 69.1, "elapsed_time": "16:04:21", "remaining_time": "7:11:14", "throughput": 656.84, "total_tokens": 38005328} {"current_steps": 27645, "total_steps": 40000, "loss": 0.7472, "lr": 1.0876544970343728e-05, "epoch": 0.8848665258306126, "percentage": 69.11, "elapsed_time": "16:04:22", "remaining_time": "7:10:59", "throughput": 656.94, "total_tokens": 38012512} {"current_steps": 27650, "total_steps": 40000, "loss": 0.7687, "lr": 1.0868445333126082e-05, "epoch": 0.885026566801101, "percentage": 69.12, "elapsed_time": "16:04:24", "remaining_time": "7:10:45", "throughput": 657.04, "total_tokens": 38019248} {"current_steps": 27655, "total_steps": 40000, "loss": 0.5763, "lr": 1.0860347875171745e-05, "epoch": 0.8851866077715895, "percentage": 69.14, "elapsed_time": "16:04:26", "remaining_time": "7:10:31", "throughput": 657.14, "total_tokens": 38026096} {"current_steps": 27660, "total_steps": 40000, "loss": 0.5984, "lr": 1.0852252597729465e-05, "epoch": 0.885346648742078, "percentage": 69.15, "elapsed_time": "16:04:28", "remaining_time": "7:10:16", "throughput": 657.23, "total_tokens": 38032832} {"current_steps": 27665, "total_steps": 40000, "loss": 0.7724, "lr": 1.0844159502047615e-05, "epoch": 0.8855066897125664, "percentage": 69.16, "elapsed_time": "16:04:29", "remaining_time": "7:10:02", "throughput": 657.33, "total_tokens": 38039488} {"current_steps": 27670, "total_steps": 40000, "loss": 0.6513, "lr": 1.0836068589374265e-05, "epoch": 0.8856667306830549, "percentage": 69.17, "elapsed_time": "16:04:31", "remaining_time": "7:09:48", "throughput": 657.43, "total_tokens": 38046752} {"current_steps": 27675, "total_steps": 40000, "loss": 0.8574, "lr": 1.0827979860957144e-05, "epoch": 0.8858267716535433, "percentage": 69.19, "elapsed_time": "16:04:33", "remaining_time": "7:09:33", "throughput": 657.54, "total_tokens": 38053904} {"current_steps": 27680, "total_steps": 40000, "loss": 0.7537, "lr": 1.0819893318043615e-05, "epoch": 0.8859868126240318, "percentage": 69.2, "elapsed_time": "16:04:35", "remaining_time": "7:09:19", "throughput": 657.64, "total_tokens": 38060992} {"current_steps": 27685, "total_steps": 40000, "loss": 0.6426, "lr": 1.0811808961880734e-05, "epoch": 0.8861468535945202, "percentage": 69.21, "elapsed_time": "16:04:36", "remaining_time": "7:09:05", "throughput": 657.74, "total_tokens": 38068048} {"current_steps": 27690, "total_steps": 40000, "loss": 0.7218, "lr": 1.080372679371522e-05, "epoch": 0.8863068945650087, "percentage": 69.23, "elapsed_time": "16:04:38", "remaining_time": "7:08:50", "throughput": 657.84, "total_tokens": 38075040} {"current_steps": 27695, "total_steps": 40000, "loss": 0.5721, "lr": 1.0795646814793428e-05, "epoch": 0.886466935535497, "percentage": 69.24, "elapsed_time": "16:04:40", "remaining_time": "7:08:36", "throughput": 657.94, "total_tokens": 38081616} {"current_steps": 27700, "total_steps": 40000, "loss": 0.8701, "lr": 1.078756902636141e-05, "epoch": 0.8866269765059855, "percentage": 69.25, "elapsed_time": "16:04:41", "remaining_time": "7:08:22", "throughput": 658.04, "total_tokens": 38088848} {"current_steps": 27705, "total_steps": 40000, "loss": 0.7054, "lr": 1.077949342966485e-05, "epoch": 0.8867870174764739, "percentage": 69.26, "elapsed_time": "16:04:43", "remaining_time": "7:08:07", "throughput": 658.15, "total_tokens": 38095920} {"current_steps": 27710, "total_steps": 40000, "loss": 0.6623, "lr": 1.0771420025949103e-05, "epoch": 0.8869470584469624, "percentage": 69.27, "elapsed_time": "16:04:45", "remaining_time": "7:07:53", "throughput": 658.26, "total_tokens": 38103552} {"current_steps": 27715, "total_steps": 40000, "loss": 0.7996, "lr": 1.0763348816459204e-05, "epoch": 0.8871070994174509, "percentage": 69.29, "elapsed_time": "16:04:47", "remaining_time": "7:07:39", "throughput": 658.35, "total_tokens": 38110336} {"current_steps": 27720, "total_steps": 40000, "loss": 0.8206, "lr": 1.0755279802439816e-05, "epoch": 0.8872671403879393, "percentage": 69.3, "elapsed_time": "16:04:49", "remaining_time": "7:07:24", "throughput": 658.45, "total_tokens": 38116960} {"current_steps": 27725, "total_steps": 40000, "loss": 0.5926, "lr": 1.0747212985135293e-05, "epoch": 0.8874271813584278, "percentage": 69.31, "elapsed_time": "16:04:50", "remaining_time": "7:07:10", "throughput": 658.54, "total_tokens": 38123744} {"current_steps": 27730, "total_steps": 40000, "loss": 0.7101, "lr": 1.073914836578965e-05, "epoch": 0.8875872223289162, "percentage": 69.33, "elapsed_time": "16:04:52", "remaining_time": "7:06:56", "throughput": 658.64, "total_tokens": 38130560} {"current_steps": 27735, "total_steps": 40000, "loss": 0.7929, "lr": 1.0731085945646529e-05, "epoch": 0.8877472632994047, "percentage": 69.34, "elapsed_time": "16:04:54", "remaining_time": "7:06:42", "throughput": 658.74, "total_tokens": 38137584} {"current_steps": 27740, "total_steps": 40000, "loss": 0.7961, "lr": 1.0723025725949285e-05, "epoch": 0.8879073042698931, "percentage": 69.35, "elapsed_time": "16:04:56", "remaining_time": "7:06:27", "throughput": 658.85, "total_tokens": 38144720} {"current_steps": 27745, "total_steps": 40000, "loss": 0.7008, "lr": 1.0714967707940875e-05, "epoch": 0.8880673452403816, "percentage": 69.36, "elapsed_time": "16:04:57", "remaining_time": "7:06:13", "throughput": 658.95, "total_tokens": 38152032} {"current_steps": 27750, "total_steps": 40000, "loss": 0.6168, "lr": 1.0706911892863963e-05, "epoch": 0.8882273862108699, "percentage": 69.38, "elapsed_time": "16:04:59", "remaining_time": "7:05:59", "throughput": 659.05, "total_tokens": 38158848} {"current_steps": 27755, "total_steps": 40000, "loss": 0.886, "lr": 1.0698858281960866e-05, "epoch": 0.8883874271813584, "percentage": 69.39, "elapsed_time": "16:05:01", "remaining_time": "7:05:45", "throughput": 659.15, "total_tokens": 38165568} {"current_steps": 27760, "total_steps": 40000, "loss": 0.5706, "lr": 1.069080687647353e-05, "epoch": 0.8885474681518468, "percentage": 69.4, "elapsed_time": "16:05:03", "remaining_time": "7:05:30", "throughput": 659.24, "total_tokens": 38172112} {"current_steps": 27765, "total_steps": 40000, "loss": 0.6396, "lr": 1.0682757677643596e-05, "epoch": 0.8887075091223353, "percentage": 69.41, "elapsed_time": "16:05:04", "remaining_time": "7:05:16", "throughput": 659.33, "total_tokens": 38178576} {"current_steps": 27770, "total_steps": 40000, "loss": 0.7077, "lr": 1.0674710686712359e-05, "epoch": 0.8888675500928238, "percentage": 69.42, "elapsed_time": "16:05:06", "remaining_time": "7:05:02", "throughput": 659.43, "total_tokens": 38185488} {"current_steps": 27775, "total_steps": 40000, "loss": 0.5255, "lr": 1.0666665904920756e-05, "epoch": 0.8890275910633122, "percentage": 69.44, "elapsed_time": "16:05:08", "remaining_time": "7:04:48", "throughput": 659.52, "total_tokens": 38191872} {"current_steps": 27780, "total_steps": 40000, "loss": 1.1061, "lr": 1.0658623333509385e-05, "epoch": 0.8891876320338007, "percentage": 69.45, "elapsed_time": "16:05:10", "remaining_time": "7:04:33", "throughput": 659.61, "total_tokens": 38198320} {"current_steps": 27785, "total_steps": 40000, "loss": 0.7693, "lr": 1.0650582973718532e-05, "epoch": 0.8893476730042891, "percentage": 69.46, "elapsed_time": "16:05:11", "remaining_time": "7:04:19", "throughput": 659.71, "total_tokens": 38205040} {"current_steps": 27790, "total_steps": 40000, "loss": 0.7363, "lr": 1.0642544826788098e-05, "epoch": 0.8895077139747776, "percentage": 69.47, "elapsed_time": "16:05:13", "remaining_time": "7:04:05", "throughput": 659.82, "total_tokens": 38212400} {"current_steps": 27795, "total_steps": 40000, "loss": 0.9758, "lr": 1.063450889395769e-05, "epoch": 0.889667754945266, "percentage": 69.49, "elapsed_time": "16:05:15", "remaining_time": "7:03:51", "throughput": 659.92, "total_tokens": 38219232} {"current_steps": 27800, "total_steps": 40000, "loss": 0.6482, "lr": 1.062647517646653e-05, "epoch": 0.8898277959157544, "percentage": 69.5, "elapsed_time": "16:05:17", "remaining_time": "7:03:36", "throughput": 660.01, "total_tokens": 38225840} {"current_steps": 27800, "total_steps": 40000, "eval_loss": 0.7331559658050537, "epoch": 0.8898277959157544, "percentage": 69.5, "elapsed_time": "16:11:04", "remaining_time": "7:06:09", "throughput": 656.08, "total_tokens": 38225840} {"current_steps": 27805, "total_steps": 40000, "loss": 0.5084, "lr": 1.0618443675553527e-05, "epoch": 0.8899878368862428, "percentage": 69.51, "elapsed_time": "16:11:07", "remaining_time": "7:05:55", "throughput": 656.15, "total_tokens": 38232304} {"current_steps": 27810, "total_steps": 40000, "loss": 0.8307, "lr": 1.0610414392457247e-05, "epoch": 0.8901478778567313, "percentage": 69.53, "elapsed_time": "16:11:09", "remaining_time": "7:05:41", "throughput": 656.24, "total_tokens": 38238848} {"current_steps": 27815, "total_steps": 40000, "loss": 0.8312, "lr": 1.0602387328415888e-05, "epoch": 0.8903079188272197, "percentage": 69.54, "elapsed_time": "16:11:11", "remaining_time": "7:05:27", "throughput": 656.35, "total_tokens": 38246048} {"current_steps": 27820, "total_steps": 40000, "loss": 0.9552, "lr": 1.0594362484667347e-05, "epoch": 0.8904679597977082, "percentage": 69.55, "elapsed_time": "16:11:12", "remaining_time": "7:05:12", "throughput": 656.44, "total_tokens": 38252768} {"current_steps": 27825, "total_steps": 40000, "loss": 1.0609, "lr": 1.0586339862449132e-05, "epoch": 0.8906280007681967, "percentage": 69.56, "elapsed_time": "16:11:14", "remaining_time": "7:04:58", "throughput": 656.54, "total_tokens": 38259504} {"current_steps": 27830, "total_steps": 40000, "loss": 0.6759, "lr": 1.0578319462998445e-05, "epoch": 0.8907880417386851, "percentage": 69.58, "elapsed_time": "16:11:16", "remaining_time": "7:04:44", "throughput": 656.63, "total_tokens": 38266192} {"current_steps": 27835, "total_steps": 40000, "loss": 0.6569, "lr": 1.057030128755214e-05, "epoch": 0.8909480827091736, "percentage": 69.59, "elapsed_time": "16:11:18", "remaining_time": "7:04:29", "throughput": 656.73, "total_tokens": 38272928} {"current_steps": 27840, "total_steps": 40000, "loss": 0.7474, "lr": 1.0562285337346703e-05, "epoch": 0.891108123679662, "percentage": 69.6, "elapsed_time": "16:11:19", "remaining_time": "7:04:15", "throughput": 656.82, "total_tokens": 38279616} {"current_steps": 27845, "total_steps": 40000, "loss": 0.7213, "lr": 1.0554271613618308e-05, "epoch": 0.8912681646501505, "percentage": 69.61, "elapsed_time": "16:11:21", "remaining_time": "7:04:01", "throughput": 656.93, "total_tokens": 38286672} {"current_steps": 27850, "total_steps": 40000, "loss": 0.8719, "lr": 1.054626011760276e-05, "epoch": 0.8914282056206388, "percentage": 69.62, "elapsed_time": "16:11:23", "remaining_time": "7:03:47", "throughput": 657.03, "total_tokens": 38294016} {"current_steps": 27855, "total_steps": 40000, "loss": 0.6644, "lr": 1.0538250850535549e-05, "epoch": 0.8915882465911273, "percentage": 69.64, "elapsed_time": "16:11:25", "remaining_time": "7:03:32", "throughput": 657.12, "total_tokens": 38300432} {"current_steps": 27860, "total_steps": 40000, "loss": 0.8431, "lr": 1.0530243813651794e-05, "epoch": 0.8917482875616157, "percentage": 69.65, "elapsed_time": "16:11:26", "remaining_time": "7:03:18", "throughput": 657.22, "total_tokens": 38307232} {"current_steps": 27865, "total_steps": 40000, "loss": 0.7676, "lr": 1.0522239008186271e-05, "epoch": 0.8919083285321042, "percentage": 69.66, "elapsed_time": "16:11:28", "remaining_time": "7:03:04", "throughput": 657.32, "total_tokens": 38314048} {"current_steps": 27870, "total_steps": 40000, "loss": 0.7146, "lr": 1.0514236435373434e-05, "epoch": 0.8920683695025927, "percentage": 69.67, "elapsed_time": "16:11:30", "remaining_time": "7:02:49", "throughput": 657.41, "total_tokens": 38320480} {"current_steps": 27875, "total_steps": 40000, "loss": 0.6692, "lr": 1.0506236096447386e-05, "epoch": 0.8922284104730811, "percentage": 69.69, "elapsed_time": "16:11:31", "remaining_time": "7:02:35", "throughput": 657.5, "total_tokens": 38327184} {"current_steps": 27880, "total_steps": 40000, "loss": 0.5807, "lr": 1.049823799264186e-05, "epoch": 0.8923884514435696, "percentage": 69.7, "elapsed_time": "16:11:33", "remaining_time": "7:02:21", "throughput": 657.6, "total_tokens": 38334128} {"current_steps": 27885, "total_steps": 40000, "loss": 0.5635, "lr": 1.049024212519028e-05, "epoch": 0.892548492414058, "percentage": 69.71, "elapsed_time": "16:11:35", "remaining_time": "7:02:07", "throughput": 657.7, "total_tokens": 38340896} {"current_steps": 27890, "total_steps": 40000, "loss": 0.5718, "lr": 1.0482248495325713e-05, "epoch": 0.8927085333845465, "percentage": 69.73, "elapsed_time": "16:11:37", "remaining_time": "7:01:52", "throughput": 657.8, "total_tokens": 38347888} {"current_steps": 27895, "total_steps": 40000, "loss": 0.6816, "lr": 1.047425710428086e-05, "epoch": 0.8928685743550349, "percentage": 69.74, "elapsed_time": "16:11:38", "remaining_time": "7:01:38", "throughput": 657.9, "total_tokens": 38354640} {"current_steps": 27900, "total_steps": 40000, "loss": 0.9021, "lr": 1.0466267953288114e-05, "epoch": 0.8930286153255234, "percentage": 69.75, "elapsed_time": "16:11:40", "remaining_time": "7:01:24", "throughput": 658.0, "total_tokens": 38361568} {"current_steps": 27905, "total_steps": 40000, "loss": 0.7241, "lr": 1.0458281043579482e-05, "epoch": 0.8931886562960117, "percentage": 69.76, "elapsed_time": "16:11:42", "remaining_time": "7:01:10", "throughput": 658.1, "total_tokens": 38368608} {"current_steps": 27910, "total_steps": 40000, "loss": 0.7525, "lr": 1.0450296376386657e-05, "epoch": 0.8933486972665002, "percentage": 69.77, "elapsed_time": "16:11:44", "remaining_time": "7:00:56", "throughput": 658.19, "total_tokens": 38375424} {"current_steps": 27915, "total_steps": 40000, "loss": 0.8832, "lr": 1.044231395294098e-05, "epoch": 0.8935087382369886, "percentage": 69.79, "elapsed_time": "16:11:45", "remaining_time": "7:00:41", "throughput": 658.29, "total_tokens": 38382288} {"current_steps": 27920, "total_steps": 40000, "loss": 0.7825, "lr": 1.0434333774473435e-05, "epoch": 0.8936687792074771, "percentage": 69.8, "elapsed_time": "16:11:47", "remaining_time": "7:00:27", "throughput": 658.4, "total_tokens": 38389488} {"current_steps": 27925, "total_steps": 40000, "loss": 0.6882, "lr": 1.0426355842214657e-05, "epoch": 0.8938288201779656, "percentage": 69.81, "elapsed_time": "16:11:49", "remaining_time": "7:00:13", "throughput": 658.49, "total_tokens": 38395936} {"current_steps": 27930, "total_steps": 40000, "loss": 0.738, "lr": 1.0418380157394963e-05, "epoch": 0.893988861148454, "percentage": 69.83, "elapsed_time": "16:11:51", "remaining_time": "6:59:59", "throughput": 658.59, "total_tokens": 38403216} {"current_steps": 27935, "total_steps": 40000, "loss": 0.5094, "lr": 1.0410406721244281e-05, "epoch": 0.8941489021189425, "percentage": 69.84, "elapsed_time": "16:11:52", "remaining_time": "6:59:45", "throughput": 658.69, "total_tokens": 38410192} {"current_steps": 27940, "total_steps": 40000, "loss": 0.6904, "lr": 1.0402435534992238e-05, "epoch": 0.8943089430894309, "percentage": 69.85, "elapsed_time": "16:11:54", "remaining_time": "6:59:30", "throughput": 658.79, "total_tokens": 38417168} {"current_steps": 27945, "total_steps": 40000, "loss": 0.756, "lr": 1.0394466599868071e-05, "epoch": 0.8944689840599194, "percentage": 69.86, "elapsed_time": "16:11:56", "remaining_time": "6:59:16", "throughput": 658.89, "total_tokens": 38424176} {"current_steps": 27950, "total_steps": 40000, "loss": 0.7434, "lr": 1.0386499917100697e-05, "epoch": 0.8946290250304078, "percentage": 69.88, "elapsed_time": "16:11:58", "remaining_time": "6:59:02", "throughput": 658.99, "total_tokens": 38431056} {"current_steps": 27955, "total_steps": 40000, "loss": 0.8189, "lr": 1.0378535487918692e-05, "epoch": 0.8947890660008962, "percentage": 69.89, "elapsed_time": "16:11:59", "remaining_time": "6:58:48", "throughput": 659.09, "total_tokens": 38437728} {"current_steps": 27960, "total_steps": 40000, "loss": 0.6076, "lr": 1.037057331355025e-05, "epoch": 0.8949491069713846, "percentage": 69.9, "elapsed_time": "16:12:01", "remaining_time": "6:58:34", "throughput": 659.18, "total_tokens": 38444576} {"current_steps": 27965, "total_steps": 40000, "loss": 0.7965, "lr": 1.0362613395223247e-05, "epoch": 0.8951091479418731, "percentage": 69.91, "elapsed_time": "16:12:03", "remaining_time": "6:58:19", "throughput": 659.28, "total_tokens": 38451312} {"current_steps": 27970, "total_steps": 40000, "loss": 0.7459, "lr": 1.0354655734165212e-05, "epoch": 0.8952691889123615, "percentage": 69.92, "elapsed_time": "16:12:04", "remaining_time": "6:58:05", "throughput": 659.38, "total_tokens": 38458448} {"current_steps": 27975, "total_steps": 40000, "loss": 0.6336, "lr": 1.03467003316033e-05, "epoch": 0.89542922988285, "percentage": 69.94, "elapsed_time": "16:12:06", "remaining_time": "6:57:51", "throughput": 659.47, "total_tokens": 38464800} {"current_steps": 27980, "total_steps": 40000, "loss": 0.7527, "lr": 1.033874718876435e-05, "epoch": 0.8955892708533385, "percentage": 69.95, "elapsed_time": "16:12:08", "remaining_time": "6:57:37", "throughput": 659.57, "total_tokens": 38471584} {"current_steps": 27985, "total_steps": 40000, "loss": 0.7774, "lr": 1.0330796306874818e-05, "epoch": 0.8957493118238269, "percentage": 69.96, "elapsed_time": "16:12:10", "remaining_time": "6:57:23", "throughput": 659.66, "total_tokens": 38478256} {"current_steps": 27990, "total_steps": 40000, "loss": 0.6456, "lr": 1.032284768716085e-05, "epoch": 0.8959093527943154, "percentage": 69.97, "elapsed_time": "16:12:11", "remaining_time": "6:57:09", "throughput": 659.77, "total_tokens": 38485408} {"current_steps": 27995, "total_steps": 40000, "loss": 0.7273, "lr": 1.0314901330848206e-05, "epoch": 0.8960693937648038, "percentage": 69.99, "elapsed_time": "16:12:13", "remaining_time": "6:56:55", "throughput": 659.86, "total_tokens": 38492144} {"current_steps": 28000, "total_steps": 40000, "loss": 0.7161, "lr": 1.030695723916233e-05, "epoch": 0.8962294347352923, "percentage": 70.0, "elapsed_time": "16:12:15", "remaining_time": "6:56:40", "throughput": 659.96, "total_tokens": 38498736} {"current_steps": 28000, "total_steps": 40000, "eval_loss": 0.7330058217048645, "epoch": 0.8962294347352923, "percentage": 70.0, "elapsed_time": "16:18:03", "remaining_time": "6:59:09", "throughput": 656.04, "total_tokens": 38498736} {"current_steps": 28005, "total_steps": 40000, "loss": 0.7801, "lr": 1.0299015413328289e-05, "epoch": 0.8963894757057806, "percentage": 70.01, "elapsed_time": "16:18:06", "remaining_time": "6:58:56", "throughput": 656.12, "total_tokens": 38505536} {"current_steps": 28010, "total_steps": 40000, "loss": 0.8318, "lr": 1.0291075854570809e-05, "epoch": 0.8965495166762691, "percentage": 70.03, "elapsed_time": "16:18:08", "remaining_time": "6:58:42", "throughput": 656.22, "total_tokens": 38512416} {"current_steps": 28015, "total_steps": 40000, "loss": 0.8482, "lr": 1.0283138564114275e-05, "epoch": 0.8967095576467575, "percentage": 70.04, "elapsed_time": "16:18:10", "remaining_time": "6:58:28", "throughput": 656.31, "total_tokens": 38519152} {"current_steps": 28020, "total_steps": 40000, "loss": 0.7508, "lr": 1.027520354318273e-05, "epoch": 0.896869598617246, "percentage": 70.05, "elapsed_time": "16:18:11", "remaining_time": "6:58:13", "throughput": 656.41, "total_tokens": 38526048} {"current_steps": 28025, "total_steps": 40000, "loss": 0.7361, "lr": 1.0267270792999828e-05, "epoch": 0.8970296395877344, "percentage": 70.06, "elapsed_time": "16:18:13", "remaining_time": "6:57:59", "throughput": 656.51, "total_tokens": 38532816} {"current_steps": 28030, "total_steps": 40000, "loss": 0.696, "lr": 1.0259340314788919e-05, "epoch": 0.8971896805582229, "percentage": 70.08, "elapsed_time": "16:18:15", "remaining_time": "6:57:45", "throughput": 656.6, "total_tokens": 38539216} {"current_steps": 28035, "total_steps": 40000, "loss": 0.7488, "lr": 1.0251412109772979e-05, "epoch": 0.8973497215287114, "percentage": 70.09, "elapsed_time": "16:18:17", "remaining_time": "6:57:31", "throughput": 656.7, "total_tokens": 38546240} {"current_steps": 28040, "total_steps": 40000, "loss": 0.9096, "lr": 1.0243486179174627e-05, "epoch": 0.8975097624991998, "percentage": 70.1, "elapsed_time": "16:18:18", "remaining_time": "6:57:16", "throughput": 656.79, "total_tokens": 38552976} {"current_steps": 28045, "total_steps": 40000, "loss": 0.6747, "lr": 1.0235562524216158e-05, "epoch": 0.8976698034696883, "percentage": 70.11, "elapsed_time": "16:18:20", "remaining_time": "6:57:02", "throughput": 656.9, "total_tokens": 38560320} {"current_steps": 28050, "total_steps": 40000, "loss": 0.8631, "lr": 1.022764114611948e-05, "epoch": 0.8978298444401767, "percentage": 70.12, "elapsed_time": "16:18:22", "remaining_time": "6:56:48", "throughput": 657.0, "total_tokens": 38567152} {"current_steps": 28055, "total_steps": 40000, "loss": 0.6907, "lr": 1.0219722046106178e-05, "epoch": 0.8979898854106652, "percentage": 70.14, "elapsed_time": "16:18:23", "remaining_time": "6:56:34", "throughput": 657.08, "total_tokens": 38573456} {"current_steps": 28060, "total_steps": 40000, "loss": 0.5764, "lr": 1.0211805225397486e-05, "epoch": 0.8981499263811535, "percentage": 70.15, "elapsed_time": "16:18:25", "remaining_time": "6:56:20", "throughput": 657.18, "total_tokens": 38580352} {"current_steps": 28065, "total_steps": 40000, "loss": 0.7201, "lr": 1.020389068521426e-05, "epoch": 0.898309967351642, "percentage": 70.16, "elapsed_time": "16:18:27", "remaining_time": "6:56:06", "throughput": 657.27, "total_tokens": 38586848} {"current_steps": 28070, "total_steps": 40000, "loss": 0.8618, "lr": 1.0195978426777039e-05, "epoch": 0.8984700083221304, "percentage": 70.17, "elapsed_time": "16:18:29", "remaining_time": "6:55:51", "throughput": 657.38, "total_tokens": 38594272} {"current_steps": 28075, "total_steps": 40000, "loss": 0.9128, "lr": 1.0188068451305982e-05, "epoch": 0.8986300492926189, "percentage": 70.19, "elapsed_time": "16:18:30", "remaining_time": "6:55:37", "throughput": 657.48, "total_tokens": 38600992} {"current_steps": 28080, "total_steps": 40000, "loss": 0.7356, "lr": 1.0180160760020902e-05, "epoch": 0.8987900902631074, "percentage": 70.2, "elapsed_time": "16:18:32", "remaining_time": "6:55:23", "throughput": 657.57, "total_tokens": 38607776} {"current_steps": 28085, "total_steps": 40000, "loss": 0.6806, "lr": 1.0172255354141278e-05, "epoch": 0.8989501312335958, "percentage": 70.21, "elapsed_time": "16:18:34", "remaining_time": "6:55:09", "throughput": 657.67, "total_tokens": 38614560} {"current_steps": 28090, "total_steps": 40000, "loss": 0.7195, "lr": 1.0164352234886205e-05, "epoch": 0.8991101722040843, "percentage": 70.23, "elapsed_time": "16:18:36", "remaining_time": "6:54:55", "throughput": 657.76, "total_tokens": 38621280} {"current_steps": 28095, "total_steps": 40000, "loss": 0.5159, "lr": 1.0156451403474454e-05, "epoch": 0.8992702131745727, "percentage": 70.24, "elapsed_time": "16:18:37", "remaining_time": "6:54:41", "throughput": 657.86, "total_tokens": 38628224} {"current_steps": 28100, "total_steps": 40000, "loss": 0.6806, "lr": 1.0148552861124443e-05, "epoch": 0.8994302541450612, "percentage": 70.25, "elapsed_time": "16:18:39", "remaining_time": "6:54:27", "throughput": 657.97, "total_tokens": 38635552} {"current_steps": 28105, "total_steps": 40000, "loss": 0.6182, "lr": 1.0140656609054205e-05, "epoch": 0.8995902951155496, "percentage": 70.26, "elapsed_time": "16:18:41", "remaining_time": "6:54:12", "throughput": 658.07, "total_tokens": 38642704} {"current_steps": 28110, "total_steps": 40000, "loss": 0.5292, "lr": 1.0132762648481455e-05, "epoch": 0.899750336086038, "percentage": 70.28, "elapsed_time": "16:18:43", "remaining_time": "6:53:58", "throughput": 658.17, "total_tokens": 38649728} {"current_steps": 28115, "total_steps": 40000, "loss": 0.8125, "lr": 1.0124870980623543e-05, "epoch": 0.8999103770565264, "percentage": 70.29, "elapsed_time": "16:18:44", "remaining_time": "6:53:44", "throughput": 658.27, "total_tokens": 38656688} {"current_steps": 28120, "total_steps": 40000, "loss": 0.8507, "lr": 1.0116981606697453e-05, "epoch": 0.9000704180270149, "percentage": 70.3, "elapsed_time": "16:18:46", "remaining_time": "6:53:30", "throughput": 658.36, "total_tokens": 38663280} {"current_steps": 28125, "total_steps": 40000, "loss": 0.7593, "lr": 1.0109094527919838e-05, "epoch": 0.9002304589975033, "percentage": 70.31, "elapsed_time": "16:18:48", "remaining_time": "6:53:16", "throughput": 658.45, "total_tokens": 38669872} {"current_steps": 28130, "total_steps": 40000, "loss": 0.7272, "lr": 1.010120974550697e-05, "epoch": 0.9003904999679918, "percentage": 70.33, "elapsed_time": "16:18:50", "remaining_time": "6:53:02", "throughput": 658.55, "total_tokens": 38676720} {"current_steps": 28135, "total_steps": 40000, "loss": 0.7006, "lr": 1.0093327260674795e-05, "epoch": 0.9005505409384803, "percentage": 70.34, "elapsed_time": "16:18:51", "remaining_time": "6:52:48", "throughput": 658.65, "total_tokens": 38683696} {"current_steps": 28140, "total_steps": 40000, "loss": 0.7929, "lr": 1.0085447074638878e-05, "epoch": 0.9007105819089687, "percentage": 70.35, "elapsed_time": "16:18:53", "remaining_time": "6:52:34", "throughput": 658.74, "total_tokens": 38690288} {"current_steps": 28145, "total_steps": 40000, "loss": 0.6394, "lr": 1.0077569188614461e-05, "epoch": 0.9008706228794572, "percentage": 70.36, "elapsed_time": "16:18:55", "remaining_time": "6:52:19", "throughput": 658.84, "total_tokens": 38696944} {"current_steps": 28150, "total_steps": 40000, "loss": 0.6285, "lr": 1.0069693603816393e-05, "epoch": 0.9010306638499456, "percentage": 70.38, "elapsed_time": "16:18:57", "remaining_time": "6:52:05", "throughput": 658.93, "total_tokens": 38703600} {"current_steps": 28155, "total_steps": 40000, "loss": 0.7169, "lr": 1.0061820321459204e-05, "epoch": 0.9011907048204341, "percentage": 70.39, "elapsed_time": "16:18:58", "remaining_time": "6:51:51", "throughput": 659.03, "total_tokens": 38710448} {"current_steps": 28160, "total_steps": 40000, "loss": 0.5492, "lr": 1.0053949342757038e-05, "epoch": 0.9013507457909224, "percentage": 70.4, "elapsed_time": "16:19:00", "remaining_time": "6:51:37", "throughput": 659.12, "total_tokens": 38717024} {"current_steps": 28165, "total_steps": 40000, "loss": 0.8858, "lr": 1.0046080668923717e-05, "epoch": 0.9015107867614109, "percentage": 70.41, "elapsed_time": "16:19:02", "remaining_time": "6:51:23", "throughput": 659.22, "total_tokens": 38724032} {"current_steps": 28170, "total_steps": 40000, "loss": 0.6023, "lr": 1.003821430117267e-05, "epoch": 0.9016708277318993, "percentage": 70.43, "elapsed_time": "16:19:03", "remaining_time": "6:51:09", "throughput": 659.32, "total_tokens": 38731152} {"current_steps": 28175, "total_steps": 40000, "loss": 0.7929, "lr": 1.0030350240716999e-05, "epoch": 0.9018308687023878, "percentage": 70.44, "elapsed_time": "16:19:05", "remaining_time": "6:50:55", "throughput": 659.42, "total_tokens": 38738016} {"current_steps": 28180, "total_steps": 40000, "loss": 0.8742, "lr": 1.0022488488769449e-05, "epoch": 0.9019909096728762, "percentage": 70.45, "elapsed_time": "16:19:07", "remaining_time": "6:50:41", "throughput": 659.51, "total_tokens": 38744608} {"current_steps": 28185, "total_steps": 40000, "loss": 0.8819, "lr": 1.0014629046542387e-05, "epoch": 0.9021509506433647, "percentage": 70.46, "elapsed_time": "16:19:09", "remaining_time": "6:50:27", "throughput": 659.61, "total_tokens": 38751568} {"current_steps": 28190, "total_steps": 40000, "loss": 0.6236, "lr": 1.0006771915247842e-05, "epoch": 0.9023109916138532, "percentage": 70.47, "elapsed_time": "16:19:10", "remaining_time": "6:50:13", "throughput": 659.71, "total_tokens": 38758352} {"current_steps": 28195, "total_steps": 40000, "loss": 0.7719, "lr": 9.998917096097495e-06, "epoch": 0.9024710325843416, "percentage": 70.49, "elapsed_time": "16:19:12", "remaining_time": "6:49:59", "throughput": 659.8, "total_tokens": 38765072} {"current_steps": 28200, "total_steps": 40000, "loss": 0.6364, "lr": 9.991064590302638e-06, "epoch": 0.9026310735548301, "percentage": 70.5, "elapsed_time": "16:19:14", "remaining_time": "6:49:45", "throughput": 659.9, "total_tokens": 38771760} {"current_steps": 28200, "total_steps": 40000, "eval_loss": 0.7328228950500488, "epoch": 0.9026310735548301, "percentage": 70.5, "elapsed_time": "16:25:02", "remaining_time": "6:52:10", "throughput": 656.01, "total_tokens": 38771760} {"current_steps": 28205, "total_steps": 40000, "loss": 0.7833, "lr": 9.983214399074241e-06, "epoch": 0.9027911145253185, "percentage": 70.51, "elapsed_time": "16:25:05", "remaining_time": "6:51:57", "throughput": 656.09, "total_tokens": 38778448} {"current_steps": 28210, "total_steps": 40000, "loss": 0.7058, "lr": 9.975366523622893e-06, "epoch": 0.902951155495807, "percentage": 70.53, "elapsed_time": "16:25:07", "remaining_time": "6:51:43", "throughput": 656.18, "total_tokens": 38785344} {"current_steps": 28215, "total_steps": 40000, "loss": 0.6214, "lr": 9.967520965158841e-06, "epoch": 0.9031111964662953, "percentage": 70.54, "elapsed_time": "16:25:09", "remaining_time": "6:51:29", "throughput": 656.29, "total_tokens": 38793056} {"current_steps": 28220, "total_steps": 40000, "loss": 0.8383, "lr": 9.95967772489197e-06, "epoch": 0.9032712374367838, "percentage": 70.55, "elapsed_time": "16:25:10", "remaining_time": "6:51:14", "throughput": 656.39, "total_tokens": 38800032} {"current_steps": 28225, "total_steps": 40000, "loss": 0.6619, "lr": 9.951836804031794e-06, "epoch": 0.9034312784072722, "percentage": 70.56, "elapsed_time": "16:25:12", "remaining_time": "6:51:00", "throughput": 656.48, "total_tokens": 38806480} {"current_steps": 28230, "total_steps": 40000, "loss": 0.55, "lr": 9.943998203787489e-06, "epoch": 0.9035913193777607, "percentage": 70.58, "elapsed_time": "16:25:14", "remaining_time": "6:50:46", "throughput": 656.58, "total_tokens": 38813232} {"current_steps": 28235, "total_steps": 40000, "loss": 0.7725, "lr": 9.936161925367874e-06, "epoch": 0.9037513603482491, "percentage": 70.59, "elapsed_time": "16:25:16", "remaining_time": "6:50:32", "throughput": 656.67, "total_tokens": 38819856} {"current_steps": 28240, "total_steps": 40000, "loss": 0.5962, "lr": 9.928327969981386e-06, "epoch": 0.9039114013187376, "percentage": 70.6, "elapsed_time": "16:25:17", "remaining_time": "6:50:18", "throughput": 656.77, "total_tokens": 38826624} {"current_steps": 28245, "total_steps": 40000, "loss": 0.6455, "lr": 9.920496338836135e-06, "epoch": 0.9040714422892261, "percentage": 70.61, "elapsed_time": "16:25:19", "remaining_time": "6:50:04", "throughput": 656.86, "total_tokens": 38833408} {"current_steps": 28250, "total_steps": 40000, "loss": 0.6931, "lr": 9.912667033139844e-06, "epoch": 0.9042314832597145, "percentage": 70.62, "elapsed_time": "16:25:21", "remaining_time": "6:49:50", "throughput": 656.96, "total_tokens": 38840208} {"current_steps": 28255, "total_steps": 40000, "loss": 0.8975, "lr": 9.904840054099893e-06, "epoch": 0.904391524230203, "percentage": 70.64, "elapsed_time": "16:25:23", "remaining_time": "6:49:36", "throughput": 657.07, "total_tokens": 38847744} {"current_steps": 28260, "total_steps": 40000, "loss": 0.7627, "lr": 9.897015402923312e-06, "epoch": 0.9045515652006914, "percentage": 70.65, "elapsed_time": "16:25:24", "remaining_time": "6:49:22", "throughput": 657.16, "total_tokens": 38854240} {"current_steps": 28265, "total_steps": 40000, "loss": 0.8284, "lr": 9.889193080816744e-06, "epoch": 0.9047116061711798, "percentage": 70.66, "elapsed_time": "16:25:26", "remaining_time": "6:49:08", "throughput": 657.26, "total_tokens": 38861728} {"current_steps": 28270, "total_steps": 40000, "loss": 0.8353, "lr": 9.881373088986498e-06, "epoch": 0.9048716471416682, "percentage": 70.67, "elapsed_time": "16:25:28", "remaining_time": "6:48:53", "throughput": 657.36, "total_tokens": 38868800} {"current_steps": 28275, "total_steps": 40000, "loss": 0.6221, "lr": 9.873555428638523e-06, "epoch": 0.9050316881121567, "percentage": 70.69, "elapsed_time": "16:25:30", "remaining_time": "6:48:39", "throughput": 657.46, "total_tokens": 38875600} {"current_steps": 28280, "total_steps": 40000, "loss": 0.7345, "lr": 9.865740100978383e-06, "epoch": 0.9051917290826451, "percentage": 70.7, "elapsed_time": "16:25:31", "remaining_time": "6:48:25", "throughput": 657.55, "total_tokens": 38882400} {"current_steps": 28285, "total_steps": 40000, "loss": 0.7196, "lr": 9.857927107211315e-06, "epoch": 0.9053517700531336, "percentage": 70.71, "elapsed_time": "16:25:33", "remaining_time": "6:48:11", "throughput": 657.65, "total_tokens": 38889168} {"current_steps": 28290, "total_steps": 40000, "loss": 0.7431, "lr": 9.850116448542177e-06, "epoch": 0.905511811023622, "percentage": 70.73, "elapsed_time": "16:25:35", "remaining_time": "6:47:57", "throughput": 657.74, "total_tokens": 38895776} {"current_steps": 28295, "total_steps": 40000, "loss": 0.719, "lr": 9.842308126175457e-06, "epoch": 0.9056718519941105, "percentage": 70.74, "elapsed_time": "16:25:37", "remaining_time": "6:47:43", "throughput": 657.85, "total_tokens": 38903056} {"current_steps": 28300, "total_steps": 40000, "loss": 0.6746, "lr": 9.834502141315315e-06, "epoch": 0.905831892964599, "percentage": 70.75, "elapsed_time": "16:25:38", "remaining_time": "6:47:29", "throughput": 657.95, "total_tokens": 38910112} {"current_steps": 28305, "total_steps": 40000, "loss": 0.6783, "lr": 9.82669849516552e-06, "epoch": 0.9059919339350874, "percentage": 70.76, "elapsed_time": "16:25:40", "remaining_time": "6:47:15", "throughput": 658.04, "total_tokens": 38916832} {"current_steps": 28310, "total_steps": 40000, "loss": 0.7663, "lr": 9.818897188929493e-06, "epoch": 0.9061519749055759, "percentage": 70.78, "elapsed_time": "16:25:42", "remaining_time": "6:47:01", "throughput": 658.14, "total_tokens": 38923696} {"current_steps": 28315, "total_steps": 40000, "loss": 0.7609, "lr": 9.811098223810309e-06, "epoch": 0.9063120158760642, "percentage": 70.79, "elapsed_time": "16:25:43", "remaining_time": "6:46:47", "throughput": 658.24, "total_tokens": 38930784} {"current_steps": 28320, "total_steps": 40000, "loss": 0.6639, "lr": 9.803301601010641e-06, "epoch": 0.9064720568465527, "percentage": 70.8, "elapsed_time": "16:25:45", "remaining_time": "6:46:33", "throughput": 658.33, "total_tokens": 38937424} {"current_steps": 28325, "total_steps": 40000, "loss": 0.5918, "lr": 9.795507321732853e-06, "epoch": 0.9066320978170411, "percentage": 70.81, "elapsed_time": "16:25:47", "remaining_time": "6:46:19", "throughput": 658.42, "total_tokens": 38943984} {"current_steps": 28330, "total_steps": 40000, "loss": 0.7767, "lr": 9.787715387178898e-06, "epoch": 0.9067921387875296, "percentage": 70.83, "elapsed_time": "16:25:49", "remaining_time": "6:46:05", "throughput": 658.52, "total_tokens": 38950688} {"current_steps": 28335, "total_steps": 40000, "loss": 0.8108, "lr": 9.779925798550399e-06, "epoch": 0.906952179758018, "percentage": 70.84, "elapsed_time": "16:25:50", "remaining_time": "6:45:51", "throughput": 658.61, "total_tokens": 38957456} {"current_steps": 28340, "total_steps": 40000, "loss": 0.8039, "lr": 9.772138557048619e-06, "epoch": 0.9071122207285065, "percentage": 70.85, "elapsed_time": "16:25:52", "remaining_time": "6:45:37", "throughput": 658.71, "total_tokens": 38964208} {"current_steps": 28345, "total_steps": 40000, "loss": 0.5175, "lr": 9.764353663874426e-06, "epoch": 0.907272261698995, "percentage": 70.86, "elapsed_time": "16:25:54", "remaining_time": "6:45:23", "throughput": 658.8, "total_tokens": 38971152} {"current_steps": 28350, "total_steps": 40000, "loss": 0.653, "lr": 9.756571120228375e-06, "epoch": 0.9074323026694834, "percentage": 70.88, "elapsed_time": "16:25:56", "remaining_time": "6:45:09", "throughput": 658.9, "total_tokens": 38978112} {"current_steps": 28355, "total_steps": 40000, "loss": 0.5939, "lr": 9.748790927310605e-06, "epoch": 0.9075923436399719, "percentage": 70.89, "elapsed_time": "16:25:57", "remaining_time": "6:44:55", "throughput": 659.0, "total_tokens": 38984736} {"current_steps": 28360, "total_steps": 40000, "loss": 0.5585, "lr": 9.741013086320946e-06, "epoch": 0.9077523846104603, "percentage": 70.9, "elapsed_time": "16:25:59", "remaining_time": "6:44:41", "throughput": 659.09, "total_tokens": 38991696} {"current_steps": 28365, "total_steps": 40000, "loss": 0.698, "lr": 9.733237598458821e-06, "epoch": 0.9079124255809488, "percentage": 70.91, "elapsed_time": "16:26:01", "remaining_time": "6:44:27", "throughput": 659.19, "total_tokens": 38998800} {"current_steps": 28370, "total_steps": 40000, "loss": 0.5923, "lr": 9.725464464923308e-06, "epoch": 0.9080724665514371, "percentage": 70.93, "elapsed_time": "16:26:03", "remaining_time": "6:44:13", "throughput": 659.29, "total_tokens": 39005536} {"current_steps": 28375, "total_steps": 40000, "loss": 0.8524, "lr": 9.717693686913123e-06, "epoch": 0.9082325075219256, "percentage": 70.94, "elapsed_time": "16:26:04", "remaining_time": "6:43:59", "throughput": 659.38, "total_tokens": 39012352} {"current_steps": 28380, "total_steps": 40000, "loss": 0.6932, "lr": 9.709925265626632e-06, "epoch": 0.908392548492414, "percentage": 70.95, "elapsed_time": "16:26:06", "remaining_time": "6:43:45", "throughput": 659.48, "total_tokens": 39019088} {"current_steps": 28385, "total_steps": 40000, "loss": 0.7556, "lr": 9.702159202261801e-06, "epoch": 0.9085525894629025, "percentage": 70.96, "elapsed_time": "16:26:08", "remaining_time": "6:43:31", "throughput": 659.57, "total_tokens": 39025728} {"current_steps": 28390, "total_steps": 40000, "loss": 0.7011, "lr": 9.694395498016268e-06, "epoch": 0.9087126304333909, "percentage": 70.97, "elapsed_time": "16:26:09", "remaining_time": "6:43:17", "throughput": 659.67, "total_tokens": 39032416} {"current_steps": 28395, "total_steps": 40000, "loss": 0.6558, "lr": 9.686634154087298e-06, "epoch": 0.9088726714038794, "percentage": 70.99, "elapsed_time": "16:26:11", "remaining_time": "6:43:03", "throughput": 659.76, "total_tokens": 39039040} {"current_steps": 28400, "total_steps": 40000, "loss": 0.7501, "lr": 9.678875171671776e-06, "epoch": 0.9090327123743679, "percentage": 71.0, "elapsed_time": "16:26:13", "remaining_time": "6:42:49", "throughput": 659.85, "total_tokens": 39045824} {"current_steps": 28400, "total_steps": 40000, "eval_loss": 0.7328060269355774, "epoch": 0.9090327123743679, "percentage": 71.0, "elapsed_time": "16:32:00", "remaining_time": "6:45:11", "throughput": 656.0, "total_tokens": 39045824} {"current_steps": 28405, "total_steps": 40000, "loss": 0.6805, "lr": 9.671118551966246e-06, "epoch": 0.9091927533448563, "percentage": 71.01, "elapsed_time": "16:32:04", "remaining_time": "6:44:58", "throughput": 656.07, "total_tokens": 39052480} {"current_steps": 28410, "total_steps": 40000, "loss": 0.7317, "lr": 9.66336429616686e-06, "epoch": 0.9093527943153448, "percentage": 71.03, "elapsed_time": "16:32:06", "remaining_time": "6:44:44", "throughput": 656.16, "total_tokens": 39059024} {"current_steps": 28415, "total_steps": 40000, "loss": 0.8482, "lr": 9.655612405469436e-06, "epoch": 0.9095128352858332, "percentage": 71.04, "elapsed_time": "16:32:07", "remaining_time": "6:44:29", "throughput": 656.26, "total_tokens": 39066000} {"current_steps": 28420, "total_steps": 40000, "loss": 0.7193, "lr": 9.647862881069413e-06, "epoch": 0.9096728762563216, "percentage": 71.05, "elapsed_time": "16:32:09", "remaining_time": "6:44:15", "throughput": 656.36, "total_tokens": 39073024} {"current_steps": 28425, "total_steps": 40000, "loss": 0.8037, "lr": 9.640115724161855e-06, "epoch": 0.90983291722681, "percentage": 71.06, "elapsed_time": "16:32:11", "remaining_time": "6:44:01", "throughput": 656.47, "total_tokens": 39080464} {"current_steps": 28430, "total_steps": 40000, "loss": 0.7409, "lr": 9.632370935941483e-06, "epoch": 0.9099929581972985, "percentage": 71.08, "elapsed_time": "16:32:13", "remaining_time": "6:43:47", "throughput": 656.57, "total_tokens": 39087760} {"current_steps": 28435, "total_steps": 40000, "loss": 0.8347, "lr": 9.624628517602634e-06, "epoch": 0.9101529991677869, "percentage": 71.09, "elapsed_time": "16:32:14", "remaining_time": "6:43:33", "throughput": 656.67, "total_tokens": 39094768} {"current_steps": 28440, "total_steps": 40000, "loss": 0.8834, "lr": 9.61688847033928e-06, "epoch": 0.9103130401382754, "percentage": 71.1, "elapsed_time": "16:32:16", "remaining_time": "6:43:19", "throughput": 656.77, "total_tokens": 39101632} {"current_steps": 28445, "total_steps": 40000, "loss": 0.6151, "lr": 9.609150795345051e-06, "epoch": 0.9104730811087638, "percentage": 71.11, "elapsed_time": "16:32:18", "remaining_time": "6:43:05", "throughput": 656.86, "total_tokens": 39108576} {"current_steps": 28450, "total_steps": 40000, "loss": 0.5503, "lr": 9.601415493813171e-06, "epoch": 0.9106331220792523, "percentage": 71.12, "elapsed_time": "16:32:20", "remaining_time": "6:42:51", "throughput": 656.96, "total_tokens": 39115392} {"current_steps": 28455, "total_steps": 40000, "loss": 0.5864, "lr": 9.593682566936533e-06, "epoch": 0.9107931630497408, "percentage": 71.14, "elapsed_time": "16:32:21", "remaining_time": "6:42:37", "throughput": 657.06, "total_tokens": 39122288} {"current_steps": 28460, "total_steps": 40000, "loss": 0.675, "lr": 9.58595201590766e-06, "epoch": 0.9109532040202292, "percentage": 71.15, "elapsed_time": "16:32:23", "remaining_time": "6:42:23", "throughput": 657.16, "total_tokens": 39129680} {"current_steps": 28465, "total_steps": 40000, "loss": 0.8327, "lr": 9.578223841918681e-06, "epoch": 0.9111132449907177, "percentage": 71.16, "elapsed_time": "16:32:25", "remaining_time": "6:42:09", "throughput": 657.25, "total_tokens": 39136096} {"current_steps": 28470, "total_steps": 40000, "loss": 0.6234, "lr": 9.570498046161389e-06, "epoch": 0.911273285961206, "percentage": 71.17, "elapsed_time": "16:32:27", "remaining_time": "6:41:55", "throughput": 657.34, "total_tokens": 39142608} {"current_steps": 28475, "total_steps": 40000, "loss": 0.6489, "lr": 9.562774629827206e-06, "epoch": 0.9114333269316945, "percentage": 71.19, "elapsed_time": "16:32:28", "remaining_time": "6:41:41", "throughput": 657.44, "total_tokens": 39149520} {"current_steps": 28480, "total_steps": 40000, "loss": 0.6679, "lr": 9.555053594107163e-06, "epoch": 0.9115933679021829, "percentage": 71.2, "elapsed_time": "16:32:30", "remaining_time": "6:41:27", "throughput": 657.53, "total_tokens": 39156384} {"current_steps": 28485, "total_steps": 40000, "loss": 0.9353, "lr": 9.547334940191957e-06, "epoch": 0.9117534088726714, "percentage": 71.21, "elapsed_time": "16:32:32", "remaining_time": "6:41:13", "throughput": 657.62, "total_tokens": 39162912} {"current_steps": 28490, "total_steps": 40000, "loss": 0.6599, "lr": 9.539618669271886e-06, "epoch": 0.9119134498431598, "percentage": 71.23, "elapsed_time": "16:32:34", "remaining_time": "6:40:59", "throughput": 657.73, "total_tokens": 39170208} {"current_steps": 28495, "total_steps": 40000, "loss": 0.6503, "lr": 9.531904782536904e-06, "epoch": 0.9120734908136483, "percentage": 71.24, "elapsed_time": "16:32:35", "remaining_time": "6:40:45", "throughput": 657.82, "total_tokens": 39176832} {"current_steps": 28500, "total_steps": 40000, "loss": 0.8963, "lr": 9.524193281176597e-06, "epoch": 0.9122335317841367, "percentage": 71.25, "elapsed_time": "16:32:37", "remaining_time": "6:40:31", "throughput": 657.92, "total_tokens": 39183968} {"current_steps": 28505, "total_steps": 40000, "loss": 0.7824, "lr": 9.516484166380165e-06, "epoch": 0.9123935727546252, "percentage": 71.26, "elapsed_time": "16:32:39", "remaining_time": "6:40:18", "throughput": 658.01, "total_tokens": 39190624} {"current_steps": 28510, "total_steps": 40000, "loss": 0.7133, "lr": 9.508777439336447e-06, "epoch": 0.9125536137251137, "percentage": 71.28, "elapsed_time": "16:32:40", "remaining_time": "6:40:04", "throughput": 658.1, "total_tokens": 39197344} {"current_steps": 28515, "total_steps": 40000, "loss": 0.6166, "lr": 9.50107310123393e-06, "epoch": 0.9127136546956021, "percentage": 71.29, "elapsed_time": "16:32:42", "remaining_time": "6:39:50", "throughput": 658.2, "total_tokens": 39204336} {"current_steps": 28520, "total_steps": 40000, "loss": 0.7382, "lr": 9.493371153260702e-06, "epoch": 0.9128736956660906, "percentage": 71.3, "elapsed_time": "16:32:44", "remaining_time": "6:39:36", "throughput": 658.29, "total_tokens": 39210896} {"current_steps": 28525, "total_steps": 40000, "loss": 0.776, "lr": 9.485671596604523e-06, "epoch": 0.9130337366365789, "percentage": 71.31, "elapsed_time": "16:32:46", "remaining_time": "6:39:22", "throughput": 658.39, "total_tokens": 39218048} {"current_steps": 28530, "total_steps": 40000, "loss": 0.5721, "lr": 9.477974432452738e-06, "epoch": 0.9131937776070674, "percentage": 71.33, "elapsed_time": "16:32:47", "remaining_time": "6:39:08", "throughput": 658.49, "total_tokens": 39224896} {"current_steps": 28535, "total_steps": 40000, "loss": 0.695, "lr": 9.470279661992356e-06, "epoch": 0.9133538185775558, "percentage": 71.34, "elapsed_time": "16:32:49", "remaining_time": "6:38:54", "throughput": 658.59, "total_tokens": 39231952} {"current_steps": 28540, "total_steps": 40000, "loss": 0.7419, "lr": 9.462587286410021e-06, "epoch": 0.9135138595480443, "percentage": 71.35, "elapsed_time": "16:32:51", "remaining_time": "6:38:40", "throughput": 658.68, "total_tokens": 39238736} {"current_steps": 28545, "total_steps": 40000, "loss": 0.917, "lr": 9.454897306891972e-06, "epoch": 0.9136739005185327, "percentage": 71.36, "elapsed_time": "16:32:53", "remaining_time": "6:38:26", "throughput": 658.78, "total_tokens": 39245728} {"current_steps": 28550, "total_steps": 40000, "loss": 0.6414, "lr": 9.44720972462411e-06, "epoch": 0.9138339414890212, "percentage": 71.38, "elapsed_time": "16:32:54", "remaining_time": "6:38:12", "throughput": 658.87, "total_tokens": 39252256} {"current_steps": 28555, "total_steps": 40000, "loss": 0.6274, "lr": 9.439524540791964e-06, "epoch": 0.9139939824595096, "percentage": 71.39, "elapsed_time": "16:32:56", "remaining_time": "6:37:58", "throughput": 658.97, "total_tokens": 39258928} {"current_steps": 28560, "total_steps": 40000, "loss": 0.6974, "lr": 9.431841756580673e-06, "epoch": 0.9141540234299981, "percentage": 71.4, "elapsed_time": "16:32:58", "remaining_time": "6:37:44", "throughput": 659.07, "total_tokens": 39266016} {"current_steps": 28565, "total_steps": 40000, "loss": 0.7381, "lr": 9.42416137317503e-06, "epoch": 0.9143140644004866, "percentage": 71.41, "elapsed_time": "16:33:00", "remaining_time": "6:37:30", "throughput": 659.17, "total_tokens": 39273424} {"current_steps": 28570, "total_steps": 40000, "loss": 0.8142, "lr": 9.416483391759437e-06, "epoch": 0.914474105370975, "percentage": 71.43, "elapsed_time": "16:33:01", "remaining_time": "6:37:16", "throughput": 659.27, "total_tokens": 39280320} {"current_steps": 28575, "total_steps": 40000, "loss": 0.8143, "lr": 9.408807813517945e-06, "epoch": 0.9146341463414634, "percentage": 71.44, "elapsed_time": "16:33:03", "remaining_time": "6:37:02", "throughput": 659.36, "total_tokens": 39286912} {"current_steps": 28580, "total_steps": 40000, "loss": 0.5969, "lr": 9.401134639634221e-06, "epoch": 0.9147941873119518, "percentage": 71.45, "elapsed_time": "16:33:05", "remaining_time": "6:36:49", "throughput": 659.45, "total_tokens": 39293600} {"current_steps": 28585, "total_steps": 40000, "loss": 0.7142, "lr": 9.393463871291555e-06, "epoch": 0.9149542282824403, "percentage": 71.46, "elapsed_time": "16:33:06", "remaining_time": "6:36:35", "throughput": 659.55, "total_tokens": 39300496} {"current_steps": 28590, "total_steps": 40000, "loss": 0.7918, "lr": 9.385795509672881e-06, "epoch": 0.9151142692529287, "percentage": 71.47, "elapsed_time": "16:33:08", "remaining_time": "6:36:21", "throughput": 659.64, "total_tokens": 39307152} {"current_steps": 28595, "total_steps": 40000, "loss": 0.7918, "lr": 9.378129555960771e-06, "epoch": 0.9152743102234172, "percentage": 71.49, "elapsed_time": "16:33:10", "remaining_time": "6:36:07", "throughput": 659.73, "total_tokens": 39313712} {"current_steps": 28600, "total_steps": 40000, "loss": 0.505, "lr": 9.370466011337392e-06, "epoch": 0.9154343511939056, "percentage": 71.5, "elapsed_time": "16:33:12", "remaining_time": "6:35:53", "throughput": 659.83, "total_tokens": 39320736} {"current_steps": 28600, "total_steps": 40000, "eval_loss": 0.7327534556388855, "epoch": 0.9154343511939056, "percentage": 71.5, "elapsed_time": "16:39:00", "remaining_time": "6:38:12", "throughput": 655.99, "total_tokens": 39320736} {"current_steps": 28605, "total_steps": 40000, "loss": 0.7105, "lr": 9.362804876984573e-06, "epoch": 0.9155943921643941, "percentage": 71.51, "elapsed_time": "16:39:04", "remaining_time": "6:37:59", "throughput": 656.07, "total_tokens": 39327648} {"current_steps": 28610, "total_steps": 40000, "loss": 0.7982, "lr": 9.355146154083747e-06, "epoch": 0.9157544331348826, "percentage": 71.53, "elapsed_time": "16:39:05", "remaining_time": "6:37:45", "throughput": 656.16, "total_tokens": 39334192} {"current_steps": 28615, "total_steps": 40000, "loss": 0.7183, "lr": 9.347489843815987e-06, "epoch": 0.915914474105371, "percentage": 71.54, "elapsed_time": "16:39:07", "remaining_time": "6:37:31", "throughput": 656.26, "total_tokens": 39341376} {"current_steps": 28620, "total_steps": 40000, "loss": 0.6519, "lr": 9.339835947362002e-06, "epoch": 0.9160745150758595, "percentage": 71.55, "elapsed_time": "16:39:09", "remaining_time": "6:37:17", "throughput": 656.36, "total_tokens": 39348320} {"current_steps": 28625, "total_steps": 40000, "loss": 0.5756, "lr": 9.332184465902105e-06, "epoch": 0.9162345560463478, "percentage": 71.56, "elapsed_time": "16:39:11", "remaining_time": "6:37:03", "throughput": 656.45, "total_tokens": 39354976} {"current_steps": 28630, "total_steps": 40000, "loss": 0.6579, "lr": 9.324535400616266e-06, "epoch": 0.9163945970168363, "percentage": 71.58, "elapsed_time": "16:39:12", "remaining_time": "6:36:49", "throughput": 656.55, "total_tokens": 39362032} {"current_steps": 28635, "total_steps": 40000, "loss": 0.7224, "lr": 9.31688875268405e-06, "epoch": 0.9165546379873247, "percentage": 71.59, "elapsed_time": "16:39:14", "remaining_time": "6:36:35", "throughput": 656.65, "total_tokens": 39368960} {"current_steps": 28640, "total_steps": 40000, "loss": 0.695, "lr": 9.309244523284674e-06, "epoch": 0.9167146789578132, "percentage": 71.6, "elapsed_time": "16:39:16", "remaining_time": "6:36:21", "throughput": 656.75, "total_tokens": 39376304} {"current_steps": 28645, "total_steps": 40000, "loss": 0.9641, "lr": 9.301602713596982e-06, "epoch": 0.9168747199283016, "percentage": 71.61, "elapsed_time": "16:39:18", "remaining_time": "6:36:07", "throughput": 656.85, "total_tokens": 39383664} {"current_steps": 28650, "total_steps": 40000, "loss": 0.5872, "lr": 9.293963324799432e-06, "epoch": 0.9170347608987901, "percentage": 71.62, "elapsed_time": "16:39:19", "remaining_time": "6:35:53", "throughput": 656.95, "total_tokens": 39390384} {"current_steps": 28655, "total_steps": 40000, "loss": 0.6653, "lr": 9.286326358070104e-06, "epoch": 0.9171948018692785, "percentage": 71.64, "elapsed_time": "16:39:21", "remaining_time": "6:35:39", "throughput": 657.04, "total_tokens": 39397152} {"current_steps": 28660, "total_steps": 40000, "loss": 0.771, "lr": 9.278691814586729e-06, "epoch": 0.917354842839767, "percentage": 71.65, "elapsed_time": "16:39:23", "remaining_time": "6:35:25", "throughput": 657.14, "total_tokens": 39404048} {"current_steps": 28665, "total_steps": 40000, "loss": 0.5817, "lr": 9.271059695526635e-06, "epoch": 0.9175148838102555, "percentage": 71.66, "elapsed_time": "16:39:24", "remaining_time": "6:35:11", "throughput": 657.23, "total_tokens": 39410512} {"current_steps": 28670, "total_steps": 40000, "loss": 0.638, "lr": 9.263430002066805e-06, "epoch": 0.9176749247807439, "percentage": 71.67, "elapsed_time": "16:39:26", "remaining_time": "6:34:58", "throughput": 657.32, "total_tokens": 39417072} {"current_steps": 28675, "total_steps": 40000, "loss": 0.5483, "lr": 9.25580273538382e-06, "epoch": 0.9178349657512324, "percentage": 71.69, "elapsed_time": "16:39:28", "remaining_time": "6:34:44", "throughput": 657.41, "total_tokens": 39423936} {"current_steps": 28680, "total_steps": 40000, "loss": 0.8976, "lr": 9.248177896653907e-06, "epoch": 0.9179950067217207, "percentage": 71.7, "elapsed_time": "16:39:30", "remaining_time": "6:34:30", "throughput": 657.5, "total_tokens": 39430640} {"current_steps": 28685, "total_steps": 40000, "loss": 0.8071, "lr": 9.240555487052918e-06, "epoch": 0.9181550476922092, "percentage": 71.71, "elapsed_time": "16:39:31", "remaining_time": "6:34:16", "throughput": 657.61, "total_tokens": 39437952} {"current_steps": 28690, "total_steps": 40000, "loss": 0.7341, "lr": 9.232935507756313e-06, "epoch": 0.9183150886626976, "percentage": 71.73, "elapsed_time": "16:39:33", "remaining_time": "6:34:02", "throughput": 657.7, "total_tokens": 39444400} {"current_steps": 28695, "total_steps": 40000, "loss": 0.6089, "lr": 9.225317959939193e-06, "epoch": 0.9184751296331861, "percentage": 71.74, "elapsed_time": "16:39:35", "remaining_time": "6:33:48", "throughput": 657.79, "total_tokens": 39451360} {"current_steps": 28700, "total_steps": 40000, "loss": 0.6182, "lr": 9.217702844776287e-06, "epoch": 0.9186351706036745, "percentage": 71.75, "elapsed_time": "16:39:37", "remaining_time": "6:33:34", "throughput": 657.88, "total_tokens": 39457952} {"current_steps": 28705, "total_steps": 40000, "loss": 0.4966, "lr": 9.210090163441929e-06, "epoch": 0.918795211574163, "percentage": 71.76, "elapsed_time": "16:39:38", "remaining_time": "6:33:20", "throughput": 657.98, "total_tokens": 39464704} {"current_steps": 28710, "total_steps": 40000, "loss": 0.7398, "lr": 9.202479917110105e-06, "epoch": 0.9189552525446514, "percentage": 71.78, "elapsed_time": "16:39:40", "remaining_time": "6:33:06", "throughput": 658.07, "total_tokens": 39471536} {"current_steps": 28715, "total_steps": 40000, "loss": 0.7244, "lr": 9.194872106954392e-06, "epoch": 0.9191152935151399, "percentage": 71.79, "elapsed_time": "16:39:42", "remaining_time": "6:32:53", "throughput": 658.17, "total_tokens": 39478704} {"current_steps": 28720, "total_steps": 40000, "loss": 0.8731, "lr": 9.187266734148029e-06, "epoch": 0.9192753344856284, "percentage": 71.8, "elapsed_time": "16:39:44", "remaining_time": "6:32:39", "throughput": 658.27, "total_tokens": 39485552} {"current_steps": 28725, "total_steps": 40000, "loss": 0.8544, "lr": 9.179663799863849e-06, "epoch": 0.9194353754561168, "percentage": 71.81, "elapsed_time": "16:39:45", "remaining_time": "6:32:25", "throughput": 658.36, "total_tokens": 39492560} {"current_steps": 28730, "total_steps": 40000, "loss": 0.6507, "lr": 9.172063305274317e-06, "epoch": 0.9195954164266052, "percentage": 71.83, "elapsed_time": "16:39:47", "remaining_time": "6:32:11", "throughput": 658.45, "total_tokens": 39499072} {"current_steps": 28735, "total_steps": 40000, "loss": 0.8969, "lr": 9.164465251551527e-06, "epoch": 0.9197554573970936, "percentage": 71.84, "elapsed_time": "16:39:49", "remaining_time": "6:31:57", "throughput": 658.54, "total_tokens": 39505536} {"current_steps": 28740, "total_steps": 40000, "loss": 0.6918, "lr": 9.156869639867205e-06, "epoch": 0.9199154983675821, "percentage": 71.85, "elapsed_time": "16:39:51", "remaining_time": "6:31:43", "throughput": 658.63, "total_tokens": 39512032} {"current_steps": 28745, "total_steps": 40000, "loss": 0.7685, "lr": 9.149276471392677e-06, "epoch": 0.9200755393380705, "percentage": 71.86, "elapsed_time": "16:39:52", "remaining_time": "6:31:29", "throughput": 658.72, "total_tokens": 39518704} {"current_steps": 28750, "total_steps": 40000, "loss": 0.6178, "lr": 9.141685747298914e-06, "epoch": 0.920235580308559, "percentage": 71.88, "elapsed_time": "16:39:54", "remaining_time": "6:31:16", "throughput": 658.82, "total_tokens": 39525584} {"current_steps": 28755, "total_steps": 40000, "loss": 0.6244, "lr": 9.13409746875649e-06, "epoch": 0.9203956212790474, "percentage": 71.89, "elapsed_time": "16:39:56", "remaining_time": "6:31:02", "throughput": 658.91, "total_tokens": 39531840} {"current_steps": 28760, "total_steps": 40000, "loss": 0.7228, "lr": 9.12651163693562e-06, "epoch": 0.9205556622495359, "percentage": 71.9, "elapsed_time": "16:39:57", "remaining_time": "6:30:48", "throughput": 659.0, "total_tokens": 39538800} {"current_steps": 28765, "total_steps": 40000, "loss": 0.9019, "lr": 9.11892825300614e-06, "epoch": 0.9207157032200243, "percentage": 71.91, "elapsed_time": "16:39:59", "remaining_time": "6:30:34", "throughput": 659.09, "total_tokens": 39545440} {"current_steps": 28770, "total_steps": 40000, "loss": 0.5732, "lr": 9.111347318137491e-06, "epoch": 0.9208757441905128, "percentage": 71.92, "elapsed_time": "16:40:01", "remaining_time": "6:30:20", "throughput": 659.19, "total_tokens": 39552272} {"current_steps": 28775, "total_steps": 40000, "loss": 0.6409, "lr": 9.103768833498755e-06, "epoch": 0.9210357851610013, "percentage": 71.94, "elapsed_time": "16:40:03", "remaining_time": "6:30:06", "throughput": 659.29, "total_tokens": 39559328} {"current_steps": 28780, "total_steps": 40000, "loss": 0.7126, "lr": 9.096192800258639e-06, "epoch": 0.9211958261314896, "percentage": 71.95, "elapsed_time": "16:40:04", "remaining_time": "6:29:53", "throughput": 659.39, "total_tokens": 39566688} {"current_steps": 28785, "total_steps": 40000, "loss": 0.6431, "lr": 9.088619219585443e-06, "epoch": 0.9213558671019781, "percentage": 71.96, "elapsed_time": "16:40:06", "remaining_time": "6:29:39", "throughput": 659.49, "total_tokens": 39573536} {"current_steps": 28790, "total_steps": 40000, "loss": 0.7728, "lr": 9.081048092647127e-06, "epoch": 0.9215159080724665, "percentage": 71.97, "elapsed_time": "16:40:08", "remaining_time": "6:29:25", "throughput": 659.59, "total_tokens": 39580784} {"current_steps": 28795, "total_steps": 40000, "loss": 0.9035, "lr": 9.073479420611245e-06, "epoch": 0.921675949042955, "percentage": 71.99, "elapsed_time": "16:40:10", "remaining_time": "6:29:11", "throughput": 659.69, "total_tokens": 39588080} {"current_steps": 28800, "total_steps": 40000, "loss": 0.6496, "lr": 9.065913204644974e-06, "epoch": 0.9218359900134434, "percentage": 72.0, "elapsed_time": "16:40:11", "remaining_time": "6:28:57", "throughput": 659.78, "total_tokens": 39594816} {"current_steps": 28800, "total_steps": 40000, "eval_loss": 0.7324339747428894, "epoch": 0.9218359900134434, "percentage": 72.0, "elapsed_time": "16:46:00", "remaining_time": "6:31:13", "throughput": 655.98, "total_tokens": 39594816} {"current_steps": 28805, "total_steps": 40000, "loss": 0.5935, "lr": 9.058349445915135e-06, "epoch": 0.9219960309839319, "percentage": 72.01, "elapsed_time": "16:46:03", "remaining_time": "6:31:00", "throughput": 656.06, "total_tokens": 39602064} {"current_steps": 28810, "total_steps": 40000, "loss": 0.8698, "lr": 9.050788145588138e-06, "epoch": 0.9221560719544203, "percentage": 72.02, "elapsed_time": "16:46:05", "remaining_time": "6:30:46", "throughput": 656.16, "total_tokens": 39609088} {"current_steps": 28815, "total_steps": 40000, "loss": 0.6416, "lr": 9.043229304830039e-06, "epoch": 0.9223161129249088, "percentage": 72.04, "elapsed_time": "16:46:06", "remaining_time": "6:30:32", "throughput": 656.25, "total_tokens": 39615952} {"current_steps": 28820, "total_steps": 40000, "loss": 0.5688, "lr": 9.035672924806515e-06, "epoch": 0.9224761538953972, "percentage": 72.05, "elapsed_time": "16:46:08", "remaining_time": "6:30:18", "throughput": 656.35, "total_tokens": 39622720} {"current_steps": 28825, "total_steps": 40000, "loss": 0.6485, "lr": 9.028119006682839e-06, "epoch": 0.9226361948658857, "percentage": 72.06, "elapsed_time": "16:46:10", "remaining_time": "6:30:04", "throughput": 656.45, "total_tokens": 39629968} {"current_steps": 28830, "total_steps": 40000, "loss": 0.712, "lr": 9.020567551623935e-06, "epoch": 0.9227962358363742, "percentage": 72.08, "elapsed_time": "16:46:12", "remaining_time": "6:29:50", "throughput": 656.54, "total_tokens": 39636880} {"current_steps": 28835, "total_steps": 40000, "loss": 0.7331, "lr": 9.013018560794318e-06, "epoch": 0.9229562768068625, "percentage": 72.09, "elapsed_time": "16:46:13", "remaining_time": "6:29:36", "throughput": 656.64, "total_tokens": 39643792} {"current_steps": 28840, "total_steps": 40000, "loss": 0.7418, "lr": 9.005472035358139e-06, "epoch": 0.923116317777351, "percentage": 72.1, "elapsed_time": "16:46:15", "remaining_time": "6:29:23", "throughput": 656.74, "total_tokens": 39650896} {"current_steps": 28845, "total_steps": 40000, "loss": 0.6625, "lr": 8.997927976479185e-06, "epoch": 0.9232763587478394, "percentage": 72.11, "elapsed_time": "16:46:17", "remaining_time": "6:29:09", "throughput": 656.83, "total_tokens": 39657568} {"current_steps": 28850, "total_steps": 40000, "loss": 0.7425, "lr": 8.99038638532082e-06, "epoch": 0.9234363997183279, "percentage": 72.12, "elapsed_time": "16:46:19", "remaining_time": "6:28:55", "throughput": 656.92, "total_tokens": 39664352} {"current_steps": 28855, "total_steps": 40000, "loss": 0.5921, "lr": 8.982847263046065e-06, "epoch": 0.9235964406888163, "percentage": 72.14, "elapsed_time": "16:46:20", "remaining_time": "6:28:41", "throughput": 657.02, "total_tokens": 39671248} {"current_steps": 28860, "total_steps": 40000, "loss": 0.783, "lr": 8.975310610817555e-06, "epoch": 0.9237564816593048, "percentage": 72.15, "elapsed_time": "16:46:22", "remaining_time": "6:28:27", "throughput": 657.11, "total_tokens": 39677856} {"current_steps": 28865, "total_steps": 40000, "loss": 0.6978, "lr": 8.967776429797528e-06, "epoch": 0.9239165226297932, "percentage": 72.16, "elapsed_time": "16:46:24", "remaining_time": "6:28:13", "throughput": 657.21, "total_tokens": 39685184} {"current_steps": 28870, "total_steps": 40000, "loss": 0.6528, "lr": 8.960244721147842e-06, "epoch": 0.9240765636002817, "percentage": 72.17, "elapsed_time": "16:46:25", "remaining_time": "6:28:00", "throughput": 657.3, "total_tokens": 39691888} {"current_steps": 28875, "total_steps": 40000, "loss": 0.5468, "lr": 8.952715486029995e-06, "epoch": 0.9242366045707702, "percentage": 72.19, "elapsed_time": "16:46:27", "remaining_time": "6:27:46", "throughput": 657.4, "total_tokens": 39698928} {"current_steps": 28880, "total_steps": 40000, "loss": 0.5374, "lr": 8.945188725605075e-06, "epoch": 0.9243966455412586, "percentage": 72.2, "elapsed_time": "16:46:29", "remaining_time": "6:27:32", "throughput": 657.49, "total_tokens": 39705584} {"current_steps": 28885, "total_steps": 40000, "loss": 0.8318, "lr": 8.937664441033817e-06, "epoch": 0.924556686511747, "percentage": 72.21, "elapsed_time": "16:46:31", "remaining_time": "6:27:18", "throughput": 657.58, "total_tokens": 39712288} {"current_steps": 28890, "total_steps": 40000, "loss": 0.6962, "lr": 8.930142633476549e-06, "epoch": 0.9247167274822354, "percentage": 72.22, "elapsed_time": "16:46:32", "remaining_time": "6:27:04", "throughput": 657.68, "total_tokens": 39719392} {"current_steps": 28895, "total_steps": 40000, "loss": 0.7249, "lr": 8.92262330409323e-06, "epoch": 0.9248767684527239, "percentage": 72.24, "elapsed_time": "16:46:34", "remaining_time": "6:26:51", "throughput": 657.78, "total_tokens": 39726464} {"current_steps": 28900, "total_steps": 40000, "loss": 0.6829, "lr": 8.915106454043448e-06, "epoch": 0.9250368094232123, "percentage": 72.25, "elapsed_time": "16:46:36", "remaining_time": "6:26:37", "throughput": 657.88, "total_tokens": 39733696} {"current_steps": 28905, "total_steps": 40000, "loss": 0.8396, "lr": 8.90759208448638e-06, "epoch": 0.9251968503937008, "percentage": 72.26, "elapsed_time": "16:46:38", "remaining_time": "6:26:23", "throughput": 657.98, "total_tokens": 39740624} {"current_steps": 28910, "total_steps": 40000, "loss": 0.7497, "lr": 8.900080196580848e-06, "epoch": 0.9253568913641892, "percentage": 72.28, "elapsed_time": "16:46:39", "remaining_time": "6:26:09", "throughput": 658.08, "total_tokens": 39747680} {"current_steps": 28915, "total_steps": 40000, "loss": 0.8441, "lr": 8.892570791485267e-06, "epoch": 0.9255169323346777, "percentage": 72.29, "elapsed_time": "16:46:41", "remaining_time": "6:25:55", "throughput": 658.18, "total_tokens": 39754848} {"current_steps": 28920, "total_steps": 40000, "loss": 0.7521, "lr": 8.885063870357688e-06, "epoch": 0.9256769733051661, "percentage": 72.3, "elapsed_time": "16:46:43", "remaining_time": "6:25:42", "throughput": 658.27, "total_tokens": 39761664} {"current_steps": 28925, "total_steps": 40000, "loss": 0.6168, "lr": 8.87755943435578e-06, "epoch": 0.9258370142756546, "percentage": 72.31, "elapsed_time": "16:46:45", "remaining_time": "6:25:28", "throughput": 658.37, "total_tokens": 39768688} {"current_steps": 28930, "total_steps": 40000, "loss": 0.6339, "lr": 8.87005748463681e-06, "epoch": 0.9259970552461431, "percentage": 72.32, "elapsed_time": "16:46:46", "remaining_time": "6:25:14", "throughput": 658.46, "total_tokens": 39775456} {"current_steps": 28935, "total_steps": 40000, "loss": 0.9365, "lr": 8.862558022357681e-06, "epoch": 0.9261570962166314, "percentage": 72.34, "elapsed_time": "16:46:48", "remaining_time": "6:25:00", "throughput": 658.55, "total_tokens": 39782048} {"current_steps": 28940, "total_steps": 40000, "loss": 0.7311, "lr": 8.855061048674903e-06, "epoch": 0.9263171371871199, "percentage": 72.35, "elapsed_time": "16:46:50", "remaining_time": "6:24:47", "throughput": 658.65, "total_tokens": 39789024} {"current_steps": 28945, "total_steps": 40000, "loss": 0.6694, "lr": 8.847566564744595e-06, "epoch": 0.9264771781576083, "percentage": 72.36, "elapsed_time": "16:46:52", "remaining_time": "6:24:33", "throughput": 658.74, "total_tokens": 39795968} {"current_steps": 28950, "total_steps": 40000, "loss": 0.7422, "lr": 8.840074571722512e-06, "epoch": 0.9266372191280968, "percentage": 72.38, "elapsed_time": "16:46:53", "remaining_time": "6:24:19", "throughput": 658.84, "total_tokens": 39802944} {"current_steps": 28955, "total_steps": 40000, "loss": 0.7395, "lr": 8.832585070764002e-06, "epoch": 0.9267972600985852, "percentage": 72.39, "elapsed_time": "16:46:55", "remaining_time": "6:24:05", "throughput": 658.93, "total_tokens": 39809600} {"current_steps": 28960, "total_steps": 40000, "loss": 0.6819, "lr": 8.825098063024045e-06, "epoch": 0.9269573010690737, "percentage": 72.4, "elapsed_time": "16:46:57", "remaining_time": "6:23:51", "throughput": 659.02, "total_tokens": 39816320} {"current_steps": 28965, "total_steps": 40000, "loss": 0.6236, "lr": 8.817613549657244e-06, "epoch": 0.9271173420395621, "percentage": 72.41, "elapsed_time": "16:46:58", "remaining_time": "6:23:38", "throughput": 659.12, "total_tokens": 39823056} {"current_steps": 28970, "total_steps": 40000, "loss": 0.7907, "lr": 8.810131531817783e-06, "epoch": 0.9272773830100506, "percentage": 72.42, "elapsed_time": "16:47:00", "remaining_time": "6:23:24", "throughput": 659.21, "total_tokens": 39830000} {"current_steps": 28975, "total_steps": 40000, "loss": 0.5877, "lr": 8.802652010659496e-06, "epoch": 0.927437423980539, "percentage": 72.44, "elapsed_time": "16:47:02", "remaining_time": "6:23:10", "throughput": 659.3, "total_tokens": 39836560} {"current_steps": 28980, "total_steps": 40000, "loss": 0.6313, "lr": 8.795174987335827e-06, "epoch": 0.9275974649510275, "percentage": 72.45, "elapsed_time": "16:47:04", "remaining_time": "6:22:57", "throughput": 659.39, "total_tokens": 39843344} {"current_steps": 28985, "total_steps": 40000, "loss": 0.8213, "lr": 8.787700462999807e-06, "epoch": 0.927757505921516, "percentage": 72.46, "elapsed_time": "16:47:05", "remaining_time": "6:22:43", "throughput": 659.49, "total_tokens": 39850128} {"current_steps": 28990, "total_steps": 40000, "loss": 0.7785, "lr": 8.780228438804122e-06, "epoch": 0.9279175468920043, "percentage": 72.47, "elapsed_time": "16:47:07", "remaining_time": "6:22:29", "throughput": 659.58, "total_tokens": 39856736} {"current_steps": 28995, "total_steps": 40000, "loss": 0.5785, "lr": 8.772758915901032e-06, "epoch": 0.9280775878624928, "percentage": 72.49, "elapsed_time": "16:47:09", "remaining_time": "6:22:15", "throughput": 659.68, "total_tokens": 39864128} {"current_steps": 29000, "total_steps": 40000, "loss": 0.7856, "lr": 8.765291895442443e-06, "epoch": 0.9282376288329812, "percentage": 72.5, "elapsed_time": "16:47:11", "remaining_time": "6:22:02", "throughput": 659.77, "total_tokens": 39870432} {"current_steps": 29000, "total_steps": 40000, "eval_loss": 0.7325732111930847, "epoch": 0.9282376288329812, "percentage": 72.5, "elapsed_time": "16:52:59", "remaining_time": "6:24:14", "throughput": 655.98, "total_tokens": 39870432} {"current_steps": 29005, "total_steps": 40000, "loss": 0.6489, "lr": 8.75782737857987e-06, "epoch": 0.9283976698034697, "percentage": 72.51, "elapsed_time": "16:53:03", "remaining_time": "6:24:01", "throughput": 656.05, "total_tokens": 39876960} {"current_steps": 29010, "total_steps": 40000, "loss": 0.8007, "lr": 8.750365366464425e-06, "epoch": 0.9285577107739581, "percentage": 72.52, "elapsed_time": "16:53:04", "remaining_time": "6:23:47", "throughput": 656.15, "total_tokens": 39884032} {"current_steps": 29015, "total_steps": 40000, "loss": 0.6746, "lr": 8.742905860246838e-06, "epoch": 0.9287177517444466, "percentage": 72.54, "elapsed_time": "16:53:06", "remaining_time": "6:23:33", "throughput": 656.24, "total_tokens": 39890640} {"current_steps": 29020, "total_steps": 40000, "loss": 0.8017, "lr": 8.735448861077478e-06, "epoch": 0.928877792714935, "percentage": 72.55, "elapsed_time": "16:53:08", "remaining_time": "6:23:19", "throughput": 656.34, "total_tokens": 39897568} {"current_steps": 29025, "total_steps": 40000, "loss": 0.8228, "lr": 8.727994370106288e-06, "epoch": 0.9290378336854235, "percentage": 72.56, "elapsed_time": "16:53:09", "remaining_time": "6:23:06", "throughput": 656.43, "total_tokens": 39904592} {"current_steps": 29030, "total_steps": 40000, "loss": 0.8186, "lr": 8.720542388482861e-06, "epoch": 0.9291978746559119, "percentage": 72.58, "elapsed_time": "16:53:11", "remaining_time": "6:22:52", "throughput": 656.53, "total_tokens": 39911360} {"current_steps": 29035, "total_steps": 40000, "loss": 0.8017, "lr": 8.71309291735637e-06, "epoch": 0.9293579156264004, "percentage": 72.59, "elapsed_time": "16:53:13", "remaining_time": "6:22:38", "throughput": 656.63, "total_tokens": 39918784} {"current_steps": 29040, "total_steps": 40000, "loss": 0.5888, "lr": 8.705645957875621e-06, "epoch": 0.9295179565968889, "percentage": 72.6, "elapsed_time": "16:53:15", "remaining_time": "6:22:24", "throughput": 656.72, "total_tokens": 39925712} {"current_steps": 29045, "total_steps": 40000, "loss": 0.9162, "lr": 8.698201511189048e-06, "epoch": 0.9296779975673772, "percentage": 72.61, "elapsed_time": "16:53:16", "remaining_time": "6:22:10", "throughput": 656.82, "total_tokens": 39932384} {"current_steps": 29050, "total_steps": 40000, "loss": 0.7663, "lr": 8.690759578444649e-06, "epoch": 0.9298380385378657, "percentage": 72.62, "elapsed_time": "16:53:18", "remaining_time": "6:21:57", "throughput": 656.91, "total_tokens": 39939408} {"current_steps": 29055, "total_steps": 40000, "loss": 0.6406, "lr": 8.68332016079008e-06, "epoch": 0.9299980795083541, "percentage": 72.64, "elapsed_time": "16:53:20", "remaining_time": "6:21:43", "throughput": 657.0, "total_tokens": 39946032} {"current_steps": 29060, "total_steps": 40000, "loss": 0.8704, "lr": 8.6758832593726e-06, "epoch": 0.9301581204788426, "percentage": 72.65, "elapsed_time": "16:53:22", "remaining_time": "6:21:29", "throughput": 657.09, "total_tokens": 39952544} {"current_steps": 29065, "total_steps": 40000, "loss": 0.7897, "lr": 8.668448875339053e-06, "epoch": 0.930318161449331, "percentage": 72.66, "elapsed_time": "16:53:23", "remaining_time": "6:21:15", "throughput": 657.18, "total_tokens": 39959296} {"current_steps": 29070, "total_steps": 40000, "loss": 0.7252, "lr": 8.661017009835933e-06, "epoch": 0.9304782024198195, "percentage": 72.67, "elapsed_time": "16:53:25", "remaining_time": "6:21:02", "throughput": 657.27, "total_tokens": 39965968} {"current_steps": 29075, "total_steps": 40000, "loss": 0.7717, "lr": 8.653587664009311e-06, "epoch": 0.9306382433903079, "percentage": 72.69, "elapsed_time": "16:53:27", "remaining_time": "6:20:48", "throughput": 657.37, "total_tokens": 39973200} {"current_steps": 29080, "total_steps": 40000, "loss": 0.7411, "lr": 8.646160839004902e-06, "epoch": 0.9307982843607964, "percentage": 72.7, "elapsed_time": "16:53:29", "remaining_time": "6:20:34", "throughput": 657.47, "total_tokens": 39980112} {"current_steps": 29085, "total_steps": 40000, "loss": 0.6313, "lr": 8.638736535967998e-06, "epoch": 0.9309583253312849, "percentage": 72.71, "elapsed_time": "16:53:30", "remaining_time": "6:20:21", "throughput": 657.56, "total_tokens": 39986880} {"current_steps": 29090, "total_steps": 40000, "loss": 0.4949, "lr": 8.631314756043535e-06, "epoch": 0.9311183663017732, "percentage": 72.72, "elapsed_time": "16:53:32", "remaining_time": "6:20:07", "throughput": 657.65, "total_tokens": 39993376} {"current_steps": 29095, "total_steps": 40000, "loss": 0.6338, "lr": 8.62389550037603e-06, "epoch": 0.9312784072722617, "percentage": 72.74, "elapsed_time": "16:53:34", "remaining_time": "6:19:53", "throughput": 657.75, "total_tokens": 40000544} {"current_steps": 29100, "total_steps": 40000, "loss": 0.7065, "lr": 8.616478770109646e-06, "epoch": 0.9314384482427501, "percentage": 72.75, "elapsed_time": "16:53:36", "remaining_time": "6:19:39", "throughput": 657.84, "total_tokens": 40006912} {"current_steps": 29105, "total_steps": 40000, "loss": 0.9381, "lr": 8.609064566388111e-06, "epoch": 0.9315984892132386, "percentage": 72.76, "elapsed_time": "16:53:37", "remaining_time": "6:19:26", "throughput": 657.92, "total_tokens": 40013456} {"current_steps": 29110, "total_steps": 40000, "loss": 0.7205, "lr": 8.601652890354815e-06, "epoch": 0.931758530183727, "percentage": 72.78, "elapsed_time": "16:53:39", "remaining_time": "6:19:12", "throughput": 658.01, "total_tokens": 40020112} {"current_steps": 29115, "total_steps": 40000, "loss": 0.7392, "lr": 8.594243743152705e-06, "epoch": 0.9319185711542155, "percentage": 72.79, "elapsed_time": "16:53:41", "remaining_time": "6:18:58", "throughput": 658.1, "total_tokens": 40026736} {"current_steps": 29120, "total_steps": 40000, "loss": 0.7391, "lr": 8.58683712592438e-06, "epoch": 0.9320786121247039, "percentage": 72.8, "elapsed_time": "16:53:42", "remaining_time": "6:18:45", "throughput": 658.2, "total_tokens": 40033664} {"current_steps": 29125, "total_steps": 40000, "loss": 0.9905, "lr": 8.579433039812037e-06, "epoch": 0.9322386530951924, "percentage": 72.81, "elapsed_time": "16:53:44", "remaining_time": "6:18:31", "throughput": 658.3, "total_tokens": 40040768} {"current_steps": 29130, "total_steps": 40000, "loss": 0.8132, "lr": 8.572031485957466e-06, "epoch": 0.9323986940656808, "percentage": 72.82, "elapsed_time": "16:53:46", "remaining_time": "6:18:17", "throughput": 658.39, "total_tokens": 40047344} {"current_steps": 29135, "total_steps": 40000, "loss": 0.7653, "lr": 8.564632465502084e-06, "epoch": 0.9325587350361693, "percentage": 72.84, "elapsed_time": "16:53:48", "remaining_time": "6:18:04", "throughput": 658.48, "total_tokens": 40054336} {"current_steps": 29140, "total_steps": 40000, "loss": 0.8961, "lr": 8.557235979586928e-06, "epoch": 0.9327187760066578, "percentage": 72.85, "elapsed_time": "16:53:49", "remaining_time": "6:17:50", "throughput": 658.58, "total_tokens": 40061312} {"current_steps": 29145, "total_steps": 40000, "loss": 1.0366, "lr": 8.549842029352606e-06, "epoch": 0.9328788169771461, "percentage": 72.86, "elapsed_time": "16:53:51", "remaining_time": "6:17:36", "throughput": 658.67, "total_tokens": 40068064} {"current_steps": 29150, "total_steps": 40000, "loss": 0.6778, "lr": 8.542450615939376e-06, "epoch": 0.9330388579476346, "percentage": 72.88, "elapsed_time": "16:53:53", "remaining_time": "6:17:22", "throughput": 658.77, "total_tokens": 40075328} {"current_steps": 29155, "total_steps": 40000, "loss": 0.7497, "lr": 8.535061740487082e-06, "epoch": 0.933198898918123, "percentage": 72.89, "elapsed_time": "16:53:55", "remaining_time": "6:17:09", "throughput": 658.86, "total_tokens": 40082032} {"current_steps": 29160, "total_steps": 40000, "loss": 0.7564, "lr": 8.527675404135168e-06, "epoch": 0.9333589398886115, "percentage": 72.9, "elapsed_time": "16:53:56", "remaining_time": "6:16:55", "throughput": 658.96, "total_tokens": 40088832} {"current_steps": 29165, "total_steps": 40000, "loss": 0.8567, "lr": 8.520291608022724e-06, "epoch": 0.9335189808590999, "percentage": 72.91, "elapsed_time": "16:53:58", "remaining_time": "6:16:41", "throughput": 659.06, "total_tokens": 40096112} {"current_steps": 29170, "total_steps": 40000, "loss": 0.9564, "lr": 8.512910353288398e-06, "epoch": 0.9336790218295884, "percentage": 72.92, "elapsed_time": "16:54:00", "remaining_time": "6:16:28", "throughput": 659.16, "total_tokens": 40103232} {"current_steps": 29175, "total_steps": 40000, "loss": 0.7697, "lr": 8.505531641070486e-06, "epoch": 0.9338390628000768, "percentage": 72.94, "elapsed_time": "16:54:02", "remaining_time": "6:16:14", "throughput": 659.25, "total_tokens": 40110256} {"current_steps": 29180, "total_steps": 40000, "loss": 0.6547, "lr": 8.498155472506885e-06, "epoch": 0.9339991037705653, "percentage": 72.95, "elapsed_time": "16:54:03", "remaining_time": "6:16:01", "throughput": 659.35, "total_tokens": 40117680} {"current_steps": 29185, "total_steps": 40000, "loss": 0.6317, "lr": 8.49078184873508e-06, "epoch": 0.9341591447410537, "percentage": 72.96, "elapsed_time": "16:54:05", "remaining_time": "6:15:47", "throughput": 659.45, "total_tokens": 40124336} {"current_steps": 29190, "total_steps": 40000, "loss": 0.7792, "lr": 8.483410770892188e-06, "epoch": 0.9343191857115422, "percentage": 72.97, "elapsed_time": "16:54:07", "remaining_time": "6:15:33", "throughput": 659.54, "total_tokens": 40131136} {"current_steps": 29195, "total_steps": 40000, "loss": 0.7509, "lr": 8.476042240114909e-06, "epoch": 0.9344792266820307, "percentage": 72.99, "elapsed_time": "16:54:09", "remaining_time": "6:15:20", "throughput": 659.63, "total_tokens": 40138064} {"current_steps": 29200, "total_steps": 40000, "loss": 0.6598, "lr": 8.468676257539568e-06, "epoch": 0.934639267652519, "percentage": 73.0, "elapsed_time": "16:54:10", "remaining_time": "6:15:06", "throughput": 659.72, "total_tokens": 40144672} {"current_steps": 29200, "total_steps": 40000, "eval_loss": 0.7322925925254822, "epoch": 0.934639267652519, "percentage": 73.0, "elapsed_time": "16:59:58", "remaining_time": "6:17:15", "throughput": 655.97, "total_tokens": 40144672} {"current_steps": 29205, "total_steps": 40000, "loss": 0.6413, "lr": 8.4613128243021e-06, "epoch": 0.9347993086230075, "percentage": 73.01, "elapsed_time": "17:00:02", "remaining_time": "6:17:02", "throughput": 656.05, "total_tokens": 40151824} {"current_steps": 29210, "total_steps": 40000, "loss": 0.8204, "lr": 8.453951941538028e-06, "epoch": 0.9349593495934959, "percentage": 73.02, "elapsed_time": "17:00:03", "remaining_time": "6:16:48", "throughput": 656.15, "total_tokens": 40158784} {"current_steps": 29215, "total_steps": 40000, "loss": 0.6771, "lr": 8.446593610382495e-06, "epoch": 0.9351193905639844, "percentage": 73.04, "elapsed_time": "17:00:05", "remaining_time": "6:16:34", "throughput": 656.25, "total_tokens": 40165984} {"current_steps": 29220, "total_steps": 40000, "loss": 0.838, "lr": 8.439237831970259e-06, "epoch": 0.9352794315344728, "percentage": 73.05, "elapsed_time": "17:00:07", "remaining_time": "6:16:20", "throughput": 656.34, "total_tokens": 40173088} {"current_steps": 29225, "total_steps": 40000, "loss": 0.6864, "lr": 8.431884607435667e-06, "epoch": 0.9354394725049613, "percentage": 73.06, "elapsed_time": "17:00:09", "remaining_time": "6:16:07", "throughput": 656.43, "total_tokens": 40179440} {"current_steps": 29230, "total_steps": 40000, "loss": 0.6001, "lr": 8.424533937912665e-06, "epoch": 0.9355995134754497, "percentage": 73.08, "elapsed_time": "17:00:10", "remaining_time": "6:15:53", "throughput": 656.52, "total_tokens": 40186432} {"current_steps": 29235, "total_steps": 40000, "loss": 0.7809, "lr": 8.41718582453484e-06, "epoch": 0.9357595544459382, "percentage": 73.09, "elapsed_time": "17:00:12", "remaining_time": "6:15:39", "throughput": 656.62, "total_tokens": 40193424} {"current_steps": 29240, "total_steps": 40000, "loss": 0.6176, "lr": 8.409840268435346e-06, "epoch": 0.9359195954164266, "percentage": 73.1, "elapsed_time": "17:00:14", "remaining_time": "6:15:26", "throughput": 656.71, "total_tokens": 40200336} {"current_steps": 29245, "total_steps": 40000, "loss": 0.6997, "lr": 8.402497270746976e-06, "epoch": 0.936079636386915, "percentage": 73.11, "elapsed_time": "17:00:16", "remaining_time": "6:15:12", "throughput": 656.81, "total_tokens": 40207472} {"current_steps": 29250, "total_steps": 40000, "loss": 0.739, "lr": 8.395156832602095e-06, "epoch": 0.9362396773574035, "percentage": 73.12, "elapsed_time": "17:00:17", "remaining_time": "6:14:58", "throughput": 656.9, "total_tokens": 40214000} {"current_steps": 29255, "total_steps": 40000, "loss": 0.6869, "lr": 8.387818955132707e-06, "epoch": 0.9363997183278919, "percentage": 73.14, "elapsed_time": "17:00:19", "remaining_time": "6:14:45", "throughput": 656.99, "total_tokens": 40220560} {"current_steps": 29260, "total_steps": 40000, "loss": 0.872, "lr": 8.38048363947039e-06, "epoch": 0.9365597592983804, "percentage": 73.15, "elapsed_time": "17:00:21", "remaining_time": "6:14:31", "throughput": 657.09, "total_tokens": 40227712} {"current_steps": 29265, "total_steps": 40000, "loss": 0.7865, "lr": 8.373150886746351e-06, "epoch": 0.9367198002688688, "percentage": 73.16, "elapsed_time": "17:00:23", "remaining_time": "6:14:17", "throughput": 657.18, "total_tokens": 40234480} {"current_steps": 29270, "total_steps": 40000, "loss": 0.8622, "lr": 8.365820698091397e-06, "epoch": 0.9368798412393573, "percentage": 73.17, "elapsed_time": "17:00:24", "remaining_time": "6:14:04", "throughput": 657.28, "total_tokens": 40241856} {"current_steps": 29275, "total_steps": 40000, "loss": 0.9639, "lr": 8.358493074635922e-06, "epoch": 0.9370398822098457, "percentage": 73.19, "elapsed_time": "17:00:26", "remaining_time": "6:13:50", "throughput": 657.37, "total_tokens": 40248448} {"current_steps": 29280, "total_steps": 40000, "loss": 0.7511, "lr": 8.351168017509948e-06, "epoch": 0.9371999231803342, "percentage": 73.2, "elapsed_time": "17:00:28", "remaining_time": "6:13:36", "throughput": 657.46, "total_tokens": 40255200} {"current_steps": 29285, "total_steps": 40000, "loss": 0.8068, "lr": 8.343845527843094e-06, "epoch": 0.9373599641508226, "percentage": 73.21, "elapsed_time": "17:00:29", "remaining_time": "6:13:23", "throughput": 657.55, "total_tokens": 40261872} {"current_steps": 29290, "total_steps": 40000, "loss": 0.6409, "lr": 8.336525606764566e-06, "epoch": 0.9375200051213111, "percentage": 73.22, "elapsed_time": "17:00:31", "remaining_time": "6:13:09", "throughput": 657.64, "total_tokens": 40268496} {"current_steps": 29295, "total_steps": 40000, "loss": 0.7144, "lr": 8.329208255403204e-06, "epoch": 0.9376800460917994, "percentage": 73.24, "elapsed_time": "17:00:33", "remaining_time": "6:12:55", "throughput": 657.73, "total_tokens": 40275200} {"current_steps": 29300, "total_steps": 40000, "loss": 0.6672, "lr": 8.321893474887426e-06, "epoch": 0.9378400870622879, "percentage": 73.25, "elapsed_time": "17:00:35", "remaining_time": "6:12:42", "throughput": 657.83, "total_tokens": 40282320} {"current_steps": 29305, "total_steps": 40000, "loss": 0.6274, "lr": 8.31458126634526e-06, "epoch": 0.9380001280327764, "percentage": 73.26, "elapsed_time": "17:00:36", "remaining_time": "6:12:28", "throughput": 657.92, "total_tokens": 40289184} {"current_steps": 29310, "total_steps": 40000, "loss": 1.0806, "lr": 8.30727163090435e-06, "epoch": 0.9381601690032648, "percentage": 73.28, "elapsed_time": "17:00:38", "remaining_time": "6:12:15", "throughput": 658.02, "total_tokens": 40296000} {"current_steps": 29315, "total_steps": 40000, "loss": 0.8431, "lr": 8.29996456969192e-06, "epoch": 0.9383202099737533, "percentage": 73.29, "elapsed_time": "17:00:40", "remaining_time": "6:12:01", "throughput": 658.11, "total_tokens": 40302720} {"current_steps": 29320, "total_steps": 40000, "loss": 0.6554, "lr": 8.292660083834818e-06, "epoch": 0.9384802509442417, "percentage": 73.3, "elapsed_time": "17:00:42", "remaining_time": "6:11:47", "throughput": 658.2, "total_tokens": 40309584} {"current_steps": 29325, "total_steps": 40000, "loss": 0.5746, "lr": 8.2853581744595e-06, "epoch": 0.9386402919147302, "percentage": 73.31, "elapsed_time": "17:00:43", "remaining_time": "6:11:34", "throughput": 658.3, "total_tokens": 40316576} {"current_steps": 29330, "total_steps": 40000, "loss": 0.6651, "lr": 8.278058842691991e-06, "epoch": 0.9388003328852186, "percentage": 73.32, "elapsed_time": "17:00:45", "remaining_time": "6:11:20", "throughput": 658.39, "total_tokens": 40323488} {"current_steps": 29335, "total_steps": 40000, "loss": 0.5947, "lr": 8.27076208965796e-06, "epoch": 0.9389603738557071, "percentage": 73.34, "elapsed_time": "17:00:47", "remaining_time": "6:11:07", "throughput": 658.49, "total_tokens": 40330768} {"current_steps": 29340, "total_steps": 40000, "loss": 0.5357, "lr": 8.263467916482637e-06, "epoch": 0.9391204148261955, "percentage": 73.35, "elapsed_time": "17:00:49", "remaining_time": "6:10:53", "throughput": 658.59, "total_tokens": 40337760} {"current_steps": 29345, "total_steps": 40000, "loss": 0.722, "lr": 8.256176324290885e-06, "epoch": 0.939280455796684, "percentage": 73.36, "elapsed_time": "17:00:50", "remaining_time": "6:10:39", "throughput": 658.67, "total_tokens": 40344256} {"current_steps": 29350, "total_steps": 40000, "loss": 0.845, "lr": 8.248887314207168e-06, "epoch": 0.9394404967671725, "percentage": 73.38, "elapsed_time": "17:00:52", "remaining_time": "6:10:26", "throughput": 658.79, "total_tokens": 40352416} {"current_steps": 29355, "total_steps": 40000, "loss": 0.9356, "lr": 8.24160088735553e-06, "epoch": 0.9396005377376608, "percentage": 73.39, "elapsed_time": "17:00:54", "remaining_time": "6:10:12", "throughput": 658.88, "total_tokens": 40359472} {"current_steps": 29360, "total_steps": 40000, "loss": 0.5315, "lr": 8.234317044859629e-06, "epoch": 0.9397605787081493, "percentage": 73.4, "elapsed_time": "17:00:56", "remaining_time": "6:09:59", "throughput": 658.99, "total_tokens": 40366864} {"current_steps": 29365, "total_steps": 40000, "loss": 0.6669, "lr": 8.227035787842744e-06, "epoch": 0.9399206196786377, "percentage": 73.41, "elapsed_time": "17:00:57", "remaining_time": "6:09:45", "throughput": 659.08, "total_tokens": 40373520} {"current_steps": 29370, "total_steps": 40000, "loss": 0.7287, "lr": 8.219757117427721e-06, "epoch": 0.9400806606491262, "percentage": 73.42, "elapsed_time": "17:00:59", "remaining_time": "6:09:31", "throughput": 659.17, "total_tokens": 40380752} {"current_steps": 29375, "total_steps": 40000, "loss": 0.8414, "lr": 8.212481034737014e-06, "epoch": 0.9402407016196146, "percentage": 73.44, "elapsed_time": "17:01:01", "remaining_time": "6:09:18", "throughput": 659.27, "total_tokens": 40387712} {"current_steps": 29380, "total_steps": 40000, "loss": 0.6627, "lr": 8.205207540892707e-06, "epoch": 0.9404007425901031, "percentage": 73.45, "elapsed_time": "17:01:03", "remaining_time": "6:09:04", "throughput": 659.36, "total_tokens": 40394320} {"current_steps": 29385, "total_steps": 40000, "loss": 0.8556, "lr": 8.197936637016442e-06, "epoch": 0.9405607835605915, "percentage": 73.46, "elapsed_time": "17:01:05", "remaining_time": "6:08:51", "throughput": 659.45, "total_tokens": 40400912} {"current_steps": 29390, "total_steps": 40000, "loss": 0.9804, "lr": 8.190668324229508e-06, "epoch": 0.94072082453108, "percentage": 73.47, "elapsed_time": "17:01:06", "remaining_time": "6:08:37", "throughput": 659.53, "total_tokens": 40407424} {"current_steps": 29395, "total_steps": 40000, "loss": 0.6962, "lr": 8.183402603652749e-06, "epoch": 0.9408808655015684, "percentage": 73.49, "elapsed_time": "17:01:08", "remaining_time": "6:08:24", "throughput": 659.63, "total_tokens": 40414240} {"current_steps": 29400, "total_steps": 40000, "loss": 0.7067, "lr": 8.176139476406635e-06, "epoch": 0.9410409064720568, "percentage": 73.5, "elapsed_time": "17:01:10", "remaining_time": "6:08:10", "throughput": 659.71, "total_tokens": 40420752} {"current_steps": 29400, "total_steps": 40000, "eval_loss": 0.7323299050331116, "epoch": 0.9410409064720568, "percentage": 73.5, "elapsed_time": "17:06:57", "remaining_time": "6:10:15", "throughput": 655.99, "total_tokens": 40420752} {"current_steps": 29405, "total_steps": 40000, "loss": 0.5761, "lr": 8.16887894361125e-06, "epoch": 0.9412009474425453, "percentage": 73.51, "elapsed_time": "17:07:02", "remaining_time": "6:10:03", "throughput": 656.06, "total_tokens": 40427792} {"current_steps": 29410, "total_steps": 40000, "loss": 0.7115, "lr": 8.161621006386233e-06, "epoch": 0.9413609884130337, "percentage": 73.52, "elapsed_time": "17:07:03", "remaining_time": "6:09:49", "throughput": 656.16, "total_tokens": 40435024} {"current_steps": 29415, "total_steps": 40000, "loss": 0.7286, "lr": 8.154365665850869e-06, "epoch": 0.9415210293835222, "percentage": 73.54, "elapsed_time": "17:07:05", "remaining_time": "6:09:35", "throughput": 656.25, "total_tokens": 40441856} {"current_steps": 29420, "total_steps": 40000, "loss": 0.5984, "lr": 8.147112923124005e-06, "epoch": 0.9416810703540106, "percentage": 73.55, "elapsed_time": "17:07:07", "remaining_time": "6:09:22", "throughput": 656.34, "total_tokens": 40448672} {"current_steps": 29425, "total_steps": 40000, "loss": 0.7618, "lr": 8.13986277932412e-06, "epoch": 0.9418411113244991, "percentage": 73.56, "elapsed_time": "17:07:09", "remaining_time": "6:09:08", "throughput": 656.43, "total_tokens": 40455360} {"current_steps": 29430, "total_steps": 40000, "loss": 0.8065, "lr": 8.132615235569277e-06, "epoch": 0.9420011522949875, "percentage": 73.58, "elapsed_time": "17:07:10", "remaining_time": "6:08:55", "throughput": 656.52, "total_tokens": 40462144} {"current_steps": 29435, "total_steps": 40000, "loss": 0.6108, "lr": 8.125370292977124e-06, "epoch": 0.942161193265476, "percentage": 73.59, "elapsed_time": "17:07:12", "remaining_time": "6:08:41", "throughput": 656.62, "total_tokens": 40469168} {"current_steps": 29440, "total_steps": 40000, "loss": 0.6952, "lr": 8.118127952664944e-06, "epoch": 0.9423212342359644, "percentage": 73.6, "elapsed_time": "17:07:14", "remaining_time": "6:08:27", "throughput": 656.71, "total_tokens": 40475856} {"current_steps": 29445, "total_steps": 40000, "loss": 0.8423, "lr": 8.110888215749574e-06, "epoch": 0.9424812752064529, "percentage": 73.61, "elapsed_time": "17:07:16", "remaining_time": "6:08:14", "throughput": 656.8, "total_tokens": 40482688} {"current_steps": 29450, "total_steps": 40000, "loss": 0.6867, "lr": 8.10365108334749e-06, "epoch": 0.9426413161769412, "percentage": 73.62, "elapsed_time": "17:07:17", "remaining_time": "6:08:00", "throughput": 656.9, "total_tokens": 40489568} {"current_steps": 29455, "total_steps": 40000, "loss": 0.6462, "lr": 8.096416556574743e-06, "epoch": 0.9428013571474297, "percentage": 73.64, "elapsed_time": "17:07:19", "remaining_time": "6:07:47", "throughput": 656.99, "total_tokens": 40496624} {"current_steps": 29460, "total_steps": 40000, "loss": 0.5537, "lr": 8.08918463654698e-06, "epoch": 0.9429613981179182, "percentage": 73.65, "elapsed_time": "17:07:21", "remaining_time": "6:07:33", "throughput": 657.08, "total_tokens": 40503328} {"current_steps": 29465, "total_steps": 40000, "loss": 0.6999, "lr": 8.081955324379458e-06, "epoch": 0.9431214390884066, "percentage": 73.66, "elapsed_time": "17:07:22", "remaining_time": "6:07:19", "throughput": 657.18, "total_tokens": 40510208} {"current_steps": 29470, "total_steps": 40000, "loss": 0.604, "lr": 8.074728621187039e-06, "epoch": 0.9432814800588951, "percentage": 73.67, "elapsed_time": "17:07:24", "remaining_time": "6:07:06", "throughput": 657.27, "total_tokens": 40517152} {"current_steps": 29475, "total_steps": 40000, "loss": 0.8974, "lr": 8.067504528084158e-06, "epoch": 0.9434415210293835, "percentage": 73.69, "elapsed_time": "17:07:26", "remaining_time": "6:06:52", "throughput": 657.36, "total_tokens": 40524112} {"current_steps": 29480, "total_steps": 40000, "loss": 0.8127, "lr": 8.060283046184861e-06, "epoch": 0.943601561999872, "percentage": 73.7, "elapsed_time": "17:07:28", "remaining_time": "6:06:39", "throughput": 657.46, "total_tokens": 40531440} {"current_steps": 29485, "total_steps": 40000, "loss": 0.5711, "lr": 8.053064176602806e-06, "epoch": 0.9437616029703604, "percentage": 73.71, "elapsed_time": "17:07:29", "remaining_time": "6:06:25", "throughput": 657.56, "total_tokens": 40538368} {"current_steps": 29490, "total_steps": 40000, "loss": 0.7195, "lr": 8.045847920451216e-06, "epoch": 0.9439216439408489, "percentage": 73.72, "elapsed_time": "17:07:31", "remaining_time": "6:06:12", "throughput": 657.65, "total_tokens": 40545408} {"current_steps": 29495, "total_steps": 40000, "loss": 0.8035, "lr": 8.038634278842944e-06, "epoch": 0.9440816849113373, "percentage": 73.74, "elapsed_time": "17:07:33", "remaining_time": "6:05:58", "throughput": 657.75, "total_tokens": 40552528} {"current_steps": 29500, "total_steps": 40000, "loss": 0.6468, "lr": 8.031423252890408e-06, "epoch": 0.9442417258818258, "percentage": 73.75, "elapsed_time": "17:07:35", "remaining_time": "6:05:45", "throughput": 657.85, "total_tokens": 40559824} {"current_steps": 29505, "total_steps": 40000, "loss": 0.8881, "lr": 8.024214843705646e-06, "epoch": 0.9444017668523141, "percentage": 73.76, "elapsed_time": "17:07:36", "remaining_time": "6:05:31", "throughput": 657.94, "total_tokens": 40566368} {"current_steps": 29510, "total_steps": 40000, "loss": 0.7897, "lr": 8.017009052400295e-06, "epoch": 0.9445618078228026, "percentage": 73.78, "elapsed_time": "17:07:38", "remaining_time": "6:05:17", "throughput": 658.04, "total_tokens": 40573536} {"current_steps": 29515, "total_steps": 40000, "loss": 0.6895, "lr": 8.00980588008557e-06, "epoch": 0.9447218487932911, "percentage": 73.79, "elapsed_time": "17:07:40", "remaining_time": "6:05:04", "throughput": 658.12, "total_tokens": 40580064} {"current_steps": 29520, "total_steps": 40000, "loss": 0.8923, "lr": 8.002605327872282e-06, "epoch": 0.9448818897637795, "percentage": 73.8, "elapsed_time": "17:07:42", "remaining_time": "6:04:50", "throughput": 658.22, "total_tokens": 40586928} {"current_steps": 29525, "total_steps": 40000, "loss": 0.624, "lr": 7.995407396870862e-06, "epoch": 0.945041930734268, "percentage": 73.81, "elapsed_time": "17:07:43", "remaining_time": "6:04:37", "throughput": 658.31, "total_tokens": 40593760} {"current_steps": 29530, "total_steps": 40000, "loss": 0.5938, "lr": 7.988212088191307e-06, "epoch": 0.9452019717047564, "percentage": 73.83, "elapsed_time": "17:07:45", "remaining_time": "6:04:23", "throughput": 658.41, "total_tokens": 40601264} {"current_steps": 29535, "total_steps": 40000, "loss": 0.6184, "lr": 7.98101940294324e-06, "epoch": 0.9453620126752449, "percentage": 73.84, "elapsed_time": "17:07:47", "remaining_time": "6:04:10", "throughput": 658.5, "total_tokens": 40608000} {"current_steps": 29540, "total_steps": 40000, "loss": 0.6698, "lr": 7.973829342235847e-06, "epoch": 0.9455220536457333, "percentage": 73.85, "elapsed_time": "17:07:49", "remaining_time": "6:03:56", "throughput": 658.59, "total_tokens": 40614608} {"current_steps": 29545, "total_steps": 40000, "loss": 0.6921, "lr": 7.966641907177936e-06, "epoch": 0.9456820946162218, "percentage": 73.86, "elapsed_time": "17:07:50", "remaining_time": "6:03:43", "throughput": 658.68, "total_tokens": 40621152} {"current_steps": 29550, "total_steps": 40000, "loss": 0.888, "lr": 7.959457098877901e-06, "epoch": 0.9458421355867102, "percentage": 73.88, "elapsed_time": "17:07:52", "remaining_time": "6:03:29", "throughput": 658.77, "total_tokens": 40628160} {"current_steps": 29555, "total_steps": 40000, "loss": 0.742, "lr": 7.952274918443719e-06, "epoch": 0.9460021765571986, "percentage": 73.89, "elapsed_time": "17:07:54", "remaining_time": "6:03:16", "throughput": 658.87, "total_tokens": 40635152} {"current_steps": 29560, "total_steps": 40000, "loss": 0.656, "lr": 7.945095366982983e-06, "epoch": 0.946162217527687, "percentage": 73.9, "elapsed_time": "17:07:55", "remaining_time": "6:03:02", "throughput": 658.97, "total_tokens": 40642608} {"current_steps": 29565, "total_steps": 40000, "loss": 0.8215, "lr": 7.937918445602871e-06, "epoch": 0.9463222584981755, "percentage": 73.91, "elapsed_time": "17:07:57", "remaining_time": "6:02:49", "throughput": 659.06, "total_tokens": 40649456} {"current_steps": 29570, "total_steps": 40000, "loss": 0.7456, "lr": 7.930744155410145e-06, "epoch": 0.946482299468664, "percentage": 73.92, "elapsed_time": "17:07:59", "remaining_time": "6:02:35", "throughput": 659.16, "total_tokens": 40656352} {"current_steps": 29575, "total_steps": 40000, "loss": 0.8914, "lr": 7.923572497511181e-06, "epoch": 0.9466423404391524, "percentage": 73.94, "elapsed_time": "17:08:01", "remaining_time": "6:02:22", "throughput": 659.25, "total_tokens": 40663200} {"current_steps": 29580, "total_steps": 40000, "loss": 0.6053, "lr": 7.916403473011927e-06, "epoch": 0.9468023814096409, "percentage": 73.95, "elapsed_time": "17:08:02", "remaining_time": "6:02:08", "throughput": 659.34, "total_tokens": 40669808} {"current_steps": 29585, "total_steps": 40000, "loss": 0.495, "lr": 7.909237083017953e-06, "epoch": 0.9469624223801293, "percentage": 73.96, "elapsed_time": "17:08:04", "remaining_time": "6:01:55", "throughput": 659.42, "total_tokens": 40676368} {"current_steps": 29590, "total_steps": 40000, "loss": 0.8882, "lr": 7.902073328634389e-06, "epoch": 0.9471224633506178, "percentage": 73.98, "elapsed_time": "17:08:06", "remaining_time": "6:01:41", "throughput": 659.52, "total_tokens": 40683264} {"current_steps": 29595, "total_steps": 40000, "loss": 0.8151, "lr": 7.894912210965987e-06, "epoch": 0.9472825043211062, "percentage": 73.99, "elapsed_time": "17:08:08", "remaining_time": "6:01:28", "throughput": 659.61, "total_tokens": 40689984} {"current_steps": 29600, "total_steps": 40000, "loss": 0.7768, "lr": 7.887753731117075e-06, "epoch": 0.9474425452915947, "percentage": 74.0, "elapsed_time": "17:08:09", "remaining_time": "6:01:14", "throughput": 659.7, "total_tokens": 40696672} {"current_steps": 29600, "total_steps": 40000, "eval_loss": 0.7317754030227661, "epoch": 0.9474425452915947, "percentage": 74.0, "elapsed_time": "17:13:57", "remaining_time": "6:03:17", "throughput": 656.0, "total_tokens": 40696672} {"current_steps": 29605, "total_steps": 40000, "loss": 0.6751, "lr": 7.880597890191587e-06, "epoch": 0.947602586262083, "percentage": 74.01, "elapsed_time": "17:14:00", "remaining_time": "6:03:04", "throughput": 656.07, "total_tokens": 40703120} {"current_steps": 29610, "total_steps": 40000, "loss": 0.763, "lr": 7.873444689293036e-06, "epoch": 0.9477626272325715, "percentage": 74.02, "elapsed_time": "17:14:02", "remaining_time": "6:02:50", "throughput": 656.16, "total_tokens": 40709936} {"current_steps": 29615, "total_steps": 40000, "loss": 0.9482, "lr": 7.866294129524548e-06, "epoch": 0.94792266820306, "percentage": 74.04, "elapsed_time": "17:14:04", "remaining_time": "6:02:36", "throughput": 656.26, "total_tokens": 40717296} {"current_steps": 29620, "total_steps": 40000, "loss": 0.7439, "lr": 7.859146211988811e-06, "epoch": 0.9480827091735484, "percentage": 74.05, "elapsed_time": "17:14:06", "remaining_time": "6:02:23", "throughput": 656.35, "total_tokens": 40724032} {"current_steps": 29625, "total_steps": 40000, "loss": 0.5821, "lr": 7.852000937788134e-06, "epoch": 0.9482427501440369, "percentage": 74.06, "elapsed_time": "17:14:07", "remaining_time": "6:02:09", "throughput": 656.44, "total_tokens": 40730768} {"current_steps": 29630, "total_steps": 40000, "loss": 0.7998, "lr": 7.844858308024416e-06, "epoch": 0.9484027911145253, "percentage": 74.08, "elapsed_time": "17:14:09", "remaining_time": "6:01:56", "throughput": 656.53, "total_tokens": 40737744} {"current_steps": 29635, "total_steps": 40000, "loss": 0.8566, "lr": 7.837718323799122e-06, "epoch": 0.9485628320850138, "percentage": 74.09, "elapsed_time": "17:14:11", "remaining_time": "6:01:42", "throughput": 656.62, "total_tokens": 40744400} {"current_steps": 29640, "total_steps": 40000, "loss": 0.6453, "lr": 7.83058098621334e-06, "epoch": 0.9487228730555022, "percentage": 74.1, "elapsed_time": "17:14:13", "remaining_time": "6:01:29", "throughput": 656.71, "total_tokens": 40751024} {"current_steps": 29645, "total_steps": 40000, "loss": 0.8202, "lr": 7.823446296367739e-06, "epoch": 0.9488829140259907, "percentage": 74.11, "elapsed_time": "17:14:14", "remaining_time": "6:01:15", "throughput": 656.8, "total_tokens": 40757808} {"current_steps": 29650, "total_steps": 40000, "loss": 0.8408, "lr": 7.81631425536257e-06, "epoch": 0.9490429549964791, "percentage": 74.12, "elapsed_time": "17:14:16", "remaining_time": "6:01:02", "throughput": 656.89, "total_tokens": 40764672} {"current_steps": 29655, "total_steps": 40000, "loss": 0.7803, "lr": 7.809184864297689e-06, "epoch": 0.9492029959669676, "percentage": 74.14, "elapsed_time": "17:14:18", "remaining_time": "6:00:48", "throughput": 656.98, "total_tokens": 40771264} {"current_steps": 29660, "total_steps": 40000, "loss": 1.0581, "lr": 7.802058124272532e-06, "epoch": 0.9493630369374559, "percentage": 74.15, "elapsed_time": "17:14:20", "remaining_time": "6:00:35", "throughput": 657.08, "total_tokens": 40778256} {"current_steps": 29665, "total_steps": 40000, "loss": 0.6517, "lr": 7.79493403638614e-06, "epoch": 0.9495230779079444, "percentage": 74.16, "elapsed_time": "17:14:21", "remaining_time": "6:00:21", "throughput": 657.17, "total_tokens": 40784912} {"current_steps": 29670, "total_steps": 40000, "loss": 0.5445, "lr": 7.787812601737132e-06, "epoch": 0.9496831188784329, "percentage": 74.17, "elapsed_time": "17:14:23", "remaining_time": "6:00:08", "throughput": 657.26, "total_tokens": 40791952} {"current_steps": 29675, "total_steps": 40000, "loss": 0.7328, "lr": 7.780693821423715e-06, "epoch": 0.9498431598489213, "percentage": 74.19, "elapsed_time": "17:14:25", "remaining_time": "5:59:54", "throughput": 657.36, "total_tokens": 40798944} {"current_steps": 29680, "total_steps": 40000, "loss": 0.6894, "lr": 7.773577696543705e-06, "epoch": 0.9500032008194098, "percentage": 74.2, "elapsed_time": "17:14:27", "remaining_time": "5:59:41", "throughput": 657.45, "total_tokens": 40806048} {"current_steps": 29685, "total_steps": 40000, "loss": 1.0732, "lr": 7.7664642281945e-06, "epoch": 0.9501632417898982, "percentage": 74.21, "elapsed_time": "17:14:28", "remaining_time": "5:59:27", "throughput": 657.55, "total_tokens": 40813040} {"current_steps": 29690, "total_steps": 40000, "loss": 0.5687, "lr": 7.759353417473072e-06, "epoch": 0.9503232827603867, "percentage": 74.22, "elapsed_time": "17:14:30", "remaining_time": "5:59:14", "throughput": 657.64, "total_tokens": 40819792} {"current_steps": 29695, "total_steps": 40000, "loss": 0.6514, "lr": 7.752245265476016e-06, "epoch": 0.9504833237308751, "percentage": 74.24, "elapsed_time": "17:14:32", "remaining_time": "5:59:00", "throughput": 657.72, "total_tokens": 40826336} {"current_steps": 29700, "total_steps": 40000, "loss": 0.8298, "lr": 7.745139773299481e-06, "epoch": 0.9506433647013636, "percentage": 74.25, "elapsed_time": "17:14:33", "remaining_time": "5:58:47", "throughput": 657.82, "total_tokens": 40833264} {"current_steps": 29705, "total_steps": 40000, "loss": 0.6858, "lr": 7.738036942039232e-06, "epoch": 0.950803405671852, "percentage": 74.26, "elapsed_time": "17:14:35", "remaining_time": "5:58:33", "throughput": 657.91, "total_tokens": 40840000} {"current_steps": 29710, "total_steps": 40000, "loss": 0.6638, "lr": 7.73093677279062e-06, "epoch": 0.9509634466423404, "percentage": 74.28, "elapsed_time": "17:14:37", "remaining_time": "5:58:20", "throughput": 658.0, "total_tokens": 40846864} {"current_steps": 29715, "total_steps": 40000, "loss": 0.7856, "lr": 7.72383926664857e-06, "epoch": 0.9511234876128288, "percentage": 74.29, "elapsed_time": "17:14:39", "remaining_time": "5:58:06", "throughput": 658.09, "total_tokens": 40853504} {"current_steps": 29720, "total_steps": 40000, "loss": 0.5779, "lr": 7.716744424707606e-06, "epoch": 0.9512835285833173, "percentage": 74.3, "elapsed_time": "17:14:40", "remaining_time": "5:57:53", "throughput": 658.18, "total_tokens": 40860608} {"current_steps": 29725, "total_steps": 40000, "loss": 0.7577, "lr": 7.709652248061858e-06, "epoch": 0.9514435695538058, "percentage": 74.31, "elapsed_time": "17:14:42", "remaining_time": "5:57:40", "throughput": 658.27, "total_tokens": 40867328} {"current_steps": 29730, "total_steps": 40000, "loss": 0.7367, "lr": 7.702562737805017e-06, "epoch": 0.9516036105242942, "percentage": 74.33, "elapsed_time": "17:14:44", "remaining_time": "5:57:26", "throughput": 658.36, "total_tokens": 40874064} {"current_steps": 29735, "total_steps": 40000, "loss": 0.6629, "lr": 7.695475895030365e-06, "epoch": 0.9517636514947827, "percentage": 74.34, "elapsed_time": "17:14:46", "remaining_time": "5:57:13", "throughput": 658.45, "total_tokens": 40880784} {"current_steps": 29740, "total_steps": 40000, "loss": 0.7454, "lr": 7.6883917208308e-06, "epoch": 0.9519236924652711, "percentage": 74.35, "elapsed_time": "17:14:47", "remaining_time": "5:56:59", "throughput": 658.55, "total_tokens": 40887744} {"current_steps": 29745, "total_steps": 40000, "loss": 0.6112, "lr": 7.681310216298778e-06, "epoch": 0.9520837334357596, "percentage": 74.36, "elapsed_time": "17:14:49", "remaining_time": "5:56:46", "throughput": 658.64, "total_tokens": 40894464} {"current_steps": 29750, "total_steps": 40000, "loss": 0.5951, "lr": 7.674231382526367e-06, "epoch": 0.952243774406248, "percentage": 74.38, "elapsed_time": "17:14:51", "remaining_time": "5:56:32", "throughput": 658.72, "total_tokens": 40900976} {"current_steps": 29755, "total_steps": 40000, "loss": 0.6053, "lr": 7.667155220605198e-06, "epoch": 0.9524038153767365, "percentage": 74.39, "elapsed_time": "17:14:53", "remaining_time": "5:56:19", "throughput": 658.81, "total_tokens": 40907824} {"current_steps": 29760, "total_steps": 40000, "loss": 0.799, "lr": 7.660081731626515e-06, "epoch": 0.9525638563472248, "percentage": 74.4, "elapsed_time": "17:14:54", "remaining_time": "5:56:05", "throughput": 658.9, "total_tokens": 40914400} {"current_steps": 29765, "total_steps": 40000, "loss": 0.5895, "lr": 7.653010916681141e-06, "epoch": 0.9527238973177133, "percentage": 74.41, "elapsed_time": "17:14:56", "remaining_time": "5:55:52", "throughput": 658.99, "total_tokens": 40920976} {"current_steps": 29770, "total_steps": 40000, "loss": 0.73, "lr": 7.645942776859472e-06, "epoch": 0.9528839382882017, "percentage": 74.42, "elapsed_time": "17:14:58", "remaining_time": "5:55:39", "throughput": 659.08, "total_tokens": 40927952} {"current_steps": 29775, "total_steps": 40000, "loss": 0.5857, "lr": 7.63887731325152e-06, "epoch": 0.9530439792586902, "percentage": 74.44, "elapsed_time": "17:15:00", "remaining_time": "5:55:25", "throughput": 659.18, "total_tokens": 40935168} {"current_steps": 29780, "total_steps": 40000, "loss": 0.7164, "lr": 7.63181452694685e-06, "epoch": 0.9532040202291787, "percentage": 74.45, "elapsed_time": "17:15:01", "remaining_time": "5:55:12", "throughput": 659.27, "total_tokens": 40941840} {"current_steps": 29785, "total_steps": 40000, "loss": 0.586, "lr": 7.624754419034644e-06, "epoch": 0.9533640611996671, "percentage": 74.46, "elapsed_time": "17:15:03", "remaining_time": "5:54:58", "throughput": 659.37, "total_tokens": 40949136} {"current_steps": 29790, "total_steps": 40000, "loss": 0.6703, "lr": 7.6176969906036645e-06, "epoch": 0.9535241021701556, "percentage": 74.48, "elapsed_time": "17:15:05", "remaining_time": "5:54:45", "throughput": 659.47, "total_tokens": 40956400} {"current_steps": 29795, "total_steps": 40000, "loss": 0.6556, "lr": 7.610642242742242e-06, "epoch": 0.953684143140644, "percentage": 74.49, "elapsed_time": "17:15:06", "remaining_time": "5:54:32", "throughput": 659.56, "total_tokens": 40963344} {"current_steps": 29800, "total_steps": 40000, "loss": 0.4495, "lr": 7.603590176538322e-06, "epoch": 0.9538441841111325, "percentage": 74.5, "elapsed_time": "17:15:08", "remaining_time": "5:54:18", "throughput": 659.65, "total_tokens": 40970096} {"current_steps": 29800, "total_steps": 40000, "eval_loss": 0.7317322492599487, "epoch": 0.9538441841111325, "percentage": 74.5, "elapsed_time": "17:20:56", "remaining_time": "5:56:17", "throughput": 655.98, "total_tokens": 40970096} {"current_steps": 29805, "total_steps": 40000, "loss": 0.6928, "lr": 7.596540793079404e-06, "epoch": 0.9540042250816209, "percentage": 74.51, "elapsed_time": "17:20:59", "remaining_time": "5:56:04", "throughput": 656.06, "total_tokens": 40977296} {"current_steps": 29810, "total_steps": 40000, "loss": 0.7264, "lr": 7.5894940934526125e-06, "epoch": 0.9541642660521094, "percentage": 74.52, "elapsed_time": "17:21:01", "remaining_time": "5:55:51", "throughput": 656.15, "total_tokens": 40984320} {"current_steps": 29815, "total_steps": 40000, "loss": 0.597, "lr": 7.582450078744621e-06, "epoch": 0.9543243070225977, "percentage": 74.54, "elapsed_time": "17:21:03", "remaining_time": "5:55:37", "throughput": 656.24, "total_tokens": 40991040} {"current_steps": 29820, "total_steps": 40000, "loss": 1.0725, "lr": 7.575408750041707e-06, "epoch": 0.9544843479930862, "percentage": 74.55, "elapsed_time": "17:21:04", "remaining_time": "5:55:24", "throughput": 656.33, "total_tokens": 40997776} {"current_steps": 29825, "total_steps": 40000, "loss": 0.7626, "lr": 7.568370108429732e-06, "epoch": 0.9546443889635747, "percentage": 74.56, "elapsed_time": "17:21:06", "remaining_time": "5:55:10", "throughput": 656.42, "total_tokens": 41004384} {"current_steps": 29830, "total_steps": 40000, "loss": 0.8325, "lr": 7.561334154994154e-06, "epoch": 0.9548044299340631, "percentage": 74.58, "elapsed_time": "17:21:08", "remaining_time": "5:54:57", "throughput": 656.51, "total_tokens": 41011072} {"current_steps": 29835, "total_steps": 40000, "loss": 0.6374, "lr": 7.55430089081999e-06, "epoch": 0.9549644709045516, "percentage": 74.59, "elapsed_time": "17:21:10", "remaining_time": "5:54:44", "throughput": 656.6, "total_tokens": 41018032} {"current_steps": 29840, "total_steps": 40000, "loss": 0.644, "lr": 7.547270316991864e-06, "epoch": 0.95512451187504, "percentage": 74.6, "elapsed_time": "17:21:11", "remaining_time": "5:54:30", "throughput": 656.7, "total_tokens": 41025056} {"current_steps": 29845, "total_steps": 40000, "loss": 0.7846, "lr": 7.5402424345939884e-06, "epoch": 0.9552845528455285, "percentage": 74.61, "elapsed_time": "17:21:13", "remaining_time": "5:54:17", "throughput": 656.79, "total_tokens": 41031760} {"current_steps": 29850, "total_steps": 40000, "loss": 0.5889, "lr": 7.533217244710133e-06, "epoch": 0.9554445938160169, "percentage": 74.62, "elapsed_time": "17:21:15", "remaining_time": "5:54:03", "throughput": 656.87, "total_tokens": 41038400} {"current_steps": 29855, "total_steps": 40000, "loss": 0.8204, "lr": 7.52619474842369e-06, "epoch": 0.9556046347865054, "percentage": 74.64, "elapsed_time": "17:21:17", "remaining_time": "5:53:50", "throughput": 656.96, "total_tokens": 41045152} {"current_steps": 29860, "total_steps": 40000, "loss": 0.8796, "lr": 7.519174946817597e-06, "epoch": 0.9557646757569938, "percentage": 74.65, "elapsed_time": "17:21:18", "remaining_time": "5:53:36", "throughput": 657.06, "total_tokens": 41052208} {"current_steps": 29865, "total_steps": 40000, "loss": 0.6026, "lr": 7.512157840974407e-06, "epoch": 0.9559247167274822, "percentage": 74.66, "elapsed_time": "17:21:20", "remaining_time": "5:53:23", "throughput": 657.15, "total_tokens": 41058816} {"current_steps": 29870, "total_steps": 40000, "loss": 0.8124, "lr": 7.5051434319762496e-06, "epoch": 0.9560847576979706, "percentage": 74.67, "elapsed_time": "17:21:22", "remaining_time": "5:53:10", "throughput": 657.24, "total_tokens": 41065600} {"current_steps": 29875, "total_steps": 40000, "loss": 0.591, "lr": 7.498131720904822e-06, "epoch": 0.9562447986684591, "percentage": 74.69, "elapsed_time": "17:21:24", "remaining_time": "5:52:56", "throughput": 657.32, "total_tokens": 41072272} {"current_steps": 29880, "total_steps": 40000, "loss": 0.6437, "lr": 7.491122708841433e-06, "epoch": 0.9564048396389476, "percentage": 74.7, "elapsed_time": "17:21:25", "remaining_time": "5:52:43", "throughput": 657.43, "total_tokens": 41079728} {"current_steps": 29885, "total_steps": 40000, "loss": 0.69, "lr": 7.4841163968669524e-06, "epoch": 0.956564880609436, "percentage": 74.71, "elapsed_time": "17:21:27", "remaining_time": "5:52:29", "throughput": 657.51, "total_tokens": 41086432} {"current_steps": 29890, "total_steps": 40000, "loss": 0.674, "lr": 7.4771127860618355e-06, "epoch": 0.9567249215799245, "percentage": 74.72, "elapsed_time": "17:21:29", "remaining_time": "5:52:16", "throughput": 657.6, "total_tokens": 41093200} {"current_steps": 29895, "total_steps": 40000, "loss": 0.6673, "lr": 7.470111877506139e-06, "epoch": 0.9568849625504129, "percentage": 74.74, "elapsed_time": "17:21:30", "remaining_time": "5:52:02", "throughput": 657.7, "total_tokens": 41100352} {"current_steps": 29900, "total_steps": 40000, "loss": 0.7525, "lr": 7.463113672279479e-06, "epoch": 0.9570450035209014, "percentage": 74.75, "elapsed_time": "17:21:32", "remaining_time": "5:51:49", "throughput": 657.79, "total_tokens": 41107376} {"current_steps": 29905, "total_steps": 40000, "loss": 0.7172, "lr": 7.456118171461071e-06, "epoch": 0.9572050444913898, "percentage": 74.76, "elapsed_time": "17:21:34", "remaining_time": "5:51:36", "throughput": 657.89, "total_tokens": 41114576} {"current_steps": 29910, "total_steps": 40000, "loss": 0.6508, "lr": 7.449125376129721e-06, "epoch": 0.9573650854618783, "percentage": 74.78, "elapsed_time": "17:21:36", "remaining_time": "5:51:22", "throughput": 657.99, "total_tokens": 41121712} {"current_steps": 29915, "total_steps": 40000, "loss": 0.7226, "lr": 7.442135287363788e-06, "epoch": 0.9575251264323666, "percentage": 74.79, "elapsed_time": "17:21:37", "remaining_time": "5:51:09", "throughput": 658.08, "total_tokens": 41128752} {"current_steps": 29920, "total_steps": 40000, "loss": 0.5267, "lr": 7.435147906241247e-06, "epoch": 0.9576851674028551, "percentage": 74.8, "elapsed_time": "17:21:39", "remaining_time": "5:50:56", "throughput": 658.17, "total_tokens": 41135616} {"current_steps": 29925, "total_steps": 40000, "loss": 0.5438, "lr": 7.428163233839624e-06, "epoch": 0.9578452083733435, "percentage": 74.81, "elapsed_time": "17:21:41", "remaining_time": "5:50:42", "throughput": 658.26, "total_tokens": 41142144} {"current_steps": 29930, "total_steps": 40000, "loss": 1.0344, "lr": 7.4211812712360525e-06, "epoch": 0.958005249343832, "percentage": 74.83, "elapsed_time": "17:21:43", "remaining_time": "5:50:29", "throughput": 658.36, "total_tokens": 41149456} {"current_steps": 29935, "total_steps": 40000, "loss": 0.5813, "lr": 7.4142020195072464e-06, "epoch": 0.9581652903143205, "percentage": 74.84, "elapsed_time": "17:21:44", "remaining_time": "5:50:15", "throughput": 658.45, "total_tokens": 41156352} {"current_steps": 29940, "total_steps": 40000, "loss": 0.6983, "lr": 7.407225479729479e-06, "epoch": 0.9583253312848089, "percentage": 74.85, "elapsed_time": "17:21:46", "remaining_time": "5:50:02", "throughput": 658.55, "total_tokens": 41163456} {"current_steps": 29945, "total_steps": 40000, "loss": 0.5989, "lr": 7.400251652978632e-06, "epoch": 0.9584853722552974, "percentage": 74.86, "elapsed_time": "17:21:48", "remaining_time": "5:49:49", "throughput": 658.64, "total_tokens": 41170624} {"current_steps": 29950, "total_steps": 40000, "loss": 0.902, "lr": 7.393280540330147e-06, "epoch": 0.9586454132257858, "percentage": 74.88, "elapsed_time": "17:21:50", "remaining_time": "5:49:35", "throughput": 658.74, "total_tokens": 41177648} {"current_steps": 29955, "total_steps": 40000, "loss": 0.7538, "lr": 7.386312142859069e-06, "epoch": 0.9588054541962743, "percentage": 74.89, "elapsed_time": "17:21:51", "remaining_time": "5:49:22", "throughput": 658.83, "total_tokens": 41184576} {"current_steps": 29960, "total_steps": 40000, "loss": 0.6386, "lr": 7.379346461640008e-06, "epoch": 0.9589654951667627, "percentage": 74.9, "elapsed_time": "17:21:53", "remaining_time": "5:49:09", "throughput": 658.92, "total_tokens": 41191472} {"current_steps": 29965, "total_steps": 40000, "loss": 0.9494, "lr": 7.372383497747149e-06, "epoch": 0.9591255361372512, "percentage": 74.91, "elapsed_time": "17:21:55", "remaining_time": "5:48:55", "throughput": 659.01, "total_tokens": 41198352} {"current_steps": 29970, "total_steps": 40000, "loss": 0.8989, "lr": 7.3654232522542775e-06, "epoch": 0.9592855771077395, "percentage": 74.92, "elapsed_time": "17:21:57", "remaining_time": "5:48:42", "throughput": 659.11, "total_tokens": 41205360} {"current_steps": 29975, "total_steps": 40000, "loss": 0.8257, "lr": 7.358465726234756e-06, "epoch": 0.959445618078228, "percentage": 74.94, "elapsed_time": "17:21:58", "remaining_time": "5:48:29", "throughput": 659.2, "total_tokens": 41212096} {"current_steps": 29980, "total_steps": 40000, "loss": 0.5231, "lr": 7.351510920761512e-06, "epoch": 0.9596056590487164, "percentage": 74.95, "elapsed_time": "17:22:00", "remaining_time": "5:48:15", "throughput": 659.29, "total_tokens": 41219072} {"current_steps": 29985, "total_steps": 40000, "loss": 0.7545, "lr": 7.344558836907067e-06, "epoch": 0.9597657000192049, "percentage": 74.96, "elapsed_time": "17:22:02", "remaining_time": "5:48:02", "throughput": 659.38, "total_tokens": 41225936} {"current_steps": 29990, "total_steps": 40000, "loss": 0.5926, "lr": 7.3376094757435285e-06, "epoch": 0.9599257409896934, "percentage": 74.98, "elapsed_time": "17:22:03", "remaining_time": "5:47:49", "throughput": 659.47, "total_tokens": 41232512} {"current_steps": 29995, "total_steps": 40000, "loss": 0.6502, "lr": 7.330662838342561e-06, "epoch": 0.9600857819601818, "percentage": 74.99, "elapsed_time": "17:22:05", "remaining_time": "5:47:35", "throughput": 659.56, "total_tokens": 41239392} {"current_steps": 30000, "total_steps": 40000, "loss": 0.6259, "lr": 7.323718925775438e-06, "epoch": 0.9602458229306703, "percentage": 75.0, "elapsed_time": "17:22:07", "remaining_time": "5:47:22", "throughput": 659.64, "total_tokens": 41245904} {"current_steps": 30000, "total_steps": 40000, "eval_loss": 0.7321456074714661, "epoch": 0.9602458229306703, "percentage": 75.0, "elapsed_time": "17:27:55", "remaining_time": "5:49:18", "throughput": 655.99, "total_tokens": 41245904} {"current_steps": 30005, "total_steps": 40000, "loss": 0.6902, "lr": 7.316777739112985e-06, "epoch": 0.9604058639011587, "percentage": 75.01, "elapsed_time": "17:27:58", "remaining_time": "5:49:05", "throughput": 656.08, "total_tokens": 41253376} {"current_steps": 30010, "total_steps": 40000, "loss": 0.6835, "lr": 7.309839279425626e-06, "epoch": 0.9605659048716472, "percentage": 75.02, "elapsed_time": "17:28:00", "remaining_time": "5:48:52", "throughput": 656.17, "total_tokens": 41260400} {"current_steps": 30015, "total_steps": 40000, "loss": 0.7251, "lr": 7.302903547783366e-06, "epoch": 0.9607259458421356, "percentage": 75.04, "elapsed_time": "17:28:02", "remaining_time": "5:48:38", "throughput": 656.27, "total_tokens": 41267424} {"current_steps": 30020, "total_steps": 40000, "loss": 0.772, "lr": 7.2959705452557644e-06, "epoch": 0.960885986812624, "percentage": 75.05, "elapsed_time": "17:28:03", "remaining_time": "5:48:25", "throughput": 656.35, "total_tokens": 41274160} {"current_steps": 30025, "total_steps": 40000, "loss": 0.719, "lr": 7.289040272911996e-06, "epoch": 0.9610460277831124, "percentage": 75.06, "elapsed_time": "17:28:05", "remaining_time": "5:48:12", "throughput": 656.44, "total_tokens": 41280784} {"current_steps": 30030, "total_steps": 40000, "loss": 0.8405, "lr": 7.282112731820789e-06, "epoch": 0.9612060687536009, "percentage": 75.08, "elapsed_time": "17:28:07", "remaining_time": "5:47:58", "throughput": 656.53, "total_tokens": 41287424} {"current_steps": 30035, "total_steps": 40000, "loss": 0.6466, "lr": 7.275187923050447e-06, "epoch": 0.9613661097240893, "percentage": 75.09, "elapsed_time": "17:28:09", "remaining_time": "5:47:45", "throughput": 656.62, "total_tokens": 41294240} {"current_steps": 30040, "total_steps": 40000, "loss": 0.8031, "lr": 7.268265847668879e-06, "epoch": 0.9615261506945778, "percentage": 75.1, "elapsed_time": "17:28:10", "remaining_time": "5:47:31", "throughput": 656.71, "total_tokens": 41301280} {"current_steps": 30045, "total_steps": 40000, "loss": 0.6143, "lr": 7.261346506743538e-06, "epoch": 0.9616861916650663, "percentage": 75.11, "elapsed_time": "17:28:12", "remaining_time": "5:47:18", "throughput": 656.8, "total_tokens": 41308016} {"current_steps": 30050, "total_steps": 40000, "loss": 0.8296, "lr": 7.254429901341486e-06, "epoch": 0.9618462326355547, "percentage": 75.12, "elapsed_time": "17:28:14", "remaining_time": "5:47:05", "throughput": 656.89, "total_tokens": 41314736} {"current_steps": 30055, "total_steps": 40000, "loss": 0.7734, "lr": 7.247516032529356e-06, "epoch": 0.9620062736060432, "percentage": 75.14, "elapsed_time": "17:28:16", "remaining_time": "5:46:51", "throughput": 656.98, "total_tokens": 41321264} {"current_steps": 30060, "total_steps": 40000, "loss": 0.5872, "lr": 7.240604901373338e-06, "epoch": 0.9621663145765316, "percentage": 75.15, "elapsed_time": "17:28:17", "remaining_time": "5:46:38", "throughput": 657.07, "total_tokens": 41328432} {"current_steps": 30065, "total_steps": 40000, "loss": 0.8267, "lr": 7.233696508939223e-06, "epoch": 0.9623263555470201, "percentage": 75.16, "elapsed_time": "17:28:19", "remaining_time": "5:46:25", "throughput": 657.16, "total_tokens": 41335200} {"current_steps": 30070, "total_steps": 40000, "loss": 0.748, "lr": 7.226790856292376e-06, "epoch": 0.9624863965175084, "percentage": 75.17, "elapsed_time": "17:28:21", "remaining_time": "5:46:11", "throughput": 657.25, "total_tokens": 41341696} {"current_steps": 30075, "total_steps": 40000, "loss": 0.7635, "lr": 7.219887944497727e-06, "epoch": 0.9626464374879969, "percentage": 75.19, "elapsed_time": "17:28:23", "remaining_time": "5:45:58", "throughput": 657.34, "total_tokens": 41348688} {"current_steps": 30080, "total_steps": 40000, "loss": 0.6875, "lr": 7.2129877746198e-06, "epoch": 0.9628064784584853, "percentage": 75.2, "elapsed_time": "17:28:24", "remaining_time": "5:45:45", "throughput": 657.43, "total_tokens": 41355712} {"current_steps": 30085, "total_steps": 40000, "loss": 0.7363, "lr": 7.20609034772268e-06, "epoch": 0.9629665194289738, "percentage": 75.21, "elapsed_time": "17:28:26", "remaining_time": "5:45:31", "throughput": 657.52, "total_tokens": 41362464} {"current_steps": 30090, "total_steps": 40000, "loss": 0.8062, "lr": 7.19919566487004e-06, "epoch": 0.9631265603994623, "percentage": 75.22, "elapsed_time": "17:28:28", "remaining_time": "5:45:18", "throughput": 657.61, "total_tokens": 41369232} {"current_steps": 30095, "total_steps": 40000, "loss": 0.7136, "lr": 7.192303727125132e-06, "epoch": 0.9632866013699507, "percentage": 75.24, "elapsed_time": "17:28:30", "remaining_time": "5:45:05", "throughput": 657.71, "total_tokens": 41376576} {"current_steps": 30100, "total_steps": 40000, "loss": 0.7862, "lr": 7.185414535550777e-06, "epoch": 0.9634466423404392, "percentage": 75.25, "elapsed_time": "17:28:31", "remaining_time": "5:44:51", "throughput": 657.8, "total_tokens": 41383408} {"current_steps": 30105, "total_steps": 40000, "loss": 0.8851, "lr": 7.178528091209363e-06, "epoch": 0.9636066833109276, "percentage": 75.26, "elapsed_time": "17:28:33", "remaining_time": "5:44:38", "throughput": 657.89, "total_tokens": 41390112} {"current_steps": 30110, "total_steps": 40000, "loss": 0.847, "lr": 7.171644395162888e-06, "epoch": 0.9637667242814161, "percentage": 75.28, "elapsed_time": "17:28:35", "remaining_time": "5:44:25", "throughput": 657.99, "total_tokens": 41397584} {"current_steps": 30115, "total_steps": 40000, "loss": 0.7219, "lr": 7.164763448472881e-06, "epoch": 0.9639267652519045, "percentage": 75.29, "elapsed_time": "17:28:36", "remaining_time": "5:44:11", "throughput": 658.08, "total_tokens": 41404240} {"current_steps": 30120, "total_steps": 40000, "loss": 0.8578, "lr": 7.157885252200491e-06, "epoch": 0.964086806222393, "percentage": 75.3, "elapsed_time": "17:28:38", "remaining_time": "5:43:58", "throughput": 658.16, "total_tokens": 41410528} {"current_steps": 30125, "total_steps": 40000, "loss": 0.7608, "lr": 7.151009807406403e-06, "epoch": 0.9642468471928813, "percentage": 75.31, "elapsed_time": "17:28:40", "remaining_time": "5:43:45", "throughput": 658.25, "total_tokens": 41417168} {"current_steps": 30130, "total_steps": 40000, "loss": 0.6645, "lr": 7.144137115150909e-06, "epoch": 0.9644068881633698, "percentage": 75.33, "elapsed_time": "17:28:42", "remaining_time": "5:43:32", "throughput": 658.34, "total_tokens": 41424096} {"current_steps": 30135, "total_steps": 40000, "loss": 0.6243, "lr": 7.1372671764938725e-06, "epoch": 0.9645669291338582, "percentage": 75.34, "elapsed_time": "17:28:43", "remaining_time": "5:43:18", "throughput": 658.44, "total_tokens": 41431328} {"current_steps": 30140, "total_steps": 40000, "loss": 0.8067, "lr": 7.130399992494705e-06, "epoch": 0.9647269701043467, "percentage": 75.35, "elapsed_time": "17:28:45", "remaining_time": "5:43:05", "throughput": 658.52, "total_tokens": 41437632} {"current_steps": 30145, "total_steps": 40000, "loss": 0.8058, "lr": 7.123535564212419e-06, "epoch": 0.9648870110748352, "percentage": 75.36, "elapsed_time": "17:28:47", "remaining_time": "5:42:52", "throughput": 658.6, "total_tokens": 41444272} {"current_steps": 30150, "total_steps": 40000, "loss": 0.6951, "lr": 7.116673892705611e-06, "epoch": 0.9650470520453236, "percentage": 75.38, "elapsed_time": "17:28:49", "remaining_time": "5:42:38", "throughput": 658.69, "total_tokens": 41450736} {"current_steps": 30155, "total_steps": 40000, "loss": 1.0894, "lr": 7.109814979032415e-06, "epoch": 0.9652070930158121, "percentage": 75.39, "elapsed_time": "17:28:50", "remaining_time": "5:42:25", "throughput": 658.78, "total_tokens": 41457680} {"current_steps": 30160, "total_steps": 40000, "loss": 0.802, "lr": 7.102958824250577e-06, "epoch": 0.9653671339863005, "percentage": 75.4, "elapsed_time": "17:28:52", "remaining_time": "5:42:12", "throughput": 658.87, "total_tokens": 41464480} {"current_steps": 30165, "total_steps": 40000, "loss": 0.6649, "lr": 7.096105429417393e-06, "epoch": 0.965527174956789, "percentage": 75.41, "elapsed_time": "17:28:54", "remaining_time": "5:41:59", "throughput": 658.96, "total_tokens": 41471248} {"current_steps": 30170, "total_steps": 40000, "loss": 0.8038, "lr": 7.0892547955897506e-06, "epoch": 0.9656872159272774, "percentage": 75.42, "elapsed_time": "17:28:56", "remaining_time": "5:41:45", "throughput": 659.06, "total_tokens": 41478368} {"current_steps": 30175, "total_steps": 40000, "loss": 0.8114, "lr": 7.0824069238241e-06, "epoch": 0.9658472568977658, "percentage": 75.44, "elapsed_time": "17:28:57", "remaining_time": "5:41:32", "throughput": 659.14, "total_tokens": 41484688} {"current_steps": 30180, "total_steps": 40000, "loss": 0.6037, "lr": 7.075561815176462e-06, "epoch": 0.9660072978682542, "percentage": 75.45, "elapsed_time": "17:28:59", "remaining_time": "5:41:19", "throughput": 659.23, "total_tokens": 41491504} {"current_steps": 30185, "total_steps": 40000, "loss": 0.7085, "lr": 7.068719470702445e-06, "epoch": 0.9661673388387427, "percentage": 75.46, "elapsed_time": "17:29:01", "remaining_time": "5:41:06", "throughput": 659.32, "total_tokens": 41498624} {"current_steps": 30190, "total_steps": 40000, "loss": 0.6918, "lr": 7.061879891457229e-06, "epoch": 0.9663273798092311, "percentage": 75.48, "elapsed_time": "17:29:03", "remaining_time": "5:40:52", "throughput": 659.41, "total_tokens": 41505488} {"current_steps": 30195, "total_steps": 40000, "loss": 0.8702, "lr": 7.0550430784955515e-06, "epoch": 0.9664874207797196, "percentage": 75.49, "elapsed_time": "17:29:04", "remaining_time": "5:40:39", "throughput": 659.51, "total_tokens": 41512448} {"current_steps": 30200, "total_steps": 40000, "loss": 0.9303, "lr": 7.048209032871752e-06, "epoch": 0.9666474617502081, "percentage": 75.5, "elapsed_time": "17:29:06", "remaining_time": "5:40:26", "throughput": 659.6, "total_tokens": 41519232} {"current_steps": 30200, "total_steps": 40000, "eval_loss": 0.7320457696914673, "epoch": 0.9666474617502081, "percentage": 75.5, "elapsed_time": "17:34:53", "remaining_time": "5:42:19", "throughput": 655.98, "total_tokens": 41519232} {"current_steps": 30205, "total_steps": 40000, "loss": 0.7533, "lr": 7.0413777556397055e-06, "epoch": 0.9668075027206965, "percentage": 75.51, "elapsed_time": "17:34:57", "remaining_time": "5:42:06", "throughput": 656.05, "total_tokens": 41525952} {"current_steps": 30210, "total_steps": 40000, "loss": 0.7759, "lr": 7.0345492478528925e-06, "epoch": 0.966967543691185, "percentage": 75.52, "elapsed_time": "17:34:58", "remaining_time": "5:41:52", "throughput": 656.14, "total_tokens": 41532752} {"current_steps": 30215, "total_steps": 40000, "loss": 0.708, "lr": 7.02772351056436e-06, "epoch": 0.9671275846616734, "percentage": 75.54, "elapsed_time": "17:35:00", "remaining_time": "5:41:39", "throughput": 656.22, "total_tokens": 41539168} {"current_steps": 30220, "total_steps": 40000, "loss": 0.7898, "lr": 7.020900544826709e-06, "epoch": 0.9672876256321619, "percentage": 75.55, "elapsed_time": "17:35:02", "remaining_time": "5:41:26", "throughput": 656.31, "total_tokens": 41545920} {"current_steps": 30225, "total_steps": 40000, "loss": 0.5767, "lr": 7.014080351692134e-06, "epoch": 0.9674476666026502, "percentage": 75.56, "elapsed_time": "17:35:04", "remaining_time": "5:41:13", "throughput": 656.4, "total_tokens": 41552704} {"current_steps": 30230, "total_steps": 40000, "loss": 0.6959, "lr": 7.0072629322124024e-06, "epoch": 0.9676077075731387, "percentage": 75.58, "elapsed_time": "17:35:05", "remaining_time": "5:40:59", "throughput": 656.49, "total_tokens": 41559728} {"current_steps": 30235, "total_steps": 40000, "loss": 0.6439, "lr": 7.000448287438827e-06, "epoch": 0.9677677485436271, "percentage": 75.59, "elapsed_time": "17:35:07", "remaining_time": "5:40:46", "throughput": 656.58, "total_tokens": 41566496} {"current_steps": 30240, "total_steps": 40000, "loss": 0.9082, "lr": 6.993636418422331e-06, "epoch": 0.9679277895141156, "percentage": 75.6, "elapsed_time": "17:35:09", "remaining_time": "5:40:33", "throughput": 656.67, "total_tokens": 41573152} {"current_steps": 30245, "total_steps": 40000, "loss": 0.7402, "lr": 6.986827326213383e-06, "epoch": 0.968087830484604, "percentage": 75.61, "elapsed_time": "17:35:11", "remaining_time": "5:40:19", "throughput": 656.76, "total_tokens": 41580000} {"current_steps": 30250, "total_steps": 40000, "loss": 0.7686, "lr": 6.9800210118620205e-06, "epoch": 0.9682478714550925, "percentage": 75.62, "elapsed_time": "17:35:12", "remaining_time": "5:40:06", "throughput": 656.86, "total_tokens": 41587568} {"current_steps": 30255, "total_steps": 40000, "loss": 0.7624, "lr": 6.973217476417876e-06, "epoch": 0.968407912425581, "percentage": 75.64, "elapsed_time": "17:35:14", "remaining_time": "5:39:53", "throughput": 656.95, "total_tokens": 41594640} {"current_steps": 30260, "total_steps": 40000, "loss": 0.6766, "lr": 6.96641672093013e-06, "epoch": 0.9685679533960694, "percentage": 75.65, "elapsed_time": "17:35:16", "remaining_time": "5:39:40", "throughput": 657.04, "total_tokens": 41601440} {"current_steps": 30265, "total_steps": 40000, "loss": 0.6055, "lr": 6.95961874644755e-06, "epoch": 0.9687279943665579, "percentage": 75.66, "elapsed_time": "17:35:18", "remaining_time": "5:39:26", "throughput": 657.13, "total_tokens": 41607920} {"current_steps": 30270, "total_steps": 40000, "loss": 0.7269, "lr": 6.952823554018476e-06, "epoch": 0.9688880353370463, "percentage": 75.67, "elapsed_time": "17:35:19", "remaining_time": "5:39:13", "throughput": 657.22, "total_tokens": 41614768} {"current_steps": 30275, "total_steps": 40000, "loss": 0.6828, "lr": 6.946031144690798e-06, "epoch": 0.9690480763075348, "percentage": 75.69, "elapsed_time": "17:35:21", "remaining_time": "5:39:00", "throughput": 657.31, "total_tokens": 41621648} {"current_steps": 30280, "total_steps": 40000, "loss": 0.5516, "lr": 6.939241519512005e-06, "epoch": 0.9692081172780231, "percentage": 75.7, "elapsed_time": "17:35:23", "remaining_time": "5:38:47", "throughput": 657.4, "total_tokens": 41628400} {"current_steps": 30285, "total_steps": 40000, "loss": 0.766, "lr": 6.932454679529129e-06, "epoch": 0.9693681582485116, "percentage": 75.71, "elapsed_time": "17:35:24", "remaining_time": "5:38:33", "throughput": 657.48, "total_tokens": 41634976} {"current_steps": 30290, "total_steps": 40000, "loss": 0.7387, "lr": 6.925670625788791e-06, "epoch": 0.969528199219, "percentage": 75.72, "elapsed_time": "17:35:26", "remaining_time": "5:38:20", "throughput": 657.57, "total_tokens": 41641920} {"current_steps": 30295, "total_steps": 40000, "loss": 0.737, "lr": 6.918889359337186e-06, "epoch": 0.9696882401894885, "percentage": 75.74, "elapsed_time": "17:35:28", "remaining_time": "5:38:07", "throughput": 657.67, "total_tokens": 41648928} {"current_steps": 30300, "total_steps": 40000, "loss": 0.7903, "lr": 6.912110881220058e-06, "epoch": 0.9698482811599769, "percentage": 75.75, "elapsed_time": "17:35:30", "remaining_time": "5:37:54", "throughput": 657.75, "total_tokens": 41655664} {"current_steps": 30305, "total_steps": 40000, "loss": 0.7872, "lr": 6.905335192482735e-06, "epoch": 0.9700083221304654, "percentage": 75.76, "elapsed_time": "17:35:31", "remaining_time": "5:37:40", "throughput": 657.85, "total_tokens": 41662736} {"current_steps": 30310, "total_steps": 40000, "loss": 0.7437, "lr": 6.8985622941701275e-06, "epoch": 0.9701683631009539, "percentage": 75.78, "elapsed_time": "17:35:33", "remaining_time": "5:37:27", "throughput": 657.94, "total_tokens": 41669664} {"current_steps": 30315, "total_steps": 40000, "loss": 0.7792, "lr": 6.89179218732669e-06, "epoch": 0.9703284040714423, "percentage": 75.79, "elapsed_time": "17:35:35", "remaining_time": "5:37:14", "throughput": 658.02, "total_tokens": 41676064} {"current_steps": 30320, "total_steps": 40000, "loss": 0.891, "lr": 6.8850248729964595e-06, "epoch": 0.9704884450419308, "percentage": 75.8, "elapsed_time": "17:35:37", "remaining_time": "5:37:01", "throughput": 658.11, "total_tokens": 41682832} {"current_steps": 30325, "total_steps": 40000, "loss": 0.7203, "lr": 6.8782603522230314e-06, "epoch": 0.9706484860124192, "percentage": 75.81, "elapsed_time": "17:35:38", "remaining_time": "5:36:47", "throughput": 658.2, "total_tokens": 41689408} {"current_steps": 30330, "total_steps": 40000, "loss": 0.6142, "lr": 6.871498626049591e-06, "epoch": 0.9708085269829076, "percentage": 75.83, "elapsed_time": "17:35:40", "remaining_time": "5:36:34", "throughput": 658.29, "total_tokens": 41696224} {"current_steps": 30335, "total_steps": 40000, "loss": 0.7744, "lr": 6.8647396955188875e-06, "epoch": 0.970968567953396, "percentage": 75.84, "elapsed_time": "17:35:42", "remaining_time": "5:36:21", "throughput": 658.37, "total_tokens": 41702608} {"current_steps": 30340, "total_steps": 40000, "loss": 0.667, "lr": 6.857983561673218e-06, "epoch": 0.9711286089238845, "percentage": 75.85, "elapsed_time": "17:35:44", "remaining_time": "5:36:08", "throughput": 658.45, "total_tokens": 41709200} {"current_steps": 30345, "total_steps": 40000, "loss": 0.7837, "lr": 6.851230225554467e-06, "epoch": 0.9712886498943729, "percentage": 75.86, "elapsed_time": "17:35:45", "remaining_time": "5:35:55", "throughput": 658.54, "total_tokens": 41715968} {"current_steps": 30350, "total_steps": 40000, "loss": 0.5539, "lr": 6.8444796882040946e-06, "epoch": 0.9714486908648614, "percentage": 75.88, "elapsed_time": "17:35:47", "remaining_time": "5:35:41", "throughput": 658.63, "total_tokens": 41722608} {"current_steps": 30355, "total_steps": 40000, "loss": 0.585, "lr": 6.837731950663106e-06, "epoch": 0.9716087318353499, "percentage": 75.89, "elapsed_time": "17:35:49", "remaining_time": "5:35:28", "throughput": 658.72, "total_tokens": 41729424} {"current_steps": 30360, "total_steps": 40000, "loss": 0.6971, "lr": 6.830987013972098e-06, "epoch": 0.9717687728058383, "percentage": 75.9, "elapsed_time": "17:35:51", "remaining_time": "5:35:15", "throughput": 658.81, "total_tokens": 41736288} {"current_steps": 30365, "total_steps": 40000, "loss": 0.7437, "lr": 6.82424487917121e-06, "epoch": 0.9719288137763268, "percentage": 75.91, "elapsed_time": "17:35:52", "remaining_time": "5:35:02", "throughput": 658.89, "total_tokens": 41742592} {"current_steps": 30370, "total_steps": 40000, "loss": 0.7072, "lr": 6.8175055473001735e-06, "epoch": 0.9720888547468152, "percentage": 75.92, "elapsed_time": "17:35:54", "remaining_time": "5:34:49", "throughput": 658.99, "total_tokens": 41749808} {"current_steps": 30375, "total_steps": 40000, "loss": 0.7804, "lr": 6.8107690193982855e-06, "epoch": 0.9722488957173037, "percentage": 75.94, "elapsed_time": "17:35:56", "remaining_time": "5:34:35", "throughput": 659.08, "total_tokens": 41756784} {"current_steps": 30380, "total_steps": 40000, "loss": 0.5943, "lr": 6.804035296504385e-06, "epoch": 0.972408936687792, "percentage": 75.95, "elapsed_time": "17:35:57", "remaining_time": "5:34:22", "throughput": 659.17, "total_tokens": 41763664} {"current_steps": 30385, "total_steps": 40000, "loss": 0.5741, "lr": 6.797304379656916e-06, "epoch": 0.9725689776582805, "percentage": 75.96, "elapsed_time": "17:35:59", "remaining_time": "5:34:09", "throughput": 659.26, "total_tokens": 41770288} {"current_steps": 30390, "total_steps": 40000, "loss": 0.7577, "lr": 6.790576269893861e-06, "epoch": 0.9727290186287689, "percentage": 75.98, "elapsed_time": "17:36:01", "remaining_time": "5:33:56", "throughput": 659.35, "total_tokens": 41777328} {"current_steps": 30395, "total_steps": 40000, "loss": 0.7099, "lr": 6.783850968252772e-06, "epoch": 0.9728890595992574, "percentage": 75.99, "elapsed_time": "17:36:03", "remaining_time": "5:33:43", "throughput": 659.44, "total_tokens": 41784272} {"current_steps": 30400, "total_steps": 40000, "loss": 1.0491, "lr": 6.777128475770789e-06, "epoch": 0.9730491005697458, "percentage": 76.0, "elapsed_time": "17:36:04", "remaining_time": "5:33:29", "throughput": 659.54, "total_tokens": 41791520} {"current_steps": 30400, "total_steps": 40000, "eval_loss": 0.7319129705429077, "epoch": 0.9730491005697458, "percentage": 76.0, "elapsed_time": "17:41:52", "remaining_time": "5:35:19", "throughput": 655.94, "total_tokens": 41791520} {"current_steps": 30405, "total_steps": 40000, "loss": 0.7885, "lr": 6.77040879348459e-06, "epoch": 0.9732091415402343, "percentage": 76.01, "elapsed_time": "17:41:55", "remaining_time": "5:35:07", "throughput": 656.01, "total_tokens": 41798304} {"current_steps": 30410, "total_steps": 40000, "loss": 0.6896, "lr": 6.763691922430443e-06, "epoch": 0.9733691825107228, "percentage": 76.02, "elapsed_time": "17:41:57", "remaining_time": "5:34:53", "throughput": 656.1, "total_tokens": 41805392} {"current_steps": 30415, "total_steps": 40000, "loss": 0.7281, "lr": 6.756977863644178e-06, "epoch": 0.9735292234812112, "percentage": 76.04, "elapsed_time": "17:41:59", "remaining_time": "5:34:40", "throughput": 656.2, "total_tokens": 41812432} {"current_steps": 30420, "total_steps": 40000, "loss": 0.6271, "lr": 6.7502666181611804e-06, "epoch": 0.9736892644516997, "percentage": 76.05, "elapsed_time": "17:42:01", "remaining_time": "5:34:27", "throughput": 656.28, "total_tokens": 41819008} {"current_steps": 30425, "total_steps": 40000, "loss": 0.8856, "lr": 6.743558187016405e-06, "epoch": 0.9738493054221881, "percentage": 76.06, "elapsed_time": "17:42:02", "remaining_time": "5:34:14", "throughput": 656.38, "total_tokens": 41826592} {"current_steps": 30430, "total_steps": 40000, "loss": 0.7762, "lr": 6.7368525712443925e-06, "epoch": 0.9740093463926766, "percentage": 76.08, "elapsed_time": "17:42:04", "remaining_time": "5:34:00", "throughput": 656.47, "total_tokens": 41833280} {"current_steps": 30435, "total_steps": 40000, "loss": 0.8528, "lr": 6.7301497718792155e-06, "epoch": 0.9741693873631649, "percentage": 76.09, "elapsed_time": "17:42:06", "remaining_time": "5:33:47", "throughput": 656.56, "total_tokens": 41840240} {"current_steps": 30440, "total_steps": 40000, "loss": 0.61, "lr": 6.723449789954544e-06, "epoch": 0.9743294283336534, "percentage": 76.1, "elapsed_time": "17:42:08", "remaining_time": "5:33:34", "throughput": 656.66, "total_tokens": 41847440} {"current_steps": 30445, "total_steps": 40000, "loss": 0.8313, "lr": 6.716752626503586e-06, "epoch": 0.9744894693041418, "percentage": 76.11, "elapsed_time": "17:42:09", "remaining_time": "5:33:21", "throughput": 656.74, "total_tokens": 41854192} {"current_steps": 30450, "total_steps": 40000, "loss": 0.845, "lr": 6.710058282559131e-06, "epoch": 0.9746495102746303, "percentage": 76.12, "elapsed_time": "17:42:11", "remaining_time": "5:33:08", "throughput": 656.84, "total_tokens": 41861136} {"current_steps": 30455, "total_steps": 40000, "loss": 0.8586, "lr": 6.703366759153545e-06, "epoch": 0.9748095512451187, "percentage": 76.14, "elapsed_time": "17:42:13", "remaining_time": "5:32:54", "throughput": 656.92, "total_tokens": 41867792} {"current_steps": 30460, "total_steps": 40000, "loss": 0.715, "lr": 6.6966780573187335e-06, "epoch": 0.9749695922156072, "percentage": 76.15, "elapsed_time": "17:42:14", "remaining_time": "5:32:41", "throughput": 657.01, "total_tokens": 41874784} {"current_steps": 30465, "total_steps": 40000, "loss": 0.9231, "lr": 6.689992178086174e-06, "epoch": 0.9751296331860957, "percentage": 76.16, "elapsed_time": "17:42:16", "remaining_time": "5:32:28", "throughput": 657.1, "total_tokens": 41881568} {"current_steps": 30470, "total_steps": 40000, "loss": 0.7536, "lr": 6.683309122486925e-06, "epoch": 0.9752896741565841, "percentage": 76.17, "elapsed_time": "17:42:18", "remaining_time": "5:32:15", "throughput": 657.19, "total_tokens": 41888224} {"current_steps": 30475, "total_steps": 40000, "loss": 0.6739, "lr": 6.676628891551584e-06, "epoch": 0.9754497151270726, "percentage": 76.19, "elapsed_time": "17:42:20", "remaining_time": "5:32:02", "throughput": 657.28, "total_tokens": 41894960} {"current_steps": 30480, "total_steps": 40000, "loss": 0.671, "lr": 6.6699514863103385e-06, "epoch": 0.975609756097561, "percentage": 76.2, "elapsed_time": "17:42:21", "remaining_time": "5:31:48", "throughput": 657.37, "total_tokens": 41901968} {"current_steps": 30485, "total_steps": 40000, "loss": 0.8915, "lr": 6.663276907792921e-06, "epoch": 0.9757697970680494, "percentage": 76.21, "elapsed_time": "17:42:23", "remaining_time": "5:31:35", "throughput": 657.46, "total_tokens": 41908736} {"current_steps": 30490, "total_steps": 40000, "loss": 0.8071, "lr": 6.656605157028634e-06, "epoch": 0.9759298380385378, "percentage": 76.22, "elapsed_time": "17:42:25", "remaining_time": "5:31:22", "throughput": 657.54, "total_tokens": 41915472} {"current_steps": 30495, "total_steps": 40000, "loss": 0.6706, "lr": 6.649936235046358e-06, "epoch": 0.9760898790090263, "percentage": 76.24, "elapsed_time": "17:42:27", "remaining_time": "5:31:09", "throughput": 657.63, "total_tokens": 41922160} {"current_steps": 30500, "total_steps": 40000, "loss": 0.7196, "lr": 6.643270142874508e-06, "epoch": 0.9762499199795147, "percentage": 76.25, "elapsed_time": "17:42:28", "remaining_time": "5:30:56", "throughput": 657.72, "total_tokens": 41928976} {"current_steps": 30505, "total_steps": 40000, "loss": 1.1467, "lr": 6.636606881541094e-06, "epoch": 0.9764099609500032, "percentage": 76.26, "elapsed_time": "17:42:30", "remaining_time": "5:30:43", "throughput": 657.81, "total_tokens": 41935536} {"current_steps": 30510, "total_steps": 40000, "loss": 0.7707, "lr": 6.629946452073662e-06, "epoch": 0.9765700019204916, "percentage": 76.28, "elapsed_time": "17:42:32", "remaining_time": "5:30:29", "throughput": 657.89, "total_tokens": 41942288} {"current_steps": 30515, "total_steps": 40000, "loss": 0.5816, "lr": 6.6232888554993375e-06, "epoch": 0.9767300428909801, "percentage": 76.29, "elapsed_time": "17:42:34", "remaining_time": "5:30:16", "throughput": 657.98, "total_tokens": 41948832} {"current_steps": 30520, "total_steps": 40000, "loss": 0.6616, "lr": 6.616634092844817e-06, "epoch": 0.9768900838614686, "percentage": 76.3, "elapsed_time": "17:42:35", "remaining_time": "5:30:03", "throughput": 658.07, "total_tokens": 41955776} {"current_steps": 30525, "total_steps": 40000, "loss": 0.7422, "lr": 6.609982165136331e-06, "epoch": 0.977050124831957, "percentage": 76.31, "elapsed_time": "17:42:37", "remaining_time": "5:29:50", "throughput": 658.15, "total_tokens": 41962352} {"current_steps": 30530, "total_steps": 40000, "loss": 0.8274, "lr": 6.603333073399706e-06, "epoch": 0.9772101658024455, "percentage": 76.33, "elapsed_time": "17:42:39", "remaining_time": "5:29:37", "throughput": 658.25, "total_tokens": 41969440} {"current_steps": 30535, "total_steps": 40000, "loss": 0.6041, "lr": 6.596686818660308e-06, "epoch": 0.9773702067729338, "percentage": 76.34, "elapsed_time": "17:42:41", "remaining_time": "5:29:24", "throughput": 658.34, "total_tokens": 41976592} {"current_steps": 30540, "total_steps": 40000, "loss": 0.5552, "lr": 6.590043401943066e-06, "epoch": 0.9775302477434223, "percentage": 76.35, "elapsed_time": "17:42:42", "remaining_time": "5:29:11", "throughput": 658.44, "total_tokens": 41983680} {"current_steps": 30545, "total_steps": 40000, "loss": 0.8438, "lr": 6.583402824272494e-06, "epoch": 0.9776902887139107, "percentage": 76.36, "elapsed_time": "17:42:44", "remaining_time": "5:28:57", "throughput": 658.53, "total_tokens": 41990800} {"current_steps": 30550, "total_steps": 40000, "loss": 0.8491, "lr": 6.576765086672634e-06, "epoch": 0.9778503296843992, "percentage": 76.38, "elapsed_time": "17:42:46", "remaining_time": "5:28:44", "throughput": 658.62, "total_tokens": 41997712} {"current_steps": 30555, "total_steps": 40000, "loss": 0.6305, "lr": 6.57013019016712e-06, "epoch": 0.9780103706548876, "percentage": 76.39, "elapsed_time": "17:42:47", "remaining_time": "5:28:31", "throughput": 658.71, "total_tokens": 42004608} {"current_steps": 30560, "total_steps": 40000, "loss": 0.5596, "lr": 6.563498135779142e-06, "epoch": 0.9781704116253761, "percentage": 76.4, "elapsed_time": "17:42:49", "remaining_time": "5:28:18", "throughput": 658.82, "total_tokens": 42012512} {"current_steps": 30565, "total_steps": 40000, "loss": 0.7135, "lr": 6.556868924531431e-06, "epoch": 0.9783304525958645, "percentage": 76.41, "elapsed_time": "17:42:51", "remaining_time": "5:28:05", "throughput": 658.9, "total_tokens": 42019264} {"current_steps": 30570, "total_steps": 40000, "loss": 0.6782, "lr": 6.550242557446304e-06, "epoch": 0.978490493566353, "percentage": 76.42, "elapsed_time": "17:42:53", "remaining_time": "5:27:52", "throughput": 658.99, "total_tokens": 42026112} {"current_steps": 30575, "total_steps": 40000, "loss": 0.664, "lr": 6.543619035545634e-06, "epoch": 0.9786505345368415, "percentage": 76.44, "elapsed_time": "17:42:54", "remaining_time": "5:27:39", "throughput": 659.08, "total_tokens": 42032640} {"current_steps": 30580, "total_steps": 40000, "loss": 0.6089, "lr": 6.53699835985084e-06, "epoch": 0.9788105755073299, "percentage": 76.45, "elapsed_time": "17:42:56", "remaining_time": "5:27:26", "throughput": 659.17, "total_tokens": 42039376} {"current_steps": 30585, "total_steps": 40000, "loss": 0.849, "lr": 6.530380531382927e-06, "epoch": 0.9789706164778184, "percentage": 76.46, "elapsed_time": "17:42:58", "remaining_time": "5:27:12", "throughput": 659.25, "total_tokens": 42046128} {"current_steps": 30590, "total_steps": 40000, "loss": 0.7926, "lr": 6.523765551162433e-06, "epoch": 0.9791306574483067, "percentage": 76.48, "elapsed_time": "17:43:00", "remaining_time": "5:26:59", "throughput": 659.34, "total_tokens": 42052816} {"current_steps": 30595, "total_steps": 40000, "loss": 0.8574, "lr": 6.517153420209476e-06, "epoch": 0.9792906984187952, "percentage": 76.49, "elapsed_time": "17:43:01", "remaining_time": "5:26:46", "throughput": 659.43, "total_tokens": 42059904} {"current_steps": 30600, "total_steps": 40000, "loss": 0.6816, "lr": 6.510544139543739e-06, "epoch": 0.9794507393892836, "percentage": 76.5, "elapsed_time": "17:43:03", "remaining_time": "5:26:33", "throughput": 659.53, "total_tokens": 42066928} {"current_steps": 30600, "total_steps": 40000, "eval_loss": 0.7318710684776306, "epoch": 0.9794507393892836, "percentage": 76.5, "elapsed_time": "17:48:51", "remaining_time": "5:28:20", "throughput": 655.94, "total_tokens": 42066928} {"current_steps": 30605, "total_steps": 40000, "loss": 0.5119, "lr": 6.503937710184452e-06, "epoch": 0.9796107803597721, "percentage": 76.51, "elapsed_time": "17:48:55", "remaining_time": "5:28:07", "throughput": 656.02, "total_tokens": 42073776} {"current_steps": 30610, "total_steps": 40000, "loss": 0.9121, "lr": 6.4973341331503954e-06, "epoch": 0.9797708213302605, "percentage": 76.53, "elapsed_time": "17:48:56", "remaining_time": "5:27:54", "throughput": 656.1, "total_tokens": 42080544} {"current_steps": 30615, "total_steps": 40000, "loss": 0.7083, "lr": 6.490733409459942e-06, "epoch": 0.979930862300749, "percentage": 76.54, "elapsed_time": "17:48:58", "remaining_time": "5:27:41", "throughput": 656.19, "total_tokens": 42087376} {"current_steps": 30620, "total_steps": 40000, "loss": 0.6903, "lr": 6.484135540130995e-06, "epoch": 0.9800909032712375, "percentage": 76.55, "elapsed_time": "17:49:00", "remaining_time": "5:27:28", "throughput": 656.29, "total_tokens": 42094672} {"current_steps": 30625, "total_steps": 40000, "loss": 1.0315, "lr": 6.4775405261810364e-06, "epoch": 0.9802509442417259, "percentage": 76.56, "elapsed_time": "17:49:02", "remaining_time": "5:27:15", "throughput": 656.38, "total_tokens": 42101664} {"current_steps": 30630, "total_steps": 40000, "loss": 0.6187, "lr": 6.470948368627092e-06, "epoch": 0.9804109852122144, "percentage": 76.58, "elapsed_time": "17:49:03", "remaining_time": "5:27:02", "throughput": 656.47, "total_tokens": 42108656} {"current_steps": 30635, "total_steps": 40000, "loss": 0.6937, "lr": 6.464359068485756e-06, "epoch": 0.9805710261827028, "percentage": 76.59, "elapsed_time": "17:49:05", "remaining_time": "5:26:49", "throughput": 656.55, "total_tokens": 42115136} {"current_steps": 30640, "total_steps": 40000, "loss": 0.7664, "lr": 6.457772626773195e-06, "epoch": 0.9807310671531912, "percentage": 76.6, "elapsed_time": "17:49:07", "remaining_time": "5:26:35", "throughput": 656.65, "total_tokens": 42122080} {"current_steps": 30645, "total_steps": 40000, "loss": 0.7012, "lr": 6.451189044505104e-06, "epoch": 0.9808911081236796, "percentage": 76.61, "elapsed_time": "17:49:09", "remaining_time": "5:26:22", "throughput": 656.73, "total_tokens": 42128704} {"current_steps": 30650, "total_steps": 40000, "loss": 0.778, "lr": 6.44460832269676e-06, "epoch": 0.9810511490941681, "percentage": 76.62, "elapsed_time": "17:49:10", "remaining_time": "5:26:09", "throughput": 656.82, "total_tokens": 42135536} {"current_steps": 30655, "total_steps": 40000, "loss": 0.8634, "lr": 6.438030462363001e-06, "epoch": 0.9812111900646565, "percentage": 76.64, "elapsed_time": "17:49:12", "remaining_time": "5:25:56", "throughput": 656.9, "total_tokens": 42141984} {"current_steps": 30660, "total_steps": 40000, "loss": 0.6136, "lr": 6.431455464518205e-06, "epoch": 0.981371231035145, "percentage": 76.65, "elapsed_time": "17:49:14", "remaining_time": "5:25:43", "throughput": 656.99, "total_tokens": 42148848} {"current_steps": 30665, "total_steps": 40000, "loss": 0.628, "lr": 6.424883330176326e-06, "epoch": 0.9815312720056334, "percentage": 76.66, "elapsed_time": "17:49:16", "remaining_time": "5:25:30", "throughput": 657.08, "total_tokens": 42155600} {"current_steps": 30670, "total_steps": 40000, "loss": 0.7485, "lr": 6.418314060350864e-06, "epoch": 0.9816913129761219, "percentage": 76.68, "elapsed_time": "17:49:17", "remaining_time": "5:25:17", "throughput": 657.17, "total_tokens": 42162400} {"current_steps": 30675, "total_steps": 40000, "loss": 0.8594, "lr": 6.4117476560548895e-06, "epoch": 0.9818513539466104, "percentage": 76.69, "elapsed_time": "17:49:19", "remaining_time": "5:25:04", "throughput": 657.26, "total_tokens": 42169344} {"current_steps": 30680, "total_steps": 40000, "loss": 0.6812, "lr": 6.405184118301016e-06, "epoch": 0.9820113949170988, "percentage": 76.7, "elapsed_time": "17:49:21", "remaining_time": "5:24:50", "throughput": 657.35, "total_tokens": 42176128} {"current_steps": 30685, "total_steps": 40000, "loss": 0.6293, "lr": 6.398623448101434e-06, "epoch": 0.9821714358875873, "percentage": 76.71, "elapsed_time": "17:49:22", "remaining_time": "5:24:37", "throughput": 657.44, "total_tokens": 42183136} {"current_steps": 30690, "total_steps": 40000, "loss": 0.4352, "lr": 6.392065646467871e-06, "epoch": 0.9823314768580756, "percentage": 76.72, "elapsed_time": "17:49:24", "remaining_time": "5:24:24", "throughput": 657.52, "total_tokens": 42189600} {"current_steps": 30695, "total_steps": 40000, "loss": 0.5976, "lr": 6.385510714411632e-06, "epoch": 0.9824915178285641, "percentage": 76.74, "elapsed_time": "17:49:26", "remaining_time": "5:24:11", "throughput": 657.61, "total_tokens": 42196352} {"current_steps": 30700, "total_steps": 40000, "loss": 0.7759, "lr": 6.378958652943559e-06, "epoch": 0.9826515587990525, "percentage": 76.75, "elapsed_time": "17:49:28", "remaining_time": "5:23:58", "throughput": 657.69, "total_tokens": 42203024} {"current_steps": 30705, "total_steps": 40000, "loss": 0.9764, "lr": 6.3724094630740776e-06, "epoch": 0.982811599769541, "percentage": 76.76, "elapsed_time": "17:49:29", "remaining_time": "5:23:45", "throughput": 657.78, "total_tokens": 42210000} {"current_steps": 30710, "total_steps": 40000, "loss": 0.6721, "lr": 6.365863145813136e-06, "epoch": 0.9829716407400294, "percentage": 76.78, "elapsed_time": "17:49:31", "remaining_time": "5:23:32", "throughput": 657.87, "total_tokens": 42216816} {"current_steps": 30715, "total_steps": 40000, "loss": 0.5782, "lr": 6.359319702170269e-06, "epoch": 0.9831316817105179, "percentage": 76.79, "elapsed_time": "17:49:33", "remaining_time": "5:23:19", "throughput": 657.96, "total_tokens": 42223632} {"current_steps": 30720, "total_steps": 40000, "loss": 1.0078, "lr": 6.352779133154566e-06, "epoch": 0.9832917226810063, "percentage": 76.8, "elapsed_time": "17:49:35", "remaining_time": "5:23:06", "throughput": 658.05, "total_tokens": 42230592} {"current_steps": 30725, "total_steps": 40000, "loss": 0.6058, "lr": 6.346241439774648e-06, "epoch": 0.9834517636514948, "percentage": 76.81, "elapsed_time": "17:49:36", "remaining_time": "5:22:53", "throughput": 658.14, "total_tokens": 42237216} {"current_steps": 30730, "total_steps": 40000, "loss": 0.7711, "lr": 6.339706623038716e-06, "epoch": 0.9836118046219833, "percentage": 76.83, "elapsed_time": "17:49:38", "remaining_time": "5:22:40", "throughput": 658.23, "total_tokens": 42244112} {"current_steps": 30735, "total_steps": 40000, "loss": 0.4853, "lr": 6.333174683954532e-06, "epoch": 0.9837718455924717, "percentage": 76.84, "elapsed_time": "17:49:40", "remaining_time": "5:22:27", "throughput": 658.32, "total_tokens": 42250944} {"current_steps": 30740, "total_steps": 40000, "loss": 0.7031, "lr": 6.326645623529387e-06, "epoch": 0.9839318865629602, "percentage": 76.85, "elapsed_time": "17:49:42", "remaining_time": "5:22:13", "throughput": 658.41, "total_tokens": 42257952} {"current_steps": 30745, "total_steps": 40000, "loss": 0.5788, "lr": 6.320119442770156e-06, "epoch": 0.9840919275334485, "percentage": 76.86, "elapsed_time": "17:49:43", "remaining_time": "5:22:00", "throughput": 658.49, "total_tokens": 42264592} {"current_steps": 30750, "total_steps": 40000, "loss": 0.5854, "lr": 6.313596142683254e-06, "epoch": 0.984251968503937, "percentage": 76.88, "elapsed_time": "17:49:45", "remaining_time": "5:21:47", "throughput": 658.58, "total_tokens": 42271648} {"current_steps": 30755, "total_steps": 40000, "loss": 0.7497, "lr": 6.307075724274647e-06, "epoch": 0.9844120094744254, "percentage": 76.89, "elapsed_time": "17:49:47", "remaining_time": "5:21:34", "throughput": 658.67, "total_tokens": 42278464} {"current_steps": 30760, "total_steps": 40000, "loss": 0.7636, "lr": 6.300558188549882e-06, "epoch": 0.9845720504449139, "percentage": 76.9, "elapsed_time": "17:49:49", "remaining_time": "5:21:21", "throughput": 658.76, "total_tokens": 42285264} {"current_steps": 30765, "total_steps": 40000, "loss": 1.0916, "lr": 6.29404353651403e-06, "epoch": 0.9847320914154023, "percentage": 76.91, "elapsed_time": "17:49:50", "remaining_time": "5:21:08", "throughput": 658.85, "total_tokens": 42291904} {"current_steps": 30770, "total_steps": 40000, "loss": 0.6307, "lr": 6.287531769171737e-06, "epoch": 0.9848921323858908, "percentage": 76.92, "elapsed_time": "17:49:52", "remaining_time": "5:20:55", "throughput": 658.93, "total_tokens": 42298608} {"current_steps": 30775, "total_steps": 40000, "loss": 0.6759, "lr": 6.2810228875272045e-06, "epoch": 0.9850521733563792, "percentage": 76.94, "elapsed_time": "17:49:54", "remaining_time": "5:20:42", "throughput": 659.02, "total_tokens": 42305184} {"current_steps": 30780, "total_steps": 40000, "loss": 0.9286, "lr": 6.274516892584179e-06, "epoch": 0.9852122143268677, "percentage": 76.95, "elapsed_time": "17:49:55", "remaining_time": "5:20:29", "throughput": 659.11, "total_tokens": 42311968} {"current_steps": 30785, "total_steps": 40000, "loss": 0.7677, "lr": 6.268013785345969e-06, "epoch": 0.9853722552973562, "percentage": 76.96, "elapsed_time": "17:49:57", "remaining_time": "5:20:16", "throughput": 659.2, "total_tokens": 42319008} {"current_steps": 30790, "total_steps": 40000, "loss": 0.4916, "lr": 6.26151356681543e-06, "epoch": 0.9855322962678446, "percentage": 76.98, "elapsed_time": "17:49:59", "remaining_time": "5:20:03", "throughput": 659.28, "total_tokens": 42325696} {"current_steps": 30795, "total_steps": 40000, "loss": 0.7224, "lr": 6.255016237994981e-06, "epoch": 0.985692337238333, "percentage": 76.99, "elapsed_time": "17:50:01", "remaining_time": "5:19:50", "throughput": 659.37, "total_tokens": 42332496} {"current_steps": 30800, "total_steps": 40000, "loss": 0.8694, "lr": 6.248521799886603e-06, "epoch": 0.9858523782088214, "percentage": 77.0, "elapsed_time": "17:50:02", "remaining_time": "5:19:37", "throughput": 659.47, "total_tokens": 42339616} {"current_steps": 30800, "total_steps": 40000, "eval_loss": 0.7325741052627563, "epoch": 0.9858523782088214, "percentage": 77.0, "elapsed_time": "17:55:50", "remaining_time": "5:21:21", "throughput": 655.92, "total_tokens": 42339616} {"current_steps": 30805, "total_steps": 40000, "loss": 0.63, "lr": 6.242030253491798e-06, "epoch": 0.9860124191793099, "percentage": 77.01, "elapsed_time": "17:55:53", "remaining_time": "5:21:08", "throughput": 655.99, "total_tokens": 42346768} {"current_steps": 30810, "total_steps": 40000, "loss": 0.7864, "lr": 6.235541599811656e-06, "epoch": 0.9861724601497983, "percentage": 77.03, "elapsed_time": "17:55:55", "remaining_time": "5:20:55", "throughput": 656.08, "total_tokens": 42353632} {"current_steps": 30815, "total_steps": 40000, "loss": 0.7973, "lr": 6.229055839846814e-06, "epoch": 0.9863325011202868, "percentage": 77.04, "elapsed_time": "17:55:57", "remaining_time": "5:20:42", "throughput": 656.17, "total_tokens": 42360320} {"current_steps": 30820, "total_steps": 40000, "loss": 0.5983, "lr": 6.222572974597455e-06, "epoch": 0.9864925420907752, "percentage": 77.05, "elapsed_time": "17:55:58", "remaining_time": "5:20:29", "throughput": 656.25, "total_tokens": 42366976} {"current_steps": 30825, "total_steps": 40000, "loss": 0.8915, "lr": 6.216093005063306e-06, "epoch": 0.9866525830612637, "percentage": 77.06, "elapsed_time": "17:56:00", "remaining_time": "5:20:16", "throughput": 656.34, "total_tokens": 42373872} {"current_steps": 30830, "total_steps": 40000, "loss": 0.8272, "lr": 6.209615932243678e-06, "epoch": 0.9868126240317522, "percentage": 77.08, "elapsed_time": "17:56:02", "remaining_time": "5:20:03", "throughput": 656.43, "total_tokens": 42380736} {"current_steps": 30835, "total_steps": 40000, "loss": 0.6957, "lr": 6.203141757137399e-06, "epoch": 0.9869726650022406, "percentage": 77.09, "elapsed_time": "17:56:04", "remaining_time": "5:19:50", "throughput": 656.52, "total_tokens": 42387824} {"current_steps": 30840, "total_steps": 40000, "loss": 0.7754, "lr": 6.196670480742886e-06, "epoch": 0.9871327059727291, "percentage": 77.1, "elapsed_time": "17:56:05", "remaining_time": "5:19:37", "throughput": 656.61, "total_tokens": 42394752} {"current_steps": 30845, "total_steps": 40000, "loss": 0.6626, "lr": 6.190202104058074e-06, "epoch": 0.9872927469432174, "percentage": 77.11, "elapsed_time": "17:56:07", "remaining_time": "5:19:24", "throughput": 656.7, "total_tokens": 42401584} {"current_steps": 30850, "total_steps": 40000, "loss": 0.5712, "lr": 6.183736628080475e-06, "epoch": 0.9874527879137059, "percentage": 77.12, "elapsed_time": "17:56:09", "remaining_time": "5:19:11", "throughput": 656.79, "total_tokens": 42408688} {"current_steps": 30855, "total_steps": 40000, "loss": 0.9185, "lr": 6.177274053807155e-06, "epoch": 0.9876128288841943, "percentage": 77.14, "elapsed_time": "17:56:11", "remaining_time": "5:18:57", "throughput": 656.88, "total_tokens": 42415344} {"current_steps": 30860, "total_steps": 40000, "loss": 0.6941, "lr": 6.170814382234713e-06, "epoch": 0.9877728698546828, "percentage": 77.15, "elapsed_time": "17:56:12", "remaining_time": "5:18:44", "throughput": 656.97, "total_tokens": 42422320} {"current_steps": 30865, "total_steps": 40000, "loss": 0.9203, "lr": 6.16435761435932e-06, "epoch": 0.9879329108251712, "percentage": 77.16, "elapsed_time": "17:56:14", "remaining_time": "5:18:31", "throughput": 657.06, "total_tokens": 42429248} {"current_steps": 30870, "total_steps": 40000, "loss": 0.6983, "lr": 6.157903751176681e-06, "epoch": 0.9880929517956597, "percentage": 77.18, "elapsed_time": "17:56:16", "remaining_time": "5:18:18", "throughput": 657.15, "total_tokens": 42436016} {"current_steps": 30875, "total_steps": 40000, "loss": 0.5852, "lr": 6.151452793682066e-06, "epoch": 0.9882529927661481, "percentage": 77.19, "elapsed_time": "17:56:18", "remaining_time": "5:18:05", "throughput": 657.23, "total_tokens": 42442800} {"current_steps": 30880, "total_steps": 40000, "loss": 0.7237, "lr": 6.145004742870305e-06, "epoch": 0.9884130337366366, "percentage": 77.2, "elapsed_time": "17:56:19", "remaining_time": "5:17:52", "throughput": 657.33, "total_tokens": 42450064} {"current_steps": 30885, "total_steps": 40000, "loss": 0.8488, "lr": 6.138559599735752e-06, "epoch": 0.9885730747071251, "percentage": 77.21, "elapsed_time": "17:56:21", "remaining_time": "5:17:39", "throughput": 657.41, "total_tokens": 42456736} {"current_steps": 30890, "total_steps": 40000, "loss": 0.6759, "lr": 6.132117365272344e-06, "epoch": 0.9887331156776135, "percentage": 77.22, "elapsed_time": "17:56:23", "remaining_time": "5:17:26", "throughput": 657.5, "total_tokens": 42463712} {"current_steps": 30895, "total_steps": 40000, "loss": 0.6201, "lr": 6.125678040473545e-06, "epoch": 0.988893156648102, "percentage": 77.24, "elapsed_time": "17:56:24", "remaining_time": "5:17:13", "throughput": 657.59, "total_tokens": 42470688} {"current_steps": 30900, "total_steps": 40000, "loss": 0.6035, "lr": 6.1192416263323755e-06, "epoch": 0.9890531976185903, "percentage": 77.25, "elapsed_time": "17:56:26", "remaining_time": "5:17:00", "throughput": 657.69, "total_tokens": 42477760} {"current_steps": 30905, "total_steps": 40000, "loss": 0.8175, "lr": 6.112808123841424e-06, "epoch": 0.9892132385890788, "percentage": 77.26, "elapsed_time": "17:56:28", "remaining_time": "5:16:47", "throughput": 657.77, "total_tokens": 42484640} {"current_steps": 30910, "total_steps": 40000, "loss": 0.6813, "lr": 6.106377533992805e-06, "epoch": 0.9893732795595672, "percentage": 77.28, "elapsed_time": "17:56:30", "remaining_time": "5:16:34", "throughput": 657.86, "total_tokens": 42491504} {"current_steps": 30915, "total_steps": 40000, "loss": 0.683, "lr": 6.099949857778204e-06, "epoch": 0.9895333205300557, "percentage": 77.29, "elapsed_time": "17:56:31", "remaining_time": "5:16:21", "throughput": 657.95, "total_tokens": 42498464} {"current_steps": 30920, "total_steps": 40000, "loss": 0.7051, "lr": 6.093525096188852e-06, "epoch": 0.9896933615005441, "percentage": 77.3, "elapsed_time": "17:56:33", "remaining_time": "5:16:08", "throughput": 658.04, "total_tokens": 42505280} {"current_steps": 30925, "total_steps": 40000, "loss": 0.7939, "lr": 6.087103250215518e-06, "epoch": 0.9898534024710326, "percentage": 77.31, "elapsed_time": "17:56:35", "remaining_time": "5:15:55", "throughput": 658.13, "total_tokens": 42512016} {"current_steps": 30930, "total_steps": 40000, "loss": 0.6932, "lr": 6.080684320848537e-06, "epoch": 0.990013443441521, "percentage": 77.33, "elapsed_time": "17:56:37", "remaining_time": "5:15:42", "throughput": 658.22, "total_tokens": 42518928} {"current_steps": 30935, "total_steps": 40000, "loss": 0.8382, "lr": 6.074268309077794e-06, "epoch": 0.9901734844120095, "percentage": 77.34, "elapsed_time": "17:56:38", "remaining_time": "5:15:29", "throughput": 658.31, "total_tokens": 42526032} {"current_steps": 30940, "total_steps": 40000, "loss": 0.8387, "lr": 6.067855215892709e-06, "epoch": 0.990333525382498, "percentage": 77.35, "elapsed_time": "17:56:40", "remaining_time": "5:15:16", "throughput": 658.4, "total_tokens": 42532976} {"current_steps": 30945, "total_steps": 40000, "loss": 0.6876, "lr": 6.061445042282271e-06, "epoch": 0.9904935663529864, "percentage": 77.36, "elapsed_time": "17:56:42", "remaining_time": "5:15:03", "throughput": 658.49, "total_tokens": 42539920} {"current_steps": 30950, "total_steps": 40000, "loss": 0.7285, "lr": 6.055037789234999e-06, "epoch": 0.9906536073234748, "percentage": 77.38, "elapsed_time": "17:56:44", "remaining_time": "5:14:50", "throughput": 658.58, "total_tokens": 42547136} {"current_steps": 30955, "total_steps": 40000, "loss": 0.6659, "lr": 6.048633457738975e-06, "epoch": 0.9908136482939632, "percentage": 77.39, "elapsed_time": "17:56:45", "remaining_time": "5:14:37", "throughput": 658.68, "total_tokens": 42554256} {"current_steps": 30960, "total_steps": 40000, "loss": 0.8434, "lr": 6.042232048781837e-06, "epoch": 0.9909736892644517, "percentage": 77.4, "elapsed_time": "17:56:47", "remaining_time": "5:14:24", "throughput": 658.76, "total_tokens": 42561104} {"current_steps": 30965, "total_steps": 40000, "loss": 0.7915, "lr": 6.035833563350757e-06, "epoch": 0.9911337302349401, "percentage": 77.41, "elapsed_time": "17:56:49", "remaining_time": "5:14:11", "throughput": 658.85, "total_tokens": 42567984} {"current_steps": 30970, "total_steps": 40000, "loss": 0.6706, "lr": 6.0294380024324525e-06, "epoch": 0.9912937712054286, "percentage": 77.42, "elapsed_time": "17:56:51", "remaining_time": "5:13:58", "throughput": 658.94, "total_tokens": 42574944} {"current_steps": 30975, "total_steps": 40000, "loss": 0.6077, "lr": 6.023045367013213e-06, "epoch": 0.991453812175917, "percentage": 77.44, "elapsed_time": "17:56:52", "remaining_time": "5:13:45", "throughput": 659.03, "total_tokens": 42581600} {"current_steps": 30980, "total_steps": 40000, "loss": 0.8107, "lr": 6.016655658078851e-06, "epoch": 0.9916138531464055, "percentage": 77.45, "elapsed_time": "17:56:54", "remaining_time": "5:13:32", "throughput": 659.11, "total_tokens": 42588176} {"current_steps": 30985, "total_steps": 40000, "loss": 0.7128, "lr": 6.010268876614753e-06, "epoch": 0.9917738941168939, "percentage": 77.46, "elapsed_time": "17:56:56", "remaining_time": "5:13:19", "throughput": 659.2, "total_tokens": 42595216} {"current_steps": 30990, "total_steps": 40000, "loss": 0.7944, "lr": 6.0038850236058266e-06, "epoch": 0.9919339350873824, "percentage": 77.48, "elapsed_time": "17:56:57", "remaining_time": "5:13:06", "throughput": 659.29, "total_tokens": 42602160} {"current_steps": 30995, "total_steps": 40000, "loss": 0.6637, "lr": 5.997504100036549e-06, "epoch": 0.9920939760578709, "percentage": 77.49, "elapsed_time": "17:56:59", "remaining_time": "5:12:54", "throughput": 659.39, "total_tokens": 42609520} {"current_steps": 31000, "total_steps": 40000, "loss": 0.9029, "lr": 5.991126106890949e-06, "epoch": 0.9922540170283592, "percentage": 77.5, "elapsed_time": "17:57:01", "remaining_time": "5:12:41", "throughput": 659.48, "total_tokens": 42616352} {"current_steps": 31000, "total_steps": 40000, "eval_loss": 0.7317811846733093, "epoch": 0.9922540170283592, "percentage": 77.5, "elapsed_time": "18:02:48", "remaining_time": "5:14:21", "throughput": 655.95, "total_tokens": 42616352} {"current_steps": 31005, "total_steps": 40000, "loss": 0.77, "lr": 5.984751045152576e-06, "epoch": 0.9924140579988477, "percentage": 77.51, "elapsed_time": "18:02:52", "remaining_time": "5:14:09", "throughput": 656.03, "total_tokens": 42623760} {"current_steps": 31010, "total_steps": 40000, "loss": 0.7495, "lr": 5.978378915804553e-06, "epoch": 0.9925740989693361, "percentage": 77.53, "elapsed_time": "18:02:54", "remaining_time": "5:13:56", "throughput": 656.12, "total_tokens": 42631152} {"current_steps": 31015, "total_steps": 40000, "loss": 0.5816, "lr": 5.972009719829547e-06, "epoch": 0.9927341399398246, "percentage": 77.54, "elapsed_time": "18:02:56", "remaining_time": "5:13:43", "throughput": 656.21, "total_tokens": 42638128} {"current_steps": 31020, "total_steps": 40000, "loss": 0.8625, "lr": 5.965643458209755e-06, "epoch": 0.992894180910313, "percentage": 77.55, "elapsed_time": "18:02:58", "remaining_time": "5:13:30", "throughput": 656.3, "total_tokens": 42645248} {"current_steps": 31025, "total_steps": 40000, "loss": 0.6279, "lr": 5.95928013192695e-06, "epoch": 0.9930542218808015, "percentage": 77.56, "elapsed_time": "18:02:59", "remaining_time": "5:13:17", "throughput": 656.39, "total_tokens": 42651920} {"current_steps": 31030, "total_steps": 40000, "loss": 0.576, "lr": 5.952919741962423e-06, "epoch": 0.9932142628512899, "percentage": 77.58, "elapsed_time": "18:03:01", "remaining_time": "5:13:04", "throughput": 656.48, "total_tokens": 42658720} {"current_steps": 31035, "total_steps": 40000, "loss": 0.8886, "lr": 5.946562289297042e-06, "epoch": 0.9933743038217784, "percentage": 77.59, "elapsed_time": "18:03:03", "remaining_time": "5:12:51", "throughput": 656.56, "total_tokens": 42665600} {"current_steps": 31040, "total_steps": 40000, "loss": 0.7299, "lr": 5.9402077749111855e-06, "epoch": 0.9935343447922668, "percentage": 77.6, "elapsed_time": "18:03:04", "remaining_time": "5:12:38", "throughput": 656.65, "total_tokens": 42672608} {"current_steps": 31045, "total_steps": 40000, "loss": 0.6794, "lr": 5.933856199784821e-06, "epoch": 0.9936943857627553, "percentage": 77.61, "elapsed_time": "18:03:06", "remaining_time": "5:12:25", "throughput": 656.74, "total_tokens": 42679680} {"current_steps": 31050, "total_steps": 40000, "loss": 0.6112, "lr": 5.927507564897419e-06, "epoch": 0.9938544267332438, "percentage": 77.62, "elapsed_time": "18:03:08", "remaining_time": "5:12:12", "throughput": 656.84, "total_tokens": 42686848} {"current_steps": 31055, "total_steps": 40000, "loss": 0.6534, "lr": 5.9211618712280395e-06, "epoch": 0.9940144677037321, "percentage": 77.64, "elapsed_time": "18:03:10", "remaining_time": "5:11:59", "throughput": 656.92, "total_tokens": 42693472} {"current_steps": 31060, "total_steps": 40000, "loss": 0.6174, "lr": 5.914819119755255e-06, "epoch": 0.9941745086742206, "percentage": 77.65, "elapsed_time": "18:03:11", "remaining_time": "5:11:46", "throughput": 657.01, "total_tokens": 42700064} {"current_steps": 31065, "total_steps": 40000, "loss": 0.6543, "lr": 5.908479311457205e-06, "epoch": 0.994334549644709, "percentage": 77.66, "elapsed_time": "18:03:13", "remaining_time": "5:11:33", "throughput": 657.1, "total_tokens": 42707376} {"current_steps": 31070, "total_steps": 40000, "loss": 0.5557, "lr": 5.902142447311559e-06, "epoch": 0.9944945906151975, "percentage": 77.68, "elapsed_time": "18:03:15", "remaining_time": "5:11:20", "throughput": 657.19, "total_tokens": 42714400} {"current_steps": 31075, "total_steps": 40000, "loss": 0.7255, "lr": 5.895808528295546e-06, "epoch": 0.9946546315856859, "percentage": 77.69, "elapsed_time": "18:03:17", "remaining_time": "5:11:07", "throughput": 657.28, "total_tokens": 42721088} {"current_steps": 31080, "total_steps": 40000, "loss": 0.6546, "lr": 5.889477555385941e-06, "epoch": 0.9948146725561744, "percentage": 77.7, "elapsed_time": "18:03:18", "remaining_time": "5:10:54", "throughput": 657.36, "total_tokens": 42727776} {"current_steps": 31085, "total_steps": 40000, "loss": 0.6291, "lr": 5.883149529559051e-06, "epoch": 0.9949747135266628, "percentage": 77.71, "elapsed_time": "18:03:20", "remaining_time": "5:10:41", "throughput": 657.45, "total_tokens": 42734912} {"current_steps": 31090, "total_steps": 40000, "loss": 0.9527, "lr": 5.876824451790738e-06, "epoch": 0.9951347544971513, "percentage": 77.72, "elapsed_time": "18:03:22", "remaining_time": "5:10:28", "throughput": 657.54, "total_tokens": 42741840} {"current_steps": 31095, "total_steps": 40000, "loss": 0.5646, "lr": 5.87050232305642e-06, "epoch": 0.9952947954676398, "percentage": 77.74, "elapsed_time": "18:03:24", "remaining_time": "5:10:15", "throughput": 657.63, "total_tokens": 42748560} {"current_steps": 31100, "total_steps": 40000, "loss": 0.7237, "lr": 5.864183144331034e-06, "epoch": 0.9954548364381282, "percentage": 77.75, "elapsed_time": "18:03:25", "remaining_time": "5:10:02", "throughput": 657.72, "total_tokens": 42755616} {"current_steps": 31105, "total_steps": 40000, "loss": 0.5208, "lr": 5.857866916589089e-06, "epoch": 0.9956148774086166, "percentage": 77.76, "elapsed_time": "18:03:27", "remaining_time": "5:09:49", "throughput": 657.82, "total_tokens": 42763024} {"current_steps": 31110, "total_steps": 40000, "loss": 0.7649, "lr": 5.8515536408046216e-06, "epoch": 0.995774918379105, "percentage": 77.78, "elapsed_time": "18:03:29", "remaining_time": "5:09:37", "throughput": 657.9, "total_tokens": 42769456} {"current_steps": 31115, "total_steps": 40000, "loss": 0.6229, "lr": 5.845243317951208e-06, "epoch": 0.9959349593495935, "percentage": 77.79, "elapsed_time": "18:03:30", "remaining_time": "5:09:24", "throughput": 657.99, "total_tokens": 42776672} {"current_steps": 31120, "total_steps": 40000, "loss": 0.859, "lr": 5.838935949001997e-06, "epoch": 0.9960950003200819, "percentage": 77.8, "elapsed_time": "18:03:32", "remaining_time": "5:09:11", "throughput": 658.08, "total_tokens": 42783872} {"current_steps": 31125, "total_steps": 40000, "loss": 0.8373, "lr": 5.8326315349296476e-06, "epoch": 0.9962550412905704, "percentage": 77.81, "elapsed_time": "18:03:34", "remaining_time": "5:08:58", "throughput": 658.17, "total_tokens": 42790736} {"current_steps": 31130, "total_steps": 40000, "loss": 0.8878, "lr": 5.826330076706396e-06, "epoch": 0.9964150822610588, "percentage": 77.83, "elapsed_time": "18:03:36", "remaining_time": "5:08:45", "throughput": 658.26, "total_tokens": 42797536} {"current_steps": 31135, "total_steps": 40000, "loss": 0.6254, "lr": 5.820031575303988e-06, "epoch": 0.9965751232315473, "percentage": 77.84, "elapsed_time": "18:03:37", "remaining_time": "5:08:32", "throughput": 658.35, "total_tokens": 42804448} {"current_steps": 31140, "total_steps": 40000, "loss": 0.7428, "lr": 5.813736031693745e-06, "epoch": 0.9967351642020357, "percentage": 77.85, "elapsed_time": "18:03:39", "remaining_time": "5:08:19", "throughput": 658.44, "total_tokens": 42811280} {"current_steps": 31145, "total_steps": 40000, "loss": 0.8149, "lr": 5.807443446846522e-06, "epoch": 0.9968952051725242, "percentage": 77.86, "elapsed_time": "18:03:41", "remaining_time": "5:08:06", "throughput": 658.52, "total_tokens": 42818096} {"current_steps": 31150, "total_steps": 40000, "loss": 0.6548, "lr": 5.801153821732699e-06, "epoch": 0.9970552461430127, "percentage": 77.88, "elapsed_time": "18:03:43", "remaining_time": "5:07:53", "throughput": 658.61, "total_tokens": 42824640} {"current_steps": 31155, "total_steps": 40000, "loss": 0.7016, "lr": 5.794867157322229e-06, "epoch": 0.997215287113501, "percentage": 77.89, "elapsed_time": "18:03:44", "remaining_time": "5:07:40", "throughput": 658.71, "total_tokens": 42832304} {"current_steps": 31160, "total_steps": 40000, "loss": 0.8107, "lr": 5.788583454584593e-06, "epoch": 0.9973753280839895, "percentage": 77.9, "elapsed_time": "18:03:46", "remaining_time": "5:07:27", "throughput": 658.79, "total_tokens": 42839056} {"current_steps": 31165, "total_steps": 40000, "loss": 0.6095, "lr": 5.7823027144888075e-06, "epoch": 0.9975353690544779, "percentage": 77.91, "elapsed_time": "18:03:48", "remaining_time": "5:07:14", "throughput": 658.88, "total_tokens": 42845728} {"current_steps": 31170, "total_steps": 40000, "loss": 0.7879, "lr": 5.776024938003455e-06, "epoch": 0.9976954100249664, "percentage": 77.92, "elapsed_time": "18:03:50", "remaining_time": "5:07:02", "throughput": 658.96, "total_tokens": 42852448} {"current_steps": 31175, "total_steps": 40000, "loss": 0.8199, "lr": 5.7697501260966345e-06, "epoch": 0.9978554509954548, "percentage": 77.94, "elapsed_time": "18:03:51", "remaining_time": "5:06:49", "throughput": 659.05, "total_tokens": 42859136} {"current_steps": 31180, "total_steps": 40000, "loss": 0.7766, "lr": 5.7634782797360145e-06, "epoch": 0.9980154919659433, "percentage": 77.95, "elapsed_time": "18:03:53", "remaining_time": "5:06:36", "throughput": 659.13, "total_tokens": 42865808} {"current_steps": 31185, "total_steps": 40000, "loss": 0.8407, "lr": 5.757209399888777e-06, "epoch": 0.9981755329364317, "percentage": 77.96, "elapsed_time": "18:03:55", "remaining_time": "5:06:23", "throughput": 659.22, "total_tokens": 42872816} {"current_steps": 31190, "total_steps": 40000, "loss": 0.7676, "lr": 5.750943487521679e-06, "epoch": 0.9983355739069202, "percentage": 77.98, "elapsed_time": "18:03:57", "remaining_time": "5:06:10", "throughput": 659.31, "total_tokens": 42879584} {"current_steps": 31195, "total_steps": 40000, "loss": 0.6968, "lr": 5.744680543600986e-06, "epoch": 0.9984956148774086, "percentage": 77.99, "elapsed_time": "18:03:58", "remaining_time": "5:05:57", "throughput": 659.4, "total_tokens": 42886336} {"current_steps": 31200, "total_steps": 40000, "loss": 0.8713, "lr": 5.738420569092537e-06, "epoch": 0.9986556558478971, "percentage": 78.0, "elapsed_time": "18:04:00", "remaining_time": "5:05:44", "throughput": 659.48, "total_tokens": 42892688} {"current_steps": 31200, "total_steps": 40000, "eval_loss": 0.7324094176292419, "epoch": 0.9986556558478971, "percentage": 78.0, "elapsed_time": "18:09:49", "remaining_time": "5:07:23", "throughput": 655.96, "total_tokens": 42892688} {"current_steps": 31205, "total_steps": 40000, "loss": 0.6737, "lr": 5.732163564961684e-06, "epoch": 0.9988156968183856, "percentage": 78.01, "elapsed_time": "18:09:52", "remaining_time": "5:07:10", "throughput": 656.03, "total_tokens": 42899840} {"current_steps": 31210, "total_steps": 40000, "loss": 0.5796, "lr": 5.725909532173354e-06, "epoch": 0.9989757377888739, "percentage": 78.03, "elapsed_time": "18:09:54", "remaining_time": "5:06:57", "throughput": 656.12, "total_tokens": 42906528} {"current_steps": 31215, "total_steps": 40000, "loss": 0.7576, "lr": 5.719658471691977e-06, "epoch": 0.9991357787593624, "percentage": 78.04, "elapsed_time": "18:09:56", "remaining_time": "5:06:44", "throughput": 656.22, "total_tokens": 42913968} {"current_steps": 31220, "total_steps": 40000, "loss": 0.7411, "lr": 5.71341038448156e-06, "epoch": 0.9992958197298508, "percentage": 78.05, "elapsed_time": "18:09:57", "remaining_time": "5:06:31", "throughput": 656.31, "total_tokens": 42921136} {"current_steps": 31225, "total_steps": 40000, "loss": 0.6988, "lr": 5.707165271505635e-06, "epoch": 0.9994558607003393, "percentage": 78.06, "elapsed_time": "18:09:59", "remaining_time": "5:06:18", "throughput": 656.4, "total_tokens": 42928144} {"current_steps": 31230, "total_steps": 40000, "loss": 0.7323, "lr": 5.700923133727271e-06, "epoch": 0.9996159016708277, "percentage": 78.08, "elapsed_time": "18:10:01", "remaining_time": "5:06:06", "throughput": 656.5, "total_tokens": 42935728} {"current_steps": 31235, "total_steps": 40000, "loss": 0.7157, "lr": 5.694683972109083e-06, "epoch": 0.9997759426413162, "percentage": 78.09, "elapsed_time": "18:10:03", "remaining_time": "5:05:53", "throughput": 656.58, "total_tokens": 42942384} {"current_steps": 31240, "total_steps": 40000, "loss": 0.9405, "lr": 5.688447787613241e-06, "epoch": 0.9999359836118046, "percentage": 78.1, "elapsed_time": "18:10:04", "remaining_time": "5:05:40", "throughput": 656.67, "total_tokens": 42949504} {"current_steps": 31245, "total_steps": 40000, "loss": 0.7042, "lr": 5.6822145812014285e-06, "epoch": 1.000096024582293, "percentage": 78.11, "elapsed_time": "18:10:07", "remaining_time": "5:05:27", "throughput": 656.75, "total_tokens": 42956000} {"current_steps": 31250, "total_steps": 40000, "loss": 0.6061, "lr": 5.675984353834896e-06, "epoch": 1.0002560655527815, "percentage": 78.12, "elapsed_time": "18:10:08", "remaining_time": "5:05:14", "throughput": 656.84, "total_tokens": 42962928} {"current_steps": 31255, "total_steps": 40000, "loss": 0.8612, "lr": 5.66975710647441e-06, "epoch": 1.00041610652327, "percentage": 78.14, "elapsed_time": "18:10:10", "remaining_time": "5:05:01", "throughput": 656.93, "total_tokens": 42969872} {"current_steps": 31260, "total_steps": 40000, "loss": 0.5893, "lr": 5.663532840080304e-06, "epoch": 1.0005761474937584, "percentage": 78.15, "elapsed_time": "18:10:12", "remaining_time": "5:04:48", "throughput": 657.01, "total_tokens": 42976592} {"current_steps": 31265, "total_steps": 40000, "loss": 0.7568, "lr": 5.6573115556124325e-06, "epoch": 1.000736188464247, "percentage": 78.16, "elapsed_time": "18:10:14", "remaining_time": "5:04:35", "throughput": 657.1, "total_tokens": 42983584} {"current_steps": 31270, "total_steps": 40000, "loss": 0.679, "lr": 5.651093254030185e-06, "epoch": 1.0008962294347352, "percentage": 78.17, "elapsed_time": "18:10:15", "remaining_time": "5:04:22", "throughput": 657.18, "total_tokens": 42990224} {"current_steps": 31275, "total_steps": 40000, "loss": 0.6102, "lr": 5.644877936292514e-06, "epoch": 1.0010562704052237, "percentage": 78.19, "elapsed_time": "18:10:17", "remaining_time": "5:04:09", "throughput": 657.27, "total_tokens": 42997280} {"current_steps": 31280, "total_steps": 40000, "loss": 0.5496, "lr": 5.638665603357901e-06, "epoch": 1.0012163113757122, "percentage": 78.2, "elapsed_time": "18:10:19", "remaining_time": "5:03:57", "throughput": 657.36, "total_tokens": 43004112} {"current_steps": 31285, "total_steps": 40000, "loss": 0.7232, "lr": 5.632456256184357e-06, "epoch": 1.0013763523462007, "percentage": 78.21, "elapsed_time": "18:10:20", "remaining_time": "5:03:44", "throughput": 657.45, "total_tokens": 43011296} {"current_steps": 31290, "total_steps": 40000, "loss": 0.8179, "lr": 5.626249895729452e-06, "epoch": 1.001536393316689, "percentage": 78.22, "elapsed_time": "18:10:22", "remaining_time": "5:03:31", "throughput": 657.55, "total_tokens": 43018496} {"current_steps": 31295, "total_steps": 40000, "loss": 0.7173, "lr": 5.620046522950273e-06, "epoch": 1.0016964342871775, "percentage": 78.24, "elapsed_time": "18:10:24", "remaining_time": "5:03:18", "throughput": 657.63, "total_tokens": 43025104} {"current_steps": 31300, "total_steps": 40000, "loss": 0.846, "lr": 5.613846138803464e-06, "epoch": 1.001856475257666, "percentage": 78.25, "elapsed_time": "18:10:26", "remaining_time": "5:03:05", "throughput": 657.72, "total_tokens": 43031856} {"current_steps": 31305, "total_steps": 40000, "loss": 0.6507, "lr": 5.607648744245206e-06, "epoch": 1.0020165162281545, "percentage": 78.26, "elapsed_time": "18:10:27", "remaining_time": "5:02:52", "throughput": 657.8, "total_tokens": 43038464} {"current_steps": 31310, "total_steps": 40000, "loss": 0.6603, "lr": 5.601454340231207e-06, "epoch": 1.002176557198643, "percentage": 78.27, "elapsed_time": "18:10:29", "remaining_time": "5:02:39", "throughput": 657.88, "total_tokens": 43045168} {"current_steps": 31315, "total_steps": 40000, "loss": 0.6442, "lr": 5.595262927716724e-06, "epoch": 1.0023365981691312, "percentage": 78.29, "elapsed_time": "18:10:31", "remaining_time": "5:02:26", "throughput": 657.97, "total_tokens": 43052160} {"current_steps": 31320, "total_steps": 40000, "loss": 0.8804, "lr": 5.589074507656561e-06, "epoch": 1.0024966391396197, "percentage": 78.3, "elapsed_time": "18:10:33", "remaining_time": "5:02:14", "throughput": 658.06, "total_tokens": 43059056} {"current_steps": 31325, "total_steps": 40000, "loss": 0.64, "lr": 5.582889081005044e-06, "epoch": 1.0026566801101082, "percentage": 78.31, "elapsed_time": "18:10:34", "remaining_time": "5:02:01", "throughput": 658.15, "total_tokens": 43065808} {"current_steps": 31330, "total_steps": 40000, "loss": 0.6738, "lr": 5.5767066487160316e-06, "epoch": 1.0028167210805967, "percentage": 78.33, "elapsed_time": "18:10:36", "remaining_time": "5:01:48", "throughput": 658.23, "total_tokens": 43072304} {"current_steps": 31335, "total_steps": 40000, "loss": 0.6593, "lr": 5.570527211742949e-06, "epoch": 1.002976762051085, "percentage": 78.34, "elapsed_time": "18:10:38", "remaining_time": "5:01:35", "throughput": 658.31, "total_tokens": 43078976} {"current_steps": 31340, "total_steps": 40000, "loss": 0.6827, "lr": 5.564350771038731e-06, "epoch": 1.0031368030215735, "percentage": 78.35, "elapsed_time": "18:10:40", "remaining_time": "5:01:22", "throughput": 658.4, "total_tokens": 43086032} {"current_steps": 31345, "total_steps": 40000, "loss": 0.7978, "lr": 5.558177327555875e-06, "epoch": 1.003296843992062, "percentage": 78.36, "elapsed_time": "18:10:41", "remaining_time": "5:01:09", "throughput": 658.49, "total_tokens": 43092496} {"current_steps": 31350, "total_steps": 40000, "loss": 0.7022, "lr": 5.552006882246388e-06, "epoch": 1.0034568849625505, "percentage": 78.38, "elapsed_time": "18:10:43", "remaining_time": "5:00:56", "throughput": 658.57, "total_tokens": 43099088} {"current_steps": 31355, "total_steps": 40000, "loss": 0.8211, "lr": 5.545839436061839e-06, "epoch": 1.0036169259330388, "percentage": 78.39, "elapsed_time": "18:10:45", "remaining_time": "5:00:44", "throughput": 658.66, "total_tokens": 43106128} {"current_steps": 31360, "total_steps": 40000, "loss": 0.8007, "lr": 5.539674989953331e-06, "epoch": 1.0037769669035272, "percentage": 78.4, "elapsed_time": "18:10:47", "remaining_time": "5:00:31", "throughput": 658.75, "total_tokens": 43113056} {"current_steps": 31365, "total_steps": 40000, "loss": 0.6335, "lr": 5.533513544871488e-06, "epoch": 1.0039370078740157, "percentage": 78.41, "elapsed_time": "18:10:48", "remaining_time": "5:00:18", "throughput": 658.84, "total_tokens": 43120304} {"current_steps": 31370, "total_steps": 40000, "loss": 0.654, "lr": 5.527355101766493e-06, "epoch": 1.0040970488445042, "percentage": 78.42, "elapsed_time": "18:10:50", "remaining_time": "5:00:05", "throughput": 658.92, "total_tokens": 43126928} {"current_steps": 31375, "total_steps": 40000, "loss": 0.7038, "lr": 5.521199661588044e-06, "epoch": 1.0042570898149927, "percentage": 78.44, "elapsed_time": "18:10:52", "remaining_time": "4:59:52", "throughput": 659.01, "total_tokens": 43133408} {"current_steps": 31380, "total_steps": 40000, "loss": 0.6023, "lr": 5.5150472252853944e-06, "epoch": 1.004417130785481, "percentage": 78.45, "elapsed_time": "18:10:54", "remaining_time": "4:59:40", "throughput": 659.09, "total_tokens": 43140176} {"current_steps": 31385, "total_steps": 40000, "loss": 0.5653, "lr": 5.50889779380733e-06, "epoch": 1.0045771717559695, "percentage": 78.46, "elapsed_time": "18:10:55", "remaining_time": "4:59:27", "throughput": 659.17, "total_tokens": 43146640} {"current_steps": 31390, "total_steps": 40000, "loss": 0.6699, "lr": 5.5027513681021605e-06, "epoch": 1.004737212726458, "percentage": 78.47, "elapsed_time": "18:10:57", "remaining_time": "4:59:14", "throughput": 659.26, "total_tokens": 43153184} {"current_steps": 31395, "total_steps": 40000, "loss": 0.5214, "lr": 5.4966079491177545e-06, "epoch": 1.0048972536969465, "percentage": 78.49, "elapsed_time": "18:10:59", "remaining_time": "4:59:01", "throughput": 659.34, "total_tokens": 43160096} {"current_steps": 31400, "total_steps": 40000, "loss": 0.4775, "lr": 5.490467537801491e-06, "epoch": 1.0050572946674348, "percentage": 78.5, "elapsed_time": "18:11:00", "remaining_time": "4:58:48", "throughput": 659.44, "total_tokens": 43167792} {"current_steps": 31400, "total_steps": 40000, "eval_loss": 0.7323500514030457, "epoch": 1.0050572946674348, "percentage": 78.5, "elapsed_time": "18:16:48", "remaining_time": "5:00:24", "throughput": 655.96, "total_tokens": 43167792} {"current_steps": 31405, "total_steps": 40000, "loss": 0.7609, "lr": 5.484330135100313e-06, "epoch": 1.0052173356379233, "percentage": 78.51, "elapsed_time": "18:16:52", "remaining_time": "5:00:11", "throughput": 656.04, "total_tokens": 43175232} {"current_steps": 31410, "total_steps": 40000, "loss": 0.6294, "lr": 5.4781957419606785e-06, "epoch": 1.0053773766084118, "percentage": 78.53, "elapsed_time": "18:16:53", "remaining_time": "4:59:58", "throughput": 656.12, "total_tokens": 43181984} {"current_steps": 31415, "total_steps": 40000, "loss": 0.8306, "lr": 5.472064359328577e-06, "epoch": 1.0055374175789002, "percentage": 78.54, "elapsed_time": "18:16:55", "remaining_time": "4:59:45", "throughput": 656.22, "total_tokens": 43189552} {"current_steps": 31420, "total_steps": 40000, "loss": 0.674, "lr": 5.4659359881495565e-06, "epoch": 1.0056974585493887, "percentage": 78.55, "elapsed_time": "18:16:57", "remaining_time": "4:59:33", "throughput": 656.31, "total_tokens": 43196864} {"current_steps": 31425, "total_steps": 40000, "loss": 0.7242, "lr": 5.4598106293686916e-06, "epoch": 1.005857499519877, "percentage": 78.56, "elapsed_time": "18:16:59", "remaining_time": "4:59:20", "throughput": 656.4, "total_tokens": 43203616} {"current_steps": 31430, "total_steps": 40000, "loss": 0.5277, "lr": 5.45368828393058e-06, "epoch": 1.0060175404903655, "percentage": 78.57, "elapsed_time": "18:17:00", "remaining_time": "4:59:07", "throughput": 656.48, "total_tokens": 43210336} {"current_steps": 31435, "total_steps": 40000, "loss": 0.7123, "lr": 5.44756895277937e-06, "epoch": 1.006177581460854, "percentage": 78.59, "elapsed_time": "18:17:02", "remaining_time": "4:58:54", "throughput": 656.57, "total_tokens": 43217056} {"current_steps": 31440, "total_steps": 40000, "loss": 0.707, "lr": 5.441452636858746e-06, "epoch": 1.0063376224313425, "percentage": 78.6, "elapsed_time": "18:17:04", "remaining_time": "4:58:41", "throughput": 656.65, "total_tokens": 43223824} {"current_steps": 31445, "total_steps": 40000, "loss": 0.5854, "lr": 5.435339337111905e-06, "epoch": 1.0064976634018308, "percentage": 78.61, "elapsed_time": "18:17:06", "remaining_time": "4:58:28", "throughput": 656.74, "total_tokens": 43230768} {"current_steps": 31450, "total_steps": 40000, "loss": 0.6401, "lr": 5.42922905448161e-06, "epoch": 1.0066577043723193, "percentage": 78.62, "elapsed_time": "18:17:07", "remaining_time": "4:58:15", "throughput": 656.83, "total_tokens": 43237632} {"current_steps": 31455, "total_steps": 40000, "loss": 0.7281, "lr": 5.423121789910129e-06, "epoch": 1.0068177453428078, "percentage": 78.64, "elapsed_time": "18:17:09", "remaining_time": "4:58:03", "throughput": 656.92, "total_tokens": 43244624} {"current_steps": 31460, "total_steps": 40000, "loss": 0.7376, "lr": 5.417017544339287e-06, "epoch": 1.0069777863132963, "percentage": 78.65, "elapsed_time": "18:17:11", "remaining_time": "4:57:50", "throughput": 657.01, "total_tokens": 43251984} {"current_steps": 31465, "total_steps": 40000, "loss": 0.7881, "lr": 5.410916318710443e-06, "epoch": 1.0071378272837848, "percentage": 78.66, "elapsed_time": "18:17:12", "remaining_time": "4:57:37", "throughput": 657.1, "total_tokens": 43258992} {"current_steps": 31470, "total_steps": 40000, "loss": 0.797, "lr": 5.404818113964466e-06, "epoch": 1.007297868254273, "percentage": 78.67, "elapsed_time": "18:17:14", "remaining_time": "4:57:24", "throughput": 657.19, "total_tokens": 43266128} {"current_steps": 31475, "total_steps": 40000, "loss": 0.6062, "lr": 5.398722931041792e-06, "epoch": 1.0074579092247615, "percentage": 78.69, "elapsed_time": "18:17:16", "remaining_time": "4:57:11", "throughput": 657.28, "total_tokens": 43272928} {"current_steps": 31480, "total_steps": 40000, "loss": 0.6162, "lr": 5.392630770882367e-06, "epoch": 1.00761795019525, "percentage": 78.7, "elapsed_time": "18:17:18", "remaining_time": "4:56:58", "throughput": 657.37, "total_tokens": 43280352} {"current_steps": 31485, "total_steps": 40000, "loss": 0.9711, "lr": 5.3865416344256705e-06, "epoch": 1.0077779911657385, "percentage": 78.71, "elapsed_time": "18:17:19", "remaining_time": "4:56:46", "throughput": 657.46, "total_tokens": 43287392} {"current_steps": 31490, "total_steps": 40000, "loss": 0.7213, "lr": 5.380455522610742e-06, "epoch": 1.0079380321362268, "percentage": 78.72, "elapsed_time": "18:17:21", "remaining_time": "4:56:33", "throughput": 657.55, "total_tokens": 43294144} {"current_steps": 31495, "total_steps": 40000, "loss": 0.6473, "lr": 5.374372436376116e-06, "epoch": 1.0080980731067153, "percentage": 78.74, "elapsed_time": "18:17:23", "remaining_time": "4:56:20", "throughput": 657.63, "total_tokens": 43300672} {"current_steps": 31500, "total_steps": 40000, "loss": 0.7201, "lr": 5.368292376659895e-06, "epoch": 1.0082581140772038, "percentage": 78.75, "elapsed_time": "18:17:25", "remaining_time": "4:56:07", "throughput": 657.71, "total_tokens": 43307296} {"current_steps": 31505, "total_steps": 40000, "loss": 0.8032, "lr": 5.362215344399701e-06, "epoch": 1.0084181550476923, "percentage": 78.76, "elapsed_time": "18:17:26", "remaining_time": "4:55:54", "throughput": 657.8, "total_tokens": 43314208} {"current_steps": 31510, "total_steps": 40000, "loss": 0.7401, "lr": 5.356141340532678e-06, "epoch": 1.0085781960181806, "percentage": 78.77, "elapsed_time": "18:17:28", "remaining_time": "4:55:42", "throughput": 657.89, "total_tokens": 43320848} {"current_steps": 31515, "total_steps": 40000, "loss": 0.555, "lr": 5.350070365995522e-06, "epoch": 1.008738236988669, "percentage": 78.79, "elapsed_time": "18:17:30", "remaining_time": "4:55:29", "throughput": 657.98, "total_tokens": 43328208} {"current_steps": 31520, "total_steps": 40000, "loss": 0.7626, "lr": 5.344002421724459e-06, "epoch": 1.0088982779591575, "percentage": 78.8, "elapsed_time": "18:17:32", "remaining_time": "4:55:16", "throughput": 658.06, "total_tokens": 43334848} {"current_steps": 31525, "total_steps": 40000, "loss": 0.8348, "lr": 5.337937508655228e-06, "epoch": 1.009058318929646, "percentage": 78.81, "elapsed_time": "18:17:33", "remaining_time": "4:55:03", "throughput": 658.15, "total_tokens": 43341728} {"current_steps": 31530, "total_steps": 40000, "loss": 0.8053, "lr": 5.331875627723126e-06, "epoch": 1.0092183599001345, "percentage": 78.83, "elapsed_time": "18:17:35", "remaining_time": "4:54:51", "throughput": 658.24, "total_tokens": 43348496} {"current_steps": 31535, "total_steps": 40000, "loss": 0.6248, "lr": 5.325816779862963e-06, "epoch": 1.0093784008706228, "percentage": 78.84, "elapsed_time": "18:17:37", "remaining_time": "4:54:38", "throughput": 658.32, "total_tokens": 43355184} {"current_steps": 31540, "total_steps": 40000, "loss": 0.6464, "lr": 5.319760966009102e-06, "epoch": 1.0095384418411113, "percentage": 78.85, "elapsed_time": "18:17:39", "remaining_time": "4:54:25", "throughput": 658.41, "total_tokens": 43362160} {"current_steps": 31545, "total_steps": 40000, "loss": 0.8027, "lr": 5.3137081870954096e-06, "epoch": 1.0096984828115998, "percentage": 78.86, "elapsed_time": "18:17:40", "remaining_time": "4:54:12", "throughput": 658.49, "total_tokens": 43368832} {"current_steps": 31550, "total_steps": 40000, "loss": 0.7829, "lr": 5.307658444055313e-06, "epoch": 1.0098585237820883, "percentage": 78.88, "elapsed_time": "18:17:42", "remaining_time": "4:53:59", "throughput": 658.58, "total_tokens": 43375632} {"current_steps": 31555, "total_steps": 40000, "loss": 0.7838, "lr": 5.301611737821749e-06, "epoch": 1.0100185647525766, "percentage": 78.89, "elapsed_time": "18:17:44", "remaining_time": "4:53:47", "throughput": 658.67, "total_tokens": 43382640} {"current_steps": 31560, "total_steps": 40000, "loss": 0.575, "lr": 5.295568069327206e-06, "epoch": 1.010178605723065, "percentage": 78.9, "elapsed_time": "18:17:46", "remaining_time": "4:53:34", "throughput": 658.76, "total_tokens": 43389792} {"current_steps": 31565, "total_steps": 40000, "loss": 0.7115, "lr": 5.289527439503683e-06, "epoch": 1.0103386466935536, "percentage": 78.91, "elapsed_time": "18:17:47", "remaining_time": "4:53:21", "throughput": 658.84, "total_tokens": 43396592} {"current_steps": 31570, "total_steps": 40000, "loss": 0.7926, "lr": 5.28348984928273e-06, "epoch": 1.010498687664042, "percentage": 78.92, "elapsed_time": "18:17:49", "remaining_time": "4:53:08", "throughput": 658.93, "total_tokens": 43403312} {"current_steps": 31575, "total_steps": 40000, "loss": 0.575, "lr": 5.27745529959541e-06, "epoch": 1.0106587286345305, "percentage": 78.94, "elapsed_time": "18:17:51", "remaining_time": "4:52:56", "throughput": 659.01, "total_tokens": 43409888} {"current_steps": 31580, "total_steps": 40000, "loss": 0.9524, "lr": 5.271423791372335e-06, "epoch": 1.0108187696050188, "percentage": 78.95, "elapsed_time": "18:17:53", "remaining_time": "4:52:43", "throughput": 659.1, "total_tokens": 43417008} {"current_steps": 31585, "total_steps": 40000, "loss": 0.6872, "lr": 5.26539532554364e-06, "epoch": 1.0109788105755073, "percentage": 78.96, "elapsed_time": "18:17:54", "remaining_time": "4:52:30", "throughput": 659.19, "total_tokens": 43423872} {"current_steps": 31590, "total_steps": 40000, "loss": 0.802, "lr": 5.25936990303898e-06, "epoch": 1.0111388515459958, "percentage": 78.97, "elapsed_time": "18:17:56", "remaining_time": "4:52:17", "throughput": 659.28, "total_tokens": 43431168} {"current_steps": 31595, "total_steps": 40000, "loss": 0.6768, "lr": 5.253347524787555e-06, "epoch": 1.0112988925164843, "percentage": 78.99, "elapsed_time": "18:17:58", "remaining_time": "4:52:05", "throughput": 659.37, "total_tokens": 43438048} {"current_steps": 31600, "total_steps": 40000, "loss": 0.7046, "lr": 5.2473281917181035e-06, "epoch": 1.0114589334869726, "percentage": 79.0, "elapsed_time": "18:18:00", "remaining_time": "4:51:52", "throughput": 659.45, "total_tokens": 43444592} {"current_steps": 31600, "total_steps": 40000, "eval_loss": 0.7318750023841858, "epoch": 1.0114589334869726, "percentage": 79.0, "elapsed_time": "18:23:48", "remaining_time": "4:53:24", "throughput": 655.98, "total_tokens": 43444592} {"current_steps": 31605, "total_steps": 40000, "loss": 0.5041, "lr": 5.241311904758864e-06, "epoch": 1.011618974457461, "percentage": 79.01, "elapsed_time": "18:23:51", "remaining_time": "4:53:12", "throughput": 656.05, "total_tokens": 43451456} {"current_steps": 31610, "total_steps": 40000, "loss": 0.5903, "lr": 5.23529866483764e-06, "epoch": 1.0117790154279496, "percentage": 79.03, "elapsed_time": "18:23:53", "remaining_time": "4:52:59", "throughput": 656.14, "total_tokens": 43458272} {"current_steps": 31615, "total_steps": 40000, "loss": 0.5945, "lr": 5.229288472881732e-06, "epoch": 1.011939056398438, "percentage": 79.04, "elapsed_time": "18:23:55", "remaining_time": "4:52:47", "throughput": 656.23, "total_tokens": 43465472} {"current_steps": 31620, "total_steps": 40000, "loss": 0.7055, "lr": 5.2232813298180025e-06, "epoch": 1.0120990973689263, "percentage": 79.05, "elapsed_time": "18:23:56", "remaining_time": "4:52:34", "throughput": 656.32, "total_tokens": 43472416} {"current_steps": 31625, "total_steps": 40000, "loss": 0.8256, "lr": 5.217277236572824e-06, "epoch": 1.0122591383394148, "percentage": 79.06, "elapsed_time": "18:23:58", "remaining_time": "4:52:21", "throughput": 656.4, "total_tokens": 43479296} {"current_steps": 31630, "total_steps": 40000, "loss": 0.5356, "lr": 5.211276194072093e-06, "epoch": 1.0124191793099033, "percentage": 79.07, "elapsed_time": "18:24:00", "remaining_time": "4:52:08", "throughput": 656.49, "total_tokens": 43486192} {"current_steps": 31635, "total_steps": 40000, "loss": 0.6017, "lr": 5.205278203241254e-06, "epoch": 1.0125792202803918, "percentage": 79.09, "elapsed_time": "18:24:02", "remaining_time": "4:51:55", "throughput": 656.57, "total_tokens": 43492896} {"current_steps": 31640, "total_steps": 40000, "loss": 0.6959, "lr": 5.199283265005278e-06, "epoch": 1.0127392612508803, "percentage": 79.1, "elapsed_time": "18:24:03", "remaining_time": "4:51:43", "throughput": 656.66, "total_tokens": 43499408} {"current_steps": 31645, "total_steps": 40000, "loss": 0.7431, "lr": 5.193291380288648e-06, "epoch": 1.0128993022213686, "percentage": 79.11, "elapsed_time": "18:24:05", "remaining_time": "4:51:30", "throughput": 656.74, "total_tokens": 43506256} {"current_steps": 31650, "total_steps": 40000, "loss": 0.9314, "lr": 5.1873025500153995e-06, "epoch": 1.013059343191857, "percentage": 79.12, "elapsed_time": "18:24:07", "remaining_time": "4:51:17", "throughput": 656.83, "total_tokens": 43513312} {"current_steps": 31655, "total_steps": 40000, "loss": 0.86, "lr": 5.181316775109071e-06, "epoch": 1.0132193841623456, "percentage": 79.14, "elapsed_time": "18:24:09", "remaining_time": "4:51:04", "throughput": 656.91, "total_tokens": 43519968} {"current_steps": 31660, "total_steps": 40000, "loss": 0.8293, "lr": 5.1753340564927564e-06, "epoch": 1.013379425132834, "percentage": 79.15, "elapsed_time": "18:24:10", "remaining_time": "4:50:52", "throughput": 657.0, "total_tokens": 43526928} {"current_steps": 31665, "total_steps": 40000, "loss": 0.7965, "lr": 5.169354395089068e-06, "epoch": 1.0135394661033224, "percentage": 79.16, "elapsed_time": "18:24:12", "remaining_time": "4:50:39", "throughput": 657.08, "total_tokens": 43533536} {"current_steps": 31670, "total_steps": 40000, "loss": 0.6324, "lr": 5.1633777918201346e-06, "epoch": 1.0136995070738108, "percentage": 79.17, "elapsed_time": "18:24:14", "remaining_time": "4:50:26", "throughput": 657.17, "total_tokens": 43540544} {"current_steps": 31675, "total_steps": 40000, "loss": 0.7083, "lr": 5.157404247607625e-06, "epoch": 1.0138595480442993, "percentage": 79.19, "elapsed_time": "18:24:16", "remaining_time": "4:50:13", "throughput": 657.25, "total_tokens": 43546992} {"current_steps": 31680, "total_steps": 40000, "loss": 0.6121, "lr": 5.1514337633727454e-06, "epoch": 1.0140195890147878, "percentage": 79.2, "elapsed_time": "18:24:17", "remaining_time": "4:50:01", "throughput": 657.34, "total_tokens": 43553696} {"current_steps": 31685, "total_steps": 40000, "loss": 0.8245, "lr": 5.145466340036206e-06, "epoch": 1.0141796299852763, "percentage": 79.21, "elapsed_time": "18:24:19", "remaining_time": "4:49:48", "throughput": 657.42, "total_tokens": 43560432} {"current_steps": 31690, "total_steps": 40000, "loss": 0.7513, "lr": 5.139501978518274e-06, "epoch": 1.0143396709557646, "percentage": 79.22, "elapsed_time": "18:24:21", "remaining_time": "4:49:35", "throughput": 657.5, "total_tokens": 43567120} {"current_steps": 31695, "total_steps": 40000, "loss": 0.6317, "lr": 5.133540679738716e-06, "epoch": 1.014499711926253, "percentage": 79.24, "elapsed_time": "18:24:23", "remaining_time": "4:49:22", "throughput": 657.59, "total_tokens": 43574176} {"current_steps": 31700, "total_steps": 40000, "loss": 0.8683, "lr": 5.127582444616838e-06, "epoch": 1.0146597528967416, "percentage": 79.25, "elapsed_time": "18:24:24", "remaining_time": "4:49:10", "throughput": 657.67, "total_tokens": 43580656} {"current_steps": 31705, "total_steps": 40000, "loss": 0.8316, "lr": 5.121627274071486e-06, "epoch": 1.01481979386723, "percentage": 79.26, "elapsed_time": "18:24:26", "remaining_time": "4:48:57", "throughput": 657.76, "total_tokens": 43587328} {"current_steps": 31710, "total_steps": 40000, "loss": 0.9075, "lr": 5.115675169021009e-06, "epoch": 1.0149798348377184, "percentage": 79.27, "elapsed_time": "18:24:28", "remaining_time": "4:48:44", "throughput": 657.84, "total_tokens": 43594176} {"current_steps": 31715, "total_steps": 40000, "loss": 0.8154, "lr": 5.1097261303832994e-06, "epoch": 1.0151398758082069, "percentage": 79.29, "elapsed_time": "18:24:30", "remaining_time": "4:48:31", "throughput": 657.93, "total_tokens": 43601312} {"current_steps": 31720, "total_steps": 40000, "loss": 0.6335, "lr": 5.103780159075788e-06, "epoch": 1.0152999167786954, "percentage": 79.3, "elapsed_time": "18:24:31", "remaining_time": "4:48:19", "throughput": 658.02, "total_tokens": 43608080} {"current_steps": 31725, "total_steps": 40000, "loss": 0.6985, "lr": 5.0978372560154e-06, "epoch": 1.0154599577491839, "percentage": 79.31, "elapsed_time": "18:24:33", "remaining_time": "4:48:06", "throughput": 658.11, "total_tokens": 43615280} {"current_steps": 31730, "total_steps": 40000, "loss": 0.7401, "lr": 5.091897422118619e-06, "epoch": 1.0156199987196723, "percentage": 79.33, "elapsed_time": "18:24:35", "remaining_time": "4:47:53", "throughput": 658.2, "total_tokens": 43622384} {"current_steps": 31735, "total_steps": 40000, "loss": 0.5361, "lr": 5.0859606583014305e-06, "epoch": 1.0157800396901606, "percentage": 79.34, "elapsed_time": "18:24:37", "remaining_time": "4:47:41", "throughput": 658.28, "total_tokens": 43629280} {"current_steps": 31740, "total_steps": 40000, "loss": 0.5553, "lr": 5.080026965479365e-06, "epoch": 1.0159400806606491, "percentage": 79.35, "elapsed_time": "18:24:38", "remaining_time": "4:47:28", "throughput": 658.37, "total_tokens": 43635792} {"current_steps": 31745, "total_steps": 40000, "loss": 0.6003, "lr": 5.074096344567475e-06, "epoch": 1.0161001216311376, "percentage": 79.36, "elapsed_time": "18:24:40", "remaining_time": "4:47:15", "throughput": 658.45, "total_tokens": 43642816} {"current_steps": 31750, "total_steps": 40000, "loss": 0.5461, "lr": 5.0681687964803294e-06, "epoch": 1.016260162601626, "percentage": 79.38, "elapsed_time": "18:24:42", "remaining_time": "4:47:03", "throughput": 658.55, "total_tokens": 43650048} {"current_steps": 31755, "total_steps": 40000, "loss": 0.8375, "lr": 5.06224432213204e-06, "epoch": 1.0164202035721144, "percentage": 79.39, "elapsed_time": "18:24:44", "remaining_time": "4:46:50", "throughput": 658.63, "total_tokens": 43656736} {"current_steps": 31760, "total_steps": 40000, "loss": 0.8449, "lr": 5.056322922436224e-06, "epoch": 1.0165802445426029, "percentage": 79.4, "elapsed_time": "18:24:45", "remaining_time": "4:46:37", "throughput": 658.71, "total_tokens": 43663392} {"current_steps": 31765, "total_steps": 40000, "loss": 0.7844, "lr": 5.0504045983060465e-06, "epoch": 1.0167402855130914, "percentage": 79.41, "elapsed_time": "18:24:47", "remaining_time": "4:46:24", "throughput": 658.8, "total_tokens": 43670240} {"current_steps": 31770, "total_steps": 40000, "loss": 0.5652, "lr": 5.044489350654183e-06, "epoch": 1.0169003264835799, "percentage": 79.42, "elapsed_time": "18:24:49", "remaining_time": "4:46:12", "throughput": 658.88, "total_tokens": 43677088} {"current_steps": 31775, "total_steps": 40000, "loss": 0.9555, "lr": 5.038577180392831e-06, "epoch": 1.0170603674540681, "percentage": 79.44, "elapsed_time": "18:24:51", "remaining_time": "4:45:59", "throughput": 658.97, "total_tokens": 43684240} {"current_steps": 31780, "total_steps": 40000, "loss": 0.8308, "lr": 5.032668088433729e-06, "epoch": 1.0172204084245566, "percentage": 79.45, "elapsed_time": "18:24:53", "remaining_time": "4:45:46", "throughput": 659.06, "total_tokens": 43690784} {"current_steps": 31785, "total_steps": 40000, "loss": 0.7657, "lr": 5.02676207568814e-06, "epoch": 1.0173804493950451, "percentage": 79.46, "elapsed_time": "18:24:54", "remaining_time": "4:45:34", "throughput": 659.15, "total_tokens": 43697872} {"current_steps": 31790, "total_steps": 40000, "loss": 0.6328, "lr": 5.02085914306683e-06, "epoch": 1.0175404903655336, "percentage": 79.47, "elapsed_time": "18:24:56", "remaining_time": "4:45:21", "throughput": 659.23, "total_tokens": 43704496} {"current_steps": 31795, "total_steps": 40000, "loss": 0.8943, "lr": 5.014959291480123e-06, "epoch": 1.0177005313360221, "percentage": 79.49, "elapsed_time": "18:24:58", "remaining_time": "4:45:08", "throughput": 659.33, "total_tokens": 43712128} {"current_steps": 31800, "total_steps": 40000, "loss": 0.7093, "lr": 5.009062521837835e-06, "epoch": 1.0178605723065104, "percentage": 79.5, "elapsed_time": "18:25:00", "remaining_time": "4:44:56", "throughput": 659.42, "total_tokens": 43719328} {"current_steps": 31800, "total_steps": 40000, "eval_loss": 0.7318029403686523, "epoch": 1.0178605723065104, "percentage": 79.5, "elapsed_time": "18:30:47", "remaining_time": "4:46:25", "throughput": 655.98, "total_tokens": 43719328} {"current_steps": 31805, "total_steps": 40000, "loss": 0.5349, "lr": 5.003168835049324e-06, "epoch": 1.0180206132769989, "percentage": 79.51, "elapsed_time": "18:30:51", "remaining_time": "4:46:13", "throughput": 656.05, "total_tokens": 43726240} {"current_steps": 31810, "total_steps": 40000, "loss": 0.7315, "lr": 4.997278232023483e-06, "epoch": 1.0181806542474874, "percentage": 79.53, "elapsed_time": "18:30:52", "remaining_time": "4:46:00", "throughput": 656.13, "total_tokens": 43732992} {"current_steps": 31815, "total_steps": 40000, "loss": 0.7323, "lr": 4.9913907136687036e-06, "epoch": 1.0183406952179759, "percentage": 79.54, "elapsed_time": "18:30:54", "remaining_time": "4:45:48", "throughput": 656.22, "total_tokens": 43740272} {"current_steps": 31820, "total_steps": 40000, "loss": 0.589, "lr": 4.985506280892918e-06, "epoch": 1.0185007361884642, "percentage": 79.55, "elapsed_time": "18:30:56", "remaining_time": "4:45:35", "throughput": 656.31, "total_tokens": 43747344} {"current_steps": 31825, "total_steps": 40000, "loss": 0.6601, "lr": 4.979624934603589e-06, "epoch": 1.0186607771589526, "percentage": 79.56, "elapsed_time": "18:30:58", "remaining_time": "4:45:22", "throughput": 656.39, "total_tokens": 43753904} {"current_steps": 31830, "total_steps": 40000, "loss": 0.7308, "lr": 4.97374667570768e-06, "epoch": 1.0188208181294411, "percentage": 79.57, "elapsed_time": "18:30:59", "remaining_time": "4:45:09", "throughput": 656.48, "total_tokens": 43760592} {"current_steps": 31835, "total_steps": 40000, "loss": 0.6096, "lr": 4.967871505111704e-06, "epoch": 1.0189808590999296, "percentage": 79.59, "elapsed_time": "18:31:01", "remaining_time": "4:44:57", "throughput": 656.56, "total_tokens": 43767568} {"current_steps": 31840, "total_steps": 40000, "loss": 0.5832, "lr": 4.961999423721686e-06, "epoch": 1.0191409000704181, "percentage": 79.6, "elapsed_time": "18:31:03", "remaining_time": "4:44:44", "throughput": 656.65, "total_tokens": 43774400} {"current_steps": 31845, "total_steps": 40000, "loss": 0.5704, "lr": 4.956130432443159e-06, "epoch": 1.0193009410409064, "percentage": 79.61, "elapsed_time": "18:31:05", "remaining_time": "4:44:31", "throughput": 656.73, "total_tokens": 43781104} {"current_steps": 31850, "total_steps": 40000, "loss": 0.659, "lr": 4.950264532181215e-06, "epoch": 1.019460982011395, "percentage": 79.62, "elapsed_time": "18:31:06", "remaining_time": "4:44:19", "throughput": 656.81, "total_tokens": 43787744} {"current_steps": 31855, "total_steps": 40000, "loss": 0.7217, "lr": 4.944401723840433e-06, "epoch": 1.0196210229818834, "percentage": 79.64, "elapsed_time": "18:31:08", "remaining_time": "4:44:06", "throughput": 656.89, "total_tokens": 43794256} {"current_steps": 31860, "total_steps": 40000, "loss": 0.8056, "lr": 4.938542008324942e-06, "epoch": 1.019781063952372, "percentage": 79.65, "elapsed_time": "18:31:10", "remaining_time": "4:43:53", "throughput": 656.98, "total_tokens": 43801376} {"current_steps": 31865, "total_steps": 40000, "loss": 0.5828, "lr": 4.9326853865383855e-06, "epoch": 1.0199411049228602, "percentage": 79.66, "elapsed_time": "18:31:12", "remaining_time": "4:43:41", "throughput": 657.07, "total_tokens": 43808416} {"current_steps": 31870, "total_steps": 40000, "loss": 0.8135, "lr": 4.926831859383918e-06, "epoch": 1.0201011458933487, "percentage": 79.67, "elapsed_time": "18:31:13", "remaining_time": "4:43:28", "throughput": 657.16, "total_tokens": 43815104} {"current_steps": 31875, "total_steps": 40000, "loss": 0.7354, "lr": 4.92098142776424e-06, "epoch": 1.0202611868638372, "percentage": 79.69, "elapsed_time": "18:31:15", "remaining_time": "4:43:15", "throughput": 657.24, "total_tokens": 43821920} {"current_steps": 31880, "total_steps": 40000, "loss": 0.7191, "lr": 4.91513409258155e-06, "epoch": 1.0204212278343257, "percentage": 79.7, "elapsed_time": "18:31:17", "remaining_time": "4:43:03", "throughput": 657.32, "total_tokens": 43828688} {"current_steps": 31885, "total_steps": 40000, "loss": 0.5358, "lr": 4.909289854737581e-06, "epoch": 1.020581268804814, "percentage": 79.71, "elapsed_time": "18:31:19", "remaining_time": "4:42:50", "throughput": 657.41, "total_tokens": 43835536} {"current_steps": 31890, "total_steps": 40000, "loss": 0.7227, "lr": 4.903448715133602e-06, "epoch": 1.0207413097753024, "percentage": 79.72, "elapsed_time": "18:31:20", "remaining_time": "4:42:37", "throughput": 657.5, "total_tokens": 43842592} {"current_steps": 31895, "total_steps": 40000, "loss": 0.8296, "lr": 4.897610674670372e-06, "epoch": 1.020901350745791, "percentage": 79.74, "elapsed_time": "18:31:22", "remaining_time": "4:42:25", "throughput": 657.58, "total_tokens": 43849344} {"current_steps": 31900, "total_steps": 40000, "loss": 0.7902, "lr": 4.8917757342482e-06, "epoch": 1.0210613917162794, "percentage": 79.75, "elapsed_time": "18:31:24", "remaining_time": "4:42:12", "throughput": 657.67, "total_tokens": 43856256} {"current_steps": 31905, "total_steps": 40000, "loss": 0.667, "lr": 4.885943894766909e-06, "epoch": 1.021221432686768, "percentage": 79.76, "elapsed_time": "18:31:26", "remaining_time": "4:41:59", "throughput": 657.77, "total_tokens": 43863920} {"current_steps": 31910, "total_steps": 40000, "loss": 0.7015, "lr": 4.880115157125842e-06, "epoch": 1.0213814736572562, "percentage": 79.77, "elapsed_time": "18:31:27", "remaining_time": "4:41:47", "throughput": 657.85, "total_tokens": 43870624} {"current_steps": 31915, "total_steps": 40000, "loss": 0.7746, "lr": 4.874289522223857e-06, "epoch": 1.0215415146277447, "percentage": 79.79, "elapsed_time": "18:31:29", "remaining_time": "4:41:34", "throughput": 657.94, "total_tokens": 43877856} {"current_steps": 31920, "total_steps": 40000, "loss": 0.8193, "lr": 4.868466990959339e-06, "epoch": 1.0217015555982332, "percentage": 79.8, "elapsed_time": "18:31:31", "remaining_time": "4:41:21", "throughput": 658.04, "total_tokens": 43885376} {"current_steps": 31925, "total_steps": 40000, "loss": 0.6845, "lr": 4.8626475642301964e-06, "epoch": 1.0218615965687217, "percentage": 79.81, "elapsed_time": "18:31:33", "remaining_time": "4:41:09", "throughput": 658.12, "total_tokens": 43891808} {"current_steps": 31930, "total_steps": 40000, "loss": 0.9094, "lr": 4.856831242933871e-06, "epoch": 1.02202163753921, "percentage": 79.83, "elapsed_time": "18:31:34", "remaining_time": "4:40:56", "throughput": 658.2, "total_tokens": 43898848} {"current_steps": 31935, "total_steps": 40000, "loss": 0.6613, "lr": 4.851018027967294e-06, "epoch": 1.0221816785096984, "percentage": 79.84, "elapsed_time": "18:31:36", "remaining_time": "4:40:43", "throughput": 658.29, "total_tokens": 43905712} {"current_steps": 31940, "total_steps": 40000, "loss": 0.729, "lr": 4.845207920226946e-06, "epoch": 1.022341719480187, "percentage": 79.85, "elapsed_time": "18:31:38", "remaining_time": "4:40:31", "throughput": 658.37, "total_tokens": 43912288} {"current_steps": 31945, "total_steps": 40000, "loss": 0.7235, "lr": 4.839400920608825e-06, "epoch": 1.0225017604506754, "percentage": 79.86, "elapsed_time": "18:31:40", "remaining_time": "4:40:18", "throughput": 658.46, "total_tokens": 43919280} {"current_steps": 31950, "total_steps": 40000, "loss": 0.61, "lr": 4.83359703000843e-06, "epoch": 1.022661801421164, "percentage": 79.88, "elapsed_time": "18:31:41", "remaining_time": "4:40:05", "throughput": 658.54, "total_tokens": 43926032} {"current_steps": 31955, "total_steps": 40000, "loss": 0.677, "lr": 4.827796249320804e-06, "epoch": 1.0228218423916522, "percentage": 79.89, "elapsed_time": "18:31:43", "remaining_time": "4:39:53", "throughput": 658.62, "total_tokens": 43932368} {"current_steps": 31960, "total_steps": 40000, "loss": 0.6805, "lr": 4.82199857944049e-06, "epoch": 1.0229818833621407, "percentage": 79.9, "elapsed_time": "18:31:45", "remaining_time": "4:39:40", "throughput": 658.7, "total_tokens": 43938912} {"current_steps": 31965, "total_steps": 40000, "loss": 0.7711, "lr": 4.8162040212615695e-06, "epoch": 1.0231419243326292, "percentage": 79.91, "elapsed_time": "18:31:47", "remaining_time": "4:39:28", "throughput": 658.79, "total_tokens": 43945968} {"current_steps": 31970, "total_steps": 40000, "loss": 0.6555, "lr": 4.810412575677639e-06, "epoch": 1.0233019653031177, "percentage": 79.92, "elapsed_time": "18:31:48", "remaining_time": "4:39:15", "throughput": 658.88, "total_tokens": 43953200} {"current_steps": 31975, "total_steps": 40000, "loss": 0.4946, "lr": 4.804624243581801e-06, "epoch": 1.023462006273606, "percentage": 79.94, "elapsed_time": "18:31:50", "remaining_time": "4:39:02", "throughput": 658.96, "total_tokens": 43959984} {"current_steps": 31980, "total_steps": 40000, "loss": 0.9485, "lr": 4.798839025866703e-06, "epoch": 1.0236220472440944, "percentage": 79.95, "elapsed_time": "18:31:52", "remaining_time": "4:38:50", "throughput": 659.06, "total_tokens": 43967264} {"current_steps": 31985, "total_steps": 40000, "loss": 0.7099, "lr": 4.793056923424491e-06, "epoch": 1.023782088214583, "percentage": 79.96, "elapsed_time": "18:31:54", "remaining_time": "4:38:37", "throughput": 659.14, "total_tokens": 43973792} {"current_steps": 31990, "total_steps": 40000, "loss": 0.5854, "lr": 4.78727793714683e-06, "epoch": 1.0239421291850714, "percentage": 79.97, "elapsed_time": "18:31:55", "remaining_time": "4:38:25", "throughput": 659.22, "total_tokens": 43980432} {"current_steps": 31995, "total_steps": 40000, "loss": 0.5319, "lr": 4.7815020679249285e-06, "epoch": 1.02410217015556, "percentage": 79.99, "elapsed_time": "18:31:57", "remaining_time": "4:38:12", "throughput": 659.3, "total_tokens": 43987312} {"current_steps": 32000, "total_steps": 40000, "loss": 0.58, "lr": 4.775729316649483e-06, "epoch": 1.0242622111260482, "percentage": 80.0, "elapsed_time": "18:31:59", "remaining_time": "4:37:59", "throughput": 659.39, "total_tokens": 43994064} {"current_steps": 32000, "total_steps": 40000, "eval_loss": 0.7311859726905823, "epoch": 1.0242622111260482, "percentage": 80.0, "elapsed_time": "18:37:46", "remaining_time": "4:39:26", "throughput": 655.97, "total_tokens": 43994064} {"current_steps": 32005, "total_steps": 40000, "loss": 0.7176, "lr": 4.769959684210728e-06, "epoch": 1.0244222520965367, "percentage": 80.01, "elapsed_time": "18:37:50", "remaining_time": "4:39:14", "throughput": 656.04, "total_tokens": 44000848} {"current_steps": 32010, "total_steps": 40000, "loss": 0.6892, "lr": 4.764193171498426e-06, "epoch": 1.0245822930670252, "percentage": 80.03, "elapsed_time": "18:37:52", "remaining_time": "4:39:01", "throughput": 656.12, "total_tokens": 44007504} {"current_steps": 32015, "total_steps": 40000, "loss": 0.754, "lr": 4.75842977940183e-06, "epoch": 1.0247423340375137, "percentage": 80.04, "elapsed_time": "18:37:53", "remaining_time": "4:38:49", "throughput": 656.21, "total_tokens": 44014528} {"current_steps": 32020, "total_steps": 40000, "loss": 0.8259, "lr": 4.752669508809729e-06, "epoch": 1.024902375008002, "percentage": 80.05, "elapsed_time": "18:37:55", "remaining_time": "4:38:36", "throughput": 656.29, "total_tokens": 44021408} {"current_steps": 32025, "total_steps": 40000, "loss": 0.5492, "lr": 4.746912360610445e-06, "epoch": 1.0250624159784905, "percentage": 80.06, "elapsed_time": "18:37:57", "remaining_time": "4:38:23", "throughput": 656.38, "total_tokens": 44028160} {"current_steps": 32030, "total_steps": 40000, "loss": 0.7643, "lr": 4.741158335691781e-06, "epoch": 1.025222456948979, "percentage": 80.08, "elapsed_time": "18:37:59", "remaining_time": "4:38:11", "throughput": 656.46, "total_tokens": 44034976} {"current_steps": 32035, "total_steps": 40000, "loss": 0.7606, "lr": 4.7354074349410994e-06, "epoch": 1.0253824979194675, "percentage": 80.09, "elapsed_time": "18:38:00", "remaining_time": "4:37:58", "throughput": 656.55, "total_tokens": 44041856} {"current_steps": 32040, "total_steps": 40000, "loss": 0.6671, "lr": 4.729659659245245e-06, "epoch": 1.0255425388899557, "percentage": 80.1, "elapsed_time": "18:38:02", "remaining_time": "4:37:45", "throughput": 656.63, "total_tokens": 44048560} {"current_steps": 32045, "total_steps": 40000, "loss": 0.7761, "lr": 4.723915009490601e-06, "epoch": 1.0257025798604442, "percentage": 80.11, "elapsed_time": "18:38:04", "remaining_time": "4:37:33", "throughput": 656.72, "total_tokens": 44055488} {"current_steps": 32050, "total_steps": 40000, "loss": 0.5987, "lr": 4.718173486563077e-06, "epoch": 1.0258626208309327, "percentage": 80.12, "elapsed_time": "18:38:06", "remaining_time": "4:37:20", "throughput": 656.8, "total_tokens": 44062416} {"current_steps": 32055, "total_steps": 40000, "loss": 0.7875, "lr": 4.71243509134808e-06, "epoch": 1.0260226618014212, "percentage": 80.14, "elapsed_time": "18:38:07", "remaining_time": "4:37:08", "throughput": 656.88, "total_tokens": 44068880} {"current_steps": 32060, "total_steps": 40000, "loss": 0.7762, "lr": 4.706699824730532e-06, "epoch": 1.0261827027719097, "percentage": 80.15, "elapsed_time": "18:38:09", "remaining_time": "4:36:55", "throughput": 656.97, "total_tokens": 44076192} {"current_steps": 32065, "total_steps": 40000, "loss": 0.6426, "lr": 4.700967687594901e-06, "epoch": 1.026342743742398, "percentage": 80.16, "elapsed_time": "18:38:11", "remaining_time": "4:36:42", "throughput": 657.06, "total_tokens": 44083120} {"current_steps": 32070, "total_steps": 40000, "loss": 0.7274, "lr": 4.69523868082514e-06, "epoch": 1.0265027847128865, "percentage": 80.17, "elapsed_time": "18:38:13", "remaining_time": "4:36:30", "throughput": 657.14, "total_tokens": 44089824} {"current_steps": 32075, "total_steps": 40000, "loss": 0.6349, "lr": 4.689512805304747e-06, "epoch": 1.026662825683375, "percentage": 80.19, "elapsed_time": "18:38:14", "remaining_time": "4:36:17", "throughput": 657.23, "total_tokens": 44096560} {"current_steps": 32080, "total_steps": 40000, "loss": 0.7416, "lr": 4.683790061916707e-06, "epoch": 1.0268228666538635, "percentage": 80.2, "elapsed_time": "18:38:16", "remaining_time": "4:36:05", "throughput": 657.32, "total_tokens": 44103696} {"current_steps": 32085, "total_steps": 40000, "loss": 0.6672, "lr": 4.678070451543551e-06, "epoch": 1.0269829076243517, "percentage": 80.21, "elapsed_time": "18:38:18", "remaining_time": "4:35:52", "throughput": 657.4, "total_tokens": 44110432} {"current_steps": 32090, "total_steps": 40000, "loss": 0.6609, "lr": 4.6723539750673204e-06, "epoch": 1.0271429485948402, "percentage": 80.23, "elapsed_time": "18:38:20", "remaining_time": "4:35:39", "throughput": 657.48, "total_tokens": 44117104} {"current_steps": 32095, "total_steps": 40000, "loss": 0.6824, "lr": 4.666640633369551e-06, "epoch": 1.0273029895653287, "percentage": 80.24, "elapsed_time": "18:38:21", "remaining_time": "4:35:27", "throughput": 657.56, "total_tokens": 44123680} {"current_steps": 32100, "total_steps": 40000, "loss": 0.6634, "lr": 4.660930427331323e-06, "epoch": 1.0274630305358172, "percentage": 80.25, "elapsed_time": "18:38:23", "remaining_time": "4:35:14", "throughput": 657.65, "total_tokens": 44130496} {"current_steps": 32105, "total_steps": 40000, "loss": 0.7619, "lr": 4.6552233578332244e-06, "epoch": 1.0276230715063057, "percentage": 80.26, "elapsed_time": "18:38:25", "remaining_time": "4:35:02", "throughput": 657.73, "total_tokens": 44137568} {"current_steps": 32110, "total_steps": 40000, "loss": 0.659, "lr": 4.649519425755347e-06, "epoch": 1.027783112476794, "percentage": 80.27, "elapsed_time": "18:38:27", "remaining_time": "4:34:49", "throughput": 657.82, "total_tokens": 44144256} {"current_steps": 32115, "total_steps": 40000, "loss": 0.7657, "lr": 4.64381863197732e-06, "epoch": 1.0279431534472825, "percentage": 80.29, "elapsed_time": "18:38:28", "remaining_time": "4:34:36", "throughput": 657.9, "total_tokens": 44151312} {"current_steps": 32120, "total_steps": 40000, "loss": 0.8404, "lr": 4.638120977378269e-06, "epoch": 1.028103194417771, "percentage": 80.3, "elapsed_time": "18:38:30", "remaining_time": "4:34:24", "throughput": 657.99, "total_tokens": 44157888} {"current_steps": 32125, "total_steps": 40000, "loss": 1.0078, "lr": 4.632426462836848e-06, "epoch": 1.0282632353882595, "percentage": 80.31, "elapsed_time": "18:38:32", "remaining_time": "4:34:11", "throughput": 658.08, "total_tokens": 44165280} {"current_steps": 32130, "total_steps": 40000, "loss": 0.6894, "lr": 4.626735089231224e-06, "epoch": 1.0284232763587478, "percentage": 80.33, "elapsed_time": "18:38:34", "remaining_time": "4:33:59", "throughput": 658.16, "total_tokens": 44171904} {"current_steps": 32135, "total_steps": 40000, "loss": 0.6127, "lr": 4.621046857439068e-06, "epoch": 1.0285833173292362, "percentage": 80.34, "elapsed_time": "18:38:35", "remaining_time": "4:33:46", "throughput": 658.25, "total_tokens": 44178768} {"current_steps": 32140, "total_steps": 40000, "loss": 0.8549, "lr": 4.615361768337587e-06, "epoch": 1.0287433582997247, "percentage": 80.35, "elapsed_time": "18:38:37", "remaining_time": "4:33:33", "throughput": 658.35, "total_tokens": 44186928} {"current_steps": 32145, "total_steps": 40000, "loss": 0.9973, "lr": 4.6096798228034946e-06, "epoch": 1.0289033992702132, "percentage": 80.36, "elapsed_time": "18:38:39", "remaining_time": "4:33:21", "throughput": 658.43, "total_tokens": 44193664} {"current_steps": 32150, "total_steps": 40000, "loss": 1.0824, "lr": 4.604001021713008e-06, "epoch": 1.0290634402407015, "percentage": 80.38, "elapsed_time": "18:38:41", "remaining_time": "4:33:08", "throughput": 658.52, "total_tokens": 44200992} {"current_steps": 32155, "total_steps": 40000, "loss": 0.5132, "lr": 4.598325365941883e-06, "epoch": 1.02922348121119, "percentage": 80.39, "elapsed_time": "18:38:43", "remaining_time": "4:32:56", "throughput": 658.61, "total_tokens": 44207824} {"current_steps": 32160, "total_steps": 40000, "loss": 0.6622, "lr": 4.5926528563653645e-06, "epoch": 1.0293835221816785, "percentage": 80.4, "elapsed_time": "18:38:44", "remaining_time": "4:32:43", "throughput": 658.69, "total_tokens": 44214496} {"current_steps": 32165, "total_steps": 40000, "loss": 0.6303, "lr": 4.5869834938582295e-06, "epoch": 1.029543563152167, "percentage": 80.41, "elapsed_time": "18:38:46", "remaining_time": "4:32:31", "throughput": 658.78, "total_tokens": 44221360} {"current_steps": 32170, "total_steps": 40000, "loss": 0.7372, "lr": 4.581317279294772e-06, "epoch": 1.0297036041226555, "percentage": 80.42, "elapsed_time": "18:38:48", "remaining_time": "4:32:18", "throughput": 658.86, "total_tokens": 44228416} {"current_steps": 32175, "total_steps": 40000, "loss": 0.8394, "lr": 4.57565421354878e-06, "epoch": 1.0298636450931438, "percentage": 80.44, "elapsed_time": "18:38:50", "remaining_time": "4:32:06", "throughput": 658.95, "total_tokens": 44235280} {"current_steps": 32180, "total_steps": 40000, "loss": 0.6879, "lr": 4.569994297493579e-06, "epoch": 1.0300236860636323, "percentage": 80.45, "elapsed_time": "18:38:51", "remaining_time": "4:31:53", "throughput": 659.04, "total_tokens": 44242256} {"current_steps": 32185, "total_steps": 40000, "loss": 0.7743, "lr": 4.564337532002002e-06, "epoch": 1.0301837270341208, "percentage": 80.46, "elapsed_time": "18:38:53", "remaining_time": "4:31:41", "throughput": 659.12, "total_tokens": 44249152} {"current_steps": 32190, "total_steps": 40000, "loss": 0.8229, "lr": 4.55868391794638e-06, "epoch": 1.0303437680046093, "percentage": 80.47, "elapsed_time": "18:38:55", "remaining_time": "4:31:28", "throughput": 659.21, "total_tokens": 44256368} {"current_steps": 32195, "total_steps": 40000, "loss": 0.7182, "lr": 4.553033456198588e-06, "epoch": 1.0305038089750975, "percentage": 80.49, "elapsed_time": "18:38:57", "remaining_time": "4:31:15", "throughput": 659.29, "total_tokens": 44262864} {"current_steps": 32200, "total_steps": 40000, "loss": 0.7032, "lr": 4.54738614762999e-06, "epoch": 1.030663849945586, "percentage": 80.5, "elapsed_time": "18:38:58", "remaining_time": "4:31:03", "throughput": 659.38, "total_tokens": 44269712} {"current_steps": 32200, "total_steps": 40000, "eval_loss": 0.7313834428787231, "epoch": 1.030663849945586, "percentage": 80.5, "elapsed_time": "18:44:46", "remaining_time": "4:32:27", "throughput": 655.98, "total_tokens": 44269712} {"current_steps": 32205, "total_steps": 40000, "loss": 0.5444, "lr": 4.541741993111465e-06, "epoch": 1.0308238909160745, "percentage": 80.51, "elapsed_time": "18:44:50", "remaining_time": "4:32:15", "throughput": 656.05, "total_tokens": 44276592} {"current_steps": 32210, "total_steps": 40000, "loss": 0.7994, "lr": 4.536100993513423e-06, "epoch": 1.030983931886563, "percentage": 80.53, "elapsed_time": "18:44:51", "remaining_time": "4:32:02", "throughput": 656.13, "total_tokens": 44283344} {"current_steps": 32215, "total_steps": 40000, "loss": 0.7993, "lr": 4.530463149705768e-06, "epoch": 1.0311439728570515, "percentage": 80.54, "elapsed_time": "18:44:53", "remaining_time": "4:31:50", "throughput": 656.21, "total_tokens": 44290064} {"current_steps": 32220, "total_steps": 40000, "loss": 0.7975, "lr": 4.524828462557934e-06, "epoch": 1.0313040138275398, "percentage": 80.55, "elapsed_time": "18:44:55", "remaining_time": "4:31:37", "throughput": 656.3, "total_tokens": 44296864} {"current_steps": 32225, "total_steps": 40000, "loss": 0.727, "lr": 4.5191969329388625e-06, "epoch": 1.0314640547980283, "percentage": 80.56, "elapsed_time": "18:44:57", "remaining_time": "4:31:25", "throughput": 656.37, "total_tokens": 44303264} {"current_steps": 32230, "total_steps": 40000, "loss": 0.7031, "lr": 4.5135685617169965e-06, "epoch": 1.0316240957685168, "percentage": 80.58, "elapsed_time": "18:44:58", "remaining_time": "4:31:12", "throughput": 656.46, "total_tokens": 44310544} {"current_steps": 32235, "total_steps": 40000, "loss": 0.4436, "lr": 4.507943349760313e-06, "epoch": 1.0317841367390053, "percentage": 80.59, "elapsed_time": "18:45:00", "remaining_time": "4:31:00", "throughput": 656.54, "total_tokens": 44317088} {"current_steps": 32240, "total_steps": 40000, "loss": 0.8175, "lr": 4.502321297936277e-06, "epoch": 1.0319441777094935, "percentage": 80.6, "elapsed_time": "18:45:02", "remaining_time": "4:30:47", "throughput": 656.63, "total_tokens": 44324288} {"current_steps": 32245, "total_steps": 40000, "loss": 0.6203, "lr": 4.496702407111888e-06, "epoch": 1.032104218679982, "percentage": 80.61, "elapsed_time": "18:45:04", "remaining_time": "4:30:34", "throughput": 656.73, "total_tokens": 44331920} {"current_steps": 32250, "total_steps": 40000, "loss": 0.6648, "lr": 4.491086678153653e-06, "epoch": 1.0322642596504705, "percentage": 80.62, "elapsed_time": "18:45:05", "remaining_time": "4:30:22", "throughput": 656.81, "total_tokens": 44338800} {"current_steps": 32255, "total_steps": 40000, "loss": 0.8302, "lr": 4.485474111927579e-06, "epoch": 1.032424300620959, "percentage": 80.64, "elapsed_time": "18:45:07", "remaining_time": "4:30:09", "throughput": 656.9, "total_tokens": 44345456} {"current_steps": 32260, "total_steps": 40000, "loss": 0.6136, "lr": 4.479864709299197e-06, "epoch": 1.0325843415914475, "percentage": 80.65, "elapsed_time": "18:45:09", "remaining_time": "4:29:57", "throughput": 656.98, "total_tokens": 44352176} {"current_steps": 32265, "total_steps": 40000, "loss": 0.7494, "lr": 4.474258471133555e-06, "epoch": 1.0327443825619358, "percentage": 80.66, "elapsed_time": "18:45:11", "remaining_time": "4:29:44", "throughput": 657.07, "total_tokens": 44359552} {"current_steps": 32270, "total_steps": 40000, "loss": 0.8888, "lr": 4.4686553982952014e-06, "epoch": 1.0329044235324243, "percentage": 80.67, "elapsed_time": "18:45:12", "remaining_time": "4:29:32", "throughput": 657.15, "total_tokens": 44366160} {"current_steps": 32275, "total_steps": 40000, "loss": 0.6125, "lr": 4.463055491648191e-06, "epoch": 1.0330644645029128, "percentage": 80.69, "elapsed_time": "18:45:14", "remaining_time": "4:29:19", "throughput": 657.24, "total_tokens": 44372992} {"current_steps": 32280, "total_steps": 40000, "loss": 0.8243, "lr": 4.457458752056112e-06, "epoch": 1.0332245054734013, "percentage": 80.7, "elapsed_time": "18:45:16", "remaining_time": "4:29:07", "throughput": 657.32, "total_tokens": 44380112} {"current_steps": 32285, "total_steps": 40000, "loss": 0.7916, "lr": 4.451865180382042e-06, "epoch": 1.0333845464438896, "percentage": 80.71, "elapsed_time": "18:45:18", "remaining_time": "4:28:54", "throughput": 657.41, "total_tokens": 44386928} {"current_steps": 32290, "total_steps": 40000, "loss": 0.6178, "lr": 4.4462747774885936e-06, "epoch": 1.033544587414378, "percentage": 80.73, "elapsed_time": "18:45:19", "remaining_time": "4:28:41", "throughput": 657.49, "total_tokens": 44393776} {"current_steps": 32295, "total_steps": 40000, "loss": 0.6449, "lr": 4.440687544237859e-06, "epoch": 1.0337046283848665, "percentage": 80.74, "elapsed_time": "18:45:21", "remaining_time": "4:28:29", "throughput": 657.58, "total_tokens": 44400688} {"current_steps": 32300, "total_steps": 40000, "loss": 0.6115, "lr": 4.435103481491471e-06, "epoch": 1.033864669355355, "percentage": 80.75, "elapsed_time": "18:45:23", "remaining_time": "4:28:16", "throughput": 657.66, "total_tokens": 44407680} {"current_steps": 32305, "total_steps": 40000, "loss": 0.7771, "lr": 4.429522590110569e-06, "epoch": 1.0340247103258433, "percentage": 80.76, "elapsed_time": "18:45:25", "remaining_time": "4:28:04", "throughput": 657.75, "total_tokens": 44414816} {"current_steps": 32310, "total_steps": 40000, "loss": 0.6379, "lr": 4.423944870955779e-06, "epoch": 1.0341847512963318, "percentage": 80.77, "elapsed_time": "18:45:26", "remaining_time": "4:27:51", "throughput": 657.84, "total_tokens": 44422016} {"current_steps": 32315, "total_steps": 40000, "loss": 0.849, "lr": 4.418370324887272e-06, "epoch": 1.0343447922668203, "percentage": 80.79, "elapsed_time": "18:45:28", "remaining_time": "4:27:39", "throughput": 657.93, "total_tokens": 44428816} {"current_steps": 32320, "total_steps": 40000, "loss": 0.8558, "lr": 4.412798952764699e-06, "epoch": 1.0345048332373088, "percentage": 80.8, "elapsed_time": "18:45:30", "remaining_time": "4:27:26", "throughput": 658.01, "total_tokens": 44435488} {"current_steps": 32325, "total_steps": 40000, "loss": 0.6316, "lr": 4.407230755447245e-06, "epoch": 1.0346648742077973, "percentage": 80.81, "elapsed_time": "18:45:32", "remaining_time": "4:27:14", "throughput": 658.1, "total_tokens": 44442704} {"current_steps": 32330, "total_steps": 40000, "loss": 0.6625, "lr": 4.401665733793598e-06, "epoch": 1.0348249151782856, "percentage": 80.83, "elapsed_time": "18:45:33", "remaining_time": "4:27:01", "throughput": 658.18, "total_tokens": 44449440} {"current_steps": 32335, "total_steps": 40000, "loss": 0.7679, "lr": 4.3961038886619425e-06, "epoch": 1.034984956148774, "percentage": 80.84, "elapsed_time": "18:45:35", "remaining_time": "4:26:49", "throughput": 658.27, "total_tokens": 44456688} {"current_steps": 32340, "total_steps": 40000, "loss": 0.8984, "lr": 4.39054522091e-06, "epoch": 1.0351449971192626, "percentage": 80.85, "elapsed_time": "18:45:37", "remaining_time": "4:26:36", "throughput": 658.35, "total_tokens": 44463360} {"current_steps": 32345, "total_steps": 40000, "loss": 0.7167, "lr": 4.384989731394979e-06, "epoch": 1.035305038089751, "percentage": 80.86, "elapsed_time": "18:45:39", "remaining_time": "4:26:24", "throughput": 658.44, "total_tokens": 44470336} {"current_steps": 32350, "total_steps": 40000, "loss": 0.8304, "lr": 4.379437420973598e-06, "epoch": 1.0354650790602393, "percentage": 80.88, "elapsed_time": "18:45:40", "remaining_time": "4:26:11", "throughput": 658.53, "total_tokens": 44477408} {"current_steps": 32355, "total_steps": 40000, "loss": 0.6765, "lr": 4.373888290502107e-06, "epoch": 1.0356251200307278, "percentage": 80.89, "elapsed_time": "18:45:42", "remaining_time": "4:25:59", "throughput": 658.61, "total_tokens": 44484304} {"current_steps": 32360, "total_steps": 40000, "loss": 0.6692, "lr": 4.36834234083624e-06, "epoch": 1.0357851610012163, "percentage": 80.9, "elapsed_time": "18:45:44", "remaining_time": "4:25:46", "throughput": 658.69, "total_tokens": 44490784} {"current_steps": 32365, "total_steps": 40000, "loss": 0.8166, "lr": 4.362799572831258e-06, "epoch": 1.0359452019717048, "percentage": 80.91, "elapsed_time": "18:45:46", "remaining_time": "4:25:34", "throughput": 658.77, "total_tokens": 44497168} {"current_steps": 32370, "total_steps": 40000, "loss": 0.5877, "lr": 4.35725998734193e-06, "epoch": 1.0361052429421933, "percentage": 80.92, "elapsed_time": "18:45:47", "remaining_time": "4:25:21", "throughput": 658.85, "total_tokens": 44503952} {"current_steps": 32375, "total_steps": 40000, "loss": 0.5619, "lr": 4.3517235852225195e-06, "epoch": 1.0362652839126816, "percentage": 80.94, "elapsed_time": "18:45:49", "remaining_time": "4:25:09", "throughput": 658.93, "total_tokens": 44510736} {"current_steps": 32380, "total_steps": 40000, "loss": 0.8564, "lr": 4.346190367326822e-06, "epoch": 1.03642532488317, "percentage": 80.95, "elapsed_time": "18:45:51", "remaining_time": "4:24:56", "throughput": 659.02, "total_tokens": 44517760} {"current_steps": 32385, "total_steps": 40000, "loss": 0.7831, "lr": 4.340660334508115e-06, "epoch": 1.0365853658536586, "percentage": 80.96, "elapsed_time": "18:45:53", "remaining_time": "4:24:44", "throughput": 659.1, "total_tokens": 44524544} {"current_steps": 32390, "total_steps": 40000, "loss": 0.6195, "lr": 4.335133487619206e-06, "epoch": 1.036745406824147, "percentage": 80.97, "elapsed_time": "18:45:54", "remaining_time": "4:24:31", "throughput": 659.19, "total_tokens": 44531328} {"current_steps": 32395, "total_steps": 40000, "loss": 0.6829, "lr": 4.329609827512409e-06, "epoch": 1.0369054477946353, "percentage": 80.99, "elapsed_time": "18:45:56", "remaining_time": "4:24:19", "throughput": 659.28, "total_tokens": 44538880} {"current_steps": 32400, "total_steps": 40000, "loss": 0.7959, "lr": 4.324089355039531e-06, "epoch": 1.0370654887651238, "percentage": 81.0, "elapsed_time": "18:45:58", "remaining_time": "4:24:07", "throughput": 659.36, "total_tokens": 44545408} {"current_steps": 32400, "total_steps": 40000, "eval_loss": 0.7308875918388367, "epoch": 1.0370654887651238, "percentage": 81.0, "elapsed_time": "18:51:46", "remaining_time": "4:25:28", "throughput": 655.99, "total_tokens": 44545408} {"current_steps": 32405, "total_steps": 40000, "loss": 0.5471, "lr": 4.3185720710519075e-06, "epoch": 1.0372255297356123, "percentage": 81.01, "elapsed_time": "18:51:49", "remaining_time": "4:25:16", "throughput": 656.05, "total_tokens": 44552288} {"current_steps": 32410, "total_steps": 40000, "loss": 0.9073, "lr": 4.3130579764003724e-06, "epoch": 1.0373855707061008, "percentage": 81.03, "elapsed_time": "18:51:51", "remaining_time": "4:25:03", "throughput": 656.14, "total_tokens": 44559024} {"current_steps": 32415, "total_steps": 40000, "loss": 0.6639, "lr": 4.307547071935267e-06, "epoch": 1.037545611676589, "percentage": 81.04, "elapsed_time": "18:51:53", "remaining_time": "4:24:51", "throughput": 656.22, "total_tokens": 44565584} {"current_steps": 32420, "total_steps": 40000, "loss": 0.6995, "lr": 4.302039358506435e-06, "epoch": 1.0377056526470776, "percentage": 81.05, "elapsed_time": "18:51:54", "remaining_time": "4:24:38", "throughput": 656.3, "total_tokens": 44572352} {"current_steps": 32425, "total_steps": 40000, "loss": 0.7806, "lr": 4.296534836963245e-06, "epoch": 1.037865693617566, "percentage": 81.06, "elapsed_time": "18:51:56", "remaining_time": "4:24:26", "throughput": 656.38, "total_tokens": 44579312} {"current_steps": 32430, "total_steps": 40000, "loss": 0.5593, "lr": 4.291033508154555e-06, "epoch": 1.0380257345880546, "percentage": 81.08, "elapsed_time": "18:51:58", "remaining_time": "4:24:13", "throughput": 656.47, "total_tokens": 44586368} {"current_steps": 32435, "total_steps": 40000, "loss": 0.8262, "lr": 4.285535372928748e-06, "epoch": 1.038185775558543, "percentage": 81.09, "elapsed_time": "18:52:00", "remaining_time": "4:24:01", "throughput": 656.56, "total_tokens": 44593360} {"current_steps": 32440, "total_steps": 40000, "loss": 0.6072, "lr": 4.280040432133695e-06, "epoch": 1.0383458165290314, "percentage": 81.1, "elapsed_time": "18:52:01", "remaining_time": "4:23:48", "throughput": 656.64, "total_tokens": 44600000} {"current_steps": 32445, "total_steps": 40000, "loss": 0.79, "lr": 4.274548686616789e-06, "epoch": 1.0385058574995198, "percentage": 81.11, "elapsed_time": "18:52:03", "remaining_time": "4:23:36", "throughput": 656.72, "total_tokens": 44606976} {"current_steps": 32450, "total_steps": 40000, "loss": 0.8204, "lr": 4.2690601372249364e-06, "epoch": 1.0386658984700083, "percentage": 81.12, "elapsed_time": "18:52:05", "remaining_time": "4:23:23", "throughput": 656.82, "total_tokens": 44614416} {"current_steps": 32455, "total_steps": 40000, "loss": 0.7612, "lr": 4.263574784804525e-06, "epoch": 1.0388259394404968, "percentage": 81.14, "elapsed_time": "18:52:07", "remaining_time": "4:23:11", "throughput": 656.9, "total_tokens": 44621200} {"current_steps": 32460, "total_steps": 40000, "loss": 0.6737, "lr": 4.258092630201479e-06, "epoch": 1.038985980410985, "percentage": 81.15, "elapsed_time": "18:52:08", "remaining_time": "4:22:58", "throughput": 656.98, "total_tokens": 44627792} {"current_steps": 32465, "total_steps": 40000, "loss": 0.7662, "lr": 4.252613674261202e-06, "epoch": 1.0391460213814736, "percentage": 81.16, "elapsed_time": "18:52:10", "remaining_time": "4:22:46", "throughput": 657.07, "total_tokens": 44635040} {"current_steps": 32470, "total_steps": 40000, "loss": 0.7103, "lr": 4.2471379178286224e-06, "epoch": 1.039306062351962, "percentage": 81.17, "elapsed_time": "18:52:12", "remaining_time": "4:22:33", "throughput": 657.15, "total_tokens": 44641936} {"current_steps": 32475, "total_steps": 40000, "loss": 0.736, "lr": 4.241665361748181e-06, "epoch": 1.0394661033224506, "percentage": 81.19, "elapsed_time": "18:52:14", "remaining_time": "4:22:21", "throughput": 657.24, "total_tokens": 44649072} {"current_steps": 32480, "total_steps": 40000, "loss": 0.6911, "lr": 4.2361960068637994e-06, "epoch": 1.039626144292939, "percentage": 81.2, "elapsed_time": "18:52:15", "remaining_time": "4:22:08", "throughput": 657.33, "total_tokens": 44656016} {"current_steps": 32485, "total_steps": 40000, "loss": 0.5623, "lr": 4.230729854018933e-06, "epoch": 1.0397861852634274, "percentage": 81.21, "elapsed_time": "18:52:17", "remaining_time": "4:21:56", "throughput": 657.41, "total_tokens": 44662912} {"current_steps": 32490, "total_steps": 40000, "loss": 0.6564, "lr": 4.225266904056521e-06, "epoch": 1.0399462262339159, "percentage": 81.23, "elapsed_time": "18:52:19", "remaining_time": "4:21:44", "throughput": 657.5, "total_tokens": 44669888} {"current_steps": 32495, "total_steps": 40000, "loss": 0.7615, "lr": 4.21980715781903e-06, "epoch": 1.0401062672044044, "percentage": 81.24, "elapsed_time": "18:52:21", "remaining_time": "4:21:31", "throughput": 657.58, "total_tokens": 44676544} {"current_steps": 32500, "total_steps": 40000, "loss": 0.7382, "lr": 4.214350616148416e-06, "epoch": 1.0402663081748929, "percentage": 81.25, "elapsed_time": "18:52:22", "remaining_time": "4:21:19", "throughput": 657.66, "total_tokens": 44683024} {"current_steps": 32505, "total_steps": 40000, "loss": 0.9513, "lr": 4.20889727988614e-06, "epoch": 1.0404263491453811, "percentage": 81.26, "elapsed_time": "18:52:24", "remaining_time": "4:21:06", "throughput": 657.74, "total_tokens": 44690032} {"current_steps": 32510, "total_steps": 40000, "loss": 0.865, "lr": 4.20344714987318e-06, "epoch": 1.0405863901158696, "percentage": 81.27, "elapsed_time": "18:52:26", "remaining_time": "4:20:54", "throughput": 657.82, "total_tokens": 44696704} {"current_steps": 32515, "total_steps": 40000, "loss": 0.761, "lr": 4.198000226950022e-06, "epoch": 1.0407464310863581, "percentage": 81.29, "elapsed_time": "18:52:28", "remaining_time": "4:20:41", "throughput": 657.9, "total_tokens": 44703264} {"current_steps": 32520, "total_steps": 40000, "loss": 0.768, "lr": 4.192556511956635e-06, "epoch": 1.0409064720568466, "percentage": 81.3, "elapsed_time": "18:52:29", "remaining_time": "4:20:29", "throughput": 657.98, "total_tokens": 44709952} {"current_steps": 32525, "total_steps": 40000, "loss": 0.7393, "lr": 4.18711600573252e-06, "epoch": 1.041066513027335, "percentage": 81.31, "elapsed_time": "18:52:31", "remaining_time": "4:20:16", "throughput": 658.07, "total_tokens": 44716848} {"current_steps": 32530, "total_steps": 40000, "loss": 0.9478, "lr": 4.181678709116671e-06, "epoch": 1.0412265539978234, "percentage": 81.33, "elapsed_time": "18:52:33", "remaining_time": "4:20:04", "throughput": 658.16, "total_tokens": 44724256} {"current_steps": 32535, "total_steps": 40000, "loss": 0.7041, "lr": 4.1762446229475785e-06, "epoch": 1.0413865949683119, "percentage": 81.34, "elapsed_time": "18:52:35", "remaining_time": "4:19:51", "throughput": 658.25, "total_tokens": 44731152} {"current_steps": 32540, "total_steps": 40000, "loss": 0.8342, "lr": 4.17081374806326e-06, "epoch": 1.0415466359388004, "percentage": 81.35, "elapsed_time": "18:52:36", "remaining_time": "4:19:39", "throughput": 658.32, "total_tokens": 44737680} {"current_steps": 32545, "total_steps": 40000, "loss": 0.5751, "lr": 4.165386085301212e-06, "epoch": 1.0417066769092889, "percentage": 81.36, "elapsed_time": "18:52:38", "remaining_time": "4:19:27", "throughput": 658.41, "total_tokens": 44744512} {"current_steps": 32550, "total_steps": 40000, "loss": 0.5652, "lr": 4.1599616354984525e-06, "epoch": 1.0418667178797771, "percentage": 81.38, "elapsed_time": "18:52:40", "remaining_time": "4:19:14", "throughput": 658.49, "total_tokens": 44751040} {"current_steps": 32555, "total_steps": 40000, "loss": 0.6773, "lr": 4.154540399491508e-06, "epoch": 1.0420267588502656, "percentage": 81.39, "elapsed_time": "18:52:42", "remaining_time": "4:19:02", "throughput": 658.57, "total_tokens": 44757552} {"current_steps": 32560, "total_steps": 40000, "loss": 0.823, "lr": 4.149122378116394e-06, "epoch": 1.0421867998207541, "percentage": 81.4, "elapsed_time": "18:52:43", "remaining_time": "4:18:49", "throughput": 658.65, "total_tokens": 44764624} {"current_steps": 32565, "total_steps": 40000, "loss": 0.7554, "lr": 4.14370757220863e-06, "epoch": 1.0423468407912426, "percentage": 81.41, "elapsed_time": "18:52:45", "remaining_time": "4:18:37", "throughput": 658.74, "total_tokens": 44771392} {"current_steps": 32570, "total_steps": 40000, "loss": 0.659, "lr": 4.138295982603263e-06, "epoch": 1.042506881761731, "percentage": 81.42, "elapsed_time": "18:52:47", "remaining_time": "4:18:24", "throughput": 658.82, "total_tokens": 44778448} {"current_steps": 32575, "total_steps": 40000, "loss": 0.7039, "lr": 4.132887610134814e-06, "epoch": 1.0426669227322194, "percentage": 81.44, "elapsed_time": "18:52:49", "remaining_time": "4:18:12", "throughput": 658.9, "total_tokens": 44785216} {"current_steps": 32580, "total_steps": 40000, "loss": 0.5184, "lr": 4.127482455637335e-06, "epoch": 1.0428269637027079, "percentage": 81.45, "elapsed_time": "18:52:50", "remaining_time": "4:18:00", "throughput": 658.99, "total_tokens": 44792096} {"current_steps": 32585, "total_steps": 40000, "loss": 0.8364, "lr": 4.1220805199443545e-06, "epoch": 1.0429870046731964, "percentage": 81.46, "elapsed_time": "18:52:52", "remaining_time": "4:17:47", "throughput": 659.07, "total_tokens": 44798560} {"current_steps": 32590, "total_steps": 40000, "loss": 0.8258, "lr": 4.116681803888925e-06, "epoch": 1.0431470456436849, "percentage": 81.47, "elapsed_time": "18:52:54", "remaining_time": "4:17:35", "throughput": 659.15, "total_tokens": 44805648} {"current_steps": 32595, "total_steps": 40000, "loss": 0.878, "lr": 4.111286308303605e-06, "epoch": 1.0433070866141732, "percentage": 81.49, "elapsed_time": "18:52:56", "remaining_time": "4:17:22", "throughput": 659.24, "total_tokens": 44812800} {"current_steps": 32600, "total_steps": 40000, "loss": 0.5933, "lr": 4.105894034020433e-06, "epoch": 1.0434671275846616, "percentage": 81.5, "elapsed_time": "18:52:57", "remaining_time": "4:17:10", "throughput": 659.33, "total_tokens": 44819808} {"current_steps": 32600, "total_steps": 40000, "eval_loss": 0.7311064004898071, "epoch": 1.0434671275846616, "percentage": 81.5, "elapsed_time": "18:58:45", "remaining_time": "4:18:29", "throughput": 655.97, "total_tokens": 44819808} {"current_steps": 32605, "total_steps": 40000, "loss": 0.8313, "lr": 4.100504981870975e-06, "epoch": 1.0436271685551501, "percentage": 81.51, "elapsed_time": "18:58:49", "remaining_time": "4:18:17", "throughput": 656.04, "total_tokens": 44826864} {"current_steps": 32610, "total_steps": 40000, "loss": 0.8608, "lr": 4.0951191526862915e-06, "epoch": 1.0437872095256386, "percentage": 81.53, "elapsed_time": "18:58:51", "remaining_time": "4:18:05", "throughput": 656.12, "total_tokens": 44833456} {"current_steps": 32615, "total_steps": 40000, "loss": 0.7574, "lr": 4.089736547296938e-06, "epoch": 1.043947250496127, "percentage": 81.54, "elapsed_time": "18:58:52", "remaining_time": "4:17:52", "throughput": 656.2, "total_tokens": 44840096} {"current_steps": 32620, "total_steps": 40000, "loss": 0.7481, "lr": 4.08435716653299e-06, "epoch": 1.0441072914666154, "percentage": 81.55, "elapsed_time": "18:58:54", "remaining_time": "4:17:40", "throughput": 656.28, "total_tokens": 44846576} {"current_steps": 32625, "total_steps": 40000, "loss": 0.7799, "lr": 4.0789810112240005e-06, "epoch": 1.044267332437104, "percentage": 81.56, "elapsed_time": "18:58:56", "remaining_time": "4:17:27", "throughput": 656.36, "total_tokens": 44853232} {"current_steps": 32630, "total_steps": 40000, "loss": 0.6782, "lr": 4.073608082199057e-06, "epoch": 1.0444273734075924, "percentage": 81.58, "elapsed_time": "18:58:58", "remaining_time": "4:17:15", "throughput": 656.44, "total_tokens": 44859824} {"current_steps": 32635, "total_steps": 40000, "loss": 0.5612, "lr": 4.068238380286718e-06, "epoch": 1.044587414378081, "percentage": 81.59, "elapsed_time": "18:58:59", "remaining_time": "4:17:02", "throughput": 656.52, "total_tokens": 44866416} {"current_steps": 32640, "total_steps": 40000, "loss": 0.8503, "lr": 4.062871906315072e-06, "epoch": 1.0447474553485692, "percentage": 81.6, "elapsed_time": "18:59:01", "remaining_time": "4:16:50", "throughput": 656.6, "total_tokens": 44872976} {"current_steps": 32645, "total_steps": 40000, "loss": 0.6652, "lr": 4.057508661111686e-06, "epoch": 1.0449074963190577, "percentage": 81.61, "elapsed_time": "18:59:03", "remaining_time": "4:16:37", "throughput": 656.68, "total_tokens": 44880000} {"current_steps": 32650, "total_steps": 40000, "loss": 0.799, "lr": 4.052148645503648e-06, "epoch": 1.0450675372895462, "percentage": 81.62, "elapsed_time": "18:59:05", "remaining_time": "4:16:25", "throughput": 656.77, "total_tokens": 44887376} {"current_steps": 32655, "total_steps": 40000, "loss": 0.8316, "lr": 4.046791860317531e-06, "epoch": 1.0452275782600347, "percentage": 81.64, "elapsed_time": "18:59:06", "remaining_time": "4:16:13", "throughput": 656.86, "total_tokens": 44894560} {"current_steps": 32660, "total_steps": 40000, "loss": 0.7673, "lr": 4.041438306379431e-06, "epoch": 1.045387619230523, "percentage": 81.65, "elapsed_time": "18:59:08", "remaining_time": "4:16:00", "throughput": 656.95, "total_tokens": 44901792} {"current_steps": 32665, "total_steps": 40000, "loss": 0.8076, "lr": 4.036087984514916e-06, "epoch": 1.0455476602010114, "percentage": 81.66, "elapsed_time": "18:59:10", "remaining_time": "4:15:48", "throughput": 657.04, "total_tokens": 44909040} {"current_steps": 32670, "total_steps": 40000, "loss": 1.0044, "lr": 4.030740895549084e-06, "epoch": 1.0457077011715, "percentage": 81.67, "elapsed_time": "18:59:12", "remaining_time": "4:15:35", "throughput": 657.13, "total_tokens": 44915920} {"current_steps": 32675, "total_steps": 40000, "loss": 0.7566, "lr": 4.025397040306531e-06, "epoch": 1.0458677421419884, "percentage": 81.69, "elapsed_time": "18:59:13", "remaining_time": "4:15:23", "throughput": 657.21, "total_tokens": 44922640} {"current_steps": 32680, "total_steps": 40000, "loss": 0.7476, "lr": 4.0200564196113285e-06, "epoch": 1.0460277831124767, "percentage": 81.7, "elapsed_time": "18:59:15", "remaining_time": "4:15:11", "throughput": 657.29, "total_tokens": 44929632} {"current_steps": 32685, "total_steps": 40000, "loss": 0.8227, "lr": 4.014719034287079e-06, "epoch": 1.0461878240829652, "percentage": 81.71, "elapsed_time": "18:59:17", "remaining_time": "4:14:58", "throughput": 657.38, "total_tokens": 44936912} {"current_steps": 32690, "total_steps": 40000, "loss": 0.8005, "lr": 4.0093848851568775e-06, "epoch": 1.0463478650534537, "percentage": 81.73, "elapsed_time": "18:59:19", "remaining_time": "4:14:46", "throughput": 657.47, "total_tokens": 44944016} {"current_steps": 32695, "total_steps": 40000, "loss": 0.6561, "lr": 4.004053973043304e-06, "epoch": 1.0465079060239422, "percentage": 81.74, "elapsed_time": "18:59:20", "remaining_time": "4:14:33", "throughput": 657.55, "total_tokens": 44950720} {"current_steps": 32700, "total_steps": 40000, "loss": 0.8074, "lr": 3.998726298768465e-06, "epoch": 1.0466679469944307, "percentage": 81.75, "elapsed_time": "18:59:22", "remaining_time": "4:14:21", "throughput": 657.63, "total_tokens": 44957632} {"current_steps": 32705, "total_steps": 40000, "loss": 0.6457, "lr": 3.99340186315395e-06, "epoch": 1.046827987964919, "percentage": 81.76, "elapsed_time": "18:59:24", "remaining_time": "4:14:08", "throughput": 657.71, "total_tokens": 44964256} {"current_steps": 32710, "total_steps": 40000, "loss": 0.6765, "lr": 3.988080667020849e-06, "epoch": 1.0469880289354074, "percentage": 81.77, "elapsed_time": "18:59:26", "remaining_time": "4:13:56", "throughput": 657.8, "total_tokens": 44971376} {"current_steps": 32715, "total_steps": 40000, "loss": 0.82, "lr": 3.982762711189766e-06, "epoch": 1.047148069905896, "percentage": 81.79, "elapsed_time": "18:59:27", "remaining_time": "4:13:44", "throughput": 657.89, "total_tokens": 44978416} {"current_steps": 32720, "total_steps": 40000, "loss": 0.6089, "lr": 3.977447996480785e-06, "epoch": 1.0473081108763844, "percentage": 81.8, "elapsed_time": "18:59:30", "remaining_time": "4:13:31", "throughput": 657.97, "total_tokens": 44985696} {"current_steps": 32725, "total_steps": 40000, "loss": 0.9521, "lr": 3.97213652371351e-06, "epoch": 1.0474681518468727, "percentage": 81.81, "elapsed_time": "18:59:31", "remaining_time": "4:13:19", "throughput": 658.07, "total_tokens": 44993184} {"current_steps": 32730, "total_steps": 40000, "loss": 0.7421, "lr": 3.966828293707042e-06, "epoch": 1.0476281928173612, "percentage": 81.83, "elapsed_time": "18:59:33", "remaining_time": "4:13:07", "throughput": 658.15, "total_tokens": 45000256} {"current_steps": 32735, "total_steps": 40000, "loss": 0.7351, "lr": 3.961523307279963e-06, "epoch": 1.0477882337878497, "percentage": 81.84, "elapsed_time": "18:59:35", "remaining_time": "4:12:54", "throughput": 658.24, "total_tokens": 45007104} {"current_steps": 32740, "total_steps": 40000, "loss": 0.7782, "lr": 3.956221565250382e-06, "epoch": 1.0479482747583382, "percentage": 81.85, "elapsed_time": "18:59:36", "remaining_time": "4:12:42", "throughput": 658.33, "total_tokens": 45014368} {"current_steps": 32745, "total_steps": 40000, "loss": 0.7006, "lr": 3.950923068435883e-06, "epoch": 1.0481083157288267, "percentage": 81.86, "elapsed_time": "18:59:38", "remaining_time": "4:12:30", "throughput": 658.42, "total_tokens": 45021872} {"current_steps": 32750, "total_steps": 40000, "loss": 0.6795, "lr": 3.945627817653566e-06, "epoch": 1.048268356699315, "percentage": 81.88, "elapsed_time": "18:59:40", "remaining_time": "4:12:17", "throughput": 658.5, "total_tokens": 45028688} {"current_steps": 32755, "total_steps": 40000, "loss": 0.6337, "lr": 3.9403358137200335e-06, "epoch": 1.0484283976698034, "percentage": 81.89, "elapsed_time": "18:59:42", "remaining_time": "4:12:05", "throughput": 658.59, "total_tokens": 45036032} {"current_steps": 32760, "total_steps": 40000, "loss": 0.8226, "lr": 3.9350470574513605e-06, "epoch": 1.048588438640292, "percentage": 81.9, "elapsed_time": "18:59:44", "remaining_time": "4:11:52", "throughput": 658.68, "total_tokens": 45043120} {"current_steps": 32765, "total_steps": 40000, "loss": 0.6766, "lr": 3.9297615496631525e-06, "epoch": 1.0487484796107804, "percentage": 81.91, "elapsed_time": "18:59:45", "remaining_time": "4:11:40", "throughput": 658.77, "total_tokens": 45050240} {"current_steps": 32770, "total_steps": 40000, "loss": 0.6177, "lr": 3.924479291170505e-06, "epoch": 1.0489085205812687, "percentage": 81.92, "elapsed_time": "18:59:47", "remaining_time": "4:11:28", "throughput": 658.85, "total_tokens": 45057232} {"current_steps": 32775, "total_steps": 40000, "loss": 0.8003, "lr": 3.919200282788002e-06, "epoch": 1.0490685615517572, "percentage": 81.94, "elapsed_time": "18:59:49", "remaining_time": "4:11:15", "throughput": 658.94, "total_tokens": 45064432} {"current_steps": 32780, "total_steps": 40000, "loss": 0.7153, "lr": 3.913924525329726e-06, "epoch": 1.0492286025222457, "percentage": 81.95, "elapsed_time": "18:59:51", "remaining_time": "4:11:03", "throughput": 659.02, "total_tokens": 45071280} {"current_steps": 32785, "total_steps": 40000, "loss": 0.7479, "lr": 3.908652019609279e-06, "epoch": 1.0493886434927342, "percentage": 81.96, "elapsed_time": "18:59:52", "remaining_time": "4:10:51", "throughput": 659.1, "total_tokens": 45078016} {"current_steps": 32790, "total_steps": 40000, "loss": 0.7212, "lr": 3.9033827664397364e-06, "epoch": 1.0495486844632227, "percentage": 81.97, "elapsed_time": "18:59:54", "remaining_time": "4:10:38", "throughput": 659.19, "total_tokens": 45084768} {"current_steps": 32795, "total_steps": 40000, "loss": 0.4811, "lr": 3.898116766633694e-06, "epoch": 1.049708725433711, "percentage": 81.99, "elapsed_time": "18:59:56", "remaining_time": "4:10:26", "throughput": 659.26, "total_tokens": 45091152} {"current_steps": 32800, "total_steps": 40000, "loss": 0.6621, "lr": 3.8928540210032225e-06, "epoch": 1.0498687664041995, "percentage": 82.0, "elapsed_time": "18:59:58", "remaining_time": "4:10:14", "throughput": 659.34, "total_tokens": 45097904} {"current_steps": 32800, "total_steps": 40000, "eval_loss": 0.7309221029281616, "epoch": 1.0498687664041995, "percentage": 82.0, "elapsed_time": "19:05:45", "remaining_time": "4:11:30", "throughput": 656.01, "total_tokens": 45097904} {"current_steps": 32805, "total_steps": 40000, "loss": 0.6705, "lr": 3.887594530359909e-06, "epoch": 1.050028807374688, "percentage": 82.01, "elapsed_time": "19:05:48", "remaining_time": "4:11:18", "throughput": 656.08, "total_tokens": 45104928} {"current_steps": 32810, "total_steps": 40000, "loss": 0.7625, "lr": 3.88233829551484e-06, "epoch": 1.0501888483451765, "percentage": 82.03, "elapsed_time": "19:05:50", "remaining_time": "4:11:06", "throughput": 656.17, "total_tokens": 45111968} {"current_steps": 32815, "total_steps": 40000, "loss": 0.6291, "lr": 3.877085317278581e-06, "epoch": 1.0503488893156647, "percentage": 82.04, "elapsed_time": "19:05:52", "remaining_time": "4:10:53", "throughput": 656.25, "total_tokens": 45118976} {"current_steps": 32820, "total_steps": 40000, "loss": 0.8093, "lr": 3.87183559646122e-06, "epoch": 1.0505089302861532, "percentage": 82.05, "elapsed_time": "19:05:54", "remaining_time": "4:10:41", "throughput": 656.33, "total_tokens": 45125760} {"current_steps": 32825, "total_steps": 40000, "loss": 0.7908, "lr": 3.866589133872317e-06, "epoch": 1.0506689712566417, "percentage": 82.06, "elapsed_time": "19:05:55", "remaining_time": "4:10:28", "throughput": 656.42, "total_tokens": 45132912} {"current_steps": 32830, "total_steps": 40000, "loss": 0.6112, "lr": 3.861345930320948e-06, "epoch": 1.0508290122271302, "percentage": 82.08, "elapsed_time": "19:05:57", "remaining_time": "4:10:16", "throughput": 656.5, "total_tokens": 45139488} {"current_steps": 32835, "total_steps": 40000, "loss": 0.7815, "lr": 3.856105986615688e-06, "epoch": 1.0509890531976185, "percentage": 82.09, "elapsed_time": "19:05:59", "remaining_time": "4:10:04", "throughput": 656.59, "total_tokens": 45146624} {"current_steps": 32840, "total_steps": 40000, "loss": 0.6506, "lr": 3.850869303564589e-06, "epoch": 1.051149094168107, "percentage": 82.1, "elapsed_time": "19:06:01", "remaining_time": "4:09:51", "throughput": 656.67, "total_tokens": 45153760} {"current_steps": 32845, "total_steps": 40000, "loss": 0.8935, "lr": 3.845635881975226e-06, "epoch": 1.0513091351385955, "percentage": 82.11, "elapsed_time": "19:06:02", "remaining_time": "4:09:39", "throughput": 656.77, "total_tokens": 45161232} {"current_steps": 32850, "total_steps": 40000, "loss": 0.7165, "lr": 3.840405722654647e-06, "epoch": 1.051469176109084, "percentage": 82.12, "elapsed_time": "19:06:04", "remaining_time": "4:09:27", "throughput": 656.86, "total_tokens": 45168560} {"current_steps": 32855, "total_steps": 40000, "loss": 0.7013, "lr": 3.835178826409419e-06, "epoch": 1.0516292170795725, "percentage": 82.14, "elapsed_time": "19:06:06", "remaining_time": "4:09:14", "throughput": 656.94, "total_tokens": 45175360} {"current_steps": 32860, "total_steps": 40000, "loss": 0.6974, "lr": 3.8299551940455895e-06, "epoch": 1.0517892580500607, "percentage": 82.15, "elapsed_time": "19:06:08", "remaining_time": "4:09:02", "throughput": 657.02, "total_tokens": 45182320} {"current_steps": 32865, "total_steps": 40000, "loss": 0.7306, "lr": 3.824734826368703e-06, "epoch": 1.0519492990205492, "percentage": 82.16, "elapsed_time": "19:06:10", "remaining_time": "4:08:49", "throughput": 657.11, "total_tokens": 45189312} {"current_steps": 32870, "total_steps": 40000, "loss": 0.7268, "lr": 3.819517724183813e-06, "epoch": 1.0521093399910377, "percentage": 82.17, "elapsed_time": "19:06:11", "remaining_time": "4:08:37", "throughput": 657.19, "total_tokens": 45196304} {"current_steps": 32875, "total_steps": 40000, "loss": 0.689, "lr": 3.8143038882954648e-06, "epoch": 1.0522693809615262, "percentage": 82.19, "elapsed_time": "19:06:13", "remaining_time": "4:08:25", "throughput": 657.27, "total_tokens": 45203040} {"current_steps": 32880, "total_steps": 40000, "loss": 0.9029, "lr": 3.8090933195076867e-06, "epoch": 1.0524294219320145, "percentage": 82.2, "elapsed_time": "19:06:15", "remaining_time": "4:08:12", "throughput": 657.36, "total_tokens": 45210128} {"current_steps": 32885, "total_steps": 40000, "loss": 0.5519, "lr": 3.8038860186240198e-06, "epoch": 1.052589462902503, "percentage": 82.21, "elapsed_time": "19:06:17", "remaining_time": "4:08:00", "throughput": 657.45, "total_tokens": 45217584} {"current_steps": 32890, "total_steps": 40000, "loss": 0.6414, "lr": 3.7986819864475026e-06, "epoch": 1.0527495038729915, "percentage": 82.23, "elapsed_time": "19:06:18", "remaining_time": "4:07:48", "throughput": 657.53, "total_tokens": 45223872} {"current_steps": 32895, "total_steps": 40000, "loss": 0.6463, "lr": 3.793481223780651e-06, "epoch": 1.05290954484348, "percentage": 82.24, "elapsed_time": "19:06:20", "remaining_time": "4:07:35", "throughput": 657.61, "total_tokens": 45230496} {"current_steps": 32900, "total_steps": 40000, "loss": 0.6097, "lr": 3.788283731425496e-06, "epoch": 1.0530695858139685, "percentage": 82.25, "elapsed_time": "19:06:22", "remaining_time": "4:07:23", "throughput": 657.69, "total_tokens": 45237552} {"current_steps": 32905, "total_steps": 40000, "loss": 0.6597, "lr": 3.7830895101835488e-06, "epoch": 1.0532296267844568, "percentage": 82.26, "elapsed_time": "19:06:24", "remaining_time": "4:07:11", "throughput": 657.78, "total_tokens": 45244512} {"current_steps": 32910, "total_steps": 40000, "loss": 0.6912, "lr": 3.7778985608558274e-06, "epoch": 1.0533896677549452, "percentage": 82.27, "elapsed_time": "19:06:25", "remaining_time": "4:06:58", "throughput": 657.86, "total_tokens": 45251440} {"current_steps": 32915, "total_steps": 40000, "loss": 0.6809, "lr": 3.7727108842428443e-06, "epoch": 1.0535497087254337, "percentage": 82.29, "elapsed_time": "19:06:27", "remaining_time": "4:06:46", "throughput": 657.94, "total_tokens": 45258048} {"current_steps": 32920, "total_steps": 40000, "loss": 0.7551, "lr": 3.7675264811446065e-06, "epoch": 1.0537097496959222, "percentage": 82.3, "elapsed_time": "19:06:29", "remaining_time": "4:06:34", "throughput": 658.02, "total_tokens": 45264944} {"current_steps": 32925, "total_steps": 40000, "loss": 0.7743, "lr": 3.7623453523605994e-06, "epoch": 1.0538697906664105, "percentage": 82.31, "elapsed_time": "19:06:31", "remaining_time": "4:06:22", "throughput": 658.1, "total_tokens": 45271760} {"current_steps": 32930, "total_steps": 40000, "loss": 0.6232, "lr": 3.757167498689834e-06, "epoch": 1.054029831636899, "percentage": 82.33, "elapsed_time": "19:06:32", "remaining_time": "4:06:09", "throughput": 658.19, "total_tokens": 45278656} {"current_steps": 32935, "total_steps": 40000, "loss": 0.7077, "lr": 3.7519929209307914e-06, "epoch": 1.0541898726073875, "percentage": 82.34, "elapsed_time": "19:06:34", "remaining_time": "4:05:57", "throughput": 658.27, "total_tokens": 45285312} {"current_steps": 32940, "total_steps": 40000, "loss": 0.7233, "lr": 3.746821619881463e-06, "epoch": 1.054349913577876, "percentage": 82.35, "elapsed_time": "19:06:36", "remaining_time": "4:05:45", "throughput": 658.36, "total_tokens": 45292592} {"current_steps": 32945, "total_steps": 40000, "loss": 0.5594, "lr": 3.74165359633932e-06, "epoch": 1.0545099545483643, "percentage": 82.36, "elapsed_time": "19:06:38", "remaining_time": "4:05:32", "throughput": 658.44, "total_tokens": 45299392} {"current_steps": 32950, "total_steps": 40000, "loss": 0.6298, "lr": 3.736488851101341e-06, "epoch": 1.0546699955188528, "percentage": 82.38, "elapsed_time": "19:06:39", "remaining_time": "4:05:20", "throughput": 658.53, "total_tokens": 45306640} {"current_steps": 32955, "total_steps": 40000, "loss": 0.8273, "lr": 3.7313273849640035e-06, "epoch": 1.0548300364893413, "percentage": 82.39, "elapsed_time": "19:06:41", "remaining_time": "4:05:08", "throughput": 658.62, "total_tokens": 45313888} {"current_steps": 32960, "total_steps": 40000, "loss": 0.7594, "lr": 3.7261691987232533e-06, "epoch": 1.0549900774598298, "percentage": 82.4, "elapsed_time": "19:06:43", "remaining_time": "4:04:55", "throughput": 658.7, "total_tokens": 45321136} {"current_steps": 32965, "total_steps": 40000, "loss": 0.842, "lr": 3.7210142931745575e-06, "epoch": 1.0551501184303183, "percentage": 82.41, "elapsed_time": "19:06:45", "remaining_time": "4:04:43", "throughput": 658.78, "total_tokens": 45327488} {"current_steps": 32970, "total_steps": 40000, "loss": 0.6534, "lr": 3.7158626691128712e-06, "epoch": 1.0553101594008065, "percentage": 82.42, "elapsed_time": "19:06:46", "remaining_time": "4:04:31", "throughput": 658.87, "total_tokens": 45334704} {"current_steps": 32975, "total_steps": 40000, "loss": 0.6837, "lr": 3.710714327332629e-06, "epoch": 1.055470200371295, "percentage": 82.44, "elapsed_time": "19:06:48", "remaining_time": "4:04:19", "throughput": 658.95, "total_tokens": 45341328} {"current_steps": 32980, "total_steps": 40000, "loss": 0.6214, "lr": 3.7055692686277815e-06, "epoch": 1.0556302413417835, "percentage": 82.45, "elapsed_time": "19:06:50", "remaining_time": "4:04:06", "throughput": 659.03, "total_tokens": 45348016} {"current_steps": 32985, "total_steps": 40000, "loss": 0.8805, "lr": 3.70042749379175e-06, "epoch": 1.055790282312272, "percentage": 82.46, "elapsed_time": "19:06:52", "remaining_time": "4:03:54", "throughput": 659.13, "total_tokens": 45355952} {"current_steps": 32990, "total_steps": 40000, "loss": 0.5706, "lr": 3.6952890036174693e-06, "epoch": 1.0559503232827603, "percentage": 82.47, "elapsed_time": "19:06:53", "remaining_time": "4:03:42", "throughput": 659.21, "total_tokens": 45362672} {"current_steps": 32995, "total_steps": 40000, "loss": 0.6121, "lr": 3.690153798897353e-06, "epoch": 1.0561103642532488, "percentage": 82.49, "elapsed_time": "19:06:55", "remaining_time": "4:03:29", "throughput": 659.29, "total_tokens": 45369472} {"current_steps": 33000, "total_steps": 40000, "loss": 0.7677, "lr": 3.6850218804233225e-06, "epoch": 1.0562704052237373, "percentage": 82.5, "elapsed_time": "19:06:57", "remaining_time": "4:03:17", "throughput": 659.37, "total_tokens": 45376272} {"current_steps": 33000, "total_steps": 40000, "eval_loss": 0.7308381199836731, "epoch": 1.0562704052237373, "percentage": 82.5, "elapsed_time": "19:12:45", "remaining_time": "4:04:31", "throughput": 656.06, "total_tokens": 45376272} {"current_steps": 33005, "total_steps": 40000, "loss": 0.7541, "lr": 3.679893248986779e-06, "epoch": 1.0564304461942258, "percentage": 82.51, "elapsed_time": "19:12:48", "remaining_time": "4:04:19", "throughput": 656.12, "total_tokens": 45382896} {"current_steps": 33010, "total_steps": 40000, "loss": 0.6658, "lr": 3.6747679053786147e-06, "epoch": 1.0565904871647143, "percentage": 82.53, "elapsed_time": "19:12:50", "remaining_time": "4:04:07", "throughput": 656.2, "total_tokens": 45389680} {"current_steps": 33015, "total_steps": 40000, "loss": 0.8421, "lr": 3.669645850389228e-06, "epoch": 1.0567505281352025, "percentage": 82.54, "elapsed_time": "19:12:52", "remaining_time": "4:03:54", "throughput": 656.29, "total_tokens": 45396816} {"current_steps": 33020, "total_steps": 40000, "loss": 0.7762, "lr": 3.664527084808514e-06, "epoch": 1.056910569105691, "percentage": 82.55, "elapsed_time": "19:12:53", "remaining_time": "4:03:42", "throughput": 656.37, "total_tokens": 45403552} {"current_steps": 33025, "total_steps": 40000, "loss": 0.7669, "lr": 3.6594116094258337e-06, "epoch": 1.0570706100761795, "percentage": 82.56, "elapsed_time": "19:12:55", "remaining_time": "4:03:30", "throughput": 656.46, "total_tokens": 45410784} {"current_steps": 33030, "total_steps": 40000, "loss": 0.9633, "lr": 3.6542994250300665e-06, "epoch": 1.057230651046668, "percentage": 82.58, "elapsed_time": "19:12:57", "remaining_time": "4:03:17", "throughput": 656.53, "total_tokens": 45417264} {"current_steps": 33035, "total_steps": 40000, "loss": 0.6111, "lr": 3.6491905324095825e-06, "epoch": 1.0573906920171563, "percentage": 82.59, "elapsed_time": "19:12:59", "remaining_time": "4:03:05", "throughput": 656.61, "total_tokens": 45424000} {"current_steps": 33040, "total_steps": 40000, "loss": 0.7971, "lr": 3.644084932352221e-06, "epoch": 1.0575507329876448, "percentage": 82.6, "elapsed_time": "19:13:00", "remaining_time": "4:02:53", "throughput": 656.69, "total_tokens": 45430752} {"current_steps": 33045, "total_steps": 40000, "loss": 0.9412, "lr": 3.6389826256453457e-06, "epoch": 1.0577107739581333, "percentage": 82.61, "elapsed_time": "19:13:02", "remaining_time": "4:02:40", "throughput": 656.77, "total_tokens": 45437296} {"current_steps": 33050, "total_steps": 40000, "loss": 0.8313, "lr": 3.633883613075781e-06, "epoch": 1.0578708149286218, "percentage": 82.62, "elapsed_time": "19:13:04", "remaining_time": "4:02:28", "throughput": 656.85, "total_tokens": 45443872} {"current_steps": 33055, "total_steps": 40000, "loss": 0.8398, "lr": 3.6287878954298693e-06, "epoch": 1.0580308558991103, "percentage": 82.64, "elapsed_time": "19:13:06", "remaining_time": "4:02:16", "throughput": 656.93, "total_tokens": 45450544} {"current_steps": 33060, "total_steps": 40000, "loss": 0.5303, "lr": 3.6236954734934354e-06, "epoch": 1.0581908968695986, "percentage": 82.65, "elapsed_time": "19:13:08", "remaining_time": "4:02:04", "throughput": 657.01, "total_tokens": 45457504} {"current_steps": 33065, "total_steps": 40000, "loss": 0.8751, "lr": 3.618606348051784e-06, "epoch": 1.058350937840087, "percentage": 82.66, "elapsed_time": "19:13:09", "remaining_time": "4:01:51", "throughput": 657.1, "total_tokens": 45464320} {"current_steps": 33070, "total_steps": 40000, "loss": 0.8513, "lr": 3.6135205198897376e-06, "epoch": 1.0585109788105755, "percentage": 82.67, "elapsed_time": "19:13:11", "remaining_time": "4:01:39", "throughput": 657.17, "total_tokens": 45470816} {"current_steps": 33075, "total_steps": 40000, "loss": 0.8807, "lr": 3.6084379897915854e-06, "epoch": 1.058671019781064, "percentage": 82.69, "elapsed_time": "19:13:13", "remaining_time": "4:01:27", "throughput": 657.25, "total_tokens": 45477456} {"current_steps": 33080, "total_steps": 40000, "loss": 0.713, "lr": 3.6033587585411115e-06, "epoch": 1.0588310607515523, "percentage": 82.7, "elapsed_time": "19:13:15", "remaining_time": "4:01:14", "throughput": 657.33, "total_tokens": 45484272} {"current_steps": 33085, "total_steps": 40000, "loss": 0.8228, "lr": 3.5982828269216117e-06, "epoch": 1.0589911017220408, "percentage": 82.71, "elapsed_time": "19:13:16", "remaining_time": "4:01:02", "throughput": 657.41, "total_tokens": 45490752} {"current_steps": 33090, "total_steps": 40000, "loss": 0.5558, "lr": 3.593210195715843e-06, "epoch": 1.0591511426925293, "percentage": 82.73, "elapsed_time": "19:13:18", "remaining_time": "4:00:50", "throughput": 657.49, "total_tokens": 45497584} {"current_steps": 33095, "total_steps": 40000, "loss": 0.8033, "lr": 3.5881408657060773e-06, "epoch": 1.0593111836630178, "percentage": 82.74, "elapsed_time": "19:13:20", "remaining_time": "4:00:38", "throughput": 657.58, "total_tokens": 45504416} {"current_steps": 33100, "total_steps": 40000, "loss": 0.6784, "lr": 3.583074837674075e-06, "epoch": 1.059471224633506, "percentage": 82.75, "elapsed_time": "19:13:22", "remaining_time": "4:00:25", "throughput": 657.66, "total_tokens": 45511312} {"current_steps": 33105, "total_steps": 40000, "loss": 0.6408, "lr": 3.578012112401069e-06, "epoch": 1.0596312656039946, "percentage": 82.76, "elapsed_time": "19:13:23", "remaining_time": "4:00:13", "throughput": 657.74, "total_tokens": 45517840} {"current_steps": 33110, "total_steps": 40000, "loss": 0.7523, "lr": 3.5729526906677996e-06, "epoch": 1.059791306574483, "percentage": 82.78, "elapsed_time": "19:13:25", "remaining_time": "4:00:01", "throughput": 657.82, "total_tokens": 45524944} {"current_steps": 33115, "total_steps": 40000, "loss": 0.6559, "lr": 3.5678965732545007e-06, "epoch": 1.0599513475449716, "percentage": 82.79, "elapsed_time": "19:13:27", "remaining_time": "3:59:49", "throughput": 657.91, "total_tokens": 45532336} {"current_steps": 33120, "total_steps": 40000, "loss": 0.8823, "lr": 3.562843760940876e-06, "epoch": 1.06011138851546, "percentage": 82.8, "elapsed_time": "19:13:29", "remaining_time": "3:59:36", "throughput": 657.99, "total_tokens": 45539056} {"current_steps": 33125, "total_steps": 40000, "loss": 0.9134, "lr": 3.5577942545061473e-06, "epoch": 1.0602714294859483, "percentage": 82.81, "elapsed_time": "19:13:30", "remaining_time": "3:59:24", "throughput": 658.07, "total_tokens": 45545872} {"current_steps": 33130, "total_steps": 40000, "loss": 0.5767, "lr": 3.5527480547289967e-06, "epoch": 1.0604314704564368, "percentage": 82.83, "elapsed_time": "19:13:32", "remaining_time": "3:59:12", "throughput": 658.15, "total_tokens": 45552432} {"current_steps": 33135, "total_steps": 40000, "loss": 0.8385, "lr": 3.547705162387624e-06, "epoch": 1.0605915114269253, "percentage": 82.84, "elapsed_time": "19:13:34", "remaining_time": "3:59:00", "throughput": 658.23, "total_tokens": 45559072} {"current_steps": 33140, "total_steps": 40000, "loss": 0.7459, "lr": 3.542665578259699e-06, "epoch": 1.0607515523974138, "percentage": 82.85, "elapsed_time": "19:13:36", "remaining_time": "3:58:47", "throughput": 658.33, "total_tokens": 45566896} {"current_steps": 33145, "total_steps": 40000, "loss": 0.6841, "lr": 3.5376293031223945e-06, "epoch": 1.060911593367902, "percentage": 82.86, "elapsed_time": "19:13:37", "remaining_time": "3:58:35", "throughput": 658.41, "total_tokens": 45573664} {"current_steps": 33150, "total_steps": 40000, "loss": 0.8295, "lr": 3.5325963377523614e-06, "epoch": 1.0610716343383906, "percentage": 82.88, "elapsed_time": "19:13:39", "remaining_time": "3:58:23", "throughput": 658.49, "total_tokens": 45580128} {"current_steps": 33155, "total_steps": 40000, "loss": 0.9144, "lr": 3.5275666829257536e-06, "epoch": 1.061231675308879, "percentage": 82.89, "elapsed_time": "19:13:41", "remaining_time": "3:58:11", "throughput": 658.57, "total_tokens": 45587136} {"current_steps": 33160, "total_steps": 40000, "loss": 0.5045, "lr": 3.5225403394181955e-06, "epoch": 1.0613917162793676, "percentage": 82.9, "elapsed_time": "19:13:43", "remaining_time": "3:57:58", "throughput": 658.65, "total_tokens": 45594016} {"current_steps": 33165, "total_steps": 40000, "loss": 0.952, "lr": 3.517517308004828e-06, "epoch": 1.061551757249856, "percentage": 82.91, "elapsed_time": "19:13:44", "remaining_time": "3:57:46", "throughput": 658.73, "total_tokens": 45600832} {"current_steps": 33170, "total_steps": 40000, "loss": 0.7959, "lr": 3.512497589460251e-06, "epoch": 1.0617117982203443, "percentage": 82.93, "elapsed_time": "19:13:46", "remaining_time": "3:57:34", "throughput": 658.82, "total_tokens": 45607808} {"current_steps": 33175, "total_steps": 40000, "loss": 0.7305, "lr": 3.5074811845585727e-06, "epoch": 1.0618718391908328, "percentage": 82.94, "elapsed_time": "19:13:48", "remaining_time": "3:57:22", "throughput": 658.9, "total_tokens": 45614688} {"current_steps": 33180, "total_steps": 40000, "loss": 0.6727, "lr": 3.5024680940733937e-06, "epoch": 1.0620318801613213, "percentage": 82.95, "elapsed_time": "19:13:50", "remaining_time": "3:57:09", "throughput": 658.98, "total_tokens": 45621632} {"current_steps": 33185, "total_steps": 40000, "loss": 0.7958, "lr": 3.4974583187777852e-06, "epoch": 1.0621919211318098, "percentage": 82.96, "elapsed_time": "19:13:51", "remaining_time": "3:56:57", "throughput": 659.06, "total_tokens": 45628288} {"current_steps": 33190, "total_steps": 40000, "loss": 0.7509, "lr": 3.4924518594443204e-06, "epoch": 1.062351962102298, "percentage": 82.97, "elapsed_time": "19:13:53", "remaining_time": "3:56:45", "throughput": 659.14, "total_tokens": 45634816} {"current_steps": 33195, "total_steps": 40000, "loss": 0.6893, "lr": 3.4874487168450682e-06, "epoch": 1.0625120030727866, "percentage": 82.99, "elapsed_time": "19:13:55", "remaining_time": "3:56:33", "throughput": 659.22, "total_tokens": 45641472} {"current_steps": 33200, "total_steps": 40000, "loss": 0.7354, "lr": 3.482448891751558e-06, "epoch": 1.062672044043275, "percentage": 83.0, "elapsed_time": "19:13:57", "remaining_time": "3:56:21", "throughput": 659.3, "total_tokens": 45647824} {"current_steps": 33200, "total_steps": 40000, "eval_loss": 0.7306894659996033, "epoch": 1.062672044043275, "percentage": 83.0, "elapsed_time": "19:19:45", "remaining_time": "3:57:32", "throughput": 656.0, "total_tokens": 45647824} {"current_steps": 33205, "total_steps": 40000, "loss": 0.7001, "lr": 3.477452384934843e-06, "epoch": 1.0628320850137636, "percentage": 83.01, "elapsed_time": "19:19:48", "remaining_time": "3:57:20", "throughput": 656.07, "total_tokens": 45654768} {"current_steps": 33210, "total_steps": 40000, "loss": 0.7739, "lr": 3.472459197165434e-06, "epoch": 1.0629921259842519, "percentage": 83.03, "elapsed_time": "19:19:50", "remaining_time": "3:57:08", "throughput": 656.15, "total_tokens": 45661536} {"current_steps": 33215, "total_steps": 40000, "loss": 0.5955, "lr": 3.4674693292133518e-06, "epoch": 1.0631521669547404, "percentage": 83.04, "elapsed_time": "19:19:52", "remaining_time": "3:56:55", "throughput": 656.22, "total_tokens": 45668128} {"current_steps": 33220, "total_steps": 40000, "loss": 0.6122, "lr": 3.4624827818480977e-06, "epoch": 1.0633122079252288, "percentage": 83.05, "elapsed_time": "19:19:54", "remaining_time": "3:56:43", "throughput": 656.31, "total_tokens": 45675040} {"current_steps": 33225, "total_steps": 40000, "loss": 0.6827, "lr": 3.4574995558386474e-06, "epoch": 1.0634722488957173, "percentage": 83.06, "elapsed_time": "19:19:55", "remaining_time": "3:56:31", "throughput": 656.39, "total_tokens": 45681856} {"current_steps": 33230, "total_steps": 40000, "loss": 0.539, "lr": 3.452519651953487e-06, "epoch": 1.0636322898662058, "percentage": 83.08, "elapsed_time": "19:19:57", "remaining_time": "3:56:19", "throughput": 656.47, "total_tokens": 45688704} {"current_steps": 33235, "total_steps": 40000, "loss": 0.6464, "lr": 3.447543070960585e-06, "epoch": 1.0637923308366941, "percentage": 83.09, "elapsed_time": "19:19:59", "remaining_time": "3:56:06", "throughput": 656.55, "total_tokens": 45695408} {"current_steps": 33240, "total_steps": 40000, "loss": 0.5949, "lr": 3.4425698136273778e-06, "epoch": 1.0639523718071826, "percentage": 83.1, "elapsed_time": "19:20:01", "remaining_time": "3:55:54", "throughput": 656.63, "total_tokens": 45701984} {"current_steps": 33245, "total_steps": 40000, "loss": 0.6107, "lr": 3.437599880720821e-06, "epoch": 1.064112412777671, "percentage": 83.11, "elapsed_time": "19:20:02", "remaining_time": "3:55:42", "throughput": 656.71, "total_tokens": 45708944} {"current_steps": 33250, "total_steps": 40000, "loss": 0.5857, "lr": 3.4326332730073267e-06, "epoch": 1.0642724537481596, "percentage": 83.12, "elapsed_time": "19:20:04", "remaining_time": "3:55:30", "throughput": 656.79, "total_tokens": 45715824} {"current_steps": 33255, "total_steps": 40000, "loss": 0.551, "lr": 3.427669991252813e-06, "epoch": 1.0644324947186479, "percentage": 83.14, "elapsed_time": "19:20:06", "remaining_time": "3:55:18", "throughput": 656.87, "total_tokens": 45722544} {"current_steps": 33260, "total_steps": 40000, "loss": 0.7015, "lr": 3.42271003622269e-06, "epoch": 1.0645925356891364, "percentage": 83.15, "elapsed_time": "19:20:08", "remaining_time": "3:55:05", "throughput": 656.96, "total_tokens": 45729792} {"current_steps": 33265, "total_steps": 40000, "loss": 0.6493, "lr": 3.4177534086818286e-06, "epoch": 1.0647525766596249, "percentage": 83.16, "elapsed_time": "19:20:09", "remaining_time": "3:54:53", "throughput": 657.04, "total_tokens": 45736608} {"current_steps": 33270, "total_steps": 40000, "loss": 0.5324, "lr": 3.412800109394612e-06, "epoch": 1.0649126176301134, "percentage": 83.17, "elapsed_time": "19:20:11", "remaining_time": "3:54:41", "throughput": 657.13, "total_tokens": 45743600} {"current_steps": 33275, "total_steps": 40000, "loss": 0.6943, "lr": 3.4078501391249044e-06, "epoch": 1.0650726586006019, "percentage": 83.19, "elapsed_time": "19:20:13", "remaining_time": "3:54:29", "throughput": 657.21, "total_tokens": 45750544} {"current_steps": 33280, "total_steps": 40000, "loss": 0.8209, "lr": 3.4029034986360453e-06, "epoch": 1.0652326995710901, "percentage": 83.2, "elapsed_time": "19:20:15", "remaining_time": "3:54:16", "throughput": 657.29, "total_tokens": 45757664} {"current_steps": 33285, "total_steps": 40000, "loss": 0.6712, "lr": 3.397960188690877e-06, "epoch": 1.0653927405415786, "percentage": 83.21, "elapsed_time": "19:20:16", "remaining_time": "3:54:04", "throughput": 657.38, "total_tokens": 45764576} {"current_steps": 33290, "total_steps": 40000, "loss": 0.7617, "lr": 3.393020210051717e-06, "epoch": 1.0655527815120671, "percentage": 83.23, "elapsed_time": "19:20:18", "remaining_time": "3:53:52", "throughput": 657.46, "total_tokens": 45771408} {"current_steps": 33295, "total_steps": 40000, "loss": 0.6964, "lr": 3.3880835634803655e-06, "epoch": 1.0657128224825556, "percentage": 83.24, "elapsed_time": "19:20:20", "remaining_time": "3:53:40", "throughput": 657.55, "total_tokens": 45778608} {"current_steps": 33300, "total_steps": 40000, "loss": 0.8289, "lr": 3.383150249738126e-06, "epoch": 1.0658728634530439, "percentage": 83.25, "elapsed_time": "19:20:22", "remaining_time": "3:53:28", "throughput": 657.63, "total_tokens": 45785376} {"current_steps": 33305, "total_steps": 40000, "loss": 0.8087, "lr": 3.3782202695857663e-06, "epoch": 1.0660329044235324, "percentage": 83.26, "elapsed_time": "19:20:23", "remaining_time": "3:53:15", "throughput": 657.7, "total_tokens": 45791984} {"current_steps": 33310, "total_steps": 40000, "loss": 0.7425, "lr": 3.373293623783558e-06, "epoch": 1.0661929453940209, "percentage": 83.28, "elapsed_time": "19:20:25", "remaining_time": "3:53:03", "throughput": 657.78, "total_tokens": 45798400} {"current_steps": 33315, "total_steps": 40000, "loss": 0.7012, "lr": 3.368370313091257e-06, "epoch": 1.0663529863645094, "percentage": 83.29, "elapsed_time": "19:20:27", "remaining_time": "3:52:51", "throughput": 657.86, "total_tokens": 45805136} {"current_steps": 33320, "total_steps": 40000, "loss": 0.6614, "lr": 3.363450338268087e-06, "epoch": 1.0665130273349979, "percentage": 83.3, "elapsed_time": "19:20:29", "remaining_time": "3:52:39", "throughput": 657.95, "total_tokens": 45812368} {"current_steps": 33325, "total_steps": 40000, "loss": 0.6252, "lr": 3.358533700072783e-06, "epoch": 1.0666730683054861, "percentage": 83.31, "elapsed_time": "19:20:30", "remaining_time": "3:52:27", "throughput": 658.03, "total_tokens": 45819392} {"current_steps": 33330, "total_steps": 40000, "loss": 0.7186, "lr": 3.3536203992635377e-06, "epoch": 1.0668331092759746, "percentage": 83.33, "elapsed_time": "19:20:32", "remaining_time": "3:52:14", "throughput": 658.11, "total_tokens": 45826192} {"current_steps": 33335, "total_steps": 40000, "loss": 0.9836, "lr": 3.348710436598057e-06, "epoch": 1.0669931502464631, "percentage": 83.34, "elapsed_time": "19:20:34", "remaining_time": "3:52:02", "throughput": 658.2, "total_tokens": 45833120} {"current_steps": 33340, "total_steps": 40000, "loss": 0.5008, "lr": 3.3438038128335155e-06, "epoch": 1.0671531912169516, "percentage": 83.35, "elapsed_time": "19:20:36", "remaining_time": "3:51:50", "throughput": 658.28, "total_tokens": 45840208} {"current_steps": 33345, "total_steps": 40000, "loss": 0.6994, "lr": 3.338900528726571e-06, "epoch": 1.06731323218744, "percentage": 83.36, "elapsed_time": "19:20:37", "remaining_time": "3:51:38", "throughput": 658.36, "total_tokens": 45846992} {"current_steps": 33350, "total_steps": 40000, "loss": 0.6843, "lr": 3.3340005850333812e-06, "epoch": 1.0674732731579284, "percentage": 83.38, "elapsed_time": "19:20:39", "remaining_time": "3:51:26", "throughput": 658.44, "total_tokens": 45853840} {"current_steps": 33355, "total_steps": 40000, "loss": 0.8877, "lr": 3.329103982509568e-06, "epoch": 1.0676333141284169, "percentage": 83.39, "elapsed_time": "19:20:41", "remaining_time": "3:51:14", "throughput": 658.53, "total_tokens": 45860672} {"current_steps": 33360, "total_steps": 40000, "loss": 0.7215, "lr": 3.324210721910259e-06, "epoch": 1.0677933550989054, "percentage": 83.4, "elapsed_time": "19:20:43", "remaining_time": "3:51:01", "throughput": 658.61, "total_tokens": 45867712} {"current_steps": 33365, "total_steps": 40000, "loss": 0.8779, "lr": 3.319320803990053e-06, "epoch": 1.0679533960693939, "percentage": 83.41, "elapsed_time": "19:20:45", "remaining_time": "3:50:49", "throughput": 658.69, "total_tokens": 45874656} {"current_steps": 33370, "total_steps": 40000, "loss": 0.554, "lr": 3.3144342295030274e-06, "epoch": 1.0681134370398822, "percentage": 83.43, "elapsed_time": "19:20:46", "remaining_time": "3:50:37", "throughput": 658.77, "total_tokens": 45881232} {"current_steps": 33375, "total_steps": 40000, "loss": 0.6087, "lr": 3.309550999202765e-06, "epoch": 1.0682734780103706, "percentage": 83.44, "elapsed_time": "19:20:48", "remaining_time": "3:50:25", "throughput": 658.85, "total_tokens": 45888160} {"current_steps": 33380, "total_steps": 40000, "loss": 0.5636, "lr": 3.3046711138423197e-06, "epoch": 1.0684335189808591, "percentage": 83.45, "elapsed_time": "19:20:50", "remaining_time": "3:50:13", "throughput": 658.93, "total_tokens": 45894960} {"current_steps": 33385, "total_steps": 40000, "loss": 0.7154, "lr": 3.2997945741742255e-06, "epoch": 1.0685935599513476, "percentage": 83.46, "elapsed_time": "19:20:52", "remaining_time": "3:50:01", "throughput": 659.01, "total_tokens": 45901696} {"current_steps": 33390, "total_steps": 40000, "loss": 0.5801, "lr": 3.2949213809505082e-06, "epoch": 1.068753600921836, "percentage": 83.47, "elapsed_time": "19:20:53", "remaining_time": "3:49:48", "throughput": 659.09, "total_tokens": 45908176} {"current_steps": 33395, "total_steps": 40000, "loss": 0.7685, "lr": 3.2900515349226834e-06, "epoch": 1.0689136418923244, "percentage": 83.49, "elapsed_time": "19:20:55", "remaining_time": "3:49:36", "throughput": 659.17, "total_tokens": 45915136} {"current_steps": 33400, "total_steps": 40000, "loss": 0.7796, "lr": 3.285185036841731e-06, "epoch": 1.069073682862813, "percentage": 83.5, "elapsed_time": "19:20:57", "remaining_time": "3:49:24", "throughput": 659.26, "total_tokens": 45922032} {"current_steps": 33400, "total_steps": 40000, "eval_loss": 0.7308374047279358, "epoch": 1.069073682862813, "percentage": 83.5, "elapsed_time": "19:26:45", "remaining_time": "3:50:33", "throughput": 655.98, "total_tokens": 45922032} {"current_steps": 33405, "total_steps": 40000, "loss": 0.6847, "lr": 3.2803218874581377e-06, "epoch": 1.0692337238333014, "percentage": 83.51, "elapsed_time": "19:26:50", "remaining_time": "3:50:21", "throughput": 656.03, "total_tokens": 45928528} {"current_steps": 33410, "total_steps": 40000, "loss": 0.5992, "lr": 3.2754620875218494e-06, "epoch": 1.0693937648037897, "percentage": 83.53, "elapsed_time": "19:26:51", "remaining_time": "3:50:09", "throughput": 656.11, "total_tokens": 45935488} {"current_steps": 33415, "total_steps": 40000, "loss": 0.7586, "lr": 3.2706056377823146e-06, "epoch": 1.0695538057742782, "percentage": 83.54, "elapsed_time": "19:26:53", "remaining_time": "3:49:57", "throughput": 656.19, "total_tokens": 45942512} {"current_steps": 33420, "total_steps": 40000, "loss": 0.6758, "lr": 3.2657525389884647e-06, "epoch": 1.0697138467447667, "percentage": 83.55, "elapsed_time": "19:26:55", "remaining_time": "3:49:45", "throughput": 656.28, "total_tokens": 45949424} {"current_steps": 33425, "total_steps": 40000, "loss": 0.8536, "lr": 3.260902791888698e-06, "epoch": 1.0698738877152552, "percentage": 83.56, "elapsed_time": "19:26:57", "remaining_time": "3:49:33", "throughput": 656.36, "total_tokens": 45956448} {"current_steps": 33430, "total_steps": 40000, "loss": 0.6759, "lr": 3.2560563972309166e-06, "epoch": 1.0700339286857437, "percentage": 83.58, "elapsed_time": "19:26:58", "remaining_time": "3:49:20", "throughput": 656.45, "total_tokens": 45964192} {"current_steps": 33435, "total_steps": 40000, "loss": 0.6173, "lr": 3.251213355762489e-06, "epoch": 1.070193969656232, "percentage": 83.59, "elapsed_time": "19:27:00", "remaining_time": "3:49:08", "throughput": 656.54, "total_tokens": 45971056} {"current_steps": 33440, "total_steps": 40000, "loss": 0.6778, "lr": 3.2463736682302707e-06, "epoch": 1.0703540106267204, "percentage": 83.6, "elapsed_time": "19:27:02", "remaining_time": "3:48:56", "throughput": 656.62, "total_tokens": 45978304} {"current_steps": 33445, "total_steps": 40000, "loss": 0.7887, "lr": 3.2415373353806124e-06, "epoch": 1.070514051597209, "percentage": 83.61, "elapsed_time": "19:27:04", "remaining_time": "3:48:44", "throughput": 656.71, "total_tokens": 45985488} {"current_steps": 33450, "total_steps": 40000, "loss": 0.548, "lr": 3.236704357959322e-06, "epoch": 1.0706740925676974, "percentage": 83.62, "elapsed_time": "19:27:05", "remaining_time": "3:48:32", "throughput": 656.79, "total_tokens": 45992336} {"current_steps": 33455, "total_steps": 40000, "loss": 0.7559, "lr": 3.2318747367117154e-06, "epoch": 1.0708341335381857, "percentage": 83.64, "elapsed_time": "19:27:07", "remaining_time": "3:48:19", "throughput": 656.87, "total_tokens": 45999040} {"current_steps": 33460, "total_steps": 40000, "loss": 0.8225, "lr": 3.227048472382585e-06, "epoch": 1.0709941745086742, "percentage": 83.65, "elapsed_time": "19:27:09", "remaining_time": "3:48:07", "throughput": 656.96, "total_tokens": 46006256} {"current_steps": 33465, "total_steps": 40000, "loss": 0.795, "lr": 3.2222255657161915e-06, "epoch": 1.0711542154791627, "percentage": 83.66, "elapsed_time": "19:27:11", "remaining_time": "3:47:55", "throughput": 657.03, "total_tokens": 46012672} {"current_steps": 33470, "total_steps": 40000, "loss": 0.68, "lr": 3.2174060174562924e-06, "epoch": 1.0713142564496512, "percentage": 83.67, "elapsed_time": "19:27:12", "remaining_time": "3:47:43", "throughput": 657.12, "total_tokens": 46020096} {"current_steps": 33475, "total_steps": 40000, "loss": 0.715, "lr": 3.2125898283461298e-06, "epoch": 1.0714742974201394, "percentage": 83.69, "elapsed_time": "19:27:14", "remaining_time": "3:47:31", "throughput": 657.2, "total_tokens": 46026784} {"current_steps": 33480, "total_steps": 40000, "loss": 0.7586, "lr": 3.207776999128406e-06, "epoch": 1.071634338390628, "percentage": 83.7, "elapsed_time": "19:27:16", "remaining_time": "3:47:19", "throughput": 657.29, "total_tokens": 46033904} {"current_steps": 33485, "total_steps": 40000, "loss": 0.842, "lr": 3.202967530545331e-06, "epoch": 1.0717943793611164, "percentage": 83.71, "elapsed_time": "19:27:18", "remaining_time": "3:47:06", "throughput": 657.37, "total_tokens": 46040928} {"current_steps": 33490, "total_steps": 40000, "loss": 0.9432, "lr": 3.1981614233385778e-06, "epoch": 1.071954420331605, "percentage": 83.73, "elapsed_time": "19:27:19", "remaining_time": "3:46:54", "throughput": 657.46, "total_tokens": 46048336} {"current_steps": 33495, "total_steps": 40000, "loss": 0.5109, "lr": 3.1933586782493115e-06, "epoch": 1.0721144613020934, "percentage": 83.74, "elapsed_time": "19:27:21", "remaining_time": "3:46:42", "throughput": 657.54, "total_tokens": 46055184} {"current_steps": 33500, "total_steps": 40000, "loss": 0.6962, "lr": 3.188559296018184e-06, "epoch": 1.0722745022725817, "percentage": 83.75, "elapsed_time": "19:27:23", "remaining_time": "3:46:30", "throughput": 657.62, "total_tokens": 46061920} {"current_steps": 33505, "total_steps": 40000, "loss": 0.7765, "lr": 3.1837632773853098e-06, "epoch": 1.0724345432430702, "percentage": 83.76, "elapsed_time": "19:27:25", "remaining_time": "3:46:18", "throughput": 657.69, "total_tokens": 46068368} {"current_steps": 33510, "total_steps": 40000, "loss": 0.7337, "lr": 3.178970623090294e-06, "epoch": 1.0725945842135587, "percentage": 83.78, "elapsed_time": "19:27:27", "remaining_time": "3:46:06", "throughput": 657.78, "total_tokens": 46075200} {"current_steps": 33515, "total_steps": 40000, "loss": 0.5624, "lr": 3.174181333872234e-06, "epoch": 1.0727546251840472, "percentage": 83.79, "elapsed_time": "19:27:28", "remaining_time": "3:45:54", "throughput": 657.85, "total_tokens": 46081584} {"current_steps": 33520, "total_steps": 40000, "loss": 0.6635, "lr": 3.169395410469686e-06, "epoch": 1.0729146661545355, "percentage": 83.8, "elapsed_time": "19:27:30", "remaining_time": "3:45:42", "throughput": 657.93, "total_tokens": 46088288} {"current_steps": 33525, "total_steps": 40000, "loss": 0.7847, "lr": 3.164612853620713e-06, "epoch": 1.073074707125024, "percentage": 83.81, "elapsed_time": "19:27:32", "remaining_time": "3:45:29", "throughput": 658.01, "total_tokens": 46095008} {"current_steps": 33530, "total_steps": 40000, "loss": 0.7046, "lr": 3.1598336640628333e-06, "epoch": 1.0732347480955124, "percentage": 83.83, "elapsed_time": "19:27:34", "remaining_time": "3:45:17", "throughput": 658.09, "total_tokens": 46102112} {"current_steps": 33535, "total_steps": 40000, "loss": 0.6936, "lr": 3.155057842533063e-06, "epoch": 1.073394789066001, "percentage": 83.84, "elapsed_time": "19:27:35", "remaining_time": "3:45:05", "throughput": 658.17, "total_tokens": 46108560} {"current_steps": 33540, "total_steps": 40000, "loss": 0.7554, "lr": 3.1502853897678984e-06, "epoch": 1.0735548300364894, "percentage": 83.85, "elapsed_time": "19:27:37", "remaining_time": "3:44:53", "throughput": 658.25, "total_tokens": 46115216} {"current_steps": 33545, "total_steps": 40000, "loss": 0.899, "lr": 3.1455163065033017e-06, "epoch": 1.0737148710069777, "percentage": 83.86, "elapsed_time": "19:27:39", "remaining_time": "3:44:41", "throughput": 658.33, "total_tokens": 46122304} {"current_steps": 33550, "total_steps": 40000, "loss": 0.5979, "lr": 3.140750593474734e-06, "epoch": 1.0738749119774662, "percentage": 83.88, "elapsed_time": "19:27:41", "remaining_time": "3:44:29", "throughput": 658.42, "total_tokens": 46129648} {"current_steps": 33555, "total_steps": 40000, "loss": 0.6748, "lr": 3.1359882514171294e-06, "epoch": 1.0740349529479547, "percentage": 83.89, "elapsed_time": "19:27:42", "remaining_time": "3:44:17", "throughput": 658.5, "total_tokens": 46136480} {"current_steps": 33560, "total_steps": 40000, "loss": 0.7625, "lr": 3.1312292810648903e-06, "epoch": 1.0741949939184432, "percentage": 83.9, "elapsed_time": "19:27:44", "remaining_time": "3:44:05", "throughput": 658.58, "total_tokens": 46143280} {"current_steps": 33565, "total_steps": 40000, "loss": 0.8505, "lr": 3.1264736831519204e-06, "epoch": 1.0743550348889315, "percentage": 83.91, "elapsed_time": "19:27:46", "remaining_time": "3:43:52", "throughput": 658.67, "total_tokens": 46150240} {"current_steps": 33570, "total_steps": 40000, "loss": 0.4865, "lr": 3.1217214584115863e-06, "epoch": 1.07451507585942, "percentage": 83.93, "elapsed_time": "19:27:48", "remaining_time": "3:43:40", "throughput": 658.75, "total_tokens": 46157280} {"current_steps": 33575, "total_steps": 40000, "loss": 0.5737, "lr": 3.116972607576746e-06, "epoch": 1.0746751168299085, "percentage": 83.94, "elapsed_time": "19:27:49", "remaining_time": "3:43:28", "throughput": 658.83, "total_tokens": 46163952} {"current_steps": 33580, "total_steps": 40000, "loss": 0.6726, "lr": 3.1122271313797303e-06, "epoch": 1.074835157800397, "percentage": 83.95, "elapsed_time": "19:27:51", "remaining_time": "3:43:16", "throughput": 658.91, "total_tokens": 46170656} {"current_steps": 33585, "total_steps": 40000, "loss": 0.7321, "lr": 3.107485030552343e-06, "epoch": 1.0749951987708855, "percentage": 83.96, "elapsed_time": "19:27:53", "remaining_time": "3:43:04", "throughput": 658.98, "total_tokens": 46177248} {"current_steps": 33590, "total_steps": 40000, "loss": 0.7034, "lr": 3.1027463058258848e-06, "epoch": 1.0751552397413737, "percentage": 83.97, "elapsed_time": "19:27:55", "remaining_time": "3:42:52", "throughput": 659.07, "total_tokens": 46184176} {"current_steps": 33595, "total_steps": 40000, "loss": 0.7987, "lr": 3.0980109579311273e-06, "epoch": 1.0753152807118622, "percentage": 83.99, "elapsed_time": "19:27:56", "remaining_time": "3:42:40", "throughput": 659.14, "total_tokens": 46190784} {"current_steps": 33600, "total_steps": 40000, "loss": 0.7574, "lr": 3.093278987598314e-06, "epoch": 1.0754753216823507, "percentage": 84.0, "elapsed_time": "19:27:58", "remaining_time": "3:42:28", "throughput": 659.23, "total_tokens": 46197840} {"current_steps": 33600, "total_steps": 40000, "eval_loss": 0.7305747866630554, "epoch": 1.0754753216823507, "percentage": 84.0, "elapsed_time": "19:33:46", "remaining_time": "3:43:34", "throughput": 655.97, "total_tokens": 46197840} {"current_steps": 33605, "total_steps": 40000, "loss": 0.7445, "lr": 3.0885503955571826e-06, "epoch": 1.0756353626528392, "percentage": 84.01, "elapsed_time": "19:33:51", "remaining_time": "3:43:22", "throughput": 656.03, "total_tokens": 46204752} {"current_steps": 33610, "total_steps": 40000, "loss": 0.6465, "lr": 3.0838251825369313e-06, "epoch": 1.0757954036233275, "percentage": 84.03, "elapsed_time": "19:33:52", "remaining_time": "3:43:10", "throughput": 656.11, "total_tokens": 46211696} {"current_steps": 33615, "total_steps": 40000, "loss": 0.8955, "lr": 3.0791033492662517e-06, "epoch": 1.075955444593816, "percentage": 84.04, "elapsed_time": "19:33:54", "remaining_time": "3:42:58", "throughput": 656.19, "total_tokens": 46218832} {"current_steps": 33620, "total_steps": 40000, "loss": 0.7147, "lr": 3.0743848964733203e-06, "epoch": 1.0761154855643045, "percentage": 84.05, "elapsed_time": "19:33:56", "remaining_time": "3:42:46", "throughput": 656.28, "total_tokens": 46225792} {"current_steps": 33625, "total_steps": 40000, "loss": 0.6982, "lr": 3.0696698248857625e-06, "epoch": 1.076275526534793, "percentage": 84.06, "elapsed_time": "19:33:58", "remaining_time": "3:42:34", "throughput": 656.36, "total_tokens": 46232592} {"current_steps": 33630, "total_steps": 40000, "loss": 0.6613, "lr": 3.0649581352307192e-06, "epoch": 1.0764355675052815, "percentage": 84.08, "elapsed_time": "19:33:59", "remaining_time": "3:42:22", "throughput": 656.44, "total_tokens": 46239376} {"current_steps": 33635, "total_steps": 40000, "loss": 0.7204, "lr": 3.060249828234776e-06, "epoch": 1.0765956084757697, "percentage": 84.09, "elapsed_time": "19:34:01", "remaining_time": "3:42:10", "throughput": 656.52, "total_tokens": 46246224} {"current_steps": 33640, "total_steps": 40000, "loss": 0.6443, "lr": 3.055544904624025e-06, "epoch": 1.0767556494462582, "percentage": 84.1, "elapsed_time": "19:34:03", "remaining_time": "3:41:58", "throughput": 656.61, "total_tokens": 46253728} {"current_steps": 33645, "total_steps": 40000, "loss": 0.6423, "lr": 3.050843365124026e-06, "epoch": 1.0769156904167467, "percentage": 84.11, "elapsed_time": "19:34:05", "remaining_time": "3:41:45", "throughput": 656.69, "total_tokens": 46260400} {"current_steps": 33650, "total_steps": 40000, "loss": 0.9085, "lr": 3.0461452104598083e-06, "epoch": 1.0770757313872352, "percentage": 84.12, "elapsed_time": "19:34:06", "remaining_time": "3:41:33", "throughput": 656.77, "total_tokens": 46267440} {"current_steps": 33655, "total_steps": 40000, "loss": 0.7335, "lr": 3.0414504413558836e-06, "epoch": 1.0772357723577235, "percentage": 84.14, "elapsed_time": "19:34:08", "remaining_time": "3:41:21", "throughput": 656.86, "total_tokens": 46274704} {"current_steps": 33660, "total_steps": 40000, "loss": 0.5667, "lr": 3.0367590585362564e-06, "epoch": 1.077395813328212, "percentage": 84.15, "elapsed_time": "19:34:10", "remaining_time": "3:41:09", "throughput": 656.94, "total_tokens": 46281648} {"current_steps": 33665, "total_steps": 40000, "loss": 0.6685, "lr": 3.0320710627243813e-06, "epoch": 1.0775558542987005, "percentage": 84.16, "elapsed_time": "19:34:12", "remaining_time": "3:40:57", "throughput": 657.03, "total_tokens": 46289312} {"current_steps": 33670, "total_steps": 40000, "loss": 0.6903, "lr": 3.027386454643222e-06, "epoch": 1.077715895269189, "percentage": 84.17, "elapsed_time": "19:34:13", "remaining_time": "3:40:45", "throughput": 657.11, "total_tokens": 46295984} {"current_steps": 33675, "total_steps": 40000, "loss": 0.6311, "lr": 3.0227052350151914e-06, "epoch": 1.0778759362396773, "percentage": 84.19, "elapsed_time": "19:34:15", "remaining_time": "3:40:33", "throughput": 657.19, "total_tokens": 46302752} {"current_steps": 33680, "total_steps": 40000, "loss": 0.7015, "lr": 3.0180274045621957e-06, "epoch": 1.0780359772101658, "percentage": 84.2, "elapsed_time": "19:34:17", "remaining_time": "3:40:21", "throughput": 657.27, "total_tokens": 46309264} {"current_steps": 33685, "total_steps": 40000, "loss": 0.6958, "lr": 3.013352964005625e-06, "epoch": 1.0781960181806542, "percentage": 84.21, "elapsed_time": "19:34:19", "remaining_time": "3:40:09", "throughput": 657.35, "total_tokens": 46316480} {"current_steps": 33690, "total_steps": 40000, "loss": 0.6553, "lr": 3.0086819140663218e-06, "epoch": 1.0783560591511427, "percentage": 84.23, "elapsed_time": "19:34:21", "remaining_time": "3:39:57", "throughput": 657.43, "total_tokens": 46323024} {"current_steps": 33695, "total_steps": 40000, "loss": 0.7207, "lr": 3.0040142554646265e-06, "epoch": 1.0785161001216312, "percentage": 84.24, "elapsed_time": "19:34:22", "remaining_time": "3:39:44", "throughput": 657.51, "total_tokens": 46329728} {"current_steps": 33700, "total_steps": 40000, "loss": 0.652, "lr": 2.999349988920361e-06, "epoch": 1.0786761410921195, "percentage": 84.25, "elapsed_time": "19:34:24", "remaining_time": "3:39:32", "throughput": 657.59, "total_tokens": 46337024} {"current_steps": 33705, "total_steps": 40000, "loss": 0.6991, "lr": 2.994689115152796e-06, "epoch": 1.078836182062608, "percentage": 84.26, "elapsed_time": "19:34:26", "remaining_time": "3:39:20", "throughput": 657.67, "total_tokens": 46343792} {"current_steps": 33710, "total_steps": 40000, "loss": 0.683, "lr": 2.9900316348807105e-06, "epoch": 1.0789962230330965, "percentage": 84.28, "elapsed_time": "19:34:28", "remaining_time": "3:39:08", "throughput": 657.75, "total_tokens": 46350560} {"current_steps": 33715, "total_steps": 40000, "loss": 0.751, "lr": 2.985377548822338e-06, "epoch": 1.079156264003585, "percentage": 84.29, "elapsed_time": "19:34:29", "remaining_time": "3:38:56", "throughput": 657.84, "total_tokens": 46357664} {"current_steps": 33720, "total_steps": 40000, "loss": 0.7372, "lr": 2.980726857695404e-06, "epoch": 1.0793163049740733, "percentage": 84.3, "elapsed_time": "19:34:31", "remaining_time": "3:38:44", "throughput": 657.91, "total_tokens": 46364192} {"current_steps": 33725, "total_steps": 40000, "loss": 0.5456, "lr": 2.9760795622171017e-06, "epoch": 1.0794763459445618, "percentage": 84.31, "elapsed_time": "19:34:33", "remaining_time": "3:38:32", "throughput": 657.99, "total_tokens": 46370608} {"current_steps": 33730, "total_steps": 40000, "loss": 0.8126, "lr": 2.971435663104094e-06, "epoch": 1.0796363869150503, "percentage": 84.33, "elapsed_time": "19:34:34", "remaining_time": "3:38:20", "throughput": 658.07, "total_tokens": 46377456} {"current_steps": 33735, "total_steps": 40000, "loss": 0.6474, "lr": 2.9667951610725385e-06, "epoch": 1.0797964278855388, "percentage": 84.34, "elapsed_time": "19:34:36", "remaining_time": "3:38:08", "throughput": 658.15, "total_tokens": 46384000} {"current_steps": 33740, "total_steps": 40000, "loss": 0.819, "lr": 2.9621580568380575e-06, "epoch": 1.079956468856027, "percentage": 84.35, "elapsed_time": "19:34:38", "remaining_time": "3:37:56", "throughput": 658.23, "total_tokens": 46391376} {"current_steps": 33745, "total_steps": 40000, "loss": 0.7084, "lr": 2.9575243511157453e-06, "epoch": 1.0801165098265155, "percentage": 84.36, "elapsed_time": "19:34:40", "remaining_time": "3:37:44", "throughput": 658.31, "total_tokens": 46398144} {"current_steps": 33750, "total_steps": 40000, "loss": 0.8955, "lr": 2.952894044620186e-06, "epoch": 1.080276550797004, "percentage": 84.38, "elapsed_time": "19:34:41", "remaining_time": "3:37:32", "throughput": 658.39, "total_tokens": 46404432} {"current_steps": 33755, "total_steps": 40000, "loss": 0.8358, "lr": 2.948267138065419e-06, "epoch": 1.0804365917674925, "percentage": 84.39, "elapsed_time": "19:34:43", "remaining_time": "3:37:20", "throughput": 658.48, "total_tokens": 46411792} {"current_steps": 33760, "total_steps": 40000, "loss": 0.6916, "lr": 2.943643632164983e-06, "epoch": 1.080596632737981, "percentage": 84.4, "elapsed_time": "19:34:45", "remaining_time": "3:37:08", "throughput": 658.56, "total_tokens": 46418832} {"current_steps": 33765, "total_steps": 40000, "loss": 0.6332, "lr": 2.939023527631879e-06, "epoch": 1.0807566737084693, "percentage": 84.41, "elapsed_time": "19:34:47", "remaining_time": "3:36:56", "throughput": 658.64, "total_tokens": 46425712} {"current_steps": 33770, "total_steps": 40000, "loss": 0.7286, "lr": 2.934406825178576e-06, "epoch": 1.0809167146789578, "percentage": 84.42, "elapsed_time": "19:34:49", "remaining_time": "3:36:44", "throughput": 658.72, "total_tokens": 46432672} {"current_steps": 33775, "total_steps": 40000, "loss": 0.8668, "lr": 2.9297935255170357e-06, "epoch": 1.0810767556494463, "percentage": 84.44, "elapsed_time": "19:34:50", "remaining_time": "3:36:32", "throughput": 658.8, "total_tokens": 46439520} {"current_steps": 33780, "total_steps": 40000, "loss": 0.8129, "lr": 2.925183629358691e-06, "epoch": 1.0812367966199348, "percentage": 84.45, "elapsed_time": "19:34:52", "remaining_time": "3:36:19", "throughput": 658.88, "total_tokens": 46446160} {"current_steps": 33785, "total_steps": 40000, "loss": 0.8097, "lr": 2.9205771374144346e-06, "epoch": 1.081396837590423, "percentage": 84.46, "elapsed_time": "19:34:54", "remaining_time": "3:36:07", "throughput": 658.96, "total_tokens": 46453312} {"current_steps": 33790, "total_steps": 40000, "loss": 0.6306, "lr": 2.915974050394657e-06, "epoch": 1.0815568785609115, "percentage": 84.47, "elapsed_time": "19:34:56", "remaining_time": "3:35:55", "throughput": 659.05, "total_tokens": 46460400} {"current_steps": 33795, "total_steps": 40000, "loss": 0.6752, "lr": 2.9113743690092067e-06, "epoch": 1.0817169195314, "percentage": 84.49, "elapsed_time": "19:34:57", "remaining_time": "3:35:43", "throughput": 659.14, "total_tokens": 46467808} {"current_steps": 33800, "total_steps": 40000, "loss": 0.8987, "lr": 2.906778093967402e-06, "epoch": 1.0818769605018885, "percentage": 84.5, "elapsed_time": "19:34:59", "remaining_time": "3:35:31", "throughput": 659.22, "total_tokens": 46474848} {"current_steps": 33800, "total_steps": 40000, "eval_loss": 0.7302864193916321, "epoch": 1.0818769605018885, "percentage": 84.5, "elapsed_time": "19:40:47", "remaining_time": "3:36:35", "throughput": 655.98, "total_tokens": 46474848} {"current_steps": 33805, "total_steps": 40000, "loss": 0.6021, "lr": 2.9021852259780656e-06, "epoch": 1.082037001472377, "percentage": 84.51, "elapsed_time": "19:40:50", "remaining_time": "3:36:23", "throughput": 656.04, "total_tokens": 46481344} {"current_steps": 33810, "total_steps": 40000, "loss": 0.6366, "lr": 2.8975957657494583e-06, "epoch": 1.0821970424428653, "percentage": 84.52, "elapsed_time": "19:40:52", "remaining_time": "3:36:11", "throughput": 656.13, "total_tokens": 46488464} {"current_steps": 33815, "total_steps": 40000, "loss": 0.5934, "lr": 2.8930097139893417e-06, "epoch": 1.0823570834133538, "percentage": 84.54, "elapsed_time": "19:40:54", "remaining_time": "3:35:59", "throughput": 656.21, "total_tokens": 46495664} {"current_steps": 33820, "total_steps": 40000, "loss": 0.6402, "lr": 2.888427071404945e-06, "epoch": 1.0825171243838423, "percentage": 84.55, "elapsed_time": "19:40:56", "remaining_time": "3:35:47", "throughput": 656.29, "total_tokens": 46502448} {"current_steps": 33825, "total_steps": 40000, "loss": 0.6272, "lr": 2.8838478387029606e-06, "epoch": 1.0826771653543308, "percentage": 84.56, "elapsed_time": "19:40:57", "remaining_time": "3:35:35", "throughput": 656.38, "total_tokens": 46509376} {"current_steps": 33830, "total_steps": 40000, "loss": 0.5655, "lr": 2.8792720165895737e-06, "epoch": 1.082837206324819, "percentage": 84.58, "elapsed_time": "19:40:59", "remaining_time": "3:35:23", "throughput": 656.45, "total_tokens": 46516144} {"current_steps": 33835, "total_steps": 40000, "loss": 0.8267, "lr": 2.874699605770423e-06, "epoch": 1.0829972472953076, "percentage": 84.59, "elapsed_time": "19:41:01", "remaining_time": "3:35:11", "throughput": 656.54, "total_tokens": 46523344} {"current_steps": 33840, "total_steps": 40000, "loss": 0.6716, "lr": 2.8701306069506383e-06, "epoch": 1.083157288265796, "percentage": 84.6, "elapsed_time": "19:41:03", "remaining_time": "3:34:59", "throughput": 656.62, "total_tokens": 46530144} {"current_steps": 33845, "total_steps": 40000, "loss": 0.6657, "lr": 2.8655650208348178e-06, "epoch": 1.0833173292362845, "percentage": 84.61, "elapsed_time": "19:41:04", "remaining_time": "3:34:47", "throughput": 656.7, "total_tokens": 46537040} {"current_steps": 33850, "total_steps": 40000, "loss": 0.7121, "lr": 2.8610028481270257e-06, "epoch": 1.083477370206773, "percentage": 84.62, "elapsed_time": "19:41:06", "remaining_time": "3:34:35", "throughput": 656.78, "total_tokens": 46543824} {"current_steps": 33855, "total_steps": 40000, "loss": 0.7179, "lr": 2.856444089530813e-06, "epoch": 1.0836374111772613, "percentage": 84.64, "elapsed_time": "19:41:08", "remaining_time": "3:34:23", "throughput": 656.86, "total_tokens": 46550864} {"current_steps": 33860, "total_steps": 40000, "loss": 0.5569, "lr": 2.8518887457491955e-06, "epoch": 1.0837974521477498, "percentage": 84.65, "elapsed_time": "19:41:10", "remaining_time": "3:34:11", "throughput": 656.94, "total_tokens": 46557536} {"current_steps": 33865, "total_steps": 40000, "loss": 0.7795, "lr": 2.8473368174846666e-06, "epoch": 1.0839574931182383, "percentage": 84.66, "elapsed_time": "19:41:11", "remaining_time": "3:33:59", "throughput": 657.02, "total_tokens": 46564480} {"current_steps": 33870, "total_steps": 40000, "loss": 0.9025, "lr": 2.842788305439184e-06, "epoch": 1.0841175340887268, "percentage": 84.67, "elapsed_time": "19:41:13", "remaining_time": "3:33:47", "throughput": 657.11, "total_tokens": 46571680} {"current_steps": 33875, "total_steps": 40000, "loss": 0.5401, "lr": 2.8382432103141925e-06, "epoch": 1.084277575059215, "percentage": 84.69, "elapsed_time": "19:41:15", "remaining_time": "3:33:35", "throughput": 657.19, "total_tokens": 46578608} {"current_steps": 33880, "total_steps": 40000, "loss": 0.703, "lr": 2.833701532810598e-06, "epoch": 1.0844376160297036, "percentage": 84.7, "elapsed_time": "19:41:17", "remaining_time": "3:33:23", "throughput": 657.27, "total_tokens": 46585200} {"current_steps": 33885, "total_steps": 40000, "loss": 0.6532, "lr": 2.8291632736287877e-06, "epoch": 1.084597657000192, "percentage": 84.71, "elapsed_time": "19:41:18", "remaining_time": "3:33:11", "throughput": 657.35, "total_tokens": 46592096} {"current_steps": 33890, "total_steps": 40000, "loss": 0.6314, "lr": 2.824628433468615e-06, "epoch": 1.0847576979706806, "percentage": 84.72, "elapsed_time": "19:41:20", "remaining_time": "3:32:59", "throughput": 657.43, "total_tokens": 46599280} {"current_steps": 33895, "total_steps": 40000, "loss": 0.9048, "lr": 2.8200970130294073e-06, "epoch": 1.084917738941169, "percentage": 84.74, "elapsed_time": "19:41:22", "remaining_time": "3:32:47", "throughput": 657.52, "total_tokens": 46606560} {"current_steps": 33900, "total_steps": 40000, "loss": 0.886, "lr": 2.8155690130099775e-06, "epoch": 1.0850777799116573, "percentage": 84.75, "elapsed_time": "19:41:24", "remaining_time": "3:32:34", "throughput": 657.6, "total_tokens": 46613392} {"current_steps": 33905, "total_steps": 40000, "loss": 0.9194, "lr": 2.8110444341085895e-06, "epoch": 1.0852378208821458, "percentage": 84.76, "elapsed_time": "19:41:26", "remaining_time": "3:32:22", "throughput": 657.68, "total_tokens": 46620144} {"current_steps": 33910, "total_steps": 40000, "loss": 0.6226, "lr": 2.806523277022996e-06, "epoch": 1.0853978618526343, "percentage": 84.78, "elapsed_time": "19:41:27", "remaining_time": "3:32:10", "throughput": 657.75, "total_tokens": 46626800} {"current_steps": 33915, "total_steps": 40000, "loss": 0.8463, "lr": 2.802005542450409e-06, "epoch": 1.0855579028231228, "percentage": 84.79, "elapsed_time": "19:41:29", "remaining_time": "3:31:58", "throughput": 657.83, "total_tokens": 46633504} {"current_steps": 33920, "total_steps": 40000, "loss": 0.7492, "lr": 2.797491231087526e-06, "epoch": 1.085717943793611, "percentage": 84.8, "elapsed_time": "19:41:31", "remaining_time": "3:31:46", "throughput": 657.91, "total_tokens": 46640128} {"current_steps": 33925, "total_steps": 40000, "loss": 0.6351, "lr": 2.7929803436305137e-06, "epoch": 1.0858779847640996, "percentage": 84.81, "elapsed_time": "19:41:33", "remaining_time": "3:31:34", "throughput": 657.99, "total_tokens": 46646832} {"current_steps": 33930, "total_steps": 40000, "loss": 0.6088, "lr": 2.788472880774998e-06, "epoch": 1.086038025734588, "percentage": 84.82, "elapsed_time": "19:41:34", "remaining_time": "3:31:22", "throughput": 658.07, "total_tokens": 46653648} {"current_steps": 33935, "total_steps": 40000, "loss": 0.7967, "lr": 2.7839688432160977e-06, "epoch": 1.0861980667050766, "percentage": 84.84, "elapsed_time": "19:41:36", "remaining_time": "3:31:10", "throughput": 658.16, "total_tokens": 46661040} {"current_steps": 33940, "total_steps": 40000, "loss": 0.7495, "lr": 2.779468231648383e-06, "epoch": 1.0863581076755648, "percentage": 84.85, "elapsed_time": "19:41:38", "remaining_time": "3:30:58", "throughput": 658.24, "total_tokens": 46667840} {"current_steps": 33945, "total_steps": 40000, "loss": 0.7653, "lr": 2.774971046765906e-06, "epoch": 1.0865181486460533, "percentage": 84.86, "elapsed_time": "19:41:40", "remaining_time": "3:30:46", "throughput": 658.32, "total_tokens": 46674960} {"current_steps": 33950, "total_steps": 40000, "loss": 0.8325, "lr": 2.770477289262194e-06, "epoch": 1.0866781896165418, "percentage": 84.88, "elapsed_time": "19:41:41", "remaining_time": "3:30:34", "throughput": 658.4, "total_tokens": 46681600} {"current_steps": 33955, "total_steps": 40000, "loss": 0.7945, "lr": 2.765986959830233e-06, "epoch": 1.0868382305870303, "percentage": 84.89, "elapsed_time": "19:41:43", "remaining_time": "3:30:22", "throughput": 658.48, "total_tokens": 46688864} {"current_steps": 33960, "total_steps": 40000, "loss": 0.7213, "lr": 2.761500059162492e-06, "epoch": 1.0869982715575188, "percentage": 84.9, "elapsed_time": "19:41:45", "remaining_time": "3:30:10", "throughput": 658.56, "total_tokens": 46695584} {"current_steps": 33965, "total_steps": 40000, "loss": 0.734, "lr": 2.757016587950914e-06, "epoch": 1.087158312528007, "percentage": 84.91, "elapsed_time": "19:41:47", "remaining_time": "3:29:58", "throughput": 658.64, "total_tokens": 46702352} {"current_steps": 33970, "total_steps": 40000, "loss": 0.4346, "lr": 2.752536546886897e-06, "epoch": 1.0873183534984956, "percentage": 84.92, "elapsed_time": "19:41:48", "remaining_time": "3:29:46", "throughput": 658.72, "total_tokens": 46709184} {"current_steps": 33975, "total_steps": 40000, "loss": 0.5566, "lr": 2.7480599366613234e-06, "epoch": 1.087478394468984, "percentage": 84.94, "elapsed_time": "19:41:50", "remaining_time": "3:29:35", "throughput": 658.8, "total_tokens": 46715856} {"current_steps": 33980, "total_steps": 40000, "loss": 0.9612, "lr": 2.7435867579645473e-06, "epoch": 1.0876384354394726, "percentage": 84.95, "elapsed_time": "19:41:52", "remaining_time": "3:29:23", "throughput": 658.88, "total_tokens": 46723008} {"current_steps": 33985, "total_steps": 40000, "loss": 0.8094, "lr": 2.739117011486378e-06, "epoch": 1.0877984764099609, "percentage": 84.96, "elapsed_time": "19:41:54", "remaining_time": "3:29:11", "throughput": 658.96, "total_tokens": 46729856} {"current_steps": 33990, "total_steps": 40000, "loss": 0.5908, "lr": 2.7346506979161216e-06, "epoch": 1.0879585173804494, "percentage": 84.97, "elapsed_time": "19:41:55", "remaining_time": "3:28:59", "throughput": 659.05, "total_tokens": 46736960} {"current_steps": 33995, "total_steps": 40000, "loss": 0.7276, "lr": 2.7301878179425227e-06, "epoch": 1.0881185583509378, "percentage": 84.99, "elapsed_time": "19:41:57", "remaining_time": "3:28:47", "throughput": 659.13, "total_tokens": 46743616} {"current_steps": 34000, "total_steps": 40000, "loss": 0.6623, "lr": 2.7257283722538244e-06, "epoch": 1.0882785993214263, "percentage": 85.0, "elapsed_time": "19:41:59", "remaining_time": "3:28:35", "throughput": 659.2, "total_tokens": 46749824} {"current_steps": 34000, "total_steps": 40000, "eval_loss": 0.730728805065155, "epoch": 1.0882785993214263, "percentage": 85.0, "elapsed_time": "19:47:47", "remaining_time": "3:29:36", "throughput": 655.98, "total_tokens": 46749824} {"current_steps": 34005, "total_steps": 40000, "loss": 0.7924, "lr": 2.7212723615377326e-06, "epoch": 1.0884386402919146, "percentage": 85.01, "elapsed_time": "19:47:50", "remaining_time": "3:29:24", "throughput": 656.04, "total_tokens": 46756768} {"current_steps": 34010, "total_steps": 40000, "loss": 0.668, "lr": 2.7168197864814145e-06, "epoch": 1.0885986812624031, "percentage": 85.02, "elapsed_time": "19:47:52", "remaining_time": "3:29:12", "throughput": 656.12, "total_tokens": 46763584} {"current_steps": 34015, "total_steps": 40000, "loss": 0.709, "lr": 2.712370647771509e-06, "epoch": 1.0887587222328916, "percentage": 85.04, "elapsed_time": "19:47:54", "remaining_time": "3:29:00", "throughput": 656.2, "total_tokens": 46770144} {"current_steps": 34020, "total_steps": 40000, "loss": 0.631, "lr": 2.707924946094137e-06, "epoch": 1.08891876320338, "percentage": 85.05, "elapsed_time": "19:47:56", "remaining_time": "3:28:48", "throughput": 656.27, "total_tokens": 46776688} {"current_steps": 34025, "total_steps": 40000, "loss": 0.7067, "lr": 2.7034826821348723e-06, "epoch": 1.0890788041738686, "percentage": 85.06, "elapsed_time": "19:47:57", "remaining_time": "3:28:36", "throughput": 656.36, "total_tokens": 46783728} {"current_steps": 34030, "total_steps": 40000, "loss": 0.6969, "lr": 2.6990438565787786e-06, "epoch": 1.0892388451443569, "percentage": 85.08, "elapsed_time": "19:47:59", "remaining_time": "3:28:24", "throughput": 656.44, "total_tokens": 46790704} {"current_steps": 34035, "total_steps": 40000, "loss": 0.6015, "lr": 2.6946084701103714e-06, "epoch": 1.0893988861148454, "percentage": 85.09, "elapsed_time": "19:48:01", "remaining_time": "3:28:12", "throughput": 656.52, "total_tokens": 46797616} {"current_steps": 34040, "total_steps": 40000, "loss": 0.8122, "lr": 2.6901765234136428e-06, "epoch": 1.0895589270853339, "percentage": 85.1, "elapsed_time": "19:48:03", "remaining_time": "3:28:00", "throughput": 656.61, "total_tokens": 46805200} {"current_steps": 34045, "total_steps": 40000, "loss": 0.8281, "lr": 2.685748017172063e-06, "epoch": 1.0897189680558224, "percentage": 85.11, "elapsed_time": "19:48:05", "remaining_time": "3:27:48", "throughput": 656.68, "total_tokens": 46811680} {"current_steps": 34050, "total_steps": 40000, "loss": 0.6833, "lr": 2.681322952068549e-06, "epoch": 1.0898790090263106, "percentage": 85.12, "elapsed_time": "19:48:06", "remaining_time": "3:27:36", "throughput": 656.77, "total_tokens": 46818864} {"current_steps": 34055, "total_steps": 40000, "loss": 0.7156, "lr": 2.6769013287855137e-06, "epoch": 1.0900390499967991, "percentage": 85.14, "elapsed_time": "19:48:08", "remaining_time": "3:27:24", "throughput": 656.84, "total_tokens": 46825376} {"current_steps": 34060, "total_steps": 40000, "loss": 0.5952, "lr": 2.6724831480048286e-06, "epoch": 1.0901990909672876, "percentage": 85.15, "elapsed_time": "19:48:10", "remaining_time": "3:27:12", "throughput": 656.93, "total_tokens": 46832384} {"current_steps": 34065, "total_steps": 40000, "loss": 0.7259, "lr": 2.66806841040782e-06, "epoch": 1.0903591319377761, "percentage": 85.16, "elapsed_time": "19:48:11", "remaining_time": "3:27:00", "throughput": 657.01, "total_tokens": 46839312} {"current_steps": 34070, "total_steps": 40000, "loss": 0.8267, "lr": 2.6636571166753083e-06, "epoch": 1.0905191729082646, "percentage": 85.17, "elapsed_time": "19:48:13", "remaining_time": "3:26:48", "throughput": 657.09, "total_tokens": 46846288} {"current_steps": 34075, "total_steps": 40000, "loss": 0.6569, "lr": 2.6592492674875598e-06, "epoch": 1.0906792138787529, "percentage": 85.19, "elapsed_time": "19:48:15", "remaining_time": "3:26:36", "throughput": 657.17, "total_tokens": 46852928} {"current_steps": 34080, "total_steps": 40000, "loss": 0.6232, "lr": 2.6548448635243305e-06, "epoch": 1.0908392548492414, "percentage": 85.2, "elapsed_time": "19:48:17", "remaining_time": "3:26:24", "throughput": 657.25, "total_tokens": 46859872} {"current_steps": 34085, "total_steps": 40000, "loss": 0.9524, "lr": 2.650443905464828e-06, "epoch": 1.0909992958197299, "percentage": 85.21, "elapsed_time": "19:48:18", "remaining_time": "3:26:12", "throughput": 657.33, "total_tokens": 46866704} {"current_steps": 34090, "total_steps": 40000, "loss": 0.6661, "lr": 2.646046393987739e-06, "epoch": 1.0911593367902184, "percentage": 85.22, "elapsed_time": "19:48:20", "remaining_time": "3:26:01", "throughput": 657.4, "total_tokens": 46873120} {"current_steps": 34095, "total_steps": 40000, "loss": 0.6441, "lr": 2.64165232977121e-06, "epoch": 1.0913193777607066, "percentage": 85.24, "elapsed_time": "19:48:22", "remaining_time": "3:25:49", "throughput": 657.48, "total_tokens": 46879840} {"current_steps": 34100, "total_steps": 40000, "loss": 0.4745, "lr": 2.6372617134928695e-06, "epoch": 1.0914794187311951, "percentage": 85.25, "elapsed_time": "19:48:24", "remaining_time": "3:25:37", "throughput": 657.55, "total_tokens": 46886304} {"current_steps": 34105, "total_steps": 40000, "loss": 0.7949, "lr": 2.6328745458297943e-06, "epoch": 1.0916394597016836, "percentage": 85.26, "elapsed_time": "19:48:25", "remaining_time": "3:25:25", "throughput": 657.63, "total_tokens": 46893104} {"current_steps": 34110, "total_steps": 40000, "loss": 0.6132, "lr": 2.6284908274585546e-06, "epoch": 1.0917995006721721, "percentage": 85.28, "elapsed_time": "19:48:27", "remaining_time": "3:25:13", "throughput": 657.71, "total_tokens": 46899920} {"current_steps": 34115, "total_steps": 40000, "loss": 0.5438, "lr": 2.6241105590551595e-06, "epoch": 1.0919595416426606, "percentage": 85.29, "elapsed_time": "19:48:29", "remaining_time": "3:25:01", "throughput": 657.79, "total_tokens": 46906768} {"current_steps": 34120, "total_steps": 40000, "loss": 0.6583, "lr": 2.6197337412951105e-06, "epoch": 1.092119582613149, "percentage": 85.3, "elapsed_time": "19:48:31", "remaining_time": "3:24:49", "throughput": 657.87, "total_tokens": 46913712} {"current_steps": 34125, "total_steps": 40000, "loss": 0.6602, "lr": 2.6153603748533705e-06, "epoch": 1.0922796235836374, "percentage": 85.31, "elapsed_time": "19:48:32", "remaining_time": "3:24:37", "throughput": 657.95, "total_tokens": 46920448} {"current_steps": 34130, "total_steps": 40000, "loss": 0.7493, "lr": 2.6109904604043585e-06, "epoch": 1.0924396645541259, "percentage": 85.32, "elapsed_time": "19:48:34", "remaining_time": "3:24:25", "throughput": 658.03, "total_tokens": 46927392} {"current_steps": 34135, "total_steps": 40000, "loss": 0.6838, "lr": 2.6066239986219765e-06, "epoch": 1.0925997055246144, "percentage": 85.34, "elapsed_time": "19:48:36", "remaining_time": "3:24:13", "throughput": 658.11, "total_tokens": 46933920} {"current_steps": 34140, "total_steps": 40000, "loss": 0.6573, "lr": 2.602260990179592e-06, "epoch": 1.0927597464951027, "percentage": 85.35, "elapsed_time": "19:48:38", "remaining_time": "3:24:01", "throughput": 658.19, "total_tokens": 46941104} {"current_steps": 34145, "total_steps": 40000, "loss": 0.7454, "lr": 2.5979014357500248e-06, "epoch": 1.0929197874655912, "percentage": 85.36, "elapsed_time": "19:48:39", "remaining_time": "3:23:49", "throughput": 658.27, "total_tokens": 46947760} {"current_steps": 34150, "total_steps": 40000, "loss": 0.7422, "lr": 2.5935453360055844e-06, "epoch": 1.0930798284360796, "percentage": 85.38, "elapsed_time": "19:48:41", "remaining_time": "3:23:37", "throughput": 658.35, "total_tokens": 46954688} {"current_steps": 34155, "total_steps": 40000, "loss": 0.8062, "lr": 2.5891926916180283e-06, "epoch": 1.0932398694065681, "percentage": 85.39, "elapsed_time": "19:48:43", "remaining_time": "3:23:25", "throughput": 658.42, "total_tokens": 46961024} {"current_steps": 34160, "total_steps": 40000, "loss": 0.7432, "lr": 2.5848435032585883e-06, "epoch": 1.0933999103770566, "percentage": 85.4, "elapsed_time": "19:48:45", "remaining_time": "3:23:13", "throughput": 658.51, "total_tokens": 46968336} {"current_steps": 34165, "total_steps": 40000, "loss": 0.6589, "lr": 2.58049777159797e-06, "epoch": 1.093559951347545, "percentage": 85.41, "elapsed_time": "19:48:47", "remaining_time": "3:23:01", "throughput": 658.58, "total_tokens": 46974912} {"current_steps": 34170, "total_steps": 40000, "loss": 0.9165, "lr": 2.576155497306332e-06, "epoch": 1.0937199923180334, "percentage": 85.42, "elapsed_time": "19:48:48", "remaining_time": "3:22:49", "throughput": 658.67, "total_tokens": 46982464} {"current_steps": 34175, "total_steps": 40000, "loss": 0.7782, "lr": 2.57181668105331e-06, "epoch": 1.093880033288522, "percentage": 85.44, "elapsed_time": "19:48:50", "remaining_time": "3:22:38", "throughput": 658.76, "total_tokens": 46989808} {"current_steps": 34180, "total_steps": 40000, "loss": 0.7527, "lr": 2.567481323508014e-06, "epoch": 1.0940400742590104, "percentage": 85.45, "elapsed_time": "19:48:52", "remaining_time": "3:22:26", "throughput": 658.84, "total_tokens": 46996560} {"current_steps": 34185, "total_steps": 40000, "loss": 0.7391, "lr": 2.5631494253389954e-06, "epoch": 1.0942001152294987, "percentage": 85.46, "elapsed_time": "19:48:54", "remaining_time": "3:22:14", "throughput": 658.92, "total_tokens": 47003184} {"current_steps": 34190, "total_steps": 40000, "loss": 0.9387, "lr": 2.5588209872142997e-06, "epoch": 1.0943601561999872, "percentage": 85.47, "elapsed_time": "19:48:55", "remaining_time": "3:22:02", "throughput": 659.0, "total_tokens": 47010528} {"current_steps": 34195, "total_steps": 40000, "loss": 0.7379, "lr": 2.5544960098014186e-06, "epoch": 1.0945201971704757, "percentage": 85.49, "elapsed_time": "19:48:57", "remaining_time": "3:21:50", "throughput": 659.08, "total_tokens": 47017168} {"current_steps": 34200, "total_steps": 40000, "loss": 0.8771, "lr": 2.550174493767318e-06, "epoch": 1.0946802381409642, "percentage": 85.5, "elapsed_time": "19:48:59", "remaining_time": "3:21:38", "throughput": 659.16, "total_tokens": 47023856} {"current_steps": 34200, "total_steps": 40000, "eval_loss": 0.7307831048965454, "epoch": 1.0946802381409642, "percentage": 85.5, "elapsed_time": "19:54:47", "remaining_time": "3:22:37", "throughput": 655.96, "total_tokens": 47023856} {"current_steps": 34205, "total_steps": 40000, "loss": 0.7677, "lr": 2.545856439778438e-06, "epoch": 1.0948402791114524, "percentage": 85.51, "elapsed_time": "19:54:50", "remaining_time": "3:22:25", "throughput": 656.02, "total_tokens": 47030720} {"current_steps": 34210, "total_steps": 40000, "loss": 0.6431, "lr": 2.541541848500667e-06, "epoch": 1.095000320081941, "percentage": 85.52, "elapsed_time": "19:54:52", "remaining_time": "3:22:13", "throughput": 656.1, "total_tokens": 47037536} {"current_steps": 34215, "total_steps": 40000, "loss": 0.5427, "lr": 2.5372307205993733e-06, "epoch": 1.0951603610524294, "percentage": 85.54, "elapsed_time": "19:54:54", "remaining_time": "3:22:01", "throughput": 656.19, "total_tokens": 47044656} {"current_steps": 34220, "total_steps": 40000, "loss": 0.7021, "lr": 2.5329230567393917e-06, "epoch": 1.095320402022918, "percentage": 85.55, "elapsed_time": "19:54:55", "remaining_time": "3:21:49", "throughput": 656.27, "total_tokens": 47051744} {"current_steps": 34225, "total_steps": 40000, "loss": 0.6768, "lr": 2.5286188575850164e-06, "epoch": 1.0954804429934064, "percentage": 85.56, "elapsed_time": "19:54:57", "remaining_time": "3:21:37", "throughput": 656.35, "total_tokens": 47058720} {"current_steps": 34230, "total_steps": 40000, "loss": 0.9332, "lr": 2.5243181237999984e-06, "epoch": 1.0956404839638947, "percentage": 85.58, "elapsed_time": "19:54:59", "remaining_time": "3:21:26", "throughput": 656.43, "total_tokens": 47065760} {"current_steps": 34235, "total_steps": 40000, "loss": 0.6714, "lr": 2.520020856047578e-06, "epoch": 1.0958005249343832, "percentage": 85.59, "elapsed_time": "19:55:01", "remaining_time": "3:21:14", "throughput": 656.52, "total_tokens": 47072912} {"current_steps": 34240, "total_steps": 40000, "loss": 0.8244, "lr": 2.515727054990438e-06, "epoch": 1.0959605659048717, "percentage": 85.6, "elapsed_time": "19:55:02", "remaining_time": "3:21:02", "throughput": 656.6, "total_tokens": 47079824} {"current_steps": 34245, "total_steps": 40000, "loss": 0.6561, "lr": 2.511436721290747e-06, "epoch": 1.0961206068753602, "percentage": 85.61, "elapsed_time": "19:55:04", "remaining_time": "3:20:50", "throughput": 656.69, "total_tokens": 47087328} {"current_steps": 34250, "total_steps": 40000, "loss": 0.9261, "lr": 2.5071498556101164e-06, "epoch": 1.0962806478458484, "percentage": 85.62, "elapsed_time": "19:55:06", "remaining_time": "3:20:38", "throughput": 656.76, "total_tokens": 47094064} {"current_steps": 34255, "total_steps": 40000, "loss": 0.6954, "lr": 2.5028664586096485e-06, "epoch": 1.096440688816337, "percentage": 85.64, "elapsed_time": "19:55:07", "remaining_time": "3:20:26", "throughput": 656.84, "total_tokens": 47100800} {"current_steps": 34260, "total_steps": 40000, "loss": 0.707, "lr": 2.498586530949881e-06, "epoch": 1.0966007297868254, "percentage": 85.65, "elapsed_time": "19:55:09", "remaining_time": "3:20:14", "throughput": 656.92, "total_tokens": 47107680} {"current_steps": 34265, "total_steps": 40000, "loss": 0.7834, "lr": 2.4943100732908427e-06, "epoch": 1.096760770757314, "percentage": 85.66, "elapsed_time": "19:55:11", "remaining_time": "3:20:02", "throughput": 657.0, "total_tokens": 47114592} {"current_steps": 34270, "total_steps": 40000, "loss": 0.6437, "lr": 2.4900370862920188e-06, "epoch": 1.0969208117278022, "percentage": 85.67, "elapsed_time": "19:55:13", "remaining_time": "3:19:50", "throughput": 657.09, "total_tokens": 47121840} {"current_steps": 34275, "total_steps": 40000, "loss": 0.7421, "lr": 2.4857675706123518e-06, "epoch": 1.0970808526982907, "percentage": 85.69, "elapsed_time": "19:55:15", "remaining_time": "3:19:38", "throughput": 657.17, "total_tokens": 47128768} {"current_steps": 34280, "total_steps": 40000, "loss": 0.7902, "lr": 2.4815015269102543e-06, "epoch": 1.0972408936687792, "percentage": 85.7, "elapsed_time": "19:55:16", "remaining_time": "3:19:26", "throughput": 657.25, "total_tokens": 47135744} {"current_steps": 34285, "total_steps": 40000, "loss": 0.7721, "lr": 2.477238955843611e-06, "epoch": 1.0974009346392677, "percentage": 85.71, "elapsed_time": "19:55:18", "remaining_time": "3:19:14", "throughput": 657.33, "total_tokens": 47142784} {"current_steps": 34290, "total_steps": 40000, "loss": 0.7571, "lr": 2.4729798580697573e-06, "epoch": 1.0975609756097562, "percentage": 85.72, "elapsed_time": "19:55:20", "remaining_time": "3:19:02", "throughput": 657.41, "total_tokens": 47149536} {"current_steps": 34295, "total_steps": 40000, "loss": 0.6124, "lr": 2.4687242342455034e-06, "epoch": 1.0977210165802445, "percentage": 85.74, "elapsed_time": "19:55:22", "remaining_time": "3:18:51", "throughput": 657.49, "total_tokens": 47156560} {"current_steps": 34300, "total_steps": 40000, "loss": 0.6161, "lr": 2.4644720850271196e-06, "epoch": 1.097881057550733, "percentage": 85.75, "elapsed_time": "19:55:24", "remaining_time": "3:18:39", "throughput": 657.57, "total_tokens": 47163424} {"current_steps": 34305, "total_steps": 40000, "loss": 0.6188, "lr": 2.4602234110703364e-06, "epoch": 1.0980410985212214, "percentage": 85.76, "elapsed_time": "19:55:25", "remaining_time": "3:18:27", "throughput": 657.65, "total_tokens": 47170192} {"current_steps": 34310, "total_steps": 40000, "loss": 0.6023, "lr": 2.4559782130303576e-06, "epoch": 1.09820113949171, "percentage": 85.78, "elapsed_time": "19:55:27", "remaining_time": "3:18:15", "throughput": 657.73, "total_tokens": 47177360} {"current_steps": 34315, "total_steps": 40000, "loss": 0.9016, "lr": 2.451736491561843e-06, "epoch": 1.0983611804621982, "percentage": 85.79, "elapsed_time": "19:55:29", "remaining_time": "3:18:03", "throughput": 657.81, "total_tokens": 47184272} {"current_steps": 34320, "total_steps": 40000, "loss": 0.6027, "lr": 2.4474982473189163e-06, "epoch": 1.0985212214326867, "percentage": 85.8, "elapsed_time": "19:55:31", "remaining_time": "3:17:51", "throughput": 657.89, "total_tokens": 47190848} {"current_steps": 34325, "total_steps": 40000, "loss": 0.7968, "lr": 2.4432634809551796e-06, "epoch": 1.0986812624031752, "percentage": 85.81, "elapsed_time": "19:55:32", "remaining_time": "3:17:39", "throughput": 657.96, "total_tokens": 47197680} {"current_steps": 34330, "total_steps": 40000, "loss": 0.7146, "lr": 2.439032193123675e-06, "epoch": 1.0988413033736637, "percentage": 85.82, "elapsed_time": "19:55:34", "remaining_time": "3:17:27", "throughput": 658.05, "total_tokens": 47204704} {"current_steps": 34335, "total_steps": 40000, "loss": 0.6693, "lr": 2.4348043844769297e-06, "epoch": 1.0990013443441522, "percentage": 85.84, "elapsed_time": "19:55:36", "remaining_time": "3:17:15", "throughput": 658.13, "total_tokens": 47211808} {"current_steps": 34340, "total_steps": 40000, "loss": 0.6368, "lr": 2.4305800556669146e-06, "epoch": 1.0991613853146405, "percentage": 85.85, "elapsed_time": "19:55:38", "remaining_time": "3:17:04", "throughput": 658.21, "total_tokens": 47218672} {"current_steps": 34345, "total_steps": 40000, "loss": 0.768, "lr": 2.426359207345083e-06, "epoch": 1.099321426285129, "percentage": 85.86, "elapsed_time": "19:55:39", "remaining_time": "3:16:52", "throughput": 658.29, "total_tokens": 47225664} {"current_steps": 34350, "total_steps": 40000, "loss": 0.7296, "lr": 2.4221418401623396e-06, "epoch": 1.0994814672556175, "percentage": 85.88, "elapsed_time": "19:55:41", "remaining_time": "3:16:40", "throughput": 658.38, "total_tokens": 47233200} {"current_steps": 34355, "total_steps": 40000, "loss": 0.6275, "lr": 2.4179279547690557e-06, "epoch": 1.099641508226106, "percentage": 85.89, "elapsed_time": "19:55:43", "remaining_time": "3:16:28", "throughput": 658.46, "total_tokens": 47240064} {"current_steps": 34360, "total_steps": 40000, "loss": 0.6839, "lr": 2.413717551815062e-06, "epoch": 1.0998015491965942, "percentage": 85.9, "elapsed_time": "19:55:45", "remaining_time": "3:16:16", "throughput": 658.54, "total_tokens": 47246800} {"current_steps": 34365, "total_steps": 40000, "loss": 0.6069, "lr": 2.409510631949666e-06, "epoch": 1.0999615901670827, "percentage": 85.91, "elapsed_time": "19:55:47", "remaining_time": "3:16:04", "throughput": 658.61, "total_tokens": 47253312} {"current_steps": 34370, "total_steps": 40000, "loss": 0.741, "lr": 2.405307195821618e-06, "epoch": 1.1001216311375712, "percentage": 85.92, "elapsed_time": "19:55:48", "remaining_time": "3:15:52", "throughput": 658.69, "total_tokens": 47260064} {"current_steps": 34375, "total_steps": 40000, "loss": 0.81, "lr": 2.4011072440791372e-06, "epoch": 1.1002816721080597, "percentage": 85.94, "elapsed_time": "19:55:50", "remaining_time": "3:15:41", "throughput": 658.77, "total_tokens": 47266976} {"current_steps": 34380, "total_steps": 40000, "loss": 0.7891, "lr": 2.3969107773699233e-06, "epoch": 1.1004417130785482, "percentage": 85.95, "elapsed_time": "19:55:52", "remaining_time": "3:15:29", "throughput": 658.85, "total_tokens": 47273856} {"current_steps": 34385, "total_steps": 40000, "loss": 0.9229, "lr": 2.3927177963411096e-06, "epoch": 1.1006017540490365, "percentage": 85.96, "elapsed_time": "19:55:54", "remaining_time": "3:15:17", "throughput": 658.93, "total_tokens": 47280752} {"current_steps": 34390, "total_steps": 40000, "loss": 0.8454, "lr": 2.3885283016393144e-06, "epoch": 1.100761795019525, "percentage": 85.97, "elapsed_time": "19:55:55", "remaining_time": "3:15:05", "throughput": 659.01, "total_tokens": 47288032} {"current_steps": 34395, "total_steps": 40000, "loss": 0.8886, "lr": 2.3843422939106076e-06, "epoch": 1.1009218359900135, "percentage": 85.99, "elapsed_time": "19:55:57", "remaining_time": "3:14:53", "throughput": 659.09, "total_tokens": 47294832} {"current_steps": 34400, "total_steps": 40000, "loss": 0.6231, "lr": 2.380159773800525e-06, "epoch": 1.101081876960502, "percentage": 86.0, "elapsed_time": "19:55:59", "remaining_time": "3:14:41", "throughput": 659.17, "total_tokens": 47301520} {"current_steps": 34400, "total_steps": 40000, "eval_loss": 0.7305418848991394, "epoch": 1.101081876960502, "percentage": 86.0, "elapsed_time": "20:01:46", "remaining_time": "3:15:38", "throughput": 656.0, "total_tokens": 47301520} {"current_steps": 34405, "total_steps": 40000, "loss": 0.7076, "lr": 2.3759807419540675e-06, "epoch": 1.1012419179309902, "percentage": 86.01, "elapsed_time": "20:01:49", "remaining_time": "3:15:26", "throughput": 656.06, "total_tokens": 47308416} {"current_steps": 34410, "total_steps": 40000, "loss": 0.8593, "lr": 2.3718051990156835e-06, "epoch": 1.1014019589014787, "percentage": 86.02, "elapsed_time": "20:01:51", "remaining_time": "3:15:14", "throughput": 656.14, "total_tokens": 47315040} {"current_steps": 34415, "total_steps": 40000, "loss": 0.6859, "lr": 2.367633145629311e-06, "epoch": 1.1015619998719672, "percentage": 86.04, "elapsed_time": "20:01:53", "remaining_time": "3:15:02", "throughput": 656.21, "total_tokens": 47321776} {"current_steps": 34420, "total_steps": 40000, "loss": 0.7218, "lr": 2.363464582438316e-06, "epoch": 1.1017220408424557, "percentage": 86.05, "elapsed_time": "20:01:54", "remaining_time": "3:14:50", "throughput": 656.29, "total_tokens": 47328512} {"current_steps": 34425, "total_steps": 40000, "loss": 0.765, "lr": 2.3592995100855526e-06, "epoch": 1.1018820818129442, "percentage": 86.06, "elapsed_time": "20:01:56", "remaining_time": "3:14:39", "throughput": 656.37, "total_tokens": 47335488} {"current_steps": 34430, "total_steps": 40000, "loss": 0.7386, "lr": 2.3551379292133273e-06, "epoch": 1.1020421227834325, "percentage": 86.08, "elapsed_time": "20:01:58", "remaining_time": "3:14:27", "throughput": 656.45, "total_tokens": 47342128} {"current_steps": 34435, "total_steps": 40000, "loss": 0.6938, "lr": 2.3509798404634047e-06, "epoch": 1.102202163753921, "percentage": 86.09, "elapsed_time": "20:02:00", "remaining_time": "3:14:15", "throughput": 656.53, "total_tokens": 47348736} {"current_steps": 34440, "total_steps": 40000, "loss": 0.5928, "lr": 2.346825244477019e-06, "epoch": 1.1023622047244095, "percentage": 86.1, "elapsed_time": "20:02:01", "remaining_time": "3:14:03", "throughput": 656.6, "total_tokens": 47355488} {"current_steps": 34445, "total_steps": 40000, "loss": 0.8172, "lr": 2.3426741418948545e-06, "epoch": 1.102522245694898, "percentage": 86.11, "elapsed_time": "20:02:03", "remaining_time": "3:13:51", "throughput": 656.69, "total_tokens": 47362624} {"current_steps": 34450, "total_steps": 40000, "loss": 0.6821, "lr": 2.3385265333570715e-06, "epoch": 1.1026822866653863, "percentage": 86.12, "elapsed_time": "20:02:05", "remaining_time": "3:13:39", "throughput": 656.76, "total_tokens": 47369312} {"current_steps": 34455, "total_steps": 40000, "loss": 0.4707, "lr": 2.334382419503278e-06, "epoch": 1.1028423276358748, "percentage": 86.14, "elapsed_time": "20:02:07", "remaining_time": "3:13:27", "throughput": 656.84, "total_tokens": 47376096} {"current_steps": 34460, "total_steps": 40000, "loss": 0.5494, "lr": 2.3302418009725465e-06, "epoch": 1.1030023686063632, "percentage": 86.15, "elapsed_time": "20:02:08", "remaining_time": "3:13:15", "throughput": 656.92, "total_tokens": 47383136} {"current_steps": 34465, "total_steps": 40000, "loss": 0.8257, "lr": 2.326104678403415e-06, "epoch": 1.1031624095768517, "percentage": 86.16, "elapsed_time": "20:02:10", "remaining_time": "3:13:04", "throughput": 657.01, "total_tokens": 47390416} {"current_steps": 34470, "total_steps": 40000, "loss": 0.7653, "lr": 2.321971052433883e-06, "epoch": 1.10332245054734, "percentage": 86.17, "elapsed_time": "20:02:12", "remaining_time": "3:12:52", "throughput": 657.09, "total_tokens": 47397488} {"current_steps": 34475, "total_steps": 40000, "loss": 1.1396, "lr": 2.3178409237014004e-06, "epoch": 1.1034824915178285, "percentage": 86.19, "elapsed_time": "20:02:14", "remaining_time": "3:12:40", "throughput": 657.17, "total_tokens": 47404112} {"current_steps": 34480, "total_steps": 40000, "loss": 0.8543, "lr": 2.313714292842889e-06, "epoch": 1.103642532488317, "percentage": 86.2, "elapsed_time": "20:02:15", "remaining_time": "3:12:28", "throughput": 657.25, "total_tokens": 47411184} {"current_steps": 34485, "total_steps": 40000, "loss": 0.7711, "lr": 2.309591160494734e-06, "epoch": 1.1038025734588055, "percentage": 86.21, "elapsed_time": "20:02:17", "remaining_time": "3:12:16", "throughput": 657.32, "total_tokens": 47417600} {"current_steps": 34490, "total_steps": 40000, "loss": 0.6841, "lr": 2.305471527292763e-06, "epoch": 1.103962614429294, "percentage": 86.22, "elapsed_time": "20:02:19", "remaining_time": "3:12:04", "throughput": 657.4, "total_tokens": 47424800} {"current_steps": 34495, "total_steps": 40000, "loss": 0.6017, "lr": 2.3013553938722817e-06, "epoch": 1.1041226553997823, "percentage": 86.24, "elapsed_time": "20:02:21", "remaining_time": "3:11:52", "throughput": 657.48, "total_tokens": 47431248} {"current_steps": 34500, "total_steps": 40000, "loss": 0.6939, "lr": 2.297242760868043e-06, "epoch": 1.1042826963702708, "percentage": 86.25, "elapsed_time": "20:02:22", "remaining_time": "3:11:41", "throughput": 657.56, "total_tokens": 47438352} {"current_steps": 34505, "total_steps": 40000, "loss": 0.5914, "lr": 2.2931336289142735e-06, "epoch": 1.1044427373407593, "percentage": 86.26, "elapsed_time": "20:02:24", "remaining_time": "3:11:29", "throughput": 657.64, "total_tokens": 47445072} {"current_steps": 34510, "total_steps": 40000, "loss": 0.6682, "lr": 2.289027998644655e-06, "epoch": 1.1046027783112478, "percentage": 86.28, "elapsed_time": "20:02:26", "remaining_time": "3:11:17", "throughput": 657.72, "total_tokens": 47452048} {"current_steps": 34515, "total_steps": 40000, "loss": 0.6765, "lr": 2.2849258706923228e-06, "epoch": 1.104762819281736, "percentage": 86.29, "elapsed_time": "20:02:28", "remaining_time": "3:11:05", "throughput": 657.8, "total_tokens": 47459296} {"current_steps": 34520, "total_steps": 40000, "loss": 0.6871, "lr": 2.2808272456898705e-06, "epoch": 1.1049228602522245, "percentage": 86.3, "elapsed_time": "20:02:30", "remaining_time": "3:10:53", "throughput": 657.88, "total_tokens": 47466384} {"current_steps": 34525, "total_steps": 40000, "loss": 0.6021, "lr": 2.2767321242693707e-06, "epoch": 1.105082901222713, "percentage": 86.31, "elapsed_time": "20:02:31", "remaining_time": "3:10:41", "throughput": 657.96, "total_tokens": 47472816} {"current_steps": 34530, "total_steps": 40000, "loss": 0.7215, "lr": 2.272640507062329e-06, "epoch": 1.1052429421932015, "percentage": 86.33, "elapsed_time": "20:02:33", "remaining_time": "3:10:30", "throughput": 658.04, "total_tokens": 47479920} {"current_steps": 34535, "total_steps": 40000, "loss": 0.631, "lr": 2.2685523946997382e-06, "epoch": 1.1054029831636898, "percentage": 86.34, "elapsed_time": "20:02:35", "remaining_time": "3:10:18", "throughput": 658.12, "total_tokens": 47486704} {"current_steps": 34540, "total_steps": 40000, "loss": 0.7512, "lr": 2.2644677878120245e-06, "epoch": 1.1055630241341783, "percentage": 86.35, "elapsed_time": "20:02:37", "remaining_time": "3:10:06", "throughput": 658.2, "total_tokens": 47493696} {"current_steps": 34545, "total_steps": 40000, "loss": 0.941, "lr": 2.2603866870290897e-06, "epoch": 1.1057230651046668, "percentage": 86.36, "elapsed_time": "20:02:38", "remaining_time": "3:09:54", "throughput": 658.27, "total_tokens": 47500320} {"current_steps": 34550, "total_steps": 40000, "loss": 0.7827, "lr": 2.256309092980294e-06, "epoch": 1.1058831060751553, "percentage": 86.38, "elapsed_time": "20:02:40", "remaining_time": "3:09:42", "throughput": 658.35, "total_tokens": 47507152} {"current_steps": 34555, "total_steps": 40000, "loss": 0.7651, "lr": 2.252235006294448e-06, "epoch": 1.1060431470456438, "percentage": 86.39, "elapsed_time": "20:02:42", "remaining_time": "3:09:30", "throughput": 658.42, "total_tokens": 47513424} {"current_steps": 34560, "total_steps": 40000, "loss": 0.7183, "lr": 2.2481644275998333e-06, "epoch": 1.106203188016132, "percentage": 86.4, "elapsed_time": "20:02:44", "remaining_time": "3:09:19", "throughput": 658.51, "total_tokens": 47520720} {"current_steps": 34565, "total_steps": 40000, "loss": 0.6408, "lr": 2.2440973575241832e-06, "epoch": 1.1063632289866205, "percentage": 86.41, "elapsed_time": "20:02:46", "remaining_time": "3:09:07", "throughput": 658.58, "total_tokens": 47527456} {"current_steps": 34570, "total_steps": 40000, "loss": 0.6963, "lr": 2.240033796694685e-06, "epoch": 1.106523269957109, "percentage": 86.42, "elapsed_time": "20:02:47", "remaining_time": "3:08:55", "throughput": 658.66, "total_tokens": 47533968} {"current_steps": 34575, "total_steps": 40000, "loss": 0.7366, "lr": 2.235973745737999e-06, "epoch": 1.1066833109275975, "percentage": 86.44, "elapsed_time": "20:02:49", "remaining_time": "3:08:43", "throughput": 658.74, "total_tokens": 47540736} {"current_steps": 34580, "total_steps": 40000, "loss": 0.6667, "lr": 2.2319172052802263e-06, "epoch": 1.1068433518980858, "percentage": 86.45, "elapsed_time": "20:02:51", "remaining_time": "3:08:31", "throughput": 658.81, "total_tokens": 47547456} {"current_steps": 34585, "total_steps": 40000, "loss": 0.5527, "lr": 2.2278641759469477e-06, "epoch": 1.1070033928685743, "percentage": 86.46, "elapsed_time": "20:02:53", "remaining_time": "3:08:20", "throughput": 658.89, "total_tokens": 47554384} {"current_steps": 34590, "total_steps": 40000, "loss": 0.5623, "lr": 2.2238146583631825e-06, "epoch": 1.1071634338390628, "percentage": 86.48, "elapsed_time": "20:02:54", "remaining_time": "3:08:08", "throughput": 658.97, "total_tokens": 47561248} {"current_steps": 34595, "total_steps": 40000, "loss": 0.9068, "lr": 2.2197686531534256e-06, "epoch": 1.1073234748095513, "percentage": 86.49, "elapsed_time": "20:02:56", "remaining_time": "3:07:56", "throughput": 659.05, "total_tokens": 47568112} {"current_steps": 34600, "total_steps": 40000, "loss": 0.6705, "lr": 2.2157261609416087e-06, "epoch": 1.1074835157800398, "percentage": 86.5, "elapsed_time": "20:02:58", "remaining_time": "3:07:44", "throughput": 659.13, "total_tokens": 47574864} {"current_steps": 34600, "total_steps": 40000, "eval_loss": 0.7306476831436157, "epoch": 1.1074835157800398, "percentage": 86.5, "elapsed_time": "20:08:45", "remaining_time": "3:08:39", "throughput": 655.97, "total_tokens": 47574864} {"current_steps": 34605, "total_steps": 40000, "loss": 0.6116, "lr": 2.211687182351149e-06, "epoch": 1.107643556750528, "percentage": 86.51, "elapsed_time": "20:08:49", "remaining_time": "3:08:27", "throughput": 656.03, "total_tokens": 47581456} {"current_steps": 34610, "total_steps": 40000, "loss": 0.683, "lr": 2.2076517180048993e-06, "epoch": 1.1078035977210166, "percentage": 86.52, "elapsed_time": "20:08:51", "remaining_time": "3:08:15", "throughput": 656.11, "total_tokens": 47588656} {"current_steps": 34615, "total_steps": 40000, "loss": 0.6958, "lr": 2.2036197685251834e-06, "epoch": 1.107963638691505, "percentage": 86.54, "elapsed_time": "20:08:52", "remaining_time": "3:08:03", "throughput": 656.19, "total_tokens": 47595312} {"current_steps": 34620, "total_steps": 40000, "loss": 0.6611, "lr": 2.199591334533771e-06, "epoch": 1.1081236796619935, "percentage": 86.55, "elapsed_time": "20:08:54", "remaining_time": "3:07:51", "throughput": 656.27, "total_tokens": 47602064} {"current_steps": 34625, "total_steps": 40000, "loss": 0.626, "lr": 2.1955664166519036e-06, "epoch": 1.1082837206324818, "percentage": 86.56, "elapsed_time": "20:08:56", "remaining_time": "3:07:40", "throughput": 656.35, "total_tokens": 47609072} {"current_steps": 34630, "total_steps": 40000, "loss": 0.6136, "lr": 2.1915450155002793e-06, "epoch": 1.1084437616029703, "percentage": 86.58, "elapsed_time": "20:08:58", "remaining_time": "3:07:28", "throughput": 656.43, "total_tokens": 47615856} {"current_steps": 34635, "total_steps": 40000, "loss": 0.7721, "lr": 2.187527131699038e-06, "epoch": 1.1086038025734588, "percentage": 86.59, "elapsed_time": "20:08:59", "remaining_time": "3:07:16", "throughput": 656.51, "total_tokens": 47622784} {"current_steps": 34640, "total_steps": 40000, "loss": 0.552, "lr": 2.18351276586779e-06, "epoch": 1.1087638435439473, "percentage": 86.6, "elapsed_time": "20:09:01", "remaining_time": "3:07:04", "throughput": 656.59, "total_tokens": 47629952} {"current_steps": 34645, "total_steps": 40000, "loss": 0.819, "lr": 2.1795019186256092e-06, "epoch": 1.1089238845144358, "percentage": 86.61, "elapsed_time": "20:09:03", "remaining_time": "3:06:52", "throughput": 656.67, "total_tokens": 47636896} {"current_steps": 34650, "total_steps": 40000, "loss": 0.7569, "lr": 2.1754945905910094e-06, "epoch": 1.109083925484924, "percentage": 86.62, "elapsed_time": "20:09:04", "remaining_time": "3:06:41", "throughput": 656.75, "total_tokens": 47644112} {"current_steps": 34655, "total_steps": 40000, "loss": 0.8191, "lr": 2.171490782381977e-06, "epoch": 1.1092439664554126, "percentage": 86.64, "elapsed_time": "20:09:06", "remaining_time": "3:06:29", "throughput": 656.84, "total_tokens": 47651440} {"current_steps": 34660, "total_steps": 40000, "loss": 0.7875, "lr": 2.1674904946159425e-06, "epoch": 1.109404007425901, "percentage": 86.65, "elapsed_time": "20:09:08", "remaining_time": "3:06:17", "throughput": 656.92, "total_tokens": 47658704} {"current_steps": 34665, "total_steps": 40000, "loss": 0.5249, "lr": 2.16349372790981e-06, "epoch": 1.1095640483963896, "percentage": 86.66, "elapsed_time": "20:09:10", "remaining_time": "3:06:05", "throughput": 657.0, "total_tokens": 47665792} {"current_steps": 34670, "total_steps": 40000, "loss": 0.676, "lr": 2.159500482879928e-06, "epoch": 1.1097240893668778, "percentage": 86.67, "elapsed_time": "20:09:11", "remaining_time": "3:05:53", "throughput": 657.09, "total_tokens": 47673264} {"current_steps": 34675, "total_steps": 40000, "loss": 0.7697, "lr": 2.155510760142096e-06, "epoch": 1.1098841303373663, "percentage": 86.69, "elapsed_time": "20:09:13", "remaining_time": "3:05:41", "throughput": 657.17, "total_tokens": 47680336} {"current_steps": 34680, "total_steps": 40000, "loss": 0.9387, "lr": 2.151524560311588e-06, "epoch": 1.1100441713078548, "percentage": 86.7, "elapsed_time": "20:09:15", "remaining_time": "3:05:30", "throughput": 657.26, "total_tokens": 47687536} {"current_steps": 34685, "total_steps": 40000, "loss": 0.6955, "lr": 2.147541884003129e-06, "epoch": 1.1102042122783433, "percentage": 86.71, "elapsed_time": "20:09:17", "remaining_time": "3:05:18", "throughput": 657.34, "total_tokens": 47694624} {"current_steps": 34690, "total_steps": 40000, "loss": 0.928, "lr": 2.1435627318308895e-06, "epoch": 1.1103642532488318, "percentage": 86.72, "elapsed_time": "20:09:18", "remaining_time": "3:05:06", "throughput": 657.42, "total_tokens": 47701696} {"current_steps": 34695, "total_steps": 40000, "loss": 0.7463, "lr": 2.139587104408511e-06, "epoch": 1.11052429421932, "percentage": 86.74, "elapsed_time": "20:09:20", "remaining_time": "3:04:54", "throughput": 657.5, "total_tokens": 47708736} {"current_steps": 34700, "total_steps": 40000, "loss": 0.666, "lr": 2.1356150023490783e-06, "epoch": 1.1106843351898086, "percentage": 86.75, "elapsed_time": "20:09:22", "remaining_time": "3:04:43", "throughput": 657.59, "total_tokens": 47715920} {"current_steps": 34705, "total_steps": 40000, "loss": 0.6525, "lr": 2.1316464262651464e-06, "epoch": 1.110844376160297, "percentage": 86.76, "elapsed_time": "20:09:24", "remaining_time": "3:04:31", "throughput": 657.66, "total_tokens": 47722672} {"current_steps": 34710, "total_steps": 40000, "loss": 0.7762, "lr": 2.1276813767687224e-06, "epoch": 1.1110044171307856, "percentage": 86.78, "elapsed_time": "20:09:25", "remaining_time": "3:04:19", "throughput": 657.74, "total_tokens": 47729248} {"current_steps": 34715, "total_steps": 40000, "loss": 0.5851, "lr": 2.123719854471254e-06, "epoch": 1.1111644581012738, "percentage": 86.79, "elapsed_time": "20:09:27", "remaining_time": "3:04:07", "throughput": 657.81, "total_tokens": 47735888} {"current_steps": 34720, "total_steps": 40000, "loss": 0.6909, "lr": 2.119761859983668e-06, "epoch": 1.1113244990717623, "percentage": 86.8, "elapsed_time": "20:09:29", "remaining_time": "3:03:55", "throughput": 657.89, "total_tokens": 47742768} {"current_steps": 34725, "total_steps": 40000, "loss": 0.8207, "lr": 2.1158073939163386e-06, "epoch": 1.1114845400422508, "percentage": 86.81, "elapsed_time": "20:09:31", "remaining_time": "3:03:44", "throughput": 657.97, "total_tokens": 47749888} {"current_steps": 34730, "total_steps": 40000, "loss": 0.716, "lr": 2.111856456879088e-06, "epoch": 1.1116445810127393, "percentage": 86.83, "elapsed_time": "20:09:32", "remaining_time": "3:03:32", "throughput": 658.05, "total_tokens": 47756608} {"current_steps": 34735, "total_steps": 40000, "loss": 0.7926, "lr": 2.1079090494811993e-06, "epoch": 1.1118046219832276, "percentage": 86.84, "elapsed_time": "20:09:34", "remaining_time": "3:03:20", "throughput": 658.13, "total_tokens": 47763712} {"current_steps": 34740, "total_steps": 40000, "loss": 0.6572, "lr": 2.103965172331418e-06, "epoch": 1.111964662953716, "percentage": 86.85, "elapsed_time": "20:09:36", "remaining_time": "3:03:08", "throughput": 658.21, "total_tokens": 47770624} {"current_steps": 34745, "total_steps": 40000, "loss": 0.7508, "lr": 2.100024826037933e-06, "epoch": 1.1121247039242046, "percentage": 86.86, "elapsed_time": "20:09:38", "remaining_time": "3:02:57", "throughput": 658.29, "total_tokens": 47777312} {"current_steps": 34750, "total_steps": 40000, "loss": 0.7586, "lr": 2.0960880112084027e-06, "epoch": 1.112284744894693, "percentage": 86.88, "elapsed_time": "20:09:40", "remaining_time": "3:02:45", "throughput": 658.37, "total_tokens": 47784176} {"current_steps": 34755, "total_steps": 40000, "loss": 0.661, "lr": 2.092154728449927e-06, "epoch": 1.1124447858651816, "percentage": 86.89, "elapsed_time": "20:09:41", "remaining_time": "3:02:33", "throughput": 658.44, "total_tokens": 47790944} {"current_steps": 34760, "total_steps": 40000, "loss": 0.664, "lr": 2.0882249783690687e-06, "epoch": 1.1126048268356699, "percentage": 86.9, "elapsed_time": "20:09:43", "remaining_time": "3:02:21", "throughput": 658.53, "total_tokens": 47798192} {"current_steps": 34765, "total_steps": 40000, "loss": 0.5127, "lr": 2.084298761571851e-06, "epoch": 1.1127648678061584, "percentage": 86.91, "elapsed_time": "20:09:45", "remaining_time": "3:02:10", "throughput": 658.61, "total_tokens": 47805168} {"current_steps": 34770, "total_steps": 40000, "loss": 0.9833, "lr": 2.080376078663737e-06, "epoch": 1.1129249087766468, "percentage": 86.92, "elapsed_time": "20:09:47", "remaining_time": "3:01:58", "throughput": 658.69, "total_tokens": 47812080} {"current_steps": 34775, "total_steps": 40000, "loss": 0.499, "lr": 2.0764569302496593e-06, "epoch": 1.1130849497471353, "percentage": 86.94, "elapsed_time": "20:09:48", "remaining_time": "3:01:46", "throughput": 658.76, "total_tokens": 47818752} {"current_steps": 34780, "total_steps": 40000, "loss": 0.6188, "lr": 2.0725413169339957e-06, "epoch": 1.1132449907176236, "percentage": 86.95, "elapsed_time": "20:09:50", "remaining_time": "3:01:34", "throughput": 658.84, "total_tokens": 47825808} {"current_steps": 34785, "total_steps": 40000, "loss": 0.615, "lr": 2.068629239320588e-06, "epoch": 1.1134050316881121, "percentage": 86.96, "elapsed_time": "20:09:52", "remaining_time": "3:01:23", "throughput": 658.92, "total_tokens": 47832736} {"current_steps": 34790, "total_steps": 40000, "loss": 0.8739, "lr": 2.064720698012726e-06, "epoch": 1.1135650726586006, "percentage": 86.98, "elapsed_time": "20:09:54", "remaining_time": "3:01:11", "throughput": 659.0, "total_tokens": 47839840} {"current_steps": 34795, "total_steps": 40000, "loss": 0.6825, "lr": 2.0608156936131522e-06, "epoch": 1.113725113629089, "percentage": 86.99, "elapsed_time": "20:09:55", "remaining_time": "3:00:59", "throughput": 659.08, "total_tokens": 47846784} {"current_steps": 34800, "total_steps": 40000, "loss": 1.0773, "lr": 2.056914226724074e-06, "epoch": 1.1138851545995774, "percentage": 87.0, "elapsed_time": "20:09:57", "remaining_time": "3:00:47", "throughput": 659.16, "total_tokens": 47853888} {"current_steps": 34800, "total_steps": 40000, "eval_loss": 0.7306553721427917, "epoch": 1.1138851545995774, "percentage": 87.0, "elapsed_time": "20:15:45", "remaining_time": "3:01:39", "throughput": 656.02, "total_tokens": 47853888} {"current_steps": 34805, "total_steps": 40000, "loss": 0.8043, "lr": 2.0530162979471385e-06, "epoch": 1.1140451955700659, "percentage": 87.01, "elapsed_time": "20:15:48", "remaining_time": "3:01:28", "throughput": 656.09, "total_tokens": 47860848} {"current_steps": 34810, "total_steps": 40000, "loss": 0.6234, "lr": 2.0491219078834667e-06, "epoch": 1.1142052365405544, "percentage": 87.02, "elapsed_time": "20:15:50", "remaining_time": "3:01:16", "throughput": 656.17, "total_tokens": 47867968} {"current_steps": 34815, "total_steps": 40000, "loss": 0.7479, "lr": 2.045231057133612e-06, "epoch": 1.1143652775110429, "percentage": 87.04, "elapsed_time": "20:15:52", "remaining_time": "3:01:04", "throughput": 656.25, "total_tokens": 47875008} {"current_steps": 34820, "total_steps": 40000, "loss": 0.6498, "lr": 2.0413437462975944e-06, "epoch": 1.1145253184815314, "percentage": 87.05, "elapsed_time": "20:15:54", "remaining_time": "3:00:53", "throughput": 656.34, "total_tokens": 47882528} {"current_steps": 34825, "total_steps": 40000, "loss": 0.5497, "lr": 2.0374599759748843e-06, "epoch": 1.1146853594520196, "percentage": 87.06, "elapsed_time": "20:15:55", "remaining_time": "3:00:41", "throughput": 656.41, "total_tokens": 47889088} {"current_steps": 34830, "total_steps": 40000, "loss": 0.7132, "lr": 2.033579746764419e-06, "epoch": 1.1148454004225081, "percentage": 87.08, "elapsed_time": "20:15:57", "remaining_time": "3:00:29", "throughput": 656.49, "total_tokens": 47896144} {"current_steps": 34835, "total_steps": 40000, "loss": 1.0111, "lr": 2.029703059264565e-06, "epoch": 1.1150054413929966, "percentage": 87.09, "elapsed_time": "20:15:59", "remaining_time": "3:00:17", "throughput": 656.57, "total_tokens": 47903280} {"current_steps": 34840, "total_steps": 40000, "loss": 0.6732, "lr": 2.02582991407316e-06, "epoch": 1.1151654823634851, "percentage": 87.1, "elapsed_time": "20:16:01", "remaining_time": "3:00:05", "throughput": 656.65, "total_tokens": 47909952} {"current_steps": 34845, "total_steps": 40000, "loss": 0.9218, "lr": 2.0219603117874992e-06, "epoch": 1.1153255233339734, "percentage": 87.11, "elapsed_time": "20:16:03", "remaining_time": "2:59:54", "throughput": 656.73, "total_tokens": 47916816} {"current_steps": 34850, "total_steps": 40000, "loss": 0.7362, "lr": 2.0180942530043156e-06, "epoch": 1.1154855643044619, "percentage": 87.12, "elapsed_time": "20:16:04", "remaining_time": "2:59:42", "throughput": 656.81, "total_tokens": 47924192} {"current_steps": 34855, "total_steps": 40000, "loss": 0.8255, "lr": 2.0142317383198107e-06, "epoch": 1.1156456052749504, "percentage": 87.14, "elapsed_time": "20:16:06", "remaining_time": "2:59:30", "throughput": 656.89, "total_tokens": 47931088} {"current_steps": 34860, "total_steps": 40000, "loss": 0.7915, "lr": 2.0103727683296243e-06, "epoch": 1.1158056462454389, "percentage": 87.15, "elapsed_time": "20:16:08", "remaining_time": "2:59:18", "throughput": 656.98, "total_tokens": 47938416} {"current_steps": 34865, "total_steps": 40000, "loss": 0.6777, "lr": 2.0065173436288636e-06, "epoch": 1.1159656872159274, "percentage": 87.16, "elapsed_time": "20:16:10", "remaining_time": "2:59:07", "throughput": 657.05, "total_tokens": 47945168} {"current_steps": 34870, "total_steps": 40000, "loss": 0.7669, "lr": 2.002665464812087e-06, "epoch": 1.1161257281864156, "percentage": 87.17, "elapsed_time": "20:16:11", "remaining_time": "2:58:55", "throughput": 657.13, "total_tokens": 47952192} {"current_steps": 34875, "total_steps": 40000, "loss": 0.6522, "lr": 1.998817132473291e-06, "epoch": 1.1162857691569041, "percentage": 87.19, "elapsed_time": "20:16:13", "remaining_time": "2:58:43", "throughput": 657.22, "total_tokens": 47959296} {"current_steps": 34880, "total_steps": 40000, "loss": 0.5742, "lr": 1.9949723472059507e-06, "epoch": 1.1164458101273926, "percentage": 87.2, "elapsed_time": "20:16:15", "remaining_time": "2:58:31", "throughput": 657.29, "total_tokens": 47965936} {"current_steps": 34885, "total_steps": 40000, "loss": 0.779, "lr": 1.9911311096029726e-06, "epoch": 1.1166058510978811, "percentage": 87.21, "elapsed_time": "20:16:16", "remaining_time": "2:58:20", "throughput": 657.37, "total_tokens": 47973248} {"current_steps": 34890, "total_steps": 40000, "loss": 0.8277, "lr": 1.9872934202567224e-06, "epoch": 1.1167658920683694, "percentage": 87.22, "elapsed_time": "20:16:18", "remaining_time": "2:58:08", "throughput": 657.45, "total_tokens": 47979968} {"current_steps": 34895, "total_steps": 40000, "loss": 1.0247, "lr": 1.9834592797590257e-06, "epoch": 1.116925933038858, "percentage": 87.24, "elapsed_time": "20:16:20", "remaining_time": "2:57:56", "throughput": 657.53, "total_tokens": 47986672} {"current_steps": 34900, "total_steps": 40000, "loss": 0.7357, "lr": 1.979628688701149e-06, "epoch": 1.1170859740093464, "percentage": 87.25, "elapsed_time": "20:16:22", "remaining_time": "2:57:45", "throughput": 657.61, "total_tokens": 47993840} {"current_steps": 34905, "total_steps": 40000, "loss": 0.7791, "lr": 1.9758016476738193e-06, "epoch": 1.117246014979835, "percentage": 87.26, "elapsed_time": "20:16:23", "remaining_time": "2:57:33", "throughput": 657.68, "total_tokens": 48000256} {"current_steps": 34910, "total_steps": 40000, "loss": 0.7842, "lr": 1.971978157267221e-06, "epoch": 1.1174060559503234, "percentage": 87.28, "elapsed_time": "20:16:25", "remaining_time": "2:57:21", "throughput": 657.76, "total_tokens": 48006944} {"current_steps": 34915, "total_steps": 40000, "loss": 0.5761, "lr": 1.968158218070973e-06, "epoch": 1.1175660969208117, "percentage": 87.29, "elapsed_time": "20:16:27", "remaining_time": "2:57:09", "throughput": 657.84, "total_tokens": 48014064} {"current_steps": 34920, "total_steps": 40000, "loss": 0.6493, "lr": 1.9643418306741682e-06, "epoch": 1.1177261378913002, "percentage": 87.3, "elapsed_time": "20:16:29", "remaining_time": "2:56:58", "throughput": 657.92, "total_tokens": 48020704} {"current_steps": 34925, "total_steps": 40000, "loss": 0.8686, "lr": 1.9605289956653337e-06, "epoch": 1.1178861788617886, "percentage": 87.31, "elapsed_time": "20:16:30", "remaining_time": "2:56:46", "throughput": 658.0, "total_tokens": 48028112} {"current_steps": 34930, "total_steps": 40000, "loss": 0.5905, "lr": 1.9567197136324626e-06, "epoch": 1.1180462198322771, "percentage": 87.33, "elapsed_time": "20:16:32", "remaining_time": "2:56:34", "throughput": 658.08, "total_tokens": 48034912} {"current_steps": 34935, "total_steps": 40000, "loss": 0.6352, "lr": 1.9529139851629935e-06, "epoch": 1.1182062608027654, "percentage": 87.34, "elapsed_time": "20:16:34", "remaining_time": "2:56:22", "throughput": 658.16, "total_tokens": 48041648} {"current_steps": 34940, "total_steps": 40000, "loss": 0.7841, "lr": 1.949111810843812e-06, "epoch": 1.118366301773254, "percentage": 87.35, "elapsed_time": "20:16:36", "remaining_time": "2:56:11", "throughput": 658.23, "total_tokens": 48048016} {"current_steps": 34945, "total_steps": 40000, "loss": 0.6945, "lr": 1.9453131912612694e-06, "epoch": 1.1185263427437424, "percentage": 87.36, "elapsed_time": "20:16:37", "remaining_time": "2:55:59", "throughput": 658.31, "total_tokens": 48054864} {"current_steps": 34950, "total_steps": 40000, "loss": 0.7869, "lr": 1.941518127001149e-06, "epoch": 1.118686383714231, "percentage": 87.38, "elapsed_time": "20:16:39", "remaining_time": "2:55:47", "throughput": 658.38, "total_tokens": 48061392} {"current_steps": 34955, "total_steps": 40000, "loss": 0.6262, "lr": 1.9377266186487107e-06, "epoch": 1.1188464246847194, "percentage": 87.39, "elapsed_time": "20:16:41", "remaining_time": "2:55:36", "throughput": 658.46, "total_tokens": 48068240} {"current_steps": 34960, "total_steps": 40000, "loss": 0.6607, "lr": 1.9339386667886483e-06, "epoch": 1.1190064656552077, "percentage": 87.4, "elapsed_time": "20:16:43", "remaining_time": "2:55:24", "throughput": 658.54, "total_tokens": 48075200} {"current_steps": 34965, "total_steps": 40000, "loss": 0.6872, "lr": 1.9301542720051024e-06, "epoch": 1.1191665066256962, "percentage": 87.41, "elapsed_time": "20:16:44", "remaining_time": "2:55:12", "throughput": 658.61, "total_tokens": 48081776} {"current_steps": 34970, "total_steps": 40000, "loss": 0.6962, "lr": 1.926373434881684e-06, "epoch": 1.1193265475961847, "percentage": 87.42, "elapsed_time": "20:16:46", "remaining_time": "2:55:01", "throughput": 658.69, "total_tokens": 48088544} {"current_steps": 34975, "total_steps": 40000, "loss": 0.6386, "lr": 1.9225961560014468e-06, "epoch": 1.1194865885666732, "percentage": 87.44, "elapsed_time": "20:16:48", "remaining_time": "2:54:49", "throughput": 658.77, "total_tokens": 48095680} {"current_steps": 34980, "total_steps": 40000, "loss": 0.708, "lr": 1.918822435946885e-06, "epoch": 1.1196466295371614, "percentage": 87.45, "elapsed_time": "20:16:49", "remaining_time": "2:54:37", "throughput": 658.85, "total_tokens": 48102272} {"current_steps": 34985, "total_steps": 40000, "loss": 0.7697, "lr": 1.915052275299961e-06, "epoch": 1.11980667050765, "percentage": 87.46, "elapsed_time": "20:16:51", "remaining_time": "2:54:26", "throughput": 658.92, "total_tokens": 48109200} {"current_steps": 34990, "total_steps": 40000, "loss": 0.6513, "lr": 1.9112856746420854e-06, "epoch": 1.1199667114781384, "percentage": 87.48, "elapsed_time": "20:16:53", "remaining_time": "2:54:14", "throughput": 659.01, "total_tokens": 48116528} {"current_steps": 34995, "total_steps": 40000, "loss": 0.737, "lr": 1.907522634554104e-06, "epoch": 1.120126752448627, "percentage": 87.49, "elapsed_time": "20:16:55", "remaining_time": "2:54:02", "throughput": 659.09, "total_tokens": 48123296} {"current_steps": 35000, "total_steps": 40000, "loss": 0.5722, "lr": 1.9037631556163337e-06, "epoch": 1.1202867934191152, "percentage": 87.5, "elapsed_time": "20:16:56", "remaining_time": "2:53:50", "throughput": 659.16, "total_tokens": 48129792} {"current_steps": 35000, "total_steps": 40000, "eval_loss": 0.7304958701133728, "epoch": 1.1202867934191152, "percentage": 87.5, "elapsed_time": "20:22:44", "remaining_time": "2:54:40", "throughput": 656.03, "total_tokens": 48129792} {"current_steps": 35005, "total_steps": 40000, "loss": 0.7798, "lr": 1.9000072384085272e-06, "epoch": 1.1204468343896037, "percentage": 87.51, "elapsed_time": "20:22:48", "remaining_time": "2:54:29", "throughput": 656.11, "total_tokens": 48137376} {"current_steps": 35010, "total_steps": 40000, "loss": 0.7715, "lr": 1.8962548835098987e-06, "epoch": 1.1206068753600922, "percentage": 87.52, "elapsed_time": "20:22:50", "remaining_time": "2:54:17", "throughput": 656.18, "total_tokens": 48144016} {"current_steps": 35015, "total_steps": 40000, "loss": 0.8569, "lr": 1.8925060914991077e-06, "epoch": 1.1207669163305807, "percentage": 87.54, "elapsed_time": "20:22:51", "remaining_time": "2:54:05", "throughput": 656.26, "total_tokens": 48150864} {"current_steps": 35020, "total_steps": 40000, "loss": 0.7272, "lr": 1.888760862954264e-06, "epoch": 1.1209269573010692, "percentage": 87.55, "elapsed_time": "20:22:53", "remaining_time": "2:53:54", "throughput": 656.33, "total_tokens": 48157520} {"current_steps": 35025, "total_steps": 40000, "loss": 0.7668, "lr": 1.8850191984529309e-06, "epoch": 1.1210869982715574, "percentage": 87.56, "elapsed_time": "20:22:55", "remaining_time": "2:53:42", "throughput": 656.41, "total_tokens": 48164416} {"current_steps": 35030, "total_steps": 40000, "loss": 0.7538, "lr": 1.8812810985721186e-06, "epoch": 1.121247039242046, "percentage": 87.58, "elapsed_time": "20:22:57", "remaining_time": "2:53:30", "throughput": 656.49, "total_tokens": 48171680} {"current_steps": 35035, "total_steps": 40000, "loss": 0.5937, "lr": 1.8775465638882856e-06, "epoch": 1.1214070802125344, "percentage": 87.59, "elapsed_time": "20:22:58", "remaining_time": "2:53:18", "throughput": 656.57, "total_tokens": 48178400} {"current_steps": 35040, "total_steps": 40000, "loss": 0.9509, "lr": 1.8738155949773517e-06, "epoch": 1.121567121183023, "percentage": 87.6, "elapsed_time": "20:23:00", "remaining_time": "2:53:07", "throughput": 656.65, "total_tokens": 48185280} {"current_steps": 35045, "total_steps": 40000, "loss": 0.7592, "lr": 1.8700881924146707e-06, "epoch": 1.1217271621535112, "percentage": 87.61, "elapsed_time": "20:23:02", "remaining_time": "2:52:55", "throughput": 656.73, "total_tokens": 48192256} {"current_steps": 35050, "total_steps": 40000, "loss": 0.7673, "lr": 1.8663643567750577e-06, "epoch": 1.1218872031239997, "percentage": 87.62, "elapsed_time": "20:23:04", "remaining_time": "2:52:43", "throughput": 656.81, "total_tokens": 48199248} {"current_steps": 35055, "total_steps": 40000, "loss": 0.6844, "lr": 1.8626440886327813e-06, "epoch": 1.1220472440944882, "percentage": 87.64, "elapsed_time": "20:23:06", "remaining_time": "2:52:32", "throughput": 656.88, "total_tokens": 48206160} {"current_steps": 35060, "total_steps": 40000, "loss": 0.7929, "lr": 1.8589273885615432e-06, "epoch": 1.1222072850649767, "percentage": 87.65, "elapsed_time": "20:23:07", "remaining_time": "2:52:20", "throughput": 656.97, "total_tokens": 48213472} {"current_steps": 35065, "total_steps": 40000, "loss": 0.5501, "lr": 1.8552142571345133e-06, "epoch": 1.122367326035465, "percentage": 87.66, "elapsed_time": "20:23:09", "remaining_time": "2:52:08", "throughput": 657.04, "total_tokens": 48219872} {"current_steps": 35070, "total_steps": 40000, "loss": 0.7146, "lr": 1.8515046949243025e-06, "epoch": 1.1225273670059535, "percentage": 87.67, "elapsed_time": "20:23:11", "remaining_time": "2:51:57", "throughput": 657.12, "total_tokens": 48226608} {"current_steps": 35075, "total_steps": 40000, "loss": 0.5788, "lr": 1.8477987025029674e-06, "epoch": 1.122687407976442, "percentage": 87.69, "elapsed_time": "20:23:13", "remaining_time": "2:51:45", "throughput": 657.19, "total_tokens": 48233248} {"current_steps": 35080, "total_steps": 40000, "loss": 0.6003, "lr": 1.8440962804420232e-06, "epoch": 1.1228474489469304, "percentage": 87.7, "elapsed_time": "20:23:14", "remaining_time": "2:51:33", "throughput": 657.27, "total_tokens": 48240544} {"current_steps": 35085, "total_steps": 40000, "loss": 0.7734, "lr": 1.8403974293124265e-06, "epoch": 1.123007489917419, "percentage": 87.71, "elapsed_time": "20:23:16", "remaining_time": "2:51:22", "throughput": 657.36, "total_tokens": 48247920} {"current_steps": 35090, "total_steps": 40000, "loss": 0.7858, "lr": 1.8367021496845854e-06, "epoch": 1.1231675308879072, "percentage": 87.72, "elapsed_time": "20:23:18", "remaining_time": "2:51:10", "throughput": 657.44, "total_tokens": 48254800} {"current_steps": 35095, "total_steps": 40000, "loss": 0.6937, "lr": 1.8330104421283662e-06, "epoch": 1.1233275718583957, "percentage": 87.74, "elapsed_time": "20:23:20", "remaining_time": "2:50:58", "throughput": 657.52, "total_tokens": 48261888} {"current_steps": 35100, "total_steps": 40000, "loss": 0.6533, "lr": 1.8293223072130717e-06, "epoch": 1.1234876128288842, "percentage": 87.75, "elapsed_time": "20:23:21", "remaining_time": "2:50:46", "throughput": 657.59, "total_tokens": 48268688} {"current_steps": 35105, "total_steps": 40000, "loss": 0.7171, "lr": 1.8256377455074525e-06, "epoch": 1.1236476537993727, "percentage": 87.76, "elapsed_time": "20:23:23", "remaining_time": "2:50:35", "throughput": 657.67, "total_tokens": 48275376} {"current_steps": 35110, "total_steps": 40000, "loss": 0.6531, "lr": 1.8219567575797263e-06, "epoch": 1.123807694769861, "percentage": 87.78, "elapsed_time": "20:23:25", "remaining_time": "2:50:23", "throughput": 657.74, "total_tokens": 48281936} {"current_steps": 35115, "total_steps": 40000, "loss": 0.693, "lr": 1.8182793439975365e-06, "epoch": 1.1239677357403495, "percentage": 87.79, "elapsed_time": "20:23:27", "remaining_time": "2:50:12", "throughput": 657.82, "total_tokens": 48288976} {"current_steps": 35120, "total_steps": 40000, "loss": 0.7135, "lr": 1.8146055053279958e-06, "epoch": 1.124127776710838, "percentage": 87.8, "elapsed_time": "20:23:29", "remaining_time": "2:50:00", "throughput": 657.9, "total_tokens": 48295648} {"current_steps": 35125, "total_steps": 40000, "loss": 0.6859, "lr": 1.8109352421376486e-06, "epoch": 1.1242878176813265, "percentage": 87.81, "elapsed_time": "20:23:30", "remaining_time": "2:49:48", "throughput": 657.97, "total_tokens": 48302016} {"current_steps": 35130, "total_steps": 40000, "loss": 0.8155, "lr": 1.8072685549924972e-06, "epoch": 1.124447858651815, "percentage": 87.83, "elapsed_time": "20:23:32", "remaining_time": "2:49:37", "throughput": 658.05, "total_tokens": 48308976} {"current_steps": 35135, "total_steps": 40000, "loss": 0.6046, "lr": 1.8036054444579982e-06, "epoch": 1.1246078996223032, "percentage": 87.84, "elapsed_time": "20:23:34", "remaining_time": "2:49:25", "throughput": 658.13, "total_tokens": 48315856} {"current_steps": 35140, "total_steps": 40000, "loss": 0.9938, "lr": 1.7999459110990407e-06, "epoch": 1.1247679405927917, "percentage": 87.85, "elapsed_time": "20:23:36", "remaining_time": "2:49:13", "throughput": 658.2, "total_tokens": 48322832} {"current_steps": 35145, "total_steps": 40000, "loss": 0.8039, "lr": 1.7962899554799712e-06, "epoch": 1.1249279815632802, "percentage": 87.86, "elapsed_time": "20:23:37", "remaining_time": "2:49:02", "throughput": 658.28, "total_tokens": 48329360} {"current_steps": 35150, "total_steps": 40000, "loss": 0.887, "lr": 1.7926375781645937e-06, "epoch": 1.1250880225337687, "percentage": 87.88, "elapsed_time": "20:23:39", "remaining_time": "2:48:50", "throughput": 658.36, "total_tokens": 48336368} {"current_steps": 35155, "total_steps": 40000, "loss": 0.9201, "lr": 1.7889887797161359e-06, "epoch": 1.125248063504257, "percentage": 87.89, "elapsed_time": "20:23:41", "remaining_time": "2:48:38", "throughput": 658.43, "total_tokens": 48343136} {"current_steps": 35160, "total_steps": 40000, "loss": 0.7694, "lr": 1.7853435606973028e-06, "epoch": 1.1254081044747455, "percentage": 87.9, "elapsed_time": "20:23:43", "remaining_time": "2:48:27", "throughput": 658.51, "total_tokens": 48349872} {"current_steps": 35165, "total_steps": 40000, "loss": 0.6031, "lr": 1.781701921670223e-06, "epoch": 1.125568145445234, "percentage": 87.91, "elapsed_time": "20:23:45", "remaining_time": "2:48:15", "throughput": 658.59, "total_tokens": 48356928} {"current_steps": 35170, "total_steps": 40000, "loss": 0.8404, "lr": 1.7780638631964886e-06, "epoch": 1.1257281864157225, "percentage": 87.92, "elapsed_time": "20:23:46", "remaining_time": "2:48:03", "throughput": 658.67, "total_tokens": 48363728} {"current_steps": 35175, "total_steps": 40000, "loss": 0.7144, "lr": 1.7744293858371314e-06, "epoch": 1.125888227386211, "percentage": 87.94, "elapsed_time": "20:23:48", "remaining_time": "2:47:52", "throughput": 658.74, "total_tokens": 48370496} {"current_steps": 35180, "total_steps": 40000, "loss": 0.6962, "lr": 1.770798490152631e-06, "epoch": 1.1260482683566992, "percentage": 87.95, "elapsed_time": "20:23:50", "remaining_time": "2:47:40", "throughput": 658.82, "total_tokens": 48377136} {"current_steps": 35185, "total_steps": 40000, "loss": 0.595, "lr": 1.767171176702917e-06, "epoch": 1.1262083093271877, "percentage": 87.96, "elapsed_time": "20:23:52", "remaining_time": "2:47:29", "throughput": 658.9, "total_tokens": 48384176} {"current_steps": 35190, "total_steps": 40000, "loss": 0.7882, "lr": 1.7635474460473755e-06, "epoch": 1.1263683502976762, "percentage": 87.98, "elapsed_time": "20:23:53", "remaining_time": "2:47:17", "throughput": 658.97, "total_tokens": 48391072} {"current_steps": 35195, "total_steps": 40000, "loss": 0.7593, "lr": 1.7599272987448206e-06, "epoch": 1.1265283912681647, "percentage": 87.99, "elapsed_time": "20:23:55", "remaining_time": "2:47:05", "throughput": 659.05, "total_tokens": 48398064} {"current_steps": 35200, "total_steps": 40000, "loss": 0.7991, "lr": 1.7563107353535362e-06, "epoch": 1.126688432238653, "percentage": 88.0, "elapsed_time": "20:23:57", "remaining_time": "2:46:54", "throughput": 659.13, "total_tokens": 48405024} {"current_steps": 35200, "total_steps": 40000, "eval_loss": 0.7306515574455261, "epoch": 1.126688432238653, "percentage": 88.0, "elapsed_time": "20:29:44", "remaining_time": "2:47:41", "throughput": 656.03, "total_tokens": 48405024} {"current_steps": 35205, "total_steps": 40000, "loss": 0.7635, "lr": 1.7526977564312263e-06, "epoch": 1.1268484732091415, "percentage": 88.01, "elapsed_time": "20:29:48", "remaining_time": "2:47:30", "throughput": 656.09, "total_tokens": 48412112} {"current_steps": 35210, "total_steps": 40000, "loss": 0.8644, "lr": 1.7490883625350701e-06, "epoch": 1.12700851417963, "percentage": 88.02, "elapsed_time": "20:29:50", "remaining_time": "2:47:18", "throughput": 656.17, "total_tokens": 48418704} {"current_steps": 35215, "total_steps": 40000, "loss": 0.7571, "lr": 1.7454825542216807e-06, "epoch": 1.1271685551501185, "percentage": 88.04, "elapsed_time": "20:29:52", "remaining_time": "2:47:06", "throughput": 656.24, "total_tokens": 48424992} {"current_steps": 35220, "total_steps": 40000, "loss": 0.773, "lr": 1.7418803320471105e-06, "epoch": 1.127328596120607, "percentage": 88.05, "elapsed_time": "20:29:53", "remaining_time": "2:46:55", "throughput": 656.31, "total_tokens": 48431552} {"current_steps": 35225, "total_steps": 40000, "loss": 0.6716, "lr": 1.7382816965668737e-06, "epoch": 1.1274886370910953, "percentage": 88.06, "elapsed_time": "20:29:55", "remaining_time": "2:46:43", "throughput": 656.38, "total_tokens": 48438096} {"current_steps": 35230, "total_steps": 40000, "loss": 0.7647, "lr": 1.7346866483359285e-06, "epoch": 1.1276486780615838, "percentage": 88.08, "elapsed_time": "20:29:57", "remaining_time": "2:46:31", "throughput": 656.46, "total_tokens": 48444976} {"current_steps": 35235, "total_steps": 40000, "loss": 0.8548, "lr": 1.7310951879086657e-06, "epoch": 1.1278087190320722, "percentage": 88.09, "elapsed_time": "20:29:58", "remaining_time": "2:46:20", "throughput": 656.53, "total_tokens": 48451568} {"current_steps": 35240, "total_steps": 40000, "loss": 0.6292, "lr": 1.7275073158389471e-06, "epoch": 1.1279687600025607, "percentage": 88.1, "elapsed_time": "20:30:00", "remaining_time": "2:46:08", "throughput": 656.61, "total_tokens": 48458224} {"current_steps": 35245, "total_steps": 40000, "loss": 0.6456, "lr": 1.723923032680061e-06, "epoch": 1.128128800973049, "percentage": 88.11, "elapsed_time": "20:30:02", "remaining_time": "2:45:56", "throughput": 656.68, "total_tokens": 48464800} {"current_steps": 35250, "total_steps": 40000, "loss": 0.9902, "lr": 1.7203423389847428e-06, "epoch": 1.1282888419435375, "percentage": 88.12, "elapsed_time": "20:30:04", "remaining_time": "2:45:45", "throughput": 656.75, "total_tokens": 48471248} {"current_steps": 35255, "total_steps": 40000, "loss": 0.9235, "lr": 1.7167652353051928e-06, "epoch": 1.128448882914026, "percentage": 88.14, "elapsed_time": "20:30:05", "remaining_time": "2:45:33", "throughput": 656.84, "total_tokens": 48478560} {"current_steps": 35260, "total_steps": 40000, "loss": 0.6038, "lr": 1.7131917221930333e-06, "epoch": 1.1286089238845145, "percentage": 88.15, "elapsed_time": "20:30:07", "remaining_time": "2:45:21", "throughput": 656.91, "total_tokens": 48485264} {"current_steps": 35265, "total_steps": 40000, "loss": 0.6174, "lr": 1.7096218001993513e-06, "epoch": 1.128768964855003, "percentage": 88.16, "elapsed_time": "20:30:09", "remaining_time": "2:45:10", "throughput": 656.99, "total_tokens": 48492208} {"current_steps": 35270, "total_steps": 40000, "loss": 0.5776, "lr": 1.706055469874676e-06, "epoch": 1.1289290058254913, "percentage": 88.17, "elapsed_time": "20:30:11", "remaining_time": "2:44:58", "throughput": 657.08, "total_tokens": 48499456} {"current_steps": 35275, "total_steps": 40000, "loss": 0.8539, "lr": 1.702492731768976e-06, "epoch": 1.1290890467959798, "percentage": 88.19, "elapsed_time": "20:30:12", "remaining_time": "2:44:47", "throughput": 657.15, "total_tokens": 48506464} {"current_steps": 35280, "total_steps": 40000, "loss": 0.7526, "lr": 1.6989335864316724e-06, "epoch": 1.1292490877664683, "percentage": 88.2, "elapsed_time": "20:30:14", "remaining_time": "2:44:35", "throughput": 657.23, "total_tokens": 48513040} {"current_steps": 35285, "total_steps": 40000, "loss": 0.6781, "lr": 1.6953780344116265e-06, "epoch": 1.1294091287369568, "percentage": 88.21, "elapsed_time": "20:30:16", "remaining_time": "2:44:23", "throughput": 657.31, "total_tokens": 48520032} {"current_steps": 35290, "total_steps": 40000, "loss": 0.9128, "lr": 1.6918260762571497e-06, "epoch": 1.129569169707445, "percentage": 88.22, "elapsed_time": "20:30:18", "remaining_time": "2:44:12", "throughput": 657.38, "total_tokens": 48526832} {"current_steps": 35295, "total_steps": 40000, "loss": 0.6334, "lr": 1.6882777125160093e-06, "epoch": 1.1297292106779335, "percentage": 88.24, "elapsed_time": "20:30:19", "remaining_time": "2:44:00", "throughput": 657.46, "total_tokens": 48533824} {"current_steps": 35300, "total_steps": 40000, "loss": 0.8147, "lr": 1.6847329437353899e-06, "epoch": 1.129889251648422, "percentage": 88.25, "elapsed_time": "20:30:21", "remaining_time": "2:43:48", "throughput": 657.55, "total_tokens": 48541200} {"current_steps": 35305, "total_steps": 40000, "loss": 0.6226, "lr": 1.6811917704619511e-06, "epoch": 1.1300492926189105, "percentage": 88.26, "elapsed_time": "20:30:23", "remaining_time": "2:43:37", "throughput": 657.62, "total_tokens": 48547744} {"current_steps": 35310, "total_steps": 40000, "loss": 0.4602, "lr": 1.67765419324179e-06, "epoch": 1.1302093335893988, "percentage": 88.28, "elapsed_time": "20:30:24", "remaining_time": "2:43:25", "throughput": 657.7, "total_tokens": 48554416} {"current_steps": 35315, "total_steps": 40000, "loss": 0.8033, "lr": 1.6741202126204364e-06, "epoch": 1.1303693745598873, "percentage": 88.29, "elapsed_time": "20:30:26", "remaining_time": "2:43:14", "throughput": 657.77, "total_tokens": 48561168} {"current_steps": 35320, "total_steps": 40000, "loss": 0.8327, "lr": 1.6705898291428767e-06, "epoch": 1.1305294155303758, "percentage": 88.3, "elapsed_time": "20:30:28", "remaining_time": "2:43:02", "throughput": 657.85, "total_tokens": 48568160} {"current_steps": 35325, "total_steps": 40000, "loss": 0.7178, "lr": 1.6670630433535395e-06, "epoch": 1.1306894565008643, "percentage": 88.31, "elapsed_time": "20:30:30", "remaining_time": "2:42:50", "throughput": 657.93, "total_tokens": 48575264} {"current_steps": 35330, "total_steps": 40000, "loss": 0.7925, "lr": 1.6635398557962979e-06, "epoch": 1.1308494974713525, "percentage": 88.33, "elapsed_time": "20:30:31", "remaining_time": "2:42:39", "throughput": 658.01, "total_tokens": 48582128} {"current_steps": 35335, "total_steps": 40000, "loss": 0.602, "lr": 1.660020267014481e-06, "epoch": 1.131009538441841, "percentage": 88.34, "elapsed_time": "20:30:33", "remaining_time": "2:42:27", "throughput": 658.09, "total_tokens": 48589296} {"current_steps": 35340, "total_steps": 40000, "loss": 0.7547, "lr": 1.6565042775508438e-06, "epoch": 1.1311695794123295, "percentage": 88.35, "elapsed_time": "20:30:35", "remaining_time": "2:42:16", "throughput": 658.16, "total_tokens": 48595856} {"current_steps": 35345, "total_steps": 40000, "loss": 0.7145, "lr": 1.6529918879475997e-06, "epoch": 1.131329620382818, "percentage": 88.36, "elapsed_time": "20:30:37", "remaining_time": "2:42:04", "throughput": 658.25, "total_tokens": 48603088} {"current_steps": 35350, "total_steps": 40000, "loss": 0.8306, "lr": 1.6494830987464043e-06, "epoch": 1.1314896613533065, "percentage": 88.38, "elapsed_time": "20:30:38", "remaining_time": "2:41:52", "throughput": 658.33, "total_tokens": 48610512} {"current_steps": 35355, "total_steps": 40000, "loss": 0.6981, "lr": 1.6459779104883555e-06, "epoch": 1.1316497023237948, "percentage": 88.39, "elapsed_time": "20:30:40", "remaining_time": "2:41:41", "throughput": 658.41, "total_tokens": 48617280} {"current_steps": 35360, "total_steps": 40000, "loss": 0.7109, "lr": 1.6424763237140013e-06, "epoch": 1.1318097432942833, "percentage": 88.4, "elapsed_time": "20:30:42", "remaining_time": "2:41:29", "throughput": 658.49, "total_tokens": 48624384} {"current_steps": 35365, "total_steps": 40000, "loss": 0.6798, "lr": 1.6389783389633207e-06, "epoch": 1.1319697842647718, "percentage": 88.41, "elapsed_time": "20:30:44", "remaining_time": "2:41:18", "throughput": 658.57, "total_tokens": 48631456} {"current_steps": 35370, "total_steps": 40000, "loss": 0.809, "lr": 1.6354839567757546e-06, "epoch": 1.1321298252352603, "percentage": 88.42, "elapsed_time": "20:30:45", "remaining_time": "2:41:06", "throughput": 658.65, "total_tokens": 48638432} {"current_steps": 35375, "total_steps": 40000, "loss": 0.565, "lr": 1.6319931776901831e-06, "epoch": 1.1322898662057486, "percentage": 88.44, "elapsed_time": "20:30:47", "remaining_time": "2:40:54", "throughput": 658.72, "total_tokens": 48645056} {"current_steps": 35380, "total_steps": 40000, "loss": 0.6166, "lr": 1.6285060022449229e-06, "epoch": 1.132449907176237, "percentage": 88.45, "elapsed_time": "20:30:49", "remaining_time": "2:40:43", "throughput": 658.8, "total_tokens": 48651728} {"current_steps": 35385, "total_steps": 40000, "loss": 0.7702, "lr": 1.6250224309777434e-06, "epoch": 1.1326099481467256, "percentage": 88.46, "elapsed_time": "20:30:51", "remaining_time": "2:40:31", "throughput": 658.87, "total_tokens": 48658064} {"current_steps": 35390, "total_steps": 40000, "loss": 0.7925, "lr": 1.6215424644258515e-06, "epoch": 1.132769989117214, "percentage": 88.48, "elapsed_time": "20:30:52", "remaining_time": "2:40:20", "throughput": 658.94, "total_tokens": 48664752} {"current_steps": 35395, "total_steps": 40000, "loss": 0.9518, "lr": 1.6180661031259036e-06, "epoch": 1.1329300300877025, "percentage": 88.49, "elapsed_time": "20:30:54", "remaining_time": "2:40:08", "throughput": 659.02, "total_tokens": 48671824} {"current_steps": 35400, "total_steps": 40000, "loss": 0.7533, "lr": 1.614593347613999e-06, "epoch": 1.1330900710581908, "percentage": 88.5, "elapsed_time": "20:30:56", "remaining_time": "2:39:57", "throughput": 659.1, "total_tokens": 48678592} {"current_steps": 35400, "total_steps": 40000, "eval_loss": 0.7305846214294434, "epoch": 1.1330900710581908, "percentage": 88.5, "elapsed_time": "20:36:44", "remaining_time": "2:40:42", "throughput": 656.01, "total_tokens": 48678592} {"current_steps": 35405, "total_steps": 40000, "loss": 0.4849, "lr": 1.6111241984256758e-06, "epoch": 1.1332501120286793, "percentage": 88.51, "elapsed_time": "20:36:47", "remaining_time": "2:40:30", "throughput": 656.06, "total_tokens": 48685184} {"current_steps": 35410, "total_steps": 40000, "loss": 0.8863, "lr": 1.6076586560959257e-06, "epoch": 1.1334101529991678, "percentage": 88.52, "elapsed_time": "20:36:49", "remaining_time": "2:40:19", "throughput": 656.14, "total_tokens": 48691888} {"current_steps": 35415, "total_steps": 40000, "loss": 0.6775, "lr": 1.604196721159182e-06, "epoch": 1.1335701939696563, "percentage": 88.54, "elapsed_time": "20:36:51", "remaining_time": "2:40:07", "throughput": 656.21, "total_tokens": 48698208} {"current_steps": 35420, "total_steps": 40000, "loss": 0.7782, "lr": 1.6007383941493092e-06, "epoch": 1.1337302349401446, "percentage": 88.55, "elapsed_time": "20:36:53", "remaining_time": "2:39:56", "throughput": 656.29, "total_tokens": 48705440} {"current_steps": 35425, "total_steps": 40000, "loss": 0.9954, "lr": 1.5972836755996285e-06, "epoch": 1.133890275910633, "percentage": 88.56, "elapsed_time": "20:36:54", "remaining_time": "2:39:44", "throughput": 656.37, "total_tokens": 48712544} {"current_steps": 35430, "total_steps": 40000, "loss": 0.7005, "lr": 1.5938325660429076e-06, "epoch": 1.1340503168811216, "percentage": 88.58, "elapsed_time": "20:36:56", "remaining_time": "2:39:32", "throughput": 656.45, "total_tokens": 48719520} {"current_steps": 35435, "total_steps": 40000, "loss": 0.648, "lr": 1.5903850660113378e-06, "epoch": 1.13421035785161, "percentage": 88.59, "elapsed_time": "20:36:58", "remaining_time": "2:39:21", "throughput": 656.52, "total_tokens": 48726144} {"current_steps": 35440, "total_steps": 40000, "loss": 0.8372, "lr": 1.5869411760365826e-06, "epoch": 1.1343703988220986, "percentage": 88.6, "elapsed_time": "20:37:00", "remaining_time": "2:39:09", "throughput": 656.6, "total_tokens": 48733152} {"current_steps": 35445, "total_steps": 40000, "loss": 0.8678, "lr": 1.58350089664972e-06, "epoch": 1.1345304397925868, "percentage": 88.61, "elapsed_time": "20:37:01", "remaining_time": "2:38:58", "throughput": 656.68, "total_tokens": 48739920} {"current_steps": 35450, "total_steps": 40000, "loss": 0.6473, "lr": 1.5800642283812865e-06, "epoch": 1.1346904807630753, "percentage": 88.62, "elapsed_time": "20:37:03", "remaining_time": "2:38:46", "throughput": 656.75, "total_tokens": 48746624} {"current_steps": 35455, "total_steps": 40000, "loss": 0.8484, "lr": 1.5766311717612698e-06, "epoch": 1.1348505217335638, "percentage": 88.64, "elapsed_time": "20:37:05", "remaining_time": "2:38:34", "throughput": 656.83, "total_tokens": 48753536} {"current_steps": 35460, "total_steps": 40000, "loss": 0.6186, "lr": 1.5732017273190818e-06, "epoch": 1.1350105627040523, "percentage": 88.65, "elapsed_time": "20:37:07", "remaining_time": "2:38:23", "throughput": 656.91, "total_tokens": 48760240} {"current_steps": 35465, "total_steps": 40000, "loss": 0.609, "lr": 1.5697758955835806e-06, "epoch": 1.1351706036745406, "percentage": 88.66, "elapsed_time": "20:37:08", "remaining_time": "2:38:11", "throughput": 656.98, "total_tokens": 48767024} {"current_steps": 35470, "total_steps": 40000, "loss": 1.0493, "lr": 1.566353677083085e-06, "epoch": 1.135330644645029, "percentage": 88.67, "elapsed_time": "20:37:10", "remaining_time": "2:38:00", "throughput": 657.07, "total_tokens": 48774368} {"current_steps": 35475, "total_steps": 40000, "loss": 0.7936, "lr": 1.562935072345334e-06, "epoch": 1.1354906856155176, "percentage": 88.69, "elapsed_time": "20:37:12", "remaining_time": "2:37:48", "throughput": 657.15, "total_tokens": 48781824} {"current_steps": 35480, "total_steps": 40000, "loss": 0.7429, "lr": 1.5595200818975281e-06, "epoch": 1.135650726586006, "percentage": 88.7, "elapsed_time": "20:37:14", "remaining_time": "2:37:37", "throughput": 657.23, "total_tokens": 48788544} {"current_steps": 35485, "total_steps": 40000, "loss": 0.6657, "lr": 1.5561087062662905e-06, "epoch": 1.1358107675564946, "percentage": 88.71, "elapsed_time": "20:37:15", "remaining_time": "2:37:25", "throughput": 657.3, "total_tokens": 48795328} {"current_steps": 35490, "total_steps": 40000, "loss": 0.6007, "lr": 1.5527009459777087e-06, "epoch": 1.1359708085269828, "percentage": 88.72, "elapsed_time": "20:37:17", "remaining_time": "2:37:13", "throughput": 657.37, "total_tokens": 48801840} {"current_steps": 35495, "total_steps": 40000, "loss": 0.8156, "lr": 1.5492968015572984e-06, "epoch": 1.1361308494974713, "percentage": 88.74, "elapsed_time": "20:37:19", "remaining_time": "2:37:02", "throughput": 657.45, "total_tokens": 48808752} {"current_steps": 35500, "total_steps": 40000, "loss": 0.5218, "lr": 1.5458962735300203e-06, "epoch": 1.1362908904679598, "percentage": 88.75, "elapsed_time": "20:37:21", "remaining_time": "2:36:50", "throughput": 657.53, "total_tokens": 48815760} {"current_steps": 35505, "total_steps": 40000, "loss": 0.7577, "lr": 1.54249936242028e-06, "epoch": 1.1364509314384483, "percentage": 88.76, "elapsed_time": "20:37:22", "remaining_time": "2:36:39", "throughput": 657.61, "total_tokens": 48822880} {"current_steps": 35510, "total_steps": 40000, "loss": 0.5435, "lr": 1.5391060687519222e-06, "epoch": 1.1366109724089366, "percentage": 88.78, "elapsed_time": "20:37:24", "remaining_time": "2:36:27", "throughput": 657.68, "total_tokens": 48829536} {"current_steps": 35515, "total_steps": 40000, "loss": 0.78, "lr": 1.5357163930482367e-06, "epoch": 1.136771013379425, "percentage": 88.79, "elapsed_time": "20:37:26", "remaining_time": "2:36:16", "throughput": 657.76, "total_tokens": 48836464} {"current_steps": 35520, "total_steps": 40000, "loss": 0.6817, "lr": 1.532330335831955e-06, "epoch": 1.1369310543499136, "percentage": 88.8, "elapsed_time": "20:37:28", "remaining_time": "2:36:04", "throughput": 657.84, "total_tokens": 48843808} {"current_steps": 35525, "total_steps": 40000, "loss": 0.681, "lr": 1.5289478976252491e-06, "epoch": 1.137091095320402, "percentage": 88.81, "elapsed_time": "20:37:30", "remaining_time": "2:35:53", "throughput": 657.92, "total_tokens": 48850320} {"current_steps": 35530, "total_steps": 40000, "loss": 0.6834, "lr": 1.5255690789497345e-06, "epoch": 1.1372511362908906, "percentage": 88.83, "elapsed_time": "20:37:31", "remaining_time": "2:35:41", "throughput": 657.99, "total_tokens": 48856992} {"current_steps": 35535, "total_steps": 40000, "loss": 0.6865, "lr": 1.5221938803264641e-06, "epoch": 1.1374111772613789, "percentage": 88.84, "elapsed_time": "20:37:33", "remaining_time": "2:35:30", "throughput": 658.06, "total_tokens": 48863552} {"current_steps": 35540, "total_steps": 40000, "loss": 0.6333, "lr": 1.518822302275938e-06, "epoch": 1.1375712182318674, "percentage": 88.85, "elapsed_time": "20:37:35", "remaining_time": "2:35:18", "throughput": 658.14, "total_tokens": 48870368} {"current_steps": 35545, "total_steps": 40000, "loss": 0.7645, "lr": 1.5154543453180958e-06, "epoch": 1.1377312592023558, "percentage": 88.86, "elapsed_time": "20:37:37", "remaining_time": "2:35:06", "throughput": 658.22, "total_tokens": 48877168} {"current_steps": 35550, "total_steps": 40000, "loss": 0.717, "lr": 1.5120900099723167e-06, "epoch": 1.1378913001728443, "percentage": 88.88, "elapsed_time": "20:37:38", "remaining_time": "2:34:55", "throughput": 658.29, "total_tokens": 48883904} {"current_steps": 35555, "total_steps": 40000, "loss": 0.5473, "lr": 1.5087292967574273e-06, "epoch": 1.1380513411433326, "percentage": 88.89, "elapsed_time": "20:37:40", "remaining_time": "2:34:43", "throughput": 658.37, "total_tokens": 48890832} {"current_steps": 35560, "total_steps": 40000, "loss": 0.6381, "lr": 1.5053722061916908e-06, "epoch": 1.1382113821138211, "percentage": 88.9, "elapsed_time": "20:37:42", "remaining_time": "2:34:32", "throughput": 658.44, "total_tokens": 48897296} {"current_steps": 35565, "total_steps": 40000, "loss": 0.923, "lr": 1.5020187387928124e-06, "epoch": 1.1383714230843096, "percentage": 88.91, "elapsed_time": "20:37:44", "remaining_time": "2:34:20", "throughput": 658.51, "total_tokens": 48904096} {"current_steps": 35570, "total_steps": 40000, "loss": 0.8114, "lr": 1.4986688950779343e-06, "epoch": 1.138531464054798, "percentage": 88.92, "elapsed_time": "20:37:46", "remaining_time": "2:34:09", "throughput": 658.59, "total_tokens": 48911120} {"current_steps": 35575, "total_steps": 40000, "loss": 0.7391, "lr": 1.495322675563654e-06, "epoch": 1.1386915050252864, "percentage": 88.94, "elapsed_time": "20:37:47", "remaining_time": "2:33:57", "throughput": 658.68, "total_tokens": 48918384} {"current_steps": 35580, "total_steps": 40000, "loss": 0.7099, "lr": 1.4919800807659922e-06, "epoch": 1.1388515459957749, "percentage": 88.95, "elapsed_time": "20:37:49", "remaining_time": "2:33:46", "throughput": 658.76, "total_tokens": 48926000} {"current_steps": 35585, "total_steps": 40000, "loss": 0.7544, "lr": 1.4886411112004255e-06, "epoch": 1.1390115869662634, "percentage": 88.96, "elapsed_time": "20:37:51", "remaining_time": "2:33:34", "throughput": 658.84, "total_tokens": 48933168} {"current_steps": 35590, "total_steps": 40000, "loss": 0.7746, "lr": 1.4853057673818588e-06, "epoch": 1.1391716279367519, "percentage": 88.98, "elapsed_time": "20:37:53", "remaining_time": "2:33:23", "throughput": 658.92, "total_tokens": 48939856} {"current_steps": 35595, "total_steps": 40000, "loss": 0.6696, "lr": 1.481974049824647e-06, "epoch": 1.1393316689072401, "percentage": 88.99, "elapsed_time": "20:37:54", "remaining_time": "2:33:11", "throughput": 658.99, "total_tokens": 48946656} {"current_steps": 35600, "total_steps": 40000, "loss": 0.7164, "lr": 1.4786459590425849e-06, "epoch": 1.1394917098777286, "percentage": 89.0, "elapsed_time": "20:37:56", "remaining_time": "2:33:00", "throughput": 659.08, "total_tokens": 48954048} {"current_steps": 35600, "total_steps": 40000, "eval_loss": 0.7301948666572571, "epoch": 1.1394917098777286, "percentage": 89.0, "elapsed_time": "20:43:43", "remaining_time": "2:33:43", "throughput": 656.01, "total_tokens": 48954048} {"current_steps": 35605, "total_steps": 40000, "loss": 0.7341, "lr": 1.4753214955489036e-06, "epoch": 1.1396517508482171, "percentage": 89.01, "elapsed_time": "20:43:47", "remaining_time": "2:33:31", "throughput": 656.07, "total_tokens": 48960800} {"current_steps": 35610, "total_steps": 40000, "loss": 0.6109, "lr": 1.4720006598562737e-06, "epoch": 1.1398117918187056, "percentage": 89.03, "elapsed_time": "20:43:49", "remaining_time": "2:33:20", "throughput": 656.15, "total_tokens": 48967968} {"current_steps": 35615, "total_steps": 40000, "loss": 0.7375, "lr": 1.4686834524768185e-06, "epoch": 1.1399718327891941, "percentage": 89.04, "elapsed_time": "20:43:50", "remaining_time": "2:33:08", "throughput": 656.22, "total_tokens": 48974576} {"current_steps": 35620, "total_steps": 40000, "loss": 0.7369, "lr": 1.4653698739220844e-06, "epoch": 1.1401318737596824, "percentage": 89.05, "elapsed_time": "20:43:52", "remaining_time": "2:32:57", "throughput": 656.3, "total_tokens": 48981424} {"current_steps": 35625, "total_steps": 40000, "loss": 0.6267, "lr": 1.4620599247030715e-06, "epoch": 1.1402919147301709, "percentage": 89.06, "elapsed_time": "20:43:54", "remaining_time": "2:32:45", "throughput": 656.38, "total_tokens": 48988320} {"current_steps": 35630, "total_steps": 40000, "loss": 0.7331, "lr": 1.4587536053302125e-06, "epoch": 1.1404519557006594, "percentage": 89.08, "elapsed_time": "20:43:56", "remaining_time": "2:32:34", "throughput": 656.46, "total_tokens": 48995376} {"current_steps": 35635, "total_steps": 40000, "loss": 0.7361, "lr": 1.4554509163133862e-06, "epoch": 1.1406119966711479, "percentage": 89.09, "elapsed_time": "20:43:57", "remaining_time": "2:32:22", "throughput": 656.53, "total_tokens": 49002288} {"current_steps": 35640, "total_steps": 40000, "loss": 0.8424, "lr": 1.4521518581619098e-06, "epoch": 1.1407720376416361, "percentage": 89.1, "elapsed_time": "20:43:59", "remaining_time": "2:32:11", "throughput": 656.62, "total_tokens": 49009696} {"current_steps": 35645, "total_steps": 40000, "loss": 0.694, "lr": 1.4488564313845348e-06, "epoch": 1.1409320786121246, "percentage": 89.11, "elapsed_time": "20:44:01", "remaining_time": "2:31:59", "throughput": 656.7, "total_tokens": 49016736} {"current_steps": 35650, "total_steps": 40000, "loss": 1.0166, "lr": 1.4455646364894603e-06, "epoch": 1.1410921195826131, "percentage": 89.12, "elapsed_time": "20:44:03", "remaining_time": "2:31:47", "throughput": 656.78, "total_tokens": 49024384} {"current_steps": 35655, "total_steps": 40000, "loss": 0.6605, "lr": 1.4422764739843247e-06, "epoch": 1.1412521605531016, "percentage": 89.14, "elapsed_time": "20:44:05", "remaining_time": "2:31:36", "throughput": 656.86, "total_tokens": 49031552} {"current_steps": 35660, "total_steps": 40000, "loss": 0.6598, "lr": 1.4389919443762e-06, "epoch": 1.1414122015235901, "percentage": 89.15, "elapsed_time": "20:44:06", "remaining_time": "2:31:24", "throughput": 656.94, "total_tokens": 49038528} {"current_steps": 35665, "total_steps": 40000, "loss": 0.6234, "lr": 1.4357110481716063e-06, "epoch": 1.1415722424940784, "percentage": 89.16, "elapsed_time": "20:44:08", "remaining_time": "2:31:13", "throughput": 657.02, "total_tokens": 49045904} {"current_steps": 35670, "total_steps": 40000, "loss": 0.5138, "lr": 1.4324337858764941e-06, "epoch": 1.141732283464567, "percentage": 89.18, "elapsed_time": "20:44:10", "remaining_time": "2:31:01", "throughput": 657.1, "total_tokens": 49052800} {"current_steps": 35675, "total_steps": 40000, "loss": 0.6607, "lr": 1.4291601579962622e-06, "epoch": 1.1418923244350554, "percentage": 89.19, "elapsed_time": "20:44:12", "remaining_time": "2:30:50", "throughput": 657.18, "total_tokens": 49059712} {"current_steps": 35680, "total_steps": 40000, "loss": 0.5816, "lr": 1.42589016503574e-06, "epoch": 1.142052365405544, "percentage": 89.2, "elapsed_time": "20:44:13", "remaining_time": "2:30:38", "throughput": 657.26, "total_tokens": 49066656} {"current_steps": 35685, "total_steps": 40000, "loss": 0.7882, "lr": 1.4226238074992099e-06, "epoch": 1.1422124063760322, "percentage": 89.21, "elapsed_time": "20:44:15", "remaining_time": "2:30:27", "throughput": 657.33, "total_tokens": 49073600} {"current_steps": 35690, "total_steps": 40000, "loss": 0.7414, "lr": 1.4193610858903778e-06, "epoch": 1.1423724473465207, "percentage": 89.22, "elapsed_time": "20:44:17", "remaining_time": "2:30:15", "throughput": 657.41, "total_tokens": 49080496} {"current_steps": 35695, "total_steps": 40000, "loss": 0.7171, "lr": 1.416102000712402e-06, "epoch": 1.1425324883170092, "percentage": 89.24, "elapsed_time": "20:44:19", "remaining_time": "2:30:04", "throughput": 657.49, "total_tokens": 49087408} {"current_steps": 35700, "total_steps": 40000, "loss": 0.8868, "lr": 1.4128465524678668e-06, "epoch": 1.1426925292874976, "percentage": 89.25, "elapsed_time": "20:44:20", "remaining_time": "2:29:52", "throughput": 657.57, "total_tokens": 49094448} {"current_steps": 35705, "total_steps": 40000, "loss": 0.7892, "lr": 1.4095947416588124e-06, "epoch": 1.1428525702579861, "percentage": 89.26, "elapsed_time": "20:44:22", "remaining_time": "2:29:41", "throughput": 657.64, "total_tokens": 49100832} {"current_steps": 35710, "total_steps": 40000, "loss": 0.9365, "lr": 1.4063465687866983e-06, "epoch": 1.1430126112284744, "percentage": 89.28, "elapsed_time": "20:44:24", "remaining_time": "2:29:29", "throughput": 657.72, "total_tokens": 49108160} {"current_steps": 35715, "total_steps": 40000, "loss": 0.6749, "lr": 1.4031020343524438e-06, "epoch": 1.143172652198963, "percentage": 89.29, "elapsed_time": "20:44:26", "remaining_time": "2:29:18", "throughput": 657.79, "total_tokens": 49114864} {"current_steps": 35720, "total_steps": 40000, "loss": 0.6976, "lr": 1.3998611388563926e-06, "epoch": 1.1433326931694514, "percentage": 89.3, "elapsed_time": "20:44:28", "remaining_time": "2:29:06", "throughput": 657.87, "total_tokens": 49121808} {"current_steps": 35725, "total_steps": 40000, "loss": 0.6628, "lr": 1.3966238827983314e-06, "epoch": 1.14349273413994, "percentage": 89.31, "elapsed_time": "20:44:29", "remaining_time": "2:28:55", "throughput": 657.95, "total_tokens": 49128944} {"current_steps": 35730, "total_steps": 40000, "loss": 0.6317, "lr": 1.393390266677483e-06, "epoch": 1.1436527751104282, "percentage": 89.33, "elapsed_time": "20:44:31", "remaining_time": "2:28:43", "throughput": 658.02, "total_tokens": 49135616} {"current_steps": 35735, "total_steps": 40000, "loss": 0.7602, "lr": 1.3901602909925204e-06, "epoch": 1.1438128160809167, "percentage": 89.34, "elapsed_time": "20:44:33", "remaining_time": "2:28:32", "throughput": 658.1, "total_tokens": 49142320} {"current_steps": 35740, "total_steps": 40000, "loss": 0.7077, "lr": 1.3869339562415373e-06, "epoch": 1.1439728570514052, "percentage": 89.35, "elapsed_time": "20:44:35", "remaining_time": "2:28:20", "throughput": 658.17, "total_tokens": 49149072} {"current_steps": 35745, "total_steps": 40000, "loss": 0.6079, "lr": 1.38371126292208e-06, "epoch": 1.1441328980218937, "percentage": 89.36, "elapsed_time": "20:44:36", "remaining_time": "2:28:09", "throughput": 658.25, "total_tokens": 49156080} {"current_steps": 35750, "total_steps": 40000, "loss": 0.9535, "lr": 1.3804922115311286e-06, "epoch": 1.1442929389923822, "percentage": 89.38, "elapsed_time": "20:44:38", "remaining_time": "2:27:57", "throughput": 658.32, "total_tokens": 49162768} {"current_steps": 35755, "total_steps": 40000, "loss": 0.6783, "lr": 1.3772768025650945e-06, "epoch": 1.1444529799628704, "percentage": 89.39, "elapsed_time": "20:44:40", "remaining_time": "2:27:46", "throughput": 658.41, "total_tokens": 49170256} {"current_steps": 35760, "total_steps": 40000, "loss": 0.549, "lr": 1.3740650365198448e-06, "epoch": 1.144613020933359, "percentage": 89.4, "elapsed_time": "20:44:42", "remaining_time": "2:27:34", "throughput": 658.48, "total_tokens": 49176992} {"current_steps": 35765, "total_steps": 40000, "loss": 0.7823, "lr": 1.3708569138906612e-06, "epoch": 1.1447730619038474, "percentage": 89.41, "elapsed_time": "20:44:43", "remaining_time": "2:27:23", "throughput": 658.56, "total_tokens": 49183728} {"current_steps": 35770, "total_steps": 40000, "loss": 0.5934, "lr": 1.367652435172287e-06, "epoch": 1.144933102874336, "percentage": 89.42, "elapsed_time": "20:44:45", "remaining_time": "2:27:12", "throughput": 658.63, "total_tokens": 49190448} {"current_steps": 35775, "total_steps": 40000, "loss": 0.7716, "lr": 1.364451600858893e-06, "epoch": 1.1450931438448242, "percentage": 89.44, "elapsed_time": "20:44:47", "remaining_time": "2:27:00", "throughput": 658.71, "total_tokens": 49197536} {"current_steps": 35780, "total_steps": 40000, "loss": 0.6325, "lr": 1.3612544114440823e-06, "epoch": 1.1452531848153127, "percentage": 89.45, "elapsed_time": "20:44:49", "remaining_time": "2:26:49", "throughput": 658.79, "total_tokens": 49204720} {"current_steps": 35785, "total_steps": 40000, "loss": 0.4865, "lr": 1.3580608674209072e-06, "epoch": 1.1454132257858012, "percentage": 89.46, "elapsed_time": "20:44:51", "remaining_time": "2:26:37", "throughput": 658.87, "total_tokens": 49211680} {"current_steps": 35790, "total_steps": 40000, "loss": 0.7123, "lr": 1.3548709692818434e-06, "epoch": 1.1455732667562897, "percentage": 89.48, "elapsed_time": "20:44:52", "remaining_time": "2:26:26", "throughput": 658.95, "total_tokens": 49218976} {"current_steps": 35795, "total_steps": 40000, "loss": 0.6144, "lr": 1.3516847175188223e-06, "epoch": 1.1457333077267782, "percentage": 89.49, "elapsed_time": "20:44:54", "remaining_time": "2:26:14", "throughput": 659.03, "total_tokens": 49225984} {"current_steps": 35800, "total_steps": 40000, "loss": 0.6525, "lr": 1.348502112623204e-06, "epoch": 1.1458933486972664, "percentage": 89.5, "elapsed_time": "20:44:56", "remaining_time": "2:26:03", "throughput": 659.1, "total_tokens": 49232480} {"current_steps": 35800, "total_steps": 40000, "eval_loss": 0.7302478551864624, "epoch": 1.1458933486972664, "percentage": 89.5, "elapsed_time": "20:50:44", "remaining_time": "2:26:44", "throughput": 656.04, "total_tokens": 49232480} {"current_steps": 35805, "total_steps": 40000, "loss": 0.7067, "lr": 1.3453231550857787e-06, "epoch": 1.146053389667755, "percentage": 89.51, "elapsed_time": "20:50:48", "remaining_time": "2:26:32", "throughput": 656.1, "total_tokens": 49239376} {"current_steps": 35810, "total_steps": 40000, "loss": 1.0059, "lr": 1.3421478453967878e-06, "epoch": 1.1462134306382434, "percentage": 89.53, "elapsed_time": "20:50:49", "remaining_time": "2:26:21", "throughput": 656.18, "total_tokens": 49246352} {"current_steps": 35815, "total_steps": 40000, "loss": 0.5883, "lr": 1.3389761840459065e-06, "epoch": 1.146373471608732, "percentage": 89.54, "elapsed_time": "20:50:51", "remaining_time": "2:26:09", "throughput": 656.25, "total_tokens": 49252768} {"current_steps": 35820, "total_steps": 40000, "loss": 0.6794, "lr": 1.3358081715222376e-06, "epoch": 1.1465335125792202, "percentage": 89.55, "elapsed_time": "20:50:53", "remaining_time": "2:25:58", "throughput": 656.33, "total_tokens": 49259472} {"current_steps": 35825, "total_steps": 40000, "loss": 0.7376, "lr": 1.3326438083143295e-06, "epoch": 1.1466935535497087, "percentage": 89.56, "elapsed_time": "20:50:55", "remaining_time": "2:25:46", "throughput": 656.4, "total_tokens": 49266176} {"current_steps": 35830, "total_steps": 40000, "loss": 0.7547, "lr": 1.3294830949101723e-06, "epoch": 1.1468535945201972, "percentage": 89.58, "elapsed_time": "20:50:56", "remaining_time": "2:25:35", "throughput": 656.47, "total_tokens": 49272864} {"current_steps": 35835, "total_steps": 40000, "loss": 0.6384, "lr": 1.3263260317971815e-06, "epoch": 1.1470136354906857, "percentage": 89.59, "elapsed_time": "20:50:58", "remaining_time": "2:25:23", "throughput": 656.55, "total_tokens": 49279680} {"current_steps": 35840, "total_steps": 40000, "loss": 0.775, "lr": 1.3231726194622208e-06, "epoch": 1.1471736764611742, "percentage": 89.6, "elapsed_time": "20:51:00", "remaining_time": "2:25:12", "throughput": 656.63, "total_tokens": 49286576} {"current_steps": 35845, "total_steps": 40000, "loss": 0.7675, "lr": 1.3200228583915814e-06, "epoch": 1.1473337174316625, "percentage": 89.61, "elapsed_time": "20:51:02", "remaining_time": "2:25:00", "throughput": 656.7, "total_tokens": 49293376} {"current_steps": 35850, "total_steps": 40000, "loss": 0.7586, "lr": 1.3168767490709971e-06, "epoch": 1.147493758402151, "percentage": 89.62, "elapsed_time": "20:51:03", "remaining_time": "2:24:49", "throughput": 656.78, "total_tokens": 49300032} {"current_steps": 35855, "total_steps": 40000, "loss": 0.6443, "lr": 1.3137342919856437e-06, "epoch": 1.1476537993726394, "percentage": 89.64, "elapsed_time": "20:51:05", "remaining_time": "2:24:37", "throughput": 656.85, "total_tokens": 49306848} {"current_steps": 35860, "total_steps": 40000, "loss": 0.8142, "lr": 1.310595487620117e-06, "epoch": 1.1478138403431277, "percentage": 89.65, "elapsed_time": "20:51:07", "remaining_time": "2:24:26", "throughput": 656.93, "total_tokens": 49313760} {"current_steps": 35865, "total_steps": 40000, "loss": 0.7311, "lr": 1.3074603364584715e-06, "epoch": 1.1479738813136162, "percentage": 89.66, "elapsed_time": "20:51:08", "remaining_time": "2:24:14", "throughput": 657.01, "total_tokens": 49320960} {"current_steps": 35870, "total_steps": 40000, "loss": 0.6186, "lr": 1.3043288389841758e-06, "epoch": 1.1481339222841047, "percentage": 89.68, "elapsed_time": "20:51:10", "remaining_time": "2:24:03", "throughput": 657.08, "total_tokens": 49327664} {"current_steps": 35875, "total_steps": 40000, "loss": 0.8127, "lr": 1.3012009956801546e-06, "epoch": 1.1482939632545932, "percentage": 89.69, "elapsed_time": "20:51:12", "remaining_time": "2:23:52", "throughput": 657.16, "total_tokens": 49334576} {"current_steps": 35880, "total_steps": 40000, "loss": 0.9066, "lr": 1.2980768070287586e-06, "epoch": 1.1484540042250817, "percentage": 89.7, "elapsed_time": "20:51:14", "remaining_time": "2:23:40", "throughput": 657.24, "total_tokens": 49341552} {"current_steps": 35885, "total_steps": 40000, "loss": 0.4987, "lr": 1.2949562735117716e-06, "epoch": 1.14861404519557, "percentage": 89.71, "elapsed_time": "20:51:15", "remaining_time": "2:23:29", "throughput": 657.31, "total_tokens": 49348176} {"current_steps": 35890, "total_steps": 40000, "loss": 0.7618, "lr": 1.291839395610428e-06, "epoch": 1.1487740861660585, "percentage": 89.72, "elapsed_time": "20:51:17", "remaining_time": "2:23:17", "throughput": 657.39, "total_tokens": 49354944} {"current_steps": 35895, "total_steps": 40000, "loss": 0.7557, "lr": 1.2887261738053852e-06, "epoch": 1.148934127136547, "percentage": 89.74, "elapsed_time": "20:51:19", "remaining_time": "2:23:06", "throughput": 657.46, "total_tokens": 49361744} {"current_steps": 35900, "total_steps": 40000, "loss": 0.7119, "lr": 1.2856166085767396e-06, "epoch": 1.1490941681070355, "percentage": 89.75, "elapsed_time": "20:51:21", "remaining_time": "2:22:54", "throughput": 657.54, "total_tokens": 49368768} {"current_steps": 35905, "total_steps": 40000, "loss": 0.7022, "lr": 1.2825107004040272e-06, "epoch": 1.1492542090775237, "percentage": 89.76, "elapsed_time": "20:51:22", "remaining_time": "2:22:43", "throughput": 657.62, "total_tokens": 49375856} {"current_steps": 35910, "total_steps": 40000, "loss": 0.6188, "lr": 1.2794084497662146e-06, "epoch": 1.1494142500480122, "percentage": 89.78, "elapsed_time": "20:51:24", "remaining_time": "2:22:31", "throughput": 657.7, "total_tokens": 49382816} {"current_steps": 35915, "total_steps": 40000, "loss": 0.5605, "lr": 1.276309857141711e-06, "epoch": 1.1495742910185007, "percentage": 89.79, "elapsed_time": "20:51:26", "remaining_time": "2:22:20", "throughput": 657.77, "total_tokens": 49389808} {"current_steps": 35920, "total_steps": 40000, "loss": 0.68, "lr": 1.273214923008359e-06, "epoch": 1.1497343319889892, "percentage": 89.8, "elapsed_time": "20:51:28", "remaining_time": "2:22:08", "throughput": 657.85, "total_tokens": 49396496} {"current_steps": 35925, "total_steps": 40000, "loss": 1.0491, "lr": 1.2701236478434352e-06, "epoch": 1.1498943729594777, "percentage": 89.81, "elapsed_time": "20:51:29", "remaining_time": "2:21:57", "throughput": 657.92, "total_tokens": 49403152} {"current_steps": 35930, "total_steps": 40000, "loss": 0.6505, "lr": 1.2670360321236502e-06, "epoch": 1.150054413929966, "percentage": 89.83, "elapsed_time": "20:51:31", "remaining_time": "2:21:46", "throughput": 657.99, "total_tokens": 49409728} {"current_steps": 35935, "total_steps": 40000, "loss": 0.6497, "lr": 1.2639520763251617e-06, "epoch": 1.1502144549004545, "percentage": 89.84, "elapsed_time": "20:51:33", "remaining_time": "2:21:34", "throughput": 658.07, "total_tokens": 49416704} {"current_steps": 35940, "total_steps": 40000, "loss": 0.5775, "lr": 1.2608717809235448e-06, "epoch": 1.150374495870943, "percentage": 89.85, "elapsed_time": "20:51:35", "remaining_time": "2:21:23", "throughput": 658.14, "total_tokens": 49423344} {"current_steps": 35945, "total_steps": 40000, "loss": 0.6353, "lr": 1.2577951463938282e-06, "epoch": 1.1505345368414315, "percentage": 89.86, "elapsed_time": "20:51:36", "remaining_time": "2:21:11", "throughput": 658.22, "total_tokens": 49429920} {"current_steps": 35950, "total_steps": 40000, "loss": 0.6565, "lr": 1.2547221732104569e-06, "epoch": 1.1506945778119197, "percentage": 89.88, "elapsed_time": "20:51:38", "remaining_time": "2:21:00", "throughput": 658.29, "total_tokens": 49436512} {"current_steps": 35955, "total_steps": 40000, "loss": 0.6067, "lr": 1.25165286184733e-06, "epoch": 1.1508546187824082, "percentage": 89.89, "elapsed_time": "20:51:40", "remaining_time": "2:20:48", "throughput": 658.37, "total_tokens": 49443376} {"current_steps": 35960, "total_steps": 40000, "loss": 0.7068, "lr": 1.248587212777777e-06, "epoch": 1.1510146597528967, "percentage": 89.9, "elapsed_time": "20:51:41", "remaining_time": "2:20:37", "throughput": 658.44, "total_tokens": 49450160} {"current_steps": 35965, "total_steps": 40000, "loss": 0.703, "lr": 1.2455252264745532e-06, "epoch": 1.1511747007233852, "percentage": 89.91, "elapsed_time": "20:51:43", "remaining_time": "2:20:26", "throughput": 658.52, "total_tokens": 49457088} {"current_steps": 35970, "total_steps": 40000, "loss": 0.621, "lr": 1.2424669034098528e-06, "epoch": 1.1513347416938737, "percentage": 89.92, "elapsed_time": "20:51:45", "remaining_time": "2:20:14", "throughput": 658.59, "total_tokens": 49463856} {"current_steps": 35975, "total_steps": 40000, "loss": 0.5472, "lr": 1.2394122440553185e-06, "epoch": 1.151494782664362, "percentage": 89.94, "elapsed_time": "20:51:47", "remaining_time": "2:20:03", "throughput": 658.67, "total_tokens": 49470544} {"current_steps": 35980, "total_steps": 40000, "loss": 0.7442, "lr": 1.2363612488820037e-06, "epoch": 1.1516548236348505, "percentage": 89.95, "elapsed_time": "20:51:48", "remaining_time": "2:19:51", "throughput": 658.74, "total_tokens": 49477392} {"current_steps": 35985, "total_steps": 40000, "loss": 0.5944, "lr": 1.2333139183604208e-06, "epoch": 1.151814864605339, "percentage": 89.96, "elapsed_time": "20:51:50", "remaining_time": "2:19:40", "throughput": 658.82, "total_tokens": 49484240} {"current_steps": 35990, "total_steps": 40000, "loss": 0.8063, "lr": 1.2302702529604998e-06, "epoch": 1.1519749055758275, "percentage": 89.98, "elapsed_time": "20:51:52", "remaining_time": "2:19:29", "throughput": 658.9, "total_tokens": 49491360} {"current_steps": 35995, "total_steps": 40000, "loss": 0.6724, "lr": 1.227230253151615e-06, "epoch": 1.1521349465463158, "percentage": 89.99, "elapsed_time": "20:51:54", "remaining_time": "2:19:17", "throughput": 658.98, "total_tokens": 49498432} {"current_steps": 36000, "total_steps": 40000, "loss": 0.7326, "lr": 1.2241939194025748e-06, "epoch": 1.1522949875168043, "percentage": 90.0, "elapsed_time": "20:51:55", "remaining_time": "2:19:06", "throughput": 659.05, "total_tokens": 49505040} {"current_steps": 36000, "total_steps": 40000, "eval_loss": 0.7302849888801575, "epoch": 1.1522949875168043, "percentage": 90.0, "elapsed_time": "20:57:43", "remaining_time": "2:19:44", "throughput": 656.01, "total_tokens": 49505040} {"current_steps": 36005, "total_steps": 40000, "loss": 0.6258, "lr": 1.2211612521816156e-06, "epoch": 1.1524550284872928, "percentage": 90.01, "elapsed_time": "20:57:46", "remaining_time": "2:19:33", "throughput": 656.07, "total_tokens": 49511744} {"current_steps": 36010, "total_steps": 40000, "loss": 0.7979, "lr": 1.2181322519564137e-06, "epoch": 1.1526150694577812, "percentage": 90.03, "elapsed_time": "20:57:48", "remaining_time": "2:19:22", "throughput": 656.15, "total_tokens": 49518832} {"current_steps": 36015, "total_steps": 40000, "loss": 0.6207, "lr": 1.2151069191940839e-06, "epoch": 1.1527751104282697, "percentage": 90.04, "elapsed_time": "20:57:50", "remaining_time": "2:19:10", "throughput": 656.24, "total_tokens": 49526416} {"current_steps": 36020, "total_steps": 40000, "loss": 0.7067, "lr": 1.2120852543611644e-06, "epoch": 1.152935151398758, "percentage": 90.05, "elapsed_time": "20:57:52", "remaining_time": "2:18:59", "throughput": 656.31, "total_tokens": 49533152} {"current_steps": 36025, "total_steps": 40000, "loss": 0.6185, "lr": 1.2090672579236379e-06, "epoch": 1.1530951923692465, "percentage": 90.06, "elapsed_time": "20:57:53", "remaining_time": "2:18:47", "throughput": 656.38, "total_tokens": 49539808} {"current_steps": 36030, "total_steps": 40000, "loss": 0.8309, "lr": 1.2060529303469126e-06, "epoch": 1.153255233339735, "percentage": 90.08, "elapsed_time": "20:57:55", "remaining_time": "2:18:36", "throughput": 656.46, "total_tokens": 49546496} {"current_steps": 36035, "total_steps": 40000, "loss": 0.7163, "lr": 1.2030422720958445e-06, "epoch": 1.1534152743102235, "percentage": 90.09, "elapsed_time": "20:57:57", "remaining_time": "2:18:24", "throughput": 656.53, "total_tokens": 49553440} {"current_steps": 36040, "total_steps": 40000, "loss": 0.8079, "lr": 1.200035283634704e-06, "epoch": 1.1535753152807118, "percentage": 90.1, "elapsed_time": "20:57:59", "remaining_time": "2:18:13", "throughput": 656.61, "total_tokens": 49560416} {"current_steps": 36045, "total_steps": 40000, "loss": 0.6662, "lr": 1.1970319654272144e-06, "epoch": 1.1537353562512003, "percentage": 90.11, "elapsed_time": "20:58:00", "remaining_time": "2:18:02", "throughput": 656.68, "total_tokens": 49566992} {"current_steps": 36050, "total_steps": 40000, "loss": 0.688, "lr": 1.1940323179365192e-06, "epoch": 1.1538953972216888, "percentage": 90.12, "elapsed_time": "20:58:02", "remaining_time": "2:17:50", "throughput": 656.77, "total_tokens": 49574448} {"current_steps": 36055, "total_steps": 40000, "loss": 0.7324, "lr": 1.1910363416252095e-06, "epoch": 1.1540554381921773, "percentage": 90.14, "elapsed_time": "20:58:04", "remaining_time": "2:17:39", "throughput": 656.84, "total_tokens": 49581040} {"current_steps": 36060, "total_steps": 40000, "loss": 0.5637, "lr": 1.1880440369552964e-06, "epoch": 1.1542154791626658, "percentage": 90.15, "elapsed_time": "20:58:05", "remaining_time": "2:17:27", "throughput": 656.92, "total_tokens": 49587904} {"current_steps": 36065, "total_steps": 40000, "loss": 0.8396, "lr": 1.1850554043882328e-06, "epoch": 1.154375520133154, "percentage": 90.16, "elapsed_time": "20:58:07", "remaining_time": "2:17:16", "throughput": 656.99, "total_tokens": 49594912} {"current_steps": 36070, "total_steps": 40000, "loss": 0.805, "lr": 1.1820704443849028e-06, "epoch": 1.1545355611036425, "percentage": 90.18, "elapsed_time": "20:58:09", "remaining_time": "2:17:04", "throughput": 657.07, "total_tokens": 49602096} {"current_steps": 36075, "total_steps": 40000, "loss": 0.7127, "lr": 1.1790891574056219e-06, "epoch": 1.154695602074131, "percentage": 90.19, "elapsed_time": "20:58:11", "remaining_time": "2:16:53", "throughput": 657.14, "total_tokens": 49608624} {"current_steps": 36080, "total_steps": 40000, "loss": 0.7787, "lr": 1.1761115439101523e-06, "epoch": 1.1548556430446195, "percentage": 90.2, "elapsed_time": "20:58:12", "remaining_time": "2:16:42", "throughput": 657.22, "total_tokens": 49615104} {"current_steps": 36085, "total_steps": 40000, "loss": 0.8942, "lr": 1.1731376043576659e-06, "epoch": 1.1550156840151078, "percentage": 90.21, "elapsed_time": "20:58:14", "remaining_time": "2:16:30", "throughput": 657.29, "total_tokens": 49621664} {"current_steps": 36090, "total_steps": 40000, "loss": 0.6939, "lr": 1.1701673392067875e-06, "epoch": 1.1551757249855963, "percentage": 90.22, "elapsed_time": "20:58:16", "remaining_time": "2:16:19", "throughput": 657.36, "total_tokens": 49628544} {"current_steps": 36095, "total_steps": 40000, "loss": 0.7685, "lr": 1.1672007489155757e-06, "epoch": 1.1553357659560848, "percentage": 90.24, "elapsed_time": "20:58:18", "remaining_time": "2:16:07", "throughput": 657.44, "total_tokens": 49635296} {"current_steps": 36100, "total_steps": 40000, "loss": 0.6672, "lr": 1.164237833941506e-06, "epoch": 1.1554958069265733, "percentage": 90.25, "elapsed_time": "20:58:19", "remaining_time": "2:15:56", "throughput": 657.51, "total_tokens": 49642048} {"current_steps": 36105, "total_steps": 40000, "loss": 0.709, "lr": 1.1612785947415022e-06, "epoch": 1.1556558478970618, "percentage": 90.26, "elapsed_time": "20:58:21", "remaining_time": "2:15:45", "throughput": 657.58, "total_tokens": 49648688} {"current_steps": 36110, "total_steps": 40000, "loss": 0.8373, "lr": 1.1583230317719185e-06, "epoch": 1.15581588886755, "percentage": 90.28, "elapsed_time": "20:58:23", "remaining_time": "2:15:33", "throughput": 657.66, "total_tokens": 49655440} {"current_steps": 36115, "total_steps": 40000, "loss": 0.8125, "lr": 1.1553711454885318e-06, "epoch": 1.1559759298380385, "percentage": 90.29, "elapsed_time": "20:58:25", "remaining_time": "2:15:22", "throughput": 657.74, "total_tokens": 49662336} {"current_steps": 36120, "total_steps": 40000, "loss": 0.7299, "lr": 1.152422936346567e-06, "epoch": 1.156135970808527, "percentage": 90.3, "elapsed_time": "20:58:26", "remaining_time": "2:15:10", "throughput": 657.81, "total_tokens": 49668976} {"current_steps": 36125, "total_steps": 40000, "loss": 0.5382, "lr": 1.1494784048006718e-06, "epoch": 1.1562960117790153, "percentage": 90.31, "elapsed_time": "20:58:28", "remaining_time": "2:14:59", "throughput": 657.88, "total_tokens": 49675616} {"current_steps": 36130, "total_steps": 40000, "loss": 0.9006, "lr": 1.1465375513049326e-06, "epoch": 1.1564560527495038, "percentage": 90.33, "elapsed_time": "20:58:30", "remaining_time": "2:14:48", "throughput": 657.96, "total_tokens": 49682400} {"current_steps": 36135, "total_steps": 40000, "loss": 0.7368, "lr": 1.1436003763128616e-06, "epoch": 1.1566160937199923, "percentage": 90.34, "elapsed_time": "20:58:32", "remaining_time": "2:14:36", "throughput": 658.03, "total_tokens": 49689104} {"current_steps": 36140, "total_steps": 40000, "loss": 0.7613, "lr": 1.1406668802774106e-06, "epoch": 1.1567761346904808, "percentage": 90.35, "elapsed_time": "20:58:33", "remaining_time": "2:14:25", "throughput": 658.1, "total_tokens": 49695936} {"current_steps": 36145, "total_steps": 40000, "loss": 0.7496, "lr": 1.137737063650965e-06, "epoch": 1.1569361756609693, "percentage": 90.36, "elapsed_time": "20:58:35", "remaining_time": "2:14:14", "throughput": 658.19, "total_tokens": 49703232} {"current_steps": 36150, "total_steps": 40000, "loss": 0.7181, "lr": 1.1348109268853323e-06, "epoch": 1.1570962166314576, "percentage": 90.38, "elapsed_time": "20:58:37", "remaining_time": "2:14:02", "throughput": 658.26, "total_tokens": 49710304} {"current_steps": 36155, "total_steps": 40000, "loss": 0.6229, "lr": 1.1318884704317634e-06, "epoch": 1.157256257601946, "percentage": 90.39, "elapsed_time": "20:58:38", "remaining_time": "2:13:51", "throughput": 658.34, "total_tokens": 49717120} {"current_steps": 36160, "total_steps": 40000, "loss": 0.8795, "lr": 1.1289696947409417e-06, "epoch": 1.1574162985724346, "percentage": 90.4, "elapsed_time": "20:58:40", "remaining_time": "2:13:39", "throughput": 658.42, "total_tokens": 49724016} {"current_steps": 36165, "total_steps": 40000, "loss": 0.6801, "lr": 1.126054600262974e-06, "epoch": 1.157576339542923, "percentage": 90.41, "elapsed_time": "20:58:42", "remaining_time": "2:13:28", "throughput": 658.49, "total_tokens": 49730976} {"current_steps": 36170, "total_steps": 40000, "loss": 0.6852, "lr": 1.1231431874474064e-06, "epoch": 1.1577363805134113, "percentage": 90.42, "elapsed_time": "20:58:44", "remaining_time": "2:13:17", "throughput": 658.56, "total_tokens": 49737568} {"current_steps": 36175, "total_steps": 40000, "loss": 0.7255, "lr": 1.12023545674321e-06, "epoch": 1.1578964214838998, "percentage": 90.44, "elapsed_time": "20:58:45", "remaining_time": "2:13:05", "throughput": 658.64, "total_tokens": 49744464} {"current_steps": 36180, "total_steps": 40000, "loss": 0.5615, "lr": 1.117331408598804e-06, "epoch": 1.1580564624543883, "percentage": 90.45, "elapsed_time": "20:58:47", "remaining_time": "2:12:54", "throughput": 658.71, "total_tokens": 49751056} {"current_steps": 36185, "total_steps": 40000, "loss": 0.5499, "lr": 1.1144310434620191e-06, "epoch": 1.1582165034248768, "percentage": 90.46, "elapsed_time": "20:58:49", "remaining_time": "2:12:43", "throughput": 658.79, "total_tokens": 49757920} {"current_steps": 36190, "total_steps": 40000, "loss": 0.6755, "lr": 1.1115343617801365e-06, "epoch": 1.1583765443953653, "percentage": 90.48, "elapsed_time": "20:58:51", "remaining_time": "2:12:31", "throughput": 658.87, "total_tokens": 49765056} {"current_steps": 36195, "total_steps": 40000, "loss": 0.7471, "lr": 1.1086413639998515e-06, "epoch": 1.1585365853658536, "percentage": 90.49, "elapsed_time": "20:58:52", "remaining_time": "2:12:20", "throughput": 658.94, "total_tokens": 49771888} {"current_steps": 36200, "total_steps": 40000, "loss": 0.6382, "lr": 1.1057520505673103e-06, "epoch": 1.158696626336342, "percentage": 90.5, "elapsed_time": "20:58:54", "remaining_time": "2:12:09", "throughput": 659.02, "total_tokens": 49778864} {"current_steps": 36200, "total_steps": 40000, "eval_loss": 0.7303056120872498, "epoch": 1.158696626336342, "percentage": 90.5, "elapsed_time": "21:04:43", "remaining_time": "2:12:45", "throughput": 655.99, "total_tokens": 49778864} {"current_steps": 36205, "total_steps": 40000, "loss": 0.8984, "lr": 1.1028664219280727e-06, "epoch": 1.1588566673068306, "percentage": 90.51, "elapsed_time": "21:04:46", "remaining_time": "2:12:34", "throughput": 656.06, "total_tokens": 49786304} {"current_steps": 36210, "total_steps": 40000, "loss": 0.753, "lr": 1.0999844785271468e-06, "epoch": 1.159016708277319, "percentage": 90.53, "elapsed_time": "21:04:48", "remaining_time": "2:12:23", "throughput": 656.14, "total_tokens": 49793056} {"current_steps": 36215, "total_steps": 40000, "loss": 0.7296, "lr": 1.097106220808955e-06, "epoch": 1.1591767492478073, "percentage": 90.54, "elapsed_time": "21:04:49", "remaining_time": "2:12:11", "throughput": 656.21, "total_tokens": 49799504} {"current_steps": 36220, "total_steps": 40000, "loss": 0.8393, "lr": 1.0942316492173698e-06, "epoch": 1.1593367902182958, "percentage": 90.55, "elapsed_time": "21:04:51", "remaining_time": "2:12:00", "throughput": 656.28, "total_tokens": 49806320} {"current_steps": 36225, "total_steps": 40000, "loss": 0.7061, "lr": 1.0913607641956841e-06, "epoch": 1.1594968311887843, "percentage": 90.56, "elapsed_time": "21:04:53", "remaining_time": "2:11:48", "throughput": 656.36, "total_tokens": 49813328} {"current_steps": 36230, "total_steps": 40000, "loss": 0.6168, "lr": 1.0884935661866213e-06, "epoch": 1.1596568721592728, "percentage": 90.58, "elapsed_time": "21:04:55", "remaining_time": "2:11:37", "throughput": 656.43, "total_tokens": 49819888} {"current_steps": 36235, "total_steps": 40000, "loss": 0.7525, "lr": 1.0856300556323418e-06, "epoch": 1.1598169131297613, "percentage": 90.59, "elapsed_time": "21:04:56", "remaining_time": "2:11:26", "throughput": 656.5, "total_tokens": 49826352} {"current_steps": 36240, "total_steps": 40000, "loss": 0.6889, "lr": 1.0827702329744365e-06, "epoch": 1.1599769541002496, "percentage": 90.6, "elapsed_time": "21:04:58", "remaining_time": "2:11:14", "throughput": 656.58, "total_tokens": 49833168} {"current_steps": 36245, "total_steps": 40000, "loss": 0.7792, "lr": 1.0799140986539197e-06, "epoch": 1.160136995070738, "percentage": 90.61, "elapsed_time": "21:05:00", "remaining_time": "2:11:03", "throughput": 656.65, "total_tokens": 49840176} {"current_steps": 36250, "total_steps": 40000, "loss": 0.5502, "lr": 1.0770616531112526e-06, "epoch": 1.1602970360412266, "percentage": 90.62, "elapsed_time": "21:05:02", "remaining_time": "2:10:51", "throughput": 656.73, "total_tokens": 49846816} {"current_steps": 36255, "total_steps": 40000, "loss": 0.701, "lr": 1.0742128967863085e-06, "epoch": 1.160457077011715, "percentage": 90.64, "elapsed_time": "21:05:03", "remaining_time": "2:10:40", "throughput": 656.8, "total_tokens": 49853872} {"current_steps": 36260, "total_steps": 40000, "loss": 0.5381, "lr": 1.071367830118411e-06, "epoch": 1.1606171179822034, "percentage": 90.65, "elapsed_time": "21:05:05", "remaining_time": "2:10:29", "throughput": 656.89, "total_tokens": 49861264} {"current_steps": 36265, "total_steps": 40000, "loss": 0.669, "lr": 1.068526453546298e-06, "epoch": 1.1607771589526918, "percentage": 90.66, "elapsed_time": "21:05:07", "remaining_time": "2:10:17", "throughput": 656.96, "total_tokens": 49868032} {"current_steps": 36270, "total_steps": 40000, "loss": 0.726, "lr": 1.0656887675081467e-06, "epoch": 1.1609371999231803, "percentage": 90.67, "elapsed_time": "21:05:09", "remaining_time": "2:10:06", "throughput": 657.04, "total_tokens": 49875296} {"current_steps": 36275, "total_steps": 40000, "loss": 0.7452, "lr": 1.0628547724415628e-06, "epoch": 1.1610972408936688, "percentage": 90.69, "elapsed_time": "21:05:10", "remaining_time": "2:09:55", "throughput": 657.11, "total_tokens": 49881936} {"current_steps": 36280, "total_steps": 40000, "loss": 0.6825, "lr": 1.0600244687835881e-06, "epoch": 1.1612572818641573, "percentage": 90.7, "elapsed_time": "21:05:12", "remaining_time": "2:09:43", "throughput": 657.19, "total_tokens": 49888704} {"current_steps": 36285, "total_steps": 40000, "loss": 0.6323, "lr": 1.0571978569706876e-06, "epoch": 1.1614173228346456, "percentage": 90.71, "elapsed_time": "21:05:14", "remaining_time": "2:09:32", "throughput": 657.27, "total_tokens": 49895984} {"current_steps": 36290, "total_steps": 40000, "loss": 0.61, "lr": 1.0543749374387652e-06, "epoch": 1.161577363805134, "percentage": 90.72, "elapsed_time": "21:05:15", "remaining_time": "2:09:21", "throughput": 657.34, "total_tokens": 49902784} {"current_steps": 36295, "total_steps": 40000, "loss": 0.6355, "lr": 1.051555710623142e-06, "epoch": 1.1617374047756226, "percentage": 90.74, "elapsed_time": "21:05:17", "remaining_time": "2:09:09", "throughput": 657.42, "total_tokens": 49909936} {"current_steps": 36300, "total_steps": 40000, "loss": 0.6554, "lr": 1.0487401769585847e-06, "epoch": 1.161897445746111, "percentage": 90.75, "elapsed_time": "21:05:19", "remaining_time": "2:08:58", "throughput": 657.5, "total_tokens": 49917024} {"current_steps": 36305, "total_steps": 40000, "loss": 0.7145, "lr": 1.0459283368792845e-06, "epoch": 1.1620574867165994, "percentage": 90.76, "elapsed_time": "21:05:21", "remaining_time": "2:08:47", "throughput": 657.57, "total_tokens": 49923664} {"current_steps": 36310, "total_steps": 40000, "loss": 0.6533, "lr": 1.043120190818858e-06, "epoch": 1.1622175276870879, "percentage": 90.77, "elapsed_time": "21:05:22", "remaining_time": "2:08:35", "throughput": 657.65, "total_tokens": 49930528} {"current_steps": 36315, "total_steps": 40000, "loss": 0.6776, "lr": 1.0403157392103596e-06, "epoch": 1.1623775686575764, "percentage": 90.79, "elapsed_time": "21:05:24", "remaining_time": "2:08:24", "throughput": 657.72, "total_tokens": 49937376} {"current_steps": 36320, "total_steps": 40000, "loss": 0.8462, "lr": 1.0375149824862735e-06, "epoch": 1.1625376096280648, "percentage": 90.8, "elapsed_time": "21:05:26", "remaining_time": "2:08:12", "throughput": 657.8, "total_tokens": 49944416} {"current_steps": 36325, "total_steps": 40000, "loss": 0.793, "lr": 1.034717921078507e-06, "epoch": 1.1626976505985533, "percentage": 90.81, "elapsed_time": "21:05:28", "remaining_time": "2:08:01", "throughput": 657.88, "total_tokens": 49951392} {"current_steps": 36330, "total_steps": 40000, "loss": 0.7024, "lr": 1.0319245554184009e-06, "epoch": 1.1628576915690416, "percentage": 90.83, "elapsed_time": "21:05:29", "remaining_time": "2:07:50", "throughput": 657.95, "total_tokens": 49958080} {"current_steps": 36335, "total_steps": 40000, "loss": 0.7588, "lr": 1.0291348859367361e-06, "epoch": 1.1630177325395301, "percentage": 90.84, "elapsed_time": "21:05:31", "remaining_time": "2:07:39", "throughput": 658.02, "total_tokens": 49964640} {"current_steps": 36340, "total_steps": 40000, "loss": 0.8193, "lr": 1.0263489130637016e-06, "epoch": 1.1631777735100186, "percentage": 90.85, "elapsed_time": "21:05:33", "remaining_time": "2:07:27", "throughput": 658.09, "total_tokens": 49971376} {"current_steps": 36345, "total_steps": 40000, "loss": 0.8044, "lr": 1.0235666372289427e-06, "epoch": 1.163337814480507, "percentage": 90.86, "elapsed_time": "21:05:35", "remaining_time": "2:07:16", "throughput": 658.17, "total_tokens": 49978096} {"current_steps": 36350, "total_steps": 40000, "loss": 0.6336, "lr": 1.0207880588615076e-06, "epoch": 1.1634978554509954, "percentage": 90.88, "elapsed_time": "21:05:37", "remaining_time": "2:07:05", "throughput": 658.24, "total_tokens": 49984944} {"current_steps": 36355, "total_steps": 40000, "loss": 0.669, "lr": 1.0180131783898984e-06, "epoch": 1.1636578964214839, "percentage": 90.89, "elapsed_time": "21:05:38", "remaining_time": "2:06:53", "throughput": 658.32, "total_tokens": 49991856} {"current_steps": 36360, "total_steps": 40000, "loss": 0.8242, "lr": 1.0152419962420362e-06, "epoch": 1.1638179373919724, "percentage": 90.9, "elapsed_time": "21:05:40", "remaining_time": "2:06:42", "throughput": 658.39, "total_tokens": 49998368} {"current_steps": 36365, "total_steps": 40000, "loss": 0.7386, "lr": 1.0124745128452685e-06, "epoch": 1.1639779783624609, "percentage": 90.91, "elapsed_time": "21:05:42", "remaining_time": "2:06:31", "throughput": 658.46, "total_tokens": 50005024} {"current_steps": 36370, "total_steps": 40000, "loss": 0.6891, "lr": 1.0097107286263758e-06, "epoch": 1.1641380193329494, "percentage": 90.92, "elapsed_time": "21:05:44", "remaining_time": "2:06:19", "throughput": 658.53, "total_tokens": 50011232} {"current_steps": 36375, "total_steps": 40000, "loss": 0.7718, "lr": 1.00695064401157e-06, "epoch": 1.1642980603034376, "percentage": 90.94, "elapsed_time": "21:05:45", "remaining_time": "2:06:08", "throughput": 658.6, "total_tokens": 50017872} {"current_steps": 36380, "total_steps": 40000, "loss": 0.811, "lr": 1.0041942594264886e-06, "epoch": 1.1644581012739261, "percentage": 90.95, "elapsed_time": "21:05:47", "remaining_time": "2:05:57", "throughput": 658.67, "total_tokens": 50024832} {"current_steps": 36385, "total_steps": 40000, "loss": 0.719, "lr": 1.001441575296208e-06, "epoch": 1.1646181422444146, "percentage": 90.96, "elapsed_time": "21:05:49", "remaining_time": "2:05:45", "throughput": 658.75, "total_tokens": 50031760} {"current_steps": 36390, "total_steps": 40000, "loss": 0.6356, "lr": 9.986925920452139e-07, "epoch": 1.164778183214903, "percentage": 90.97, "elapsed_time": "21:05:51", "remaining_time": "2:05:34", "throughput": 658.83, "total_tokens": 50038608} {"current_steps": 36395, "total_steps": 40000, "loss": 0.8324, "lr": 9.959473100974475e-07, "epoch": 1.1649382241853914, "percentage": 90.99, "elapsed_time": "21:05:53", "remaining_time": "2:05:23", "throughput": 658.9, "total_tokens": 50045072} {"current_steps": 36400, "total_steps": 40000, "loss": 0.7743, "lr": 9.932057298762564e-07, "epoch": 1.1650982651558799, "percentage": 91.0, "elapsed_time": "21:05:54", "remaining_time": "2:05:12", "throughput": 658.97, "total_tokens": 50051632} {"current_steps": 36400, "total_steps": 40000, "eval_loss": 0.7298858761787415, "epoch": 1.1650982651558799, "percentage": 91.0, "elapsed_time": "21:11:42", "remaining_time": "2:05:46", "throughput": 655.96, "total_tokens": 50051632} {"current_steps": 36405, "total_steps": 40000, "loss": 0.7303, "lr": 9.90467851804433e-07, "epoch": 1.1652583061263684, "percentage": 91.01, "elapsed_time": "21:11:46", "remaining_time": "2:05:35", "throughput": 656.02, "total_tokens": 50058496} {"current_steps": 36410, "total_steps": 40000, "loss": 0.6932, "lr": 9.877336763041895e-07, "epoch": 1.1654183470968569, "percentage": 91.03, "elapsed_time": "21:11:47", "remaining_time": "2:05:23", "throughput": 656.1, "total_tokens": 50065280} {"current_steps": 36415, "total_steps": 40000, "loss": 0.6553, "lr": 9.850032037971662e-07, "epoch": 1.1655783880673452, "percentage": 91.04, "elapsed_time": "21:11:49", "remaining_time": "2:05:12", "throughput": 656.17, "total_tokens": 50072144} {"current_steps": 36420, "total_steps": 40000, "loss": 0.8002, "lr": 9.822764347044406e-07, "epoch": 1.1657384290378336, "percentage": 91.05, "elapsed_time": "21:11:51", "remaining_time": "2:05:01", "throughput": 656.24, "total_tokens": 50078880} {"current_steps": 36425, "total_steps": 40000, "loss": 0.7027, "lr": 9.795533694465175e-07, "epoch": 1.1658984700083221, "percentage": 91.06, "elapsed_time": "21:11:53", "remaining_time": "2:04:49", "throughput": 656.32, "total_tokens": 50086080} {"current_steps": 36430, "total_steps": 40000, "loss": 0.8023, "lr": 9.768340084433197e-07, "epoch": 1.1660585109788106, "percentage": 91.07, "elapsed_time": "21:11:54", "remaining_time": "2:04:38", "throughput": 656.4, "total_tokens": 50092736} {"current_steps": 36435, "total_steps": 40000, "loss": 0.7892, "lr": 9.741183521142143e-07, "epoch": 1.166218551949299, "percentage": 91.09, "elapsed_time": "21:11:56", "remaining_time": "2:04:27", "throughput": 656.47, "total_tokens": 50099536} {"current_steps": 36440, "total_steps": 40000, "loss": 0.7632, "lr": 9.714064008779889e-07, "epoch": 1.1663785929197874, "percentage": 91.1, "elapsed_time": "21:11:58", "remaining_time": "2:04:15", "throughput": 656.55, "total_tokens": 50106752} {"current_steps": 36445, "total_steps": 40000, "loss": 0.7129, "lr": 9.686981551528584e-07, "epoch": 1.166538633890276, "percentage": 91.11, "elapsed_time": "21:12:00", "remaining_time": "2:04:04", "throughput": 656.62, "total_tokens": 50113536} {"current_steps": 36450, "total_steps": 40000, "loss": 0.5183, "lr": 9.65993615356467e-07, "epoch": 1.1666986748607644, "percentage": 91.12, "elapsed_time": "21:12:02", "remaining_time": "2:03:53", "throughput": 656.7, "total_tokens": 50120576} {"current_steps": 36455, "total_steps": 40000, "loss": 0.8582, "lr": 9.632927819058917e-07, "epoch": 1.166858715831253, "percentage": 91.14, "elapsed_time": "21:12:03", "remaining_time": "2:03:41", "throughput": 656.77, "total_tokens": 50127520} {"current_steps": 36460, "total_steps": 40000, "loss": 0.6681, "lr": 9.605956552176305e-07, "epoch": 1.1670187568017412, "percentage": 91.15, "elapsed_time": "21:12:05", "remaining_time": "2:03:30", "throughput": 656.85, "total_tokens": 50134160} {"current_steps": 36465, "total_steps": 40000, "loss": 0.8455, "lr": 9.579022357076223e-07, "epoch": 1.1671787977722297, "percentage": 91.16, "elapsed_time": "21:12:07", "remaining_time": "2:03:19", "throughput": 656.92, "total_tokens": 50140864} {"current_steps": 36470, "total_steps": 40000, "loss": 0.6172, "lr": 9.552125237912158e-07, "epoch": 1.1673388387427182, "percentage": 91.17, "elapsed_time": "21:12:09", "remaining_time": "2:03:08", "throughput": 656.99, "total_tokens": 50147808} {"current_steps": 36475, "total_steps": 40000, "loss": 0.6545, "lr": 9.525265198832096e-07, "epoch": 1.1674988797132066, "percentage": 91.19, "elapsed_time": "21:12:10", "remaining_time": "2:02:56", "throughput": 657.07, "total_tokens": 50154832} {"current_steps": 36480, "total_steps": 40000, "loss": 0.6544, "lr": 9.498442243978112e-07, "epoch": 1.167658920683695, "percentage": 91.2, "elapsed_time": "21:12:12", "remaining_time": "2:02:45", "throughput": 657.15, "total_tokens": 50161712} {"current_steps": 36485, "total_steps": 40000, "loss": 0.5813, "lr": 9.471656377486649e-07, "epoch": 1.1678189616541834, "percentage": 91.21, "elapsed_time": "21:12:14", "remaining_time": "2:02:34", "throughput": 657.22, "total_tokens": 50168176} {"current_steps": 36490, "total_steps": 40000, "loss": 0.8442, "lr": 9.444907603488456e-07, "epoch": 1.167979002624672, "percentage": 91.22, "elapsed_time": "21:12:16", "remaining_time": "2:02:22", "throughput": 657.29, "total_tokens": 50174992} {"current_steps": 36495, "total_steps": 40000, "loss": 0.5352, "lr": 9.418195926108514e-07, "epoch": 1.1681390435951604, "percentage": 91.24, "elapsed_time": "21:12:17", "remaining_time": "2:02:11", "throughput": 657.36, "total_tokens": 50181520} {"current_steps": 36500, "total_steps": 40000, "loss": 0.6721, "lr": 9.391521349466053e-07, "epoch": 1.168299084565649, "percentage": 91.25, "elapsed_time": "21:12:19", "remaining_time": "2:02:00", "throughput": 657.44, "total_tokens": 50188608} {"current_steps": 36505, "total_steps": 40000, "loss": 0.6643, "lr": 9.364883877674758e-07, "epoch": 1.1684591255361372, "percentage": 91.26, "elapsed_time": "21:12:21", "remaining_time": "2:01:48", "throughput": 657.52, "total_tokens": 50195696} {"current_steps": 36510, "total_steps": 40000, "loss": 0.7582, "lr": 9.33828351484231e-07, "epoch": 1.1686191665066257, "percentage": 91.27, "elapsed_time": "21:12:23", "remaining_time": "2:01:37", "throughput": 657.59, "total_tokens": 50202816} {"current_steps": 36515, "total_steps": 40000, "loss": 0.7619, "lr": 9.311720265070906e-07, "epoch": 1.1687792074771142, "percentage": 91.29, "elapsed_time": "21:12:25", "remaining_time": "2:01:26", "throughput": 657.67, "total_tokens": 50209856} {"current_steps": 36520, "total_steps": 40000, "loss": 0.6336, "lr": 9.285194132456931e-07, "epoch": 1.1689392484476027, "percentage": 91.3, "elapsed_time": "21:12:26", "remaining_time": "2:01:15", "throughput": 657.74, "total_tokens": 50216496} {"current_steps": 36525, "total_steps": 40000, "loss": 0.6866, "lr": 9.258705121091032e-07, "epoch": 1.169099289418091, "percentage": 91.31, "elapsed_time": "21:12:28", "remaining_time": "2:01:03", "throughput": 657.81, "total_tokens": 50223088} {"current_steps": 36530, "total_steps": 40000, "loss": 0.773, "lr": 9.232253235058136e-07, "epoch": 1.1692593303885794, "percentage": 91.33, "elapsed_time": "21:12:30", "remaining_time": "2:00:52", "throughput": 657.88, "total_tokens": 50229632} {"current_steps": 36535, "total_steps": 40000, "loss": 0.7648, "lr": 9.205838478437478e-07, "epoch": 1.169419371359068, "percentage": 91.34, "elapsed_time": "21:12:32", "remaining_time": "2:00:41", "throughput": 657.96, "total_tokens": 50236832} {"current_steps": 36540, "total_steps": 40000, "loss": 0.7508, "lr": 9.179460855302524e-07, "epoch": 1.1695794123295564, "percentage": 91.35, "elapsed_time": "21:12:33", "remaining_time": "2:00:30", "throughput": 658.04, "total_tokens": 50243552} {"current_steps": 36545, "total_steps": 40000, "loss": 0.665, "lr": 9.153120369721046e-07, "epoch": 1.169739453300045, "percentage": 91.36, "elapsed_time": "21:12:35", "remaining_time": "2:00:18", "throughput": 658.11, "total_tokens": 50250496} {"current_steps": 36550, "total_steps": 40000, "loss": 0.6016, "lr": 9.126817025755103e-07, "epoch": 1.1698994942705332, "percentage": 91.38, "elapsed_time": "21:12:37", "remaining_time": "2:00:07", "throughput": 658.18, "total_tokens": 50256976} {"current_steps": 36555, "total_steps": 40000, "loss": 0.7056, "lr": 9.100550827460947e-07, "epoch": 1.1700595352410217, "percentage": 91.39, "elapsed_time": "21:12:39", "remaining_time": "1:59:56", "throughput": 658.25, "total_tokens": 50263680} {"current_steps": 36560, "total_steps": 40000, "loss": 0.7029, "lr": 9.0743217788892e-07, "epoch": 1.1702195762115102, "percentage": 91.4, "elapsed_time": "21:12:40", "remaining_time": "1:59:44", "throughput": 658.33, "total_tokens": 50270656} {"current_steps": 36565, "total_steps": 40000, "loss": 0.6326, "lr": 9.048129884084683e-07, "epoch": 1.1703796171819987, "percentage": 91.41, "elapsed_time": "21:12:42", "remaining_time": "1:59:33", "throughput": 658.4, "total_tokens": 50277520} {"current_steps": 36570, "total_steps": 40000, "loss": 0.7163, "lr": 9.021975147086553e-07, "epoch": 1.170539658152487, "percentage": 91.42, "elapsed_time": "21:12:44", "remaining_time": "1:59:22", "throughput": 658.48, "total_tokens": 50284496} {"current_steps": 36575, "total_steps": 40000, "loss": 0.7311, "lr": 8.995857571928141e-07, "epoch": 1.1706996991229754, "percentage": 91.44, "elapsed_time": "21:12:46", "remaining_time": "1:59:11", "throughput": 658.56, "total_tokens": 50291568} {"current_steps": 36580, "total_steps": 40000, "loss": 0.7257, "lr": 8.969777162637139e-07, "epoch": 1.170859740093464, "percentage": 91.45, "elapsed_time": "21:12:48", "remaining_time": "1:58:59", "throughput": 658.63, "total_tokens": 50298176} {"current_steps": 36585, "total_steps": 40000, "loss": 0.5855, "lr": 8.943733923235525e-07, "epoch": 1.1710197810639524, "percentage": 91.46, "elapsed_time": "21:12:49", "remaining_time": "1:58:48", "throughput": 658.71, "total_tokens": 50305328} {"current_steps": 36590, "total_steps": 40000, "loss": 0.5201, "lr": 8.917727857739394e-07, "epoch": 1.171179822034441, "percentage": 91.47, "elapsed_time": "21:12:51", "remaining_time": "1:58:37", "throughput": 658.78, "total_tokens": 50312048} {"current_steps": 36595, "total_steps": 40000, "loss": 0.5703, "lr": 8.891758970159258e-07, "epoch": 1.1713398630049292, "percentage": 91.49, "elapsed_time": "21:12:53", "remaining_time": "1:58:26", "throughput": 658.85, "total_tokens": 50318816} {"current_steps": 36600, "total_steps": 40000, "loss": 0.5618, "lr": 8.86582726449986e-07, "epoch": 1.1714999039754177, "percentage": 91.5, "elapsed_time": "21:12:55", "remaining_time": "1:58:14", "throughput": 658.93, "total_tokens": 50325888} {"current_steps": 36600, "total_steps": 40000, "eval_loss": 0.7302461862564087, "epoch": 1.1714999039754177, "percentage": 91.5, "elapsed_time": "21:18:44", "remaining_time": "1:58:47", "throughput": 655.93, "total_tokens": 50325888} {"current_steps": 36605, "total_steps": 40000, "loss": 0.8003, "lr": 8.839932744760165e-07, "epoch": 1.1716599449459062, "percentage": 91.51, "elapsed_time": "21:18:47", "remaining_time": "1:58:36", "throughput": 655.99, "total_tokens": 50332880} {"current_steps": 36610, "total_steps": 40000, "loss": 0.6987, "lr": 8.814075414933482e-07, "epoch": 1.1718199859163947, "percentage": 91.53, "elapsed_time": "21:18:49", "remaining_time": "1:58:24", "throughput": 656.07, "total_tokens": 50339744} {"current_steps": 36615, "total_steps": 40000, "loss": 0.6188, "lr": 8.788255279007257e-07, "epoch": 1.171980026886883, "percentage": 91.54, "elapsed_time": "21:18:51", "remaining_time": "1:58:13", "throughput": 656.14, "total_tokens": 50346592} {"current_steps": 36620, "total_steps": 40000, "loss": 0.5984, "lr": 8.762472340963362e-07, "epoch": 1.1721400678573715, "percentage": 91.55, "elapsed_time": "21:18:53", "remaining_time": "1:58:02", "throughput": 656.21, "total_tokens": 50353280} {"current_steps": 36625, "total_steps": 40000, "loss": 0.7855, "lr": 8.736726604777811e-07, "epoch": 1.17230010882786, "percentage": 91.56, "elapsed_time": "21:18:54", "remaining_time": "1:57:51", "throughput": 656.28, "total_tokens": 50359792} {"current_steps": 36630, "total_steps": 40000, "loss": 0.8761, "lr": 8.711018074420901e-07, "epoch": 1.1724601497983484, "percentage": 91.57, "elapsed_time": "21:18:56", "remaining_time": "1:57:39", "throughput": 656.36, "total_tokens": 50366512} {"current_steps": 36635, "total_steps": 40000, "loss": 0.7544, "lr": 8.685346753857209e-07, "epoch": 1.172620190768837, "percentage": 91.59, "elapsed_time": "21:18:58", "remaining_time": "1:57:28", "throughput": 656.43, "total_tokens": 50373456} {"current_steps": 36640, "total_steps": 40000, "loss": 0.6583, "lr": 8.659712647045654e-07, "epoch": 1.1727802317393252, "percentage": 91.6, "elapsed_time": "21:19:00", "remaining_time": "1:57:17", "throughput": 656.51, "total_tokens": 50380304} {"current_steps": 36645, "total_steps": 40000, "loss": 0.7881, "lr": 8.634115757939209e-07, "epoch": 1.1729402727098137, "percentage": 91.61, "elapsed_time": "21:19:01", "remaining_time": "1:57:06", "throughput": 656.58, "total_tokens": 50387200} {"current_steps": 36650, "total_steps": 40000, "loss": 0.6902, "lr": 8.608556090485387e-07, "epoch": 1.1731003136803022, "percentage": 91.62, "elapsed_time": "21:19:03", "remaining_time": "1:56:54", "throughput": 656.65, "total_tokens": 50393984} {"current_steps": 36655, "total_steps": 40000, "loss": 0.8917, "lr": 8.583033648625671e-07, "epoch": 1.1732603546507905, "percentage": 91.64, "elapsed_time": "21:19:05", "remaining_time": "1:56:43", "throughput": 656.73, "total_tokens": 50401024} {"current_steps": 36660, "total_steps": 40000, "loss": 1.0218, "lr": 8.557548436295998e-07, "epoch": 1.173420395621279, "percentage": 91.65, "elapsed_time": "21:19:07", "remaining_time": "1:56:32", "throughput": 656.8, "total_tokens": 50407600} {"current_steps": 36665, "total_steps": 40000, "loss": 0.6499, "lr": 8.532100457426556e-07, "epoch": 1.1735804365917675, "percentage": 91.66, "elapsed_time": "21:19:08", "remaining_time": "1:56:20", "throughput": 656.88, "total_tokens": 50414592} {"current_steps": 36670, "total_steps": 40000, "loss": 0.6641, "lr": 8.506689715941679e-07, "epoch": 1.173740477562256, "percentage": 91.67, "elapsed_time": "21:19:10", "remaining_time": "1:56:09", "throughput": 656.95, "total_tokens": 50421376} {"current_steps": 36675, "total_steps": 40000, "loss": 0.599, "lr": 8.481316215760011e-07, "epoch": 1.1739005185327445, "percentage": 91.69, "elapsed_time": "21:19:12", "remaining_time": "1:55:58", "throughput": 657.02, "total_tokens": 50428000} {"current_steps": 36680, "total_steps": 40000, "loss": 0.7229, "lr": 8.455979960794558e-07, "epoch": 1.1740605595032327, "percentage": 91.7, "elapsed_time": "21:19:14", "remaining_time": "1:55:47", "throughput": 657.09, "total_tokens": 50434784} {"current_steps": 36685, "total_steps": 40000, "loss": 0.6569, "lr": 8.430680954952364e-07, "epoch": 1.1742206004737212, "percentage": 91.71, "elapsed_time": "21:19:16", "remaining_time": "1:55:35", "throughput": 657.17, "total_tokens": 50441408} {"current_steps": 36690, "total_steps": 40000, "loss": 0.6724, "lr": 8.405419202134974e-07, "epoch": 1.1743806414442097, "percentage": 91.72, "elapsed_time": "21:19:17", "remaining_time": "1:55:24", "throughput": 657.24, "total_tokens": 50448608} {"current_steps": 36695, "total_steps": 40000, "loss": 0.7467, "lr": 8.380194706237993e-07, "epoch": 1.1745406824146982, "percentage": 91.74, "elapsed_time": "21:19:19", "remaining_time": "1:55:13", "throughput": 657.32, "total_tokens": 50455280} {"current_steps": 36700, "total_steps": 40000, "loss": 0.9104, "lr": 8.355007471151366e-07, "epoch": 1.1747007233851865, "percentage": 91.75, "elapsed_time": "21:19:21", "remaining_time": "1:55:02", "throughput": 657.39, "total_tokens": 50461920} {"current_steps": 36705, "total_steps": 40000, "loss": 0.6073, "lr": 8.329857500759292e-07, "epoch": 1.174860764355675, "percentage": 91.76, "elapsed_time": "21:19:23", "remaining_time": "1:54:51", "throughput": 657.46, "total_tokens": 50468352} {"current_steps": 36710, "total_steps": 40000, "loss": 0.6893, "lr": 8.304744798940194e-07, "epoch": 1.1750208053261635, "percentage": 91.77, "elapsed_time": "21:19:24", "remaining_time": "1:54:39", "throughput": 657.53, "total_tokens": 50475584} {"current_steps": 36715, "total_steps": 40000, "loss": 0.5683, "lr": 8.279669369566756e-07, "epoch": 1.175180846296652, "percentage": 91.79, "elapsed_time": "21:19:26", "remaining_time": "1:54:28", "throughput": 657.61, "total_tokens": 50482320} {"current_steps": 36720, "total_steps": 40000, "loss": 0.6209, "lr": 8.254631216505993e-07, "epoch": 1.1753408872671405, "percentage": 91.8, "elapsed_time": "21:19:28", "remaining_time": "1:54:17", "throughput": 657.69, "total_tokens": 50489568} {"current_steps": 36725, "total_steps": 40000, "loss": 0.7614, "lr": 8.229630343619038e-07, "epoch": 1.1755009282376288, "percentage": 91.81, "elapsed_time": "21:19:30", "remaining_time": "1:54:06", "throughput": 657.76, "total_tokens": 50496368} {"current_steps": 36730, "total_steps": 40000, "loss": 0.6781, "lr": 8.204666754761392e-07, "epoch": 1.1756609692081172, "percentage": 91.83, "elapsed_time": "21:19:32", "remaining_time": "1:53:54", "throughput": 657.84, "total_tokens": 50503632} {"current_steps": 36735, "total_steps": 40000, "loss": 0.7894, "lr": 8.179740453782669e-07, "epoch": 1.1758210101786057, "percentage": 91.84, "elapsed_time": "21:19:33", "remaining_time": "1:53:43", "throughput": 657.92, "total_tokens": 50510656} {"current_steps": 36740, "total_steps": 40000, "loss": 0.6079, "lr": 8.154851444526907e-07, "epoch": 1.1759810511490942, "percentage": 91.85, "elapsed_time": "21:19:35", "remaining_time": "1:53:32", "throughput": 657.99, "total_tokens": 50517568} {"current_steps": 36745, "total_steps": 40000, "loss": 0.5175, "lr": 8.129999730832283e-07, "epoch": 1.1761410921195825, "percentage": 91.86, "elapsed_time": "21:19:37", "remaining_time": "1:53:21", "throughput": 658.07, "total_tokens": 50525008} {"current_steps": 36750, "total_steps": 40000, "loss": 0.704, "lr": 8.105185316531178e-07, "epoch": 1.176301133090071, "percentage": 91.88, "elapsed_time": "21:19:39", "remaining_time": "1:53:09", "throughput": 658.15, "total_tokens": 50531952} {"current_steps": 36755, "total_steps": 40000, "loss": 0.6852, "lr": 8.08040820545039e-07, "epoch": 1.1764611740605595, "percentage": 91.89, "elapsed_time": "21:19:40", "remaining_time": "1:52:58", "throughput": 658.22, "total_tokens": 50538832} {"current_steps": 36760, "total_steps": 40000, "loss": 0.7536, "lr": 8.055668401410782e-07, "epoch": 1.176621215031048, "percentage": 91.9, "elapsed_time": "21:19:42", "remaining_time": "1:52:47", "throughput": 658.3, "total_tokens": 50545648} {"current_steps": 36765, "total_steps": 40000, "loss": 0.7026, "lr": 8.030965908227578e-07, "epoch": 1.1767812560015365, "percentage": 91.91, "elapsed_time": "21:19:44", "remaining_time": "1:52:36", "throughput": 658.37, "total_tokens": 50552800} {"current_steps": 36770, "total_steps": 40000, "loss": 0.8546, "lr": 8.006300729710203e-07, "epoch": 1.1769412969720248, "percentage": 91.92, "elapsed_time": "21:19:46", "remaining_time": "1:52:25", "throughput": 658.45, "total_tokens": 50560000} {"current_steps": 36775, "total_steps": 40000, "loss": 0.6601, "lr": 7.981672869662337e-07, "epoch": 1.1771013379425133, "percentage": 91.94, "elapsed_time": "21:19:47", "remaining_time": "1:52:13", "throughput": 658.53, "total_tokens": 50566992} {"current_steps": 36780, "total_steps": 40000, "loss": 0.6589, "lr": 7.957082331881888e-07, "epoch": 1.1772613789130018, "percentage": 91.95, "elapsed_time": "21:19:49", "remaining_time": "1:52:02", "throughput": 658.6, "total_tokens": 50573904} {"current_steps": 36785, "total_steps": 40000, "loss": 0.8028, "lr": 7.932529120161069e-07, "epoch": 1.1774214198834903, "percentage": 91.96, "elapsed_time": "21:19:51", "remaining_time": "1:51:51", "throughput": 658.67, "total_tokens": 50580528} {"current_steps": 36790, "total_steps": 40000, "loss": 0.6959, "lr": 7.908013238286243e-07, "epoch": 1.1775814608539785, "percentage": 91.97, "elapsed_time": "21:19:53", "remaining_time": "1:51:40", "throughput": 658.74, "total_tokens": 50587136} {"current_steps": 36795, "total_steps": 40000, "loss": 0.8103, "lr": 7.883534690038136e-07, "epoch": 1.177741501824467, "percentage": 91.99, "elapsed_time": "21:19:55", "remaining_time": "1:51:29", "throughput": 658.82, "total_tokens": 50594160} {"current_steps": 36800, "total_steps": 40000, "loss": 0.5741, "lr": 7.859093479191559e-07, "epoch": 1.1779015427949555, "percentage": 92.0, "elapsed_time": "21:19:56", "remaining_time": "1:51:17", "throughput": 658.9, "total_tokens": 50601136} {"current_steps": 36800, "total_steps": 40000, "eval_loss": 0.7303029298782349, "epoch": 1.1779015427949555, "percentage": 92.0, "elapsed_time": "21:25:45", "remaining_time": "1:51:48", "throughput": 655.92, "total_tokens": 50601136} {"current_steps": 36805, "total_steps": 40000, "loss": 0.8164, "lr": 7.834689609515722e-07, "epoch": 1.178061583765444, "percentage": 92.01, "elapsed_time": "21:25:49", "remaining_time": "1:51:37", "throughput": 655.97, "total_tokens": 50607632} {"current_steps": 36810, "total_steps": 40000, "loss": 0.8319, "lr": 7.810323084774002e-07, "epoch": 1.1782216247359325, "percentage": 92.03, "elapsed_time": "21:25:51", "remaining_time": "1:51:26", "throughput": 656.04, "total_tokens": 50614480} {"current_steps": 36815, "total_steps": 40000, "loss": 1.0246, "lr": 7.785993908723976e-07, "epoch": 1.1783816657064208, "percentage": 92.04, "elapsed_time": "21:25:53", "remaining_time": "1:51:14", "throughput": 656.12, "total_tokens": 50621504} {"current_steps": 36820, "total_steps": 40000, "loss": 0.7009, "lr": 7.761702085117534e-07, "epoch": 1.1785417066769093, "percentage": 92.05, "elapsed_time": "21:25:55", "remaining_time": "1:51:03", "throughput": 656.2, "total_tokens": 50628896} {"current_steps": 36825, "total_steps": 40000, "loss": 0.8054, "lr": 7.737447617700844e-07, "epoch": 1.1787017476473978, "percentage": 92.06, "elapsed_time": "21:25:56", "remaining_time": "1:50:52", "throughput": 656.26, "total_tokens": 50635168} {"current_steps": 36830, "total_steps": 40000, "loss": 0.663, "lr": 7.713230510214136e-07, "epoch": 1.1788617886178863, "percentage": 92.07, "elapsed_time": "21:25:58", "remaining_time": "1:50:41", "throughput": 656.34, "total_tokens": 50641888} {"current_steps": 36835, "total_steps": 40000, "loss": 0.5695, "lr": 7.689050766392092e-07, "epoch": 1.1790218295883745, "percentage": 92.09, "elapsed_time": "21:26:00", "remaining_time": "1:50:29", "throughput": 656.41, "total_tokens": 50648544} {"current_steps": 36840, "total_steps": 40000, "loss": 0.9408, "lr": 7.664908389963477e-07, "epoch": 1.179181870558863, "percentage": 92.1, "elapsed_time": "21:26:02", "remaining_time": "1:50:18", "throughput": 656.48, "total_tokens": 50655120} {"current_steps": 36845, "total_steps": 40000, "loss": 0.7246, "lr": 7.64080338465134e-07, "epoch": 1.1793419115293515, "percentage": 92.11, "elapsed_time": "21:26:03", "remaining_time": "1:50:07", "throughput": 656.56, "total_tokens": 50662576} {"current_steps": 36850, "total_steps": 40000, "loss": 0.7847, "lr": 7.616735754173043e-07, "epoch": 1.17950195249984, "percentage": 92.12, "elapsed_time": "21:26:05", "remaining_time": "1:49:56", "throughput": 656.64, "total_tokens": 50669904} {"current_steps": 36855, "total_steps": 40000, "loss": 0.5869, "lr": 7.592705502240005e-07, "epoch": 1.1796619934703285, "percentage": 92.14, "elapsed_time": "21:26:07", "remaining_time": "1:49:45", "throughput": 656.71, "total_tokens": 50676896} {"current_steps": 36860, "total_steps": 40000, "loss": 0.6459, "lr": 7.568712632558095e-07, "epoch": 1.1798220344408168, "percentage": 92.15, "elapsed_time": "21:26:09", "remaining_time": "1:49:33", "throughput": 656.79, "total_tokens": 50683984} {"current_steps": 36865, "total_steps": 40000, "loss": 0.6515, "lr": 7.544757148827297e-07, "epoch": 1.1799820754113053, "percentage": 92.16, "elapsed_time": "21:26:11", "remaining_time": "1:49:22", "throughput": 656.86, "total_tokens": 50690896} {"current_steps": 36870, "total_steps": 40000, "loss": 0.7609, "lr": 7.520839054741797e-07, "epoch": 1.1801421163817938, "percentage": 92.17, "elapsed_time": "21:26:12", "remaining_time": "1:49:11", "throughput": 656.94, "total_tokens": 50697744} {"current_steps": 36875, "total_steps": 40000, "loss": 0.8288, "lr": 7.496958353990113e-07, "epoch": 1.1803021573522823, "percentage": 92.19, "elapsed_time": "21:26:14", "remaining_time": "1:49:00", "throughput": 657.01, "total_tokens": 50704432} {"current_steps": 36880, "total_steps": 40000, "loss": 0.6817, "lr": 7.473115050254941e-07, "epoch": 1.1804621983227706, "percentage": 92.2, "elapsed_time": "21:26:16", "remaining_time": "1:48:49", "throughput": 657.08, "total_tokens": 50711296} {"current_steps": 36885, "total_steps": 40000, "loss": 0.6926, "lr": 7.449309147213173e-07, "epoch": 1.180622239293259, "percentage": 92.21, "elapsed_time": "21:26:18", "remaining_time": "1:48:37", "throughput": 657.16, "total_tokens": 50718208} {"current_steps": 36890, "total_steps": 40000, "loss": 0.8068, "lr": 7.425540648536067e-07, "epoch": 1.1807822802637475, "percentage": 92.22, "elapsed_time": "21:26:19", "remaining_time": "1:48:26", "throughput": 657.23, "total_tokens": 50724944} {"current_steps": 36895, "total_steps": 40000, "loss": 0.561, "lr": 7.40180955788894e-07, "epoch": 1.180942321234236, "percentage": 92.24, "elapsed_time": "21:26:21", "remaining_time": "1:48:15", "throughput": 657.3, "total_tokens": 50731680} {"current_steps": 36900, "total_steps": 40000, "loss": 0.6781, "lr": 7.378115878931474e-07, "epoch": 1.1811023622047245, "percentage": 92.25, "elapsed_time": "21:26:23", "remaining_time": "1:48:04", "throughput": 657.37, "total_tokens": 50738432} {"current_steps": 36905, "total_steps": 40000, "loss": 0.6095, "lr": 7.354459615317527e-07, "epoch": 1.1812624031752128, "percentage": 92.26, "elapsed_time": "21:26:25", "remaining_time": "1:47:53", "throughput": 657.44, "total_tokens": 50744800} {"current_steps": 36910, "total_steps": 40000, "loss": 0.6448, "lr": 7.33084077069518e-07, "epoch": 1.1814224441457013, "percentage": 92.27, "elapsed_time": "21:26:26", "remaining_time": "1:47:41", "throughput": 657.52, "total_tokens": 50751856} {"current_steps": 36915, "total_steps": 40000, "loss": 0.9755, "lr": 7.307259348706768e-07, "epoch": 1.1815824851161898, "percentage": 92.29, "elapsed_time": "21:26:28", "remaining_time": "1:47:30", "throughput": 657.6, "total_tokens": 50759168} {"current_steps": 36920, "total_steps": 40000, "loss": 0.654, "lr": 7.283715352988801e-07, "epoch": 1.181742526086678, "percentage": 92.3, "elapsed_time": "21:26:30", "remaining_time": "1:47:19", "throughput": 657.68, "total_tokens": 50766816} {"current_steps": 36925, "total_steps": 40000, "loss": 0.7819, "lr": 7.260208787172068e-07, "epoch": 1.1819025670571666, "percentage": 92.31, "elapsed_time": "21:26:32", "remaining_time": "1:47:08", "throughput": 657.76, "total_tokens": 50773664} {"current_steps": 36930, "total_steps": 40000, "loss": 0.8106, "lr": 7.23673965488167e-07, "epoch": 1.182062608027655, "percentage": 92.33, "elapsed_time": "21:26:34", "remaining_time": "1:46:57", "throughput": 657.83, "total_tokens": 50780752} {"current_steps": 36935, "total_steps": 40000, "loss": 0.8146, "lr": 7.213307959736709e-07, "epoch": 1.1822226489981436, "percentage": 92.34, "elapsed_time": "21:26:35", "remaining_time": "1:46:45", "throughput": 657.9, "total_tokens": 50787216} {"current_steps": 36940, "total_steps": 40000, "loss": 0.6823, "lr": 7.189913705350715e-07, "epoch": 1.182382689968632, "percentage": 92.35, "elapsed_time": "21:26:37", "remaining_time": "1:46:34", "throughput": 657.97, "total_tokens": 50794048} {"current_steps": 36945, "total_steps": 40000, "loss": 0.84, "lr": 7.166556895331411e-07, "epoch": 1.1825427309391203, "percentage": 92.36, "elapsed_time": "21:26:39", "remaining_time": "1:46:23", "throughput": 658.05, "total_tokens": 50801120} {"current_steps": 36950, "total_steps": 40000, "loss": 0.761, "lr": 7.143237533280639e-07, "epoch": 1.1827027719096088, "percentage": 92.38, "elapsed_time": "21:26:41", "remaining_time": "1:46:12", "throughput": 658.12, "total_tokens": 50807936} {"current_steps": 36955, "total_steps": 40000, "loss": 0.6213, "lr": 7.119955622794578e-07, "epoch": 1.1828628128800973, "percentage": 92.39, "elapsed_time": "21:26:42", "remaining_time": "1:46:01", "throughput": 658.19, "total_tokens": 50814528} {"current_steps": 36960, "total_steps": 40000, "loss": 0.5903, "lr": 7.096711167463577e-07, "epoch": 1.1830228538505858, "percentage": 92.4, "elapsed_time": "21:26:44", "remaining_time": "1:45:50", "throughput": 658.27, "total_tokens": 50821472} {"current_steps": 36965, "total_steps": 40000, "loss": 0.7528, "lr": 7.073504170872213e-07, "epoch": 1.183182894821074, "percentage": 92.41, "elapsed_time": "21:26:46", "remaining_time": "1:45:39", "throughput": 658.35, "total_tokens": 50828560} {"current_steps": 36970, "total_steps": 40000, "loss": 0.7069, "lr": 7.05033463659932e-07, "epoch": 1.1833429357915626, "percentage": 92.42, "elapsed_time": "21:26:48", "remaining_time": "1:45:27", "throughput": 658.42, "total_tokens": 50835232} {"current_steps": 36975, "total_steps": 40000, "loss": 0.7054, "lr": 7.027202568217928e-07, "epoch": 1.183502976762051, "percentage": 92.44, "elapsed_time": "21:26:50", "remaining_time": "1:45:16", "throughput": 658.49, "total_tokens": 50842112} {"current_steps": 36980, "total_steps": 40000, "loss": 0.7185, "lr": 7.004107969295293e-07, "epoch": 1.1836630177325396, "percentage": 92.45, "elapsed_time": "21:26:51", "remaining_time": "1:45:05", "throughput": 658.56, "total_tokens": 50848960} {"current_steps": 36985, "total_steps": 40000, "loss": 0.5575, "lr": 6.9810508433929e-07, "epoch": 1.183823058703028, "percentage": 92.46, "elapsed_time": "21:26:53", "remaining_time": "1:44:54", "throughput": 658.64, "total_tokens": 50856176} {"current_steps": 36990, "total_steps": 40000, "loss": 0.7925, "lr": 6.958031194066406e-07, "epoch": 1.1839830996735163, "percentage": 92.47, "elapsed_time": "21:26:55", "remaining_time": "1:44:43", "throughput": 658.72, "total_tokens": 50863424} {"current_steps": 36995, "total_steps": 40000, "loss": 0.6639, "lr": 6.935049024865776e-07, "epoch": 1.1841431406440048, "percentage": 92.49, "elapsed_time": "21:26:57", "remaining_time": "1:44:32", "throughput": 658.79, "total_tokens": 50870144} {"current_steps": 37000, "total_steps": 40000, "loss": 0.7073, "lr": 6.912104339335118e-07, "epoch": 1.1843031816144933, "percentage": 92.5, "elapsed_time": "21:26:58", "remaining_time": "1:44:20", "throughput": 658.87, "total_tokens": 50876992} {"current_steps": 37000, "total_steps": 40000, "eval_loss": 0.7299611568450928, "epoch": 1.1843031816144933, "percentage": 92.5, "elapsed_time": "21:32:47", "remaining_time": "1:44:49", "throughput": 655.9, "total_tokens": 50876992} {"current_steps": 37005, "total_steps": 40000, "loss": 0.7144, "lr": 6.889197141012799e-07, "epoch": 1.1844632225849818, "percentage": 92.51, "elapsed_time": "21:32:51", "remaining_time": "1:44:38", "throughput": 655.97, "total_tokens": 50884400} {"current_steps": 37010, "total_steps": 40000, "loss": 0.9681, "lr": 6.866327433431435e-07, "epoch": 1.18462326355547, "percentage": 92.53, "elapsed_time": "21:32:52", "remaining_time": "1:44:27", "throughput": 656.05, "total_tokens": 50891680} {"current_steps": 37015, "total_steps": 40000, "loss": 0.5829, "lr": 6.843495220117735e-07, "epoch": 1.1847833045259586, "percentage": 92.54, "elapsed_time": "21:32:54", "remaining_time": "1:44:15", "throughput": 656.12, "total_tokens": 50898592} {"current_steps": 37020, "total_steps": 40000, "loss": 0.7698, "lr": 6.820700504592798e-07, "epoch": 1.184943345496447, "percentage": 92.55, "elapsed_time": "21:32:56", "remaining_time": "1:44:04", "throughput": 656.2, "total_tokens": 50905376} {"current_steps": 37025, "total_steps": 40000, "loss": 0.6378, "lr": 6.797943290371839e-07, "epoch": 1.1851033864669356, "percentage": 92.56, "elapsed_time": "21:32:58", "remaining_time": "1:43:53", "throughput": 656.27, "total_tokens": 50912064} {"current_steps": 37030, "total_steps": 40000, "loss": 0.8976, "lr": 6.775223580964274e-07, "epoch": 1.185263427437424, "percentage": 92.58, "elapsed_time": "21:32:59", "remaining_time": "1:43:42", "throughput": 656.34, "total_tokens": 50919072} {"current_steps": 37035, "total_steps": 40000, "loss": 0.7383, "lr": 6.7525413798738e-07, "epoch": 1.1854234684079124, "percentage": 92.59, "elapsed_time": "21:33:01", "remaining_time": "1:43:31", "throughput": 656.42, "total_tokens": 50926064} {"current_steps": 37040, "total_steps": 40000, "loss": 0.8237, "lr": 6.729896690598259e-07, "epoch": 1.1855835093784008, "percentage": 92.6, "elapsed_time": "21:33:03", "remaining_time": "1:43:19", "throughput": 656.49, "total_tokens": 50932832} {"current_steps": 37045, "total_steps": 40000, "loss": 0.7004, "lr": 6.707289516629772e-07, "epoch": 1.1857435503488893, "percentage": 92.61, "elapsed_time": "21:33:05", "remaining_time": "1:43:08", "throughput": 656.56, "total_tokens": 50939488} {"current_steps": 37050, "total_steps": 40000, "loss": 0.6799, "lr": 6.684719861454692e-07, "epoch": 1.1859035913193778, "percentage": 92.62, "elapsed_time": "21:33:07", "remaining_time": "1:42:57", "throughput": 656.63, "total_tokens": 50946144} {"current_steps": 37055, "total_steps": 40000, "loss": 0.6256, "lr": 6.662187728553481e-07, "epoch": 1.186063632289866, "percentage": 92.64, "elapsed_time": "21:33:08", "remaining_time": "1:42:46", "throughput": 656.7, "total_tokens": 50952864} {"current_steps": 37060, "total_steps": 40000, "loss": 0.8937, "lr": 6.639693121400892e-07, "epoch": 1.1862236732603546, "percentage": 92.65, "elapsed_time": "21:33:10", "remaining_time": "1:42:35", "throughput": 656.77, "total_tokens": 50959488} {"current_steps": 37065, "total_steps": 40000, "loss": 0.5817, "lr": 6.617236043465868e-07, "epoch": 1.186383714230843, "percentage": 92.66, "elapsed_time": "21:33:12", "remaining_time": "1:42:24", "throughput": 656.85, "total_tokens": 50966336} {"current_steps": 37070, "total_steps": 40000, "loss": 0.7184, "lr": 6.594816498211587e-07, "epoch": 1.1865437552013316, "percentage": 92.67, "elapsed_time": "21:33:14", "remaining_time": "1:42:13", "throughput": 656.92, "total_tokens": 50972960} {"current_steps": 37075, "total_steps": 40000, "loss": 0.8076, "lr": 6.572434489095447e-07, "epoch": 1.18670379617182, "percentage": 92.69, "elapsed_time": "21:33:15", "remaining_time": "1:42:01", "throughput": 656.99, "total_tokens": 50979696} {"current_steps": 37080, "total_steps": 40000, "loss": 0.5418, "lr": 6.550090019568994e-07, "epoch": 1.1868638371423084, "percentage": 92.7, "elapsed_time": "21:33:17", "remaining_time": "1:41:50", "throughput": 657.06, "total_tokens": 50986704} {"current_steps": 37085, "total_steps": 40000, "loss": 0.8283, "lr": 6.527783093078027e-07, "epoch": 1.1870238781127969, "percentage": 92.71, "elapsed_time": "21:33:19", "remaining_time": "1:41:39", "throughput": 657.15, "total_tokens": 50994384} {"current_steps": 37090, "total_steps": 40000, "loss": 0.5974, "lr": 6.5055137130626e-07, "epoch": 1.1871839190832854, "percentage": 92.73, "elapsed_time": "21:33:21", "remaining_time": "1:41:28", "throughput": 657.22, "total_tokens": 51001232} {"current_steps": 37095, "total_steps": 40000, "loss": 0.7197, "lr": 6.483281882956854e-07, "epoch": 1.1873439600537739, "percentage": 92.74, "elapsed_time": "21:33:23", "remaining_time": "1:41:17", "throughput": 657.29, "total_tokens": 51007920} {"current_steps": 37100, "total_steps": 40000, "loss": 0.6194, "lr": 6.461087606189298e-07, "epoch": 1.1875040010242621, "percentage": 92.75, "elapsed_time": "21:33:24", "remaining_time": "1:41:06", "throughput": 657.37, "total_tokens": 51015216} {"current_steps": 37105, "total_steps": 40000, "loss": 0.8453, "lr": 6.438930886182554e-07, "epoch": 1.1876640419947506, "percentage": 92.76, "elapsed_time": "21:33:26", "remaining_time": "1:40:55", "throughput": 657.45, "total_tokens": 51022224} {"current_steps": 37110, "total_steps": 40000, "loss": 0.6379, "lr": 6.416811726353417e-07, "epoch": 1.1878240829652391, "percentage": 92.77, "elapsed_time": "21:33:28", "remaining_time": "1:40:43", "throughput": 657.52, "total_tokens": 51028768} {"current_steps": 37115, "total_steps": 40000, "loss": 0.703, "lr": 6.394730130112991e-07, "epoch": 1.1879841239357276, "percentage": 92.79, "elapsed_time": "21:33:30", "remaining_time": "1:40:32", "throughput": 657.59, "total_tokens": 51035680} {"current_steps": 37120, "total_steps": 40000, "loss": 0.6344, "lr": 6.372686100866471e-07, "epoch": 1.188144164906216, "percentage": 92.8, "elapsed_time": "21:33:31", "remaining_time": "1:40:21", "throughput": 657.66, "total_tokens": 51042368} {"current_steps": 37125, "total_steps": 40000, "loss": 0.6457, "lr": 6.350679642013413e-07, "epoch": 1.1883042058767044, "percentage": 92.81, "elapsed_time": "21:33:33", "remaining_time": "1:40:10", "throughput": 657.73, "total_tokens": 51049072} {"current_steps": 37130, "total_steps": 40000, "loss": 0.7558, "lr": 6.328710756947437e-07, "epoch": 1.1884642468471929, "percentage": 92.83, "elapsed_time": "21:33:35", "remaining_time": "1:39:59", "throughput": 657.81, "total_tokens": 51055920} {"current_steps": 37135, "total_steps": 40000, "loss": 1.0032, "lr": 6.306779449056416e-07, "epoch": 1.1886242878176814, "percentage": 92.84, "elapsed_time": "21:33:37", "remaining_time": "1:39:48", "throughput": 657.89, "total_tokens": 51063376} {"current_steps": 37140, "total_steps": 40000, "loss": 0.7343, "lr": 6.284885721722422e-07, "epoch": 1.1887843287881699, "percentage": 92.85, "elapsed_time": "21:33:38", "remaining_time": "1:39:37", "throughput": 657.96, "total_tokens": 51070304} {"current_steps": 37145, "total_steps": 40000, "loss": 0.6739, "lr": 6.26302957832181e-07, "epoch": 1.1889443697586581, "percentage": 92.86, "elapsed_time": "21:33:40", "remaining_time": "1:39:26", "throughput": 658.03, "total_tokens": 51076992} {"current_steps": 37150, "total_steps": 40000, "loss": 0.7028, "lr": 6.241211022224997e-07, "epoch": 1.1891044107291466, "percentage": 92.88, "elapsed_time": "21:33:42", "remaining_time": "1:39:14", "throughput": 658.1, "total_tokens": 51083616} {"current_steps": 37155, "total_steps": 40000, "loss": 0.7251, "lr": 6.219430056796732e-07, "epoch": 1.1892644516996351, "percentage": 92.89, "elapsed_time": "21:33:44", "remaining_time": "1:39:03", "throughput": 658.17, "total_tokens": 51090080} {"current_steps": 37160, "total_steps": 40000, "loss": 0.5175, "lr": 6.19768668539586e-07, "epoch": 1.1894244926701236, "percentage": 92.9, "elapsed_time": "21:33:46", "remaining_time": "1:38:52", "throughput": 658.25, "total_tokens": 51097184} {"current_steps": 37165, "total_steps": 40000, "loss": 0.5774, "lr": 6.175980911375528e-07, "epoch": 1.1895845336406121, "percentage": 92.91, "elapsed_time": "21:33:47", "remaining_time": "1:38:41", "throughput": 658.32, "total_tokens": 51104064} {"current_steps": 37170, "total_steps": 40000, "loss": 0.6063, "lr": 6.154312738083034e-07, "epoch": 1.1897445746111004, "percentage": 92.92, "elapsed_time": "21:33:49", "remaining_time": "1:38:30", "throughput": 658.39, "total_tokens": 51110896} {"current_steps": 37175, "total_steps": 40000, "loss": 0.587, "lr": 6.132682168859843e-07, "epoch": 1.1899046155815889, "percentage": 92.94, "elapsed_time": "21:33:51", "remaining_time": "1:38:19", "throughput": 658.47, "total_tokens": 51117936} {"current_steps": 37180, "total_steps": 40000, "loss": 0.6294, "lr": 6.111089207041704e-07, "epoch": 1.1900646565520774, "percentage": 92.95, "elapsed_time": "21:33:53", "remaining_time": "1:38:08", "throughput": 658.54, "total_tokens": 51124848} {"current_steps": 37185, "total_steps": 40000, "loss": 0.9386, "lr": 6.089533855958507e-07, "epoch": 1.1902246975225657, "percentage": 92.96, "elapsed_time": "21:33:54", "remaining_time": "1:37:57", "throughput": 658.62, "total_tokens": 51132064} {"current_steps": 37190, "total_steps": 40000, "loss": 0.9965, "lr": 6.068016118934372e-07, "epoch": 1.1903847384930542, "percentage": 92.97, "elapsed_time": "21:33:56", "remaining_time": "1:37:46", "throughput": 658.7, "total_tokens": 51139168} {"current_steps": 37195, "total_steps": 40000, "loss": 0.7901, "lr": 6.04653599928759e-07, "epoch": 1.1905447794635426, "percentage": 92.99, "elapsed_time": "21:33:58", "remaining_time": "1:37:34", "throughput": 658.77, "total_tokens": 51146240} {"current_steps": 37200, "total_steps": 40000, "loss": 0.8427, "lr": 6.025093500330675e-07, "epoch": 1.1907048204340311, "percentage": 93.0, "elapsed_time": "21:34:00", "remaining_time": "1:37:23", "throughput": 658.85, "total_tokens": 51153296} {"current_steps": 37200, "total_steps": 40000, "eval_loss": 0.730063259601593, "epoch": 1.1907048204340311, "percentage": 93.0, "elapsed_time": "21:39:47", "remaining_time": "1:37:50", "throughput": 655.91, "total_tokens": 51153296} {"current_steps": 37205, "total_steps": 40000, "loss": 0.6401, "lr": 6.003688625370291e-07, "epoch": 1.1908648614045196, "percentage": 93.01, "elapsed_time": "21:39:51", "remaining_time": "1:37:39", "throughput": 655.98, "total_tokens": 51160400} {"current_steps": 37210, "total_steps": 40000, "loss": 0.5543, "lr": 5.982321377707406e-07, "epoch": 1.191024902375008, "percentage": 93.03, "elapsed_time": "21:39:53", "remaining_time": "1:37:27", "throughput": 656.04, "total_tokens": 51166800} {"current_steps": 37215, "total_steps": 40000, "loss": 0.5704, "lr": 5.96099176063708e-07, "epoch": 1.1911849433454964, "percentage": 93.04, "elapsed_time": "21:39:55", "remaining_time": "1:37:16", "throughput": 656.11, "total_tokens": 51173648} {"current_steps": 37220, "total_steps": 40000, "loss": 0.7901, "lr": 5.93969977744857e-07, "epoch": 1.191344984315985, "percentage": 93.05, "elapsed_time": "21:39:56", "remaining_time": "1:37:05", "throughput": 656.18, "total_tokens": 51180288} {"current_steps": 37225, "total_steps": 40000, "loss": 0.8885, "lr": 5.918445431425445e-07, "epoch": 1.1915050252864734, "percentage": 93.06, "elapsed_time": "21:39:58", "remaining_time": "1:36:54", "throughput": 656.26, "total_tokens": 51187440} {"current_steps": 37230, "total_steps": 40000, "loss": 0.8367, "lr": 5.897228725845333e-07, "epoch": 1.1916650662569617, "percentage": 93.08, "elapsed_time": "21:40:00", "remaining_time": "1:36:43", "throughput": 656.33, "total_tokens": 51194000} {"current_steps": 37235, "total_steps": 40000, "loss": 0.7203, "lr": 5.876049663980171e-07, "epoch": 1.1918251072274502, "percentage": 93.09, "elapsed_time": "21:40:02", "remaining_time": "1:36:32", "throughput": 656.4, "total_tokens": 51200880} {"current_steps": 37240, "total_steps": 40000, "loss": 0.6913, "lr": 5.854908249095959e-07, "epoch": 1.1919851481979387, "percentage": 93.1, "elapsed_time": "21:40:03", "remaining_time": "1:36:21", "throughput": 656.47, "total_tokens": 51207440} {"current_steps": 37245, "total_steps": 40000, "loss": 0.8789, "lr": 5.833804484453031e-07, "epoch": 1.1921451891684272, "percentage": 93.11, "elapsed_time": "21:40:05", "remaining_time": "1:36:10", "throughput": 656.55, "total_tokens": 51214432} {"current_steps": 37250, "total_steps": 40000, "loss": 0.5378, "lr": 5.81273837330587e-07, "epoch": 1.1923052301389157, "percentage": 93.12, "elapsed_time": "21:40:07", "remaining_time": "1:35:58", "throughput": 656.62, "total_tokens": 51221360} {"current_steps": 37255, "total_steps": 40000, "loss": 0.5307, "lr": 5.791709918903071e-07, "epoch": 1.192465271109404, "percentage": 93.14, "elapsed_time": "21:40:09", "remaining_time": "1:35:47", "throughput": 656.7, "total_tokens": 51228384} {"current_steps": 37260, "total_steps": 40000, "loss": 0.6656, "lr": 5.770719124487483e-07, "epoch": 1.1926253120798924, "percentage": 93.15, "elapsed_time": "21:40:10", "remaining_time": "1:35:36", "throughput": 656.77, "total_tokens": 51235120} {"current_steps": 37265, "total_steps": 40000, "loss": 0.6436, "lr": 5.749765993296241e-07, "epoch": 1.192785353050381, "percentage": 93.16, "elapsed_time": "21:40:12", "remaining_time": "1:35:25", "throughput": 656.84, "total_tokens": 51241776} {"current_steps": 37270, "total_steps": 40000, "loss": 0.5737, "lr": 5.728850528560509e-07, "epoch": 1.1929453940208694, "percentage": 93.17, "elapsed_time": "21:40:14", "remaining_time": "1:35:14", "throughput": 656.91, "total_tokens": 51248352} {"current_steps": 37275, "total_steps": 40000, "loss": 0.6185, "lr": 5.707972733505707e-07, "epoch": 1.1931054349913577, "percentage": 93.19, "elapsed_time": "21:40:16", "remaining_time": "1:35:03", "throughput": 656.98, "total_tokens": 51254976} {"current_steps": 37280, "total_steps": 40000, "loss": 0.8878, "lr": 5.687132611351509e-07, "epoch": 1.1932654759618462, "percentage": 93.2, "elapsed_time": "21:40:18", "remaining_time": "1:34:52", "throughput": 657.05, "total_tokens": 51262144} {"current_steps": 37285, "total_steps": 40000, "loss": 0.7504, "lr": 5.666330165311651e-07, "epoch": 1.1934255169323347, "percentage": 93.21, "elapsed_time": "21:40:19", "remaining_time": "1:34:41", "throughput": 657.13, "total_tokens": 51268800} {"current_steps": 37290, "total_steps": 40000, "loss": 0.6353, "lr": 5.645565398594204e-07, "epoch": 1.1935855579028232, "percentage": 93.23, "elapsed_time": "21:40:21", "remaining_time": "1:34:30", "throughput": 657.2, "total_tokens": 51275776} {"current_steps": 37295, "total_steps": 40000, "loss": 0.5731, "lr": 5.624838314401304e-07, "epoch": 1.1937455988733117, "percentage": 93.24, "elapsed_time": "21:40:23", "remaining_time": "1:34:19", "throughput": 657.27, "total_tokens": 51282672} {"current_steps": 37300, "total_steps": 40000, "loss": 0.8585, "lr": 5.604148915929336e-07, "epoch": 1.1939056398438, "percentage": 93.25, "elapsed_time": "21:40:25", "remaining_time": "1:34:07", "throughput": 657.35, "total_tokens": 51290032} {"current_steps": 37305, "total_steps": 40000, "loss": 0.6048, "lr": 5.583497206368887e-07, "epoch": 1.1940656808142884, "percentage": 93.26, "elapsed_time": "21:40:26", "remaining_time": "1:33:56", "throughput": 657.42, "total_tokens": 51296704} {"current_steps": 37310, "total_steps": 40000, "loss": 0.6114, "lr": 5.562883188904688e-07, "epoch": 1.194225721784777, "percentage": 93.27, "elapsed_time": "21:40:28", "remaining_time": "1:33:45", "throughput": 657.5, "total_tokens": 51303520} {"current_steps": 37315, "total_steps": 40000, "loss": 0.6525, "lr": 5.542306866715724e-07, "epoch": 1.1943857627552654, "percentage": 93.29, "elapsed_time": "21:40:30", "remaining_time": "1:33:34", "throughput": 657.57, "total_tokens": 51310320} {"current_steps": 37320, "total_steps": 40000, "loss": 0.6683, "lr": 5.52176824297504e-07, "epoch": 1.1945458037257537, "percentage": 93.3, "elapsed_time": "21:40:32", "remaining_time": "1:33:23", "throughput": 657.65, "total_tokens": 51317488} {"current_steps": 37325, "total_steps": 40000, "loss": 0.8237, "lr": 5.501267320850018e-07, "epoch": 1.1947058446962422, "percentage": 93.31, "elapsed_time": "21:40:33", "remaining_time": "1:33:12", "throughput": 657.72, "total_tokens": 51324704} {"current_steps": 37330, "total_steps": 40000, "loss": 0.5963, "lr": 5.480804103502157e-07, "epoch": 1.1948658856667307, "percentage": 93.33, "elapsed_time": "21:40:35", "remaining_time": "1:33:01", "throughput": 657.79, "total_tokens": 51331472} {"current_steps": 37335, "total_steps": 40000, "loss": 0.6921, "lr": 5.460378594087101e-07, "epoch": 1.1950259266372192, "percentage": 93.34, "elapsed_time": "21:40:37", "remaining_time": "1:32:50", "throughput": 657.87, "total_tokens": 51338384} {"current_steps": 37340, "total_steps": 40000, "loss": 0.7553, "lr": 5.439990795754773e-07, "epoch": 1.1951859676077077, "percentage": 93.35, "elapsed_time": "21:40:39", "remaining_time": "1:32:39", "throughput": 657.94, "total_tokens": 51345296} {"current_steps": 37345, "total_steps": 40000, "loss": 0.7256, "lr": 5.419640711649188e-07, "epoch": 1.195346008578196, "percentage": 93.36, "elapsed_time": "21:40:41", "remaining_time": "1:32:28", "throughput": 658.02, "total_tokens": 51352416} {"current_steps": 37350, "total_steps": 40000, "loss": 0.5336, "lr": 5.399328344908583e-07, "epoch": 1.1955060495486844, "percentage": 93.38, "elapsed_time": "21:40:42", "remaining_time": "1:32:17", "throughput": 658.09, "total_tokens": 51359504} {"current_steps": 37355, "total_steps": 40000, "loss": 0.736, "lr": 5.379053698665399e-07, "epoch": 1.195666090519173, "percentage": 93.39, "elapsed_time": "21:40:44", "remaining_time": "1:32:06", "throughput": 658.16, "total_tokens": 51366144} {"current_steps": 37360, "total_steps": 40000, "loss": 0.8603, "lr": 5.358816776046216e-07, "epoch": 1.1958261314896614, "percentage": 93.4, "elapsed_time": "21:40:46", "remaining_time": "1:31:55", "throughput": 658.23, "total_tokens": 51372752} {"current_steps": 37365, "total_steps": 40000, "loss": 0.8223, "lr": 5.338617580171817e-07, "epoch": 1.1959861724601497, "percentage": 93.41, "elapsed_time": "21:40:48", "remaining_time": "1:31:43", "throughput": 658.31, "total_tokens": 51380032} {"current_steps": 37370, "total_steps": 40000, "loss": 0.5661, "lr": 5.318456114157239e-07, "epoch": 1.1961462134306382, "percentage": 93.42, "elapsed_time": "21:40:49", "remaining_time": "1:31:32", "throughput": 658.39, "total_tokens": 51387104} {"current_steps": 37375, "total_steps": 40000, "loss": 0.6476, "lr": 5.298332381111576e-07, "epoch": 1.1963062544011267, "percentage": 93.44, "elapsed_time": "21:40:51", "remaining_time": "1:31:21", "throughput": 658.46, "total_tokens": 51393872} {"current_steps": 37380, "total_steps": 40000, "loss": 0.8711, "lr": 5.27824638413818e-07, "epoch": 1.1964662953716152, "percentage": 93.45, "elapsed_time": "21:40:53", "remaining_time": "1:31:10", "throughput": 658.53, "total_tokens": 51400848} {"current_steps": 37385, "total_steps": 40000, "loss": 0.5905, "lr": 5.258198126334546e-07, "epoch": 1.1966263363421037, "percentage": 93.46, "elapsed_time": "21:40:55", "remaining_time": "1:30:59", "throughput": 658.61, "total_tokens": 51407632} {"current_steps": 37390, "total_steps": 40000, "loss": 0.7203, "lr": 5.238187610792367e-07, "epoch": 1.196786377312592, "percentage": 93.47, "elapsed_time": "21:40:56", "remaining_time": "1:30:48", "throughput": 658.68, "total_tokens": 51414352} {"current_steps": 37395, "total_steps": 40000, "loss": 0.5631, "lr": 5.218214840597563e-07, "epoch": 1.1969464182830805, "percentage": 93.49, "elapsed_time": "21:40:58", "remaining_time": "1:30:37", "throughput": 658.75, "total_tokens": 51421136} {"current_steps": 37400, "total_steps": 40000, "loss": 0.9195, "lr": 5.198279818830115e-07, "epoch": 1.197106459253569, "percentage": 93.5, "elapsed_time": "21:41:00", "remaining_time": "1:30:26", "throughput": 658.82, "total_tokens": 51427552} {"current_steps": 37400, "total_steps": 40000, "eval_loss": 0.7300239205360413, "epoch": 1.197106459253569, "percentage": 93.5, "elapsed_time": "21:46:48", "remaining_time": "1:30:50", "throughput": 655.89, "total_tokens": 51427552} {"current_steps": 37405, "total_steps": 40000, "loss": 0.7429, "lr": 5.178382548564287e-07, "epoch": 1.1972665002240575, "percentage": 93.51, "elapsed_time": "21:46:52", "remaining_time": "1:30:39", "throughput": 655.95, "total_tokens": 51434368} {"current_steps": 37410, "total_steps": 40000, "loss": 0.6563, "lr": 5.15852303286854e-07, "epoch": 1.1974265411945457, "percentage": 93.53, "elapsed_time": "21:46:54", "remaining_time": "1:30:28", "throughput": 656.02, "total_tokens": 51441008} {"current_steps": 37415, "total_steps": 40000, "loss": 0.7212, "lr": 5.138701274805396e-07, "epoch": 1.1975865821650342, "percentage": 93.54, "elapsed_time": "21:46:55", "remaining_time": "1:30:17", "throughput": 656.09, "total_tokens": 51447856} {"current_steps": 37420, "total_steps": 40000, "loss": 0.5591, "lr": 5.118917277431606e-07, "epoch": 1.1977466231355227, "percentage": 93.55, "elapsed_time": "21:46:57", "remaining_time": "1:30:06", "throughput": 656.16, "total_tokens": 51454752} {"current_steps": 37425, "total_steps": 40000, "loss": 0.6589, "lr": 5.099171043798145e-07, "epoch": 1.1979066641060112, "percentage": 93.56, "elapsed_time": "21:46:59", "remaining_time": "1:29:55", "throughput": 656.23, "total_tokens": 51461392} {"current_steps": 37430, "total_steps": 40000, "loss": 0.7557, "lr": 5.079462576950133e-07, "epoch": 1.1980667050764997, "percentage": 93.58, "elapsed_time": "21:47:01", "remaining_time": "1:29:44", "throughput": 656.31, "total_tokens": 51468896} {"current_steps": 37435, "total_steps": 40000, "loss": 0.6082, "lr": 5.059791879926862e-07, "epoch": 1.198226746046988, "percentage": 93.59, "elapsed_time": "21:47:02", "remaining_time": "1:29:33", "throughput": 656.38, "total_tokens": 51475328} {"current_steps": 37440, "total_steps": 40000, "loss": 0.6115, "lr": 5.040158955761793e-07, "epoch": 1.1983867870174765, "percentage": 93.6, "elapsed_time": "21:47:04", "remaining_time": "1:29:22", "throughput": 656.45, "total_tokens": 51481888} {"current_steps": 37445, "total_steps": 40000, "loss": 0.8175, "lr": 5.020563807482559e-07, "epoch": 1.198546827987965, "percentage": 93.61, "elapsed_time": "21:47:06", "remaining_time": "1:29:11", "throughput": 656.53, "total_tokens": 51489088} {"current_steps": 37450, "total_steps": 40000, "loss": 0.7639, "lr": 5.001006438110995e-07, "epoch": 1.1987068689584532, "percentage": 93.62, "elapsed_time": "21:47:08", "remaining_time": "1:29:00", "throughput": 656.6, "total_tokens": 51495712} {"current_steps": 37455, "total_steps": 40000, "loss": 0.6769, "lr": 4.981486850663075e-07, "epoch": 1.1988669099289417, "percentage": 93.64, "elapsed_time": "21:47:09", "remaining_time": "1:28:49", "throughput": 656.67, "total_tokens": 51502624} {"current_steps": 37460, "total_steps": 40000, "loss": 0.7113, "lr": 4.962005048149005e-07, "epoch": 1.1990269508994302, "percentage": 93.65, "elapsed_time": "21:47:11", "remaining_time": "1:28:38", "throughput": 656.74, "total_tokens": 51509520} {"current_steps": 37465, "total_steps": 40000, "loss": 0.8158, "lr": 4.942561033573073e-07, "epoch": 1.1991869918699187, "percentage": 93.66, "elapsed_time": "21:47:13", "remaining_time": "1:28:27", "throughput": 656.82, "total_tokens": 51516320} {"current_steps": 37470, "total_steps": 40000, "loss": 0.6947, "lr": 4.923154809933827e-07, "epoch": 1.1993470328404072, "percentage": 93.67, "elapsed_time": "21:47:15", "remaining_time": "1:28:15", "throughput": 656.89, "total_tokens": 51523456} {"current_steps": 37475, "total_steps": 40000, "loss": 0.7904, "lr": 4.903786380223957e-07, "epoch": 1.1995070738108955, "percentage": 93.69, "elapsed_time": "21:47:16", "remaining_time": "1:28:04", "throughput": 656.97, "total_tokens": 51530624} {"current_steps": 37480, "total_steps": 40000, "loss": 0.9315, "lr": 4.884455747430266e-07, "epoch": 1.199667114781384, "percentage": 93.7, "elapsed_time": "21:47:18", "remaining_time": "1:27:53", "throughput": 657.05, "total_tokens": 51537856} {"current_steps": 37485, "total_steps": 40000, "loss": 0.5808, "lr": 4.865162914533816e-07, "epoch": 1.1998271557518725, "percentage": 93.71, "elapsed_time": "21:47:20", "remaining_time": "1:27:42", "throughput": 657.12, "total_tokens": 51544448} {"current_steps": 37490, "total_steps": 40000, "loss": 0.6657, "lr": 4.845907884509809e-07, "epoch": 1.199987196722361, "percentage": 93.73, "elapsed_time": "21:47:21", "remaining_time": "1:27:31", "throughput": 657.19, "total_tokens": 51551584} {"current_steps": 37495, "total_steps": 40000, "loss": 0.5641, "lr": 4.82669066032762e-07, "epoch": 1.2001472376928493, "percentage": 93.74, "elapsed_time": "21:47:23", "remaining_time": "1:27:20", "throughput": 657.26, "total_tokens": 51558096} {"current_steps": 37500, "total_steps": 40000, "loss": 0.6644, "lr": 4.807511244950768e-07, "epoch": 1.2003072786633378, "percentage": 93.75, "elapsed_time": "21:47:25", "remaining_time": "1:27:09", "throughput": 657.33, "total_tokens": 51564944} {"current_steps": 37505, "total_steps": 40000, "loss": 0.5724, "lr": 4.788369641336943e-07, "epoch": 1.2004673196338262, "percentage": 93.76, "elapsed_time": "21:47:27", "remaining_time": "1:26:58", "throughput": 657.41, "total_tokens": 51572144} {"current_steps": 37510, "total_steps": 40000, "loss": 0.7002, "lr": 4.769265852438032e-07, "epoch": 1.2006273606043147, "percentage": 93.77, "elapsed_time": "21:47:28", "remaining_time": "1:26:47", "throughput": 657.49, "total_tokens": 51579056} {"current_steps": 37515, "total_steps": 40000, "loss": 0.6785, "lr": 4.750199881200124e-07, "epoch": 1.2007874015748032, "percentage": 93.79, "elapsed_time": "21:47:30", "remaining_time": "1:26:36", "throughput": 657.56, "total_tokens": 51585840} {"current_steps": 37520, "total_steps": 40000, "loss": 0.9853, "lr": 4.7311717305633664e-07, "epoch": 1.2009474425452915, "percentage": 93.8, "elapsed_time": "21:47:32", "remaining_time": "1:26:25", "throughput": 657.63, "total_tokens": 51592464} {"current_steps": 37525, "total_steps": 40000, "loss": 0.7619, "lr": 4.7121814034621623e-07, "epoch": 1.20110748351578, "percentage": 93.81, "elapsed_time": "21:47:34", "remaining_time": "1:26:14", "throughput": 657.7, "total_tokens": 51599568} {"current_steps": 37530, "total_steps": 40000, "loss": 0.7033, "lr": 4.693228902825114e-07, "epoch": 1.2012675244862685, "percentage": 93.83, "elapsed_time": "21:47:35", "remaining_time": "1:26:03", "throughput": 657.77, "total_tokens": 51606128} {"current_steps": 37535, "total_steps": 40000, "loss": 0.5721, "lr": 4.6743142315748277e-07, "epoch": 1.201427565456757, "percentage": 93.84, "elapsed_time": "21:47:37", "remaining_time": "1:25:52", "throughput": 657.84, "total_tokens": 51612880} {"current_steps": 37540, "total_steps": 40000, "loss": 0.8667, "lr": 4.655437392628276e-07, "epoch": 1.2015876064272453, "percentage": 93.85, "elapsed_time": "21:47:39", "remaining_time": "1:25:41", "throughput": 657.91, "total_tokens": 51619552} {"current_steps": 37545, "total_steps": 40000, "loss": 0.9554, "lr": 4.636598388896463e-07, "epoch": 1.2017476473977338, "percentage": 93.86, "elapsed_time": "21:47:41", "remaining_time": "1:25:30", "throughput": 657.99, "total_tokens": 51626416} {"current_steps": 37550, "total_steps": 40000, "loss": 0.657, "lr": 4.6177972232845925e-07, "epoch": 1.2019076883682223, "percentage": 93.88, "elapsed_time": "21:47:42", "remaining_time": "1:25:19", "throughput": 658.06, "total_tokens": 51633184} {"current_steps": 37555, "total_steps": 40000, "loss": 0.8157, "lr": 4.5990338986920953e-07, "epoch": 1.2020677293387108, "percentage": 93.89, "elapsed_time": "21:47:44", "remaining_time": "1:25:08", "throughput": 658.14, "total_tokens": 51640704} {"current_steps": 37560, "total_steps": 40000, "loss": 0.7042, "lr": 4.5803084180124633e-07, "epoch": 1.2022277703091993, "percentage": 93.9, "elapsed_time": "21:47:46", "remaining_time": "1:24:57", "throughput": 658.22, "total_tokens": 51647856} {"current_steps": 37565, "total_steps": 40000, "loss": 0.4952, "lr": 4.561620784133386e-07, "epoch": 1.2023878112796875, "percentage": 93.91, "elapsed_time": "21:47:48", "remaining_time": "1:24:46", "throughput": 658.29, "total_tokens": 51654720} {"current_steps": 37570, "total_steps": 40000, "loss": 0.5994, "lr": 4.5429709999367796e-07, "epoch": 1.202547852250176, "percentage": 93.92, "elapsed_time": "21:47:49", "remaining_time": "1:24:35", "throughput": 658.36, "total_tokens": 51661520} {"current_steps": 37575, "total_steps": 40000, "loss": 0.5978, "lr": 4.5243590682986223e-07, "epoch": 1.2027078932206645, "percentage": 93.94, "elapsed_time": "21:47:51", "remaining_time": "1:24:24", "throughput": 658.44, "total_tokens": 51668464} {"current_steps": 37580, "total_steps": 40000, "loss": 0.624, "lr": 4.5057849920891735e-07, "epoch": 1.202867934191153, "percentage": 93.95, "elapsed_time": "21:47:53", "remaining_time": "1:24:13", "throughput": 658.51, "total_tokens": 51675584} {"current_steps": 37585, "total_steps": 40000, "loss": 0.7184, "lr": 4.487248774172698e-07, "epoch": 1.2030279751616413, "percentage": 93.96, "elapsed_time": "21:47:54", "remaining_time": "1:24:02", "throughput": 658.59, "total_tokens": 51682608} {"current_steps": 37590, "total_steps": 40000, "loss": 1.1969, "lr": 4.4687504174077965e-07, "epoch": 1.2031880161321298, "percentage": 93.97, "elapsed_time": "21:47:57", "remaining_time": "1:23:51", "throughput": 658.71, "total_tokens": 51693216} {"current_steps": 37595, "total_steps": 40000, "loss": 0.7204, "lr": 4.450289924647133e-07, "epoch": 1.2033480571026183, "percentage": 93.99, "elapsed_time": "21:47:58", "remaining_time": "1:23:40", "throughput": 658.78, "total_tokens": 51700160} {"current_steps": 37600, "total_steps": 40000, "loss": 0.8146, "lr": 4.431867298737513e-07, "epoch": 1.2035080980731068, "percentage": 94.0, "elapsed_time": "21:48:00", "remaining_time": "1:23:29", "throughput": 658.85, "total_tokens": 51707088} {"current_steps": 37600, "total_steps": 40000, "eval_loss": 0.7300160527229309, "epoch": 1.2035080980731068, "percentage": 94.0, "elapsed_time": "21:53:49", "remaining_time": "1:23:51", "throughput": 655.94, "total_tokens": 51707088} {"current_steps": 37605, "total_steps": 40000, "loss": 0.6829, "lr": 4.41348254251997e-07, "epoch": 1.2036681390435953, "percentage": 94.01, "elapsed_time": "21:53:53", "remaining_time": "1:23:40", "throughput": 655.99, "total_tokens": 51713504} {"current_steps": 37610, "total_steps": 40000, "loss": 0.8542, "lr": 4.395135658829652e-07, "epoch": 1.2038281800140835, "percentage": 94.03, "elapsed_time": "21:53:54", "remaining_time": "1:23:29", "throughput": 656.06, "total_tokens": 51720144} {"current_steps": 37615, "total_steps": 40000, "loss": 0.9507, "lr": 4.376826650495852e-07, "epoch": 1.203988220984572, "percentage": 94.04, "elapsed_time": "21:53:56", "remaining_time": "1:23:18", "throughput": 656.13, "total_tokens": 51726992} {"current_steps": 37620, "total_steps": 40000, "loss": 0.6864, "lr": 4.358555520342117e-07, "epoch": 1.2041482619550605, "percentage": 94.05, "elapsed_time": "21:53:58", "remaining_time": "1:23:07", "throughput": 656.2, "total_tokens": 51733552} {"current_steps": 37625, "total_steps": 40000, "loss": 0.7967, "lr": 4.3403222711860257e-07, "epoch": 1.204308302925549, "percentage": 94.06, "elapsed_time": "21:54:00", "remaining_time": "1:22:56", "throughput": 656.27, "total_tokens": 51740096} {"current_steps": 37630, "total_steps": 40000, "loss": 0.6678, "lr": 4.3221269058394133e-07, "epoch": 1.2044683438960373, "percentage": 94.08, "elapsed_time": "21:54:01", "remaining_time": "1:22:45", "throughput": 656.35, "total_tokens": 51747488} {"current_steps": 37635, "total_steps": 40000, "loss": 0.6425, "lr": 4.303969427108173e-07, "epoch": 1.2046283848665258, "percentage": 94.09, "elapsed_time": "21:54:03", "remaining_time": "1:22:34", "throughput": 656.43, "total_tokens": 51754912} {"current_steps": 37640, "total_steps": 40000, "loss": 0.8499, "lr": 4.2858498377924825e-07, "epoch": 1.2047884258370143, "percentage": 94.1, "elapsed_time": "21:54:05", "remaining_time": "1:22:23", "throughput": 656.5, "total_tokens": 51761760} {"current_steps": 37645, "total_steps": 40000, "loss": 0.654, "lr": 4.267768140686579e-07, "epoch": 1.2049484668075028, "percentage": 94.11, "elapsed_time": "21:54:06", "remaining_time": "1:22:12", "throughput": 656.57, "total_tokens": 51768624} {"current_steps": 37650, "total_steps": 40000, "loss": 0.6204, "lr": 4.2497243385788975e-07, "epoch": 1.2051085077779913, "percentage": 94.12, "elapsed_time": "21:54:08", "remaining_time": "1:22:01", "throughput": 656.65, "total_tokens": 51776032} {"current_steps": 37655, "total_steps": 40000, "loss": 0.8375, "lr": 4.231718434251991e-07, "epoch": 1.2052685487484796, "percentage": 94.14, "elapsed_time": "21:54:10", "remaining_time": "1:21:50", "throughput": 656.72, "total_tokens": 51782800} {"current_steps": 37660, "total_steps": 40000, "loss": 0.8894, "lr": 4.213750430482666e-07, "epoch": 1.205428589718968, "percentage": 94.15, "elapsed_time": "21:54:12", "remaining_time": "1:21:39", "throughput": 656.79, "total_tokens": 51789568} {"current_steps": 37665, "total_steps": 40000, "loss": 0.7074, "lr": 4.1958203300417054e-07, "epoch": 1.2055886306894565, "percentage": 94.16, "elapsed_time": "21:54:13", "remaining_time": "1:21:28", "throughput": 656.86, "total_tokens": 51796272} {"current_steps": 37670, "total_steps": 40000, "loss": 0.7403, "lr": 4.177928135694259e-07, "epoch": 1.205748671659945, "percentage": 94.17, "elapsed_time": "21:54:15", "remaining_time": "1:21:17", "throughput": 656.94, "total_tokens": 51803088} {"current_steps": 37675, "total_steps": 40000, "loss": 0.8799, "lr": 4.1600738501994807e-07, "epoch": 1.2059087126304333, "percentage": 94.19, "elapsed_time": "21:54:17", "remaining_time": "1:21:06", "throughput": 657.01, "total_tokens": 51809968} {"current_steps": 37680, "total_steps": 40000, "loss": 0.7086, "lr": 4.1422574763107237e-07, "epoch": 1.2060687536009218, "percentage": 94.2, "elapsed_time": "21:54:19", "remaining_time": "1:20:55", "throughput": 657.09, "total_tokens": 51817664} {"current_steps": 37685, "total_steps": 40000, "loss": 0.7903, "lr": 4.124479016775512e-07, "epoch": 1.2062287945714103, "percentage": 94.21, "elapsed_time": "21:54:20", "remaining_time": "1:20:44", "throughput": 657.16, "total_tokens": 51824464} {"current_steps": 37690, "total_steps": 40000, "loss": 0.7454, "lr": 4.106738474335514e-07, "epoch": 1.2063888355418988, "percentage": 94.23, "elapsed_time": "21:54:22", "remaining_time": "1:20:33", "throughput": 657.24, "total_tokens": 51831360} {"current_steps": 37695, "total_steps": 40000, "loss": 0.7427, "lr": 4.089035851726486e-07, "epoch": 1.2065488765123873, "percentage": 94.24, "elapsed_time": "21:54:24", "remaining_time": "1:20:22", "throughput": 657.31, "total_tokens": 51838528} {"current_steps": 37700, "total_steps": 40000, "loss": 0.8861, "lr": 4.0713711516784937e-07, "epoch": 1.2067089174828756, "percentage": 94.25, "elapsed_time": "21:54:26", "remaining_time": "1:20:11", "throughput": 657.38, "total_tokens": 51845344} {"current_steps": 37705, "total_steps": 40000, "loss": 0.7871, "lr": 4.05374437691558e-07, "epoch": 1.206868958453364, "percentage": 94.26, "elapsed_time": "21:54:27", "remaining_time": "1:20:00", "throughput": 657.46, "total_tokens": 51852096} {"current_steps": 37710, "total_steps": 40000, "loss": 0.7105, "lr": 4.036155530156044e-07, "epoch": 1.2070289994238526, "percentage": 94.27, "elapsed_time": "21:54:29", "remaining_time": "1:19:49", "throughput": 657.53, "total_tokens": 51858976} {"current_steps": 37715, "total_steps": 40000, "loss": 0.8917, "lr": 4.018604614112298e-07, "epoch": 1.2071890403943408, "percentage": 94.29, "elapsed_time": "21:54:31", "remaining_time": "1:19:38", "throughput": 657.59, "total_tokens": 51865360} {"current_steps": 37720, "total_steps": 40000, "loss": 0.6728, "lr": 4.0010916314908996e-07, "epoch": 1.2073490813648293, "percentage": 94.3, "elapsed_time": "21:54:33", "remaining_time": "1:19:27", "throughput": 657.67, "total_tokens": 51872688} {"current_steps": 37725, "total_steps": 40000, "loss": 0.7052, "lr": 3.983616584992578e-07, "epoch": 1.2075091223353178, "percentage": 94.31, "elapsed_time": "21:54:34", "remaining_time": "1:19:16", "throughput": 657.75, "total_tokens": 51879552} {"current_steps": 37730, "total_steps": 40000, "loss": 0.6432, "lr": 3.9661794773122595e-07, "epoch": 1.2076691633058063, "percentage": 94.33, "elapsed_time": "21:54:36", "remaining_time": "1:19:05", "throughput": 657.82, "total_tokens": 51886208} {"current_steps": 37735, "total_steps": 40000, "loss": 0.7032, "lr": 3.9487803111388777e-07, "epoch": 1.2078292042762948, "percentage": 94.34, "elapsed_time": "21:54:38", "remaining_time": "1:18:54", "throughput": 657.89, "total_tokens": 51893232} {"current_steps": 37740, "total_steps": 40000, "loss": 0.7625, "lr": 3.9314190891556747e-07, "epoch": 1.207989245246783, "percentage": 94.35, "elapsed_time": "21:54:39", "remaining_time": "1:18:43", "throughput": 657.96, "total_tokens": 51900016} {"current_steps": 37745, "total_steps": 40000, "loss": 0.6786, "lr": 3.914095814039925e-07, "epoch": 1.2081492862172716, "percentage": 94.36, "elapsed_time": "21:54:41", "remaining_time": "1:18:32", "throughput": 658.03, "total_tokens": 51906800} {"current_steps": 37750, "total_steps": 40000, "loss": 0.6566, "lr": 3.896810488463104e-07, "epoch": 1.20830932718776, "percentage": 94.38, "elapsed_time": "21:54:43", "remaining_time": "1:18:21", "throughput": 658.1, "total_tokens": 51913296} {"current_steps": 37755, "total_steps": 40000, "loss": 0.7168, "lr": 3.8795631150908565e-07, "epoch": 1.2084693681582486, "percentage": 94.39, "elapsed_time": "21:54:45", "remaining_time": "1:18:10", "throughput": 658.17, "total_tokens": 51920224} {"current_steps": 37760, "total_steps": 40000, "loss": 0.9102, "lr": 3.862353696582888e-07, "epoch": 1.2086294091287368, "percentage": 94.4, "elapsed_time": "21:54:46", "remaining_time": "1:17:59", "throughput": 658.25, "total_tokens": 51927472} {"current_steps": 37765, "total_steps": 40000, "loss": 0.7886, "lr": 3.8451822355931313e-07, "epoch": 1.2087894500992253, "percentage": 94.41, "elapsed_time": "21:54:48", "remaining_time": "1:17:48", "throughput": 658.32, "total_tokens": 51934048} {"current_steps": 37770, "total_steps": 40000, "loss": 0.6068, "lr": 3.82804873476969e-07, "epoch": 1.2089494910697138, "percentage": 94.42, "elapsed_time": "21:54:50", "remaining_time": "1:17:37", "throughput": 658.39, "total_tokens": 51940560} {"current_steps": 37775, "total_steps": 40000, "loss": 0.8244, "lr": 3.810953196754702e-07, "epoch": 1.2091095320402023, "percentage": 94.44, "elapsed_time": "21:54:52", "remaining_time": "1:17:26", "throughput": 658.46, "total_tokens": 51947392} {"current_steps": 37780, "total_steps": 40000, "loss": 0.7739, "lr": 3.793895624184529e-07, "epoch": 1.2092695730106908, "percentage": 94.45, "elapsed_time": "21:54:53", "remaining_time": "1:17:15", "throughput": 658.53, "total_tokens": 51954144} {"current_steps": 37785, "total_steps": 40000, "loss": 0.703, "lr": 3.776876019689679e-07, "epoch": 1.209429613981179, "percentage": 94.46, "elapsed_time": "21:54:55", "remaining_time": "1:17:04", "throughput": 658.6, "total_tokens": 51960656} {"current_steps": 37790, "total_steps": 40000, "loss": 0.8646, "lr": 3.7598943858947743e-07, "epoch": 1.2095896549516676, "percentage": 94.47, "elapsed_time": "21:54:57", "remaining_time": "1:16:54", "throughput": 658.67, "total_tokens": 51967616} {"current_steps": 37795, "total_steps": 40000, "loss": 0.4808, "lr": 3.742950725418637e-07, "epoch": 1.209749695922156, "percentage": 94.49, "elapsed_time": "21:54:59", "remaining_time": "1:16:43", "throughput": 658.75, "total_tokens": 51974656} {"current_steps": 37800, "total_steps": 40000, "loss": 0.682, "lr": 3.726045040874093e-07, "epoch": 1.2099097368926446, "percentage": 94.5, "elapsed_time": "21:55:00", "remaining_time": "1:16:32", "throughput": 658.82, "total_tokens": 51981712} {"current_steps": 37800, "total_steps": 40000, "eval_loss": 0.7302023768424988, "epoch": 1.2099097368926446, "percentage": 94.5, "elapsed_time": "22:00:49", "remaining_time": "1:16:52", "throughput": 655.93, "total_tokens": 51981712} {"current_steps": 37805, "total_steps": 40000, "loss": 0.6445, "lr": 3.709177334868308e-07, "epoch": 1.2100697778631329, "percentage": 94.51, "elapsed_time": "22:00:52", "remaining_time": "1:16:41", "throughput": 655.98, "total_tokens": 51988448} {"current_steps": 37810, "total_steps": 40000, "loss": 0.9225, "lr": 3.692347610002478e-07, "epoch": 1.2102298188336214, "percentage": 94.53, "elapsed_time": "22:00:54", "remaining_time": "1:16:30", "throughput": 656.05, "total_tokens": 51994976} {"current_steps": 37815, "total_steps": 40000, "loss": 0.6587, "lr": 3.675555868871916e-07, "epoch": 1.2103898598041098, "percentage": 94.54, "elapsed_time": "22:00:56", "remaining_time": "1:16:19", "throughput": 656.12, "total_tokens": 52001776} {"current_steps": 37820, "total_steps": 40000, "loss": 0.757, "lr": 3.658802114066162e-07, "epoch": 1.2105499007745983, "percentage": 94.55, "elapsed_time": "22:00:58", "remaining_time": "1:16:08", "throughput": 656.19, "total_tokens": 52008688} {"current_steps": 37825, "total_steps": 40000, "loss": 0.4786, "lr": 3.6420863481688437e-07, "epoch": 1.2107099417450868, "percentage": 94.56, "elapsed_time": "22:00:59", "remaining_time": "1:15:57", "throughput": 656.26, "total_tokens": 52015312} {"current_steps": 37830, "total_steps": 40000, "loss": 0.5666, "lr": 3.625408573757705e-07, "epoch": 1.210869982715575, "percentage": 94.58, "elapsed_time": "22:01:01", "remaining_time": "1:15:46", "throughput": 656.33, "total_tokens": 52021792} {"current_steps": 37835, "total_steps": 40000, "loss": 0.827, "lr": 3.608768793404743e-07, "epoch": 1.2110300236860636, "percentage": 94.59, "elapsed_time": "22:01:03", "remaining_time": "1:15:35", "throughput": 656.41, "total_tokens": 52029088} {"current_steps": 37840, "total_steps": 40000, "loss": 0.7458, "lr": 3.592167009675934e-07, "epoch": 1.211190064656552, "percentage": 94.6, "elapsed_time": "22:01:05", "remaining_time": "1:15:24", "throughput": 656.48, "total_tokens": 52035792} {"current_steps": 37845, "total_steps": 40000, "loss": 0.5426, "lr": 3.575603225131563e-07, "epoch": 1.2113501056270406, "percentage": 94.61, "elapsed_time": "22:01:06", "remaining_time": "1:15:13", "throughput": 656.55, "total_tokens": 52042864} {"current_steps": 37850, "total_steps": 40000, "loss": 0.6208, "lr": 3.55907744232592e-07, "epoch": 1.2115101465975289, "percentage": 94.62, "elapsed_time": "22:01:08", "remaining_time": "1:15:02", "throughput": 656.62, "total_tokens": 52049376} {"current_steps": 37855, "total_steps": 40000, "loss": 0.7177, "lr": 3.5425896638075217e-07, "epoch": 1.2116701875680174, "percentage": 94.64, "elapsed_time": "22:01:10", "remaining_time": "1:14:51", "throughput": 656.69, "total_tokens": 52055936} {"current_steps": 37860, "total_steps": 40000, "loss": 0.5059, "lr": 3.5261398921189736e-07, "epoch": 1.2118302285385059, "percentage": 94.65, "elapsed_time": "22:01:11", "remaining_time": "1:14:40", "throughput": 656.76, "total_tokens": 52062560} {"current_steps": 37865, "total_steps": 40000, "loss": 0.6668, "lr": 3.509728129797024e-07, "epoch": 1.2119902695089944, "percentage": 94.66, "elapsed_time": "22:01:13", "remaining_time": "1:14:29", "throughput": 656.83, "total_tokens": 52069120} {"current_steps": 37870, "total_steps": 40000, "loss": 0.6279, "lr": 3.4933543793725656e-07, "epoch": 1.2121503104794829, "percentage": 94.67, "elapsed_time": "22:01:15", "remaining_time": "1:14:18", "throughput": 656.9, "total_tokens": 52075680} {"current_steps": 37875, "total_steps": 40000, "loss": 0.7227, "lr": 3.4770186433707163e-07, "epoch": 1.2123103514499711, "percentage": 94.69, "elapsed_time": "22:01:17", "remaining_time": "1:14:07", "throughput": 656.97, "total_tokens": 52082400} {"current_steps": 37880, "total_steps": 40000, "loss": 0.822, "lr": 3.4607209243105453e-07, "epoch": 1.2124703924204596, "percentage": 94.7, "elapsed_time": "22:01:18", "remaining_time": "1:13:56", "throughput": 657.04, "total_tokens": 52089488} {"current_steps": 37885, "total_steps": 40000, "loss": 0.6159, "lr": 3.444461224705431e-07, "epoch": 1.2126304333909481, "percentage": 94.71, "elapsed_time": "22:01:20", "remaining_time": "1:13:45", "throughput": 657.11, "total_tokens": 52096288} {"current_steps": 37890, "total_steps": 40000, "loss": 0.7841, "lr": 3.4282395470628116e-07, "epoch": 1.2127904743614366, "percentage": 94.73, "elapsed_time": "22:01:22", "remaining_time": "1:13:35", "throughput": 657.19, "total_tokens": 52103216} {"current_steps": 37895, "total_steps": 40000, "loss": 0.8845, "lr": 3.4120558938842417e-07, "epoch": 1.2129505153319249, "percentage": 94.74, "elapsed_time": "22:01:24", "remaining_time": "1:13:24", "throughput": 657.26, "total_tokens": 52110160} {"current_steps": 37900, "total_steps": 40000, "loss": 0.7658, "lr": 3.395910267665503e-07, "epoch": 1.2131105563024134, "percentage": 94.75, "elapsed_time": "22:01:25", "remaining_time": "1:13:13", "throughput": 657.33, "total_tokens": 52117040} {"current_steps": 37905, "total_steps": 40000, "loss": 0.861, "lr": 3.3798026708964094e-07, "epoch": 1.2132705972729019, "percentage": 94.76, "elapsed_time": "22:01:27", "remaining_time": "1:13:02", "throughput": 657.4, "total_tokens": 52123568} {"current_steps": 37910, "total_steps": 40000, "loss": 0.6161, "lr": 3.3637331060609456e-07, "epoch": 1.2134306382433904, "percentage": 94.77, "elapsed_time": "22:01:29", "remaining_time": "1:12:51", "throughput": 657.47, "total_tokens": 52130512} {"current_steps": 37915, "total_steps": 40000, "loss": 0.6721, "lr": 3.3477015756372966e-07, "epoch": 1.2135906792138789, "percentage": 94.79, "elapsed_time": "22:01:31", "remaining_time": "1:12:40", "throughput": 657.55, "total_tokens": 52137728} {"current_steps": 37920, "total_steps": 40000, "loss": 0.6395, "lr": 3.3317080820976785e-07, "epoch": 1.2137507201843671, "percentage": 94.8, "elapsed_time": "22:01:32", "remaining_time": "1:12:29", "throughput": 657.62, "total_tokens": 52144336} {"current_steps": 37925, "total_steps": 40000, "loss": 0.7818, "lr": 3.315752627908508e-07, "epoch": 1.2139107611548556, "percentage": 94.81, "elapsed_time": "22:01:34", "remaining_time": "1:12:18", "throughput": 657.69, "total_tokens": 52150864} {"current_steps": 37930, "total_steps": 40000, "loss": 0.6946, "lr": 3.299835215530317e-07, "epoch": 1.2140708021253441, "percentage": 94.83, "elapsed_time": "22:01:36", "remaining_time": "1:12:07", "throughput": 657.75, "total_tokens": 52157408} {"current_steps": 37935, "total_steps": 40000, "loss": 0.6732, "lr": 3.2839558474177245e-07, "epoch": 1.2142308430958326, "percentage": 94.84, "elapsed_time": "22:01:38", "remaining_time": "1:11:56", "throughput": 657.83, "total_tokens": 52164224} {"current_steps": 37940, "total_steps": 40000, "loss": 0.5904, "lr": 3.2681145260196056e-07, "epoch": 1.214390884066321, "percentage": 94.85, "elapsed_time": "22:01:39", "remaining_time": "1:11:45", "throughput": 657.9, "total_tokens": 52171088} {"current_steps": 37945, "total_steps": 40000, "loss": 0.5623, "lr": 3.252311253778839e-07, "epoch": 1.2145509250368094, "percentage": 94.86, "elapsed_time": "22:01:41", "remaining_time": "1:11:34", "throughput": 657.97, "total_tokens": 52178368} {"current_steps": 37950, "total_steps": 40000, "loss": 0.9524, "lr": 3.2365460331325034e-07, "epoch": 1.2147109660072979, "percentage": 94.88, "elapsed_time": "22:01:43", "remaining_time": "1:11:23", "throughput": 658.05, "total_tokens": 52185232} {"current_steps": 37955, "total_steps": 40000, "loss": 0.8039, "lr": 3.2208188665117934e-07, "epoch": 1.2148710069777864, "percentage": 94.89, "elapsed_time": "22:01:44", "remaining_time": "1:11:12", "throughput": 658.12, "total_tokens": 52192544} {"current_steps": 37960, "total_steps": 40000, "loss": 0.5603, "lr": 3.205129756342018e-07, "epoch": 1.2150310479482749, "percentage": 94.9, "elapsed_time": "22:01:46", "remaining_time": "1:11:02", "throughput": 658.2, "total_tokens": 52199520} {"current_steps": 37965, "total_steps": 40000, "loss": 0.7335, "lr": 3.189478705042659e-07, "epoch": 1.2151910889187632, "percentage": 94.91, "elapsed_time": "22:01:48", "remaining_time": "1:10:51", "throughput": 658.27, "total_tokens": 52206368} {"current_steps": 37970, "total_steps": 40000, "loss": 0.8643, "lr": 3.173865715027341e-07, "epoch": 1.2153511298892516, "percentage": 94.92, "elapsed_time": "22:01:50", "remaining_time": "1:10:40", "throughput": 658.34, "total_tokens": 52213072} {"current_steps": 37975, "total_steps": 40000, "loss": 0.8425, "lr": 3.158290788703694e-07, "epoch": 1.2155111708597401, "percentage": 94.94, "elapsed_time": "22:01:51", "remaining_time": "1:10:29", "throughput": 658.41, "total_tokens": 52219712} {"current_steps": 37980, "total_steps": 40000, "loss": 0.6681, "lr": 3.1427539284736297e-07, "epoch": 1.2156712118302284, "percentage": 94.95, "elapsed_time": "22:01:53", "remaining_time": "1:10:18", "throughput": 658.48, "total_tokens": 52226432} {"current_steps": 37985, "total_steps": 40000, "loss": 0.7013, "lr": 3.127255136733093e-07, "epoch": 1.215831252800717, "percentage": 94.96, "elapsed_time": "22:01:55", "remaining_time": "1:10:07", "throughput": 658.55, "total_tokens": 52232960} {"current_steps": 37990, "total_steps": 40000, "loss": 0.5435, "lr": 3.1117944158722544e-07, "epoch": 1.2159912937712054, "percentage": 94.97, "elapsed_time": "22:01:57", "remaining_time": "1:09:56", "throughput": 658.62, "total_tokens": 52240192} {"current_steps": 37995, "total_steps": 40000, "loss": 0.784, "lr": 3.0963717682752635e-07, "epoch": 1.216151334741694, "percentage": 94.99, "elapsed_time": "22:01:58", "remaining_time": "1:09:45", "throughput": 658.7, "total_tokens": 52247584} {"current_steps": 38000, "total_steps": 40000, "loss": 0.6585, "lr": 3.080987196320578e-07, "epoch": 1.2163113757121824, "percentage": 95.0, "elapsed_time": "22:02:00", "remaining_time": "1:09:34", "throughput": 658.77, "total_tokens": 52254352} {"current_steps": 38000, "total_steps": 40000, "eval_loss": 0.7302348613739014, "epoch": 1.2163113757121824, "percentage": 95.0, "elapsed_time": "22:07:48", "remaining_time": "1:09:53", "throughput": 655.9, "total_tokens": 52254352} {"current_steps": 38005, "total_steps": 40000, "loss": 0.7484, "lr": 3.065640702380607e-07, "epoch": 1.2164714166826707, "percentage": 95.01, "elapsed_time": "22:07:52", "remaining_time": "1:09:42", "throughput": 655.95, "total_tokens": 52261024} {"current_steps": 38010, "total_steps": 40000, "loss": 0.6251, "lr": 3.050332288822011e-07, "epoch": 1.2166314576531592, "percentage": 95.03, "elapsed_time": "22:07:53", "remaining_time": "1:09:31", "throughput": 656.02, "total_tokens": 52267696} {"current_steps": 38015, "total_steps": 40000, "loss": 0.6853, "lr": 3.035061958005542e-07, "epoch": 1.2167914986236477, "percentage": 95.04, "elapsed_time": "22:07:55", "remaining_time": "1:09:20", "throughput": 656.09, "total_tokens": 52274736} {"current_steps": 38020, "total_steps": 40000, "loss": 0.7561, "lr": 3.019829712286093e-07, "epoch": 1.2169515395941362, "percentage": 95.05, "elapsed_time": "22:07:57", "remaining_time": "1:09:09", "throughput": 656.17, "total_tokens": 52281616} {"current_steps": 38025, "total_steps": 40000, "loss": 0.7684, "lr": 3.004635554012647e-07, "epoch": 1.2171115805646244, "percentage": 95.06, "elapsed_time": "22:07:59", "remaining_time": "1:08:58", "throughput": 656.23, "total_tokens": 52288064} {"current_steps": 38030, "total_steps": 40000, "loss": 0.8071, "lr": 2.9894794855283017e-07, "epoch": 1.217271621535113, "percentage": 95.08, "elapsed_time": "22:08:00", "remaining_time": "1:08:47", "throughput": 656.31, "total_tokens": 52295056} {"current_steps": 38035, "total_steps": 40000, "loss": 0.6398, "lr": 2.9743615091703816e-07, "epoch": 1.2174316625056014, "percentage": 95.09, "elapsed_time": "22:08:02", "remaining_time": "1:08:36", "throughput": 656.38, "total_tokens": 52302032} {"current_steps": 38040, "total_steps": 40000, "loss": 0.5072, "lr": 2.959281627270216e-07, "epoch": 1.21759170347609, "percentage": 95.1, "elapsed_time": "22:08:04", "remaining_time": "1:08:25", "throughput": 656.45, "total_tokens": 52309024} {"current_steps": 38045, "total_steps": 40000, "loss": 0.5928, "lr": 2.944239842153362e-07, "epoch": 1.2177517444465784, "percentage": 95.11, "elapsed_time": "22:08:06", "remaining_time": "1:08:14", "throughput": 656.52, "total_tokens": 52315616} {"current_steps": 38050, "total_steps": 40000, "loss": 0.9158, "lr": 2.929236156139381e-07, "epoch": 1.2179117854170667, "percentage": 95.12, "elapsed_time": "22:08:07", "remaining_time": "1:08:03", "throughput": 656.59, "total_tokens": 52322512} {"current_steps": 38055, "total_steps": 40000, "loss": 0.8233, "lr": 2.9142705715420883e-07, "epoch": 1.2180718263875552, "percentage": 95.14, "elapsed_time": "22:08:09", "remaining_time": "1:07:52", "throughput": 656.67, "total_tokens": 52329392} {"current_steps": 38060, "total_steps": 40000, "loss": 0.7987, "lr": 2.8993430906693595e-07, "epoch": 1.2182318673580437, "percentage": 95.15, "elapsed_time": "22:08:11", "remaining_time": "1:07:42", "throughput": 656.74, "total_tokens": 52336096} {"current_steps": 38065, "total_steps": 40000, "loss": 0.8703, "lr": 2.88445371582316e-07, "epoch": 1.2183919083285322, "percentage": 95.16, "elapsed_time": "22:08:12", "remaining_time": "1:07:31", "throughput": 656.81, "total_tokens": 52343008} {"current_steps": 38070, "total_steps": 40000, "loss": 0.7636, "lr": 2.8696024492996796e-07, "epoch": 1.2185519492990204, "percentage": 95.17, "elapsed_time": "22:08:14", "remaining_time": "1:07:20", "throughput": 656.88, "total_tokens": 52349712} {"current_steps": 38075, "total_steps": 40000, "loss": 0.9491, "lr": 2.854789293389115e-07, "epoch": 1.218711990269509, "percentage": 95.19, "elapsed_time": "22:08:16", "remaining_time": "1:07:09", "throughput": 656.95, "total_tokens": 52356608} {"current_steps": 38080, "total_steps": 40000, "loss": 0.7224, "lr": 2.8400142503758606e-07, "epoch": 1.2188720312399974, "percentage": 95.2, "elapsed_time": "22:08:18", "remaining_time": "1:06:58", "throughput": 657.02, "total_tokens": 52363440} {"current_steps": 38085, "total_steps": 40000, "loss": 0.7525, "lr": 2.8252773225384276e-07, "epoch": 1.219032072210486, "percentage": 95.21, "elapsed_time": "22:08:19", "remaining_time": "1:06:47", "throughput": 657.09, "total_tokens": 52370224} {"current_steps": 38090, "total_steps": 40000, "loss": 0.8347, "lr": 2.8105785121494143e-07, "epoch": 1.2191921131809744, "percentage": 95.23, "elapsed_time": "22:08:21", "remaining_time": "1:06:36", "throughput": 657.17, "total_tokens": 52377200} {"current_steps": 38095, "total_steps": 40000, "loss": 0.5928, "lr": 2.795917821475563e-07, "epoch": 1.2193521541514627, "percentage": 95.24, "elapsed_time": "22:08:23", "remaining_time": "1:06:25", "throughput": 657.24, "total_tokens": 52384016} {"current_steps": 38100, "total_steps": 40000, "loss": 0.767, "lr": 2.78129525277776e-07, "epoch": 1.2195121951219512, "percentage": 95.25, "elapsed_time": "22:08:25", "remaining_time": "1:06:14", "throughput": 657.31, "total_tokens": 52391184} {"current_steps": 38105, "total_steps": 40000, "loss": 0.6755, "lr": 2.766710808310952e-07, "epoch": 1.2196722360924397, "percentage": 95.26, "elapsed_time": "22:08:26", "remaining_time": "1:06:03", "throughput": 657.39, "total_tokens": 52398416} {"current_steps": 38110, "total_steps": 40000, "loss": 0.8066, "lr": 2.7521644903242827e-07, "epoch": 1.2198322770629282, "percentage": 95.28, "elapsed_time": "22:08:28", "remaining_time": "1:05:53", "throughput": 657.46, "total_tokens": 52405024} {"current_steps": 38115, "total_steps": 40000, "loss": 0.6198, "lr": 2.7376563010609593e-07, "epoch": 1.2199923180334165, "percentage": 95.29, "elapsed_time": "22:08:30", "remaining_time": "1:05:42", "throughput": 657.53, "total_tokens": 52411856} {"current_steps": 38120, "total_steps": 40000, "loss": 0.7101, "lr": 2.72318624275833e-07, "epoch": 1.220152359003905, "percentage": 95.3, "elapsed_time": "22:08:32", "remaining_time": "1:05:31", "throughput": 657.6, "total_tokens": 52418608} {"current_steps": 38125, "total_steps": 40000, "loss": 0.7109, "lr": 2.7087543176478324e-07, "epoch": 1.2203123999743934, "percentage": 95.31, "elapsed_time": "22:08:33", "remaining_time": "1:05:20", "throughput": 657.68, "total_tokens": 52425920} {"current_steps": 38130, "total_steps": 40000, "loss": 0.7815, "lr": 2.694360527955103e-07, "epoch": 1.220472440944882, "percentage": 95.33, "elapsed_time": "22:08:35", "remaining_time": "1:05:09", "throughput": 657.75, "total_tokens": 52432816} {"current_steps": 38135, "total_steps": 40000, "loss": 0.727, "lr": 2.680004875899811e-07, "epoch": 1.2206324819153704, "percentage": 95.34, "elapsed_time": "22:08:37", "remaining_time": "1:04:58", "throughput": 657.82, "total_tokens": 52440000} {"current_steps": 38140, "total_steps": 40000, "loss": 0.7222, "lr": 2.665687363695768e-07, "epoch": 1.2207925228858587, "percentage": 95.35, "elapsed_time": "22:08:39", "remaining_time": "1:04:47", "throughput": 657.89, "total_tokens": 52446672} {"current_steps": 38145, "total_steps": 40000, "loss": 0.7915, "lr": 2.6514079935509584e-07, "epoch": 1.2209525638563472, "percentage": 95.36, "elapsed_time": "22:08:40", "remaining_time": "1:04:36", "throughput": 657.98, "total_tokens": 52454704} {"current_steps": 38150, "total_steps": 40000, "loss": 0.7552, "lr": 2.6371667676673983e-07, "epoch": 1.2211126048268357, "percentage": 95.38, "elapsed_time": "22:08:42", "remaining_time": "1:04:25", "throughput": 658.06, "total_tokens": 52461840} {"current_steps": 38155, "total_steps": 40000, "loss": 0.5313, "lr": 2.6229636882412755e-07, "epoch": 1.2212726457973242, "percentage": 95.39, "elapsed_time": "22:08:44", "remaining_time": "1:04:15", "throughput": 658.13, "total_tokens": 52468624} {"current_steps": 38160, "total_steps": 40000, "loss": 0.7008, "lr": 2.6087987574628935e-07, "epoch": 1.2214326867678125, "percentage": 95.4, "elapsed_time": "22:08:45", "remaining_time": "1:04:04", "throughput": 658.2, "total_tokens": 52475584} {"current_steps": 38165, "total_steps": 40000, "loss": 0.6443, "lr": 2.5946719775166437e-07, "epoch": 1.221592727738301, "percentage": 95.41, "elapsed_time": "22:08:47", "remaining_time": "1:03:53", "throughput": 658.27, "total_tokens": 52482160} {"current_steps": 38170, "total_steps": 40000, "loss": 0.8282, "lr": 2.5805833505810616e-07, "epoch": 1.2217527687087895, "percentage": 95.43, "elapsed_time": "22:08:49", "remaining_time": "1:03:42", "throughput": 658.34, "total_tokens": 52489072} {"current_steps": 38175, "total_steps": 40000, "loss": 0.6461, "lr": 2.566532878828798e-07, "epoch": 1.221912809679278, "percentage": 95.44, "elapsed_time": "22:08:51", "remaining_time": "1:03:31", "throughput": 658.41, "total_tokens": 52495808} {"current_steps": 38180, "total_steps": 40000, "loss": 0.6313, "lr": 2.552520564426619e-07, "epoch": 1.2220728506497665, "percentage": 95.45, "elapsed_time": "22:08:52", "remaining_time": "1:03:20", "throughput": 658.48, "total_tokens": 52502560} {"current_steps": 38185, "total_steps": 40000, "loss": 0.7961, "lr": 2.5385464095353803e-07, "epoch": 1.2222328916202547, "percentage": 95.46, "elapsed_time": "22:08:54", "remaining_time": "1:03:09", "throughput": 658.55, "total_tokens": 52509184} {"current_steps": 38190, "total_steps": 40000, "loss": 0.5897, "lr": 2.5246104163100804e-07, "epoch": 1.2223929325907432, "percentage": 95.47, "elapsed_time": "22:08:56", "remaining_time": "1:02:59", "throughput": 658.62, "total_tokens": 52515632} {"current_steps": 38195, "total_steps": 40000, "loss": 0.6494, "lr": 2.510712586899833e-07, "epoch": 1.2225529735612317, "percentage": 95.49, "elapsed_time": "22:08:58", "remaining_time": "1:02:48", "throughput": 658.68, "total_tokens": 52522272} {"current_steps": 38200, "total_steps": 40000, "loss": 0.7149, "lr": 2.4968529234478124e-07, "epoch": 1.2227130145317202, "percentage": 95.5, "elapsed_time": "22:08:59", "remaining_time": "1:02:37", "throughput": 658.76, "total_tokens": 52529584} {"current_steps": 38200, "total_steps": 40000, "eval_loss": 0.7299951910972595, "epoch": 1.2227130145317202, "percentage": 95.5, "elapsed_time": "22:14:48", "remaining_time": "1:02:53", "throughput": 655.89, "total_tokens": 52529584} {"current_steps": 38205, "total_steps": 40000, "loss": 0.7406, "lr": 2.483031428091448e-07, "epoch": 1.2228730555022085, "percentage": 95.51, "elapsed_time": "22:14:52", "remaining_time": "1:02:42", "throughput": 655.95, "total_tokens": 52536192} {"current_steps": 38210, "total_steps": 40000, "loss": 0.4262, "lr": 2.469248102962091e-07, "epoch": 1.223033096472697, "percentage": 95.53, "elapsed_time": "22:14:53", "remaining_time": "1:02:32", "throughput": 656.03, "total_tokens": 52543824} {"current_steps": 38215, "total_steps": 40000, "loss": 0.7802, "lr": 2.4555029501853455e-07, "epoch": 1.2231931374431855, "percentage": 95.54, "elapsed_time": "22:14:55", "remaining_time": "1:02:21", "throughput": 656.11, "total_tokens": 52551280} {"current_steps": 38220, "total_steps": 40000, "loss": 0.6146, "lr": 2.441795971880906e-07, "epoch": 1.223353178413674, "percentage": 95.55, "elapsed_time": "22:14:57", "remaining_time": "1:02:10", "throughput": 656.17, "total_tokens": 52557824} {"current_steps": 38225, "total_steps": 40000, "loss": 0.8259, "lr": 2.4281271701625255e-07, "epoch": 1.2235132193841625, "percentage": 95.56, "elapsed_time": "22:14:59", "remaining_time": "1:01:59", "throughput": 656.25, "total_tokens": 52565184} {"current_steps": 38230, "total_steps": 40000, "loss": 0.8976, "lr": 2.4144965471381007e-07, "epoch": 1.2236732603546507, "percentage": 95.58, "elapsed_time": "22:15:00", "remaining_time": "1:01:48", "throughput": 656.32, "total_tokens": 52572112} {"current_steps": 38235, "total_steps": 40000, "loss": 0.8775, "lr": 2.400904104909674e-07, "epoch": 1.2238333013251392, "percentage": 95.59, "elapsed_time": "22:15:02", "remaining_time": "1:01:37", "throughput": 656.4, "total_tokens": 52579024} {"current_steps": 38240, "total_steps": 40000, "loss": 0.7782, "lr": 2.3873498455733725e-07, "epoch": 1.2239933422956277, "percentage": 95.6, "elapsed_time": "22:15:04", "remaining_time": "1:01:26", "throughput": 656.47, "total_tokens": 52585904} {"current_steps": 38245, "total_steps": 40000, "loss": 0.7498, "lr": 2.3738337712194137e-07, "epoch": 1.224153383266116, "percentage": 95.61, "elapsed_time": "22:15:06", "remaining_time": "1:01:15", "throughput": 656.54, "total_tokens": 52592768} {"current_steps": 38250, "total_steps": 40000, "loss": 0.5463, "lr": 2.3603558839321305e-07, "epoch": 1.2243134242366045, "percentage": 95.62, "elapsed_time": "22:15:07", "remaining_time": "1:01:05", "throughput": 656.61, "total_tokens": 52599856} {"current_steps": 38255, "total_steps": 40000, "loss": 0.6952, "lr": 2.3469161857900267e-07, "epoch": 1.224473465207093, "percentage": 95.64, "elapsed_time": "22:15:09", "remaining_time": "1:00:54", "throughput": 656.68, "total_tokens": 52606672} {"current_steps": 38260, "total_steps": 40000, "loss": 0.7033, "lr": 2.3335146788656393e-07, "epoch": 1.2246335061775815, "percentage": 95.65, "elapsed_time": "22:15:11", "remaining_time": "1:00:43", "throughput": 656.75, "total_tokens": 52613216} {"current_steps": 38265, "total_steps": 40000, "loss": 0.6341, "lr": 2.3201513652256757e-07, "epoch": 1.22479354714807, "percentage": 95.66, "elapsed_time": "22:15:12", "remaining_time": "1:00:32", "throughput": 656.82, "total_tokens": 52619792} {"current_steps": 38270, "total_steps": 40000, "loss": 0.4951, "lr": 2.3068262469308766e-07, "epoch": 1.2249535881185583, "percentage": 95.67, "elapsed_time": "22:15:14", "remaining_time": "1:00:21", "throughput": 656.89, "total_tokens": 52626880} {"current_steps": 38275, "total_steps": 40000, "loss": 0.6631, "lr": 2.2935393260362093e-07, "epoch": 1.2251136290890468, "percentage": 95.69, "elapsed_time": "22:15:16", "remaining_time": "1:00:10", "throughput": 656.96, "total_tokens": 52633392} {"current_steps": 38280, "total_steps": 40000, "loss": 0.8657, "lr": 2.2802906045906458e-07, "epoch": 1.2252736700595352, "percentage": 95.7, "elapsed_time": "22:15:18", "remaining_time": "0:59:59", "throughput": 657.04, "total_tokens": 52640528} {"current_steps": 38285, "total_steps": 40000, "loss": 0.8953, "lr": 2.2670800846373018e-07, "epoch": 1.2254337110300237, "percentage": 95.71, "elapsed_time": "22:15:19", "remaining_time": "0:59:49", "throughput": 657.11, "total_tokens": 52647248} {"current_steps": 38290, "total_steps": 40000, "loss": 0.6488, "lr": 2.2539077682134367e-07, "epoch": 1.225593752000512, "percentage": 95.73, "elapsed_time": "22:15:21", "remaining_time": "0:59:38", "throughput": 657.17, "total_tokens": 52653840} {"current_steps": 38295, "total_steps": 40000, "loss": 0.62, "lr": 2.2407736573503423e-07, "epoch": 1.2257537929710005, "percentage": 95.74, "elapsed_time": "22:15:23", "remaining_time": "0:59:27", "throughput": 657.25, "total_tokens": 52661376} {"current_steps": 38300, "total_steps": 40000, "loss": 0.6383, "lr": 2.2276777540735093e-07, "epoch": 1.225913833941489, "percentage": 95.75, "elapsed_time": "22:15:25", "remaining_time": "0:59:16", "throughput": 657.32, "total_tokens": 52668064} {"current_steps": 38305, "total_steps": 40000, "loss": 0.8335, "lr": 2.2146200604024613e-07, "epoch": 1.2260738749119775, "percentage": 95.76, "elapsed_time": "22:15:26", "remaining_time": "0:59:05", "throughput": 657.39, "total_tokens": 52674656} {"current_steps": 38310, "total_steps": 40000, "loss": 0.7218, "lr": 2.2016005783508375e-07, "epoch": 1.226233915882466, "percentage": 95.78, "elapsed_time": "22:15:28", "remaining_time": "0:58:54", "throughput": 657.46, "total_tokens": 52681296} {"current_steps": 38315, "total_steps": 40000, "loss": 0.7052, "lr": 2.1886193099264763e-07, "epoch": 1.2263939568529543, "percentage": 95.79, "elapsed_time": "22:15:30", "remaining_time": "0:58:43", "throughput": 657.53, "total_tokens": 52688176} {"current_steps": 38320, "total_steps": 40000, "loss": 0.6586, "lr": 2.175676257131165e-07, "epoch": 1.2265539978234428, "percentage": 95.8, "elapsed_time": "22:15:32", "remaining_time": "0:58:33", "throughput": 657.61, "total_tokens": 52695424} {"current_steps": 38325, "total_steps": 40000, "loss": 0.9763, "lr": 2.162771421960974e-07, "epoch": 1.2267140387939313, "percentage": 95.81, "elapsed_time": "22:15:33", "remaining_time": "0:58:22", "throughput": 657.68, "total_tokens": 52702320} {"current_steps": 38330, "total_steps": 40000, "loss": 0.6098, "lr": 2.1499048064059224e-07, "epoch": 1.2268740797644198, "percentage": 95.83, "elapsed_time": "22:15:35", "remaining_time": "0:58:11", "throughput": 657.75, "total_tokens": 52709360} {"current_steps": 38335, "total_steps": 40000, "loss": 0.8031, "lr": 2.1370764124502285e-07, "epoch": 1.227034120734908, "percentage": 95.84, "elapsed_time": "22:15:37", "remaining_time": "0:58:00", "throughput": 657.82, "total_tokens": 52716336} {"current_steps": 38340, "total_steps": 40000, "loss": 0.5304, "lr": 2.1242862420721988e-07, "epoch": 1.2271941617053965, "percentage": 95.85, "elapsed_time": "22:15:39", "remaining_time": "0:57:49", "throughput": 657.89, "total_tokens": 52723024} {"current_steps": 38345, "total_steps": 40000, "loss": 0.8503, "lr": 2.1115342972442276e-07, "epoch": 1.227354202675885, "percentage": 95.86, "elapsed_time": "22:15:40", "remaining_time": "0:57:38", "throughput": 657.96, "total_tokens": 52729696} {"current_steps": 38350, "total_steps": 40000, "loss": 0.7281, "lr": 2.0988205799328252e-07, "epoch": 1.2275142436463735, "percentage": 95.88, "elapsed_time": "22:15:42", "remaining_time": "0:57:28", "throughput": 658.03, "total_tokens": 52736464} {"current_steps": 38355, "total_steps": 40000, "loss": 0.666, "lr": 2.0861450920986182e-07, "epoch": 1.227674284616862, "percentage": 95.89, "elapsed_time": "22:15:44", "remaining_time": "0:57:17", "throughput": 658.11, "total_tokens": 52743648} {"current_steps": 38360, "total_steps": 40000, "loss": 0.7416, "lr": 2.07350783569632e-07, "epoch": 1.2278343255873503, "percentage": 95.9, "elapsed_time": "22:15:46", "remaining_time": "0:57:06", "throughput": 658.18, "total_tokens": 52750560} {"current_steps": 38365, "total_steps": 40000, "loss": 0.7788, "lr": 2.060908812674761e-07, "epoch": 1.2279943665578388, "percentage": 95.91, "elapsed_time": "22:15:47", "remaining_time": "0:56:55", "throughput": 658.25, "total_tokens": 52757328} {"current_steps": 38370, "total_steps": 40000, "loss": 0.7317, "lr": 2.0483480249768317e-07, "epoch": 1.2281544075283273, "percentage": 95.93, "elapsed_time": "22:15:49", "remaining_time": "0:56:44", "throughput": 658.32, "total_tokens": 52764176} {"current_steps": 38375, "total_steps": 40000, "loss": 0.9164, "lr": 2.035825474539621e-07, "epoch": 1.2283144484988158, "percentage": 95.94, "elapsed_time": "22:15:51", "remaining_time": "0:56:34", "throughput": 658.4, "total_tokens": 52771248} {"current_steps": 38380, "total_steps": 40000, "loss": 0.6192, "lr": 2.0233411632942235e-07, "epoch": 1.228474489469304, "percentage": 95.95, "elapsed_time": "22:15:52", "remaining_time": "0:56:23", "throughput": 658.46, "total_tokens": 52777664} {"current_steps": 38385, "total_steps": 40000, "loss": 0.688, "lr": 2.0108950931658764e-07, "epoch": 1.2286345304397925, "percentage": 95.96, "elapsed_time": "22:15:54", "remaining_time": "0:56:12", "throughput": 658.53, "total_tokens": 52784096} {"current_steps": 38390, "total_steps": 40000, "loss": 0.6006, "lr": 1.998487266073934e-07, "epoch": 1.228794571410281, "percentage": 95.97, "elapsed_time": "22:15:56", "remaining_time": "0:56:01", "throughput": 658.59, "total_tokens": 52790416} {"current_steps": 38395, "total_steps": 40000, "loss": 0.6675, "lr": 1.986117683931865e-07, "epoch": 1.2289546123807695, "percentage": 95.99, "elapsed_time": "22:15:58", "remaining_time": "0:55:50", "throughput": 658.66, "total_tokens": 52796944} {"current_steps": 38400, "total_steps": 40000, "loss": 0.892, "lr": 1.9737863486471442e-07, "epoch": 1.229114653351258, "percentage": 96.0, "elapsed_time": "22:15:59", "remaining_time": "0:55:39", "throughput": 658.73, "total_tokens": 52803776} {"current_steps": 38400, "total_steps": 40000, "eval_loss": 0.7298663258552551, "epoch": 1.229114653351258, "percentage": 96.0, "elapsed_time": "22:21:48", "remaining_time": "0:55:54", "throughput": 655.88, "total_tokens": 52803776} {"current_steps": 38405, "total_steps": 40000, "loss": 0.6227, "lr": 1.9614932621215e-07, "epoch": 1.2292746943217463, "percentage": 96.01, "elapsed_time": "22:21:51", "remaining_time": "0:55:43", "throughput": 655.94, "total_tokens": 52810624} {"current_steps": 38410, "total_steps": 40000, "loss": 0.6883, "lr": 1.9492384262506102e-07, "epoch": 1.2294347352922348, "percentage": 96.03, "elapsed_time": "22:21:53", "remaining_time": "0:55:32", "throughput": 656.0, "total_tokens": 52817376} {"current_steps": 38415, "total_steps": 40000, "loss": 0.88, "lr": 1.9370218429243524e-07, "epoch": 1.2295947762627233, "percentage": 96.04, "elapsed_time": "22:21:55", "remaining_time": "0:55:22", "throughput": 656.07, "total_tokens": 52824080} {"current_steps": 38420, "total_steps": 40000, "loss": 0.6953, "lr": 1.9248435140267197e-07, "epoch": 1.2297548172332118, "percentage": 96.05, "elapsed_time": "22:21:57", "remaining_time": "0:55:11", "throughput": 656.15, "total_tokens": 52830960} {"current_steps": 38425, "total_steps": 40000, "loss": 0.6032, "lr": 1.9127034414356814e-07, "epoch": 1.2299148582037, "percentage": 96.06, "elapsed_time": "22:21:58", "remaining_time": "0:55:00", "throughput": 656.22, "total_tokens": 52837728} {"current_steps": 38430, "total_steps": 40000, "loss": 0.7764, "lr": 1.9006016270234627e-07, "epoch": 1.2300748991741886, "percentage": 96.08, "elapsed_time": "22:22:00", "remaining_time": "0:54:49", "throughput": 656.28, "total_tokens": 52844272} {"current_steps": 38435, "total_steps": 40000, "loss": 0.7882, "lr": 1.888538072656293e-07, "epoch": 1.230234940144677, "percentage": 96.09, "elapsed_time": "22:22:02", "remaining_time": "0:54:38", "throughput": 656.35, "total_tokens": 52851152} {"current_steps": 38440, "total_steps": 40000, "loss": 0.5221, "lr": 1.8765127801944893e-07, "epoch": 1.2303949811151655, "percentage": 96.1, "elapsed_time": "22:22:04", "remaining_time": "0:54:27", "throughput": 656.43, "total_tokens": 52858096} {"current_steps": 38445, "total_steps": 40000, "loss": 0.777, "lr": 1.8645257514925406e-07, "epoch": 1.230555022085654, "percentage": 96.11, "elapsed_time": "22:22:05", "remaining_time": "0:54:17", "throughput": 656.49, "total_tokens": 52864816} {"current_steps": 38450, "total_steps": 40000, "loss": 0.7025, "lr": 1.8525769883989685e-07, "epoch": 1.2307150630561423, "percentage": 96.12, "elapsed_time": "22:22:07", "remaining_time": "0:54:06", "throughput": 656.57, "total_tokens": 52871872} {"current_steps": 38455, "total_steps": 40000, "loss": 0.6313, "lr": 1.8406664927564654e-07, "epoch": 1.2308751040266308, "percentage": 96.14, "elapsed_time": "22:22:09", "remaining_time": "0:53:55", "throughput": 656.64, "total_tokens": 52878768} {"current_steps": 38460, "total_steps": 40000, "loss": 0.7245, "lr": 1.8287942664017566e-07, "epoch": 1.2310351449971193, "percentage": 96.15, "elapsed_time": "22:22:11", "remaining_time": "0:53:44", "throughput": 656.71, "total_tokens": 52885568} {"current_steps": 38465, "total_steps": 40000, "loss": 0.9462, "lr": 1.8169603111656552e-07, "epoch": 1.2311951859676078, "percentage": 96.16, "elapsed_time": "22:22:12", "remaining_time": "0:53:33", "throughput": 656.78, "total_tokens": 52892512} {"current_steps": 38470, "total_steps": 40000, "loss": 0.7443, "lr": 1.805164628873146e-07, "epoch": 1.231355226938096, "percentage": 96.17, "elapsed_time": "22:22:14", "remaining_time": "0:53:22", "throughput": 656.86, "total_tokens": 52900048} {"current_steps": 38475, "total_steps": 40000, "loss": 0.6904, "lr": 1.793407221343274e-07, "epoch": 1.2315152679085846, "percentage": 96.19, "elapsed_time": "22:22:16", "remaining_time": "0:53:12", "throughput": 656.93, "total_tokens": 52907104} {"current_steps": 38480, "total_steps": 40000, "loss": 0.7082, "lr": 1.781688090389172e-07, "epoch": 1.231675308879073, "percentage": 96.2, "elapsed_time": "22:22:18", "remaining_time": "0:53:01", "throughput": 657.01, "total_tokens": 52914048} {"current_steps": 38485, "total_steps": 40000, "loss": 0.6933, "lr": 1.770007237818061e-07, "epoch": 1.2318353498495616, "percentage": 96.21, "elapsed_time": "22:22:19", "remaining_time": "0:52:50", "throughput": 657.08, "total_tokens": 52920896} {"current_steps": 38490, "total_steps": 40000, "loss": 0.4655, "lr": 1.7583646654313059e-07, "epoch": 1.23199539082005, "percentage": 96.23, "elapsed_time": "22:22:21", "remaining_time": "0:52:39", "throughput": 657.14, "total_tokens": 52927408} {"current_steps": 38495, "total_steps": 40000, "loss": 0.6873, "lr": 1.7467603750242757e-07, "epoch": 1.2321554317905383, "percentage": 96.24, "elapsed_time": "22:22:23", "remaining_time": "0:52:28", "throughput": 657.21, "total_tokens": 52934128} {"current_steps": 38500, "total_steps": 40000, "loss": 0.7385, "lr": 1.7351943683865944e-07, "epoch": 1.2323154727610268, "percentage": 96.25, "elapsed_time": "22:22:25", "remaining_time": "0:52:18", "throughput": 657.28, "total_tokens": 52940416} {"current_steps": 38505, "total_steps": 40000, "loss": 0.6222, "lr": 1.723666647301808e-07, "epoch": 1.2324755137315153, "percentage": 96.26, "elapsed_time": "22:22:26", "remaining_time": "0:52:07", "throughput": 657.35, "total_tokens": 52947040} {"current_steps": 38510, "total_steps": 40000, "loss": 0.57, "lr": 1.712177213547661e-07, "epoch": 1.2326355547020036, "percentage": 96.28, "elapsed_time": "22:22:28", "remaining_time": "0:51:56", "throughput": 657.42, "total_tokens": 52953872} {"current_steps": 38515, "total_steps": 40000, "loss": 0.6959, "lr": 1.7007260688959581e-07, "epoch": 1.232795595672492, "percentage": 96.29, "elapsed_time": "22:22:30", "remaining_time": "0:51:45", "throughput": 657.49, "total_tokens": 52960720} {"current_steps": 38520, "total_steps": 40000, "loss": 0.4894, "lr": 1.68931321511262e-07, "epoch": 1.2329556366429806, "percentage": 96.3, "elapsed_time": "22:22:31", "remaining_time": "0:51:34", "throughput": 657.56, "total_tokens": 52967440} {"current_steps": 38525, "total_steps": 40000, "loss": 0.7842, "lr": 1.6779386539576835e-07, "epoch": 1.233115677613469, "percentage": 96.31, "elapsed_time": "22:22:33", "remaining_time": "0:51:24", "throughput": 657.63, "total_tokens": 52974704} {"current_steps": 38530, "total_steps": 40000, "loss": 0.4926, "lr": 1.666602387185162e-07, "epoch": 1.2332757185839576, "percentage": 96.33, "elapsed_time": "22:22:35", "remaining_time": "0:51:13", "throughput": 657.7, "total_tokens": 52981408} {"current_steps": 38535, "total_steps": 40000, "loss": 0.7908, "lr": 1.655304416543352e-07, "epoch": 1.2334357595544458, "percentage": 96.34, "elapsed_time": "22:22:37", "remaining_time": "0:51:02", "throughput": 657.77, "total_tokens": 52988368} {"current_steps": 38540, "total_steps": 40000, "loss": 0.6308, "lr": 1.6440447437744698e-07, "epoch": 1.2335958005249343, "percentage": 96.35, "elapsed_time": "22:22:38", "remaining_time": "0:50:51", "throughput": 657.84, "total_tokens": 52995152} {"current_steps": 38545, "total_steps": 40000, "loss": 0.955, "lr": 1.6328233706149332e-07, "epoch": 1.2337558414954228, "percentage": 96.36, "elapsed_time": "22:22:40", "remaining_time": "0:50:41", "throughput": 657.92, "total_tokens": 53002160} {"current_steps": 38550, "total_steps": 40000, "loss": 0.8413, "lr": 1.6216402987951906e-07, "epoch": 1.2339158824659113, "percentage": 96.38, "elapsed_time": "22:22:42", "remaining_time": "0:50:30", "throughput": 657.98, "total_tokens": 53008496} {"current_steps": 38555, "total_steps": 40000, "loss": 0.8148, "lr": 1.6104955300398627e-07, "epoch": 1.2340759234363996, "percentage": 96.39, "elapsed_time": "22:22:44", "remaining_time": "0:50:19", "throughput": 658.05, "total_tokens": 53015296} {"current_steps": 38560, "total_steps": 40000, "loss": 1.0192, "lr": 1.5993890660675748e-07, "epoch": 1.234235964406888, "percentage": 96.4, "elapsed_time": "22:22:45", "remaining_time": "0:50:08", "throughput": 658.12, "total_tokens": 53022272} {"current_steps": 38565, "total_steps": 40000, "loss": 0.4185, "lr": 1.5883209085910678e-07, "epoch": 1.2343960053773766, "percentage": 96.41, "elapsed_time": "22:22:47", "remaining_time": "0:49:57", "throughput": 658.2, "total_tokens": 53029616} {"current_steps": 38570, "total_steps": 40000, "loss": 0.9269, "lr": 1.5772910593172264e-07, "epoch": 1.234556046347865, "percentage": 96.43, "elapsed_time": "22:22:49", "remaining_time": "0:49:47", "throughput": 658.28, "total_tokens": 53036816} {"current_steps": 38575, "total_steps": 40000, "loss": 0.9197, "lr": 1.5662995199469954e-07, "epoch": 1.2347160873183536, "percentage": 96.44, "elapsed_time": "22:22:51", "remaining_time": "0:49:36", "throughput": 658.35, "total_tokens": 53043968} {"current_steps": 38580, "total_steps": 40000, "loss": 0.7013, "lr": 1.5553462921753802e-07, "epoch": 1.2348761282888419, "percentage": 96.45, "elapsed_time": "22:22:52", "remaining_time": "0:49:25", "throughput": 658.43, "total_tokens": 53051184} {"current_steps": 38585, "total_steps": 40000, "loss": 0.7127, "lr": 1.544431377691502e-07, "epoch": 1.2350361692593304, "percentage": 96.46, "elapsed_time": "22:22:54", "remaining_time": "0:49:14", "throughput": 658.5, "total_tokens": 53058016} {"current_steps": 38590, "total_steps": 40000, "loss": 0.5549, "lr": 1.5335547781785975e-07, "epoch": 1.2351962102298188, "percentage": 96.47, "elapsed_time": "22:22:56", "remaining_time": "0:49:04", "throughput": 658.57, "total_tokens": 53064896} {"current_steps": 38595, "total_steps": 40000, "loss": 0.7225, "lr": 1.5227164953139917e-07, "epoch": 1.2353562512003073, "percentage": 96.49, "elapsed_time": "22:22:58", "remaining_time": "0:48:53", "throughput": 658.64, "total_tokens": 53071824} {"current_steps": 38600, "total_steps": 40000, "loss": 0.626, "lr": 1.511916530769042e-07, "epoch": 1.2355162921707956, "percentage": 96.5, "elapsed_time": "22:22:59", "remaining_time": "0:48:42", "throughput": 658.71, "total_tokens": 53078736} {"current_steps": 38600, "total_steps": 40000, "eval_loss": 0.7299603819847107, "epoch": 1.2355162921707956, "percentage": 96.5, "elapsed_time": "22:28:48", "remaining_time": "0:48:55", "throughput": 655.88, "total_tokens": 53078736} {"current_steps": 38605, "total_steps": 40000, "loss": 0.7916, "lr": 1.5011548862092773e-07, "epoch": 1.2356763331412841, "percentage": 96.51, "elapsed_time": "22:28:51", "remaining_time": "0:48:44", "throughput": 655.94, "total_tokens": 53085808} {"current_steps": 38610, "total_steps": 40000, "loss": 0.6327, "lr": 1.490431563294231e-07, "epoch": 1.2358363741117726, "percentage": 96.53, "elapsed_time": "22:28:53", "remaining_time": "0:48:33", "throughput": 656.01, "total_tokens": 53092848} {"current_steps": 38615, "total_steps": 40000, "loss": 0.6992, "lr": 1.4797465636776365e-07, "epoch": 1.235996415082261, "percentage": 96.54, "elapsed_time": "22:28:54", "remaining_time": "0:48:22", "throughput": 656.09, "total_tokens": 53100256} {"current_steps": 38620, "total_steps": 40000, "loss": 0.628, "lr": 1.4690998890072027e-07, "epoch": 1.2361564560527496, "percentage": 96.55, "elapsed_time": "22:28:56", "remaining_time": "0:48:12", "throughput": 656.15, "total_tokens": 53106560} {"current_steps": 38625, "total_steps": 40000, "loss": 0.6285, "lr": 1.4584915409248112e-07, "epoch": 1.2363164970232379, "percentage": 96.56, "elapsed_time": "22:28:58", "remaining_time": "0:48:01", "throughput": 656.22, "total_tokens": 53113312} {"current_steps": 38630, "total_steps": 40000, "loss": 0.8094, "lr": 1.4479215210663754e-07, "epoch": 1.2364765379937264, "percentage": 96.58, "elapsed_time": "22:29:00", "remaining_time": "0:47:50", "throughput": 656.29, "total_tokens": 53120480} {"current_steps": 38635, "total_steps": 40000, "loss": 0.7916, "lr": 1.4373898310619528e-07, "epoch": 1.2366365789642149, "percentage": 96.59, "elapsed_time": "22:29:01", "remaining_time": "0:47:39", "throughput": 656.36, "total_tokens": 53127312} {"current_steps": 38640, "total_steps": 40000, "loss": 0.748, "lr": 1.4268964725356604e-07, "epoch": 1.2367966199347034, "percentage": 96.6, "elapsed_time": "22:29:03", "remaining_time": "0:47:28", "throughput": 656.43, "total_tokens": 53133952} {"current_steps": 38645, "total_steps": 40000, "loss": 0.7378, "lr": 1.4164414471056764e-07, "epoch": 1.2369566609051916, "percentage": 96.61, "elapsed_time": "22:29:05", "remaining_time": "0:47:18", "throughput": 656.51, "total_tokens": 53141136} {"current_steps": 38650, "total_steps": 40000, "loss": 0.6823, "lr": 1.4060247563843497e-07, "epoch": 1.2371167018756801, "percentage": 96.62, "elapsed_time": "22:29:07", "remaining_time": "0:47:07", "throughput": 656.58, "total_tokens": 53148032} {"current_steps": 38655, "total_steps": 40000, "loss": 0.574, "lr": 1.3956464019780068e-07, "epoch": 1.2372767428461686, "percentage": 96.64, "elapsed_time": "22:29:08", "remaining_time": "0:46:56", "throughput": 656.65, "total_tokens": 53154784} {"current_steps": 38660, "total_steps": 40000, "loss": 0.6536, "lr": 1.385306385487145e-07, "epoch": 1.2374367838166571, "percentage": 96.65, "elapsed_time": "22:29:10", "remaining_time": "0:46:45", "throughput": 656.72, "total_tokens": 53161664} {"current_steps": 38665, "total_steps": 40000, "loss": 0.6725, "lr": 1.3750047085063222e-07, "epoch": 1.2375968247871456, "percentage": 96.66, "elapsed_time": "22:29:12", "remaining_time": "0:46:35", "throughput": 656.79, "total_tokens": 53168400} {"current_steps": 38670, "total_steps": 40000, "loss": 0.9389, "lr": 1.3647413726242119e-07, "epoch": 1.2377568657576339, "percentage": 96.67, "elapsed_time": "22:29:14", "remaining_time": "0:46:24", "throughput": 656.86, "total_tokens": 53175120} {"current_steps": 38675, "total_steps": 40000, "loss": 0.5759, "lr": 1.3545163794235205e-07, "epoch": 1.2379169067281224, "percentage": 96.69, "elapsed_time": "22:29:15", "remaining_time": "0:46:13", "throughput": 656.93, "total_tokens": 53181968} {"current_steps": 38680, "total_steps": 40000, "loss": 0.769, "lr": 1.3443297304810698e-07, "epoch": 1.2380769476986109, "percentage": 96.7, "elapsed_time": "22:29:17", "remaining_time": "0:46:02", "throughput": 656.99, "total_tokens": 53188528} {"current_steps": 38685, "total_steps": 40000, "loss": 0.7502, "lr": 1.3341814273677977e-07, "epoch": 1.2382369886690994, "percentage": 96.71, "elapsed_time": "22:29:19", "remaining_time": "0:45:52", "throughput": 657.06, "total_tokens": 53195088} {"current_steps": 38690, "total_steps": 40000, "loss": 0.7274, "lr": 1.324071471648647e-07, "epoch": 1.2383970296395876, "percentage": 96.73, "elapsed_time": "22:29:21", "remaining_time": "0:45:41", "throughput": 657.13, "total_tokens": 53202016} {"current_steps": 38695, "total_steps": 40000, "loss": 0.7611, "lr": 1.3139998648827312e-07, "epoch": 1.2385570706100761, "percentage": 96.74, "elapsed_time": "22:29:22", "remaining_time": "0:45:30", "throughput": 657.2, "total_tokens": 53208928} {"current_steps": 38700, "total_steps": 40000, "loss": 0.6269, "lr": 1.3039666086232526e-07, "epoch": 1.2387171115805646, "percentage": 96.75, "elapsed_time": "22:29:24", "remaining_time": "0:45:19", "throughput": 657.27, "total_tokens": 53215632} {"current_steps": 38705, "total_steps": 40000, "loss": 0.5334, "lr": 1.2939717044174183e-07, "epoch": 1.2388771525510531, "percentage": 96.76, "elapsed_time": "22:29:26", "remaining_time": "0:45:08", "throughput": 657.34, "total_tokens": 53222608} {"current_steps": 38710, "total_steps": 40000, "loss": 0.567, "lr": 1.284015153806578e-07, "epoch": 1.2390371935215416, "percentage": 96.78, "elapsed_time": "22:29:27", "remaining_time": "0:44:58", "throughput": 657.41, "total_tokens": 53229296} {"current_steps": 38715, "total_steps": 40000, "loss": 0.6946, "lr": 1.274096958326171e-07, "epoch": 1.23919723449203, "percentage": 96.79, "elapsed_time": "22:29:29", "remaining_time": "0:44:47", "throughput": 657.49, "total_tokens": 53236656} {"current_steps": 38720, "total_steps": 40000, "loss": 0.8653, "lr": 1.2642171195056952e-07, "epoch": 1.2393572754625184, "percentage": 96.8, "elapsed_time": "22:29:31", "remaining_time": "0:44:36", "throughput": 657.56, "total_tokens": 53243696} {"current_steps": 38725, "total_steps": 40000, "loss": 0.6864, "lr": 1.2543756388687377e-07, "epoch": 1.2395173164330069, "percentage": 96.81, "elapsed_time": "22:29:33", "remaining_time": "0:44:25", "throughput": 657.63, "total_tokens": 53250608} {"current_steps": 38730, "total_steps": 40000, "loss": 0.6948, "lr": 1.2445725179330014e-07, "epoch": 1.2396773574034954, "percentage": 96.83, "elapsed_time": "22:29:34", "remaining_time": "0:44:15", "throughput": 657.7, "total_tokens": 53257488} {"current_steps": 38735, "total_steps": 40000, "loss": 0.747, "lr": 1.2348077582102212e-07, "epoch": 1.2398373983739837, "percentage": 96.84, "elapsed_time": "22:29:36", "remaining_time": "0:44:04", "throughput": 657.77, "total_tokens": 53264032} {"current_steps": 38740, "total_steps": 40000, "loss": 0.7217, "lr": 1.2250813612062762e-07, "epoch": 1.2399974393444722, "percentage": 96.85, "elapsed_time": "22:29:38", "remaining_time": "0:43:53", "throughput": 657.84, "total_tokens": 53270800} {"current_steps": 38745, "total_steps": 40000, "loss": 0.7191, "lr": 1.215393328421105e-07, "epoch": 1.2401574803149606, "percentage": 96.86, "elapsed_time": "22:29:40", "remaining_time": "0:43:43", "throughput": 657.91, "total_tokens": 53277248} {"current_steps": 38750, "total_steps": 40000, "loss": 0.6763, "lr": 1.2057436613486796e-07, "epoch": 1.2403175212854491, "percentage": 96.88, "elapsed_time": "22:29:41", "remaining_time": "0:43:32", "throughput": 657.98, "total_tokens": 53284144} {"current_steps": 38755, "total_steps": 40000, "loss": 0.6223, "lr": 1.1961323614771424e-07, "epoch": 1.2404775622559376, "percentage": 96.89, "elapsed_time": "22:29:43", "remaining_time": "0:43:21", "throughput": 658.05, "total_tokens": 53291008} {"current_steps": 38760, "total_steps": 40000, "loss": 0.6381, "lr": 1.1865594302886418e-07, "epoch": 1.240637603226426, "percentage": 96.9, "elapsed_time": "22:29:45", "remaining_time": "0:43:10", "throughput": 658.12, "total_tokens": 53297824} {"current_steps": 38765, "total_steps": 40000, "loss": 0.7255, "lr": 1.1770248692594687e-07, "epoch": 1.2407976441969144, "percentage": 96.91, "elapsed_time": "22:29:47", "remaining_time": "0:43:00", "throughput": 658.19, "total_tokens": 53304624} {"current_steps": 38770, "total_steps": 40000, "loss": 0.7672, "lr": 1.167528679859975e-07, "epoch": 1.240957685167403, "percentage": 96.92, "elapsed_time": "22:29:48", "remaining_time": "0:42:49", "throughput": 658.26, "total_tokens": 53311632} {"current_steps": 38775, "total_steps": 40000, "loss": 0.6651, "lr": 1.1580708635545446e-07, "epoch": 1.2411177261378914, "percentage": 96.94, "elapsed_time": "22:29:50", "remaining_time": "0:42:38", "throughput": 658.33, "total_tokens": 53318816} {"current_steps": 38780, "total_steps": 40000, "loss": 0.5284, "lr": 1.1486514218017885e-07, "epoch": 1.2412777671083797, "percentage": 96.95, "elapsed_time": "22:29:52", "remaining_time": "0:42:27", "throughput": 658.4, "total_tokens": 53325504} {"current_steps": 38785, "total_steps": 40000, "loss": 0.5198, "lr": 1.1392703560542117e-07, "epoch": 1.2414378080788682, "percentage": 96.96, "elapsed_time": "22:29:54", "remaining_time": "0:42:17", "throughput": 658.47, "total_tokens": 53332416} {"current_steps": 38790, "total_steps": 40000, "loss": 0.7631, "lr": 1.129927667758518e-07, "epoch": 1.2415978490493567, "percentage": 96.97, "elapsed_time": "22:29:55", "remaining_time": "0:42:06", "throughput": 658.54, "total_tokens": 53338928} {"current_steps": 38795, "total_steps": 40000, "loss": 0.8861, "lr": 1.1206233583554992e-07, "epoch": 1.2417578900198452, "percentage": 96.99, "elapsed_time": "22:29:57", "remaining_time": "0:41:55", "throughput": 658.61, "total_tokens": 53345792} {"current_steps": 38800, "total_steps": 40000, "loss": 0.6822, "lr": 1.1113574292799523e-07, "epoch": 1.2419179309903334, "percentage": 97.0, "elapsed_time": "22:29:59", "remaining_time": "0:41:45", "throughput": 658.68, "total_tokens": 53352672} {"current_steps": 38800, "total_steps": 40000, "eval_loss": 0.7300453782081604, "epoch": 1.2419179309903334, "percentage": 97.0, "elapsed_time": "22:35:47", "remaining_time": "0:41:55", "throughput": 655.86, "total_tokens": 53352672} {"current_steps": 38805, "total_steps": 40000, "loss": 0.5993, "lr": 1.1021298819608449e-07, "epoch": 1.242077971960822, "percentage": 97.01, "elapsed_time": "22:35:51", "remaining_time": "0:41:45", "throughput": 655.92, "total_tokens": 53359648} {"current_steps": 38810, "total_steps": 40000, "loss": 0.6485, "lr": 1.0929407178211226e-07, "epoch": 1.2422380129313104, "percentage": 97.02, "elapsed_time": "22:35:52", "remaining_time": "0:41:34", "throughput": 655.98, "total_tokens": 53366240} {"current_steps": 38815, "total_steps": 40000, "loss": 0.6758, "lr": 1.0837899382779293e-07, "epoch": 1.242398053901799, "percentage": 97.04, "elapsed_time": "22:35:54", "remaining_time": "0:41:23", "throughput": 656.05, "total_tokens": 53372832} {"current_steps": 38820, "total_steps": 40000, "loss": 0.6106, "lr": 1.0746775447423862e-07, "epoch": 1.2425580948722872, "percentage": 97.05, "elapsed_time": "22:35:56", "remaining_time": "0:41:12", "throughput": 656.12, "total_tokens": 53379680} {"current_steps": 38825, "total_steps": 40000, "loss": 0.7006, "lr": 1.0656035386197583e-07, "epoch": 1.2427181358427757, "percentage": 97.06, "elapsed_time": "22:35:58", "remaining_time": "0:41:02", "throughput": 656.19, "total_tokens": 53386624} {"current_steps": 38830, "total_steps": 40000, "loss": 0.7214, "lr": 1.0565679213093982e-07, "epoch": 1.2428781768132642, "percentage": 97.08, "elapsed_time": "22:35:59", "remaining_time": "0:40:51", "throughput": 656.26, "total_tokens": 53393488} {"current_steps": 38835, "total_steps": 40000, "loss": 0.7197, "lr": 1.0475706942046638e-07, "epoch": 1.2430382177837527, "percentage": 97.09, "elapsed_time": "22:36:01", "remaining_time": "0:40:40", "throughput": 656.33, "total_tokens": 53400032} {"current_steps": 38840, "total_steps": 40000, "loss": 0.6405, "lr": 1.0386118586930282e-07, "epoch": 1.2431982587542412, "percentage": 97.1, "elapsed_time": "22:36:03", "remaining_time": "0:40:30", "throughput": 656.4, "total_tokens": 53406864} {"current_steps": 38845, "total_steps": 40000, "loss": 0.8289, "lr": 1.0296914161561367e-07, "epoch": 1.2433582997247294, "percentage": 97.11, "elapsed_time": "22:36:05", "remaining_time": "0:40:19", "throughput": 656.47, "total_tokens": 53413456} {"current_steps": 38850, "total_steps": 40000, "loss": 0.8431, "lr": 1.0208093679695552e-07, "epoch": 1.243518340695218, "percentage": 97.12, "elapsed_time": "22:36:06", "remaining_time": "0:40:08", "throughput": 656.54, "total_tokens": 53420208} {"current_steps": 38855, "total_steps": 40000, "loss": 0.6489, "lr": 1.0119657155030493e-07, "epoch": 1.2436783816657064, "percentage": 97.14, "elapsed_time": "22:36:08", "remaining_time": "0:39:57", "throughput": 656.6, "total_tokens": 53426768} {"current_steps": 38860, "total_steps": 40000, "loss": 0.7074, "lr": 1.003160460120417e-07, "epoch": 1.243838422636195, "percentage": 97.15, "elapsed_time": "22:36:10", "remaining_time": "0:39:47", "throughput": 656.67, "total_tokens": 53433568} {"current_steps": 38865, "total_steps": 40000, "loss": 0.5752, "lr": 9.943936031795165e-08, "epoch": 1.2439984636066832, "percentage": 97.16, "elapsed_time": "22:36:12", "remaining_time": "0:39:36", "throughput": 656.74, "total_tokens": 53440512} {"current_steps": 38870, "total_steps": 40000, "loss": 0.8739, "lr": 9.856651460323219e-08, "epoch": 1.2441585045771717, "percentage": 97.17, "elapsed_time": "22:36:13", "remaining_time": "0:39:25", "throughput": 656.81, "total_tokens": 53447472} {"current_steps": 38875, "total_steps": 40000, "loss": 0.6717, "lr": 9.769750900248953e-08, "epoch": 1.2443185455476602, "percentage": 97.19, "elapsed_time": "22:36:15", "remaining_time": "0:39:14", "throughput": 656.89, "total_tokens": 53454416} {"current_steps": 38880, "total_steps": 40000, "loss": 0.8517, "lr": 9.683234364973038e-08, "epoch": 1.2444785865181487, "percentage": 97.2, "elapsed_time": "22:36:17", "remaining_time": "0:39:04", "throughput": 656.96, "total_tokens": 53461488} {"current_steps": 38885, "total_steps": 40000, "loss": 0.5269, "lr": 9.597101867837854e-08, "epoch": 1.2446386274886372, "percentage": 97.21, "elapsed_time": "22:36:18", "remaining_time": "0:38:53", "throughput": 657.03, "total_tokens": 53468128} {"current_steps": 38890, "total_steps": 40000, "loss": 0.664, "lr": 9.511353422125835e-08, "epoch": 1.2447986684591255, "percentage": 97.22, "elapsed_time": "22:36:20", "remaining_time": "0:38:42", "throughput": 657.1, "total_tokens": 53475440} {"current_steps": 38895, "total_steps": 40000, "loss": 0.8879, "lr": 9.42598904106029e-08, "epoch": 1.244958709429614, "percentage": 97.24, "elapsed_time": "22:36:22", "remaining_time": "0:38:32", "throughput": 657.18, "total_tokens": 53482736} {"current_steps": 38900, "total_steps": 40000, "loss": 0.7279, "lr": 9.341008737806245e-08, "epoch": 1.2451187504001024, "percentage": 97.25, "elapsed_time": "22:36:24", "remaining_time": "0:38:21", "throughput": 657.25, "total_tokens": 53489536} {"current_steps": 38905, "total_steps": 40000, "loss": 0.7204, "lr": 9.256412525467661e-08, "epoch": 1.245278791370591, "percentage": 97.26, "elapsed_time": "22:36:25", "remaining_time": "0:38:10", "throughput": 657.32, "total_tokens": 53496352} {"current_steps": 38910, "total_steps": 40000, "loss": 0.7384, "lr": 9.172200417091326e-08, "epoch": 1.2454388323410792, "percentage": 97.28, "elapsed_time": "22:36:27", "remaining_time": "0:37:59", "throughput": 657.39, "total_tokens": 53503664} {"current_steps": 38915, "total_steps": 40000, "loss": 0.4492, "lr": 9.088372425663239e-08, "epoch": 1.2455988733115677, "percentage": 97.29, "elapsed_time": "22:36:29", "remaining_time": "0:37:49", "throughput": 657.46, "total_tokens": 53510352} {"current_steps": 38920, "total_steps": 40000, "loss": 0.7744, "lr": 9.004928564110837e-08, "epoch": 1.2457589142820562, "percentage": 97.3, "elapsed_time": "22:36:31", "remaining_time": "0:37:38", "throughput": 657.53, "total_tokens": 53517104} {"current_steps": 38925, "total_steps": 40000, "loss": 0.6592, "lr": 8.92186884530244e-08, "epoch": 1.2459189552525447, "percentage": 97.31, "elapsed_time": "22:36:32", "remaining_time": "0:37:27", "throughput": 657.6, "total_tokens": 53523952} {"current_steps": 38930, "total_steps": 40000, "loss": 0.6033, "lr": 8.83919328204641e-08, "epoch": 1.2460789962230332, "percentage": 97.32, "elapsed_time": "22:36:34", "remaining_time": "0:37:17", "throughput": 657.67, "total_tokens": 53531168} {"current_steps": 38935, "total_steps": 40000, "loss": 0.8276, "lr": 8.756901887093105e-08, "epoch": 1.2462390371935215, "percentage": 97.34, "elapsed_time": "22:36:36", "remaining_time": "0:37:06", "throughput": 657.75, "total_tokens": 53538144} {"current_steps": 38940, "total_steps": 40000, "loss": 0.7996, "lr": 8.674994673132098e-08, "epoch": 1.24639907816401, "percentage": 97.35, "elapsed_time": "22:36:38", "remaining_time": "0:36:55", "throughput": 657.81, "total_tokens": 53544848} {"current_steps": 38945, "total_steps": 40000, "loss": 0.9006, "lr": 8.593471652794949e-08, "epoch": 1.2465591191344985, "percentage": 97.36, "elapsed_time": "22:36:39", "remaining_time": "0:36:45", "throughput": 657.89, "total_tokens": 53551728} {"current_steps": 38950, "total_steps": 40000, "loss": 0.7761, "lr": 8.512332838653548e-08, "epoch": 1.246719160104987, "percentage": 97.38, "elapsed_time": "22:36:41", "remaining_time": "0:36:34", "throughput": 657.96, "total_tokens": 53558960} {"current_steps": 38955, "total_steps": 40000, "loss": 0.668, "lr": 8.431578243220106e-08, "epoch": 1.2468792010754752, "percentage": 97.39, "elapsed_time": "22:36:43", "remaining_time": "0:36:23", "throughput": 658.03, "total_tokens": 53565616} {"current_steps": 38960, "total_steps": 40000, "loss": 0.6311, "lr": 8.351207878948552e-08, "epoch": 1.2470392420459637, "percentage": 97.4, "elapsed_time": "22:36:45", "remaining_time": "0:36:13", "throughput": 658.1, "total_tokens": 53572736} {"current_steps": 38965, "total_steps": 40000, "loss": 0.7846, "lr": 8.271221758232583e-08, "epoch": 1.2471992830164522, "percentage": 97.41, "elapsed_time": "22:36:46", "remaining_time": "0:36:02", "throughput": 658.17, "total_tokens": 53579856} {"current_steps": 38970, "total_steps": 40000, "loss": 0.8397, "lr": 8.191619893407332e-08, "epoch": 1.2473593239869407, "percentage": 97.42, "elapsed_time": "22:36:48", "remaining_time": "0:35:51", "throughput": 658.25, "total_tokens": 53586896} {"current_steps": 38975, "total_steps": 40000, "loss": 0.5288, "lr": 8.112402296748534e-08, "epoch": 1.2475193649574292, "percentage": 97.44, "elapsed_time": "22:36:50", "remaining_time": "0:35:40", "throughput": 658.32, "total_tokens": 53593872} {"current_steps": 38980, "total_steps": 40000, "loss": 0.5278, "lr": 8.033568980471973e-08, "epoch": 1.2476794059279175, "percentage": 97.45, "elapsed_time": "22:36:51", "remaining_time": "0:35:30", "throughput": 658.39, "total_tokens": 53600992} {"current_steps": 38985, "total_steps": 40000, "loss": 0.5287, "lr": 7.955119956735146e-08, "epoch": 1.247839446898406, "percentage": 97.46, "elapsed_time": "22:36:53", "remaining_time": "0:35:19", "throughput": 658.46, "total_tokens": 53607888} {"current_steps": 38990, "total_steps": 40000, "loss": 0.6961, "lr": 7.877055237636155e-08, "epoch": 1.2479994878688945, "percentage": 97.47, "elapsed_time": "22:36:55", "remaining_time": "0:35:08", "throughput": 658.54, "total_tokens": 53615088} {"current_steps": 38995, "total_steps": 40000, "loss": 0.6613, "lr": 7.79937483521287e-08, "epoch": 1.248159528839383, "percentage": 97.49, "elapsed_time": "22:36:57", "remaining_time": "0:34:58", "throughput": 658.6, "total_tokens": 53621680} {"current_steps": 39000, "total_steps": 40000, "loss": 0.5693, "lr": 7.722078761444873e-08, "epoch": 1.2483195698098712, "percentage": 97.5, "elapsed_time": "22:36:58", "remaining_time": "0:34:47", "throughput": 658.68, "total_tokens": 53628768} {"current_steps": 39000, "total_steps": 40000, "eval_loss": 0.7301680445671082, "epoch": 1.2483195698098712, "percentage": 97.5, "elapsed_time": "22:42:47", "remaining_time": "0:34:56", "throughput": 655.87, "total_tokens": 53628768} {"current_steps": 39005, "total_steps": 40000, "loss": 0.966, "lr": 7.645167028252631e-08, "epoch": 1.2484796107803597, "percentage": 97.51, "elapsed_time": "22:42:51", "remaining_time": "0:34:45", "throughput": 655.93, "total_tokens": 53636016} {"current_steps": 39010, "total_steps": 40000, "loss": 0.6312, "lr": 7.568639647496379e-08, "epoch": 1.2486396517508482, "percentage": 97.52, "elapsed_time": "22:42:53", "remaining_time": "0:34:35", "throughput": 656.0, "total_tokens": 53642896} {"current_steps": 39015, "total_steps": 40000, "loss": 0.7896, "lr": 7.492496630977508e-08, "epoch": 1.2487996927213367, "percentage": 97.54, "elapsed_time": "22:42:54", "remaining_time": "0:34:24", "throughput": 656.07, "total_tokens": 53650000} {"current_steps": 39020, "total_steps": 40000, "loss": 0.7721, "lr": 7.416737990438571e-08, "epoch": 1.2489597336918252, "percentage": 97.55, "elapsed_time": "22:42:56", "remaining_time": "0:34:13", "throughput": 656.14, "total_tokens": 53657008} {"current_steps": 39025, "total_steps": 40000, "loss": 0.5755, "lr": 7.341363737562445e-08, "epoch": 1.2491197746623135, "percentage": 97.56, "elapsed_time": "22:42:58", "remaining_time": "0:34:03", "throughput": 656.22, "total_tokens": 53664352} {"current_steps": 39030, "total_steps": 40000, "loss": 0.7975, "lr": 7.266373883972887e-08, "epoch": 1.249279815632802, "percentage": 97.58, "elapsed_time": "22:42:59", "remaining_time": "0:33:52", "throughput": 656.29, "total_tokens": 53671536} {"current_steps": 39035, "total_steps": 40000, "loss": 0.702, "lr": 7.191768441233981e-08, "epoch": 1.2494398566032905, "percentage": 97.59, "elapsed_time": "22:43:01", "remaining_time": "0:33:41", "throughput": 656.37, "total_tokens": 53678784} {"current_steps": 39040, "total_steps": 40000, "loss": 0.65, "lr": 7.11754742085069e-08, "epoch": 1.249599897573779, "percentage": 97.6, "elapsed_time": "22:43:03", "remaining_time": "0:33:31", "throughput": 656.44, "total_tokens": 53685536} {"current_steps": 39045, "total_steps": 40000, "loss": 0.7498, "lr": 7.043710834269413e-08, "epoch": 1.2497599385442673, "percentage": 97.61, "elapsed_time": "22:43:05", "remaining_time": "0:33:20", "throughput": 656.5, "total_tokens": 53692208} {"current_steps": 39050, "total_steps": 40000, "loss": 0.9485, "lr": 6.970258692876319e-08, "epoch": 1.2499199795147558, "percentage": 97.62, "elapsed_time": "22:43:06", "remaining_time": "0:33:09", "throughput": 656.58, "total_tokens": 53699328} {"current_steps": 39055, "total_steps": 40000, "loss": 0.6364, "lr": 6.897191007998738e-08, "epoch": 1.2500800204852442, "percentage": 97.64, "elapsed_time": "22:43:08", "remaining_time": "0:32:59", "throughput": 656.65, "total_tokens": 53706112} {"current_steps": 39060, "total_steps": 40000, "loss": 0.7146, "lr": 6.824507790904599e-08, "epoch": 1.2502400614557327, "percentage": 97.65, "elapsed_time": "22:43:10", "remaining_time": "0:32:48", "throughput": 656.72, "total_tokens": 53713312} {"current_steps": 39065, "total_steps": 40000, "loss": 0.7532, "lr": 6.752209052802439e-08, "epoch": 1.2504001024262212, "percentage": 97.66, "elapsed_time": "22:43:12", "remaining_time": "0:32:37", "throughput": 656.79, "total_tokens": 53720288} {"current_steps": 39070, "total_steps": 40000, "loss": 0.7655, "lr": 6.680294804841946e-08, "epoch": 1.2505601433967095, "percentage": 97.67, "elapsed_time": "22:43:13", "remaining_time": "0:32:26", "throughput": 656.87, "total_tokens": 53727584} {"current_steps": 39075, "total_steps": 40000, "loss": 0.818, "lr": 6.608765058112865e-08, "epoch": 1.250720184367198, "percentage": 97.69, "elapsed_time": "22:43:15", "remaining_time": "0:32:16", "throughput": 656.93, "total_tokens": 53734224} {"current_steps": 39080, "total_steps": 40000, "loss": 0.7845, "lr": 6.537619823646368e-08, "epoch": 1.2508802253376865, "percentage": 97.7, "elapsed_time": "22:43:17", "remaining_time": "0:32:05", "throughput": 657.01, "total_tokens": 53741440} {"current_steps": 39085, "total_steps": 40000, "loss": 0.6926, "lr": 6.466859112413404e-08, "epoch": 1.2510402663081748, "percentage": 97.71, "elapsed_time": "22:43:19", "remaining_time": "0:31:54", "throughput": 657.08, "total_tokens": 53748464} {"current_steps": 39090, "total_steps": 40000, "loss": 0.6714, "lr": 6.39648293532663e-08, "epoch": 1.2512003072786633, "percentage": 97.72, "elapsed_time": "22:43:20", "remaining_time": "0:31:44", "throughput": 657.14, "total_tokens": 53754960} {"current_steps": 39095, "total_steps": 40000, "loss": 0.5305, "lr": 6.32649130323848e-08, "epoch": 1.2513603482491518, "percentage": 97.74, "elapsed_time": "22:43:22", "remaining_time": "0:31:33", "throughput": 657.22, "total_tokens": 53761984} {"current_steps": 39100, "total_steps": 40000, "loss": 0.7248, "lr": 6.256884226943094e-08, "epoch": 1.2515203892196403, "percentage": 97.75, "elapsed_time": "22:43:24", "remaining_time": "0:31:22", "throughput": 657.28, "total_tokens": 53768512} {"current_steps": 39105, "total_steps": 40000, "loss": 0.6526, "lr": 6.187661717174386e-08, "epoch": 1.2516804301901288, "percentage": 97.76, "elapsed_time": "22:43:26", "remaining_time": "0:31:12", "throughput": 657.35, "total_tokens": 53775424} {"current_steps": 39110, "total_steps": 40000, "loss": 0.7356, "lr": 6.118823784607708e-08, "epoch": 1.2518404711606173, "percentage": 97.78, "elapsed_time": "22:43:27", "remaining_time": "0:31:01", "throughput": 657.42, "total_tokens": 53782320} {"current_steps": 39115, "total_steps": 40000, "loss": 0.6127, "lr": 6.050370439858178e-08, "epoch": 1.2520005121311055, "percentage": 97.79, "elapsed_time": "22:43:29", "remaining_time": "0:30:50", "throughput": 657.5, "total_tokens": 53789408} {"current_steps": 39120, "total_steps": 40000, "loss": 0.8478, "lr": 5.98230169348235e-08, "epoch": 1.252160553101594, "percentage": 97.8, "elapsed_time": "22:43:31", "remaining_time": "0:30:40", "throughput": 657.57, "total_tokens": 53796192} {"current_steps": 39125, "total_steps": 40000, "loss": 0.7759, "lr": 5.914617555977664e-08, "epoch": 1.2523205940720825, "percentage": 97.81, "elapsed_time": "22:43:32", "remaining_time": "0:30:29", "throughput": 657.63, "total_tokens": 53802992} {"current_steps": 39130, "total_steps": 40000, "loss": 0.79, "lr": 5.8473180377816017e-08, "epoch": 1.2524806350425708, "percentage": 97.82, "elapsed_time": "22:43:34", "remaining_time": "0:30:19", "throughput": 657.7, "total_tokens": 53809808} {"current_steps": 39135, "total_steps": 40000, "loss": 0.6614, "lr": 5.780403149272251e-08, "epoch": 1.2526406760130593, "percentage": 97.84, "elapsed_time": "22:43:36", "remaining_time": "0:30:08", "throughput": 657.77, "total_tokens": 53816656} {"current_steps": 39140, "total_steps": 40000, "loss": 0.5808, "lr": 5.7138729007694126e-08, "epoch": 1.2528007169835478, "percentage": 97.85, "elapsed_time": "22:43:38", "remaining_time": "0:29:57", "throughput": 657.85, "total_tokens": 53823712} {"current_steps": 39145, "total_steps": 40000, "loss": 0.8265, "lr": 5.64772730253238e-08, "epoch": 1.2529607579540363, "percentage": 97.86, "elapsed_time": "22:43:39", "remaining_time": "0:29:47", "throughput": 657.92, "total_tokens": 53830832} {"current_steps": 39150, "total_steps": 40000, "loss": 0.5834, "lr": 5.5819663647618814e-08, "epoch": 1.2531207989245248, "percentage": 97.88, "elapsed_time": "22:43:41", "remaining_time": "0:29:36", "throughput": 657.99, "total_tokens": 53837760} {"current_steps": 39155, "total_steps": 40000, "loss": 0.7799, "lr": 5.5165900975989723e-08, "epoch": 1.253280839895013, "percentage": 97.89, "elapsed_time": "22:43:43", "remaining_time": "0:29:25", "throughput": 658.06, "total_tokens": 53844976} {"current_steps": 39160, "total_steps": 40000, "loss": 0.6303, "lr": 5.451598511125311e-08, "epoch": 1.2534408808655015, "percentage": 97.9, "elapsed_time": "22:43:45", "remaining_time": "0:29:15", "throughput": 658.13, "total_tokens": 53851792} {"current_steps": 39165, "total_steps": 40000, "loss": 0.8133, "lr": 5.3869916153637124e-08, "epoch": 1.25360092183599, "percentage": 97.91, "elapsed_time": "22:43:46", "remaining_time": "0:29:04", "throughput": 658.2, "total_tokens": 53858656} {"current_steps": 39170, "total_steps": 40000, "loss": 0.7539, "lr": 5.322769420277318e-08, "epoch": 1.2537609628064785, "percentage": 97.92, "elapsed_time": "22:43:48", "remaining_time": "0:28:53", "throughput": 658.28, "total_tokens": 53865712} {"current_steps": 39175, "total_steps": 40000, "loss": 0.6237, "lr": 5.258931935769873e-08, "epoch": 1.2539210037769668, "percentage": 97.94, "elapsed_time": "22:43:50", "remaining_time": "0:28:43", "throughput": 658.34, "total_tokens": 53872336} {"current_steps": 39180, "total_steps": 40000, "loss": 0.7996, "lr": 5.19547917168628e-08, "epoch": 1.2540810447474553, "percentage": 97.95, "elapsed_time": "22:43:52", "remaining_time": "0:28:32", "throughput": 658.41, "total_tokens": 53878880} {"current_steps": 39185, "total_steps": 40000, "loss": 0.5531, "lr": 5.13241113781121e-08, "epoch": 1.2542410857179438, "percentage": 97.96, "elapsed_time": "22:43:53", "remaining_time": "0:28:22", "throughput": 658.47, "total_tokens": 53885216} {"current_steps": 39190, "total_steps": 40000, "loss": 0.8705, "lr": 5.0697278438707755e-08, "epoch": 1.2544011266884323, "percentage": 97.97, "elapsed_time": "22:43:55", "remaining_time": "0:28:11", "throughput": 658.54, "total_tokens": 53892096} {"current_steps": 39195, "total_steps": 40000, "loss": 0.7643, "lr": 5.0074292995316854e-08, "epoch": 1.2545611676589208, "percentage": 97.99, "elapsed_time": "22:43:57", "remaining_time": "0:28:00", "throughput": 658.61, "total_tokens": 53898592} {"current_steps": 39200, "total_steps": 40000, "loss": 0.7027, "lr": 4.945515514400978e-08, "epoch": 1.254721208629409, "percentage": 98.0, "elapsed_time": "22:43:58", "remaining_time": "0:27:50", "throughput": 658.67, "total_tokens": 53905216} {"current_steps": 39200, "total_steps": 40000, "eval_loss": 0.7300665974617004, "epoch": 1.254721208629409, "percentage": 98.0, "elapsed_time": "22:49:47", "remaining_time": "0:27:57", "throughput": 655.88, "total_tokens": 53905216} {"current_steps": 39205, "total_steps": 40000, "loss": 0.6252, "lr": 4.883986498026571e-08, "epoch": 1.2548812495998976, "percentage": 98.01, "elapsed_time": "22:49:51", "remaining_time": "0:27:46", "throughput": 655.93, "total_tokens": 53911904} {"current_steps": 39210, "total_steps": 40000, "loss": 0.9083, "lr": 4.822842259896987e-08, "epoch": 1.255041290570386, "percentage": 98.02, "elapsed_time": "22:49:52", "remaining_time": "0:27:36", "throughput": 656.0, "total_tokens": 53918640} {"current_steps": 39215, "total_steps": 40000, "loss": 0.5691, "lr": 4.762082809441626e-08, "epoch": 1.2552013315408745, "percentage": 98.04, "elapsed_time": "22:49:54", "remaining_time": "0:27:25", "throughput": 656.07, "total_tokens": 53925536} {"current_steps": 39220, "total_steps": 40000, "loss": 0.8384, "lr": 4.7017081560302156e-08, "epoch": 1.2553613725113628, "percentage": 98.05, "elapsed_time": "22:49:56", "remaining_time": "0:27:14", "throughput": 656.14, "total_tokens": 53932144} {"current_steps": 39225, "total_steps": 40000, "loss": 0.6244, "lr": 4.6417183089730866e-08, "epoch": 1.2555214134818513, "percentage": 98.06, "elapsed_time": "22:49:58", "remaining_time": "0:27:04", "throughput": 656.21, "total_tokens": 53938880} {"current_steps": 39230, "total_steps": 40000, "loss": 0.5332, "lr": 4.5821132775217265e-08, "epoch": 1.2556814544523398, "percentage": 98.08, "elapsed_time": "22:49:59", "remaining_time": "0:26:53", "throughput": 656.27, "total_tokens": 53945744} {"current_steps": 39235, "total_steps": 40000, "loss": 0.7627, "lr": 4.5228930708679504e-08, "epoch": 1.2558414954228283, "percentage": 98.09, "elapsed_time": "22:50:01", "remaining_time": "0:26:42", "throughput": 656.34, "total_tokens": 53952576} {"current_steps": 39240, "total_steps": 40000, "loss": 0.7814, "lr": 4.464057698144175e-08, "epoch": 1.2560015363933168, "percentage": 98.1, "elapsed_time": "22:50:03", "remaining_time": "0:26:32", "throughput": 656.41, "total_tokens": 53958944} {"current_steps": 39245, "total_steps": 40000, "loss": 0.5386, "lr": 4.4056071684236974e-08, "epoch": 1.256161577363805, "percentage": 98.11, "elapsed_time": "22:50:05", "remaining_time": "0:26:21", "throughput": 656.48, "total_tokens": 53966000} {"current_steps": 39250, "total_steps": 40000, "loss": 0.6307, "lr": 4.347541490719864e-08, "epoch": 1.2563216183342936, "percentage": 98.12, "elapsed_time": "22:50:06", "remaining_time": "0:26:10", "throughput": 656.55, "total_tokens": 53972784} {"current_steps": 39255, "total_steps": 40000, "loss": 0.7425, "lr": 4.2898606739877336e-08, "epoch": 1.256481659304782, "percentage": 98.14, "elapsed_time": "22:50:08", "remaining_time": "0:26:00", "throughput": 656.62, "total_tokens": 53979904} {"current_steps": 39260, "total_steps": 40000, "loss": 0.7758, "lr": 4.232564727122135e-08, "epoch": 1.2566417002752703, "percentage": 98.15, "elapsed_time": "22:50:10", "remaining_time": "0:25:49", "throughput": 656.69, "total_tokens": 53986928} {"current_steps": 39265, "total_steps": 40000, "loss": 0.7657, "lr": 4.1756536589585004e-08, "epoch": 1.2568017412457588, "percentage": 98.16, "elapsed_time": "22:50:12", "remaining_time": "0:25:38", "throughput": 656.76, "total_tokens": 53993904} {"current_steps": 39270, "total_steps": 40000, "loss": 0.6749, "lr": 4.119127478273976e-08, "epoch": 1.2569617822162473, "percentage": 98.17, "elapsed_time": "22:50:13", "remaining_time": "0:25:28", "throughput": 656.83, "total_tokens": 54000832} {"current_steps": 39275, "total_steps": 40000, "loss": 0.7242, "lr": 4.062986193784923e-08, "epoch": 1.2571218231867358, "percentage": 98.19, "elapsed_time": "22:50:15", "remaining_time": "0:25:17", "throughput": 656.9, "total_tokens": 54007616} {"current_steps": 39280, "total_steps": 40000, "loss": 0.5797, "lr": 4.007229814149416e-08, "epoch": 1.2572818641572243, "percentage": 98.2, "elapsed_time": "22:50:17", "remaining_time": "0:25:07", "throughput": 656.97, "total_tokens": 54014304} {"current_steps": 39285, "total_steps": 40000, "loss": 0.7102, "lr": 3.951858347965576e-08, "epoch": 1.2574419051277128, "percentage": 98.21, "elapsed_time": "22:50:19", "remaining_time": "0:24:56", "throughput": 657.04, "total_tokens": 54021248} {"current_steps": 39290, "total_steps": 40000, "loss": 0.7581, "lr": 3.896871803772684e-08, "epoch": 1.257601946098201, "percentage": 98.22, "elapsed_time": "22:50:20", "remaining_time": "0:24:45", "throughput": 657.11, "total_tokens": 54027936} {"current_steps": 39295, "total_steps": 40000, "loss": 0.6644, "lr": 3.842270190050068e-08, "epoch": 1.2577619870686896, "percentage": 98.24, "elapsed_time": "22:50:22", "remaining_time": "0:24:35", "throughput": 657.18, "total_tokens": 54035120} {"current_steps": 39300, "total_steps": 40000, "loss": 0.7128, "lr": 3.7880535152179376e-08, "epoch": 1.257922028039178, "percentage": 98.25, "elapsed_time": "22:50:24", "remaining_time": "0:24:24", "throughput": 657.25, "total_tokens": 54042032} {"current_steps": 39305, "total_steps": 40000, "loss": 0.501, "lr": 3.734221787637382e-08, "epoch": 1.2580820690096663, "percentage": 98.26, "elapsed_time": "22:50:25", "remaining_time": "0:24:13", "throughput": 657.32, "total_tokens": 54048784} {"current_steps": 39310, "total_steps": 40000, "loss": 0.8272, "lr": 3.680775015609817e-08, "epoch": 1.2582421099801548, "percentage": 98.28, "elapsed_time": "22:50:27", "remaining_time": "0:24:03", "throughput": 657.39, "total_tokens": 54055664} {"current_steps": 39315, "total_steps": 40000, "loss": 0.5773, "lr": 3.627713207377537e-08, "epoch": 1.2584021509506433, "percentage": 98.29, "elapsed_time": "22:50:29", "remaining_time": "0:23:52", "throughput": 657.46, "total_tokens": 54062720} {"current_steps": 39320, "total_steps": 40000, "loss": 0.6568, "lr": 3.575036371123164e-08, "epoch": 1.2585621919211318, "percentage": 98.3, "elapsed_time": "22:50:31", "remaining_time": "0:23:42", "throughput": 657.53, "total_tokens": 54069408} {"current_steps": 39325, "total_steps": 40000, "loss": 0.6852, "lr": 3.5227445149704776e-08, "epoch": 1.2587222328916203, "percentage": 98.31, "elapsed_time": "22:50:32", "remaining_time": "0:23:31", "throughput": 657.6, "total_tokens": 54076768} {"current_steps": 39330, "total_steps": 40000, "loss": 0.5558, "lr": 3.470837646983027e-08, "epoch": 1.2588822738621088, "percentage": 98.32, "elapsed_time": "22:50:34", "remaining_time": "0:23:20", "throughput": 657.67, "total_tokens": 54083520} {"current_steps": 39335, "total_steps": 40000, "loss": 0.7619, "lr": 3.419315775165799e-08, "epoch": 1.259042314832597, "percentage": 98.34, "elapsed_time": "22:50:36", "remaining_time": "0:23:10", "throughput": 657.74, "total_tokens": 54090448} {"current_steps": 39340, "total_steps": 40000, "loss": 0.7645, "lr": 3.368178907464103e-08, "epoch": 1.2592023558030856, "percentage": 98.35, "elapsed_time": "22:50:38", "remaining_time": "0:22:59", "throughput": 657.81, "total_tokens": 54097296} {"current_steps": 39345, "total_steps": 40000, "loss": 0.5805, "lr": 3.317427051763855e-08, "epoch": 1.259362396773574, "percentage": 98.36, "elapsed_time": "22:50:39", "remaining_time": "0:22:49", "throughput": 657.88, "total_tokens": 54104272} {"current_steps": 39350, "total_steps": 40000, "loss": 0.7607, "lr": 3.267060215891571e-08, "epoch": 1.2595224377440624, "percentage": 98.38, "elapsed_time": "22:50:41", "remaining_time": "0:22:38", "throughput": 657.95, "total_tokens": 54110848} {"current_steps": 39355, "total_steps": 40000, "loss": 0.5469, "lr": 3.217078407614649e-08, "epoch": 1.2596824787145509, "percentage": 98.39, "elapsed_time": "22:50:43", "remaining_time": "0:22:27", "throughput": 658.02, "total_tokens": 54117584} {"current_steps": 39360, "total_steps": 40000, "loss": 0.8152, "lr": 3.1674816346405345e-08, "epoch": 1.2598425196850394, "percentage": 98.4, "elapsed_time": "22:50:45", "remaining_time": "0:22:17", "throughput": 658.09, "total_tokens": 54124336} {"current_steps": 39365, "total_steps": 40000, "loss": 0.7852, "lr": 3.11826990461811e-08, "epoch": 1.2600025606555278, "percentage": 98.41, "elapsed_time": "22:50:46", "remaining_time": "0:22:06", "throughput": 658.15, "total_tokens": 54130992} {"current_steps": 39370, "total_steps": 40000, "loss": 0.5763, "lr": 3.069443225136304e-08, "epoch": 1.2601626016260163, "percentage": 98.42, "elapsed_time": "22:50:48", "remaining_time": "0:21:56", "throughput": 658.22, "total_tokens": 54137584} {"current_steps": 39375, "total_steps": 40000, "loss": 0.6494, "lr": 3.021001603724372e-08, "epoch": 1.2603226425965048, "percentage": 98.44, "elapsed_time": "22:50:50", "remaining_time": "0:21:45", "throughput": 658.29, "total_tokens": 54144400} {"current_steps": 39380, "total_steps": 40000, "loss": 0.7325, "lr": 2.9729450478532818e-08, "epoch": 1.2604826835669931, "percentage": 98.45, "elapsed_time": "22:50:52", "remaining_time": "0:21:34", "throughput": 658.36, "total_tokens": 54151392} {"current_steps": 39385, "total_steps": 40000, "loss": 0.7072, "lr": 2.9252735649337726e-08, "epoch": 1.2606427245374816, "percentage": 98.46, "elapsed_time": "22:50:53", "remaining_time": "0:21:24", "throughput": 658.43, "total_tokens": 54157952} {"current_steps": 39390, "total_steps": 40000, "loss": 0.7736, "lr": 2.8779871623171863e-08, "epoch": 1.26080276550797, "percentage": 98.47, "elapsed_time": "22:50:55", "remaining_time": "0:21:13", "throughput": 658.5, "total_tokens": 54165008} {"current_steps": 39395, "total_steps": 40000, "loss": 0.9068, "lr": 2.8310858472957448e-08, "epoch": 1.2609628064784584, "percentage": 98.49, "elapsed_time": "22:50:57", "remaining_time": "0:21:03", "throughput": 658.57, "total_tokens": 54171920} {"current_steps": 39400, "total_steps": 40000, "loss": 0.838, "lr": 2.784569627101996e-08, "epoch": 1.2611228474489469, "percentage": 98.5, "elapsed_time": "22:50:58", "remaining_time": "0:20:52", "throughput": 658.64, "total_tokens": 54178832} {"current_steps": 39400, "total_steps": 40000, "eval_loss": 0.7300497889518738, "epoch": 1.2611228474489469, "percentage": 98.5, "elapsed_time": "22:56:47", "remaining_time": "0:20:57", "throughput": 655.86, "total_tokens": 54178832} {"current_steps": 39405, "total_steps": 40000, "loss": 0.7851, "lr": 2.738438508909924e-08, "epoch": 1.2612828884194354, "percentage": 98.51, "elapsed_time": "22:56:50", "remaining_time": "0:20:47", "throughput": 655.91, "total_tokens": 54185312} {"current_steps": 39410, "total_steps": 40000, "loss": 0.7847, "lr": 2.692692499833005e-08, "epoch": 1.2614429293899239, "percentage": 98.52, "elapsed_time": "22:56:52", "remaining_time": "0:20:36", "throughput": 655.99, "total_tokens": 54193008} {"current_steps": 39415, "total_steps": 40000, "loss": 0.6846, "lr": 2.647331606926151e-08, "epoch": 1.2616029703604124, "percentage": 98.54, "elapsed_time": "22:56:53", "remaining_time": "0:20:26", "throughput": 656.06, "total_tokens": 54199984} {"current_steps": 39420, "total_steps": 40000, "loss": 0.782, "lr": 2.6023558371843225e-08, "epoch": 1.2617630113309006, "percentage": 98.55, "elapsed_time": "22:56:55", "remaining_time": "0:20:15", "throughput": 656.13, "total_tokens": 54206848} {"current_steps": 39425, "total_steps": 40000, "loss": 0.854, "lr": 2.557765197543638e-08, "epoch": 1.2619230523013891, "percentage": 98.56, "elapsed_time": "22:56:57", "remaining_time": "0:20:04", "throughput": 656.2, "total_tokens": 54213600} {"current_steps": 39430, "total_steps": 40000, "loss": 0.6237, "lr": 2.513559694880263e-08, "epoch": 1.2620830932718776, "percentage": 98.58, "elapsed_time": "22:56:59", "remaining_time": "0:19:54", "throughput": 656.27, "total_tokens": 54220192} {"current_steps": 39435, "total_steps": 40000, "loss": 0.7103, "lr": 2.469739336011523e-08, "epoch": 1.2622431342423661, "percentage": 98.59, "elapsed_time": "22:57:00", "remaining_time": "0:19:43", "throughput": 656.34, "total_tokens": 54227040} {"current_steps": 39440, "total_steps": 40000, "loss": 0.7671, "lr": 2.4263041276947894e-08, "epoch": 1.2624031752128544, "percentage": 98.6, "elapsed_time": "22:57:02", "remaining_time": "0:19:33", "throughput": 656.4, "total_tokens": 54233664} {"current_steps": 39445, "total_steps": 40000, "loss": 0.7292, "lr": 2.3832540766283164e-08, "epoch": 1.2625632161833429, "percentage": 98.61, "elapsed_time": "22:57:04", "remaining_time": "0:19:22", "throughput": 656.47, "total_tokens": 54240480} {"current_steps": 39450, "total_steps": 40000, "loss": 0.6301, "lr": 2.3405891894512366e-08, "epoch": 1.2627232571538314, "percentage": 98.62, "elapsed_time": "22:57:06", "remaining_time": "0:19:11", "throughput": 656.54, "total_tokens": 54247296} {"current_steps": 39455, "total_steps": 40000, "loss": 0.5402, "lr": 2.29830947274301e-08, "epoch": 1.2628832981243199, "percentage": 98.64, "elapsed_time": "22:57:07", "remaining_time": "0:19:01", "throughput": 656.61, "total_tokens": 54254640} {"current_steps": 39460, "total_steps": 40000, "loss": 0.6363, "lr": 2.2564149330231432e-08, "epoch": 1.2630433390948084, "percentage": 98.65, "elapsed_time": "22:57:09", "remaining_time": "0:18:50", "throughput": 656.68, "total_tokens": 54261312} {"current_steps": 39465, "total_steps": 40000, "loss": 0.6611, "lr": 2.2149055767528572e-08, "epoch": 1.2632033800652966, "percentage": 98.66, "elapsed_time": "22:57:11", "remaining_time": "0:18:40", "throughput": 656.75, "total_tokens": 54267792} {"current_steps": 39470, "total_steps": 40000, "loss": 0.8165, "lr": 2.1737814103334197e-08, "epoch": 1.2633634210357851, "percentage": 98.67, "elapsed_time": "22:57:13", "remaining_time": "0:18:29", "throughput": 656.82, "total_tokens": 54274736} {"current_steps": 39475, "total_steps": 40000, "loss": 0.6253, "lr": 2.1330424401064253e-08, "epoch": 1.2635234620062736, "percentage": 98.69, "elapsed_time": "22:57:14", "remaining_time": "0:18:19", "throughput": 656.88, "total_tokens": 54281440} {"current_steps": 39480, "total_steps": 40000, "loss": 0.8422, "lr": 2.092688672354348e-08, "epoch": 1.2636835029767621, "percentage": 98.7, "elapsed_time": "22:57:16", "remaining_time": "0:18:08", "throughput": 656.95, "total_tokens": 54288320} {"current_steps": 39485, "total_steps": 40000, "loss": 0.8235, "lr": 2.0527201133005435e-08, "epoch": 1.2638435439472504, "percentage": 98.71, "elapsed_time": "22:57:18", "remaining_time": "0:17:57", "throughput": 657.03, "total_tokens": 54295392} {"current_steps": 39490, "total_steps": 40000, "loss": 0.5422, "lr": 2.0131367691084148e-08, "epoch": 1.264003584917739, "percentage": 98.72, "elapsed_time": "22:57:19", "remaining_time": "0:17:47", "throughput": 657.1, "total_tokens": 54302448} {"current_steps": 39495, "total_steps": 40000, "loss": 0.6495, "lr": 1.9739386458819675e-08, "epoch": 1.2641636258882274, "percentage": 98.74, "elapsed_time": "22:57:21", "remaining_time": "0:17:36", "throughput": 657.17, "total_tokens": 54309584} {"current_steps": 39500, "total_steps": 40000, "loss": 0.6496, "lr": 1.9351257496666442e-08, "epoch": 1.2643236668587159, "percentage": 98.75, "elapsed_time": "22:57:23", "remaining_time": "0:17:26", "throughput": 657.25, "total_tokens": 54317040} {"current_steps": 39505, "total_steps": 40000, "loss": 0.6817, "lr": 1.896698086447657e-08, "epoch": 1.2644837078292044, "percentage": 98.76, "elapsed_time": "22:57:25", "remaining_time": "0:17:15", "throughput": 657.32, "total_tokens": 54324208} {"current_steps": 39510, "total_steps": 40000, "loss": 0.7226, "lr": 1.8586556621505436e-08, "epoch": 1.2646437487996927, "percentage": 98.78, "elapsed_time": "22:57:26", "remaining_time": "0:17:04", "throughput": 657.39, "total_tokens": 54330944} {"current_steps": 39515, "total_steps": 40000, "loss": 0.6058, "lr": 1.820998482642833e-08, "epoch": 1.2648037897701812, "percentage": 98.79, "elapsed_time": "22:57:28", "remaining_time": "0:16:54", "throughput": 657.45, "total_tokens": 54337440} {"current_steps": 39520, "total_steps": 40000, "loss": 0.6528, "lr": 1.7837265537309912e-08, "epoch": 1.2649638307406696, "percentage": 98.8, "elapsed_time": "22:57:30", "remaining_time": "0:16:43", "throughput": 657.52, "total_tokens": 54344608} {"current_steps": 39525, "total_steps": 40000, "loss": 0.7475, "lr": 1.7468398811629206e-08, "epoch": 1.265123871711158, "percentage": 98.81, "elapsed_time": "22:57:32", "remaining_time": "0:16:33", "throughput": 657.59, "total_tokens": 54351472} {"current_steps": 39530, "total_steps": 40000, "loss": 0.6358, "lr": 1.710338470627404e-08, "epoch": 1.2652839126816464, "percentage": 98.83, "elapsed_time": "22:57:33", "remaining_time": "0:16:22", "throughput": 657.66, "total_tokens": 54358208} {"current_steps": 39535, "total_steps": 40000, "loss": 0.6681, "lr": 1.6742223277529945e-08, "epoch": 1.265443953652135, "percentage": 98.84, "elapsed_time": "22:57:35", "remaining_time": "0:16:12", "throughput": 657.72, "total_tokens": 54364656} {"current_steps": 39540, "total_steps": 40000, "loss": 0.4436, "lr": 1.6384914581094036e-08, "epoch": 1.2656039946226234, "percentage": 98.85, "elapsed_time": "22:57:37", "remaining_time": "0:16:01", "throughput": 657.8, "total_tokens": 54371808} {"current_steps": 39545, "total_steps": 40000, "loss": 0.7784, "lr": 1.6031458672069455e-08, "epoch": 1.265764035593112, "percentage": 98.86, "elapsed_time": "22:57:39", "remaining_time": "0:15:51", "throughput": 657.87, "total_tokens": 54378752} {"current_steps": 39550, "total_steps": 40000, "loss": 0.8781, "lr": 1.5681855604962602e-08, "epoch": 1.2659240765636004, "percentage": 98.88, "elapsed_time": "22:57:40", "remaining_time": "0:15:40", "throughput": 657.94, "total_tokens": 54385456} {"current_steps": 39555, "total_steps": 40000, "loss": 0.7616, "lr": 1.5336105433683135e-08, "epoch": 1.2660841175340887, "percentage": 98.89, "elapsed_time": "22:57:42", "remaining_time": "0:15:29", "throughput": 658.01, "total_tokens": 54392608} {"current_steps": 39560, "total_steps": 40000, "loss": 0.8275, "lr": 1.499420821155506e-08, "epoch": 1.2662441585045772, "percentage": 98.9, "elapsed_time": "22:57:44", "remaining_time": "0:15:19", "throughput": 658.08, "total_tokens": 54399728} {"current_steps": 39565, "total_steps": 40000, "loss": 0.5736, "lr": 1.4656163991302874e-08, "epoch": 1.2664041994750657, "percentage": 98.91, "elapsed_time": "22:57:46", "remaining_time": "0:15:08", "throughput": 658.15, "total_tokens": 54406448} {"current_steps": 39570, "total_steps": 40000, "loss": 0.9138, "lr": 1.4321972825051544e-08, "epoch": 1.266564240445554, "percentage": 98.92, "elapsed_time": "22:57:47", "remaining_time": "0:14:58", "throughput": 658.22, "total_tokens": 54413712} {"current_steps": 39575, "total_steps": 40000, "loss": 0.6312, "lr": 1.3991634764345951e-08, "epoch": 1.2667242814160424, "percentage": 98.94, "elapsed_time": "22:57:49", "remaining_time": "0:14:47", "throughput": 658.29, "total_tokens": 54420576} {"current_steps": 39580, "total_steps": 40000, "loss": 0.692, "lr": 1.3665149860120352e-08, "epoch": 1.266884322386531, "percentage": 98.95, "elapsed_time": "22:57:51", "remaining_time": "0:14:37", "throughput": 658.36, "total_tokens": 54427824} {"current_steps": 39585, "total_steps": 40000, "loss": 0.7596, "lr": 1.3342518162728912e-08, "epoch": 1.2670443633570194, "percentage": 98.96, "elapsed_time": "22:57:52", "remaining_time": "0:14:26", "throughput": 658.43, "total_tokens": 54434576} {"current_steps": 39590, "total_steps": 40000, "loss": 0.686, "lr": 1.30237397219235e-08, "epoch": 1.267204404327508, "percentage": 98.98, "elapsed_time": "22:57:54", "remaining_time": "0:14:16", "throughput": 658.5, "total_tokens": 54441392} {"current_steps": 39595, "total_steps": 40000, "loss": 0.8238, "lr": 1.2708814586862016e-08, "epoch": 1.2673644452979964, "percentage": 98.99, "elapsed_time": "22:57:56", "remaining_time": "0:14:05", "throughput": 658.57, "total_tokens": 54447872} {"current_steps": 39600, "total_steps": 40000, "loss": 0.5893, "lr": 1.2397742806111168e-08, "epoch": 1.2675244862684847, "percentage": 99.0, "elapsed_time": "22:57:58", "remaining_time": "0:13:55", "throughput": 658.64, "total_tokens": 54454880} {"current_steps": 39600, "total_steps": 40000, "eval_loss": 0.7300497889518738, "epoch": 1.2675244862684847, "percentage": 99.0, "elapsed_time": "23:03:46", "remaining_time": "0:13:58", "throughput": 655.87, "total_tokens": 54454880} {"current_steps": 39605, "total_steps": 40000, "loss": 0.6662, "lr": 1.209052442764369e-08, "epoch": 1.2676845272389732, "percentage": 99.01, "elapsed_time": "23:03:50", "remaining_time": "0:13:48", "throughput": 655.93, "total_tokens": 54462032} {"current_steps": 39610, "total_steps": 40000, "loss": 0.8247, "lr": 1.17871594988328e-08, "epoch": 1.2678445682094617, "percentage": 99.02, "elapsed_time": "23:03:51", "remaining_time": "0:13:37", "throughput": 656.0, "total_tokens": 54468704} {"current_steps": 39615, "total_steps": 40000, "loss": 0.5456, "lr": 1.1487648066466072e-08, "epoch": 1.26800460917995, "percentage": 99.04, "elapsed_time": "23:03:53", "remaining_time": "0:13:26", "throughput": 656.06, "total_tokens": 54475296} {"current_steps": 39620, "total_steps": 40000, "loss": 0.7969, "lr": 1.1191990176728784e-08, "epoch": 1.2681646501504384, "percentage": 99.05, "elapsed_time": "23:03:55", "remaining_time": "0:13:16", "throughput": 656.13, "total_tokens": 54481920} {"current_steps": 39625, "total_steps": 40000, "loss": 0.591, "lr": 1.0900185875215018e-08, "epoch": 1.268324691120927, "percentage": 99.06, "elapsed_time": "23:03:57", "remaining_time": "0:13:05", "throughput": 656.2, "total_tokens": 54488688} {"current_steps": 39630, "total_steps": 40000, "loss": 0.4885, "lr": 1.0612235206924891e-08, "epoch": 1.2684847320914154, "percentage": 99.08, "elapsed_time": "23:03:58", "remaining_time": "0:12:55", "throughput": 656.26, "total_tokens": 54495296} {"current_steps": 39635, "total_steps": 40000, "loss": 0.7683, "lr": 1.0328138216264549e-08, "epoch": 1.268644773061904, "percentage": 99.09, "elapsed_time": "23:04:00", "remaining_time": "0:12:44", "throughput": 656.33, "total_tokens": 54502112} {"current_steps": 39640, "total_steps": 40000, "loss": 0.7869, "lr": 1.004789494704339e-08, "epoch": 1.2688048140323924, "percentage": 99.1, "elapsed_time": "23:04:02", "remaining_time": "0:12:34", "throughput": 656.4, "total_tokens": 54508928} {"current_steps": 39645, "total_steps": 40000, "loss": 0.7266, "lr": 9.771505442482397e-09, "epoch": 1.2689648550028807, "percentage": 99.11, "elapsed_time": "23:04:04", "remaining_time": "0:12:23", "throughput": 656.47, "total_tokens": 54515536} {"current_steps": 39650, "total_steps": 40000, "loss": 0.6952, "lr": 9.498969745200259e-09, "epoch": 1.2691248959733692, "percentage": 99.12, "elapsed_time": "23:04:05", "remaining_time": "0:12:13", "throughput": 656.54, "total_tokens": 54522912} {"current_steps": 39655, "total_steps": 40000, "loss": 0.5949, "lr": 9.230287897230017e-09, "epoch": 1.2692849369438577, "percentage": 99.14, "elapsed_time": "23:04:07", "remaining_time": "0:12:02", "throughput": 656.61, "total_tokens": 54529600} {"current_steps": 39660, "total_steps": 40000, "loss": 0.9598, "lr": 8.965459940002419e-09, "epoch": 1.269444977914346, "percentage": 99.15, "elapsed_time": "23:04:09", "remaining_time": "0:11:51", "throughput": 656.67, "total_tokens": 54536256} {"current_steps": 39665, "total_steps": 40000, "loss": 0.5591, "lr": 8.704485914357019e-09, "epoch": 1.2696050188848345, "percentage": 99.16, "elapsed_time": "23:04:10", "remaining_time": "0:11:41", "throughput": 656.74, "total_tokens": 54543056} {"current_steps": 39670, "total_steps": 40000, "loss": 0.5668, "lr": 8.447365860539402e-09, "epoch": 1.269765059855323, "percentage": 99.17, "elapsed_time": "23:04:12", "remaining_time": "0:11:30", "throughput": 656.81, "total_tokens": 54550016} {"current_steps": 39675, "total_steps": 40000, "loss": 0.8078, "lr": 8.194099818201184e-09, "epoch": 1.2699251008258114, "percentage": 99.19, "elapsed_time": "23:04:14", "remaining_time": "0:11:20", "throughput": 656.88, "total_tokens": 54556960} {"current_steps": 39680, "total_steps": 40000, "loss": 0.9862, "lr": 7.944687826400011e-09, "epoch": 1.2700851417963, "percentage": 99.2, "elapsed_time": "23:04:16", "remaining_time": "0:11:09", "throughput": 656.95, "total_tokens": 54563760} {"current_steps": 39685, "total_steps": 40000, "loss": 0.5643, "lr": 7.699129923599557e-09, "epoch": 1.2702451827667882, "percentage": 99.21, "elapsed_time": "23:04:17", "remaining_time": "0:10:59", "throughput": 657.02, "total_tokens": 54570768} {"current_steps": 39690, "total_steps": 40000, "loss": 0.7322, "lr": 7.457426147663982e-09, "epoch": 1.2704052237372767, "percentage": 99.22, "elapsed_time": "23:04:19", "remaining_time": "0:10:48", "throughput": 657.09, "total_tokens": 54577712} {"current_steps": 39695, "total_steps": 40000, "loss": 0.7412, "lr": 7.219576535871797e-09, "epoch": 1.2705652647077652, "percentage": 99.24, "elapsed_time": "23:04:21", "remaining_time": "0:10:38", "throughput": 657.15, "total_tokens": 54584176} {"current_steps": 39700, "total_steps": 40000, "loss": 0.5746, "lr": 6.985581124896445e-09, "epoch": 1.2707253056782537, "percentage": 99.25, "elapsed_time": "23:04:23", "remaining_time": "0:10:27", "throughput": 657.22, "total_tokens": 54590512} {"current_steps": 39705, "total_steps": 40000, "loss": 0.7619, "lr": 6.755439950828501e-09, "epoch": 1.270885346648742, "percentage": 99.26, "elapsed_time": "23:04:24", "remaining_time": "0:10:17", "throughput": 657.29, "total_tokens": 54597568} {"current_steps": 39710, "total_steps": 40000, "loss": 0.8584, "lr": 6.5291530491562444e-09, "epoch": 1.2710453876192305, "percentage": 99.28, "elapsed_time": "23:04:26", "remaining_time": "0:10:06", "throughput": 657.36, "total_tokens": 54604624} {"current_steps": 39715, "total_steps": 40000, "loss": 0.6779, "lr": 6.3067204547739845e-09, "epoch": 1.271205428589719, "percentage": 99.29, "elapsed_time": "23:04:28", "remaining_time": "0:09:56", "throughput": 657.42, "total_tokens": 54611008} {"current_steps": 39720, "total_steps": 40000, "loss": 0.7762, "lr": 6.088142201987612e-09, "epoch": 1.2713654695602075, "percentage": 99.3, "elapsed_time": "23:04:30", "remaining_time": "0:09:45", "throughput": 657.49, "total_tokens": 54618160} {"current_steps": 39725, "total_steps": 40000, "loss": 0.6598, "lr": 5.873418324503499e-09, "epoch": 1.271525510530696, "percentage": 99.31, "elapsed_time": "23:04:31", "remaining_time": "0:09:35", "throughput": 657.56, "total_tokens": 54624560} {"current_steps": 39730, "total_steps": 40000, "loss": 0.5963, "lr": 5.6625488554340465e-09, "epoch": 1.2716855515011842, "percentage": 99.33, "elapsed_time": "23:04:33", "remaining_time": "0:09:24", "throughput": 657.62, "total_tokens": 54630960} {"current_steps": 39735, "total_steps": 40000, "loss": 0.5467, "lr": 5.455533827297688e-09, "epoch": 1.2718455924716727, "percentage": 99.34, "elapsed_time": "23:04:35", "remaining_time": "0:09:14", "throughput": 657.69, "total_tokens": 54637952} {"current_steps": 39740, "total_steps": 40000, "loss": 0.9625, "lr": 5.252373272018885e-09, "epoch": 1.2720056334421612, "percentage": 99.35, "elapsed_time": "23:04:37", "remaining_time": "0:09:03", "throughput": 657.76, "total_tokens": 54644960} {"current_steps": 39745, "total_steps": 40000, "loss": 0.6029, "lr": 5.053067220925356e-09, "epoch": 1.2721656744126497, "percentage": 99.36, "elapsed_time": "23:04:38", "remaining_time": "0:08:53", "throughput": 657.83, "total_tokens": 54651872} {"current_steps": 39750, "total_steps": 40000, "loss": 0.597, "lr": 4.857615704759177e-09, "epoch": 1.272325715383138, "percentage": 99.38, "elapsed_time": "23:04:40", "remaining_time": "0:08:42", "throughput": 657.9, "total_tokens": 54658704} {"current_steps": 39755, "total_steps": 40000, "loss": 0.7238, "lr": 4.666018753654577e-09, "epoch": 1.2724857563536265, "percentage": 99.39, "elapsed_time": "23:04:42", "remaining_time": "0:08:32", "throughput": 657.97, "total_tokens": 54665632} {"current_steps": 39760, "total_steps": 40000, "loss": 0.6896, "lr": 4.478276397162917e-09, "epoch": 1.272645797324115, "percentage": 99.4, "elapsed_time": "23:04:43", "remaining_time": "0:08:21", "throughput": 658.04, "total_tokens": 54672432} {"current_steps": 39765, "total_steps": 40000, "loss": 0.8182, "lr": 4.294388664233262e-09, "epoch": 1.2728058382946035, "percentage": 99.41, "elapsed_time": "23:04:45", "remaining_time": "0:08:11", "throughput": 658.11, "total_tokens": 54679136} {"current_steps": 39770, "total_steps": 40000, "loss": 0.6374, "lr": 4.114355583223484e-09, "epoch": 1.272965879265092, "percentage": 99.42, "elapsed_time": "23:04:47", "remaining_time": "0:08:00", "throughput": 658.17, "total_tokens": 54685456} {"current_steps": 39775, "total_steps": 40000, "loss": 0.7978, "lr": 3.9381771818974845e-09, "epoch": 1.2731259202355802, "percentage": 99.44, "elapsed_time": "23:04:49", "remaining_time": "0:07:50", "throughput": 658.23, "total_tokens": 54691936} {"current_steps": 39780, "total_steps": 40000, "loss": 1.0088, "lr": 3.765853487427973e-09, "epoch": 1.2732859612060687, "percentage": 99.45, "elapsed_time": "23:04:50", "remaining_time": "0:07:39", "throughput": 658.3, "total_tokens": 54698944} {"current_steps": 39785, "total_steps": 40000, "loss": 0.5449, "lr": 3.5973845263825857e-09, "epoch": 1.2734460021765572, "percentage": 99.46, "elapsed_time": "23:04:52", "remaining_time": "0:07:29", "throughput": 658.38, "total_tokens": 54706176} {"current_steps": 39790, "total_steps": 40000, "loss": 0.6171, "lr": 3.4327703247488684e-09, "epoch": 1.2736060431470455, "percentage": 99.48, "elapsed_time": "23:04:54", "remaining_time": "0:07:18", "throughput": 658.45, "total_tokens": 54713360} {"current_steps": 39795, "total_steps": 40000, "loss": 0.748, "lr": 3.2720109079037443e-09, "epoch": 1.273766084117534, "percentage": 99.49, "elapsed_time": "23:04:56", "remaining_time": "0:07:08", "throughput": 658.52, "total_tokens": 54720384} {"current_steps": 39800, "total_steps": 40000, "loss": 0.818, "lr": 3.1151063006468193e-09, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "23:04:57", "remaining_time": "0:06:57", "throughput": 658.59, "total_tokens": 54727600} {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.7300497889518738, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "23:10:46", "remaining_time": "0:06:59", "throughput": 655.84, "total_tokens": 54727600} {"current_steps": 39805, "total_steps": 40000, "loss": 0.7634, "lr": 2.962056527169854e-09, "epoch": 1.274086166058511, "percentage": 99.51, "elapsed_time": "23:10:50", "remaining_time": "0:06:48", "throughput": 655.9, "total_tokens": 54734624} {"current_steps": 39810, "total_steps": 40000, "loss": 0.671, "lr": 2.8128616110761898e-09, "epoch": 1.2742462070289995, "percentage": 99.52, "elapsed_time": "23:10:52", "remaining_time": "0:06:38", "throughput": 655.96, "total_tokens": 54741424} {"current_steps": 39815, "total_steps": 40000, "loss": 0.6885, "lr": 2.6675215753724223e-09, "epoch": 1.274406247999488, "percentage": 99.54, "elapsed_time": "23:10:53", "remaining_time": "0:06:27", "throughput": 656.03, "total_tokens": 54747760} {"current_steps": 39820, "total_steps": 40000, "loss": 0.8227, "lr": 2.5260364424739557e-09, "epoch": 1.2745662889699763, "percentage": 99.55, "elapsed_time": "23:10:55", "remaining_time": "0:06:17", "throughput": 656.1, "total_tokens": 54754880} {"current_steps": 39825, "total_steps": 40000, "loss": 0.7006, "lr": 2.3884062341994475e-09, "epoch": 1.2747263299404648, "percentage": 99.56, "elapsed_time": "23:10:57", "remaining_time": "0:06:06", "throughput": 656.17, "total_tokens": 54761840} {"current_steps": 39830, "total_steps": 40000, "loss": 0.7233, "lr": 2.25463097177081e-09, "epoch": 1.2748863709109532, "percentage": 99.58, "elapsed_time": "23:10:58", "remaining_time": "0:05:56", "throughput": 656.24, "total_tokens": 54768896} {"current_steps": 39835, "total_steps": 40000, "loss": 0.6976, "lr": 2.1247106758215397e-09, "epoch": 1.2750464118814415, "percentage": 99.59, "elapsed_time": "23:11:00", "remaining_time": "0:05:45", "throughput": 656.31, "total_tokens": 54775792} {"current_steps": 39840, "total_steps": 40000, "loss": 0.7648, "lr": 1.998645366382834e-09, "epoch": 1.27520645285193, "percentage": 99.6, "elapsed_time": "23:11:02", "remaining_time": "0:05:35", "throughput": 656.38, "total_tokens": 54783008} {"current_steps": 39845, "total_steps": 40000, "loss": 0.6491, "lr": 1.876435062897475e-09, "epoch": 1.2753664938224185, "percentage": 99.61, "elapsed_time": "23:11:04", "remaining_time": "0:05:24", "throughput": 656.45, "total_tokens": 54790336} {"current_steps": 39850, "total_steps": 40000, "loss": 0.7907, "lr": 1.758079784211497e-09, "epoch": 1.275526534792907, "percentage": 99.62, "elapsed_time": "23:11:05", "remaining_time": "0:05:14", "throughput": 656.52, "total_tokens": 54797264} {"current_steps": 39855, "total_steps": 40000, "loss": 0.6597, "lr": 1.6435795485797434e-09, "epoch": 1.2756865757633955, "percentage": 99.64, "elapsed_time": "23:11:07", "remaining_time": "0:05:03", "throughput": 656.59, "total_tokens": 54803952} {"current_steps": 39860, "total_steps": 40000, "loss": 0.6577, "lr": 1.5329343736547596e-09, "epoch": 1.275846616733884, "percentage": 99.65, "elapsed_time": "23:11:09", "remaining_time": "0:04:53", "throughput": 656.66, "total_tokens": 54810688} {"current_steps": 39865, "total_steps": 40000, "loss": 0.5586, "lr": 1.4261442765006739e-09, "epoch": 1.2760066577043723, "percentage": 99.66, "elapsed_time": "23:11:11", "remaining_time": "0:04:42", "throughput": 656.72, "total_tokens": 54817216} {"current_steps": 39870, "total_steps": 40000, "loss": 0.8212, "lr": 1.3232092735876445e-09, "epoch": 1.2761666986748608, "percentage": 99.67, "elapsed_time": "23:11:12", "remaining_time": "0:04:32", "throughput": 656.79, "total_tokens": 54824416} {"current_steps": 39875, "total_steps": 40000, "loss": 0.6078, "lr": 1.2241293807918607e-09, "epoch": 1.2763267396453493, "percentage": 99.69, "elapsed_time": "23:11:14", "remaining_time": "0:04:21", "throughput": 656.87, "total_tokens": 54831648} {"current_steps": 39880, "total_steps": 40000, "loss": 0.5896, "lr": 1.128904613387216e-09, "epoch": 1.2764867806158375, "percentage": 99.7, "elapsed_time": "23:11:16", "remaining_time": "0:04:11", "throughput": 656.94, "total_tokens": 54839168} {"current_steps": 39885, "total_steps": 40000, "loss": 0.688, "lr": 1.0375349860591853e-09, "epoch": 1.276646821586326, "percentage": 99.71, "elapsed_time": "23:11:18", "remaining_time": "0:04:00", "throughput": 657.01, "total_tokens": 54845904} {"current_steps": 39890, "total_steps": 40000, "loss": 0.7835, "lr": 9.5002051290205e-10, "epoch": 1.2768068625568145, "percentage": 99.72, "elapsed_time": "23:11:19", "remaining_time": "0:03:50", "throughput": 657.08, "total_tokens": 54852784} {"current_steps": 39895, "total_steps": 40000, "loss": 0.6459, "lr": 8.663612074077954e-10, "epoch": 1.276966903527303, "percentage": 99.74, "elapsed_time": "23:11:21", "remaining_time": "0:03:39", "throughput": 657.14, "total_tokens": 54859440} {"current_steps": 39900, "total_steps": 40000, "loss": 0.6671, "lr": 7.865570824799884e-10, "epoch": 1.2771269444977915, "percentage": 99.75, "elapsed_time": "23:11:23", "remaining_time": "0:03:29", "throughput": 657.22, "total_tokens": 54866608} {"current_steps": 39905, "total_steps": 40000, "loss": 0.6432, "lr": 7.106081504254514e-10, "epoch": 1.27728698546828, "percentage": 99.76, "elapsed_time": "23:11:25", "remaining_time": "0:03:18", "throughput": 657.28, "total_tokens": 54873104} {"current_steps": 39910, "total_steps": 40000, "loss": 0.6207, "lr": 6.385144229570372e-10, "epoch": 1.2774470264387683, "percentage": 99.78, "elapsed_time": "23:11:26", "remaining_time": "0:03:08", "throughput": 657.35, "total_tokens": 54879648} {"current_steps": 39915, "total_steps": 40000, "loss": 0.6611, "lr": 5.70275911190854e-10, "epoch": 1.2776070674092568, "percentage": 99.79, "elapsed_time": "23:11:28", "remaining_time": "0:02:57", "throughput": 657.42, "total_tokens": 54886688} {"current_steps": 39920, "total_steps": 40000, "loss": 0.6494, "lr": 5.058926256490403e-10, "epoch": 1.2777671083797453, "percentage": 99.8, "elapsed_time": "23:11:30", "remaining_time": "0:02:47", "throughput": 657.48, "total_tokens": 54893328} {"current_steps": 39925, "total_steps": 40000, "loss": 0.8202, "lr": 4.4536457626254134e-10, "epoch": 1.2779271493502335, "percentage": 99.81, "elapsed_time": "23:11:31", "remaining_time": "0:02:36", "throughput": 657.55, "total_tokens": 54899984} {"current_steps": 39930, "total_steps": 40000, "loss": 0.7961, "lr": 3.88691772365557e-10, "epoch": 1.278087190320722, "percentage": 99.83, "elapsed_time": "23:11:33", "remaining_time": "0:02:26", "throughput": 657.62, "total_tokens": 54906832} {"current_steps": 39935, "total_steps": 40000, "loss": 0.6147, "lr": 3.358742226955425e-10, "epoch": 1.2782472312912105, "percentage": 99.84, "elapsed_time": "23:11:35", "remaining_time": "0:02:15", "throughput": 657.68, "total_tokens": 54913632} {"current_steps": 39940, "total_steps": 40000, "loss": 0.8869, "lr": 2.8691193539875925e-10, "epoch": 1.278407272261699, "percentage": 99.85, "elapsed_time": "23:11:37", "remaining_time": "0:02:05", "throughput": 657.75, "total_tokens": 54920528} {"current_steps": 39945, "total_steps": 40000, "loss": 0.8599, "lr": 2.418049180274995e-10, "epoch": 1.2785673132321875, "percentage": 99.86, "elapsed_time": "23:11:38", "remaining_time": "0:01:54", "throughput": 657.82, "total_tokens": 54927584} {"current_steps": 39950, "total_steps": 40000, "loss": 0.8566, "lr": 2.005531775373104e-10, "epoch": 1.2787273542026758, "percentage": 99.88, "elapsed_time": "23:11:40", "remaining_time": "0:01:44", "throughput": 657.89, "total_tokens": 54934240} {"current_steps": 39955, "total_steps": 40000, "loss": 0.6631, "lr": 1.6315672028699435e-10, "epoch": 1.2788873951731643, "percentage": 99.89, "elapsed_time": "23:11:42", "remaining_time": "0:01:34", "throughput": 657.96, "total_tokens": 54941232} {"current_steps": 39960, "total_steps": 40000, "loss": 0.6343, "lr": 1.2961555204693555e-10, "epoch": 1.2790474361436528, "percentage": 99.9, "elapsed_time": "23:11:44", "remaining_time": "0:01:23", "throughput": 658.02, "total_tokens": 54947808} {"current_steps": 39965, "total_steps": 40000, "loss": 0.6781, "lr": 9.992967798799768e-11, "epoch": 1.2792074771141413, "percentage": 99.91, "elapsed_time": "23:11:45", "remaining_time": "0:01:13", "throughput": 658.09, "total_tokens": 54954704} {"current_steps": 39970, "total_steps": 40000, "loss": 0.7444, "lr": 7.409910268707521e-11, "epoch": 1.2793675180846296, "percentage": 99.92, "elapsed_time": "23:11:47", "remaining_time": "0:01:02", "throughput": 658.16, "total_tokens": 54961680} {"current_steps": 39975, "total_steps": 40000, "loss": 0.6754, "lr": 5.212383012986877e-11, "epoch": 1.279527559055118, "percentage": 99.94, "elapsed_time": "23:11:49", "remaining_time": "0:00:52", "throughput": 658.23, "total_tokens": 54968656} {"current_steps": 39980, "total_steps": 40000, "loss": 0.7706, "lr": 3.400386370533415e-11, "epoch": 1.2796876000256066, "percentage": 99.95, "elapsed_time": "23:11:51", "remaining_time": "0:00:41", "throughput": 658.3, "total_tokens": 54975280} {"current_steps": 39985, "total_steps": 40000, "loss": 0.6272, "lr": 1.9739206205682258e-11, "epoch": 1.279847640996095, "percentage": 99.96, "elapsed_time": "23:11:52", "remaining_time": "0:00:31", "throughput": 658.37, "total_tokens": 54982032} {"current_steps": 39990, "total_steps": 40000, "loss": 0.5685, "lr": 9.329859829154685e-12, "epoch": 1.2800076819665835, "percentage": 99.98, "elapsed_time": "23:11:54", "remaining_time": "0:00:20", "throughput": 658.43, "total_tokens": 54988688} {"current_steps": 39995, "total_steps": 40000, "loss": 0.5521, "lr": 2.7758261855748148e-12, "epoch": 1.2801677229370718, "percentage": 99.99, "elapsed_time": "23:11:56", "remaining_time": "0:00:10", "throughput": 658.5, "total_tokens": 54995344} {"current_steps": 40000, "total_steps": 40000, "loss": 0.6806, "lr": 7.710628524559838e-14, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "23:11:58", "remaining_time": "0:00:00", "throughput": 658.57, "total_tokens": 55002224} {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.7300497889518738, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "23:17:46", "remaining_time": "0:00:00", "throughput": 655.83, "total_tokens": 55002224} {"current_steps": 40000, "total_steps": 40000, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "23:17:47", "remaining_time": "0:00:00", "throughput": 655.82, "total_tokens": 55002224}